Merge pull request #823 from router-for-me/translator

feat(translator): enhance Claude-to-OpenAI conversion with thinking block and tool result handling

.dockerignore

@@ -13,8 +13,6 @@ Dockerfile
 docs/*
 README.md
 README_CN.md
-MANAGEMENT_API.md
-MANAGEMENT_API_CN.md
 LICENSE
 
 # Runtime data folders (should be mounted as volumes)
@@ -25,10 +23,14 @@ config.yaml
 
 # Development/editor
 bin/*
-.claude/*
 .vscode/*
+.claude/*
+.codex/*
 .gemini/*
 .serena/*
 .agent/*
+.agents/*
+.opencode/*
 .bmad/*
 _bmad/*
+_bmad-output/*

.github/ISSUE_TEMPLATE/bug_report.md

@@ -7,6 +7,13 @@ assignees: ''
 
 ---
 
+**Is it a request payload issue?**
+[  ] Yes, this is a request payload issue. I am using a client/cURL to send a request payload, but I received an unexpected error.
+[  ] No, it's another issue.
+
+**If it's a request payload issue, you MUST know**
+Our team doesn't have any GODs or ORACLEs or MIND READERs. Please make sure to attach the request log or curl payload.
+
 **Describe the bug**
 A clear and concise description of what the bug is.
 

.gitignore

@@ -11,11 +11,15 @@ bin/*
 logs/*
 conv/*
 temp/*
+refs/*
+
+# Storage backends
 pgstore/*
 gitstore/*
 objectstore/*
+
+# Static assets
 static/*
-refs/*
 
 # Authentication data
 auths/*
@@ -29,12 +33,17 @@ GEMINI.md
 
 # Tooling metadata
 .vscode/*
+.codex/*
 .claude/*
 .gemini/*
 .serena/*
 .agent/*
+.agents/*
+.agents/*
+.opencode/*
 .bmad/*
 _bmad/*
+_bmad-output/*
 
 # macOS
 .DS_Store

README.md

@@ -10,14 +10,29 @@ So you can use local or multi-account CLI access with OpenAI(include Responses)/
 
 ## Sponsor
 
-[![z.ai](https://assets.router-for.me/english.png)](https://z.ai/subscribe?ic=8JVLJQFSKB)
+[![z.ai](https://assets.router-for.me/english-4.7.png)](https://z.ai/subscribe?ic=8JVLJQFSKB)
 
 This project is sponsored by Z.ai, supporting us with their GLM CODING PLAN.
 
-GLM CODING PLAN is a subscription service designed for AI coding, starting at just $3/month. It provides access to their flagship GLM-4.6 model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
+GLM CODING PLAN is a subscription service designed for AI coding, starting at just $3/month. It provides access to their flagship GLM-4.7 model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
 
 Get 10% OFF GLM CODING PLAN：https://z.ai/subscribe?ic=8JVLJQFSKB
 
+---
+
+<table>
+<tbody>
+<tr>
+<td width="180"><a href="https://www.packyapi.com/register?aff=cliproxyapi"><img src="./assets/packycode.png" alt="PackyCode" width="150"></a></td>
+<td>Thanks to PackyCode for sponsoring this project! PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. PackyCode provides special discounts for our software users: register using <a href="https://www.packyapi.com/register?aff=cliproxyapi">this link</a> and enter the "cliproxyapi" promo code during recharge to get 10% off.</td>
+</tr>
+<tr>
+<td width="180"><a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa"><img src="./assets/cubence.png" alt="Cubence" width="150"></a></td>
+<td>Thanks to Cubence for sponsoring this project! Cubence is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. Cubence provides special discounts for our software users: register using <a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa">this link</a> and enter the "CLIPROXYAPI" promo code during recharge to get 10% off.</td>
+</tr>
+</tbody>
+</table>
+
 ## Overview
 
 - OpenAI/Gemini/Claude compatible API endpoints for CLI models
@@ -99,6 +114,10 @@ CLI wrapper for instant switching between multiple Claude accounts and alternati
 
 Native macOS GUI for managing CLIProxyAPI: configure providers, model mappings, and endpoints via OAuth - no API keys needed.
 
+### [Quotio](https://github.com/nguyenphutrong/quotio)
+
+Native macOS menu bar app that unifies Claude, Gemini, OpenAI, Qwen, and Antigravity subscriptions with real-time quota tracking and smart auto-failover for AI coding tools like Claude Code, OpenCode, and Droid - no API keys needed.
+
 > [!NOTE]  
 > If you developed a project based on CLIProxyAPI, please open a PR to add it to this list.
 

README_CN.md

@@ -10,14 +10,30 @@
 
 ## 赞助商
 
-[![bigmodel.cn](https://assets.router-for.me/chinese.png)](https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII)
+[![bigmodel.cn](https://assets.router-for.me/chinese-4.7.png)](https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII)
 
 本项目由 Z智谱 提供赞助, 他们通过 GLM CODING PLAN 对本项目提供技术支持。
 
-GLM CODING PLAN 是专为AI编码打造的订阅套餐，每月最低仅需20元，即可在十余款主流AI编码工具如 Claude Code、Cline、Roo Code 中畅享智谱旗舰模型GLM-4.6，为开发者提供顶尖的编码体验。
+GLM CODING PLAN 是专为AI编码打造的订阅套餐，每月最低仅需20元，即可在十余款主流AI编码工具如 Claude Code、Cline、Roo Code 中畅享智谱旗舰模型GLM-4.7，为开发者提供顶尖的编码体验。
 
 智谱AI为本软件提供了特别优惠，使用以下链接购买可以享受九折优惠：https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII
 
+---
+
+<table>
+<tbody>
+<tr>
+<td width="180"><a href="https://www.packyapi.com/register?aff=cliproxyapi"><img src="./assets/packycode.png" alt="PackyCode" width="150"></a></td>
+<td>感谢 PackyCode 对本项目的赞助！PackyCode 是一家可靠高效的 API 中转服务商，提供 Claude Code、Codex、Gemini 等多种服务的中转。PackyCode 为本软件用户提供了特别优惠：使用<a href="https://www.packyapi.com/register?aff=cliproxyapi">此链接</a>注册，并在充值时输入 "cliproxyapi" 优惠码即可享受九折优惠。</td>
+</tr>
+<tr>
+<td width="180"><a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa"><img src="./assets/cubence.png" alt="Cubence" width="150"></a></td>
+<td>感谢 Cubence 对本项目的赞助！Cubence 是一家可靠高效的 API 中转服务商，提供 Claude Code、Codex、Gemini 等多种服务的中转。Cubence 为本软件用户提供了特别优惠：使用<a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa">此链接</a>注册，并在充值时输入 "CLIPROXYAPI" 优惠码即可享受九折优惠。</td>
+</tr>
+</tbody>
+</table>
+
+
 ## 功能特性
 
 - 为 CLI 模型提供 OpenAI/Gemini/Claude/Codex 兼容的 API 端点
@@ -97,6 +113,10 @@ CLI 封装器，用于通过 CLIProxyAPI OAuth 即时切换多个 Claude 账户
 
 基于 macOS 平台的原生 CLIProxyAPI GUI：配置供应商、模型映射以及OAuth端点，无需 API 密钥。
 
+### [Quotio](https://github.com/nguyenphutrong/quotio)
+
+原生 macOS 菜单栏应用，统一管理 Claude、Gemini、OpenAI、Qwen 和 Antigravity 订阅，提供实时配额追踪和智能自动故障转移，支持 Claude Code、OpenCode 和 Droid 等 AI 编程工具，无需 API 密钥。
+
 > [!NOTE]  
 > 如果你开发了基于 CLIProxyAPI 的项目，请提交一个 PR（拉取请求）将其添加到此列表中。
 

cmd/server/main.go

@@ -405,7 +405,7 @@ func main() {
 	usage.SetStatisticsEnabled(cfg.UsageStatisticsEnabled)
 	coreauth.SetQuotaCooldownDisabled(cfg.DisableCooling)
 
-	if err = logging.ConfigureLogOutput(cfg.LoggingToFile); err != nil {
+	if err = logging.ConfigureLogOutput(cfg); err != nil {
 		log.Errorf("failed to configure log output: %v", err)
 		return
 	}

config.example.yaml

@@ -35,13 +35,21 @@ auth-dir: "~/.cli-proxy-api"
 api-keys:
   - "your-api-key-1"
   - "your-api-key-2"
+  - "your-api-key-3"
 
 # Enable debug logging
 debug: false
 
+# When true, disable high-overhead HTTP middleware features to reduce per-request memory usage under high concurrency.
+commercial-mode: false
+
 # When true, write application logs to rotating files instead of stdout
 logging-to-file: false
 
+# Maximum total size (MB) of log files under the logs directory. When exceeded, the oldest log
+# files are deleted until within the limit. Set to 0 to disable.
+logs-max-total-size-mb: 0
+
 # When false, disable in-memory usage statistics aggregation
 usage-statistics-enabled: false
 
@@ -62,9 +70,18 @@ quota-exceeded:
   switch-project: true # Whether to automatically switch to another project when a quota is exceeded
   switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded
 
+# Routing strategy for selecting credentials when multiple match.
+routing:
+  strategy: "round-robin" # round-robin (default), fill-first
+
 # When true, enable authentication for the WebSocket API (/v1/ws).
 ws-auth: false
 
+# Streaming behavior (SSE keep-alives + safe bootstrap retries).
+# streaming:
+#   keepalive-seconds: 15   # Default: 0 (disabled). <= 0 disables keep-alives.
+#   bootstrap-retries: 1    # Default: 0 (disabled). Retries before first byte is sent.
+
 # Gemini API keys
 # gemini-api-key:
 #   - api-key: "AIzaSy...01"
@@ -73,6 +90,9 @@ ws-auth: false
 #     headers:
 #       X-Custom-Header: "custom-value"
 #     proxy-url: "socks5://proxy.example.com:1080"
+#     models:
+#       - name: "gemini-2.5-flash" # upstream model name
+#         alias: "gemini-flash"    # client alias mapped to the upstream model
 #     excluded-models:
 #       - "gemini-2.5-pro"     # exclude specific models from this provider (exact match)
 #       - "gemini-2.5-*"       # wildcard matching prefix (e.g. gemini-2.5-flash, gemini-2.5-pro)
@@ -88,6 +108,9 @@ ws-auth: false
 #     headers:
 #       X-Custom-Header: "custom-value"
 #     proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
+#     models:
+#       - name: "gpt-5-codex"   # upstream model name
+#         alias: "codex-latest" # client alias mapped to the upstream model
 #     excluded-models:
 #       - "gpt-5.1"         # exclude specific models (exact match)
 #       - "gpt-5-*"         # wildcard matching prefix (e.g. gpt-5-medium, gpt-5-codex)
@@ -105,7 +128,7 @@ ws-auth: false
 #     proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
 #     models:
 #       - name: "claude-3-5-sonnet-20241022" # upstream model name
-#         alias: "claude-sonnet-latest" # client alias mapped to the upstream model
+#         alias: "claude-sonnet-latest"      # client alias mapped to the upstream model
 #     excluded-models:
 #       - "claude-opus-4-5-20251101" # exclude specific models (exact match)
 #       - "claude-3-*"               # wildcard matching prefix (e.g. claude-3-7-sonnet-20250219)
@@ -136,9 +159,9 @@ ws-auth: false
 #     headers:
 #       X-Custom-Header: "custom-value"
 #     models:                                     # optional: map aliases to upstream model names
-#       - name: "gemini-2.0-flash"                # upstream model name
+#       - name: "gemini-2.5-flash"                # upstream model name
 #         alias: "vertex-flash"                   # client-visible alias
-#       - name: "gemini-1.5-pro"
+#       - name: "gemini-2.5-pro"
 #         alias: "vertex-pro"
 
 # Amp Integration
@@ -147,6 +170,18 @@ ws-auth: false
 #   upstream-url: "https://ampcode.com"
 #   # Optional: Override API key for Amp upstream (otherwise uses env or file)
 #   upstream-api-key: ""
+#   # Per-client upstream API key mapping
+#   # Maps client API keys (from top-level api-keys) to different Amp upstream API keys.
+#   # Useful when different clients need to use different Amp accounts/quotas.
+#   # If a client key isn't mapped, falls back to upstream-api-key (default behavior).
+#   upstream-api-keys:
+#     - upstream-api-key: "amp_key_for_team_a"    # Upstream key to use for these clients
+#       api-keys:                                 # Client keys that use this upstream key
+#         - "your-api-key-1"
+#         - "your-api-key-2"
+#     - upstream-api-key: "amp_key_for_team_b"
+#       api-keys:
+#         - "your-api-key-3"
 #   # Restrict Amp management routes (/api/auth, /api/user, etc.) to localhost only (default: false)
 #   restrict-management-to-localhost: false
 #   # Force model mappings to run before checking local API keys (default: false)
@@ -156,12 +191,42 @@ ws-auth: false
 #   # Useful when Amp CLI requests models you don't have access to (e.g., Claude Opus 4.5)
 #   # but you have a similar model available (e.g., Claude Sonnet 4).
 #   model-mappings:
-#     - from: "claude-opus-4.5"       # Model requested by Amp CLI
-#       to: "claude-sonnet-4"         # Route to this available model instead
-#     - from: "gpt-5"
-#       to: "gemini-2.5-pro"
-#     - from: "claude-3-opus-20240229"
-#       to: "claude-3-5-sonnet-20241022"
+#     - from: "claude-opus-4-5-20251101"          # Model requested by Amp CLI
+#       to: "gemini-claude-opus-4-5-thinking"     # Route to this available model instead
+#     - from: "claude-sonnet-4-5-20250929"
+#       to: "gemini-claude-sonnet-4-5-thinking"
+#     - from: "claude-haiku-4-5-20251001"
+#       to: "gemini-2.5-flash"
+
+# Global OAuth model name mappings (per channel)
+# These mappings rename model IDs for both model listing and request routing.
+# Supported channels: gemini-cli, vertex, aistudio, antigravity, claude, codex, qwen, iflow.
+# NOTE: Mappings do not apply to gemini-api-key, codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, or ampcode.
+# oauth-model-mappings:
+#   gemini-cli:
+#     - name: "gemini-2.5-pro"          # original model name under this channel
+#       alias: "g2.5p"                  # client-visible alias
+#   vertex:
+#     - name: "gemini-2.5-pro"
+#       alias: "g2.5p"
+#   aistudio:
+#     - name: "gemini-2.5-pro"
+#       alias: "g2.5p"
+#   antigravity:
+#     - name: "gemini-3-pro-preview"
+#       alias: "g3p"
+#   claude:
+#     - name: "claude-sonnet-4-5-20250929"
+#       alias: "cs4.5"
+#   codex:
+#     - name: "gpt-5"
+#       alias: "g5"
+#   qwen:
+#     - name: "qwen3-coder-plus"
+#       alias: "qwen-plus"
+#   iflow:
+#     - name: "glm-4.7"
+#       alias: "glm-god"
 
 # OAuth provider excluded models
 # oauth-excluded-models:

internal/api/handlers/management/api_tools.go

@@ -0,0 +1,538 @@
+package management
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"net/url"
+	"strings"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/runtime/geminicli"
+	coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/net/proxy"
+	"golang.org/x/oauth2"
+	"golang.org/x/oauth2/google"
+)
+
+const defaultAPICallTimeout = 60 * time.Second
+
+const (
+	geminiOAuthClientID     = "681255809395-oo8ft2oprdrnp9e3aqf6av3hmdib135j.apps.googleusercontent.com"
+	geminiOAuthClientSecret = "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"
+)
+
+var geminiOAuthScopes = []string{
+	"https://www.googleapis.com/auth/cloud-platform",
+	"https://www.googleapis.com/auth/userinfo.email",
+	"https://www.googleapis.com/auth/userinfo.profile",
+}
+
+type apiCallRequest struct {
+	AuthIndexSnake  *string           `json:"auth_index"`
+	AuthIndexCamel  *string           `json:"authIndex"`
+	AuthIndexPascal *string           `json:"AuthIndex"`
+	Method          string            `json:"method"`
+	URL             string            `json:"url"`
+	Header          map[string]string `json:"header"`
+	Data            string            `json:"data"`
+}
+
+type apiCallResponse struct {
+	StatusCode int                 `json:"status_code"`
+	Header     map[string][]string `json:"header"`
+	Body       string              `json:"body"`
+}
+
+// APICall makes a generic HTTP request on behalf of the management API caller.
+// It is protected by the management middleware.
+//
+// Endpoint:
+//
+//	POST /v0/management/api-call
+//
+// Authentication:
+//
+//	Same as other management APIs (requires a management key and remote-management rules).
+//	You can provide the key via:
+//	- Authorization: Bearer <key>
+//	- X-Management-Key: <key>
+//
+// Request JSON:
+//   - auth_index / authIndex / AuthIndex (optional):
+//     The credential "auth_index" from GET /v0/management/auth-files (or other endpoints returning it).
+//     If omitted or not found, credential-specific proxy/token substitution is skipped.
+//   - method (required): HTTP method, e.g. GET, POST, PUT, PATCH, DELETE.
+//   - url (required): Absolute URL including scheme and host, e.g. "https://api.example.com/v1/ping".
+//   - header (optional): Request headers map.
+//     Supports magic variable "$TOKEN$" which is replaced using the selected credential:
+//     1) metadata.access_token
+//     2) attributes.api_key
+//     3) metadata.token / metadata.id_token / metadata.cookie
+//     Example: {"Authorization":"Bearer $TOKEN$"}.
+//     Note: if you need to override the HTTP Host header, set header["Host"].
+//   - data (optional): Raw request body as string (useful for POST/PUT/PATCH).
+//
+// Proxy selection (highest priority first):
+//  1. Selected credential proxy_url
+//  2. Global config proxy-url
+//  3. Direct connect (environment proxies are not used)
+//
+// Response JSON (returned with HTTP 200 when the APICall itself succeeds):
+//   - status_code: Upstream HTTP status code.
+//   - header: Upstream response headers.
+//   - body: Upstream response body as string.
+//
+// Example:
+//
+//	curl -sS -X POST "http://127.0.0.1:8317/v0/management/api-call" \
+//	  -H "Authorization: Bearer <MANAGEMENT_KEY>" \
+//	  -H "Content-Type: application/json" \
+//	  -d '{"auth_index":"<AUTH_INDEX>","method":"GET","url":"https://api.example.com/v1/ping","header":{"Authorization":"Bearer $TOKEN$"}}'
+//
+//	curl -sS -X POST "http://127.0.0.1:8317/v0/management/api-call" \
+//	  -H "Authorization: Bearer 831227" \
+//	  -H "Content-Type: application/json" \
+//	  -d '{"auth_index":"<AUTH_INDEX>","method":"POST","url":"https://api.example.com/v1/fetchAvailableModels","header":{"Authorization":"Bearer $TOKEN$","Content-Type":"application/json","User-Agent":"cliproxyapi"},"data":"{}"}'
+func (h *Handler) APICall(c *gin.Context) {
+	var body apiCallRequest
+	if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
+		return
+	}
+
+	method := strings.ToUpper(strings.TrimSpace(body.Method))
+	if method == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "missing method"})
+		return
+	}
+
+	urlStr := strings.TrimSpace(body.URL)
+	if urlStr == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "missing url"})
+		return
+	}
+	parsedURL, errParseURL := url.Parse(urlStr)
+	if errParseURL != nil || parsedURL.Scheme == "" || parsedURL.Host == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid url"})
+		return
+	}
+
+	authIndex := firstNonEmptyString(body.AuthIndexSnake, body.AuthIndexCamel, body.AuthIndexPascal)
+	auth := h.authByIndex(authIndex)
+
+	reqHeaders := body.Header
+	if reqHeaders == nil {
+		reqHeaders = map[string]string{}
+	}
+
+	var hostOverride string
+	var token string
+	var tokenResolved bool
+	var tokenErr error
+	for key, value := range reqHeaders {
+		if !strings.Contains(value, "$TOKEN$") {
+			continue
+		}
+		if !tokenResolved {
+			token, tokenErr = h.resolveTokenForAuth(c.Request.Context(), auth)
+			tokenResolved = true
+		}
+		if auth != nil && token == "" {
+			if tokenErr != nil {
+				c.JSON(http.StatusBadRequest, gin.H{"error": "auth token refresh failed"})
+				return
+			}
+			c.JSON(http.StatusBadRequest, gin.H{"error": "auth token not found"})
+			return
+		}
+		if token == "" {
+			continue
+		}
+		reqHeaders[key] = strings.ReplaceAll(value, "$TOKEN$", token)
+	}
+
+	var requestBody io.Reader
+	if body.Data != "" {
+		requestBody = strings.NewReader(body.Data)
+	}
+
+	req, errNewRequest := http.NewRequestWithContext(c.Request.Context(), method, urlStr, requestBody)
+	if errNewRequest != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "failed to build request"})
+		return
+	}
+
+	for key, value := range reqHeaders {
+		if strings.EqualFold(key, "host") {
+			hostOverride = strings.TrimSpace(value)
+			continue
+		}
+		req.Header.Set(key, value)
+	}
+	if hostOverride != "" {
+		req.Host = hostOverride
+	}
+
+	httpClient := &http.Client{
+		Timeout: defaultAPICallTimeout,
+	}
+	httpClient.Transport = h.apiCallTransport(auth)
+
+	resp, errDo := httpClient.Do(req)
+	if errDo != nil {
+		log.WithError(errDo).Debug("management APICall request failed")
+		c.JSON(http.StatusBadGateway, gin.H{"error": "request failed"})
+		return
+	}
+	defer func() {
+		if errClose := resp.Body.Close(); errClose != nil {
+			log.Errorf("response body close error: %v", errClose)
+		}
+	}()
+
+	respBody, errReadAll := io.ReadAll(resp.Body)
+	if errReadAll != nil {
+		c.JSON(http.StatusBadGateway, gin.H{"error": "failed to read response"})
+		return
+	}
+
+	c.JSON(http.StatusOK, apiCallResponse{
+		StatusCode: resp.StatusCode,
+		Header:     resp.Header,
+		Body:       string(respBody),
+	})
+}
+
+func firstNonEmptyString(values ...*string) string {
+	for _, v := range values {
+		if v == nil {
+			continue
+		}
+		if out := strings.TrimSpace(*v); out != "" {
+			return out
+		}
+	}
+	return ""
+}
+
+func tokenValueForAuth(auth *coreauth.Auth) string {
+	if auth == nil {
+		return ""
+	}
+	if v := tokenValueFromMetadata(auth.Metadata); v != "" {
+		return v
+	}
+	if auth.Attributes != nil {
+		if v := strings.TrimSpace(auth.Attributes["api_key"]); v != "" {
+			return v
+		}
+	}
+	if shared := geminicli.ResolveSharedCredential(auth.Runtime); shared != nil {
+		if v := tokenValueFromMetadata(shared.MetadataSnapshot()); v != "" {
+			return v
+		}
+	}
+	return ""
+}
+
+func (h *Handler) resolveTokenForAuth(ctx context.Context, auth *coreauth.Auth) (string, error) {
+	if auth == nil {
+		return "", nil
+	}
+
+	provider := strings.ToLower(strings.TrimSpace(auth.Provider))
+	if provider == "gemini-cli" {
+		token, errToken := h.refreshGeminiOAuthAccessToken(ctx, auth)
+		return token, errToken
+	}
+
+	return tokenValueForAuth(auth), nil
+}
+
+func (h *Handler) refreshGeminiOAuthAccessToken(ctx context.Context, auth *coreauth.Auth) (string, error) {
+	if ctx == nil {
+		ctx = context.Background()
+	}
+	if auth == nil {
+		return "", nil
+	}
+
+	metadata, updater := geminiOAuthMetadata(auth)
+	if len(metadata) == 0 {
+		return "", fmt.Errorf("gemini oauth metadata missing")
+	}
+
+	base := make(map[string]any)
+	if tokenRaw, ok := metadata["token"].(map[string]any); ok && tokenRaw != nil {
+		base = cloneMap(tokenRaw)
+	}
+
+	var token oauth2.Token
+	if len(base) > 0 {
+		if raw, errMarshal := json.Marshal(base); errMarshal == nil {
+			_ = json.Unmarshal(raw, &token)
+		}
+	}
+
+	if token.AccessToken == "" {
+		token.AccessToken = stringValue(metadata, "access_token")
+	}
+	if token.RefreshToken == "" {
+		token.RefreshToken = stringValue(metadata, "refresh_token")
+	}
+	if token.TokenType == "" {
+		token.TokenType = stringValue(metadata, "token_type")
+	}
+	if token.Expiry.IsZero() {
+		if expiry := stringValue(metadata, "expiry"); expiry != "" {
+			if ts, errParseTime := time.Parse(time.RFC3339, expiry); errParseTime == nil {
+				token.Expiry = ts
+			}
+		}
+	}
+
+	conf := &oauth2.Config{
+		ClientID:     geminiOAuthClientID,
+		ClientSecret: geminiOAuthClientSecret,
+		Scopes:       geminiOAuthScopes,
+		Endpoint:     google.Endpoint,
+	}
+
+	ctxToken := ctx
+	httpClient := &http.Client{
+		Timeout:   defaultAPICallTimeout,
+		Transport: h.apiCallTransport(auth),
+	}
+	ctxToken = context.WithValue(ctxToken, oauth2.HTTPClient, httpClient)
+
+	src := conf.TokenSource(ctxToken, &token)
+	currentToken, errToken := src.Token()
+	if errToken != nil {
+		return "", errToken
+	}
+
+	merged := buildOAuthTokenMap(base, currentToken)
+	fields := buildOAuthTokenFields(currentToken, merged)
+	if updater != nil {
+		updater(fields)
+	}
+	return strings.TrimSpace(currentToken.AccessToken), nil
+}
+
+func geminiOAuthMetadata(auth *coreauth.Auth) (map[string]any, func(map[string]any)) {
+	if auth == nil {
+		return nil, nil
+	}
+	if shared := geminicli.ResolveSharedCredential(auth.Runtime); shared != nil {
+		snapshot := shared.MetadataSnapshot()
+		return snapshot, func(fields map[string]any) { shared.MergeMetadata(fields) }
+	}
+	return auth.Metadata, func(fields map[string]any) {
+		if auth.Metadata == nil {
+			auth.Metadata = make(map[string]any)
+		}
+		for k, v := range fields {
+			auth.Metadata[k] = v
+		}
+	}
+}
+
+func stringValue(metadata map[string]any, key string) string {
+	if len(metadata) == 0 || key == "" {
+		return ""
+	}
+	if v, ok := metadata[key].(string); ok {
+		return strings.TrimSpace(v)
+	}
+	return ""
+}
+
+func cloneMap(in map[string]any) map[string]any {
+	if len(in) == 0 {
+		return nil
+	}
+	out := make(map[string]any, len(in))
+	for k, v := range in {
+		out[k] = v
+	}
+	return out
+}
+
+func buildOAuthTokenMap(base map[string]any, tok *oauth2.Token) map[string]any {
+	merged := cloneMap(base)
+	if merged == nil {
+		merged = make(map[string]any)
+	}
+	if tok == nil {
+		return merged
+	}
+	if raw, errMarshal := json.Marshal(tok); errMarshal == nil {
+		var tokenMap map[string]any
+		if errUnmarshal := json.Unmarshal(raw, &tokenMap); errUnmarshal == nil {
+			for k, v := range tokenMap {
+				merged[k] = v
+			}
+		}
+	}
+	return merged
+}
+
+func buildOAuthTokenFields(tok *oauth2.Token, merged map[string]any) map[string]any {
+	fields := make(map[string]any, 5)
+	if tok != nil && tok.AccessToken != "" {
+		fields["access_token"] = tok.AccessToken
+	}
+	if tok != nil && tok.TokenType != "" {
+		fields["token_type"] = tok.TokenType
+	}
+	if tok != nil && tok.RefreshToken != "" {
+		fields["refresh_token"] = tok.RefreshToken
+	}
+	if tok != nil && !tok.Expiry.IsZero() {
+		fields["expiry"] = tok.Expiry.Format(time.RFC3339)
+	}
+	if len(merged) > 0 {
+		fields["token"] = cloneMap(merged)
+	}
+	return fields
+}
+
+func tokenValueFromMetadata(metadata map[string]any) string {
+	if len(metadata) == 0 {
+		return ""
+	}
+	if v, ok := metadata["accessToken"].(string); ok && strings.TrimSpace(v) != "" {
+		return strings.TrimSpace(v)
+	}
+	if v, ok := metadata["access_token"].(string); ok && strings.TrimSpace(v) != "" {
+		return strings.TrimSpace(v)
+	}
+	if tokenRaw, ok := metadata["token"]; ok && tokenRaw != nil {
+		switch typed := tokenRaw.(type) {
+		case string:
+			if v := strings.TrimSpace(typed); v != "" {
+				return v
+			}
+		case map[string]any:
+			if v, ok := typed["access_token"].(string); ok && strings.TrimSpace(v) != "" {
+				return strings.TrimSpace(v)
+			}
+			if v, ok := typed["accessToken"].(string); ok && strings.TrimSpace(v) != "" {
+				return strings.TrimSpace(v)
+			}
+		case map[string]string:
+			if v := strings.TrimSpace(typed["access_token"]); v != "" {
+				return v
+			}
+			if v := strings.TrimSpace(typed["accessToken"]); v != "" {
+				return v
+			}
+		}
+	}
+	if v, ok := metadata["token"].(string); ok && strings.TrimSpace(v) != "" {
+		return strings.TrimSpace(v)
+	}
+	if v, ok := metadata["id_token"].(string); ok && strings.TrimSpace(v) != "" {
+		return strings.TrimSpace(v)
+	}
+	if v, ok := metadata["cookie"].(string); ok && strings.TrimSpace(v) != "" {
+		return strings.TrimSpace(v)
+	}
+	return ""
+}
+
+func (h *Handler) authByIndex(authIndex string) *coreauth.Auth {
+	authIndex = strings.TrimSpace(authIndex)
+	if authIndex == "" || h == nil || h.authManager == nil {
+		return nil
+	}
+	auths := h.authManager.List()
+	for _, auth := range auths {
+		if auth == nil {
+			continue
+		}
+		auth.EnsureIndex()
+		if auth.Index == authIndex {
+			return auth
+		}
+	}
+	return nil
+}
+
+func (h *Handler) apiCallTransport(auth *coreauth.Auth) http.RoundTripper {
+	var proxyCandidates []string
+	if auth != nil {
+		if proxyStr := strings.TrimSpace(auth.ProxyURL); proxyStr != "" {
+			proxyCandidates = append(proxyCandidates, proxyStr)
+		}
+	}
+	if h != nil && h.cfg != nil {
+		if proxyStr := strings.TrimSpace(h.cfg.ProxyURL); proxyStr != "" {
+			proxyCandidates = append(proxyCandidates, proxyStr)
+		}
+	}
+
+	for _, proxyStr := range proxyCandidates {
+		if transport := buildProxyTransport(proxyStr); transport != nil {
+			return transport
+		}
+	}
+
+	transport, ok := http.DefaultTransport.(*http.Transport)
+	if !ok || transport == nil {
+		return &http.Transport{Proxy: nil}
+	}
+	clone := transport.Clone()
+	clone.Proxy = nil
+	return clone
+}
+
+func buildProxyTransport(proxyStr string) *http.Transport {
+	proxyStr = strings.TrimSpace(proxyStr)
+	if proxyStr == "" {
+		return nil
+	}
+
+	proxyURL, errParse := url.Parse(proxyStr)
+	if errParse != nil {
+		log.WithError(errParse).Debug("parse proxy URL failed")
+		return nil
+	}
+	if proxyURL.Scheme == "" || proxyURL.Host == "" {
+		log.Debug("proxy URL missing scheme/host")
+		return nil
+	}
+
+	if proxyURL.Scheme == "socks5" {
+		var proxyAuth *proxy.Auth
+		if proxyURL.User != nil {
+			username := proxyURL.User.Username()
+			password, _ := proxyURL.User.Password()
+			proxyAuth = &proxy.Auth{User: username, Password: password}
+		}
+		dialer, errSOCKS5 := proxy.SOCKS5("tcp", proxyURL.Host, proxyAuth, proxy.Direct)
+		if errSOCKS5 != nil {
+			log.WithError(errSOCKS5).Debug("create SOCKS5 dialer failed")
+			return nil
+		}
+		return &http.Transport{
+			Proxy: nil,
+			DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
+				return dialer.Dial(network, addr)
+			},
+		}
+	}
+
+	if proxyURL.Scheme == "http" || proxyURL.Scheme == "https" {
+		return &http.Transport{Proxy: http.ProxyURL(proxyURL)}
+	}
+
+	log.Debugf("unsupported proxy scheme: %s", proxyURL.Scheme)
+	return nil
+}

internal/api/handlers/management/auth_files.go

@@ -197,6 +197,19 @@ func stopCallbackForwarder(port int) {
 	stopForwarderInstance(port, forwarder)
 }
 
+func stopCallbackForwarderInstance(port int, forwarder *callbackForwarder) {
+	if forwarder == nil {
+		return
+	}
+	callbackForwardersMu.Lock()
+	if current := callbackForwarders[port]; current == forwarder {
+		delete(callbackForwarders, port)
+	}
+	callbackForwardersMu.Unlock()
+
+	stopForwarderInstance(port, forwarder)
+}
+
 func stopForwarderInstance(port int, forwarder *callbackForwarder) {
 	if forwarder == nil || forwarder.server == nil {
 		return
@@ -414,9 +427,46 @@ func (h *Handler) buildAuthFileEntry(auth *coreauth.Auth) gin.H {
 			log.WithError(err).Warnf("failed to stat auth file %s", path)
 		}
 	}
+	if claims := extractCodexIDTokenClaims(auth); claims != nil {
+		entry["id_token"] = claims
+	}
 	return entry
 }
 
+func extractCodexIDTokenClaims(auth *coreauth.Auth) gin.H {
+	if auth == nil || auth.Metadata == nil {
+		return nil
+	}
+	if !strings.EqualFold(strings.TrimSpace(auth.Provider), "codex") {
+		return nil
+	}
+	idTokenRaw, ok := auth.Metadata["id_token"].(string)
+	if !ok {
+		return nil
+	}
+	idToken := strings.TrimSpace(idTokenRaw)
+	if idToken == "" {
+		return nil
+	}
+	claims, err := codex.ParseJWTToken(idToken)
+	if err != nil || claims == nil {
+		return nil
+	}
+
+	result := gin.H{}
+	if v := strings.TrimSpace(claims.CodexAuthInfo.ChatgptAccountID); v != "" {
+		result["chatgpt_account_id"] = v
+	}
+	if v := strings.TrimSpace(claims.CodexAuthInfo.ChatgptPlanType); v != "" {
+		result["plan_type"] = v
+	}
+
+	if len(result) == 0 {
+		return nil
+	}
+	return result
+}
+
 func authEmail(auth *coreauth.Auth) string {
 	if auth == nil {
 		return ""
@@ -785,6 +835,7 @@ func (h *Handler) RequestAnthropicToken(c *gin.Context) {
 	RegisterOAuthSession(state, "anthropic")
 
 	isWebUI := isWebUIRequest(c)
+	var forwarder *callbackForwarder
 	if isWebUI {
 		targetURL, errTarget := h.managementCallbackURL("/anthropic/callback")
 		if errTarget != nil {
@@ -792,7 +843,8 @@ func (h *Handler) RequestAnthropicToken(c *gin.Context) {
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "callback server unavailable"})
 			return
 		}
-		if _, errStart := startCallbackForwarder(anthropicCallbackPort, "anthropic", targetURL); errStart != nil {
+		var errStart error
+		if forwarder, errStart = startCallbackForwarder(anthropicCallbackPort, "anthropic", targetURL); errStart != nil {
 			log.WithError(errStart).Error("failed to start anthropic callback forwarder")
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to start callback server"})
 			return
@@ -801,7 +853,7 @@ func (h *Handler) RequestAnthropicToken(c *gin.Context) {
 
 	go func() {
 		if isWebUI {
-			defer stopCallbackForwarder(anthropicCallbackPort)
+			defer stopCallbackForwarderInstance(anthropicCallbackPort, forwarder)
 		}
 
 		// Helper: wait for callback file
@@ -809,6 +861,9 @@ func (h *Handler) RequestAnthropicToken(c *gin.Context) {
 		waitForFile := func(path string, timeout time.Duration) (map[string]string, error) {
 			deadline := time.Now().Add(timeout)
 			for {
+				if !IsOAuthSessionPending(state, "anthropic") {
+					return nil, errOAuthSessionNotPending
+				}
 				if time.Now().After(deadline) {
 					SetOAuthSessionError(state, "Timeout waiting for OAuth callback")
 					return nil, fmt.Errorf("timeout waiting for OAuth callback")
@@ -828,6 +883,9 @@ func (h *Handler) RequestAnthropicToken(c *gin.Context) {
 		// Wait up to 5 minutes
 		resultMap, errWait := waitForFile(waitFile, 5*time.Minute)
 		if errWait != nil {
+			if errors.Is(errWait, errOAuthSessionNotPending) {
+				return
+			}
 			authErr := claude.NewAuthenticationError(claude.ErrCallbackTimeout, errWait)
 			log.Error(claude.GetUserFriendlyMessage(authErr))
 			return
@@ -933,6 +991,7 @@ func (h *Handler) RequestAnthropicToken(c *gin.Context) {
 		}
 		fmt.Println("You can now use Claude services through this CLI")
 		CompleteOAuthSession(state)
+		CompleteOAuthSessionsByProvider("anthropic")
 	}()
 
 	c.JSON(200, gin.H{"status": "ok", "url": authURL, "state": state})
@@ -968,6 +1027,7 @@ func (h *Handler) RequestGeminiCLIToken(c *gin.Context) {
 	RegisterOAuthSession(state, "gemini")
 
 	isWebUI := isWebUIRequest(c)
+	var forwarder *callbackForwarder
 	if isWebUI {
 		targetURL, errTarget := h.managementCallbackURL("/google/callback")
 		if errTarget != nil {
@@ -975,7 +1035,8 @@ func (h *Handler) RequestGeminiCLIToken(c *gin.Context) {
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "callback server unavailable"})
 			return
 		}
-		if _, errStart := startCallbackForwarder(geminiCallbackPort, "gemini", targetURL); errStart != nil {
+		var errStart error
+		if forwarder, errStart = startCallbackForwarder(geminiCallbackPort, "gemini", targetURL); errStart != nil {
 			log.WithError(errStart).Error("failed to start gemini callback forwarder")
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to start callback server"})
 			return
@@ -984,7 +1045,7 @@ func (h *Handler) RequestGeminiCLIToken(c *gin.Context) {
 
 	go func() {
 		if isWebUI {
-			defer stopCallbackForwarder(geminiCallbackPort)
+			defer stopCallbackForwarderInstance(geminiCallbackPort, forwarder)
 		}
 
 		// Wait for callback file written by server route
@@ -993,6 +1054,9 @@ func (h *Handler) RequestGeminiCLIToken(c *gin.Context) {
 		deadline := time.Now().Add(5 * time.Minute)
 		var authCode string
 		for {
+			if !IsOAuthSessionPending(state, "gemini") {
+				return
+			}
 			if time.Now().After(deadline) {
 				log.Error("oauth flow timed out")
 				SetOAuthSessionError(state, "OAuth flow timed out")
@@ -1093,7 +1157,9 @@ func (h *Handler) RequestGeminiCLIToken(c *gin.Context) {
 
 		// Initialize authenticated HTTP client via GeminiAuth to honor proxy settings
 		gemAuth := geminiAuth.NewGeminiAuth()
-		gemClient, errGetClient := gemAuth.GetAuthenticatedClient(ctx, &ts, h.cfg, true)
+		gemClient, errGetClient := gemAuth.GetAuthenticatedClient(ctx, &ts, h.cfg, &geminiAuth.WebLoginOptions{
+			NoBrowser: true,
+		})
 		if errGetClient != nil {
 			log.Errorf("failed to get authenticated client: %v", errGetClient)
 			SetOAuthSessionError(state, "Failed to get authenticated client")
@@ -1166,6 +1232,7 @@ func (h *Handler) RequestGeminiCLIToken(c *gin.Context) {
 		}
 
 		CompleteOAuthSession(state)
+		CompleteOAuthSessionsByProvider("gemini")
 		fmt.Printf("You can now use Gemini CLI services through this CLI; token saved to %s\n", savedPath)
 	}()
 
@@ -1207,6 +1274,7 @@ func (h *Handler) RequestCodexToken(c *gin.Context) {
 	RegisterOAuthSession(state, "codex")
 
 	isWebUI := isWebUIRequest(c)
+	var forwarder *callbackForwarder
 	if isWebUI {
 		targetURL, errTarget := h.managementCallbackURL("/codex/callback")
 		if errTarget != nil {
@@ -1214,7 +1282,8 @@ func (h *Handler) RequestCodexToken(c *gin.Context) {
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "callback server unavailable"})
 			return
 		}
-		if _, errStart := startCallbackForwarder(codexCallbackPort, "codex", targetURL); errStart != nil {
+		var errStart error
+		if forwarder, errStart = startCallbackForwarder(codexCallbackPort, "codex", targetURL); errStart != nil {
 			log.WithError(errStart).Error("failed to start codex callback forwarder")
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to start callback server"})
 			return
@@ -1223,7 +1292,7 @@ func (h *Handler) RequestCodexToken(c *gin.Context) {
 
 	go func() {
 		if isWebUI {
-			defer stopCallbackForwarder(codexCallbackPort)
+			defer stopCallbackForwarderInstance(codexCallbackPort, forwarder)
 		}
 
 		// Wait for callback file
@@ -1231,6 +1300,9 @@ func (h *Handler) RequestCodexToken(c *gin.Context) {
 		deadline := time.Now().Add(5 * time.Minute)
 		var code string
 		for {
+			if !IsOAuthSessionPending(state, "codex") {
+				return
+			}
 			if time.Now().After(deadline) {
 				authErr := codex.NewAuthenticationError(codex.ErrCallbackTimeout, fmt.Errorf("timeout waiting for OAuth callback"))
 				log.Error(codex.GetUserFriendlyMessage(authErr))
@@ -1346,6 +1418,7 @@ func (h *Handler) RequestCodexToken(c *gin.Context) {
 		}
 		fmt.Println("You can now use Codex services through this CLI")
 		CompleteOAuthSession(state)
+		CompleteOAuthSessionsByProvider("codex")
 	}()
 
 	c.JSON(200, gin.H{"status": "ok", "url": authURL, "state": state})
@@ -1391,6 +1464,7 @@ func (h *Handler) RequestAntigravityToken(c *gin.Context) {
 	RegisterOAuthSession(state, "antigravity")
 
 	isWebUI := isWebUIRequest(c)
+	var forwarder *callbackForwarder
 	if isWebUI {
 		targetURL, errTarget := h.managementCallbackURL("/antigravity/callback")
 		if errTarget != nil {
@@ -1398,7 +1472,8 @@ func (h *Handler) RequestAntigravityToken(c *gin.Context) {
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "callback server unavailable"})
 			return
 		}
-		if _, errStart := startCallbackForwarder(antigravityCallbackPort, "antigravity", targetURL); errStart != nil {
+		var errStart error
+		if forwarder, errStart = startCallbackForwarder(antigravityCallbackPort, "antigravity", targetURL); errStart != nil {
 			log.WithError(errStart).Error("failed to start antigravity callback forwarder")
 			c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to start callback server"})
 			return
@@ -1407,13 +1482,16 @@ func (h *Handler) RequestAntigravityToken(c *gin.Context) {
 
 	go func() {
 		if isWebUI {
-			defer stopCallbackForwarder(antigravityCallbackPort)
+			defer stopCallbackForwarderInstance(antigravityCallbackPort, forwarder)
 		}
 
 		waitFile := filepath.Join(h.cfg.AuthDir, fmt.Sprintf(".oauth-antigravity-%s.oauth", state))
 		deadline := time.Now().Add(5 * time.Minute)
 		var authCode string
 		for {
+			if !IsOAuthSessionPending(state, "antigravity") {
+				return
+			}
 			if time.Now().After(deadline) {
 				log.Error("oauth flow timed out")
 				SetOAuthSessionError(state, "OAuth flow timed out")
@@ -1576,6 +1654,7 @@ func (h *Handler) RequestAntigravityToken(c *gin.Context) {
 		}
 
 		CompleteOAuthSession(state)
+		CompleteOAuthSessionsByProvider("antigravity")
 		fmt.Printf("Authentication successful! Token saved to %s\n", savedPath)
 		if projectID != "" {
 			fmt.Printf("Using GCP project: %s\n", projectID)
@@ -1653,6 +1732,7 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
 	RegisterOAuthSession(state, "iflow")
 
 	isWebUI := isWebUIRequest(c)
+	var forwarder *callbackForwarder
 	if isWebUI {
 		targetURL, errTarget := h.managementCallbackURL("/iflow/callback")
 		if errTarget != nil {
@@ -1660,7 +1740,8 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
 			c.JSON(http.StatusInternalServerError, gin.H{"status": "error", "error": "callback server unavailable"})
 			return
 		}
-		if _, errStart := startCallbackForwarder(iflowauth.CallbackPort, "iflow", targetURL); errStart != nil {
+		var errStart error
+		if forwarder, errStart = startCallbackForwarder(iflowauth.CallbackPort, "iflow", targetURL); errStart != nil {
 			log.WithError(errStart).Error("failed to start iflow callback forwarder")
 			c.JSON(http.StatusInternalServerError, gin.H{"status": "error", "error": "failed to start callback server"})
 			return
@@ -1669,7 +1750,7 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
 
 	go func() {
 		if isWebUI {
-			defer stopCallbackForwarder(iflowauth.CallbackPort)
+			defer stopCallbackForwarderInstance(iflowauth.CallbackPort, forwarder)
 		}
 		fmt.Println("Waiting for authentication...")
 
@@ -1677,6 +1758,9 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
 		deadline := time.Now().Add(5 * time.Minute)
 		var resultMap map[string]string
 		for {
+			if !IsOAuthSessionPending(state, "iflow") {
+				return
+			}
 			if time.Now().After(deadline) {
 				SetOAuthSessionError(state, "Authentication failed")
 				fmt.Println("Authentication failed: timeout waiting for callback")
@@ -1743,6 +1827,7 @@ func (h *Handler) RequestIFlowToken(c *gin.Context) {
 		}
 		fmt.Println("You can now use iFlow services through this CLI")
 		CompleteOAuthSession(state)
+		CompleteOAuthSessionsByProvider("iflow")
 	}()
 
 	c.JSON(http.StatusOK, gin.H{"status": "ok", "url": authURL, "state": state})

internal/api/handlers/management/config_lists.go

@@ -145,71 +145,74 @@ func (h *Handler) PutGeminiKeys(c *gin.Context) {
 	h.persist(c)
 }
 func (h *Handler) PatchGeminiKey(c *gin.Context) {
+	type geminiKeyPatch struct {
+		APIKey         *string            `json:"api-key"`
+		Prefix         *string            `json:"prefix"`
+		BaseURL        *string            `json:"base-url"`
+		ProxyURL       *string            `json:"proxy-url"`
+		Headers        *map[string]string `json:"headers"`
+		ExcludedModels *[]string          `json:"excluded-models"`
+	}
 	var body struct {
-		Index *int              `json:"index"`
-		Match *string           `json:"match"`
-		Value *config.GeminiKey `json:"value"`
+		Index *int            `json:"index"`
+		Match *string         `json:"match"`
+		Value *geminiKeyPatch `json:"value"`
 	}
 	if err := c.ShouldBindJSON(&body); err != nil || body.Value == nil {
 		c.JSON(400, gin.H{"error": "invalid body"})
 		return
 	}
-	value := *body.Value
-	value.APIKey = strings.TrimSpace(value.APIKey)
-	value.BaseURL = strings.TrimSpace(value.BaseURL)
-	value.ProxyURL = strings.TrimSpace(value.ProxyURL)
-	value.ExcludedModels = config.NormalizeExcludedModels(value.ExcludedModels)
-	if value.APIKey == "" {
-		// Treat empty API key as delete.
-		if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.GeminiKey) {
-			h.cfg.GeminiKey = append(h.cfg.GeminiKey[:*body.Index], h.cfg.GeminiKey[*body.Index+1:]...)
-			h.cfg.SanitizeGeminiKeys()
-			h.persist(c)
-			return
-		}
-		if body.Match != nil {
-			match := strings.TrimSpace(*body.Match)
-			if match != "" {
-				out := make([]config.GeminiKey, 0, len(h.cfg.GeminiKey))
-				removed := false
-				for i := range h.cfg.GeminiKey {
-					if !removed && h.cfg.GeminiKey[i].APIKey == match {
-						removed = true
-						continue
-					}
-					out = append(out, h.cfg.GeminiKey[i])
-				}
-				if removed {
-					h.cfg.GeminiKey = out
-					h.cfg.SanitizeGeminiKeys()
-					h.persist(c)
-					return
+	targetIndex := -1
+	if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.GeminiKey) {
+		targetIndex = *body.Index
+	}
+	if targetIndex == -1 && body.Match != nil {
+		match := strings.TrimSpace(*body.Match)
+		if match != "" {
+			for i := range h.cfg.GeminiKey {
+				if h.cfg.GeminiKey[i].APIKey == match {
+					targetIndex = i
+					break
 				}
 			}
 		}
+	}
+	if targetIndex == -1 {
 		c.JSON(404, gin.H{"error": "item not found"})
 		return
 	}
 
-	if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.GeminiKey) {
-		h.cfg.GeminiKey[*body.Index] = value
-		h.cfg.SanitizeGeminiKeys()
-		h.persist(c)
-		return
-	}
-	if body.Match != nil {
-		match := strings.TrimSpace(*body.Match)
-		for i := range h.cfg.GeminiKey {
-			if h.cfg.GeminiKey[i].APIKey == match {
-				h.cfg.GeminiKey[i] = value
-				h.cfg.SanitizeGeminiKeys()
-				h.persist(c)
-				return
-			}
+	entry := h.cfg.GeminiKey[targetIndex]
+	if body.Value.APIKey != nil {
+		trimmed := strings.TrimSpace(*body.Value.APIKey)
+		if trimmed == "" {
+			h.cfg.GeminiKey = append(h.cfg.GeminiKey[:targetIndex], h.cfg.GeminiKey[targetIndex+1:]...)
+			h.cfg.SanitizeGeminiKeys()
+			h.persist(c)
+			return
 		}
+		entry.APIKey = trimmed
 	}
-	c.JSON(404, gin.H{"error": "item not found"})
+	if body.Value.Prefix != nil {
+		entry.Prefix = strings.TrimSpace(*body.Value.Prefix)
+	}
+	if body.Value.BaseURL != nil {
+		entry.BaseURL = strings.TrimSpace(*body.Value.BaseURL)
+	}
+	if body.Value.ProxyURL != nil {
+		entry.ProxyURL = strings.TrimSpace(*body.Value.ProxyURL)
+	}
+	if body.Value.Headers != nil {
+		entry.Headers = config.NormalizeHeaders(*body.Value.Headers)
+	}
+	if body.Value.ExcludedModels != nil {
+		entry.ExcludedModels = config.NormalizeExcludedModels(*body.Value.ExcludedModels)
+	}
+	h.cfg.GeminiKey[targetIndex] = entry
+	h.cfg.SanitizeGeminiKeys()
+	h.persist(c)
 }
+
 func (h *Handler) DeleteGeminiKey(c *gin.Context) {
 	if val := strings.TrimSpace(c.Query("api-key")); val != "" {
 		out := make([]config.GeminiKey, 0, len(h.cfg.GeminiKey))
@@ -268,35 +271,70 @@ func (h *Handler) PutClaudeKeys(c *gin.Context) {
 	h.persist(c)
 }
 func (h *Handler) PatchClaudeKey(c *gin.Context) {
+	type claudeKeyPatch struct {
+		APIKey         *string               `json:"api-key"`
+		Prefix         *string               `json:"prefix"`
+		BaseURL        *string               `json:"base-url"`
+		ProxyURL       *string               `json:"proxy-url"`
+		Models         *[]config.ClaudeModel `json:"models"`
+		Headers        *map[string]string    `json:"headers"`
+		ExcludedModels *[]string             `json:"excluded-models"`
+	}
 	var body struct {
-		Index *int              `json:"index"`
-		Match *string           `json:"match"`
-		Value *config.ClaudeKey `json:"value"`
+		Index *int            `json:"index"`
+		Match *string         `json:"match"`
+		Value *claudeKeyPatch `json:"value"`
 	}
 	if err := c.ShouldBindJSON(&body); err != nil || body.Value == nil {
 		c.JSON(400, gin.H{"error": "invalid body"})
 		return
 	}
-	value := *body.Value
-	normalizeClaudeKey(&value)
+	targetIndex := -1
 	if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.ClaudeKey) {
-		h.cfg.ClaudeKey[*body.Index] = value
-		h.cfg.SanitizeClaudeKeys()
-		h.persist(c)
-		return
+		targetIndex = *body.Index
 	}
-	if body.Match != nil {
+	if targetIndex == -1 && body.Match != nil {
+		match := strings.TrimSpace(*body.Match)
 		for i := range h.cfg.ClaudeKey {
-			if h.cfg.ClaudeKey[i].APIKey == *body.Match {
-				h.cfg.ClaudeKey[i] = value
-				h.cfg.SanitizeClaudeKeys()
-				h.persist(c)
-				return
+			if h.cfg.ClaudeKey[i].APIKey == match {
+				targetIndex = i
+				break
 			}
 		}
 	}
-	c.JSON(404, gin.H{"error": "item not found"})
+	if targetIndex == -1 {
+		c.JSON(404, gin.H{"error": "item not found"})
+		return
+	}
+
+	entry := h.cfg.ClaudeKey[targetIndex]
+	if body.Value.APIKey != nil {
+		entry.APIKey = strings.TrimSpace(*body.Value.APIKey)
+	}
+	if body.Value.Prefix != nil {
+		entry.Prefix = strings.TrimSpace(*body.Value.Prefix)
+	}
+	if body.Value.BaseURL != nil {
+		entry.BaseURL = strings.TrimSpace(*body.Value.BaseURL)
+	}
+	if body.Value.ProxyURL != nil {
+		entry.ProxyURL = strings.TrimSpace(*body.Value.ProxyURL)
+	}
+	if body.Value.Models != nil {
+		entry.Models = append([]config.ClaudeModel(nil), (*body.Value.Models)...)
+	}
+	if body.Value.Headers != nil {
+		entry.Headers = config.NormalizeHeaders(*body.Value.Headers)
+	}
+	if body.Value.ExcludedModels != nil {
+		entry.ExcludedModels = config.NormalizeExcludedModels(*body.Value.ExcludedModels)
+	}
+	normalizeClaudeKey(&entry)
+	h.cfg.ClaudeKey[targetIndex] = entry
+	h.cfg.SanitizeClaudeKeys()
+	h.persist(c)
 }
+
 func (h *Handler) DeleteClaudeKey(c *gin.Context) {
 	if val := c.Query("api-key"); val != "" {
 		out := make([]config.ClaudeKey, 0, len(h.cfg.ClaudeKey))
@@ -356,62 +394,73 @@ func (h *Handler) PutOpenAICompat(c *gin.Context) {
 	h.persist(c)
 }
 func (h *Handler) PatchOpenAICompat(c *gin.Context) {
+	type openAICompatPatch struct {
+		Name          *string                             `json:"name"`
+		Prefix        *string                             `json:"prefix"`
+		BaseURL       *string                             `json:"base-url"`
+		APIKeyEntries *[]config.OpenAICompatibilityAPIKey `json:"api-key-entries"`
+		Models        *[]config.OpenAICompatibilityModel  `json:"models"`
+		Headers       *map[string]string                  `json:"headers"`
+	}
 	var body struct {
-		Name  *string                     `json:"name"`
-		Index *int                        `json:"index"`
-		Value *config.OpenAICompatibility `json:"value"`
+		Name  *string            `json:"name"`
+		Index *int               `json:"index"`
+		Value *openAICompatPatch `json:"value"`
 	}
 	if err := c.ShouldBindJSON(&body); err != nil || body.Value == nil {
 		c.JSON(400, gin.H{"error": "invalid body"})
 		return
 	}
-	normalizeOpenAICompatibilityEntry(body.Value)
-	// If base-url becomes empty, delete the provider instead of updating
-	if strings.TrimSpace(body.Value.BaseURL) == "" {
-		if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.OpenAICompatibility) {
-			h.cfg.OpenAICompatibility = append(h.cfg.OpenAICompatibility[:*body.Index], h.cfg.OpenAICompatibility[*body.Index+1:]...)
+	targetIndex := -1
+	if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.OpenAICompatibility) {
+		targetIndex = *body.Index
+	}
+	if targetIndex == -1 && body.Name != nil {
+		match := strings.TrimSpace(*body.Name)
+		for i := range h.cfg.OpenAICompatibility {
+			if h.cfg.OpenAICompatibility[i].Name == match {
+				targetIndex = i
+				break
+			}
+		}
+	}
+	if targetIndex == -1 {
+		c.JSON(404, gin.H{"error": "item not found"})
+		return
+	}
+
+	entry := h.cfg.OpenAICompatibility[targetIndex]
+	if body.Value.Name != nil {
+		entry.Name = strings.TrimSpace(*body.Value.Name)
+	}
+	if body.Value.Prefix != nil {
+		entry.Prefix = strings.TrimSpace(*body.Value.Prefix)
+	}
+	if body.Value.BaseURL != nil {
+		trimmed := strings.TrimSpace(*body.Value.BaseURL)
+		if trimmed == "" {
+			h.cfg.OpenAICompatibility = append(h.cfg.OpenAICompatibility[:targetIndex], h.cfg.OpenAICompatibility[targetIndex+1:]...)
 			h.cfg.SanitizeOpenAICompatibility()
 			h.persist(c)
 			return
 		}
-		if body.Name != nil {
-			out := make([]config.OpenAICompatibility, 0, len(h.cfg.OpenAICompatibility))
-			removed := false
-			for i := range h.cfg.OpenAICompatibility {
-				if !removed && h.cfg.OpenAICompatibility[i].Name == *body.Name {
-					removed = true
-					continue
-				}
-				out = append(out, h.cfg.OpenAICompatibility[i])
-			}
-			if removed {
-				h.cfg.OpenAICompatibility = out
-				h.cfg.SanitizeOpenAICompatibility()
-				h.persist(c)
-				return
-			}
-		}
-		c.JSON(404, gin.H{"error": "item not found"})
-		return
+		entry.BaseURL = trimmed
 	}
-	if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.OpenAICompatibility) {
-		h.cfg.OpenAICompatibility[*body.Index] = *body.Value
-		h.cfg.SanitizeOpenAICompatibility()
-		h.persist(c)
-		return
+	if body.Value.APIKeyEntries != nil {
+		entry.APIKeyEntries = append([]config.OpenAICompatibilityAPIKey(nil), (*body.Value.APIKeyEntries)...)
 	}
-	if body.Name != nil {
-		for i := range h.cfg.OpenAICompatibility {
-			if h.cfg.OpenAICompatibility[i].Name == *body.Name {
-				h.cfg.OpenAICompatibility[i] = *body.Value
-				h.cfg.SanitizeOpenAICompatibility()
-				h.persist(c)
-				return
-			}
-		}
+	if body.Value.Models != nil {
+		entry.Models = append([]config.OpenAICompatibilityModel(nil), (*body.Value.Models)...)
 	}
-	c.JSON(404, gin.H{"error": "item not found"})
+	if body.Value.Headers != nil {
+		entry.Headers = config.NormalizeHeaders(*body.Value.Headers)
+	}
+	normalizeOpenAICompatibilityEntry(&entry)
+	h.cfg.OpenAICompatibility[targetIndex] = entry
+	h.cfg.SanitizeOpenAICompatibility()
+	h.persist(c)
 }
+
 func (h *Handler) DeleteOpenAICompat(c *gin.Context) {
 	if name := c.Query("name"); name != "" {
 		out := make([]config.OpenAICompatibility, 0, len(h.cfg.OpenAICompatibility))
@@ -548,11 +597,7 @@ func (h *Handler) PutCodexKeys(c *gin.Context) {
 	filtered := make([]config.CodexKey, 0, len(arr))
 	for i := range arr {
 		entry := arr[i]
-		entry.APIKey = strings.TrimSpace(entry.APIKey)
-		entry.BaseURL = strings.TrimSpace(entry.BaseURL)
-		entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
-		entry.Headers = config.NormalizeHeaders(entry.Headers)
-		entry.ExcludedModels = config.NormalizeExcludedModels(entry.ExcludedModels)
+		normalizeCodexKey(&entry)
 		if entry.BaseURL == "" {
 			continue
 		}
@@ -563,66 +608,77 @@ func (h *Handler) PutCodexKeys(c *gin.Context) {
 	h.persist(c)
 }
 func (h *Handler) PatchCodexKey(c *gin.Context) {
+	type codexKeyPatch struct {
+		APIKey         *string              `json:"api-key"`
+		Prefix         *string              `json:"prefix"`
+		BaseURL        *string              `json:"base-url"`
+		ProxyURL       *string              `json:"proxy-url"`
+		Models         *[]config.CodexModel `json:"models"`
+		Headers        *map[string]string   `json:"headers"`
+		ExcludedModels *[]string            `json:"excluded-models"`
+	}
 	var body struct {
-		Index *int             `json:"index"`
-		Match *string          `json:"match"`
-		Value *config.CodexKey `json:"value"`
+		Index *int           `json:"index"`
+		Match *string        `json:"match"`
+		Value *codexKeyPatch `json:"value"`
 	}
 	if err := c.ShouldBindJSON(&body); err != nil || body.Value == nil {
 		c.JSON(400, gin.H{"error": "invalid body"})
 		return
 	}
-	value := *body.Value
-	value.APIKey = strings.TrimSpace(value.APIKey)
-	value.BaseURL = strings.TrimSpace(value.BaseURL)
-	value.ProxyURL = strings.TrimSpace(value.ProxyURL)
-	value.Headers = config.NormalizeHeaders(value.Headers)
-	value.ExcludedModels = config.NormalizeExcludedModels(value.ExcludedModels)
-	// If base-url becomes empty, delete instead of update
-	if value.BaseURL == "" {
-		if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.CodexKey) {
-			h.cfg.CodexKey = append(h.cfg.CodexKey[:*body.Index], h.cfg.CodexKey[*body.Index+1:]...)
-			h.cfg.SanitizeCodexKeys()
-			h.persist(c)
-			return
-		}
-		if body.Match != nil {
-			out := make([]config.CodexKey, 0, len(h.cfg.CodexKey))
-			removed := false
-			for i := range h.cfg.CodexKey {
-				if !removed && h.cfg.CodexKey[i].APIKey == *body.Match {
-					removed = true
-					continue
-				}
-				out = append(out, h.cfg.CodexKey[i])
-			}
-			if removed {
-				h.cfg.CodexKey = out
-				h.cfg.SanitizeCodexKeys()
-				h.persist(c)
-				return
-			}
-		}
-	} else {
-		if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.CodexKey) {
-			h.cfg.CodexKey[*body.Index] = value
-			h.cfg.SanitizeCodexKeys()
-			h.persist(c)
-			return
-		}
-		if body.Match != nil {
-			for i := range h.cfg.CodexKey {
-				if h.cfg.CodexKey[i].APIKey == *body.Match {
-					h.cfg.CodexKey[i] = value
-					h.cfg.SanitizeCodexKeys()
-					h.persist(c)
-					return
-				}
+	targetIndex := -1
+	if body.Index != nil && *body.Index >= 0 && *body.Index < len(h.cfg.CodexKey) {
+		targetIndex = *body.Index
+	}
+	if targetIndex == -1 && body.Match != nil {
+		match := strings.TrimSpace(*body.Match)
+		for i := range h.cfg.CodexKey {
+			if h.cfg.CodexKey[i].APIKey == match {
+				targetIndex = i
+				break
 			}
 		}
 	}
-	c.JSON(404, gin.H{"error": "item not found"})
+	if targetIndex == -1 {
+		c.JSON(404, gin.H{"error": "item not found"})
+		return
+	}
+
+	entry := h.cfg.CodexKey[targetIndex]
+	if body.Value.APIKey != nil {
+		entry.APIKey = strings.TrimSpace(*body.Value.APIKey)
+	}
+	if body.Value.Prefix != nil {
+		entry.Prefix = strings.TrimSpace(*body.Value.Prefix)
+	}
+	if body.Value.BaseURL != nil {
+		trimmed := strings.TrimSpace(*body.Value.BaseURL)
+		if trimmed == "" {
+			h.cfg.CodexKey = append(h.cfg.CodexKey[:targetIndex], h.cfg.CodexKey[targetIndex+1:]...)
+			h.cfg.SanitizeCodexKeys()
+			h.persist(c)
+			return
+		}
+		entry.BaseURL = trimmed
+	}
+	if body.Value.ProxyURL != nil {
+		entry.ProxyURL = strings.TrimSpace(*body.Value.ProxyURL)
+	}
+	if body.Value.Models != nil {
+		entry.Models = append([]config.CodexModel(nil), (*body.Value.Models)...)
+	}
+	if body.Value.Headers != nil {
+		entry.Headers = config.NormalizeHeaders(*body.Value.Headers)
+	}
+	if body.Value.ExcludedModels != nil {
+		entry.ExcludedModels = config.NormalizeExcludedModels(*body.Value.ExcludedModels)
+	}
+	normalizeCodexKey(&entry)
+	h.cfg.CodexKey[targetIndex] = entry
+	h.cfg.SanitizeCodexKeys()
+	h.persist(c)
 }
+
 func (h *Handler) DeleteCodexKey(c *gin.Context) {
 	if val := c.Query("api-key"); val != "" {
 		out := make([]config.CodexKey, 0, len(h.cfg.CodexKey))
@@ -707,6 +763,32 @@ func normalizeClaudeKey(entry *config.ClaudeKey) {
 	entry.Models = normalized
 }
 
+func normalizeCodexKey(entry *config.CodexKey) {
+	if entry == nil {
+		return
+	}
+	entry.APIKey = strings.TrimSpace(entry.APIKey)
+	entry.Prefix = strings.TrimSpace(entry.Prefix)
+	entry.BaseURL = strings.TrimSpace(entry.BaseURL)
+	entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
+	entry.Headers = config.NormalizeHeaders(entry.Headers)
+	entry.ExcludedModels = config.NormalizeExcludedModels(entry.ExcludedModels)
+	if len(entry.Models) == 0 {
+		return
+	}
+	normalized := make([]config.CodexModel, 0, len(entry.Models))
+	for i := range entry.Models {
+		model := entry.Models[i]
+		model.Name = strings.TrimSpace(model.Name)
+		model.Alias = strings.TrimSpace(model.Alias)
+		if model.Name == "" && model.Alias == "" {
+			continue
+		}
+		normalized = append(normalized, model)
+	}
+	entry.Models = normalized
+}
+
 // GetAmpCode returns the complete ampcode configuration.
 func (h *Handler) GetAmpCode(c *gin.Context) {
 	if h == nil || h.cfg == nil {
@@ -858,3 +940,151 @@ func (h *Handler) GetAmpForceModelMappings(c *gin.Context) {
 func (h *Handler) PutAmpForceModelMappings(c *gin.Context) {
 	h.updateBoolField(c, func(v bool) { h.cfg.AmpCode.ForceModelMappings = v })
 }
+
+// GetAmpUpstreamAPIKeys returns the ampcode upstream API keys mapping.
+func (h *Handler) GetAmpUpstreamAPIKeys(c *gin.Context) {
+	if h == nil || h.cfg == nil {
+		c.JSON(200, gin.H{"upstream-api-keys": []config.AmpUpstreamAPIKeyEntry{}})
+		return
+	}
+	c.JSON(200, gin.H{"upstream-api-keys": h.cfg.AmpCode.UpstreamAPIKeys})
+}
+
+// PutAmpUpstreamAPIKeys replaces all ampcode upstream API keys mappings.
+func (h *Handler) PutAmpUpstreamAPIKeys(c *gin.Context) {
+	var body struct {
+		Value []config.AmpUpstreamAPIKeyEntry `json:"value"`
+	}
+	if err := c.ShouldBindJSON(&body); err != nil {
+		c.JSON(400, gin.H{"error": "invalid body"})
+		return
+	}
+	// Normalize entries: trim whitespace, filter empty
+	normalized := normalizeAmpUpstreamAPIKeyEntries(body.Value)
+	h.cfg.AmpCode.UpstreamAPIKeys = normalized
+	h.persist(c)
+}
+
+// PatchAmpUpstreamAPIKeys adds or updates upstream API keys entries.
+// Matching is done by upstream-api-key value.
+func (h *Handler) PatchAmpUpstreamAPIKeys(c *gin.Context) {
+	var body struct {
+		Value []config.AmpUpstreamAPIKeyEntry `json:"value"`
+	}
+	if err := c.ShouldBindJSON(&body); err != nil {
+		c.JSON(400, gin.H{"error": "invalid body"})
+		return
+	}
+
+	existing := make(map[string]int)
+	for i, entry := range h.cfg.AmpCode.UpstreamAPIKeys {
+		existing[strings.TrimSpace(entry.UpstreamAPIKey)] = i
+	}
+
+	for _, newEntry := range body.Value {
+		upstreamKey := strings.TrimSpace(newEntry.UpstreamAPIKey)
+		if upstreamKey == "" {
+			continue
+		}
+		normalizedEntry := config.AmpUpstreamAPIKeyEntry{
+			UpstreamAPIKey: upstreamKey,
+			APIKeys:        normalizeAPIKeysList(newEntry.APIKeys),
+		}
+		if idx, ok := existing[upstreamKey]; ok {
+			h.cfg.AmpCode.UpstreamAPIKeys[idx] = normalizedEntry
+		} else {
+			h.cfg.AmpCode.UpstreamAPIKeys = append(h.cfg.AmpCode.UpstreamAPIKeys, normalizedEntry)
+			existing[upstreamKey] = len(h.cfg.AmpCode.UpstreamAPIKeys) - 1
+		}
+	}
+	h.persist(c)
+}
+
+// DeleteAmpUpstreamAPIKeys removes specified upstream API keys entries.
+// Body must be JSON: {"value": ["<upstream-api-key>", ...]}.
+// If "value" is an empty array, clears all entries.
+// If JSON is invalid or "value" is missing/null, returns 400 and does not persist any change.
+func (h *Handler) DeleteAmpUpstreamAPIKeys(c *gin.Context) {
+	var body struct {
+		Value []string `json:"value"`
+	}
+	if err := c.ShouldBindJSON(&body); err != nil {
+		c.JSON(400, gin.H{"error": "invalid body"})
+		return
+	}
+
+	if body.Value == nil {
+		c.JSON(400, gin.H{"error": "missing value"})
+		return
+	}
+
+	// Empty array means clear all
+	if len(body.Value) == 0 {
+		h.cfg.AmpCode.UpstreamAPIKeys = nil
+		h.persist(c)
+		return
+	}
+
+	toRemove := make(map[string]bool)
+	for _, key := range body.Value {
+		trimmed := strings.TrimSpace(key)
+		if trimmed == "" {
+			continue
+		}
+		toRemove[trimmed] = true
+	}
+	if len(toRemove) == 0 {
+		c.JSON(400, gin.H{"error": "empty value"})
+		return
+	}
+
+	newEntries := make([]config.AmpUpstreamAPIKeyEntry, 0, len(h.cfg.AmpCode.UpstreamAPIKeys))
+	for _, entry := range h.cfg.AmpCode.UpstreamAPIKeys {
+		if !toRemove[strings.TrimSpace(entry.UpstreamAPIKey)] {
+			newEntries = append(newEntries, entry)
+		}
+	}
+	h.cfg.AmpCode.UpstreamAPIKeys = newEntries
+	h.persist(c)
+}
+
+// normalizeAmpUpstreamAPIKeyEntries normalizes a list of upstream API key entries.
+func normalizeAmpUpstreamAPIKeyEntries(entries []config.AmpUpstreamAPIKeyEntry) []config.AmpUpstreamAPIKeyEntry {
+	if len(entries) == 0 {
+		return nil
+	}
+	out := make([]config.AmpUpstreamAPIKeyEntry, 0, len(entries))
+	for _, entry := range entries {
+		upstreamKey := strings.TrimSpace(entry.UpstreamAPIKey)
+		if upstreamKey == "" {
+			continue
+		}
+		apiKeys := normalizeAPIKeysList(entry.APIKeys)
+		out = append(out, config.AmpUpstreamAPIKeyEntry{
+			UpstreamAPIKey: upstreamKey,
+			APIKeys:        apiKeys,
+		})
+	}
+	if len(out) == 0 {
+		return nil
+	}
+	return out
+}
+
+// normalizeAPIKeysList trims and filters empty strings from a list of API keys.
+func normalizeAPIKeysList(keys []string) []string {
+	if len(keys) == 0 {
+		return nil
+	}
+	out := make([]string, 0, len(keys))
+	for _, k := range keys {
+		trimmed := strings.TrimSpace(k)
+		if trimmed != "" {
+			out = append(out, trimmed)
+		}
+	}
+	if len(out) == 0 {
+		return nil
+	}
+	return out
+}

internal/api/handlers/management/handler.go

@@ -59,6 +59,11 @@ func NewHandler(cfg *config.Config, configFilePath string, manager *coreauth.Man
 	}
 }
 
+// NewHandler creates a new management handler instance.
+func NewHandlerWithoutConfigFilePath(cfg *config.Config, manager *coreauth.Manager) *Handler {
+	return NewHandler(cfg, "", manager)
+}
+
 // SetConfig updates the in-memory config reference when the server hot-reloads.
 func (h *Handler) SetConfig(cfg *config.Config) { h.cfg = cfg }
 

internal/api/handlers/management/logs.go

@@ -209,6 +209,94 @@ func (h *Handler) GetRequestErrorLogs(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"files": files})
 }
 
+// GetRequestLogByID finds and downloads a request log file by its request ID.
+// The ID is matched against the suffix of log file names (format: *-{requestID}.log).
+func (h *Handler) GetRequestLogByID(c *gin.Context) {
+	if h == nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "handler unavailable"})
+		return
+	}
+	if h.cfg == nil {
+		c.JSON(http.StatusServiceUnavailable, gin.H{"error": "configuration unavailable"})
+		return
+	}
+
+	dir := h.logDirectory()
+	if strings.TrimSpace(dir) == "" {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "log directory not configured"})
+		return
+	}
+
+	requestID := strings.TrimSpace(c.Param("id"))
+	if requestID == "" {
+		requestID = strings.TrimSpace(c.Query("id"))
+	}
+	if requestID == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "missing request ID"})
+		return
+	}
+	if strings.ContainsAny(requestID, "/\\") {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid request ID"})
+		return
+	}
+
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		if os.IsNotExist(err) {
+			c.JSON(http.StatusNotFound, gin.H{"error": "log directory not found"})
+			return
+		}
+		c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to list log directory: %v", err)})
+		return
+	}
+
+	suffix := "-" + requestID + ".log"
+	var matchedFile string
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		name := entry.Name()
+		if strings.HasSuffix(name, suffix) {
+			matchedFile = name
+			break
+		}
+	}
+
+	if matchedFile == "" {
+		c.JSON(http.StatusNotFound, gin.H{"error": "log file not found for the given request ID"})
+		return
+	}
+
+	dirAbs, errAbs := filepath.Abs(dir)
+	if errAbs != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to resolve log directory: %v", errAbs)})
+		return
+	}
+	fullPath := filepath.Clean(filepath.Join(dirAbs, matchedFile))
+	prefix := dirAbs + string(os.PathSeparator)
+	if !strings.HasPrefix(fullPath, prefix) {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid log file path"})
+		return
+	}
+
+	info, errStat := os.Stat(fullPath)
+	if errStat != nil {
+		if os.IsNotExist(errStat) {
+			c.JSON(http.StatusNotFound, gin.H{"error": "log file not found"})
+			return
+		}
+		c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to read log file: %v", errStat)})
+		return
+	}
+	if info.IsDir() {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid log file"})
+		return
+	}
+
+	c.FileAttachment(fullPath, matchedFile)
+}
+
 // DownloadRequestErrorLog downloads a specific error request log file by name.
 func (h *Handler) DownloadRequestErrorLog(c *gin.Context) {
 	if h == nil {

internal/api/handlers/management/oauth_sessions.go

@@ -111,6 +111,27 @@ func (s *oauthSessionStore) Complete(state string) {
 	delete(s.sessions, state)
 }
 
+func (s *oauthSessionStore) CompleteProvider(provider string) int {
+	provider = strings.ToLower(strings.TrimSpace(provider))
+	if provider == "" {
+		return 0
+	}
+	now := time.Now()
+
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	s.purgeExpiredLocked(now)
+	removed := 0
+	for state, session := range s.sessions {
+		if strings.EqualFold(session.Provider, provider) {
+			delete(s.sessions, state)
+			removed++
+		}
+	}
+	return removed
+}
+
 func (s *oauthSessionStore) Get(state string) (oauthSession, bool) {
 	state = strings.TrimSpace(state)
 	now := time.Now()
@@ -153,6 +174,10 @@ func SetOAuthSessionError(state, message string) { oauthSessions.SetError(state,
 
 func CompleteOAuthSession(state string) { oauthSessions.Complete(state) }
 
+func CompleteOAuthSessionsByProvider(provider string) int {
+	return oauthSessions.CompleteProvider(provider)
+}
+
 func GetOAuthSession(state string) (provider string, status string, ok bool) {
 	session, ok := oauthSessions.Get(state)
 	if !ok {

internal/api/handlers/management/usage.go

@@ -1,12 +1,25 @@
 package management
 
 import (
+	"encoding/json"
 	"net/http"
+	"time"
 
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/usage"
 )
 
+type usageExportPayload struct {
+	Version    int                      `json:"version"`
+	ExportedAt time.Time                `json:"exported_at"`
+	Usage      usage.StatisticsSnapshot `json:"usage"`
+}
+
+type usageImportPayload struct {
+	Version int                      `json:"version"`
+	Usage   usage.StatisticsSnapshot `json:"usage"`
+}
+
 // GetUsageStatistics returns the in-memory request statistics snapshot.
 func (h *Handler) GetUsageStatistics(c *gin.Context) {
 	var snapshot usage.StatisticsSnapshot
@@ -18,3 +31,49 @@ func (h *Handler) GetUsageStatistics(c *gin.Context) {
 		"failed_requests": snapshot.FailureCount,
 	})
 }
+
+// ExportUsageStatistics returns a complete usage snapshot for backup/migration.
+func (h *Handler) ExportUsageStatistics(c *gin.Context) {
+	var snapshot usage.StatisticsSnapshot
+	if h != nil && h.usageStats != nil {
+		snapshot = h.usageStats.Snapshot()
+	}
+	c.JSON(http.StatusOK, usageExportPayload{
+		Version:    1,
+		ExportedAt: time.Now().UTC(),
+		Usage:      snapshot,
+	})
+}
+
+// ImportUsageStatistics merges a previously exported usage snapshot into memory.
+func (h *Handler) ImportUsageStatistics(c *gin.Context) {
+	if h == nil || h.usageStats == nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "usage statistics unavailable"})
+		return
+	}
+
+	data, err := c.GetRawData()
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "failed to read request body"})
+		return
+	}
+
+	var payload usageImportPayload
+	if err := json.Unmarshal(data, &payload); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "invalid json"})
+		return
+	}
+	if payload.Version != 0 && payload.Version != 1 {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "unsupported version"})
+		return
+	}
+
+	result := h.usageStats.MergeSnapshot(payload.Usage)
+	snapshot := h.usageStats.Snapshot()
+	c.JSON(http.StatusOK, gin.H{
+		"added":           result.Added,
+		"skipped":         result.Skipped,
+		"total_requests":  snapshot.TotalRequests,
+		"failed_requests": snapshot.FailureCount,
+	})
+}

internal/api/middleware/request_logging.go

@@ -98,10 +98,11 @@ func captureRequestInfo(c *gin.Context) (*RequestInfo, error) {
 	}
 
 	return &RequestInfo{
-		URL:     url,
-		Method:  method,
-		Headers: headers,
-		Body:    body,
+		URL:       url,
+		Method:    method,
+		Headers:   headers,
+		Body:      body,
+		RequestID: logging.GetGinRequestID(c),
 	}, nil
 }
 

internal/api/middleware/response_writer.go

@@ -15,10 +15,11 @@ import (
 
 // RequestInfo holds essential details of an incoming HTTP request for logging purposes.
 type RequestInfo struct {
-	URL     string              // URL is the request URL.
-	Method  string              // Method is the HTTP method (e.g., GET, POST).
-	Headers map[string][]string // Headers contains the request headers.
-	Body    []byte              // Body is the raw request body.
+	URL       string              // URL is the request URL.
+	Method    string              // Method is the HTTP method (e.g., GET, POST).
+	Headers   map[string][]string // Headers contains the request headers.
+	Body      []byte              // Body is the raw request body.
+	RequestID string              // RequestID is the unique identifier for the request.
 }
 
 // ResponseWriterWrapper wraps the standard gin.ResponseWriter to intercept and log response data.
@@ -149,6 +150,7 @@ func (w *ResponseWriterWrapper) WriteHeader(statusCode int) {
 			w.requestInfo.Method,
 			w.requestInfo.Headers,
 			w.requestInfo.Body,
+			w.requestInfo.RequestID,
 		)
 		if err == nil {
 			w.streamWriter = streamWriter
@@ -346,7 +348,7 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
 	}
 
 	if loggerWithOptions, ok := w.logger.(interface {
-		LogRequestWithOptions(string, string, map[string][]string, []byte, int, map[string][]string, []byte, []byte, []byte, []*interfaces.ErrorMessage, bool) error
+		LogRequestWithOptions(string, string, map[string][]string, []byte, int, map[string][]string, []byte, []byte, []byte, []*interfaces.ErrorMessage, bool, string) error
 	}); ok {
 		return loggerWithOptions.LogRequestWithOptions(
 			w.requestInfo.URL,
@@ -360,6 +362,7 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
 			apiResponseBody,
 			apiResponseErrors,
 			forceLog,
+			w.requestInfo.RequestID,
 		)
 	}
 
@@ -374,5 +377,6 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
 		apiRequestBody,
 		apiResponseBody,
 		apiResponseErrors,
+		w.requestInfo.RequestID,
 	)
 }

internal/api/modules/amp/amp.go

@@ -227,11 +227,20 @@ func (m *AmpModule) OnConfigUpdated(cfg *config.Config) error {
 			}
 		}
 
-		// Check API key change
+		// Check API key change (both default and per-client mappings)
 		apiKeyChanged := m.hasAPIKeyChanged(oldSettings, &newSettings)
-		if apiKeyChanged {
+		upstreamAPIKeysChanged := m.hasUpstreamAPIKeysChanged(oldSettings, &newSettings)
+		if apiKeyChanged || upstreamAPIKeysChanged {
 			if m.secretSource != nil {
-				if ms, ok := m.secretSource.(*MultiSourceSecret); ok {
+				if ms, ok := m.secretSource.(*MappedSecretSource); ok {
+					if apiKeyChanged {
+						ms.UpdateDefaultExplicitKey(newSettings.UpstreamAPIKey)
+						ms.InvalidateCache()
+					}
+					if upstreamAPIKeysChanged {
+						ms.UpdateMappings(newSettings.UpstreamAPIKeys)
+					}
+				} else if ms, ok := m.secretSource.(*MultiSourceSecret); ok {
 					ms.UpdateExplicitKey(newSettings.UpstreamAPIKey)
 					ms.InvalidateCache()
 				}
@@ -251,10 +260,22 @@ func (m *AmpModule) OnConfigUpdated(cfg *config.Config) error {
 
 func (m *AmpModule) enableUpstreamProxy(upstreamURL string, settings *config.AmpCode) error {
 	if m.secretSource == nil {
-		m.secretSource = NewMultiSourceSecret(settings.UpstreamAPIKey, 0 /* default 5min */)
+		// Create MultiSourceSecret as the default source, then wrap with MappedSecretSource
+		defaultSource := NewMultiSourceSecret(settings.UpstreamAPIKey, 0 /* default 5min */)
+		mappedSource := NewMappedSecretSource(defaultSource)
+		mappedSource.UpdateMappings(settings.UpstreamAPIKeys)
+		m.secretSource = mappedSource
+	} else if ms, ok := m.secretSource.(*MappedSecretSource); ok {
+		ms.UpdateDefaultExplicitKey(settings.UpstreamAPIKey)
+		ms.InvalidateCache()
+		ms.UpdateMappings(settings.UpstreamAPIKeys)
 	} else if ms, ok := m.secretSource.(*MultiSourceSecret); ok {
+		// Legacy path: wrap existing MultiSourceSecret with MappedSecretSource
 		ms.UpdateExplicitKey(settings.UpstreamAPIKey)
 		ms.InvalidateCache()
+		mappedSource := NewMappedSecretSource(ms)
+		mappedSource.UpdateMappings(settings.UpstreamAPIKeys)
+		m.secretSource = mappedSource
 	}
 
 	proxy, err := createReverseProxy(upstreamURL, m.secretSource)
@@ -279,16 +300,23 @@ func (m *AmpModule) hasModelMappingsChanged(old *config.AmpCode, new *config.Amp
 		return true
 	}
 
-	// Build map for efficient comparison
-	oldMap := make(map[string]string, len(old.ModelMappings))
+	// Build map for efficient and robust comparison
+	type mappingInfo struct {
+		to    string
+		regex bool
+	}
+	oldMap := make(map[string]mappingInfo, len(old.ModelMappings))
 	for _, mapping := range old.ModelMappings {
-		oldMap[strings.TrimSpace(mapping.From)] = strings.TrimSpace(mapping.To)
+		oldMap[strings.TrimSpace(mapping.From)] = mappingInfo{
+			to:    strings.TrimSpace(mapping.To),
+			regex: mapping.Regex,
+		}
 	}
 
 	for _, mapping := range new.ModelMappings {
 		from := strings.TrimSpace(mapping.From)
 		to := strings.TrimSpace(mapping.To)
-		if oldTo, exists := oldMap[from]; !exists || oldTo != to {
+		if oldVal, exists := oldMap[from]; !exists || oldVal.to != to || oldVal.regex != mapping.Regex {
 			return true
 		}
 	}
@@ -306,6 +334,66 @@ func (m *AmpModule) hasAPIKeyChanged(old *config.AmpCode, new *config.AmpCode) b
 	return oldKey != newKey
 }
 
+// hasUpstreamAPIKeysChanged compares old and new per-client upstream API key mappings.
+func (m *AmpModule) hasUpstreamAPIKeysChanged(old *config.AmpCode, new *config.AmpCode) bool {
+	if old == nil {
+		return len(new.UpstreamAPIKeys) > 0
+	}
+
+	if len(old.UpstreamAPIKeys) != len(new.UpstreamAPIKeys) {
+		return true
+	}
+
+	// Build map for comparison: upstreamKey -> set of clientKeys
+	type entryInfo struct {
+		upstreamKey string
+		clientKeys  map[string]struct{}
+	}
+	oldEntries := make([]entryInfo, len(old.UpstreamAPIKeys))
+	for i, entry := range old.UpstreamAPIKeys {
+		clientKeys := make(map[string]struct{}, len(entry.APIKeys))
+		for _, k := range entry.APIKeys {
+			trimmed := strings.TrimSpace(k)
+			if trimmed == "" {
+				continue
+			}
+			clientKeys[trimmed] = struct{}{}
+		}
+		oldEntries[i] = entryInfo{
+			upstreamKey: strings.TrimSpace(entry.UpstreamAPIKey),
+			clientKeys:  clientKeys,
+		}
+	}
+
+	for i, newEntry := range new.UpstreamAPIKeys {
+		if i >= len(oldEntries) {
+			return true
+		}
+		oldE := oldEntries[i]
+		if strings.TrimSpace(newEntry.UpstreamAPIKey) != oldE.upstreamKey {
+			return true
+		}
+		newKeys := make(map[string]struct{}, len(newEntry.APIKeys))
+		for _, k := range newEntry.APIKeys {
+			trimmed := strings.TrimSpace(k)
+			if trimmed == "" {
+				continue
+			}
+			newKeys[trimmed] = struct{}{}
+		}
+		if len(newKeys) != len(oldE.clientKeys) {
+			return true
+		}
+		for k := range newKeys {
+			if _, ok := oldE.clientKeys[k]; !ok {
+				return true
+			}
+		}
+	}
+
+	return false
+}
+
 // GetModelMapper returns the model mapper instance (for testing/debugging).
 func (m *AmpModule) GetModelMapper() *DefaultModelMapper {
 	return m.modelMapper

internal/api/modules/amp/amp_test.go

@@ -312,3 +312,41 @@ func TestAmpModule_ProviderAliasesAlwaysRegistered(t *testing.T) {
 		})
 	}
 }
+
+func TestAmpModule_hasUpstreamAPIKeysChanged_DetectsRemovedKeyWithDuplicateInput(t *testing.T) {
+	m := &AmpModule{}
+
+	oldCfg := &config.AmpCode{
+		UpstreamAPIKeys: []config.AmpUpstreamAPIKeyEntry{
+			{UpstreamAPIKey: "u1", APIKeys: []string{"k1", "k2"}},
+		},
+	}
+	newCfg := &config.AmpCode{
+		UpstreamAPIKeys: []config.AmpUpstreamAPIKeyEntry{
+			{UpstreamAPIKey: "u1", APIKeys: []string{"k1", "k1"}},
+		},
+	}
+
+	if !m.hasUpstreamAPIKeysChanged(oldCfg, newCfg) {
+		t.Fatal("expected change to be detected when k2 is removed but new list contains duplicates")
+	}
+}
+
+func TestAmpModule_hasUpstreamAPIKeysChanged_IgnoresEmptyAndWhitespaceKeys(t *testing.T) {
+	m := &AmpModule{}
+
+	oldCfg := &config.AmpCode{
+		UpstreamAPIKeys: []config.AmpUpstreamAPIKeyEntry{
+			{UpstreamAPIKey: "u1", APIKeys: []string{"k1", "k2"}},
+		},
+	}
+	newCfg := &config.AmpCode{
+		UpstreamAPIKeys: []config.AmpUpstreamAPIKeyEntry{
+			{UpstreamAPIKey: "u1", APIKeys: []string{"  k1  ", "", "k2", "   "}},
+		},
+	}
+
+	if m.hasUpstreamAPIKeysChanged(oldCfg, newCfg) {
+		t.Fatal("expected no change when only whitespace/empty entries differ")
+	}
+}

internal/api/modules/amp/fallback_handlers.go

@@ -134,7 +134,43 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 		}
 
 		// Normalize model (handles dynamic thinking suffixes)
-		normalizedModel, _ := util.NormalizeThinkingModel(modelName)
+		normalizedModel, thinkingMetadata := util.NormalizeThinkingModel(modelName)
+		thinkingSuffix := ""
+		if thinkingMetadata != nil && strings.HasPrefix(modelName, normalizedModel) {
+			thinkingSuffix = modelName[len(normalizedModel):]
+		}
+
+		resolveMappedModel := func() (string, []string) {
+			if fh.modelMapper == nil {
+				return "", nil
+			}
+
+			mappedModel := fh.modelMapper.MapModel(modelName)
+			if mappedModel == "" {
+				mappedModel = fh.modelMapper.MapModel(normalizedModel)
+			}
+			mappedModel = strings.TrimSpace(mappedModel)
+			if mappedModel == "" {
+				return "", nil
+			}
+
+			// Preserve dynamic thinking suffix (e.g. "(xhigh)") when mapping applies, unless the target
+			// already specifies its own thinking suffix.
+			if thinkingSuffix != "" {
+				_, mappedThinkingMetadata := util.NormalizeThinkingModel(mappedModel)
+				if mappedThinkingMetadata == nil {
+					mappedModel += thinkingSuffix
+				}
+			}
+
+			mappedBaseModel, _ := util.NormalizeThinkingModel(mappedModel)
+			mappedProviders := util.GetProviderName(mappedBaseModel)
+			if len(mappedProviders) == 0 {
+				return "", nil
+			}
+
+			return mappedModel, mappedProviders
+		}
 
 		// Track resolved model for logging (may change if mapping is applied)
 		resolvedModel := normalizedModel
@@ -147,21 +183,15 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 		if forceMappings {
 			// FORCE MODE: Check model mappings FIRST (takes precedence over local API keys)
 			// This allows users to route Amp requests to their preferred OAuth providers
-			if fh.modelMapper != nil {
-				if mappedModel := fh.modelMapper.MapModel(normalizedModel); mappedModel != "" {
-					// Mapping found - check if we have a provider for the mapped model
-					mappedProviders := util.GetProviderName(mappedModel)
-					if len(mappedProviders) > 0 {
-						// Mapping found and provider available - rewrite the model in request body
-						bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
-						c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
-						// Store mapped model in context for handlers that check it (like gemini bridge)
-						c.Set(MappedModelContextKey, mappedModel)
-						resolvedModel = mappedModel
-						usedMapping = true
-						providers = mappedProviders
-					}
-				}
+			if mappedModel, mappedProviders := resolveMappedModel(); mappedModel != "" {
+				// Mapping found and provider available - rewrite the model in request body
+				bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
+				c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+				// Store mapped model in context for handlers that check it (like gemini bridge)
+				c.Set(MappedModelContextKey, mappedModel)
+				resolvedModel = mappedModel
+				usedMapping = true
+				providers = mappedProviders
 			}
 
 			// If no mapping applied, check for local providers
@@ -174,21 +204,15 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 
 			if len(providers) == 0 {
 				// No providers configured - check if we have a model mapping
-				if fh.modelMapper != nil {
-					if mappedModel := fh.modelMapper.MapModel(normalizedModel); mappedModel != "" {
-						// Mapping found - check if we have a provider for the mapped model
-						mappedProviders := util.GetProviderName(mappedModel)
-						if len(mappedProviders) > 0 {
-							// Mapping found and provider available - rewrite the model in request body
-							bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
-							c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
-							// Store mapped model in context for handlers that check it (like gemini bridge)
-							c.Set(MappedModelContextKey, mappedModel)
-							resolvedModel = mappedModel
-							usedMapping = true
-							providers = mappedProviders
-						}
-					}
+				if mappedModel, mappedProviders := resolveMappedModel(); mappedModel != "" {
+					// Mapping found and provider available - rewrite the model in request body
+					bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
+					c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+					// Store mapped model in context for handlers that check it (like gemini bridge)
+					c.Set(MappedModelContextKey, mappedModel)
+					resolvedModel = mappedModel
+					usedMapping = true
+					providers = mappedProviders
 				}
 			}
 		}
@@ -222,14 +246,14 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 			// Log: Model was mapped to another model
 			log.Debugf("amp model mapping: request %s -> %s", normalizedModel, resolvedModel)
 			logAmpRouting(RouteTypeModelMapping, modelName, resolvedModel, providerName, requestPath)
-			rewriter := NewResponseRewriter(c.Writer, normalizedModel)
+			rewriter := NewResponseRewriter(c.Writer, modelName)
 			c.Writer = rewriter
 			// Filter Anthropic-Beta header only for local handling paths
 			filterAntropicBetaHeader(c)
 			c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
 			handler(c)
 			rewriter.Flush()
-			log.Debugf("amp model mapping: response %s -> %s", resolvedModel, normalizedModel)
+			log.Debugf("amp model mapping: response %s -> %s", resolvedModel, modelName)
 		} else if len(providers) > 0 {
 			// Log: Using local provider (free)
 			logAmpRouting(RouteTypeLocalProvider, modelName, resolvedModel, providerName, requestPath)

internal/api/modules/amp/fallback_handlers_test.go

@@ -0,0 +1,73 @@
+package amp
+
+import (
+	"bytes"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"net/http/httputil"
+	"testing"
+
+	"github.com/gin-gonic/gin"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+)
+
+func TestFallbackHandler_ModelMapping_PreservesThinkingSuffixAndRewritesResponse(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-amp-fallback", "codex", []*registry.ModelInfo{
+		{ID: "test/gpt-5.2", OwnedBy: "openai", Type: "codex"},
+	})
+	defer reg.UnregisterClient("test-client-amp-fallback")
+
+	mapper := NewModelMapper([]config.AmpModelMapping{
+		{From: "gpt-5.2", To: "test/gpt-5.2"},
+	})
+
+	fallback := NewFallbackHandlerWithMapper(func() *httputil.ReverseProxy { return nil }, mapper, nil)
+
+	handler := func(c *gin.Context) {
+		var req struct {
+			Model string `json:"model"`
+		}
+		if err := c.ShouldBindJSON(&req); err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+			return
+		}
+
+		c.JSON(http.StatusOK, gin.H{
+			"model":      req.Model,
+			"seen_model": req.Model,
+		})
+	}
+
+	r := gin.New()
+	r.POST("/chat/completions", fallback.WrapHandler(handler))
+
+	reqBody := []byte(`{"model":"gpt-5.2(xhigh)"}`)
+	req := httptest.NewRequest(http.MethodPost, "/chat/completions", bytes.NewReader(reqBody))
+	req.Header.Set("Content-Type", "application/json")
+	w := httptest.NewRecorder()
+	r.ServeHTTP(w, req)
+
+	if w.Code != http.StatusOK {
+		t.Fatalf("Expected status 200, got %d", w.Code)
+	}
+
+	var resp struct {
+		Model     string `json:"model"`
+		SeenModel string `json:"seen_model"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
+		t.Fatalf("Failed to parse response JSON: %v", err)
+	}
+
+	if resp.Model != "gpt-5.2(xhigh)" {
+		t.Errorf("Expected response model gpt-5.2(xhigh), got %s", resp.Model)
+	}
+	if resp.SeenModel != "test/gpt-5.2(xhigh)" {
+		t.Errorf("Expected handler to see test/gpt-5.2(xhigh), got %s", resp.SeenModel)
+	}
+}

internal/api/modules/amp/model_mapping.go

@@ -3,6 +3,7 @@
 package amp
 
 import (
+	"regexp"
 	"strings"
 	"sync"
 
@@ -26,13 +27,15 @@ type ModelMapper interface {
 // DefaultModelMapper implements ModelMapper with thread-safe mapping storage.
 type DefaultModelMapper struct {
 	mu       sync.RWMutex
-	mappings map[string]string // from -> to (normalized lowercase keys)
+	mappings map[string]string // exact: from -> to (normalized lowercase keys)
+	regexps  []regexMapping    // regex rules evaluated in order
 }
 
 // NewModelMapper creates a new model mapper with the given initial mappings.
 func NewModelMapper(mappings []config.AmpModelMapping) *DefaultModelMapper {
 	m := &DefaultModelMapper{
 		mappings: make(map[string]string),
+		regexps:  nil,
 	}
 	m.UpdateMappings(mappings)
 	return m
@@ -55,11 +58,23 @@ func (m *DefaultModelMapper) MapModel(requestedModel string) string {
 	// Check for direct mapping
 	targetModel, exists := m.mappings[normalizedRequest]
 	if !exists {
-		return ""
+		// Try regex mappings in order
+		base, _ := util.NormalizeThinkingModel(requestedModel)
+		for _, rm := range m.regexps {
+			if rm.re.MatchString(requestedModel) || (base != "" && rm.re.MatchString(base)) {
+				targetModel = rm.to
+				exists = true
+				break
+			}
+		}
+		if !exists {
+			return ""
+		}
 	}
 
 	// Verify target model has available providers
-	providers := util.GetProviderName(targetModel)
+	normalizedTarget, _ := util.NormalizeThinkingModel(targetModel)
+	providers := util.GetProviderName(normalizedTarget)
 	if len(providers) == 0 {
 		log.Debugf("amp model mapping: target model %s has no available providers, skipping mapping", targetModel)
 		return ""
@@ -77,6 +92,7 @@ func (m *DefaultModelMapper) UpdateMappings(mappings []config.AmpModelMapping) {
 
 	// Clear and rebuild mappings
 	m.mappings = make(map[string]string, len(mappings))
+	m.regexps = make([]regexMapping, 0, len(mappings))
 
 	for _, mapping := range mappings {
 		from := strings.TrimSpace(mapping.From)
@@ -87,16 +103,30 @@ func (m *DefaultModelMapper) UpdateMappings(mappings []config.AmpModelMapping) {
 			continue
 		}
 
-		// Store with normalized lowercase key for case-insensitive lookup
-		normalizedFrom := strings.ToLower(from)
-		m.mappings[normalizedFrom] = to
-
-		log.Debugf("amp model mapping registered: %s -> %s", from, to)
+		if mapping.Regex {
+			// Compile case-insensitive regex; wrap with (?i) to match behavior of exact lookups
+			pattern := "(?i)" + from
+			re, err := regexp.Compile(pattern)
+			if err != nil {
+				log.Warnf("amp model mapping: invalid regex %q: %v", from, err)
+				continue
+			}
+			m.regexps = append(m.regexps, regexMapping{re: re, to: to})
+			log.Debugf("amp model regex mapping registered: /%s/ -> %s", from, to)
+		} else {
+			// Store with normalized lowercase key for case-insensitive lookup
+			normalizedFrom := strings.ToLower(from)
+			m.mappings[normalizedFrom] = to
+			log.Debugf("amp model mapping registered: %s -> %s", from, to)
+		}
 	}
 
 	if len(m.mappings) > 0 {
 		log.Infof("amp model mapping: loaded %d mapping(s)", len(m.mappings))
 	}
+	if n := len(m.regexps); n > 0 {
+		log.Infof("amp model mapping: loaded %d regex mapping(s)", n)
+	}
 }
 
 // GetMappings returns a copy of current mappings (for debugging/status).
@@ -110,3 +140,8 @@ func (m *DefaultModelMapper) GetMappings() map[string]string {
 	}
 	return result
 }
+
+type regexMapping struct {
+	re *regexp.Regexp
+	to string
+}

internal/api/modules/amp/model_mapping_test.go

@@ -71,6 +71,25 @@ func TestModelMapper_MapModel_WithProvider(t *testing.T) {
 	}
 }
 
+func TestModelMapper_MapModel_TargetWithThinkingSuffix(t *testing.T) {
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-thinking", "codex", []*registry.ModelInfo{
+		{ID: "gpt-5.2", OwnedBy: "openai", Type: "codex"},
+	})
+	defer reg.UnregisterClient("test-client-thinking")
+
+	mappings := []config.AmpModelMapping{
+		{From: "gpt-5.2-alias", To: "gpt-5.2(xhigh)"},
+	}
+
+	mapper := NewModelMapper(mappings)
+
+	result := mapper.MapModel("gpt-5.2-alias")
+	if result != "gpt-5.2(xhigh)" {
+		t.Errorf("Expected gpt-5.2(xhigh), got %s", result)
+	}
+}
+
 func TestModelMapper_MapModel_CaseInsensitive(t *testing.T) {
 	reg := registry.GetGlobalRegistry()
 	reg.RegisterClient("test-client2", "claude", []*registry.ModelInfo{
@@ -184,3 +203,81 @@ func TestModelMapper_GetMappings_ReturnsCopy(t *testing.T) {
 		t.Error("Original map was modified")
 	}
 }
+
+func TestModelMapper_Regex_MatchBaseWithoutParens(t *testing.T) {
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-regex-1", "gemini", []*registry.ModelInfo{
+		{ID: "gemini-2.5-pro", OwnedBy: "google", Type: "gemini"},
+	})
+	defer reg.UnregisterClient("test-client-regex-1")
+
+	mappings := []config.AmpModelMapping{
+		{From: "^gpt-5$", To: "gemini-2.5-pro", Regex: true},
+	}
+
+	mapper := NewModelMapper(mappings)
+
+	// Incoming model has reasoning suffix but should match base via regex
+	result := mapper.MapModel("gpt-5(high)")
+	if result != "gemini-2.5-pro" {
+		t.Errorf("Expected gemini-2.5-pro, got %s", result)
+	}
+}
+
+func TestModelMapper_Regex_ExactPrecedence(t *testing.T) {
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-regex-2", "claude", []*registry.ModelInfo{
+		{ID: "claude-sonnet-4", OwnedBy: "anthropic", Type: "claude"},
+	})
+	reg.RegisterClient("test-client-regex-3", "gemini", []*registry.ModelInfo{
+		{ID: "gemini-2.5-pro", OwnedBy: "google", Type: "gemini"},
+	})
+	defer reg.UnregisterClient("test-client-regex-2")
+	defer reg.UnregisterClient("test-client-regex-3")
+
+	mappings := []config.AmpModelMapping{
+		{From: "gpt-5", To: "claude-sonnet-4"},                 // exact
+		{From: "^gpt-5.*$", To: "gemini-2.5-pro", Regex: true}, // regex
+	}
+
+	mapper := NewModelMapper(mappings)
+
+	// Exact match should win over regex
+	result := mapper.MapModel("gpt-5")
+	if result != "claude-sonnet-4" {
+		t.Errorf("Expected claude-sonnet-4, got %s", result)
+	}
+}
+
+func TestModelMapper_Regex_InvalidPattern_Skipped(t *testing.T) {
+	// Invalid regex should be skipped and not cause panic
+	mappings := []config.AmpModelMapping{
+		{From: "(", To: "target", Regex: true},
+	}
+
+	mapper := NewModelMapper(mappings)
+
+	result := mapper.MapModel("anything")
+	if result != "" {
+		t.Errorf("Expected empty result due to invalid regex, got %s", result)
+	}
+}
+
+func TestModelMapper_Regex_CaseInsensitive(t *testing.T) {
+	reg := registry.GetGlobalRegistry()
+	reg.RegisterClient("test-client-regex-4", "claude", []*registry.ModelInfo{
+		{ID: "claude-sonnet-4", OwnedBy: "anthropic", Type: "claude"},
+	})
+	defer reg.UnregisterClient("test-client-regex-4")
+
+	mappings := []config.AmpModelMapping{
+		{From: "^CLAUDE-OPUS-.*$", To: "claude-sonnet-4", Regex: true},
+	}
+
+	mapper := NewModelMapper(mappings)
+
+	result := mapper.MapModel("claude-opus-4.5")
+	if result != "claude-sonnet-4" {
+		t.Errorf("Expected claude-sonnet-4, got %s", result)
+	}
+}

internal/api/modules/amp/proxy.go

@@ -15,6 +15,33 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
+func removeQueryValuesMatching(req *http.Request, key string, match string) {
+	if req == nil || req.URL == nil || match == "" {
+		return
+	}
+
+	q := req.URL.Query()
+	values, ok := q[key]
+	if !ok || len(values) == 0 {
+		return
+	}
+
+	kept := make([]string, 0, len(values))
+	for _, v := range values {
+		if v == match {
+			continue
+		}
+		kept = append(kept, v)
+	}
+
+	if len(kept) == 0 {
+		q.Del(key)
+	} else {
+		q[key] = kept
+	}
+	req.URL.RawQuery = q.Encode()
+}
+
 // readCloser wraps a reader and forwards Close to a separate closer.
 // Used to restore peeked bytes while preserving upstream body Close behavior.
 type readCloser struct {
@@ -45,6 +72,14 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
 		// We will set our own Authorization using the configured upstream-api-key
 		req.Header.Del("Authorization")
 		req.Header.Del("X-Api-Key")
+		req.Header.Del("X-Goog-Api-Key")
+
+		// Remove query-based credentials if they match the authenticated client API key.
+		// This prevents leaking client auth material to the Amp upstream while avoiding
+		// breaking unrelated upstream query parameters.
+		clientKey := getClientAPIKeyFromContext(req.Context())
+		removeQueryValuesMatching(req, "key", clientKey)
+		removeQueryValuesMatching(req, "auth_token", clientKey)
 
 		// Preserve correlation headers for debugging
 		if req.Header.Get("X-Request-ID") == "" {

internal/api/modules/amp/proxy_test.go

@@ -3,11 +3,15 @@ package amp
 import (
 	"bytes"
 	"compress/gzip"
+	"context"
 	"fmt"
 	"io"
 	"net/http"
 	"net/http/httptest"
+	"strings"
 	"testing"
+
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 )
 
 // Helper: compress data with gzip
@@ -306,6 +310,159 @@ func TestReverseProxy_EmptySecret(t *testing.T) {
 	}
 }
 
+func TestReverseProxy_StripsClientCredentialsFromHeadersAndQuery(t *testing.T) {
+	type captured struct {
+		headers http.Header
+		query   string
+	}
+	got := make(chan captured, 1)
+	upstream := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		got <- captured{headers: r.Header.Clone(), query: r.URL.RawQuery}
+		w.WriteHeader(200)
+		w.Write([]byte(`ok`))
+	}))
+	defer upstream.Close()
+
+	proxy, err := createReverseProxy(upstream.URL, NewStaticSecretSource("upstream"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		// Simulate clientAPIKeyMiddleware injection (per-request)
+		ctx := context.WithValue(r.Context(), clientAPIKeyContextKey{}, "client-key")
+		proxy.ServeHTTP(w, r.WithContext(ctx))
+	}))
+	defer srv.Close()
+
+	req, err := http.NewRequest(http.MethodGet, srv.URL+"/test?key=client-key&key=keep&auth_token=client-key&foo=bar", nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	req.Header.Set("Authorization", "Bearer client-key")
+	req.Header.Set("X-Api-Key", "client-key")
+	req.Header.Set("X-Goog-Api-Key", "client-key")
+
+	res, err := http.DefaultClient.Do(req)
+	if err != nil {
+		t.Fatal(err)
+	}
+	res.Body.Close()
+
+	c := <-got
+
+	// These are client-provided credentials and must not reach the upstream.
+	if v := c.headers.Get("X-Goog-Api-Key"); v != "" {
+		t.Fatalf("X-Goog-Api-Key should be stripped, got: %q", v)
+	}
+
+	// We inject upstream Authorization/X-Api-Key, so the client auth must not survive.
+	if v := c.headers.Get("Authorization"); v != "Bearer upstream" {
+		t.Fatalf("Authorization should be upstream-injected, got: %q", v)
+	}
+	if v := c.headers.Get("X-Api-Key"); v != "upstream" {
+		t.Fatalf("X-Api-Key should be upstream-injected, got: %q", v)
+	}
+
+	// Query-based credentials should be stripped only when they match the authenticated client key.
+	// Should keep unrelated values and parameters.
+	if strings.Contains(c.query, "auth_token=client-key") || strings.Contains(c.query, "key=client-key") {
+		t.Fatalf("query credentials should be stripped, got raw query: %q", c.query)
+	}
+	if !strings.Contains(c.query, "key=keep") || !strings.Contains(c.query, "foo=bar") {
+		t.Fatalf("expected query to keep non-credential params, got raw query: %q", c.query)
+	}
+}
+
+func TestReverseProxy_InjectsMappedSecret_FromRequestContext(t *testing.T) {
+	gotHeaders := make(chan http.Header, 1)
+	upstream := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotHeaders <- r.Header.Clone()
+		w.WriteHeader(200)
+		w.Write([]byte(`ok`))
+	}))
+	defer upstream.Close()
+
+	defaultSource := NewStaticSecretSource("default")
+	mapped := NewMappedSecretSource(defaultSource)
+	mapped.UpdateMappings([]config.AmpUpstreamAPIKeyEntry{
+		{
+			UpstreamAPIKey: "u1",
+			APIKeys:        []string{"k1"},
+		},
+	})
+
+	proxy, err := createReverseProxy(upstream.URL, mapped)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		// Simulate clientAPIKeyMiddleware injection (per-request)
+		ctx := context.WithValue(r.Context(), clientAPIKeyContextKey{}, "k1")
+		proxy.ServeHTTP(w, r.WithContext(ctx))
+	}))
+	defer srv.Close()
+
+	res, err := http.Get(srv.URL + "/test")
+	if err != nil {
+		t.Fatal(err)
+	}
+	res.Body.Close()
+
+	hdr := <-gotHeaders
+	if hdr.Get("X-Api-Key") != "u1" {
+		t.Fatalf("X-Api-Key missing or wrong, got: %q", hdr.Get("X-Api-Key"))
+	}
+	if hdr.Get("Authorization") != "Bearer u1" {
+		t.Fatalf("Authorization missing or wrong, got: %q", hdr.Get("Authorization"))
+	}
+}
+
+func TestReverseProxy_MappedSecret_FallsBackToDefault(t *testing.T) {
+	gotHeaders := make(chan http.Header, 1)
+	upstream := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		gotHeaders <- r.Header.Clone()
+		w.WriteHeader(200)
+		w.Write([]byte(`ok`))
+	}))
+	defer upstream.Close()
+
+	defaultSource := NewStaticSecretSource("default")
+	mapped := NewMappedSecretSource(defaultSource)
+	mapped.UpdateMappings([]config.AmpUpstreamAPIKeyEntry{
+		{
+			UpstreamAPIKey: "u1",
+			APIKeys:        []string{"k1"},
+		},
+	})
+
+	proxy, err := createReverseProxy(upstream.URL, mapped)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		ctx := context.WithValue(r.Context(), clientAPIKeyContextKey{}, "k2")
+		proxy.ServeHTTP(w, r.WithContext(ctx))
+	}))
+	defer srv.Close()
+
+	res, err := http.Get(srv.URL + "/test")
+	if err != nil {
+		t.Fatal(err)
+	}
+	res.Body.Close()
+
+	hdr := <-gotHeaders
+	if hdr.Get("X-Api-Key") != "default" {
+		t.Fatalf("X-Api-Key fallback missing or wrong, got: %q", hdr.Get("X-Api-Key"))
+	}
+	if hdr.Get("Authorization") != "Bearer default" {
+		t.Fatalf("Authorization fallback missing or wrong, got: %q", hdr.Get("Authorization"))
+	}
+}
+
 func TestReverseProxy_ErrorHandler(t *testing.T) {
 	// Point proxy to a non-routable address to trigger error
 	proxy, err := createReverseProxy("http://127.0.0.1:1", NewStaticSecretSource(""))

internal/api/modules/amp/routes.go

@@ -1,6 +1,7 @@
 package amp
 
 import (
+	"context"
 	"errors"
 	"net"
 	"net/http"
@@ -16,6 +17,37 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
+// clientAPIKeyContextKey is the context key used to pass the client API key
+// from gin.Context to the request context for SecretSource lookup.
+type clientAPIKeyContextKey struct{}
+
+// clientAPIKeyMiddleware injects the authenticated client API key from gin.Context["apiKey"]
+// into the request context so that SecretSource can look it up for per-client upstream routing.
+func clientAPIKeyMiddleware() gin.HandlerFunc {
+	return func(c *gin.Context) {
+		// Extract the client API key from gin context (set by AuthMiddleware)
+		if apiKey, exists := c.Get("apiKey"); exists {
+			if keyStr, ok := apiKey.(string); ok && keyStr != "" {
+				// Inject into request context for SecretSource.Get(ctx) to read
+				ctx := context.WithValue(c.Request.Context(), clientAPIKeyContextKey{}, keyStr)
+				c.Request = c.Request.WithContext(ctx)
+			}
+		}
+		c.Next()
+	}
+}
+
+// getClientAPIKeyFromContext retrieves the client API key from request context.
+// Returns empty string if not present.
+func getClientAPIKeyFromContext(ctx context.Context) string {
+	if val := ctx.Value(clientAPIKeyContextKey{}); val != nil {
+		if keyStr, ok := val.(string); ok {
+			return keyStr
+		}
+	}
+	return ""
+}
+
 // localhostOnlyMiddleware returns a middleware that dynamically checks the module's
 // localhost restriction setting. This allows hot-reload of the restriction without restarting.
 func (m *AmpModule) localhostOnlyMiddleware() gin.HandlerFunc {
@@ -126,9 +158,12 @@ func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *ha
 	var authWithBypass gin.HandlerFunc
 	if auth != nil {
 		ampAPI.Use(auth)
-		authWithBypass = wrapManagementAuth(auth, "/threads", "/auth")
+		authWithBypass = wrapManagementAuth(auth, "/threads", "/auth", "/docs", "/settings")
 	}
 
+	// Inject client API key into request context for per-client upstream routing
+	ampAPI.Use(clientAPIKeyMiddleware())
+
 	// Dynamic proxy handler that uses m.getProxy() for hot-reload support
 	proxyHandler := func(c *gin.Context) {
 		// Swallow ErrAbortHandler panics from ReverseProxy copyResponse to avoid noisy stack traces
@@ -175,7 +210,15 @@ func (m *AmpModule) registerManagementRoutes(engine *gin.Engine, baseHandler *ha
 	if authWithBypass != nil {
 		rootMiddleware = append(rootMiddleware, authWithBypass)
 	}
+	// Add clientAPIKeyMiddleware after auth for per-client upstream routing
+	rootMiddleware = append(rootMiddleware, clientAPIKeyMiddleware())
+	engine.GET("/threads", append(rootMiddleware, proxyHandler)...)
 	engine.GET("/threads/*path", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/docs", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/docs/*path", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/settings", append(rootMiddleware, proxyHandler)...)
+	engine.GET("/settings/*path", append(rootMiddleware, proxyHandler)...)
+
 	engine.GET("/threads.rss", append(rootMiddleware, proxyHandler)...)
 	engine.GET("/news.rss", append(rootMiddleware, proxyHandler)...)
 
@@ -238,6 +281,8 @@ func (m *AmpModule) registerProviderAliases(engine *gin.Engine, baseHandler *han
 	if auth != nil {
 		ampProviders.Use(auth)
 	}
+	// Inject client API key into request context for per-client upstream routing
+	ampProviders.Use(clientAPIKeyMiddleware())
 
 	provider := ampProviders.Group("/:provider")
 

internal/api/modules/amp/secret.go

@@ -9,6 +9,9 @@ import (
 	"strings"
 	"sync"
 	"time"
+
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
+	log "github.com/sirupsen/logrus"
 )
 
 // SecretSource provides Amp API keys with configurable precedence and caching
@@ -164,3 +167,82 @@ func NewStaticSecretSource(key string) *StaticSecretSource {
 func (s *StaticSecretSource) Get(ctx context.Context) (string, error) {
 	return s.key, nil
 }
+
+// MappedSecretSource wraps a default SecretSource and adds per-client API key mapping.
+// When a request context contains a client API key that matches a configured mapping,
+// the corresponding upstream key is returned. Otherwise, falls back to the default source.
+type MappedSecretSource struct {
+	defaultSource SecretSource
+	mu            sync.RWMutex
+	lookup        map[string]string // clientKey -> upstreamKey
+}
+
+// NewMappedSecretSource creates a MappedSecretSource wrapping the given default source.
+func NewMappedSecretSource(defaultSource SecretSource) *MappedSecretSource {
+	return &MappedSecretSource{
+		defaultSource: defaultSource,
+		lookup:        make(map[string]string),
+	}
+}
+
+// Get retrieves the Amp API key, checking per-client mappings first.
+// If the request context contains a client API key that matches a configured mapping,
+// returns the corresponding upstream key. Otherwise, falls back to the default source.
+func (s *MappedSecretSource) Get(ctx context.Context) (string, error) {
+	// Try to get client API key from request context
+	clientKey := getClientAPIKeyFromContext(ctx)
+	if clientKey != "" {
+		s.mu.RLock()
+		if upstreamKey, ok := s.lookup[clientKey]; ok && upstreamKey != "" {
+			s.mu.RUnlock()
+			return upstreamKey, nil
+		}
+		s.mu.RUnlock()
+	}
+
+	// Fall back to default source
+	return s.defaultSource.Get(ctx)
+}
+
+// UpdateMappings rebuilds the client-to-upstream key mapping from configuration entries.
+// If the same client key appears in multiple entries, logs a warning and uses the first one.
+func (s *MappedSecretSource) UpdateMappings(entries []config.AmpUpstreamAPIKeyEntry) {
+	newLookup := make(map[string]string)
+
+	for _, entry := range entries {
+		upstreamKey := strings.TrimSpace(entry.UpstreamAPIKey)
+		if upstreamKey == "" {
+			continue
+		}
+		for _, clientKey := range entry.APIKeys {
+			trimmedKey := strings.TrimSpace(clientKey)
+			if trimmedKey == "" {
+				continue
+			}
+			if _, exists := newLookup[trimmedKey]; exists {
+				// Log warning for duplicate client key, first one wins
+				log.Warnf("amp upstream-api-keys: client API key appears in multiple entries; using first mapping.")
+				continue
+			}
+			newLookup[trimmedKey] = upstreamKey
+		}
+	}
+
+	s.mu.Lock()
+	s.lookup = newLookup
+	s.mu.Unlock()
+}
+
+// UpdateDefaultExplicitKey updates the explicit key on the underlying MultiSourceSecret (if applicable).
+func (s *MappedSecretSource) UpdateDefaultExplicitKey(key string) {
+	if ms, ok := s.defaultSource.(*MultiSourceSecret); ok {
+		ms.UpdateExplicitKey(key)
+	}
+}
+
+// InvalidateCache invalidates cache on the underlying MultiSourceSecret (if applicable).
+func (s *MappedSecretSource) InvalidateCache() {
+	if ms, ok := s.defaultSource.(*MultiSourceSecret); ok {
+		ms.InvalidateCache()
+	}
+}

internal/api/modules/amp/secret_test.go

@@ -8,6 +8,10 @@ import (
 	"sync"
 	"testing"
 	"time"
+
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
+	log "github.com/sirupsen/logrus"
+	"github.com/sirupsen/logrus/hooks/test"
 )
 
 func TestMultiSourceSecret_PrecedenceOrder(t *testing.T) {
@@ -278,3 +282,85 @@ func TestMultiSourceSecret_CacheEmptyResult(t *testing.T) {
 		t.Fatalf("after cache expiry, expected new-value, got %q", got3)
 	}
 }
+
+func TestMappedSecretSource_UsesMappingFromContext(t *testing.T) {
+	defaultSource := NewStaticSecretSource("default")
+	s := NewMappedSecretSource(defaultSource)
+	s.UpdateMappings([]config.AmpUpstreamAPIKeyEntry{
+		{
+			UpstreamAPIKey: "u1",
+			APIKeys:        []string{"k1"},
+		},
+	})
+
+	ctx := context.WithValue(context.Background(), clientAPIKeyContextKey{}, "k1")
+	got, err := s.Get(ctx)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if got != "u1" {
+		t.Fatalf("want u1, got %q", got)
+	}
+
+	ctx = context.WithValue(context.Background(), clientAPIKeyContextKey{}, "k2")
+	got, err = s.Get(ctx)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if got != "default" {
+		t.Fatalf("want default fallback, got %q", got)
+	}
+}
+
+func TestMappedSecretSource_DuplicateClientKey_FirstWins(t *testing.T) {
+	defaultSource := NewStaticSecretSource("default")
+	s := NewMappedSecretSource(defaultSource)
+	s.UpdateMappings([]config.AmpUpstreamAPIKeyEntry{
+		{
+			UpstreamAPIKey: "u1",
+			APIKeys:        []string{"k1"},
+		},
+		{
+			UpstreamAPIKey: "u2",
+			APIKeys:        []string{"k1"},
+		},
+	})
+
+	ctx := context.WithValue(context.Background(), clientAPIKeyContextKey{}, "k1")
+	got, err := s.Get(ctx)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if got != "u1" {
+		t.Fatalf("want u1 (first wins), got %q", got)
+	}
+}
+
+func TestMappedSecretSource_DuplicateClientKey_LogsWarning(t *testing.T) {
+	hook := test.NewLocal(log.StandardLogger())
+	defer hook.Reset()
+
+	defaultSource := NewStaticSecretSource("default")
+	s := NewMappedSecretSource(defaultSource)
+	s.UpdateMappings([]config.AmpUpstreamAPIKeyEntry{
+		{
+			UpstreamAPIKey: "u1",
+			APIKeys:        []string{"k1"},
+		},
+		{
+			UpstreamAPIKey: "u2",
+			APIKeys:        []string{"k1"},
+		},
+	})
+
+	foundWarning := false
+	for _, entry := range hook.AllEntries() {
+		if entry.Level == log.WarnLevel && entry.Message == "amp upstream-api-keys: client API key appears in multiple entries; using first mapping." {
+			foundWarning = true
+			break
+		}
+	}
+	if !foundWarning {
+		t.Fatal("expected warning log for duplicate client key, but none was found")
+	}
+}

internal/api/server.go

@@ -209,13 +209,15 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
 	// Resolve logs directory relative to the configuration file directory.
 	var requestLogger logging.RequestLogger
 	var toggle func(bool)
-	if optionState.requestLoggerFactory != nil {
-		requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
-	}
-	if requestLogger != nil {
-		engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
-		if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
-			toggle = setter.SetEnabled
+	if !cfg.CommercialMode {
+		if optionState.requestLoggerFactory != nil {
+			requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
+		}
+		if requestLogger != nil {
+			engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
+			if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
+				toggle = setter.SetEnabled
+			}
 		}
 	}
 
@@ -474,6 +476,8 @@ func (s *Server) registerManagementRoutes() {
 	mgmt.Use(s.managementAvailabilityMiddleware(), s.mgmt.Middleware())
 	{
 		mgmt.GET("/usage", s.mgmt.GetUsageStatistics)
+		mgmt.GET("/usage/export", s.mgmt.ExportUsageStatistics)
+		mgmt.POST("/usage/import", s.mgmt.ImportUsageStatistics)
 		mgmt.GET("/config", s.mgmt.GetConfig)
 		mgmt.GET("/config.yaml", s.mgmt.GetConfigYAML)
 		mgmt.PUT("/config.yaml", s.mgmt.PutConfigYAML)
@@ -496,6 +500,8 @@ func (s *Server) registerManagementRoutes() {
 		mgmt.PATCH("/proxy-url", s.mgmt.PutProxyURL)
 		mgmt.DELETE("/proxy-url", s.mgmt.DeleteProxyURL)
 
+		mgmt.POST("/api-call", s.mgmt.APICall)
+
 		mgmt.GET("/quota-exceeded/switch-project", s.mgmt.GetSwitchProject)
 		mgmt.PUT("/quota-exceeded/switch-project", s.mgmt.PutSwitchProject)
 		mgmt.PATCH("/quota-exceeded/switch-project", s.mgmt.PutSwitchProject)
@@ -518,6 +524,7 @@ func (s *Server) registerManagementRoutes() {
 		mgmt.DELETE("/logs", s.mgmt.DeleteLogs)
 		mgmt.GET("/request-error-logs", s.mgmt.GetRequestErrorLogs)
 		mgmt.GET("/request-error-logs/:name", s.mgmt.DownloadRequestErrorLog)
+		mgmt.GET("/request-log-by-id/:id", s.mgmt.GetRequestLogByID)
 		mgmt.GET("/request-log", s.mgmt.GetRequestLog)
 		mgmt.PUT("/request-log", s.mgmt.PutRequestLog)
 		mgmt.PATCH("/request-log", s.mgmt.PutRequestLog)
@@ -544,6 +551,10 @@ func (s *Server) registerManagementRoutes() {
 		mgmt.GET("/ampcode/force-model-mappings", s.mgmt.GetAmpForceModelMappings)
 		mgmt.PUT("/ampcode/force-model-mappings", s.mgmt.PutAmpForceModelMappings)
 		mgmt.PATCH("/ampcode/force-model-mappings", s.mgmt.PutAmpForceModelMappings)
+		mgmt.GET("/ampcode/upstream-api-keys", s.mgmt.GetAmpUpstreamAPIKeys)
+		mgmt.PUT("/ampcode/upstream-api-keys", s.mgmt.PutAmpUpstreamAPIKeys)
+		mgmt.PATCH("/ampcode/upstream-api-keys", s.mgmt.PatchAmpUpstreamAPIKeys)
+		mgmt.DELETE("/ampcode/upstream-api-keys", s.mgmt.DeleteAmpUpstreamAPIKeys)
 
 		mgmt.GET("/request-retry", s.mgmt.GetRequestRetry)
 		mgmt.PUT("/request-retry", s.mgmt.PutRequestRetry)
@@ -844,11 +855,20 @@ func (s *Server) UpdateClients(cfg *config.Config) {
 		}
 	}
 
-	if oldCfg != nil && oldCfg.LoggingToFile != cfg.LoggingToFile {
-		if err := logging.ConfigureLogOutput(cfg.LoggingToFile); err != nil {
+	if oldCfg == nil || oldCfg.LoggingToFile != cfg.LoggingToFile || oldCfg.LogsMaxTotalSizeMB != cfg.LogsMaxTotalSizeMB {
+		if err := logging.ConfigureLogOutput(cfg); err != nil {
 			log.Errorf("failed to reconfigure log output: %v", err)
 		} else {
-			log.Debugf("logging_to_file updated from %t to %t", oldCfg.LoggingToFile, cfg.LoggingToFile)
+			if oldCfg == nil {
+				log.Debug("log output configuration refreshed")
+			} else {
+				if oldCfg.LoggingToFile != cfg.LoggingToFile {
+					log.Debugf("logging_to_file updated from %t to %t", oldCfg.LoggingToFile, cfg.LoggingToFile)
+				}
+				if oldCfg.LogsMaxTotalSizeMB != cfg.LogsMaxTotalSizeMB {
+					log.Debugf("logs_max_total_size_mb updated from %d to %d", oldCfg.LogsMaxTotalSizeMB, cfg.LogsMaxTotalSizeMB)
+				}
+			}
 		}
 	}
 

internal/auth/gemini/gemini_auth.go

@@ -18,6 +18,7 @@ import (
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/auth/codex"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/browser"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/misc"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
@@ -46,6 +47,12 @@ var (
 type GeminiAuth struct {
 }
 
+// WebLoginOptions customizes the interactive OAuth flow.
+type WebLoginOptions struct {
+	NoBrowser bool
+	Prompt    func(string) (string, error)
+}
+
 // NewGeminiAuth creates a new instance of GeminiAuth.
 func NewGeminiAuth() *GeminiAuth {
 	return &GeminiAuth{}
@@ -59,12 +66,12 @@ func NewGeminiAuth() *GeminiAuth {
 //   - ctx: The context for the HTTP client
 //   - ts: The Gemini token storage containing authentication tokens
 //   - cfg: The configuration containing proxy settings
-//   - noBrowser: Optional parameter to disable browser opening
+//   - opts: Optional parameters to customize browser and prompt behavior
 //
 // Returns:
 //   - *http.Client: An HTTP client configured with authentication
 //   - error: An error if the client configuration fails, nil otherwise
-func (g *GeminiAuth) GetAuthenticatedClient(ctx context.Context, ts *GeminiTokenStorage, cfg *config.Config, noBrowser ...bool) (*http.Client, error) {
+func (g *GeminiAuth) GetAuthenticatedClient(ctx context.Context, ts *GeminiTokenStorage, cfg *config.Config, opts *WebLoginOptions) (*http.Client, error) {
 	// Configure proxy settings for the HTTP client if a proxy URL is provided.
 	proxyURL, err := url.Parse(cfg.ProxyURL)
 	if err == nil {
@@ -109,7 +116,7 @@ func (g *GeminiAuth) GetAuthenticatedClient(ctx context.Context, ts *GeminiToken
 	// If no token is found in storage, initiate the web-based OAuth flow.
 	if ts.Token == nil {
 		fmt.Printf("Could not load token from file, starting OAuth flow.\n")
-		token, err = g.getTokenFromWeb(ctx, conf, noBrowser...)
+		token, err = g.getTokenFromWeb(ctx, conf, opts)
 		if err != nil {
 			return nil, fmt.Errorf("failed to get token from web: %w", err)
 		}
@@ -205,15 +212,15 @@ func (g *GeminiAuth) createTokenStorage(ctx context.Context, config *oauth2.Conf
 // Parameters:
 //   - ctx: The context for the HTTP client
 //   - config: The OAuth2 configuration
-//   - noBrowser: Optional parameter to disable browser opening
+//   - opts: Optional parameters to customize browser and prompt behavior
 //
 // Returns:
 //   - *oauth2.Token: The OAuth2 token obtained from the authorization flow
 //   - error: An error if the token acquisition fails, nil otherwise
-func (g *GeminiAuth) getTokenFromWeb(ctx context.Context, config *oauth2.Config, noBrowser ...bool) (*oauth2.Token, error) {
+func (g *GeminiAuth) getTokenFromWeb(ctx context.Context, config *oauth2.Config, opts *WebLoginOptions) (*oauth2.Token, error) {
 	// Use a channel to pass the authorization code from the HTTP handler to the main function.
-	codeChan := make(chan string)
-	errChan := make(chan error)
+	codeChan := make(chan string, 1)
+	errChan := make(chan error, 1)
 
 	// Create a new HTTP server with its own multiplexer.
 	mux := http.NewServeMux()
@@ -223,17 +230,26 @@ func (g *GeminiAuth) getTokenFromWeb(ctx context.Context, config *oauth2.Config,
 	mux.HandleFunc("/oauth2callback", func(w http.ResponseWriter, r *http.Request) {
 		if err := r.URL.Query().Get("error"); err != "" {
 			_, _ = fmt.Fprintf(w, "Authentication failed: %s", err)
-			errChan <- fmt.Errorf("authentication failed via callback: %s", err)
+			select {
+			case errChan <- fmt.Errorf("authentication failed via callback: %s", err):
+			default:
+			}
 			return
 		}
 		code := r.URL.Query().Get("code")
 		if code == "" {
 			_, _ = fmt.Fprint(w, "Authentication failed: code not found.")
-			errChan <- fmt.Errorf("code not found in callback")
+			select {
+			case errChan <- fmt.Errorf("code not found in callback"):
+			default:
+			}
 			return
 		}
 		_, _ = fmt.Fprint(w, "<html><body><h1>Authentication successful!</h1><p>You can close this window.</p></body></html>")
-		codeChan <- code
+		select {
+		case codeChan <- code:
+		default:
+		}
 	})
 
 	// Start the server in a goroutine.
@@ -250,7 +266,12 @@ func (g *GeminiAuth) getTokenFromWeb(ctx context.Context, config *oauth2.Config,
 	// Open the authorization URL in the user's browser.
 	authURL := config.AuthCodeURL("state-token", oauth2.AccessTypeOffline, oauth2.SetAuthURLParam("prompt", "consent"))
 
-	if len(noBrowser) == 1 && !noBrowser[0] {
+	noBrowser := false
+	if opts != nil {
+		noBrowser = opts.NoBrowser
+	}
+
+	if !noBrowser {
 		fmt.Println("Opening browser for authentication...")
 
 		// Check if browser is available
@@ -281,13 +302,60 @@ func (g *GeminiAuth) getTokenFromWeb(ctx context.Context, config *oauth2.Config,
 
 	// Wait for the authorization code or an error.
 	var authCode string
-	select {
-	case code := <-codeChan:
-		authCode = code
-	case err := <-errChan:
-		return nil, err
-	case <-time.After(5 * time.Minute): // Timeout
-		return nil, fmt.Errorf("oauth flow timed out")
+	timeoutTimer := time.NewTimer(5 * time.Minute)
+	defer timeoutTimer.Stop()
+
+	var manualPromptTimer *time.Timer
+	var manualPromptC <-chan time.Time
+	if opts != nil && opts.Prompt != nil {
+		manualPromptTimer = time.NewTimer(15 * time.Second)
+		manualPromptC = manualPromptTimer.C
+		defer manualPromptTimer.Stop()
+	}
+
+waitForCallback:
+	for {
+		select {
+		case code := <-codeChan:
+			authCode = code
+			break waitForCallback
+		case err := <-errChan:
+			return nil, err
+		case <-manualPromptC:
+			manualPromptC = nil
+			if manualPromptTimer != nil {
+				manualPromptTimer.Stop()
+			}
+			select {
+			case code := <-codeChan:
+				authCode = code
+				break waitForCallback
+			case err := <-errChan:
+				return nil, err
+			default:
+			}
+			input, err := opts.Prompt("Paste the Gemini callback URL (or press Enter to keep waiting): ")
+			if err != nil {
+				return nil, err
+			}
+			parsed, err := misc.ParseOAuthCallback(input)
+			if err != nil {
+				return nil, err
+			}
+			if parsed == nil {
+				continue
+			}
+			if parsed.Error != "" {
+				return nil, fmt.Errorf("authentication failed via callback: %s", parsed.Error)
+			}
+			if parsed.Code == "" {
+				return nil, fmt.Errorf("code not found in callback")
+			}
+			authCode = parsed.Code
+			break waitForCallback
+		case <-timeoutTimer.C:
+			return nil, fmt.Errorf("oauth flow timed out")
+		}
 	}
 
 	// Shutdown the server.

internal/cache/signature_cache.go

@@ -0,0 +1,164 @@
+package cache
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"sort"
+	"sync"
+	"time"
+)
+
+// SignatureEntry holds a cached thinking signature with timestamp
+type SignatureEntry struct {
+	Signature string
+	Timestamp time.Time
+}
+
+const (
+	// SignatureCacheTTL is how long signatures are valid
+	SignatureCacheTTL = 1 * time.Hour
+
+	// MaxEntriesPerSession limits memory usage per session
+	MaxEntriesPerSession = 100
+
+	// SignatureTextHashLen is the length of the hash key (16 hex chars = 64-bit key space)
+	SignatureTextHashLen = 16
+
+	// MinValidSignatureLen is the minimum length for a signature to be considered valid
+	MinValidSignatureLen = 50
+)
+
+// signatureCache stores signatures by sessionId -> textHash -> SignatureEntry
+var signatureCache sync.Map
+
+// sessionCache is the inner map type
+type sessionCache struct {
+	mu      sync.RWMutex
+	entries map[string]SignatureEntry
+}
+
+// hashText creates a stable, Unicode-safe key from text content
+func hashText(text string) string {
+	h := sha256.Sum256([]byte(text))
+	return hex.EncodeToString(h[:])[:SignatureTextHashLen]
+}
+
+// getOrCreateSession gets or creates a session cache
+func getOrCreateSession(sessionID string) *sessionCache {
+	if val, ok := signatureCache.Load(sessionID); ok {
+		return val.(*sessionCache)
+	}
+	sc := &sessionCache{entries: make(map[string]SignatureEntry)}
+	actual, _ := signatureCache.LoadOrStore(sessionID, sc)
+	return actual.(*sessionCache)
+}
+
+// CacheSignature stores a thinking signature for a given session and text.
+// Used for Claude models that require signed thinking blocks in multi-turn conversations.
+func CacheSignature(sessionID, text, signature string) {
+	if sessionID == "" || text == "" || signature == "" {
+		return
+	}
+	if len(signature) < MinValidSignatureLen {
+		return
+	}
+
+	sc := getOrCreateSession(sessionID)
+	textHash := hashText(text)
+
+	sc.mu.Lock()
+	defer sc.mu.Unlock()
+
+	// Evict expired entries if at capacity
+	if len(sc.entries) >= MaxEntriesPerSession {
+		now := time.Now()
+		for key, entry := range sc.entries {
+			if now.Sub(entry.Timestamp) > SignatureCacheTTL {
+				delete(sc.entries, key)
+			}
+		}
+		// If still at capacity, remove oldest entries
+		if len(sc.entries) >= MaxEntriesPerSession {
+			// Find and remove oldest quarter
+			oldest := make([]struct {
+				key string
+				ts  time.Time
+			}, 0, len(sc.entries))
+			for key, entry := range sc.entries {
+				oldest = append(oldest, struct {
+					key string
+					ts  time.Time
+				}{key, entry.Timestamp})
+			}
+			// Sort by timestamp (oldest first) using sort.Slice
+			sort.Slice(oldest, func(i, j int) bool {
+				return oldest[i].ts.Before(oldest[j].ts)
+			})
+
+			toRemove := len(oldest) / 4
+			if toRemove < 1 {
+				toRemove = 1
+			}
+
+			for i := 0; i < toRemove; i++ {
+				delete(sc.entries, oldest[i].key)
+			}
+		}
+	}
+
+	sc.entries[textHash] = SignatureEntry{
+		Signature: signature,
+		Timestamp: time.Now(),
+	}
+}
+
+// GetCachedSignature retrieves a cached signature for a given session and text.
+// Returns empty string if not found or expired.
+func GetCachedSignature(sessionID, text string) string {
+	if sessionID == "" || text == "" {
+		return ""
+	}
+
+	val, ok := signatureCache.Load(sessionID)
+	if !ok {
+		return ""
+	}
+	sc := val.(*sessionCache)
+
+	textHash := hashText(text)
+
+	sc.mu.RLock()
+	entry, exists := sc.entries[textHash]
+	sc.mu.RUnlock()
+
+	if !exists {
+		return ""
+	}
+
+	// Check if expired
+	if time.Since(entry.Timestamp) > SignatureCacheTTL {
+		sc.mu.Lock()
+		delete(sc.entries, textHash)
+		sc.mu.Unlock()
+		return ""
+	}
+
+	return entry.Signature
+}
+
+// ClearSignatureCache clears signature cache for a specific session or all sessions.
+func ClearSignatureCache(sessionID string) {
+	if sessionID != "" {
+		signatureCache.Delete(sessionID)
+	} else {
+		signatureCache.Range(func(key, _ any) bool {
+			signatureCache.Delete(key)
+			return true
+		})
+	}
+}
+
+// HasValidSignature checks if a signature is valid (non-empty and long enough)
+func HasValidSignature(signature string) bool {
+	return signature != "" && len(signature) >= MinValidSignatureLen
+}

internal/cache/signature_cache_test.go

@@ -0,0 +1,216 @@
+package cache
+
+import (
+	"testing"
+	"time"
+)
+
+func TestCacheSignature_BasicStorageAndRetrieval(t *testing.T) {
+	ClearSignatureCache("")
+
+	sessionID := "test-session-1"
+	text := "This is some thinking text content"
+	signature := "abc123validSignature1234567890123456789012345678901234567890"
+
+	// Store signature
+	CacheSignature(sessionID, text, signature)
+
+	// Retrieve signature
+	retrieved := GetCachedSignature(sessionID, text)
+	if retrieved != signature {
+		t.Errorf("Expected signature '%s', got '%s'", signature, retrieved)
+	}
+}
+
+func TestCacheSignature_DifferentSessions(t *testing.T) {
+	ClearSignatureCache("")
+
+	text := "Same text in different sessions"
+	sig1 := "signature1_1234567890123456789012345678901234567890123456"
+	sig2 := "signature2_1234567890123456789012345678901234567890123456"
+
+	CacheSignature("session-a", text, sig1)
+	CacheSignature("session-b", text, sig2)
+
+	if GetCachedSignature("session-a", text) != sig1 {
+		t.Error("Session-a signature mismatch")
+	}
+	if GetCachedSignature("session-b", text) != sig2 {
+		t.Error("Session-b signature mismatch")
+	}
+}
+
+func TestCacheSignature_NotFound(t *testing.T) {
+	ClearSignatureCache("")
+
+	// Non-existent session
+	if got := GetCachedSignature("nonexistent", "some text"); got != "" {
+		t.Errorf("Expected empty string for nonexistent session, got '%s'", got)
+	}
+
+	// Existing session but different text
+	CacheSignature("session-x", "text-a", "sigA12345678901234567890123456789012345678901234567890")
+	if got := GetCachedSignature("session-x", "text-b"); got != "" {
+		t.Errorf("Expected empty string for different text, got '%s'", got)
+	}
+}
+
+func TestCacheSignature_EmptyInputs(t *testing.T) {
+	ClearSignatureCache("")
+
+	// All empty/invalid inputs should be no-ops
+	CacheSignature("", "text", "sig12345678901234567890123456789012345678901234567890")
+	CacheSignature("session", "", "sig12345678901234567890123456789012345678901234567890")
+	CacheSignature("session", "text", "")
+	CacheSignature("session", "text", "short") // Too short
+
+	if got := GetCachedSignature("session", "text"); got != "" {
+		t.Errorf("Expected empty after invalid cache attempts, got '%s'", got)
+	}
+}
+
+func TestCacheSignature_ShortSignatureRejected(t *testing.T) {
+	ClearSignatureCache("")
+
+	sessionID := "test-short-sig"
+	text := "Some text"
+	shortSig := "abc123" // Less than 50 chars
+
+	CacheSignature(sessionID, text, shortSig)
+
+	if got := GetCachedSignature(sessionID, text); got != "" {
+		t.Errorf("Short signature should be rejected, got '%s'", got)
+	}
+}
+
+func TestClearSignatureCache_SpecificSession(t *testing.T) {
+	ClearSignatureCache("")
+
+	sig := "validSig1234567890123456789012345678901234567890123456"
+	CacheSignature("session-1", "text", sig)
+	CacheSignature("session-2", "text", sig)
+
+	ClearSignatureCache("session-1")
+
+	if got := GetCachedSignature("session-1", "text"); got != "" {
+		t.Error("session-1 should be cleared")
+	}
+	if got := GetCachedSignature("session-2", "text"); got != sig {
+		t.Error("session-2 should still exist")
+	}
+}
+
+func TestClearSignatureCache_AllSessions(t *testing.T) {
+	ClearSignatureCache("")
+
+	sig := "validSig1234567890123456789012345678901234567890123456"
+	CacheSignature("session-1", "text", sig)
+	CacheSignature("session-2", "text", sig)
+
+	ClearSignatureCache("")
+
+	if got := GetCachedSignature("session-1", "text"); got != "" {
+		t.Error("session-1 should be cleared")
+	}
+	if got := GetCachedSignature("session-2", "text"); got != "" {
+		t.Error("session-2 should be cleared")
+	}
+}
+
+func TestHasValidSignature(t *testing.T) {
+	tests := []struct {
+		name      string
+		signature string
+		expected  bool
+	}{
+		{"valid long signature", "abc123validSignature1234567890123456789012345678901234567890", true},
+		{"exactly 50 chars", "12345678901234567890123456789012345678901234567890", true},
+		{"49 chars - invalid", "1234567890123456789012345678901234567890123456789", false},
+		{"empty string", "", false},
+		{"short signature", "abc", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := HasValidSignature(tt.signature)
+			if result != tt.expected {
+				t.Errorf("HasValidSignature(%q) = %v, expected %v", tt.signature, result, tt.expected)
+			}
+		})
+	}
+}
+
+func TestCacheSignature_TextHashCollisionResistance(t *testing.T) {
+	ClearSignatureCache("")
+
+	sessionID := "hash-test-session"
+
+	// Different texts should produce different hashes
+	text1 := "First thinking text"
+	text2 := "Second thinking text"
+	sig1 := "signature1_1234567890123456789012345678901234567890123456"
+	sig2 := "signature2_1234567890123456789012345678901234567890123456"
+
+	CacheSignature(sessionID, text1, sig1)
+	CacheSignature(sessionID, text2, sig2)
+
+	if GetCachedSignature(sessionID, text1) != sig1 {
+		t.Error("text1 signature mismatch")
+	}
+	if GetCachedSignature(sessionID, text2) != sig2 {
+		t.Error("text2 signature mismatch")
+	}
+}
+
+func TestCacheSignature_UnicodeText(t *testing.T) {
+	ClearSignatureCache("")
+
+	sessionID := "unicode-session"
+	text := "한글 텍스트와 이모지 🎉 그리고 特殊文字"
+	sig := "unicodeSig123456789012345678901234567890123456789012345"
+
+	CacheSignature(sessionID, text, sig)
+
+	if got := GetCachedSignature(sessionID, text); got != sig {
+		t.Errorf("Unicode text signature retrieval failed, got '%s'", got)
+	}
+}
+
+func TestCacheSignature_Overwrite(t *testing.T) {
+	ClearSignatureCache("")
+
+	sessionID := "overwrite-session"
+	text := "Same text"
+	sig1 := "firstSignature12345678901234567890123456789012345678901"
+	sig2 := "secondSignature1234567890123456789012345678901234567890"
+
+	CacheSignature(sessionID, text, sig1)
+	CacheSignature(sessionID, text, sig2) // Overwrite
+
+	if got := GetCachedSignature(sessionID, text); got != sig2 {
+		t.Errorf("Expected overwritten signature '%s', got '%s'", sig2, got)
+	}
+}
+
+// Note: TTL expiration test is tricky to test without mocking time
+// We test the logic path exists but actual expiration would require time manipulation
+func TestCacheSignature_ExpirationLogic(t *testing.T) {
+	ClearSignatureCache("")
+
+	// This test verifies the expiration check exists
+	// In a real scenario, we'd mock time.Now()
+	sessionID := "expiration-test"
+	text := "text"
+	sig := "validSig1234567890123456789012345678901234567890123456"
+
+	CacheSignature(sessionID, text, sig)
+
+	// Fresh entry should be retrievable
+	if got := GetCachedSignature(sessionID, text); got != sig {
+		t.Errorf("Fresh entry should be retrievable, got '%s'", got)
+	}
+
+	// We can't easily test actual expiration without time mocking
+	// but the logic is verified by the implementation
+	_ = time.Now() // Acknowledge we're not testing time passage
+}

internal/cmd/anthropic_login.go

@@ -24,12 +24,17 @@ func DoClaudeLogin(cfg *config.Config, options *LoginOptions) {
 		options = &LoginOptions{}
 	}
 
+	promptFn := options.Prompt
+	if promptFn == nil {
+		promptFn = defaultProjectPrompt()
+	}
+
 	manager := newAuthManager()
 
 	authOpts := &sdkAuth.LoginOptions{
 		NoBrowser: options.NoBrowser,
 		Metadata:  map[string]string{},
-		Prompt:    options.Prompt,
+		Prompt:    promptFn,
 	}
 
 	_, savedPath, err := manager.Login(context.Background(), "claude", cfg, authOpts)

internal/cmd/antigravity_login.go

@@ -15,11 +15,16 @@ func DoAntigravityLogin(cfg *config.Config, options *LoginOptions) {
 		options = &LoginOptions{}
 	}
 
+	promptFn := options.Prompt
+	if promptFn == nil {
+		promptFn = defaultProjectPrompt()
+	}
+
 	manager := newAuthManager()
 	authOpts := &sdkAuth.LoginOptions{
 		NoBrowser: options.NoBrowser,
 		Metadata:  map[string]string{},
-		Prompt:    options.Prompt,
+		Prompt:    promptFn,
 	}
 
 	record, savedPath, err := manager.Login(context.Background(), "antigravity", cfg, authOpts)

internal/cmd/iflow_login.go

@@ -20,13 +20,7 @@ func DoIFlowLogin(cfg *config.Config, options *LoginOptions) {
 
 	promptFn := options.Prompt
 	if promptFn == nil {
-		promptFn = func(prompt string) (string, error) {
-			fmt.Println()
-			fmt.Println(prompt)
-			var value string
-			_, err := fmt.Scanln(&value)
-			return value, err
-		}
+		promptFn = defaultProjectPrompt()
 	}
 
 	authOpts := &sdkAuth.LoginOptions{

internal/cmd/login.go

@@ -55,11 +55,22 @@ func DoLogin(cfg *config.Config, projectID string, options *LoginOptions) {
 
 	ctx := context.Background()
 
+	promptFn := options.Prompt
+	if promptFn == nil {
+		promptFn = defaultProjectPrompt()
+	}
+
+	trimmedProjectID := strings.TrimSpace(projectID)
+	callbackPrompt := promptFn
+	if trimmedProjectID == "" {
+		callbackPrompt = nil
+	}
+
 	loginOpts := &sdkAuth.LoginOptions{
 		NoBrowser: options.NoBrowser,
-		ProjectID: strings.TrimSpace(projectID),
+		ProjectID: trimmedProjectID,
 		Metadata:  map[string]string{},
-		Prompt:    options.Prompt,
+		Prompt:    callbackPrompt,
 	}
 
 	authenticator := sdkAuth.NewGeminiAuthenticator()
@@ -76,7 +87,10 @@ func DoLogin(cfg *config.Config, projectID string, options *LoginOptions) {
 	}
 
 	geminiAuth := gemini.NewGeminiAuth()
-	httpClient, errClient := geminiAuth.GetAuthenticatedClient(ctx, storage, cfg, options.NoBrowser)
+	httpClient, errClient := geminiAuth.GetAuthenticatedClient(ctx, storage, cfg, &gemini.WebLoginOptions{
+		NoBrowser: options.NoBrowser,
+		Prompt:    callbackPrompt,
+	})
 	if errClient != nil {
 		log.Errorf("Gemini authentication failed: %v", errClient)
 		return
@@ -90,12 +104,7 @@ func DoLogin(cfg *config.Config, projectID string, options *LoginOptions) {
 		return
 	}
 
-	promptFn := options.Prompt
-	if promptFn == nil {
-		promptFn = defaultProjectPrompt()
-	}
-
-	selectedProjectID := promptForProjectSelection(projects, strings.TrimSpace(projectID), promptFn)
+	selectedProjectID := promptForProjectSelection(projects, trimmedProjectID, promptFn)
 	projectSelections, errSelection := resolveProjectSelections(selectedProjectID, projects)
 	if errSelection != nil {
 		log.Errorf("Invalid project selection: %v", errSelection)

internal/cmd/openai_login.go

@@ -35,12 +35,17 @@ func DoCodexLogin(cfg *config.Config, options *LoginOptions) {
 		options = &LoginOptions{}
 	}
 
+	promptFn := options.Prompt
+	if promptFn == nil {
+		promptFn = defaultProjectPrompt()
+	}
+
 	manager := newAuthManager()
 
 	authOpts := &sdkAuth.LoginOptions{
 		NoBrowser: options.NoBrowser,
 		Metadata:  map[string]string{},
-		Prompt:    options.Prompt,
+		Prompt:    promptFn,
 	}
 
 	_, savedPath, err := manager.Login(context.Background(), "codex", cfg, authOpts)

internal/config/config.go

@@ -39,9 +39,16 @@ type Config struct {
 	// Debug enables or disables debug-level logging and other debug features.
 	Debug bool `yaml:"debug" json:"debug"`
 
+	// CommercialMode disables high-overhead HTTP middleware features to minimize per-request memory usage.
+	CommercialMode bool `yaml:"commercial-mode" json:"commercial-mode"`
+
 	// LoggingToFile controls whether application logs are written to rotating files or stdout.
 	LoggingToFile bool `yaml:"logging-to-file" json:"logging-to-file"`
 
+	// LogsMaxTotalSizeMB limits the total size (in MB) of log files under the logs directory.
+	// When exceeded, the oldest log files are deleted until within the limit. Set to 0 to disable.
+	LogsMaxTotalSizeMB int `yaml:"logs-max-total-size-mb" json:"logs-max-total-size-mb"`
+
 	// UsageStatisticsEnabled toggles in-memory usage aggregation; when false, usage data is discarded.
 	UsageStatisticsEnabled bool `yaml:"usage-statistics-enabled" json:"usage-statistics-enabled"`
 
@@ -56,6 +63,9 @@ type Config struct {
 	// QuotaExceeded defines the behavior when a quota is exceeded.
 	QuotaExceeded QuotaExceeded `yaml:"quota-exceeded" json:"quota-exceeded"`
 
+	// Routing controls credential selection behavior.
+	Routing RoutingConfig `yaml:"routing" json:"routing"`
+
 	// WebsocketAuth enables or disables authentication for the WebSocket API.
 	WebsocketAuth bool `yaml:"ws-auth" json:"ws-auth"`
 
@@ -81,6 +91,14 @@ type Config struct {
 	// OAuthExcludedModels defines per-provider global model exclusions applied to OAuth/file-backed auth entries.
 	OAuthExcludedModels map[string][]string `yaml:"oauth-excluded-models,omitempty" json:"oauth-excluded-models,omitempty"`
 
+	// OAuthModelMappings defines global model name mappings for OAuth/file-backed auth channels.
+	// These mappings affect both model listing and model routing for supported channels:
+	// gemini-cli, vertex, aistudio, antigravity, claude, codex, qwen, iflow.
+	//
+	// NOTE: This does not apply to existing per-credential model alias features under:
+	// gemini-api-key, codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, and ampcode.
+	OAuthModelMappings map[string][]ModelNameMapping `yaml:"oauth-model-mappings,omitempty" json:"oauth-model-mappings,omitempty"`
+
 	// Payload defines default and override rules for provider payload parameters.
 	Payload PayloadConfig `yaml:"payload" json:"payload"`
 
@@ -120,6 +138,20 @@ type QuotaExceeded struct {
 	SwitchPreviewModel bool `yaml:"switch-preview-model" json:"switch-preview-model"`
 }
 
+// RoutingConfig configures how credentials are selected for requests.
+type RoutingConfig struct {
+	// Strategy selects the credential selection strategy.
+	// Supported values: "round-robin" (default), "fill-first".
+	Strategy string `yaml:"strategy,omitempty" json:"strategy,omitempty"`
+}
+
+// ModelNameMapping defines a model ID rename mapping for a specific channel.
+// It maps the original model name (Name) to the client-visible alias (Alias).
+type ModelNameMapping struct {
+	Name  string `yaml:"name" json:"name"`
+	Alias string `yaml:"alias" json:"alias"`
+}
+
 // AmpModelMapping defines a model name mapping for Amp CLI requests.
 // When Amp requests a model that isn't available locally, this mapping
 // allows routing to an alternative model that IS available.
@@ -130,6 +162,11 @@ type AmpModelMapping struct {
 	// To is the target model name to route to (e.g., "claude-sonnet-4").
 	// The target model must have available providers in the registry.
 	To string `yaml:"to" json:"to"`
+
+	// Regex indicates whether the 'from' field should be interpreted as a regular
+	// expression for matching model names. When true, this mapping is evaluated
+	// after exact matches and in the order provided. Defaults to false (exact match).
+	Regex bool `yaml:"regex,omitempty" json:"regex,omitempty"`
 }
 
 // AmpCode groups Amp CLI integration settings including upstream routing,
@@ -141,6 +178,11 @@ type AmpCode struct {
 	// UpstreamAPIKey optionally overrides the Authorization header when proxying Amp upstream calls.
 	UpstreamAPIKey string `yaml:"upstream-api-key" json:"upstream-api-key"`
 
+	// UpstreamAPIKeys maps client API keys (from top-level api-keys) to upstream API keys.
+	// When a client authenticates with a key that matches an entry, that upstream key is used.
+	// If no match is found, falls back to UpstreamAPIKey (default behavior).
+	UpstreamAPIKeys []AmpUpstreamAPIKeyEntry `yaml:"upstream-api-keys,omitempty" json:"upstream-api-keys,omitempty"`
+
 	// RestrictManagementToLocalhost restricts Amp management routes (/api/user, /api/threads, etc.)
 	// to only accept connections from localhost (127.0.0.1, ::1). When true, prevents drive-by
 	// browser attacks and remote access to management endpoints. Default: false (API key auth is sufficient).
@@ -156,6 +198,17 @@ type AmpCode struct {
 	ForceModelMappings bool `yaml:"force-model-mappings" json:"force-model-mappings"`
 }
 
+// AmpUpstreamAPIKeyEntry maps a set of client API keys to a specific upstream API key.
+// When a request is authenticated with one of the APIKeys, the corresponding UpstreamAPIKey
+// is used for the upstream Amp request.
+type AmpUpstreamAPIKeyEntry struct {
+	// UpstreamAPIKey is the API key to use when proxying to the Amp upstream.
+	UpstreamAPIKey string `yaml:"upstream-api-key" json:"upstream-api-key"`
+
+	// APIKeys are the client API keys (from top-level api-keys) that map to this upstream key.
+	APIKeys []string `yaml:"api-keys" json:"api-keys"`
+}
+
 // PayloadConfig defines default and override parameter rules applied to provider payloads.
 type PayloadConfig struct {
 	// Default defines rules that only set parameters when they are missing in the payload.
@@ -215,6 +268,9 @@ type ClaudeModel struct {
 	Alias string `yaml:"alias" json:"alias"`
 }
 
+func (m ClaudeModel) GetName() string  { return m.Name }
+func (m ClaudeModel) GetAlias() string { return m.Alias }
+
 // CodexKey represents the configuration for a Codex API key,
 // including the API key itself and an optional base URL for the API endpoint.
 type CodexKey struct {
@@ -231,6 +287,9 @@ type CodexKey struct {
 	// ProxyURL overrides the global proxy setting for this API key if provided.
 	ProxyURL string `yaml:"proxy-url" json:"proxy-url"`
 
+	// Models defines upstream model names and aliases for request routing.
+	Models []CodexModel `yaml:"models" json:"models"`
+
 	// Headers optionally adds extra HTTP headers for requests sent with this key.
 	Headers map[string]string `yaml:"headers,omitempty" json:"headers,omitempty"`
 
@@ -238,6 +297,18 @@ type CodexKey struct {
 	ExcludedModels []string `yaml:"excluded-models,omitempty" json:"excluded-models,omitempty"`
 }
 
+// CodexModel describes a mapping between an alias and the actual upstream model name.
+type CodexModel struct {
+	// Name is the upstream model identifier used when issuing requests.
+	Name string `yaml:"name" json:"name"`
+
+	// Alias is the client-facing model name that maps to Name.
+	Alias string `yaml:"alias" json:"alias"`
+}
+
+func (m CodexModel) GetName() string  { return m.Name }
+func (m CodexModel) GetAlias() string { return m.Alias }
+
 // GeminiKey represents the configuration for a Gemini API key,
 // including optional overrides for upstream base URL, proxy routing, and headers.
 type GeminiKey struct {
@@ -253,6 +324,9 @@ type GeminiKey struct {
 	// ProxyURL optionally overrides the global proxy for this API key.
 	ProxyURL string `yaml:"proxy-url,omitempty" json:"proxy-url,omitempty"`
 
+	// Models defines upstream model names and aliases for request routing.
+	Models []GeminiModel `yaml:"models,omitempty" json:"models,omitempty"`
+
 	// Headers optionally adds extra HTTP headers for requests sent with this key.
 	Headers map[string]string `yaml:"headers,omitempty" json:"headers,omitempty"`
 
@@ -260,6 +334,18 @@ type GeminiKey struct {
 	ExcludedModels []string `yaml:"excluded-models,omitempty" json:"excluded-models,omitempty"`
 }
 
+// GeminiModel describes a mapping between an alias and the actual upstream model name.
+type GeminiModel struct {
+	// Name is the upstream model identifier used when issuing requests.
+	Name string `yaml:"name" json:"name"`
+
+	// Alias is the client-facing model name that maps to Name.
+	Alias string `yaml:"alias" json:"alias"`
+}
+
+func (m GeminiModel) GetName() string  { return m.Name }
+func (m GeminiModel) GetAlias() string { return m.Alias }
+
 // OpenAICompatibility represents the configuration for OpenAI API compatibility
 // with external providers, allowing model aliases to be routed through OpenAI API format.
 type OpenAICompatibility struct {
@@ -341,6 +427,7 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	// Set defaults before unmarshal so that absent keys keep defaults.
 	cfg.Host = "" // Default empty: binds to all interfaces (IPv4 + IPv6)
 	cfg.LoggingToFile = false
+	cfg.LogsMaxTotalSizeMB = 0
 	cfg.UsageStatisticsEnabled = false
 	cfg.DisableCooling = false
 	cfg.AmpCode.RestrictManagementToLocalhost = false // Default to false: API key auth is sufficient
@@ -385,6 +472,10 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 		cfg.RemoteManagement.PanelGitHubRepository = DefaultPanelGitHubRepository
 	}
 
+	if cfg.LogsMaxTotalSizeMB < 0 {
+		cfg.LogsMaxTotalSizeMB = 0
+	}
+
 	// Sync request authentication providers with inline API keys for backwards compatibility.
 	syncInlineAccessProvider(&cfg)
 
@@ -406,6 +497,9 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	// Normalize OAuth provider model exclusion map.
 	cfg.OAuthExcludedModels = NormalizeOAuthExcludedModels(cfg.OAuthExcludedModels)
 
+	// Normalize global OAuth model name mappings.
+	cfg.SanitizeOAuthModelMappings()
+
 	if cfg.legacyMigrationPending {
 		fmt.Println("Detected legacy configuration keys, attempting to persist the normalized config...")
 		if !optional && configFile != "" {
@@ -422,6 +516,50 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
 	return &cfg, nil
 }
 
+// SanitizeOAuthModelMappings normalizes and deduplicates global OAuth model name mappings.
+// It trims whitespace, normalizes channel keys to lower-case, drops empty entries,
+// and ensures (From, To) pairs are unique within each channel.
+func (cfg *Config) SanitizeOAuthModelMappings() {
+	if cfg == nil || len(cfg.OAuthModelMappings) == 0 {
+		return
+	}
+	out := make(map[string][]ModelNameMapping, len(cfg.OAuthModelMappings))
+	for rawChannel, mappings := range cfg.OAuthModelMappings {
+		channel := strings.ToLower(strings.TrimSpace(rawChannel))
+		if channel == "" || len(mappings) == 0 {
+			continue
+		}
+		seenName := make(map[string]struct{}, len(mappings))
+		seenAlias := make(map[string]struct{}, len(mappings))
+		clean := make([]ModelNameMapping, 0, len(mappings))
+		for _, mapping := range mappings {
+			name := strings.TrimSpace(mapping.Name)
+			alias := strings.TrimSpace(mapping.Alias)
+			if name == "" || alias == "" {
+				continue
+			}
+			if strings.EqualFold(name, alias) {
+				continue
+			}
+			nameKey := strings.ToLower(name)
+			aliasKey := strings.ToLower(alias)
+			if _, ok := seenName[nameKey]; ok {
+				continue
+			}
+			if _, ok := seenAlias[aliasKey]; ok {
+				continue
+			}
+			seenName[nameKey] = struct{}{}
+			seenAlias[aliasKey] = struct{}{}
+			clean = append(clean, ModelNameMapping{Name: name, Alias: alias})
+		}
+		if len(clean) > 0 {
+			out[channel] = clean
+		}
+	}
+	cfg.OAuthModelMappings = out
+}
+
 // SanitizeOpenAICompatibility removes OpenAI-compatibility provider entries that are
 // not actionable, specifically those missing a BaseURL. It trims whitespace before
 // evaluation and preserves the relative order of remaining entries.
@@ -790,8 +928,8 @@ func getOrCreateMapValue(mapNode *yaml.Node, key string) *yaml.Node {
 }
 
 // mergeMappingPreserve merges keys from src into dst mapping node while preserving
-// key order and comments of existing keys in dst. Unknown keys from src are appended
-// to dst at the end, copying their node structure from src.
+// key order and comments of existing keys in dst. New keys are only added if their
+// value is non-zero to avoid polluting the config with defaults.
 func mergeMappingPreserve(dst, src *yaml.Node) {
 	if dst == nil || src == nil {
 		return
@@ -802,20 +940,19 @@ func mergeMappingPreserve(dst, src *yaml.Node) {
 		copyNodeShallow(dst, src)
 		return
 	}
-	// Build a lookup of existing keys in dst
 	for i := 0; i+1 < len(src.Content); i += 2 {
 		sk := src.Content[i]
 		sv := src.Content[i+1]
 		idx := findMapKeyIndex(dst, sk.Value)
 		if idx >= 0 {
-			// Merge into existing value node
+			// Merge into existing value node (always update, even to zero values)
 			dv := dst.Content[idx+1]
 			mergeNodePreserve(dv, sv)
 		} else {
-			if shouldSkipEmptyCollectionOnPersist(sk.Value, sv) {
+			// New key: only add if value is non-zero to avoid polluting config with defaults
+			if isZeroValueNode(sv) {
 				continue
 			}
-			// Append new key/value pair by deep-copying from src
 			dst.Content = append(dst.Content, deepCopyNode(sk), deepCopyNode(sv))
 		}
 	}
@@ -898,32 +1035,49 @@ func findMapKeyIndex(mapNode *yaml.Node, key string) int {
 	return -1
 }
 
-func shouldSkipEmptyCollectionOnPersist(key string, node *yaml.Node) bool {
-	switch key {
-	case "generative-language-api-key",
-		"gemini-api-key",
-		"vertex-api-key",
-		"claude-api-key",
-		"codex-api-key",
-		"openai-compatibility":
-		return isEmptyCollectionNode(node)
-	default:
-		return false
-	}
-}
-
-func isEmptyCollectionNode(node *yaml.Node) bool {
+// isZeroValueNode returns true if the YAML node represents a zero/default value
+// that should not be written as a new key to preserve config cleanliness.
+// For mappings and sequences, recursively checks if all children are zero values.
+func isZeroValueNode(node *yaml.Node) bool {
 	if node == nil {
 		return true
 	}
 	switch node.Kind {
-	case yaml.SequenceNode:
-		return len(node.Content) == 0
 	case yaml.ScalarNode:
-		return node.Tag == "!!null"
-	default:
-		return false
+		switch node.Tag {
+		case "!!bool":
+			return node.Value == "false"
+		case "!!int", "!!float":
+			return node.Value == "0" || node.Value == "0.0"
+		case "!!str":
+			return node.Value == ""
+		case "!!null":
+			return true
+		}
+	case yaml.SequenceNode:
+		if len(node.Content) == 0 {
+			return true
+		}
+		// Check if all elements are zero values
+		for _, child := range node.Content {
+			if !isZeroValueNode(child) {
+				return false
+			}
+		}
+		return true
+	case yaml.MappingNode:
+		if len(node.Content) == 0 {
+			return true
+		}
+		// Check if all values are zero values (values are at odd indices)
+		for i := 1; i < len(node.Content); i += 2 {
+			if !isZeroValueNode(node.Content[i]) {
+				return false
+			}
+		}
+		return true
 	}
+	return false
 }
 
 // deepCopyNode creates a deep copy of a yaml.Node graph.

internal/config/sdk_config.go

@@ -22,6 +22,21 @@ type SDKConfig struct {
 
 	// Access holds request authentication provider configuration.
 	Access AccessConfig `yaml:"auth,omitempty" json:"auth,omitempty"`
+
+	// Streaming configures server-side streaming behavior (keep-alives and safe bootstrap retries).
+	Streaming StreamingConfig `yaml:"streaming" json:"streaming"`
+}
+
+// StreamingConfig holds server streaming behavior configuration.
+type StreamingConfig struct {
+	// KeepAliveSeconds controls how often the server emits SSE heartbeats (": keep-alive\n\n").
+	// <= 0 disables keep-alives. Default is 0.
+	KeepAliveSeconds int `yaml:"keepalive-seconds,omitempty" json:"keepalive-seconds,omitempty"`
+
+	// BootstrapRetries controls how many times the server may retry a streaming request before any bytes are sent,
+	// to allow auth rotation / transient recovery.
+	// <= 0 disables bootstrap retries. Default is 0.
+	BootstrapRetries int `yaml:"bootstrap-retries,omitempty" json:"bootstrap-retries,omitempty"`
 }
 
 // AccessConfig groups request authentication providers.

internal/config/vertex_compat.go

@@ -42,6 +42,9 @@ type VertexCompatModel struct {
 	Alias string `yaml:"alias" json:"alias"`
 }
 
+func (m VertexCompatModel) GetName() string  { return m.Name }
+func (m VertexCompatModel) GetAlias() string { return m.Alias }
+
 // SanitizeVertexCompatKeys deduplicates and normalizes Vertex-compatible API key credentials.
 func (cfg *Config) SanitizeVertexCompatKeys() {
 	if cfg == nil {

internal/logging/gin_logger.go

@@ -7,6 +7,7 @@ import (
 	"fmt"
 	"net/http"
 	"runtime/debug"
+	"strings"
 	"time"
 
 	"github.com/gin-gonic/gin"
@@ -14,11 +15,24 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
+// aiAPIPrefixes defines path prefixes for AI API requests that should have request ID tracking.
+var aiAPIPrefixes = []string{
+	"/v1/chat/completions",
+	"/v1/completions",
+	"/v1/messages",
+	"/v1/responses",
+	"/v1beta/models/",
+	"/api/provider/",
+}
+
 const skipGinLogKey = "__gin_skip_request_logging__"
 
 // GinLogrusLogger returns a Gin middleware handler that logs HTTP requests and responses
 // using logrus. It captures request details including method, path, status code, latency,
-// client IP, and any error messages, formatting them in a Gin-style log format.
+// client IP, and any error messages. Request ID is only added for AI API requests.
+//
+// Output format (AI API): [2025-12-23 20:14:10] [info ] | a1b2c3d4 | 200 |       23.559s | ...
+// Output format (others): [2025-12-23 20:14:10] [info ] | -------- | 200 |       23.559s | ...
 //
 // Returns:
 //   - gin.HandlerFunc: A middleware handler for request logging
@@ -28,6 +42,15 @@ func GinLogrusLogger() gin.HandlerFunc {
 		path := c.Request.URL.Path
 		raw := util.MaskSensitiveQuery(c.Request.URL.RawQuery)
 
+		// Only generate request ID for AI API paths
+		var requestID string
+		if isAIAPIPath(path) {
+			requestID = GenerateRequestID()
+			SetGinRequestID(c, requestID)
+			ctx := WithRequestID(c.Request.Context(), requestID)
+			c.Request = c.Request.WithContext(ctx)
+		}
+
 		c.Next()
 
 		if shouldSkipGinRequestLogging(c) {
@@ -49,23 +72,38 @@ func GinLogrusLogger() gin.HandlerFunc {
 		clientIP := c.ClientIP()
 		method := c.Request.Method
 		errorMessage := c.Errors.ByType(gin.ErrorTypePrivate).String()
-		timestamp := time.Now().Format("2006/01/02 - 15:04:05")
-		logLine := fmt.Sprintf("[GIN] %s | %3d | %13v | %15s | %-7s \"%s\"", timestamp, statusCode, latency, clientIP, method, path)
+
+		if requestID == "" {
+			requestID = "--------"
+		}
+		logLine := fmt.Sprintf("%3d | %13v | %15s | %-7s \"%s\"", statusCode, latency, clientIP, method, path)
 		if errorMessage != "" {
 			logLine = logLine + " | " + errorMessage
 		}
 
+		entry := log.WithField("request_id", requestID)
+
 		switch {
 		case statusCode >= http.StatusInternalServerError:
-			log.Error(logLine)
+			entry.Error(logLine)
 		case statusCode >= http.StatusBadRequest:
-			log.Warn(logLine)
+			entry.Warn(logLine)
 		default:
-			log.Info(logLine)
+			entry.Info(logLine)
 		}
 	}
 }
 
+// isAIAPIPath checks if the given path is an AI API endpoint that should have request ID tracking.
+func isAIAPIPath(path string) bool {
+	for _, prefix := range aiAPIPrefixes {
+		if strings.HasPrefix(path, prefix) {
+			return true
+		}
+	}
+	return false
+}
+
 // GinLogrusRecovery returns a Gin middleware handler that recovers from panics and logs
 // them using logrus. When a panic occurs, it captures the panic value, stack trace,
 // and request path, then returns a 500 Internal Server Error response to the client.

internal/logging/global_logger.go

@@ -10,6 +10,7 @@ import (
 	"sync"
 
 	"github.com/gin-gonic/gin"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	log "github.com/sirupsen/logrus"
 	"gopkg.in/natefinch/lumberjack.v2"
@@ -24,7 +25,8 @@ var (
 )
 
 // LogFormatter defines a custom log format for logrus.
-// This formatter adds timestamp, level, and source location to each log entry.
+// This formatter adds timestamp, level, request ID, and source location to each log entry.
+// Format: [2025-12-23 20:14:04] [debug] [manager.go:524] | a1b2c3d4 | Use API key sk-9...0RHO for model gpt-5.2
 type LogFormatter struct{}
 
 // Format renders a single log entry with custom formatting.
@@ -39,11 +41,22 @@ func (m *LogFormatter) Format(entry *log.Entry) ([]byte, error) {
 	timestamp := entry.Time.Format("2006-01-02 15:04:05")
 	message := strings.TrimRight(entry.Message, "\r\n")
 
+	reqID := "--------"
+	if id, ok := entry.Data["request_id"].(string); ok && id != "" {
+		reqID = id
+	}
+
+	level := entry.Level.String()
+	if level == "warning" {
+		level = "warn"
+	}
+	levelStr := fmt.Sprintf("%-5s", level)
+
 	var formatted string
 	if entry.Caller != nil {
-		formatted = fmt.Sprintf("[%s] [%s] [%s:%d] %s\n", timestamp, entry.Level, filepath.Base(entry.Caller.File), entry.Caller.Line, message)
+		formatted = fmt.Sprintf("[%s] [%s] [%s] [%s:%d] %s\n", timestamp, reqID, levelStr, filepath.Base(entry.Caller.File), entry.Caller.Line, message)
 	} else {
-		formatted = fmt.Sprintf("[%s] [%s] %s\n", timestamp, entry.Level, message)
+		formatted = fmt.Sprintf("[%s] [%s] [%s] %s\n", timestamp, reqID, levelStr, message)
 	}
 	buffer.WriteString(formatted)
 
@@ -71,40 +84,68 @@ func SetupBaseLogger() {
 	})
 }
 
+// isDirWritable checks if the specified directory exists and is writable by attempting to create and remove a test file.
+func isDirWritable(dir string) bool {
+	info, err := os.Stat(dir)
+	if err != nil || !info.IsDir() {
+		return false
+	}
+
+	testFile := filepath.Join(dir, ".perm_test")
+	f, err := os.Create(testFile)
+	if err != nil {
+		return false
+	}
+
+	defer func() {
+		_ = f.Close()
+		_ = os.Remove(testFile)
+	}()
+	return true
+}
+
 // ConfigureLogOutput switches the global log destination between rotating files and stdout.
-func ConfigureLogOutput(loggingToFile bool) error {
+// When logsMaxTotalSizeMB > 0, a background cleaner removes the oldest log files in the logs directory
+// until the total size is within the limit.
+func ConfigureLogOutput(cfg *config.Config) error {
 	SetupBaseLogger()
 
 	writerMu.Lock()
 	defer writerMu.Unlock()
 
-	if loggingToFile {
-		logDir := "logs"
-		if base := util.WritablePath(); base != "" {
-			logDir = filepath.Join(base, "logs")
-		}
+	logDir := "logs"
+	if base := util.WritablePath(); base != "" {
+		logDir = filepath.Join(base, "logs")
+	} else if !isDirWritable(logDir) {
+		logDir = filepath.Join(cfg.AuthDir, "logs")
+	}
+
+	protectedPath := ""
+	if cfg.LoggingToFile {
 		if err := os.MkdirAll(logDir, 0o755); err != nil {
 			return fmt.Errorf("logging: failed to create log directory: %w", err)
 		}
 		if logWriter != nil {
 			_ = logWriter.Close()
 		}
+		protectedPath = filepath.Join(logDir, "main.log")
 		logWriter = &lumberjack.Logger{
-			Filename:   filepath.Join(logDir, "main.log"),
+			Filename:   protectedPath,
 			MaxSize:    10,
 			MaxBackups: 0,
 			MaxAge:     0,
 			Compress:   false,
 		}
 		log.SetOutput(logWriter)
-		return nil
+	} else {
+		if logWriter != nil {
+			_ = logWriter.Close()
+			logWriter = nil
+		}
+		log.SetOutput(os.Stdout)
 	}
 
-	if logWriter != nil {
-		_ = logWriter.Close()
-		logWriter = nil
-	}
-	log.SetOutput(os.Stdout)
+	configureLogDirCleanerLocked(logDir, cfg.LogsMaxTotalSizeMB, protectedPath)
 	return nil
 }
 
@@ -112,6 +153,8 @@ func closeLogOutputs() {
 	writerMu.Lock()
 	defer writerMu.Unlock()
 
+	stopLogDirCleanerLocked()
+
 	if logWriter != nil {
 		_ = logWriter.Close()
 		logWriter = nil

internal/logging/log_dir_cleaner.go

@@ -0,0 +1,166 @@
+package logging
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+	"sort"
+	"strings"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+)
+
+const logDirCleanerInterval = time.Minute
+
+var logDirCleanerCancel context.CancelFunc
+
+func configureLogDirCleanerLocked(logDir string, maxTotalSizeMB int, protectedPath string) {
+	stopLogDirCleanerLocked()
+
+	if maxTotalSizeMB <= 0 {
+		return
+	}
+
+	maxBytes := int64(maxTotalSizeMB) * 1024 * 1024
+	if maxBytes <= 0 {
+		return
+	}
+
+	dir := strings.TrimSpace(logDir)
+	if dir == "" {
+		return
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	logDirCleanerCancel = cancel
+	go runLogDirCleaner(ctx, filepath.Clean(dir), maxBytes, strings.TrimSpace(protectedPath))
+}
+
+func stopLogDirCleanerLocked() {
+	if logDirCleanerCancel == nil {
+		return
+	}
+	logDirCleanerCancel()
+	logDirCleanerCancel = nil
+}
+
+func runLogDirCleaner(ctx context.Context, logDir string, maxBytes int64, protectedPath string) {
+	ticker := time.NewTicker(logDirCleanerInterval)
+	defer ticker.Stop()
+
+	cleanOnce := func() {
+		deleted, errClean := enforceLogDirSizeLimit(logDir, maxBytes, protectedPath)
+		if errClean != nil {
+			log.WithError(errClean).Warn("logging: failed to enforce log directory size limit")
+			return
+		}
+		if deleted > 0 {
+			log.Debugf("logging: removed %d old log file(s) to enforce log directory size limit", deleted)
+		}
+	}
+
+	cleanOnce()
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			cleanOnce()
+		}
+	}
+}
+
+func enforceLogDirSizeLimit(logDir string, maxBytes int64, protectedPath string) (int, error) {
+	if maxBytes <= 0 {
+		return 0, nil
+	}
+
+	dir := strings.TrimSpace(logDir)
+	if dir == "" {
+		return 0, nil
+	}
+	dir = filepath.Clean(dir)
+
+	entries, errRead := os.ReadDir(dir)
+	if errRead != nil {
+		if os.IsNotExist(errRead) {
+			return 0, nil
+		}
+		return 0, errRead
+	}
+
+	protected := strings.TrimSpace(protectedPath)
+	if protected != "" {
+		protected = filepath.Clean(protected)
+	}
+
+	type logFile struct {
+		path    string
+		size    int64
+		modTime time.Time
+	}
+
+	var (
+		files []logFile
+		total int64
+	)
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		name := entry.Name()
+		if !isLogFileName(name) {
+			continue
+		}
+		info, errInfo := entry.Info()
+		if errInfo != nil {
+			continue
+		}
+		if !info.Mode().IsRegular() {
+			continue
+		}
+		path := filepath.Join(dir, name)
+		files = append(files, logFile{
+			path:    path,
+			size:    info.Size(),
+			modTime: info.ModTime(),
+		})
+		total += info.Size()
+	}
+
+	if total <= maxBytes {
+		return 0, nil
+	}
+
+	sort.Slice(files, func(i, j int) bool {
+		return files[i].modTime.Before(files[j].modTime)
+	})
+
+	deleted := 0
+	for _, file := range files {
+		if total <= maxBytes {
+			break
+		}
+		if protected != "" && filepath.Clean(file.path) == protected {
+			continue
+		}
+		if errRemove := os.Remove(file.path); errRemove != nil {
+			log.WithError(errRemove).Warnf("logging: failed to remove old log file: %s", filepath.Base(file.path))
+			continue
+		}
+		total -= file.size
+		deleted++
+	}
+
+	return deleted, nil
+}
+
+func isLogFileName(name string) bool {
+	trimmed := strings.TrimSpace(name)
+	if trimmed == "" {
+		return false
+	}
+	lower := strings.ToLower(trimmed)
+	return strings.HasSuffix(lower, ".log") || strings.HasSuffix(lower, ".log.gz")
+}

internal/logging/log_dir_cleaner_test.go

@@ -0,0 +1,70 @@
+package logging
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+)
+
+func TestEnforceLogDirSizeLimitDeletesOldest(t *testing.T) {
+	dir := t.TempDir()
+
+	writeLogFile(t, filepath.Join(dir, "old.log"), 60, time.Unix(1, 0))
+	writeLogFile(t, filepath.Join(dir, "mid.log"), 60, time.Unix(2, 0))
+	protected := filepath.Join(dir, "main.log")
+	writeLogFile(t, protected, 60, time.Unix(3, 0))
+
+	deleted, err := enforceLogDirSizeLimit(dir, 120, protected)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("expected 1 deleted file, got %d", deleted)
+	}
+
+	if _, err := os.Stat(filepath.Join(dir, "old.log")); !os.IsNotExist(err) {
+		t.Fatalf("expected old.log to be removed, stat error: %v", err)
+	}
+	if _, err := os.Stat(filepath.Join(dir, "mid.log")); err != nil {
+		t.Fatalf("expected mid.log to remain, stat error: %v", err)
+	}
+	if _, err := os.Stat(protected); err != nil {
+		t.Fatalf("expected protected main.log to remain, stat error: %v", err)
+	}
+}
+
+func TestEnforceLogDirSizeLimitSkipsProtected(t *testing.T) {
+	dir := t.TempDir()
+
+	protected := filepath.Join(dir, "main.log")
+	writeLogFile(t, protected, 200, time.Unix(1, 0))
+	writeLogFile(t, filepath.Join(dir, "other.log"), 50, time.Unix(2, 0))
+
+	deleted, err := enforceLogDirSizeLimit(dir, 100, protected)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("expected 1 deleted file, got %d", deleted)
+	}
+
+	if _, err := os.Stat(protected); err != nil {
+		t.Fatalf("expected protected main.log to remain, stat error: %v", err)
+	}
+	if _, err := os.Stat(filepath.Join(dir, "other.log")); !os.IsNotExist(err) {
+		t.Fatalf("expected other.log to be removed, stat error: %v", err)
+	}
+}
+
+func writeLogFile(t *testing.T, path string, size int, modTime time.Time) {
+	t.Helper()
+
+	data := make([]byte, size)
+	if err := os.WriteFile(path, data, 0o644); err != nil {
+		t.Fatalf("write file: %v", err)
+	}
+	if err := os.Chtimes(path, modTime, modTime); err != nil {
+		t.Fatalf("set times: %v", err)
+	}
+}

internal/logging/request_logger.go

@@ -14,6 +14,7 @@ import (
 	"regexp"
 	"sort"
 	"strings"
+	"sync/atomic"
 	"time"
 
 	"github.com/andybalholm/brotli"
@@ -25,6 +26,8 @@ import (
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 )
 
+var requestLogID atomic.Uint64
+
 // RequestLogger defines the interface for logging HTTP requests and responses.
 // It provides methods for logging both regular and streaming HTTP request/response cycles.
 type RequestLogger interface {
@@ -40,10 +43,11 @@ type RequestLogger interface {
 	//   - response: The raw response data
 	//   - apiRequest: The API request data
 	//   - apiResponse: The API response data
+	//   - requestID: Optional request ID for log file naming
 	//
 	// Returns:
 	//   - error: An error if logging fails, nil otherwise
-	LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage) error
+	LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, requestID string) error
 
 	// LogStreamingRequest initiates logging for a streaming request and returns a writer for chunks.
 	//
@@ -52,11 +56,12 @@ type RequestLogger interface {
 	//   - method: The HTTP method
 	//   - headers: The request headers
 	//   - body: The request body
+	//   - requestID: Optional request ID for log file naming
 	//
 	// Returns:
 	//   - StreamingLogWriter: A writer for streaming response chunks
 	//   - error: An error if logging initialization fails, nil otherwise
-	LogStreamingRequest(url, method string, headers map[string][]string, body []byte) (StreamingLogWriter, error)
+	LogStreamingRequest(url, method string, headers map[string][]string, body []byte, requestID string) (StreamingLogWriter, error)
 
 	// IsEnabled returns whether request logging is currently enabled.
 	//
@@ -174,20 +179,21 @@ func (l *FileRequestLogger) SetEnabled(enabled bool) {
 //   - response: The raw response data
 //   - apiRequest: The API request data
 //   - apiResponse: The API response data
+//   - requestID: Optional request ID for log file naming
 //
 // Returns:
 //   - error: An error if logging fails, nil otherwise
-func (l *FileRequestLogger) LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage) error {
-	return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, false)
+func (l *FileRequestLogger) LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, requestID string) error {
+	return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, false, requestID)
 }
 
 // LogRequestWithOptions logs a request with optional forced logging behavior.
 // The force flag allows writing error logs even when regular request logging is disabled.
-func (l *FileRequestLogger) LogRequestWithOptions(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool) error {
-	return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, force)
+func (l *FileRequestLogger) LogRequestWithOptions(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool, requestID string) error {
+	return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, force, requestID)
 }
 
-func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool) error {
+func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool, requestID string) error {
 	if !l.enabled && !force {
 		return nil
 	}
@@ -197,26 +203,59 @@ func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[st
 		return fmt.Errorf("failed to create logs directory: %w", errEnsure)
 	}
 
-	// Generate filename
-	filename := l.generateFilename(url)
+	// Generate filename with request ID
+	filename := l.generateFilename(url, requestID)
 	if force && !l.enabled {
-		filename = l.generateErrorFilename(url)
+		filename = l.generateErrorFilename(url, requestID)
 	}
 	filePath := filepath.Join(l.logsDir, filename)
 
-	// Decompress response if needed
-	decompressedResponse, err := l.decompressResponse(responseHeaders, response)
-	if err != nil {
-		// If decompression fails, log the error but continue with original response
-		decompressedResponse = append(response, []byte(fmt.Sprintf("\n[DECOMPRESSION ERROR: %v]", err))...)
+	requestBodyPath, errTemp := l.writeRequestBodyTempFile(body)
+	if errTemp != nil {
+		log.WithError(errTemp).Warn("failed to create request body temp file, falling back to direct write")
+	}
+	if requestBodyPath != "" {
+		defer func() {
+			if errRemove := os.Remove(requestBodyPath); errRemove != nil {
+				log.WithError(errRemove).Warn("failed to remove request body temp file")
+			}
+		}()
 	}
 
-	// Create log content
-	content := l.formatLogContent(url, method, requestHeaders, body, apiRequest, apiResponse, decompressedResponse, statusCode, responseHeaders, apiResponseErrors)
+	responseToWrite, decompressErr := l.decompressResponse(responseHeaders, response)
+	if decompressErr != nil {
+		// If decompression fails, continue with original response and annotate the log output.
+		responseToWrite = response
+	}
 
-	// Write to file
-	if err = os.WriteFile(filePath, []byte(content), 0644); err != nil {
-		return fmt.Errorf("failed to write log file: %w", err)
+	logFile, errOpen := os.OpenFile(filePath, os.O_CREATE|os.O_WRONLY|os.O_TRUNC, 0644)
+	if errOpen != nil {
+		return fmt.Errorf("failed to create log file: %w", errOpen)
+	}
+
+	writeErr := l.writeNonStreamingLog(
+		logFile,
+		url,
+		method,
+		requestHeaders,
+		body,
+		requestBodyPath,
+		apiRequest,
+		apiResponse,
+		apiResponseErrors,
+		statusCode,
+		responseHeaders,
+		responseToWrite,
+		decompressErr,
+	)
+	if errClose := logFile.Close(); errClose != nil {
+		log.WithError(errClose).Warn("failed to close request log file")
+		if writeErr == nil {
+			return errClose
+		}
+	}
+	if writeErr != nil {
+		return fmt.Errorf("failed to write log file: %w", writeErr)
 	}
 
 	if force && !l.enabled {
@@ -235,11 +274,12 @@ func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[st
 //   - method: The HTTP method
 //   - headers: The request headers
 //   - body: The request body
+//   - requestID: Optional request ID for log file naming
 //
 // Returns:
 //   - StreamingLogWriter: A writer for streaming response chunks
 //   - error: An error if logging initialization fails, nil otherwise
-func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[string][]string, body []byte) (StreamingLogWriter, error) {
+func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[string][]string, body []byte, requestID string) (StreamingLogWriter, error) {
 	if !l.enabled {
 		return &NoOpStreamingLogWriter{}, nil
 	}
@@ -249,30 +289,42 @@ func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[
 		return nil, fmt.Errorf("failed to create logs directory: %w", err)
 	}
 
-	// Generate filename
-	filename := l.generateFilename(url)
+	// Generate filename with request ID
+	filename := l.generateFilename(url, requestID)
 	filePath := filepath.Join(l.logsDir, filename)
 
-	// Create and open file
-	file, err := os.Create(filePath)
-	if err != nil {
-		return nil, fmt.Errorf("failed to create log file: %w", err)
+	requestHeaders := make(map[string][]string, len(headers))
+	for key, values := range headers {
+		headerValues := make([]string, len(values))
+		copy(headerValues, values)
+		requestHeaders[key] = headerValues
 	}
 
-	// Write initial request information
-	requestInfo := l.formatRequestInfo(url, method, headers, body)
-	if _, err = file.WriteString(requestInfo); err != nil {
-		_ = file.Close()
-		return nil, fmt.Errorf("failed to write request info: %w", err)
+	requestBodyPath, errTemp := l.writeRequestBodyTempFile(body)
+	if errTemp != nil {
+		return nil, fmt.Errorf("failed to create request body temp file: %w", errTemp)
 	}
 
+	responseBodyFile, errCreate := os.CreateTemp(l.logsDir, "response-body-*.tmp")
+	if errCreate != nil {
+		_ = os.Remove(requestBodyPath)
+		return nil, fmt.Errorf("failed to create response body temp file: %w", errCreate)
+	}
+	responseBodyPath := responseBodyFile.Name()
+
 	// Create streaming writer
 	writer := &FileStreamingLogWriter{
-		file:           file,
-		chunkChan:      make(chan []byte, 100), // Buffered channel for async writes
-		closeChan:      make(chan struct{}),
-		errorChan:      make(chan error, 1),
-		bufferedChunks: &bytes.Buffer{},
+		logFilePath:      filePath,
+		url:              url,
+		method:           method,
+		timestamp:        time.Now(),
+		requestHeaders:   requestHeaders,
+		requestBodyPath:  requestBodyPath,
+		responseBodyPath: responseBodyPath,
+		responseBodyFile: responseBodyFile,
+		chunkChan:        make(chan []byte, 100), // Buffered channel for async writes
+		closeChan:        make(chan struct{}),
+		errorChan:        make(chan error, 1),
 	}
 
 	// Start async writer goroutine
@@ -282,8 +334,8 @@ func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[
 }
 
 // generateErrorFilename creates a filename with an error prefix to differentiate forced error logs.
-func (l *FileRequestLogger) generateErrorFilename(url string) string {
-	return fmt.Sprintf("error-%s", l.generateFilename(url))
+func (l *FileRequestLogger) generateErrorFilename(url string, requestID ...string) string {
+	return fmt.Sprintf("error-%s", l.generateFilename(url, requestID...))
 }
 
 // ensureLogsDir creates the logs directory if it doesn't exist.
@@ -298,13 +350,15 @@ func (l *FileRequestLogger) ensureLogsDir() error {
 }
 
 // generateFilename creates a sanitized filename from the URL path and current timestamp.
+// Format: v1-responses-2025-12-23T195811-a1b2c3d4.log
 //
 // Parameters:
 //   - url: The request URL
+//   - requestID: Optional request ID to include in filename
 //
 // Returns:
 //   - string: A sanitized filename for the log file
-func (l *FileRequestLogger) generateFilename(url string) string {
+func (l *FileRequestLogger) generateFilename(url string, requestID ...string) string {
 	// Extract path from URL
 	path := url
 	if strings.Contains(url, "?") {
@@ -320,10 +374,18 @@ func (l *FileRequestLogger) generateFilename(url string) string {
 	sanitized := l.sanitizeForFilename(path)
 
 	// Add timestamp
-	timestamp := time.Now().Format("2006-01-02T150405-.000000000")
-	timestamp = strings.Replace(timestamp, ".", "", -1)
+	timestamp := time.Now().Format("2006-01-02T150405")
 
-	return fmt.Sprintf("%s-%s.log", sanitized, timestamp)
+	// Use request ID if provided, otherwise use sequential ID
+	var idPart string
+	if len(requestID) > 0 && requestID[0] != "" {
+		idPart = requestID[0]
+	} else {
+		id := requestLogID.Add(1)
+		idPart = fmt.Sprintf("%d", id)
+	}
+
+	return fmt.Sprintf("%s-%s-%s.log", sanitized, timestamp, idPart)
 }
 
 // sanitizeForFilename replaces characters that are not safe for filenames.
@@ -405,6 +467,220 @@ func (l *FileRequestLogger) cleanupOldErrorLogs() error {
 	return nil
 }
 
+func (l *FileRequestLogger) writeRequestBodyTempFile(body []byte) (string, error) {
+	tmpFile, errCreate := os.CreateTemp(l.logsDir, "request-body-*.tmp")
+	if errCreate != nil {
+		return "", errCreate
+	}
+	tmpPath := tmpFile.Name()
+
+	if _, errCopy := io.Copy(tmpFile, bytes.NewReader(body)); errCopy != nil {
+		_ = tmpFile.Close()
+		_ = os.Remove(tmpPath)
+		return "", errCopy
+	}
+	if errClose := tmpFile.Close(); errClose != nil {
+		_ = os.Remove(tmpPath)
+		return "", errClose
+	}
+	return tmpPath, nil
+}
+
+func (l *FileRequestLogger) writeNonStreamingLog(
+	w io.Writer,
+	url, method string,
+	requestHeaders map[string][]string,
+	requestBody []byte,
+	requestBodyPath string,
+	apiRequest []byte,
+	apiResponse []byte,
+	apiResponseErrors []*interfaces.ErrorMessage,
+	statusCode int,
+	responseHeaders map[string][]string,
+	response []byte,
+	decompressErr error,
+) error {
+	if errWrite := writeRequestInfoWithBody(w, url, method, requestHeaders, requestBody, requestBodyPath, time.Now()); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(w, "=== API REQUEST ===\n", "=== API REQUEST", apiRequest); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPIErrorResponses(w, apiResponseErrors); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(w, "=== API RESPONSE ===\n", "=== API RESPONSE", apiResponse); errWrite != nil {
+		return errWrite
+	}
+	return writeResponseSection(w, statusCode, true, responseHeaders, bytes.NewReader(response), decompressErr, true)
+}
+
+func writeRequestInfoWithBody(
+	w io.Writer,
+	url, method string,
+	headers map[string][]string,
+	body []byte,
+	bodyPath string,
+	timestamp time.Time,
+) error {
+	if _, errWrite := io.WriteString(w, "=== REQUEST INFO ===\n"); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("Version: %s\n", buildinfo.Version)); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("URL: %s\n", url)); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("Method: %s\n", method)); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, fmt.Sprintf("Timestamp: %s\n", timestamp.Format(time.RFC3339Nano))); errWrite != nil {
+		return errWrite
+	}
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if _, errWrite := io.WriteString(w, "=== HEADERS ===\n"); errWrite != nil {
+		return errWrite
+	}
+	for key, values := range headers {
+		for _, value := range values {
+			masked := util.MaskSensitiveHeaderValue(key, value)
+			if _, errWrite := io.WriteString(w, fmt.Sprintf("%s: %s\n", key, masked)); errWrite != nil {
+				return errWrite
+			}
+		}
+	}
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if _, errWrite := io.WriteString(w, "=== REQUEST BODY ===\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if bodyPath != "" {
+		bodyFile, errOpen := os.Open(bodyPath)
+		if errOpen != nil {
+			return errOpen
+		}
+		if _, errCopy := io.Copy(w, bodyFile); errCopy != nil {
+			_ = bodyFile.Close()
+			return errCopy
+		}
+		if errClose := bodyFile.Close(); errClose != nil {
+			log.WithError(errClose).Warn("failed to close request body temp file")
+		}
+	} else if _, errWrite := w.Write(body); errWrite != nil {
+		return errWrite
+	}
+
+	if _, errWrite := io.WriteString(w, "\n\n"); errWrite != nil {
+		return errWrite
+	}
+	return nil
+}
+
+func writeAPISection(w io.Writer, sectionHeader string, sectionPrefix string, payload []byte) error {
+	if len(payload) == 0 {
+		return nil
+	}
+
+	if bytes.HasPrefix(payload, []byte(sectionPrefix)) {
+		if _, errWrite := w.Write(payload); errWrite != nil {
+			return errWrite
+		}
+		if !bytes.HasSuffix(payload, []byte("\n")) {
+			if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+				return errWrite
+			}
+		}
+	} else {
+		if _, errWrite := io.WriteString(w, sectionHeader); errWrite != nil {
+			return errWrite
+		}
+		if _, errWrite := w.Write(payload); errWrite != nil {
+			return errWrite
+		}
+		if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+			return errWrite
+		}
+	}
+
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+	return nil
+}
+
+func writeAPIErrorResponses(w io.Writer, apiResponseErrors []*interfaces.ErrorMessage) error {
+	for i := 0; i < len(apiResponseErrors); i++ {
+		if apiResponseErrors[i] == nil {
+			continue
+		}
+		if _, errWrite := io.WriteString(w, "=== API ERROR RESPONSE ===\n"); errWrite != nil {
+			return errWrite
+		}
+		if _, errWrite := io.WriteString(w, fmt.Sprintf("HTTP Status: %d\n", apiResponseErrors[i].StatusCode)); errWrite != nil {
+			return errWrite
+		}
+		if apiResponseErrors[i].Error != nil {
+			if _, errWrite := io.WriteString(w, apiResponseErrors[i].Error.Error()); errWrite != nil {
+				return errWrite
+			}
+		}
+		if _, errWrite := io.WriteString(w, "\n\n"); errWrite != nil {
+			return errWrite
+		}
+	}
+	return nil
+}
+
+func writeResponseSection(w io.Writer, statusCode int, statusWritten bool, responseHeaders map[string][]string, responseReader io.Reader, decompressErr error, trailingNewline bool) error {
+	if _, errWrite := io.WriteString(w, "=== RESPONSE ===\n"); errWrite != nil {
+		return errWrite
+	}
+	if statusWritten {
+		if _, errWrite := io.WriteString(w, fmt.Sprintf("Status: %d\n", statusCode)); errWrite != nil {
+			return errWrite
+		}
+	}
+
+	if responseHeaders != nil {
+		for key, values := range responseHeaders {
+			for _, value := range values {
+				if _, errWrite := io.WriteString(w, fmt.Sprintf("%s: %s\n", key, value)); errWrite != nil {
+					return errWrite
+				}
+			}
+		}
+	}
+
+	if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+		return errWrite
+	}
+
+	if responseReader != nil {
+		if _, errCopy := io.Copy(w, responseReader); errCopy != nil {
+			return errCopy
+		}
+	}
+	if decompressErr != nil {
+		if _, errWrite := io.WriteString(w, fmt.Sprintf("\n[DECOMPRESSION ERROR: %v]", decompressErr)); errWrite != nil {
+			return errWrite
+		}
+	}
+
+	if trailingNewline {
+		if _, errWrite := io.WriteString(w, "\n"); errWrite != nil {
+			return errWrite
+		}
+	}
+	return nil
+}
+
 // formatLogContent creates the complete log content for non-streaming requests.
 //
 // Parameters:
@@ -648,13 +924,34 @@ func (l *FileRequestLogger) formatRequestInfo(url, method string, headers map[st
 }
 
 // FileStreamingLogWriter implements StreamingLogWriter for file-based streaming logs.
-// It handles asynchronous writing of streaming response chunks to a file.
-// All data is buffered and written in the correct order when Close is called.
+// It spools streaming response chunks to a temporary file to avoid retaining large responses in memory.
+// The final log file is assembled when Close is called.
 type FileStreamingLogWriter struct {
-	// file is the file where log data is written.
-	file *os.File
+	// logFilePath is the final log file path.
+	logFilePath string
 
-	// chunkChan is a channel for receiving response chunks to buffer.
+	// url is the request URL (masked upstream in middleware).
+	url string
+
+	// method is the HTTP method.
+	method string
+
+	// timestamp is captured when the streaming log is initialized.
+	timestamp time.Time
+
+	// requestHeaders stores the request headers.
+	requestHeaders map[string][]string
+
+	// requestBodyPath is a temporary file path holding the request body.
+	requestBodyPath string
+
+	// responseBodyPath is a temporary file path holding the streaming response body.
+	responseBodyPath string
+
+	// responseBodyFile is the temp file where chunks are appended by the async writer.
+	responseBodyFile *os.File
+
+	// chunkChan is a channel for receiving response chunks to spool.
 	chunkChan chan []byte
 
 	// closeChan is a channel for signaling when the writer is closed.
@@ -663,9 +960,6 @@ type FileStreamingLogWriter struct {
 	// errorChan is a channel for reporting errors during writing.
 	errorChan chan error
 
-	// bufferedChunks stores the response chunks in order.
-	bufferedChunks *bytes.Buffer
-
 	// responseStatus stores the HTTP status code.
 	responseStatus int
 
@@ -770,85 +1064,115 @@ func (w *FileStreamingLogWriter) Close() error {
 		close(w.chunkChan)
 	}
 
-	// Wait for async writer to finish buffering chunks
+	// Wait for async writer to finish spooling chunks
 	if w.closeChan != nil {
 		<-w.closeChan
 		w.chunkChan = nil
 	}
 
-	if w.file == nil {
+	select {
+	case errWrite := <-w.errorChan:
+		w.cleanupTempFiles()
+		return errWrite
+	default:
+	}
+
+	if w.logFilePath == "" {
+		w.cleanupTempFiles()
 		return nil
 	}
 
-	// Write all content in the correct order
-	var content strings.Builder
-
-	// 1. Write API REQUEST section
-	if len(w.apiRequest) > 0 {
-		if bytes.HasPrefix(w.apiRequest, []byte("=== API REQUEST")) {
-			content.Write(w.apiRequest)
-			if !bytes.HasSuffix(w.apiRequest, []byte("\n")) {
-				content.WriteString("\n")
-			}
-		} else {
-			content.WriteString("=== API REQUEST ===\n")
-			content.Write(w.apiRequest)
-			content.WriteString("\n")
-		}
-		content.WriteString("\n")
+	logFile, errOpen := os.OpenFile(w.logFilePath, os.O_CREATE|os.O_WRONLY|os.O_TRUNC, 0644)
+	if errOpen != nil {
+		w.cleanupTempFiles()
+		return fmt.Errorf("failed to create log file: %w", errOpen)
 	}
 
-	// 2. Write API RESPONSE section
-	if len(w.apiResponse) > 0 {
-		if bytes.HasPrefix(w.apiResponse, []byte("=== API RESPONSE")) {
-			content.Write(w.apiResponse)
-			if !bytes.HasSuffix(w.apiResponse, []byte("\n")) {
-				content.WriteString("\n")
-			}
-		} else {
-			content.WriteString("=== API RESPONSE ===\n")
-			content.Write(w.apiResponse)
-			content.WriteString("\n")
-		}
-		content.WriteString("\n")
-	}
-
-	// 3. Write RESPONSE section (status, headers, buffered chunks)
-	content.WriteString("=== RESPONSE ===\n")
-	if w.statusWritten {
-		content.WriteString(fmt.Sprintf("Status: %d\n", w.responseStatus))
-	}
-
-	for key, values := range w.responseHeaders {
-		for _, value := range values {
-			content.WriteString(fmt.Sprintf("%s: %s\n", key, value))
+	writeErr := w.writeFinalLog(logFile)
+	if errClose := logFile.Close(); errClose != nil {
+		log.WithError(errClose).Warn("failed to close request log file")
+		if writeErr == nil {
+			writeErr = errClose
 		}
 	}
-	content.WriteString("\n")
 
-	// Write buffered response body chunks
-	if w.bufferedChunks != nil && w.bufferedChunks.Len() > 0 {
-		content.Write(w.bufferedChunks.Bytes())
-	}
-
-	// Write the complete content to file
-	if _, err := w.file.WriteString(content.String()); err != nil {
-		_ = w.file.Close()
-		return err
-	}
-
-	return w.file.Close()
+	w.cleanupTempFiles()
+	return writeErr
 }
 
 // asyncWriter runs in a goroutine to buffer chunks from the channel.
-// It continuously reads chunks from the channel and buffers them for later writing.
+// It continuously reads chunks from the channel and appends them to a temp file for later assembly.
 func (w *FileStreamingLogWriter) asyncWriter() {
 	defer close(w.closeChan)
 
 	for chunk := range w.chunkChan {
-		if w.bufferedChunks != nil {
-			w.bufferedChunks.Write(chunk)
+		if w.responseBodyFile == nil {
+			continue
 		}
+		if _, errWrite := w.responseBodyFile.Write(chunk); errWrite != nil {
+			select {
+			case w.errorChan <- errWrite:
+			default:
+			}
+			if errClose := w.responseBodyFile.Close(); errClose != nil {
+				select {
+				case w.errorChan <- errClose:
+				default:
+				}
+			}
+			w.responseBodyFile = nil
+		}
+	}
+
+	if w.responseBodyFile == nil {
+		return
+	}
+	if errClose := w.responseBodyFile.Close(); errClose != nil {
+		select {
+		case w.errorChan <- errClose:
+		default:
+		}
+	}
+	w.responseBodyFile = nil
+}
+
+func (w *FileStreamingLogWriter) writeFinalLog(logFile *os.File) error {
+	if errWrite := writeRequestInfoWithBody(logFile, w.url, w.method, w.requestHeaders, nil, w.requestBodyPath, w.timestamp); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(logFile, "=== API REQUEST ===\n", "=== API REQUEST", w.apiRequest); errWrite != nil {
+		return errWrite
+	}
+	if errWrite := writeAPISection(logFile, "=== API RESPONSE ===\n", "=== API RESPONSE", w.apiResponse); errWrite != nil {
+		return errWrite
+	}
+
+	responseBodyFile, errOpen := os.Open(w.responseBodyPath)
+	if errOpen != nil {
+		return errOpen
+	}
+	defer func() {
+		if errClose := responseBodyFile.Close(); errClose != nil {
+			log.WithError(errClose).Warn("failed to close response body temp file")
+		}
+	}()
+
+	return writeResponseSection(logFile, w.responseStatus, w.statusWritten, w.responseHeaders, responseBodyFile, nil, false)
+}
+
+func (w *FileStreamingLogWriter) cleanupTempFiles() {
+	if w.requestBodyPath != "" {
+		if errRemove := os.Remove(w.requestBodyPath); errRemove != nil {
+			log.WithError(errRemove).Warn("failed to remove request body temp file")
+		}
+		w.requestBodyPath = ""
+	}
+
+	if w.responseBodyPath != "" {
+		if errRemove := os.Remove(w.responseBodyPath); errRemove != nil {
+			log.WithError(errRemove).Warn("failed to remove response body temp file")
+		}
+		w.responseBodyPath = ""
 	}
 }
 

internal/logging/requestid.go

@@ -0,0 +1,61 @@
+package logging
+
+import (
+	"context"
+	"crypto/rand"
+	"encoding/hex"
+
+	"github.com/gin-gonic/gin"
+)
+
+// requestIDKey is the context key for storing/retrieving request IDs.
+type requestIDKey struct{}
+
+// ginRequestIDKey is the Gin context key for request IDs.
+const ginRequestIDKey = "__request_id__"
+
+// GenerateRequestID creates a new 8-character hex request ID.
+func GenerateRequestID() string {
+	b := make([]byte, 4)
+	if _, err := rand.Read(b); err != nil {
+		return "00000000"
+	}
+	return hex.EncodeToString(b)
+}
+
+// WithRequestID returns a new context with the request ID attached.
+func WithRequestID(ctx context.Context, requestID string) context.Context {
+	return context.WithValue(ctx, requestIDKey{}, requestID)
+}
+
+// GetRequestID retrieves the request ID from the context.
+// Returns empty string if not found.
+func GetRequestID(ctx context.Context) string {
+	if ctx == nil {
+		return ""
+	}
+	if id, ok := ctx.Value(requestIDKey{}).(string); ok {
+		return id
+	}
+	return ""
+}
+
+// SetGinRequestID stores the request ID in the Gin context.
+func SetGinRequestID(c *gin.Context, requestID string) {
+	if c != nil {
+		c.Set(ginRequestIDKey, requestID)
+	}
+}
+
+// GetGinRequestID retrieves the request ID from the Gin context.
+func GetGinRequestID(c *gin.Context) string {
+	if c == nil {
+		return ""
+	}
+	if id, exists := c.Get(ginRequestIDKey); exists {
+		if s, ok := id.(string); ok {
+			return s
+		}
+	}
+	return ""
+}

internal/managementasset/updater.go

@@ -24,10 +24,11 @@ import (
 )
 
 const (
-	defaultManagementReleaseURL = "https://api.github.com/repos/router-for-me/Cli-Proxy-API-Management-Center/releases/latest"
-	managementAssetName         = "management.html"
-	httpUserAgent               = "CLIProxyAPI-management-updater"
-	updateCheckInterval         = 3 * time.Hour
+	defaultManagementReleaseURL  = "https://api.github.com/repos/router-for-me/Cli-Proxy-API-Management-Center/releases/latest"
+	defaultManagementFallbackURL = "https://cpamc.router-for.me/"
+	managementAssetName          = "management.html"
+	httpUserAgent                = "CLIProxyAPI-management-updater"
+	updateCheckInterval          = 3 * time.Hour
 )
 
 // ManagementFileName exposes the control panel asset filename.
@@ -198,6 +199,16 @@ func EnsureLatestManagementHTML(ctx context.Context, staticDir string, proxyURL
 		return
 	}
 
+	localPath := filepath.Join(staticDir, managementAssetName)
+	localFileMissing := false
+	if _, errStat := os.Stat(localPath); errStat != nil {
+		if errors.Is(errStat, os.ErrNotExist) {
+			localFileMissing = true
+		} else {
+			log.WithError(errStat).Debug("failed to stat local management asset")
+		}
+	}
+
 	// Rate limiting: check only once every 3 hours
 	lastUpdateCheckMu.Lock()
 	now := time.Now()
@@ -210,15 +221,14 @@ func EnsureLatestManagementHTML(ctx context.Context, staticDir string, proxyURL
 	lastUpdateCheckTime = now
 	lastUpdateCheckMu.Unlock()
 
-	if err := os.MkdirAll(staticDir, 0o755); err != nil {
-		log.WithError(err).Warn("failed to prepare static directory for management asset")
+	if errMkdirAll := os.MkdirAll(staticDir, 0o755); errMkdirAll != nil {
+		log.WithError(errMkdirAll).Warn("failed to prepare static directory for management asset")
 		return
 	}
 
 	releaseURL := resolveReleaseURL(panelRepository)
 	client := newHTTPClient(proxyURL)
 
-	localPath := filepath.Join(staticDir, managementAssetName)
 	localHash, err := fileSHA256(localPath)
 	if err != nil {
 		if !errors.Is(err, os.ErrNotExist) {
@@ -229,6 +239,13 @@ func EnsureLatestManagementHTML(ctx context.Context, staticDir string, proxyURL
 
 	asset, remoteHash, err := fetchLatestAsset(ctx, client, releaseURL)
 	if err != nil {
+		if localFileMissing {
+			log.WithError(err).Warn("failed to fetch latest management release information, trying fallback page")
+			if ensureFallbackManagementHTML(ctx, client, localPath) {
+				return
+			}
+			return
+		}
 		log.WithError(err).Warn("failed to fetch latest management release information")
 		return
 	}
@@ -240,6 +257,13 @@ func EnsureLatestManagementHTML(ctx context.Context, staticDir string, proxyURL
 
 	data, downloadedHash, err := downloadAsset(ctx, client, asset.BrowserDownloadURL)
 	if err != nil {
+		if localFileMissing {
+			log.WithError(err).Warn("failed to download management asset, trying fallback page")
+			if ensureFallbackManagementHTML(ctx, client, localPath) {
+				return
+			}
+			return
+		}
 		log.WithError(err).Warn("failed to download management asset")
 		return
 	}
@@ -256,6 +280,22 @@ func EnsureLatestManagementHTML(ctx context.Context, staticDir string, proxyURL
 	log.Infof("management asset updated successfully (hash=%s)", downloadedHash)
 }
 
+func ensureFallbackManagementHTML(ctx context.Context, client *http.Client, localPath string) bool {
+	data, downloadedHash, err := downloadAsset(ctx, client, defaultManagementFallbackURL)
+	if err != nil {
+		log.WithError(err).Warn("failed to download fallback management control panel page")
+		return false
+	}
+
+	if err = atomicWriteFile(localPath, data); err != nil {
+		log.WithError(err).Warn("failed to persist fallback management control panel page")
+		return false
+	}
+
+	log.Infof("management asset updated from fallback page successfully (hash=%s)", downloadedHash)
+	return true
+}
+
 func resolveReleaseURL(repo string) string {
 	repo = strings.TrimSpace(repo)
 	if repo == "" {

internal/misc/oauth.go

@@ -4,6 +4,8 @@ import (
 	"crypto/rand"
 	"encoding/hex"
 	"fmt"
+	"net/url"
+	"strings"
 )
 
 // GenerateRandomState generates a cryptographically secure random state parameter
@@ -19,3 +21,83 @@ func GenerateRandomState() (string, error) {
 	}
 	return hex.EncodeToString(bytes), nil
 }
+
+// OAuthCallback captures the parsed OAuth callback parameters.
+type OAuthCallback struct {
+	Code             string
+	State            string
+	Error            string
+	ErrorDescription string
+}
+
+// ParseOAuthCallback extracts OAuth parameters from a callback URL.
+// It returns nil when the input is empty.
+func ParseOAuthCallback(input string) (*OAuthCallback, error) {
+	trimmed := strings.TrimSpace(input)
+	if trimmed == "" {
+		return nil, nil
+	}
+
+	candidate := trimmed
+	if !strings.Contains(candidate, "://") {
+		if strings.HasPrefix(candidate, "?") {
+			candidate = "http://localhost" + candidate
+		} else if strings.ContainsAny(candidate, "/?#") || strings.Contains(candidate, ":") {
+			candidate = "http://" + candidate
+		} else if strings.Contains(candidate, "=") {
+			candidate = "http://localhost/?" + candidate
+		} else {
+			return nil, fmt.Errorf("invalid callback URL")
+		}
+	}
+
+	parsedURL, err := url.Parse(candidate)
+	if err != nil {
+		return nil, err
+	}
+
+	query := parsedURL.Query()
+	code := strings.TrimSpace(query.Get("code"))
+	state := strings.TrimSpace(query.Get("state"))
+	errCode := strings.TrimSpace(query.Get("error"))
+	errDesc := strings.TrimSpace(query.Get("error_description"))
+
+	if parsedURL.Fragment != "" {
+		if fragQuery, errFrag := url.ParseQuery(parsedURL.Fragment); errFrag == nil {
+			if code == "" {
+				code = strings.TrimSpace(fragQuery.Get("code"))
+			}
+			if state == "" {
+				state = strings.TrimSpace(fragQuery.Get("state"))
+			}
+			if errCode == "" {
+				errCode = strings.TrimSpace(fragQuery.Get("error"))
+			}
+			if errDesc == "" {
+				errDesc = strings.TrimSpace(fragQuery.Get("error_description"))
+			}
+		}
+	}
+
+	if code != "" && state == "" && strings.Contains(code, "#") {
+		parts := strings.SplitN(code, "#", 2)
+		code = parts[0]
+		state = parts[1]
+	}
+
+	if errCode == "" && errDesc != "" {
+		errCode = errDesc
+		errDesc = ""
+	}
+
+	if code == "" && errCode == "" {
+		return nil, fmt.Errorf("callback URL missing code")
+	}
+
+	return &OAuthCallback{
+		Code:             code,
+		State:            state,
+		Error:            errCode,
+		ErrorDescription: errDesc,
+	}, nil
+}

internal/registry/model_definitions.go

@@ -162,6 +162,21 @@ func GetGeminiModels() []*ModelInfo {
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
 			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}},
 		},
+		{
+			ID:                         "gemini-3-flash-preview",
+			Object:                     "model",
+			Created:                    1765929600,
+			OwnedBy:                    "google",
+			Type:                       "gemini",
+			Name:                       "models/gemini-3-flash-preview",
+			Version:                    "3.0",
+			DisplayName:                "Gemini 3 Flash Preview",
+			Description:                "Gemini 3 Flash Preview",
+			InputTokenLimit:            1048576,
+			OutputTokenLimit:           65536,
+			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}},
+		},
 		{
 			ID:                         "gemini-3-pro-image-preview",
 			Object:                     "model",
@@ -712,6 +727,7 @@ func GetIFlowModels() []*ModelInfo {
 		{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build", Created: 1757030400},
 		{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905", Created: 1757030400},
 		{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400, Thinking: iFlowThinkingSupport},
+		{ID: "glm-4.7", DisplayName: "GLM-4.7", Description: "Zhipu GLM 4.7 general model", Created: 1766448000, Thinking: iFlowThinkingSupport},
 		{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model", Created: 1752192000},
 		{ID: "kimi-k2-thinking", DisplayName: "Kimi-K2-Thinking", Description: "Moonshot Kimi K2 thinking model", Created: 1762387200},
 		{ID: "deepseek-v3.2-chat", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2 Chat", Created: 1764576000},
@@ -724,7 +740,8 @@ func GetIFlowModels() []*ModelInfo {
 		{ID: "qwen3-235b-a22b-thinking-2507", DisplayName: "Qwen3-235B-A22B-Thinking", Description: "Qwen3 235B A22B Thinking (2507)", Created: 1753401600},
 		{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
 		{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
-		{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000},
+		{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000, Thinking: iFlowThinkingSupport},
+		{ID: "minimax-m2.1", DisplayName: "MiniMax-M2.1", Description: "MiniMax M2.1", Created: 1766448000, Thinking: iFlowThinkingSupport},
 	}
 	models := make([]*ModelInfo, 0, len(entries))
 	for _, entry := range entries {
@@ -756,7 +773,7 @@ func GetAntigravityModelConfig() map[string]*AntigravityModelConfig {
 	return map[string]*AntigravityModelConfig{
 		"gemini-2.5-flash":                        {Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, Name: "models/gemini-2.5-flash"},
 		"gemini-2.5-flash-lite":                   {Thinking: &ThinkingSupport{Min: 0, Max: 24576, ZeroAllowed: true, DynamicAllowed: true}, Name: "models/gemini-2.5-flash-lite"},
-		"gemini-2.5-computer-use-preview-10-2025": {Name: "models/gemini-2.5-computer-use-preview-10-2025"},
+		"gemini-2.5-computer-use-preview-10-2025": {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true}, Name: "models/gemini-2.5-computer-use-preview-10-2025"},
 		"gemini-3-pro-preview":                    {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}}, Name: "models/gemini-3-pro-preview"},
 		"gemini-3-pro-image-preview":              {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"low", "high"}}, Name: "models/gemini-3-pro-image-preview"},
 		"gemini-3-flash-preview":                  {Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true, Levels: []string{"minimal", "low", "medium", "high"}}, Name: "models/gemini-3-flash-preview"},
@@ -764,3 +781,29 @@ func GetAntigravityModelConfig() map[string]*AntigravityModelConfig {
 		"gemini-claude-opus-4-5-thinking":         {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000},
 	}
 }
+
+// LookupStaticModelInfo searches all static model definitions for a model by ID.
+// Returns nil if no matching model is found.
+func LookupStaticModelInfo(modelID string) *ModelInfo {
+	if modelID == "" {
+		return nil
+	}
+	allModels := [][]*ModelInfo{
+		GetClaudeModels(),
+		GetGeminiModels(),
+		GetGeminiVertexModels(),
+		GetGeminiCLIModels(),
+		GetAIStudioModels(),
+		GetOpenAIModels(),
+		GetQwenModels(),
+		GetIFlowModels(),
+	}
+	for _, models := range allModels {
+		for _, m := range models {
+			if m != nil && m.ID == modelID {
+				return m
+			}
+		}
+	}
+	return nil
+}

internal/registry/model_registry.go

@@ -625,6 +625,131 @@ func (r *ModelRegistry) GetAvailableModels(handlerType string) []map[string]any
 	return models
 }
 
+// GetAvailableModelsByProvider returns models available for the given provider identifier.
+// Parameters:
+//   - provider: Provider identifier (e.g., "codex", "gemini", "antigravity")
+//
+// Returns:
+//   - []*ModelInfo: List of available models for the provider
+func (r *ModelRegistry) GetAvailableModelsByProvider(provider string) []*ModelInfo {
+	provider = strings.ToLower(strings.TrimSpace(provider))
+	if provider == "" {
+		return nil
+	}
+
+	r.mutex.RLock()
+	defer r.mutex.RUnlock()
+
+	type providerModel struct {
+		count int
+		info  *ModelInfo
+	}
+
+	providerModels := make(map[string]*providerModel)
+
+	for clientID, clientProvider := range r.clientProviders {
+		if clientProvider != provider {
+			continue
+		}
+		modelIDs := r.clientModels[clientID]
+		if len(modelIDs) == 0 {
+			continue
+		}
+		clientInfos := r.clientModelInfos[clientID]
+		for _, modelID := range modelIDs {
+			modelID = strings.TrimSpace(modelID)
+			if modelID == "" {
+				continue
+			}
+			entry := providerModels[modelID]
+			if entry == nil {
+				entry = &providerModel{}
+				providerModels[modelID] = entry
+			}
+			entry.count++
+			if entry.info == nil {
+				if clientInfos != nil {
+					if info := clientInfos[modelID]; info != nil {
+						entry.info = info
+					}
+				}
+				if entry.info == nil {
+					if reg, ok := r.models[modelID]; ok && reg != nil && reg.Info != nil {
+						entry.info = reg.Info
+					}
+				}
+			}
+		}
+	}
+
+	if len(providerModels) == 0 {
+		return nil
+	}
+
+	quotaExpiredDuration := 5 * time.Minute
+	now := time.Now()
+	result := make([]*ModelInfo, 0, len(providerModels))
+
+	for modelID, entry := range providerModels {
+		if entry == nil || entry.count <= 0 {
+			continue
+		}
+		registration, ok := r.models[modelID]
+
+		expiredClients := 0
+		cooldownSuspended := 0
+		otherSuspended := 0
+		if ok && registration != nil {
+			if registration.QuotaExceededClients != nil {
+				for clientID, quotaTime := range registration.QuotaExceededClients {
+					if clientID == "" {
+						continue
+					}
+					if p, okProvider := r.clientProviders[clientID]; !okProvider || p != provider {
+						continue
+					}
+					if quotaTime != nil && now.Sub(*quotaTime) < quotaExpiredDuration {
+						expiredClients++
+					}
+				}
+			}
+			if registration.SuspendedClients != nil {
+				for clientID, reason := range registration.SuspendedClients {
+					if clientID == "" {
+						continue
+					}
+					if p, okProvider := r.clientProviders[clientID]; !okProvider || p != provider {
+						continue
+					}
+					if strings.EqualFold(reason, "quota") {
+						cooldownSuspended++
+						continue
+					}
+					otherSuspended++
+				}
+			}
+		}
+
+		availableClients := entry.count
+		effectiveClients := availableClients - expiredClients - otherSuspended
+		if effectiveClients < 0 {
+			effectiveClients = 0
+		}
+
+		if effectiveClients > 0 || (availableClients > 0 && (expiredClients > 0 || cooldownSuspended > 0) && otherSuspended == 0) {
+			if entry.info != nil {
+				result = append(result, entry.info)
+				continue
+			}
+			if ok && registration != nil && registration.Info != nil {
+				result = append(result, registration.Info)
+			}
+		}
+	}
+
+	return result
+}
+
 // GetModelCount returns the number of available clients for a specific model
 // Parameters:
 //   - modelID: The model ID to check

internal/runtime/executor/aistudio_executor.go

@@ -59,6 +59,7 @@ func (e *AIStudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth,
 	if err != nil {
 		return resp, err
 	}
+
 	endpoint := e.buildEndpoint(req.Model, body.action, opts.Alt)
 	wsReq := &wsrelay.HTTPRequest{
 		Method:  http.MethodPost,
@@ -113,6 +114,7 @@ func (e *AIStudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
 	if err != nil {
 		return nil, err
 	}
+
 	endpoint := e.buildEndpoint(req.Model, body.action, opts.Alt)
 	wsReq := &wsrelay.HTTPRequest{
 		Method:  http.MethodPost,

internal/runtime/executor/antigravity_executor.go

@@ -7,6 +7,8 @@ import (
 	"bufio"
 	"bytes"
 	"context"
+	"crypto/sha256"
+	"encoding/binary"
 	"encoding/json"
 	"fmt"
 	"io"
@@ -15,6 +17,7 @@ import (
 	"net/url"
 	"strconv"
 	"strings"
+	"sync"
 	"time"
 
 	"github.com/google/uuid"
@@ -30,21 +33,24 @@ import (
 )
 
 const (
-	antigravityBaseURLDaily = "https://daily-cloudcode-pa.sandbox.googleapis.com"
-	// antigravityBaseURLAutopush     = "https://autopush-cloudcode-pa.sandbox.googleapis.com"
-	antigravityBaseURLProd     = "https://cloudcode-pa.googleapis.com"
-	antigravityCountTokensPath = "/v1internal:countTokens"
-	antigravityStreamPath      = "/v1internal:streamGenerateContent"
-	antigravityGeneratePath    = "/v1internal:generateContent"
-	antigravityModelsPath      = "/v1internal:fetchAvailableModels"
-	antigravityClientID        = "1071006060591-tmhssin2h21lcre235vtolojh4g403ep.apps.googleusercontent.com"
-	antigravityClientSecret    = "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"
-	defaultAntigravityAgent    = "antigravity/1.11.5 windows/amd64"
-	antigravityAuthType        = "antigravity"
-	refreshSkew                = 3000 * time.Second
+	antigravityBaseURLDaily        = "https://daily-cloudcode-pa.googleapis.com"
+	antigravitySandboxBaseURLDaily = "https://daily-cloudcode-pa.sandbox.googleapis.com"
+	antigravityBaseURLProd         = "https://cloudcode-pa.googleapis.com"
+	antigravityCountTokensPath     = "/v1internal:countTokens"
+	antigravityStreamPath          = "/v1internal:streamGenerateContent"
+	antigravityGeneratePath        = "/v1internal:generateContent"
+	antigravityModelsPath          = "/v1internal:fetchAvailableModels"
+	antigravityClientID            = "1071006060591-tmhssin2h21lcre235vtolojh4g403ep.apps.googleusercontent.com"
+	antigravityClientSecret        = "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"
+	defaultAntigravityAgent        = "antigravity/1.104.0 darwin/arm64"
+	antigravityAuthType            = "antigravity"
+	refreshSkew                    = 3000 * time.Second
 )
 
-var randSource = rand.New(rand.NewSource(time.Now().UnixNano()))
+var (
+	randSource      = rand.New(rand.NewSource(time.Now().UnixNano()))
+	randSourceMutex sync.Mutex
+)
 
 // AntigravityExecutor proxies requests to the antigravity upstream.
 type AntigravityExecutor struct {
@@ -70,7 +76,8 @@ func (e *AntigravityExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Au
 
 // Execute performs a non-streaming request to the Antigravity API.
 func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
-	if strings.Contains(req.Model, "claude") {
+	isClaude := strings.Contains(strings.ToLower(req.Model), "claude")
+	if isClaude {
 		return e.executeClaudeNonStream(ctx, auth, req, opts)
 	}
 
@@ -89,10 +96,11 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
 	to := sdktranslator.FromString("antigravity")
 	translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
 
-	translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
+	translated = ApplyThinkingMetadataCLI(translated, req.Metadata, req.Model)
 	translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
-	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
-	translated = normalizeAntigravityThinking(req.Model, translated)
+	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, translated)
+	translated = normalizeAntigravityThinking(req.Model, translated, isClaude)
+	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
 
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
@@ -183,10 +191,11 @@ func (e *AntigravityExecutor) executeClaudeNonStream(ctx context.Context, auth *
 	to := sdktranslator.FromString("antigravity")
 	translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
+	translated = ApplyThinkingMetadataCLI(translated, req.Metadata, req.Model)
 	translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
-	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
-	translated = normalizeAntigravityThinking(req.Model, translated)
+	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, translated)
+	translated = normalizeAntigravityThinking(req.Model, translated, true)
+	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
 
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
@@ -512,14 +521,17 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
+	isClaude := strings.Contains(strings.ToLower(req.Model), "claude")
+
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("antigravity")
 	translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
-	translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
+	translated = ApplyThinkingMetadataCLI(translated, req.Metadata, req.Model)
 	translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
-	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
-	translated = normalizeAntigravityThinking(req.Model, translated)
+	translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, translated)
+	translated = normalizeAntigravityThinking(req.Model, translated, isClaude)
+	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
 
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
@@ -667,6 +679,8 @@ func (e *AntigravityExecutor) CountTokens(ctx context.Context, auth *cliproxyaut
 	to := sdktranslator.FromString("antigravity")
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 
+	isClaude := strings.Contains(strings.ToLower(req.Model), "claude")
+
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
@@ -683,9 +697,9 @@ func (e *AntigravityExecutor) CountTokens(ctx context.Context, auth *cliproxyaut
 
 	for idx, baseURL := range baseURLs {
 		payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-		payload = applyThinkingMetadataCLI(payload, req.Metadata, req.Model)
-		payload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, payload)
-		payload = normalizeAntigravityThinking(req.Model, payload)
+		payload = ApplyThinkingMetadataCLI(payload, req.Metadata, req.Model)
+		payload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, payload)
+		payload = normalizeAntigravityThinking(req.Model, payload, isClaude)
 		payload = deleteJSONField(payload, "project")
 		payload = deleteJSONField(payload, "model")
 		payload = deleteJSONField(payload, "request.safetySettings")
@@ -1007,7 +1021,7 @@ func (e *AntigravityExecutor) buildRequest(ctx context.Context, auth *cliproxyau
 
 		// Use the centralized schema cleaner to handle unsupported keywords,
 		// const->enum conversion, and flattening of types/anyOf.
-		strJSON = util.CleanJSONSchemaForGemini(strJSON)
+		strJSON = util.CleanJSONSchemaForAntigravity(strJSON)
 
 		payload = []byte(strJSON)
 	}
@@ -1147,7 +1161,7 @@ func antigravityBaseURLFallbackOrder(auth *cliproxyauth.Auth) []string {
 	}
 	return []string{
 		antigravityBaseURLDaily,
-		// antigravityBaseURLAutopush,
+		antigravitySandboxBaseURLDaily,
 		antigravityBaseURLProd,
 	}
 }
@@ -1183,7 +1197,7 @@ func geminiToAntigravity(modelName string, payload []byte, projectID string) []b
 		template, _ = sjson.Set(template, "project", generateProjectID())
 	}
 	template, _ = sjson.Set(template, "requestId", generateRequestID())
-	template, _ = sjson.Set(template, "request.sessionId", generateSessionID())
+	template, _ = sjson.Set(template, "request.sessionId", generateStableSessionID(payload))
 
 	template, _ = sjson.Delete(template, "request.safetySettings")
 	template, _ = sjson.Set(template, "request.toolConfig.functionCallingConfig.mode", "VALIDATED")
@@ -1219,15 +1233,36 @@ func generateRequestID() string {
 }
 
 func generateSessionID() string {
+	randSourceMutex.Lock()
 	n := randSource.Int63n(9_000_000_000_000_000_000)
+	randSourceMutex.Unlock()
 	return "-" + strconv.FormatInt(n, 10)
 }
 
+func generateStableSessionID(payload []byte) string {
+	contents := gjson.GetBytes(payload, "request.contents")
+	if contents.IsArray() {
+		for _, content := range contents.Array() {
+			if content.Get("role").String() == "user" {
+				text := content.Get("parts.0.text").String()
+				if text != "" {
+					h := sha256.Sum256([]byte(text))
+					n := int64(binary.BigEndian.Uint64(h[:8])) & 0x7FFFFFFFFFFFFFFF
+					return "-" + strconv.FormatInt(n, 10)
+				}
+			}
+		}
+	}
+	return generateSessionID()
+}
+
 func generateProjectID() string {
 	adjectives := []string{"useful", "bright", "swift", "calm", "bold"}
 	nouns := []string{"fuze", "wave", "spark", "flow", "core"}
+	randSourceMutex.Lock()
 	adj := adjectives[randSource.Intn(len(adjectives))]
 	noun := nouns[randSource.Intn(len(nouns))]
+	randSourceMutex.Unlock()
 	randomPart := strings.ToLower(uuid.NewString())[:5]
 	return adj + "-" + noun + "-" + randomPart
 }
@@ -1278,7 +1313,7 @@ func alias2ModelName(modelName string) string {
 
 // normalizeAntigravityThinking clamps or removes thinking config based on model support.
 // For Claude models, it additionally ensures thinking budget < max_tokens.
-func normalizeAntigravityThinking(model string, payload []byte) []byte {
+func normalizeAntigravityThinking(model string, payload []byte, isClaude bool) []byte {
 	payload = util.StripThinkingConfigIfUnsupported(model, payload)
 	if !util.ModelSupportsThinking(model) {
 		return payload
@@ -1290,7 +1325,6 @@ func normalizeAntigravityThinking(model string, payload []byte) []byte {
 	raw := int(budget.Int())
 	normalized := util.NormalizeThinkingBudget(model, raw)
 
-	isClaude := strings.Contains(strings.ToLower(model), "claude")
 	if isClaude {
 		effectiveMax, setDefaultMax := antigravityEffectiveMaxTokens(model, payload)
 		if effectiveMax > 0 && normalized >= effectiveMax {

internal/runtime/executor/claude_executor.go

@@ -49,33 +49,29 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	}
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("claude")
 	// Use streaming translation to preserve function calling, except for claude.
 	stream := from != to
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel == "" {
-		upstreamModel = req.Model
-	}
-	if modelOverride := e.resolveUpstreamModel(upstreamModel, auth); modelOverride != "" {
-		upstreamModel = modelOverride
-	} else if !strings.EqualFold(upstreamModel, req.Model) {
-		if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
-			upstreamModel = modelOverride
-		}
-	}
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), stream)
+	body, _ = sjson.SetBytes(body, "model", model)
 	// Inject thinking config based on model metadata for thinking variants
-	body = e.injectThinkingConfig(req.Model, req.Metadata, body)
+	body = e.injectThinkingConfig(model, req.Metadata, body)
 
-	if !strings.HasPrefix(upstreamModel, "claude-3-5-haiku") {
+	if !strings.HasPrefix(model, "claude-3-5-haiku") {
 		body = checkSystemInstructions(body)
 	}
-	body = applyPayloadConfig(e.cfg, req.Model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
+
+	// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
+	body = disableThinkingIfToolChoiceForced(body)
 
 	// Ensure max_tokens > thinking.budget_tokens when thinking is enabled
-	body = ensureMaxTokensForThinking(req.Model, body)
+	body = ensureMaxTokensForThinking(model, body)
 
 	// Extract betas from body and convert to header
 	var extraBetas []string
@@ -167,26 +163,22 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	defer reporter.trackFailure(ctx, &err)
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("claude")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel == "" {
-		upstreamModel = req.Model
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
 	}
-	if modelOverride := e.resolveUpstreamModel(upstreamModel, auth); modelOverride != "" {
-		upstreamModel = modelOverride
-	} else if !strings.EqualFold(upstreamModel, req.Model) {
-		if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
-			upstreamModel = modelOverride
-		}
-	}
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), true)
+	body, _ = sjson.SetBytes(body, "model", model)
 	// Inject thinking config based on model metadata for thinking variants
-	body = e.injectThinkingConfig(req.Model, req.Metadata, body)
+	body = e.injectThinkingConfig(model, req.Metadata, body)
 	body = checkSystemInstructions(body)
-	body = applyPayloadConfig(e.cfg, req.Model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
+
+	// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
+	body = disableThinkingIfToolChoiceForced(body)
 
 	// Ensure max_tokens > thinking.budget_tokens when thinking is enabled
-	body = ensureMaxTokensForThinking(req.Model, body)
+	body = ensureMaxTokensForThinking(model, body)
 
 	// Extract betas from body and convert to header
 	var extraBetas []string
@@ -310,21 +302,14 @@ func (e *ClaudeExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
 	to := sdktranslator.FromString("claude")
 	// Use streaming translation to preserve function calling, except for claude.
 	stream := from != to
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel == "" {
-		upstreamModel = req.Model
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
 	}
-	if modelOverride := e.resolveUpstreamModel(upstreamModel, auth); modelOverride != "" {
-		upstreamModel = modelOverride
-	} else if !strings.EqualFold(upstreamModel, req.Model) {
-		if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
-			upstreamModel = modelOverride
-		}
-	}
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), stream)
+	body, _ = sjson.SetBytes(body, "model", model)
 
-	if !strings.HasPrefix(upstreamModel, "claude-3-5-haiku") {
+	if !strings.HasPrefix(model, "claude-3-5-haiku") {
 		body = checkSystemInstructions(body)
 	}
 
@@ -461,6 +446,19 @@ func (e *ClaudeExecutor) injectThinkingConfig(modelName string, metadata map[str
 	return util.ApplyClaudeThinkingConfig(body, budget)
 }
 
+// disableThinkingIfToolChoiceForced checks if tool_choice forces tool use and disables thinking.
+// Anthropic API does not allow thinking when tool_choice is set to "any" or a specific tool.
+// See: https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations
+func disableThinkingIfToolChoiceForced(body []byte) []byte {
+	toolChoiceType := gjson.GetBytes(body, "tool_choice.type").String()
+	// "auto" is allowed with thinking, but "any" or "tool" (specific tool) are not
+	if toolChoiceType == "any" || toolChoiceType == "tool" {
+		// Remove thinking configuration entirely to avoid API error
+		body, _ = sjson.DeleteBytes(body, "thinking")
+	}
+	return body
+}
+
 // ensureMaxTokensForThinking ensures max_tokens > thinking.budget_tokens when thinking is enabled.
 // Anthropic API requires this constraint; violating it returns a 400 error.
 // This function should be called after all thinking configuration is finalized.
@@ -662,7 +660,14 @@ func decodeResponseBody(body io.ReadCloser, contentEncoding string) (io.ReadClos
 }
 
 func applyClaudeHeaders(r *http.Request, auth *cliproxyauth.Auth, apiKey string, stream bool, extraBetas []string) {
-	r.Header.Set("Authorization", "Bearer "+apiKey)
+	useAPIKey := auth != nil && auth.Attributes != nil && strings.TrimSpace(auth.Attributes["api_key"]) != ""
+	isAnthropicBase := r.URL != nil && strings.EqualFold(r.URL.Scheme, "https") && strings.EqualFold(r.URL.Host, "api.anthropic.com")
+	if isAnthropicBase && useAPIKey {
+		r.Header.Del("Authorization")
+		r.Header.Set("x-api-key", apiKey)
+	} else {
+		r.Header.Set("Authorization", "Bearer "+apiKey)
+	}
 	r.Header.Set("Content-Type", "application/json")
 
 	var ginHeaders http.Header

internal/runtime/executor/codex_executor.go

@@ -49,18 +49,21 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("codex")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), false)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, model, "reasoning.effort", false)
+	body = NormalizeThinkingConfig(body, model, false)
+	if errValidate := ValidateThinkingConfig(body, model); errValidate != nil {
 		return resp, errValidate
 	}
-	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body = applyPayloadConfig(e.cfg, model, body)
+	body, _ = sjson.SetBytes(body, "model", model)
 	body, _ = sjson.SetBytes(body, "stream", true)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
 
@@ -146,20 +149,23 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("codex")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), true)
 
-	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, model, "reasoning.effort", false)
+	body = NormalizeThinkingConfig(body, model, false)
+	if errValidate := ValidateThinkingConfig(body, model); errValidate != nil {
 		return nil, errValidate
 	}
-	body = applyPayloadConfig(e.cfg, req.Model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body, _ = sjson.SetBytes(body, "model", model)
 
 	url := strings.TrimSuffix(baseURL, "/") + "/responses"
 	httpReq, err := e.cacheHelper(ctx, from, url, req, body)
@@ -246,20 +252,21 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 }
 
 func (e *CodexExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("codex")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), false)
 
-	modelForCounting := req.Model
-
-	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body = ApplyReasoningEffortMetadata(body, req.Metadata, model, "reasoning.effort", false)
+	body, _ = sjson.SetBytes(body, "model", model)
 	body, _ = sjson.DeleteBytes(body, "previous_response_id")
 	body, _ = sjson.SetBytes(body, "stream", false)
 
-	enc, err := tokenizerForCodexModel(modelForCounting)
+	enc, err := tokenizerForCodexModel(model)
 	if err != nil {
 		return cliproxyexecutor.Response{}, fmt.Errorf("codex executor: tokenizer init failed: %w", err)
 	}
@@ -520,3 +527,87 @@ func codexCreds(a *cliproxyauth.Auth) (apiKey, baseURL string) {
 	}
 	return
 }
+
+func (e *CodexExecutor) resolveUpstreamModel(alias string, auth *cliproxyauth.Auth) string {
+	trimmed := strings.TrimSpace(alias)
+	if trimmed == "" {
+		return ""
+	}
+
+	entry := e.resolveCodexConfig(auth)
+	if entry == nil {
+		return ""
+	}
+
+	normalizedModel, metadata := util.NormalizeThinkingModel(trimmed)
+
+	// Candidate names to match against configured aliases/names.
+	candidates := []string{strings.TrimSpace(normalizedModel)}
+	if !strings.EqualFold(normalizedModel, trimmed) {
+		candidates = append(candidates, trimmed)
+	}
+	if original := util.ResolveOriginalModel(normalizedModel, metadata); original != "" && !strings.EqualFold(original, normalizedModel) {
+		candidates = append(candidates, original)
+	}
+
+	for i := range entry.Models {
+		model := entry.Models[i]
+		name := strings.TrimSpace(model.Name)
+		modelAlias := strings.TrimSpace(model.Alias)
+
+		for _, candidate := range candidates {
+			if candidate == "" {
+				continue
+			}
+			if modelAlias != "" && strings.EqualFold(modelAlias, candidate) {
+				if name != "" {
+					return name
+				}
+				return candidate
+			}
+			if name != "" && strings.EqualFold(name, candidate) {
+				return name
+			}
+		}
+	}
+	return ""
+}
+
+func (e *CodexExecutor) resolveCodexConfig(auth *cliproxyauth.Auth) *config.CodexKey {
+	if auth == nil || e.cfg == nil {
+		return nil
+	}
+	var attrKey, attrBase string
+	if auth.Attributes != nil {
+		attrKey = strings.TrimSpace(auth.Attributes["api_key"])
+		attrBase = strings.TrimSpace(auth.Attributes["base_url"])
+	}
+	for i := range e.cfg.CodexKey {
+		entry := &e.cfg.CodexKey[i]
+		cfgKey := strings.TrimSpace(entry.APIKey)
+		cfgBase := strings.TrimSpace(entry.BaseURL)
+		if attrKey != "" && attrBase != "" {
+			if strings.EqualFold(cfgKey, attrKey) && strings.EqualFold(cfgBase, attrBase) {
+				return entry
+			}
+			continue
+		}
+		if attrKey != "" && strings.EqualFold(cfgKey, attrKey) {
+			if cfgBase == "" || strings.EqualFold(cfgBase, attrBase) {
+				return entry
+			}
+		}
+		if attrKey == "" && attrBase != "" && strings.EqualFold(cfgBase, attrBase) {
+			return entry
+		}
+	}
+	if attrKey != "" {
+		for i := range e.cfg.CodexKey {
+			entry := &e.cfg.CodexKey[i]
+			if strings.EqualFold(strings.TrimSpace(entry.APIKey), attrKey) {
+				return entry
+			}
+		}
+	}
+	return nil
+}

internal/runtime/executor/gemini_cli_executor.go

@@ -78,9 +78,9 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini-cli")
 	basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	basePayload = applyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
+	basePayload = ApplyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
 	basePayload = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, basePayload)
-	basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, basePayload)
+	basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, basePayload)
 	basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload)
 	basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
 	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -217,9 +217,9 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini-cli")
 	basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	basePayload = applyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
+	basePayload = ApplyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
 	basePayload = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, basePayload)
-	basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, basePayload)
+	basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, basePayload)
 	basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload)
 	basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
 	basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -318,7 +318,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 
 		out := make(chan cliproxyexecutor.StreamChunk)
 		stream = out
-		go func(resp *http.Response, reqBody []byte, attempt string) {
+		go func(resp *http.Response, reqBody []byte, attemptModel string) {
 			defer close(out)
 			defer func() {
 				if errClose := resp.Body.Close(); errClose != nil {
@@ -336,14 +336,14 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 						reporter.publish(ctx, detail)
 					}
 					if bytes.HasPrefix(line, dataTag) {
-						segments := sdktranslator.TranslateStream(respCtx, to, from, attempt, bytes.Clone(opts.OriginalRequest), reqBody, bytes.Clone(line), &param)
+						segments := sdktranslator.TranslateStream(respCtx, to, from, attemptModel, bytes.Clone(opts.OriginalRequest), reqBody, bytes.Clone(line), &param)
 						for i := range segments {
 							out <- cliproxyexecutor.StreamChunk{Payload: []byte(segments[i])}
 						}
 					}
 				}
 
-				segments := sdktranslator.TranslateStream(respCtx, to, from, attempt, bytes.Clone(opts.OriginalRequest), reqBody, bytes.Clone([]byte("[DONE]")), &param)
+				segments := sdktranslator.TranslateStream(respCtx, to, from, attemptModel, bytes.Clone(opts.OriginalRequest), reqBody, bytes.Clone([]byte("[DONE]")), &param)
 				for i := range segments {
 					out <- cliproxyexecutor.StreamChunk{Payload: []byte(segments[i])}
 				}
@@ -365,12 +365,12 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
 			appendAPIResponseChunk(ctx, e.cfg, data)
 			reporter.publish(ctx, parseGeminiCLIUsage(data))
 			var param any
-			segments := sdktranslator.TranslateStream(respCtx, to, from, attempt, bytes.Clone(opts.OriginalRequest), reqBody, data, &param)
+			segments := sdktranslator.TranslateStream(respCtx, to, from, attemptModel, bytes.Clone(opts.OriginalRequest), reqBody, data, &param)
 			for i := range segments {
 				out <- cliproxyexecutor.StreamChunk{Payload: []byte(segments[i])}
 			}
 
-			segments = sdktranslator.TranslateStream(respCtx, to, from, attempt, bytes.Clone(opts.OriginalRequest), reqBody, bytes.Clone([]byte("[DONE]")), &param)
+			segments = sdktranslator.TranslateStream(respCtx, to, from, attemptModel, bytes.Clone(opts.OriginalRequest), reqBody, bytes.Clone([]byte("[DONE]")), &param)
 			for i := range segments {
 				out <- cliproxyexecutor.StreamChunk{Payload: []byte(segments[i])}
 			}
@@ -417,15 +417,17 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
 	var lastStatus int
 	var lastBody []byte
 
+	// The loop variable attemptModel is only used as the concrete model id sent to the upstream
+	// Gemini CLI endpoint when iterating fallback variants.
 	for _, attemptModel := range models {
 		payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
-		payload = applyThinkingMetadataCLI(payload, req.Metadata, req.Model)
+		payload = ApplyThinkingMetadataCLI(payload, req.Metadata, req.Model)
 		payload = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, payload)
 		payload = deleteJSONField(payload, "project")
 		payload = deleteJSONField(payload, "model")
 		payload = deleteJSONField(payload, "request.safetySettings")
 		payload = util.StripThinkingConfigIfUnsupported(req.Model, payload)
-		payload = fixGeminiCLIImageAspectRatio(attemptModel, payload)
+		payload = fixGeminiCLIImageAspectRatio(req.Model, payload)
 
 		tok, errTok := tokenSource.Token()
 		if errTok != nil {

internal/runtime/executor/gemini_executor.go

@@ -77,19 +77,22 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(model, auth); override != "" {
+		model = override
+	}
 
 	// Official Gemini API via API key or OAuth bearer
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	body = ApplyThinkingMetadata(body, req.Metadata, req.Model)
-	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
-	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
-	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
-	body = fixGeminiImageAspectRatio(req.Model, body)
-	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), false)
+	body = ApplyThinkingMetadata(body, req.Metadata, model)
+	body = util.ApplyDefaultThinkingIfNeeded(model, body)
+	body = util.NormalizeGeminiThinkingBudget(model, body)
+	body = util.StripThinkingConfigIfUnsupported(model, body)
+	body = fixGeminiImageAspectRatio(model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
+	body, _ = sjson.SetBytes(body, "model", model)
 
 	action := "generateContent"
 	if req.Metadata != nil {
@@ -98,7 +101,7 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
 		}
 	}
 	baseURL := resolveGeminiBaseURL(auth)
-	url := fmt.Sprintf("%s/%s/models/%s:%s", baseURL, glAPIVersion, upstreamModel, action)
+	url := fmt.Sprintf("%s/%s/models/%s:%s", baseURL, glAPIVersion, model, action)
 	if opts.Alt != "" && action != "countTokens" {
 		url = url + fmt.Sprintf("?$alt=%s", opts.Alt)
 	}
@@ -173,21 +176,24 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	body = ApplyThinkingMetadata(body, req.Metadata, req.Model)
-	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
-	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
-	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
-	body = fixGeminiImageAspectRatio(req.Model, body)
-	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), true)
+	body = ApplyThinkingMetadata(body, req.Metadata, model)
+	body = util.ApplyDefaultThinkingIfNeeded(model, body)
+	body = util.NormalizeGeminiThinkingBudget(model, body)
+	body = util.StripThinkingConfigIfUnsupported(model, body)
+	body = fixGeminiImageAspectRatio(model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
+	body, _ = sjson.SetBytes(body, "model", model)
 
 	baseURL := resolveGeminiBaseURL(auth)
-	url := fmt.Sprintf("%s/%s/models/%s:%s", baseURL, glAPIVersion, upstreamModel, "streamGenerateContent")
+	url := fmt.Sprintf("%s/%s/models/%s:%s", baseURL, glAPIVersion, model, "streamGenerateContent")
 	if opts.Alt == "" {
 		url = url + "?alt=sse"
 	} else {
@@ -287,19 +293,25 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
 func (e *GeminiExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
 	apiKey, bearer := geminiCreds(auth)
 
+	model := req.Model
+	if override := e.resolveUpstreamModel(model, auth); override != "" {
+		model = override
+	}
+
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
-	translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	translatedReq = ApplyThinkingMetadata(translatedReq, req.Metadata, req.Model)
-	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
-	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
+	translatedReq := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), false)
+	translatedReq = ApplyThinkingMetadata(translatedReq, req.Metadata, model)
+	translatedReq = util.StripThinkingConfigIfUnsupported(model, translatedReq)
+	translatedReq = fixGeminiImageAspectRatio(model, translatedReq)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "generationConfig")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "safetySettings")
+	translatedReq, _ = sjson.SetBytes(translatedReq, "model", model)
 
 	baseURL := resolveGeminiBaseURL(auth)
-	url := fmt.Sprintf("%s/%s/models/%s:%s", baseURL, glAPIVersion, req.Model, "countTokens")
+	url := fmt.Sprintf("%s/%s/models/%s:%s", baseURL, glAPIVersion, model, "countTokens")
 
 	requestBody := bytes.NewReader(translatedReq)
 
@@ -398,6 +410,90 @@ func resolveGeminiBaseURL(auth *cliproxyauth.Auth) string {
 	return base
 }
 
+func (e *GeminiExecutor) resolveUpstreamModel(alias string, auth *cliproxyauth.Auth) string {
+	trimmed := strings.TrimSpace(alias)
+	if trimmed == "" {
+		return ""
+	}
+
+	entry := e.resolveGeminiConfig(auth)
+	if entry == nil {
+		return ""
+	}
+
+	normalizedModel, metadata := util.NormalizeThinkingModel(trimmed)
+
+	// Candidate names to match against configured aliases/names.
+	candidates := []string{strings.TrimSpace(normalizedModel)}
+	if !strings.EqualFold(normalizedModel, trimmed) {
+		candidates = append(candidates, trimmed)
+	}
+	if original := util.ResolveOriginalModel(normalizedModel, metadata); original != "" && !strings.EqualFold(original, normalizedModel) {
+		candidates = append(candidates, original)
+	}
+
+	for i := range entry.Models {
+		model := entry.Models[i]
+		name := strings.TrimSpace(model.Name)
+		modelAlias := strings.TrimSpace(model.Alias)
+
+		for _, candidate := range candidates {
+			if candidate == "" {
+				continue
+			}
+			if modelAlias != "" && strings.EqualFold(modelAlias, candidate) {
+				if name != "" {
+					return name
+				}
+				return candidate
+			}
+			if name != "" && strings.EqualFold(name, candidate) {
+				return name
+			}
+		}
+	}
+	return ""
+}
+
+func (e *GeminiExecutor) resolveGeminiConfig(auth *cliproxyauth.Auth) *config.GeminiKey {
+	if auth == nil || e.cfg == nil {
+		return nil
+	}
+	var attrKey, attrBase string
+	if auth.Attributes != nil {
+		attrKey = strings.TrimSpace(auth.Attributes["api_key"])
+		attrBase = strings.TrimSpace(auth.Attributes["base_url"])
+	}
+	for i := range e.cfg.GeminiKey {
+		entry := &e.cfg.GeminiKey[i]
+		cfgKey := strings.TrimSpace(entry.APIKey)
+		cfgBase := strings.TrimSpace(entry.BaseURL)
+		if attrKey != "" && attrBase != "" {
+			if strings.EqualFold(cfgKey, attrKey) && strings.EqualFold(cfgBase, attrBase) {
+				return entry
+			}
+			continue
+		}
+		if attrKey != "" && strings.EqualFold(cfgKey, attrKey) {
+			if cfgBase == "" || strings.EqualFold(cfgBase, attrBase) {
+				return entry
+			}
+		}
+		if attrKey == "" && attrBase != "" && strings.EqualFold(cfgBase, attrBase) {
+			return entry
+		}
+	}
+	if attrKey != "" {
+		for i := range e.cfg.GeminiKey {
+			entry := &e.cfg.GeminiKey[i]
+			if strings.EqualFold(strings.TrimSpace(entry.APIKey), attrKey) {
+				return entry
+			}
+		}
+	}
+	return nil
+}
+
 func applyGeminiHeaders(req *http.Request, auth *cliproxyauth.Auth) {
 	var attrs map[string]string
 	if auth != nil {

internal/runtime/executor/gemini_vertex_executor.go

@@ -120,8 +120,6 @@ func (e *GeminiVertexExecutor) executeWithServiceAccount(ctx context.Context, au
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
@@ -137,7 +135,7 @@ func (e *GeminiVertexExecutor) executeWithServiceAccount(ctx context.Context, au
 	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
 	body = fixGeminiImageAspectRatio(req.Model, body)
 	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body, _ = sjson.SetBytes(body, "model", req.Model)
 
 	action := "generateContent"
 	if req.Metadata != nil {
@@ -146,7 +144,7 @@ func (e *GeminiVertexExecutor) executeWithServiceAccount(ctx context.Context, au
 		}
 	}
 	baseURL := vertexBaseURL(location)
-	url := fmt.Sprintf("%s/%s/projects/%s/locations/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, projectID, location, upstreamModel, action)
+	url := fmt.Sprintf("%s/%s/projects/%s/locations/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, projectID, location, req.Model, action)
 	if opts.Alt != "" && action != "countTokens" {
 		url = url + fmt.Sprintf("?$alt=%s", opts.Alt)
 	}
@@ -220,24 +218,27 @@ func (e *GeminiVertexExecutor) executeWithAPIKey(ctx context.Context, auth *clip
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	if budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(req.Model, req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), false)
+	if budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, req.Metadata); ok && util.ModelSupportsThinking(model) {
 		if budgetOverride != nil {
-			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			norm := util.NormalizeThinkingBudget(model, *budgetOverride)
 			budgetOverride = &norm
 		}
 		body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
 	}
-	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
-	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
-	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
-	body = fixGeminiImageAspectRatio(req.Model, body)
-	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body = util.ApplyDefaultThinkingIfNeeded(model, body)
+	body = util.NormalizeGeminiThinkingBudget(model, body)
+	body = util.StripThinkingConfigIfUnsupported(model, body)
+	body = fixGeminiImageAspectRatio(model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
+	body, _ = sjson.SetBytes(body, "model", model)
 
 	action := "generateContent"
 	if req.Metadata != nil {
@@ -250,7 +251,7 @@ func (e *GeminiVertexExecutor) executeWithAPIKey(ctx context.Context, auth *clip
 	if baseURL == "" {
 		baseURL = "https://generativelanguage.googleapis.com"
 	}
-	url := fmt.Sprintf("%s/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, upstreamModel, action)
+	url := fmt.Sprintf("%s/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, model, action)
 	if opts.Alt != "" && action != "countTokens" {
 		url = url + fmt.Sprintf("?$alt=%s", opts.Alt)
 	}
@@ -321,8 +322,6 @@ func (e *GeminiVertexExecutor) executeStreamWithServiceAccount(ctx context.Conte
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
@@ -338,10 +337,10 @@ func (e *GeminiVertexExecutor) executeStreamWithServiceAccount(ctx context.Conte
 	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
 	body = fixGeminiImageAspectRatio(req.Model, body)
 	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body, _ = sjson.SetBytes(body, "model", req.Model)
 
 	baseURL := vertexBaseURL(location)
-	url := fmt.Sprintf("%s/%s/projects/%s/locations/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, projectID, location, upstreamModel, "streamGenerateContent")
+	url := fmt.Sprintf("%s/%s/projects/%s/locations/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, projectID, location, req.Model, "streamGenerateContent")
 	if opts.Alt == "" {
 		url = url + "?alt=sse"
 	} else {
@@ -438,30 +437,33 @@ func (e *GeminiVertexExecutor) executeStreamWithAPIKey(ctx context.Context, auth
 	reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
 	defer reporter.trackFailure(ctx, &err)
 
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
-	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
-	if budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(req.Model, req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+	body := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), true)
+	if budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, req.Metadata); ok && util.ModelSupportsThinking(model) {
 		if budgetOverride != nil {
-			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			norm := util.NormalizeThinkingBudget(model, *budgetOverride)
 			budgetOverride = &norm
 		}
 		body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
 	}
-	body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
-	body = util.NormalizeGeminiThinkingBudget(req.Model, body)
-	body = util.StripThinkingConfigIfUnsupported(req.Model, body)
-	body = fixGeminiImageAspectRatio(req.Model, body)
-	body = applyPayloadConfig(e.cfg, req.Model, body)
-	body, _ = sjson.SetBytes(body, "model", upstreamModel)
+	body = util.ApplyDefaultThinkingIfNeeded(model, body)
+	body = util.NormalizeGeminiThinkingBudget(model, body)
+	body = util.StripThinkingConfigIfUnsupported(model, body)
+	body = fixGeminiImageAspectRatio(model, body)
+	body = applyPayloadConfig(e.cfg, model, body)
+	body, _ = sjson.SetBytes(body, "model", model)
 
 	// For API key auth, use simpler URL format without project/location
 	if baseURL == "" {
 		baseURL = "https://generativelanguage.googleapis.com"
 	}
-	url := fmt.Sprintf("%s/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, upstreamModel, "streamGenerateContent")
+	url := fmt.Sprintf("%s/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, model, "streamGenerateContent")
 	if opts.Alt == "" {
 		url = url + "?alt=sse"
 	} else {
@@ -552,8 +554,6 @@ func (e *GeminiVertexExecutor) executeStreamWithAPIKey(ctx context.Context, auth
 
 // countTokensWithServiceAccount counts tokens using service account credentials.
 func (e *GeminiVertexExecutor) countTokensWithServiceAccount(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options, projectID, location string, saJSON []byte) (cliproxyexecutor.Response, error) {
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
 	translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
@@ -566,14 +566,14 @@ func (e *GeminiVertexExecutor) countTokensWithServiceAccount(ctx context.Context
 	}
 	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
 	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
-	translatedReq, _ = sjson.SetBytes(translatedReq, "model", upstreamModel)
+	translatedReq, _ = sjson.SetBytes(translatedReq, "model", req.Model)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "generationConfig")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "safetySettings")
 
 	baseURL := vertexBaseURL(location)
-	url := fmt.Sprintf("%s/%s/projects/%s/locations/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, projectID, location, upstreamModel, "countTokens")
+	url := fmt.Sprintf("%s/%s/projects/%s/locations/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, projectID, location, req.Model, "countTokens")
 
 	httpReq, errNewReq := http.NewRequestWithContext(respCtx, http.MethodPost, url, bytes.NewReader(translatedReq))
 	if errNewReq != nil {
@@ -641,21 +641,24 @@ func (e *GeminiVertexExecutor) countTokensWithServiceAccount(ctx context.Context
 
 // countTokensWithAPIKey handles token counting using API key credentials.
 func (e *GeminiVertexExecutor) countTokensWithAPIKey(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options, apiKey, baseURL string) (cliproxyexecutor.Response, error) {
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
+	model := req.Model
+	if override := e.resolveUpstreamModel(req.Model, auth); override != "" {
+		model = override
+	}
 
 	from := opts.SourceFormat
 	to := sdktranslator.FromString("gemini")
-	translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
-	if budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(req.Model, req.Metadata); ok && util.ModelSupportsThinking(req.Model) {
+	translatedReq := sdktranslator.TranslateRequest(from, to, model, bytes.Clone(req.Payload), false)
+	if budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, req.Metadata); ok && util.ModelSupportsThinking(model) {
 		if budgetOverride != nil {
-			norm := util.NormalizeThinkingBudget(req.Model, *budgetOverride)
+			norm := util.NormalizeThinkingBudget(model, *budgetOverride)
 			budgetOverride = &norm
 		}
 		translatedReq = util.ApplyGeminiThinkingConfig(translatedReq, budgetOverride, includeOverride)
 	}
-	translatedReq = util.StripThinkingConfigIfUnsupported(req.Model, translatedReq)
-	translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
-	translatedReq, _ = sjson.SetBytes(translatedReq, "model", upstreamModel)
+	translatedReq = util.StripThinkingConfigIfUnsupported(model, translatedReq)
+	translatedReq = fixGeminiImageAspectRatio(model, translatedReq)
+	translatedReq, _ = sjson.SetBytes(translatedReq, "model", model)
 	respCtx := context.WithValue(ctx, "alt", opts.Alt)
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "tools")
 	translatedReq, _ = sjson.DeleteBytes(translatedReq, "generationConfig")
@@ -665,7 +668,7 @@ func (e *GeminiVertexExecutor) countTokensWithAPIKey(ctx context.Context, auth *
 	if baseURL == "" {
 		baseURL = "https://generativelanguage.googleapis.com"
 	}
-	url := fmt.Sprintf("%s/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, req.Model, "countTokens")
+	url := fmt.Sprintf("%s/%s/publishers/google/models/%s:%s", baseURL, vertexAPIVersion, model, "countTokens")
 
 	httpReq, errNewReq := http.NewRequestWithContext(respCtx, http.MethodPost, url, bytes.NewReader(translatedReq))
 	if errNewReq != nil {
@@ -808,3 +811,90 @@ func vertexAccessToken(ctx context.Context, cfg *config.Config, auth *cliproxyau
 	}
 	return tok.AccessToken, nil
 }
+
+// resolveUpstreamModel resolves the upstream model name from vertex-api-key configuration.
+// It matches the requested model alias against configured models and returns the actual upstream name.
+func (e *GeminiVertexExecutor) resolveUpstreamModel(alias string, auth *cliproxyauth.Auth) string {
+	trimmed := strings.TrimSpace(alias)
+	if trimmed == "" {
+		return ""
+	}
+
+	entry := e.resolveVertexConfig(auth)
+	if entry == nil {
+		return ""
+	}
+
+	normalizedModel, metadata := util.NormalizeThinkingModel(trimmed)
+
+	// Candidate names to match against configured aliases/names.
+	candidates := []string{strings.TrimSpace(normalizedModel)}
+	if !strings.EqualFold(normalizedModel, trimmed) {
+		candidates = append(candidates, trimmed)
+	}
+	if original := util.ResolveOriginalModel(normalizedModel, metadata); original != "" && !strings.EqualFold(original, normalizedModel) {
+		candidates = append(candidates, original)
+	}
+
+	for i := range entry.Models {
+		model := entry.Models[i]
+		name := strings.TrimSpace(model.Name)
+		modelAlias := strings.TrimSpace(model.Alias)
+
+		for _, candidate := range candidates {
+			if candidate == "" {
+				continue
+			}
+			if modelAlias != "" && strings.EqualFold(modelAlias, candidate) {
+				if name != "" {
+					return name
+				}
+				return candidate
+			}
+			if name != "" && strings.EqualFold(name, candidate) {
+				return name
+			}
+		}
+	}
+	return ""
+}
+
+// resolveVertexConfig finds the matching vertex-api-key configuration entry for the given auth.
+func (e *GeminiVertexExecutor) resolveVertexConfig(auth *cliproxyauth.Auth) *config.VertexCompatKey {
+	if auth == nil || e.cfg == nil {
+		return nil
+	}
+	var attrKey, attrBase string
+	if auth.Attributes != nil {
+		attrKey = strings.TrimSpace(auth.Attributes["api_key"])
+		attrBase = strings.TrimSpace(auth.Attributes["base_url"])
+	}
+	for i := range e.cfg.VertexCompatAPIKey {
+		entry := &e.cfg.VertexCompatAPIKey[i]
+		cfgKey := strings.TrimSpace(entry.APIKey)
+		cfgBase := strings.TrimSpace(entry.BaseURL)
+		if attrKey != "" && attrBase != "" {
+			if strings.EqualFold(cfgKey, attrKey) && strings.EqualFold(cfgBase, attrBase) {
+				return entry
+			}
+			continue
+		}
+		if attrKey != "" && strings.EqualFold(cfgKey, attrKey) {
+			if cfgBase == "" || strings.EqualFold(cfgBase, attrBase) {
+				return entry
+			}
+		}
+		if attrKey == "" && attrBase != "" && strings.EqualFold(cfgBase, attrBase) {
+			return entry
+		}
+	}
+	if attrKey != "" {
+		for i := range e.cfg.VertexCompatAPIKey {
+			entry := &e.cfg.VertexCompatAPIKey[i]
+			if strings.EqualFold(strings.TrimSpace(entry.APIKey), attrKey) {
+				return entry
+			}
+		}
+	}
+	return nil
+}

internal/runtime/executor/iflow_executor.go

@@ -58,15 +58,13 @@ func (e *IFlowExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
 	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" {
-		body, _ = sjson.SetBytes(body, "model", upstreamModel)
-	}
-	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body, _ = sjson.SetBytes(body, "model", req.Model)
+	body = NormalizeThinkingConfig(body, req.Model, false)
+	if errValidate := ValidateThinkingConfig(body, req.Model); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyIFlowThinkingConfig(body)
+	body = preserveReasoningContentInMessages(body)
 	body = applyPayloadConfig(e.cfg, req.Model, body)
 
 	endpoint := strings.TrimSuffix(baseURL, "/") + iflowDefaultEndpoint
@@ -150,15 +148,13 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
 	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" {
-		body, _ = sjson.SetBytes(body, "model", upstreamModel)
-	}
-	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body, _ = sjson.SetBytes(body, "model", req.Model)
+	body = NormalizeThinkingConfig(body, req.Model, false)
+	if errValidate := ValidateThinkingConfig(body, req.Model); errValidate != nil {
 		return nil, errValidate
 	}
 	body = applyIFlowThinkingConfig(body)
+	body = preserveReasoningContentInMessages(body)
 	// Ensure tools array exists to avoid provider quirks similar to Qwen's behaviour.
 	toolsResult := gjson.GetBytes(body, "tools")
 	if toolsResult.Exists() && toolsResult.IsArray() && len(toolsResult.Array()) == 0 {
@@ -445,20 +441,85 @@ func ensureToolsArray(body []byte) []byte {
 	return updated
 }
 
-// applyIFlowThinkingConfig converts normalized reasoning_effort to iFlow chat_template_kwargs.enable_thinking.
+// preserveReasoningContentInMessages checks if reasoning_content from assistant messages
+// is preserved in conversation history for iFlow models that support thinking.
+// This is helpful for multi-turn conversations where the model may benefit from seeing
+// its previous reasoning to maintain coherent thought chains.
+//
+// For GLM-4.6/4.7 and MiniMax M2/M2.1, it is recommended to include the full assistant
+// response (including reasoning_content) in message history for better context continuity.
+func preserveReasoningContentInMessages(body []byte) []byte {
+	model := strings.ToLower(gjson.GetBytes(body, "model").String())
+
+	// Only apply to models that support thinking with history preservation
+	needsPreservation := strings.HasPrefix(model, "glm-4") || strings.HasPrefix(model, "minimax-m2")
+
+	if !needsPreservation {
+		return body
+	}
+
+	messages := gjson.GetBytes(body, "messages")
+	if !messages.Exists() || !messages.IsArray() {
+		return body
+	}
+
+	// Check if any assistant message already has reasoning_content preserved
+	hasReasoningContent := false
+	messages.ForEach(func(_, msg gjson.Result) bool {
+		role := msg.Get("role").String()
+		if role == "assistant" {
+			rc := msg.Get("reasoning_content")
+			if rc.Exists() && rc.String() != "" {
+				hasReasoningContent = true
+				return false // stop iteration
+			}
+		}
+		return true
+	})
+
+	// If reasoning content is already present, the messages are properly formatted
+	// No need to modify - the client has correctly preserved reasoning in history
+	if hasReasoningContent {
+		log.Debugf("iflow executor: reasoning_content found in message history for %s", model)
+	}
+
+	return body
+}
+
+// applyIFlowThinkingConfig converts normalized reasoning_effort to model-specific thinking configurations.
 // This should be called after NormalizeThinkingConfig has processed the payload.
-// iFlow only supports boolean enable_thinking, so any non-"none" effort enables thinking.
+//
+// Model-specific handling:
+//   - GLM-4.6/4.7: Uses chat_template_kwargs.enable_thinking (boolean) and chat_template_kwargs.clear_thinking=false
+//   - MiniMax M2/M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
 func applyIFlowThinkingConfig(body []byte) []byte {
 	effort := gjson.GetBytes(body, "reasoning_effort")
 	if !effort.Exists() {
 		return body
 	}
 
+	model := strings.ToLower(gjson.GetBytes(body, "model").String())
 	val := strings.ToLower(strings.TrimSpace(effort.String()))
 	enableThinking := val != "none" && val != ""
 
+	// Remove reasoning_effort as we'll convert to model-specific format
 	body, _ = sjson.DeleteBytes(body, "reasoning_effort")
-	body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
+	body, _ = sjson.DeleteBytes(body, "thinking")
+
+	// GLM-4.6/4.7: Use chat_template_kwargs
+	if strings.HasPrefix(model, "glm-4") {
+		body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
+		if enableThinking {
+			body, _ = sjson.SetBytes(body, "chat_template_kwargs.clear_thinking", false)
+		}
+		return body
+	}
+
+	// MiniMax M2/M2.1: Use reasoning_split
+	if strings.HasPrefix(model, "minimax-m2") {
+		body, _ = sjson.SetBytes(body, "reasoning_split", enableThinking)
+		return body
+	}
 
 	return body
 }

internal/runtime/executor/openai_compat_executor.go

@@ -61,12 +61,8 @@ func (e *OpenAICompatExecutor) Execute(ctx context.Context, auth *cliproxyauth.A
 	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, to.String(), "", translated)
 	allowCompat := e.allowCompatReasoningEffort(req.Model, auth)
 	translated = ApplyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" && modelOverride == "" {
-		translated, _ = sjson.SetBytes(translated, "model", upstreamModel)
-	}
-	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
-	if errValidate := ValidateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	translated = NormalizeThinkingConfig(translated, req.Model, allowCompat)
+	if errValidate := ValidateThinkingConfig(translated, req.Model); errValidate != nil {
 		return resp, errValidate
 	}
 
@@ -157,12 +153,8 @@ func (e *OpenAICompatExecutor) ExecuteStream(ctx context.Context, auth *cliproxy
 	translated = applyPayloadConfigWithRoot(e.cfg, req.Model, to.String(), "", translated)
 	allowCompat := e.allowCompatReasoningEffort(req.Model, auth)
 	translated = ApplyReasoningEffortMetadata(translated, req.Metadata, req.Model, "reasoning_effort", allowCompat)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" && modelOverride == "" {
-		translated, _ = sjson.SetBytes(translated, "model", upstreamModel)
-	}
-	translated = NormalizeThinkingConfig(translated, upstreamModel, allowCompat)
-	if errValidate := ValidateThinkingConfig(translated, upstreamModel); errValidate != nil {
+	translated = NormalizeThinkingConfig(translated, req.Model, allowCompat)
+	if errValidate := ValidateThinkingConfig(translated, req.Model); errValidate != nil {
 		return nil, errValidate
 	}
 

internal/runtime/executor/payload_helpers.go

@@ -14,32 +14,54 @@ import (
 // ApplyThinkingMetadata applies thinking config from model suffix metadata (e.g., (high), (8192))
 // for standard Gemini format payloads. It normalizes the budget when the model supports thinking.
 func ApplyThinkingMetadata(payload []byte, metadata map[string]any, model string) []byte {
-	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
+	// Use the alias from metadata if available, as it's registered in the global registry
+	// with thinking metadata; the upstream model name may not be registered.
+	lookupModel := util.ResolveOriginalModel(model, metadata)
+
+	// Determine which model to use for thinking support check.
+	// If the alias (lookupModel) is not in the registry, fall back to the upstream model.
+	thinkingModel := lookupModel
+	if !util.ModelSupportsThinking(lookupModel) && util.ModelSupportsThinking(model) {
+		thinkingModel = model
+	}
+
+	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(thinkingModel, metadata)
 	if !ok || (budgetOverride == nil && includeOverride == nil) {
 		return payload
 	}
-	if !util.ModelSupportsThinking(model) {
+	if !util.ModelSupportsThinking(thinkingModel) {
 		return payload
 	}
 	if budgetOverride != nil {
-		norm := util.NormalizeThinkingBudget(model, *budgetOverride)
+		norm := util.NormalizeThinkingBudget(thinkingModel, *budgetOverride)
 		budgetOverride = &norm
 	}
 	return util.ApplyGeminiThinkingConfig(payload, budgetOverride, includeOverride)
 }
 
-// applyThinkingMetadataCLI applies thinking config from model suffix metadata (e.g., (high), (8192))
+// ApplyThinkingMetadataCLI applies thinking config from model suffix metadata (e.g., (high), (8192))
 // for Gemini CLI format payloads (nested under "request"). It normalizes the budget when the model supports thinking.
-func applyThinkingMetadataCLI(payload []byte, metadata map[string]any, model string) []byte {
-	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
+func ApplyThinkingMetadataCLI(payload []byte, metadata map[string]any, model string) []byte {
+	// Use the alias from metadata if available, as it's registered in the global registry
+	// with thinking metadata; the upstream model name may not be registered.
+	lookupModel := util.ResolveOriginalModel(model, metadata)
+
+	// Determine which model to use for thinking support check.
+	// If the alias (lookupModel) is not in the registry, fall back to the upstream model.
+	thinkingModel := lookupModel
+	if !util.ModelSupportsThinking(lookupModel) && util.ModelSupportsThinking(model) {
+		thinkingModel = model
+	}
+
+	budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(thinkingModel, metadata)
 	if !ok || (budgetOverride == nil && includeOverride == nil) {
 		return payload
 	}
-	if !util.ModelSupportsThinking(model) {
+	if !util.ModelSupportsThinking(thinkingModel) {
 		return payload
 	}
 	if budgetOverride != nil {
-		norm := util.NormalizeThinkingBudget(model, *budgetOverride)
+		norm := util.NormalizeThinkingBudget(thinkingModel, *budgetOverride)
 		budgetOverride = &norm
 	}
 	return util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)

internal/runtime/executor/qwen_executor.go

@@ -12,7 +12,6 @@ import (
 
 	qwenauth "github.com/router-for-me/CLIProxyAPI/v6/internal/auth/qwen"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
-	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
 	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
@@ -52,12 +51,9 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
 	to := sdktranslator.FromString("openai")
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
 	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" {
-		body, _ = sjson.SetBytes(body, "model", upstreamModel)
-	}
-	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body, _ = sjson.SetBytes(body, "model", req.Model)
+	body = NormalizeThinkingConfig(body, req.Model, false)
+	if errValidate := ValidateThinkingConfig(body, req.Model); errValidate != nil {
 		return resp, errValidate
 	}
 	body = applyPayloadConfig(e.cfg, req.Model, body)
@@ -132,12 +128,9 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
 	body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
 	body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning_effort", false)
-	upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
-	if upstreamModel != "" {
-		body, _ = sjson.SetBytes(body, "model", upstreamModel)
-	}
-	body = NormalizeThinkingConfig(body, upstreamModel, false)
-	if errValidate := ValidateThinkingConfig(body, upstreamModel); errValidate != nil {
+	body, _ = sjson.SetBytes(body, "model", req.Model)
+	body = NormalizeThinkingConfig(body, req.Model, false)
+	if errValidate := ValidateThinkingConfig(body, req.Model); errValidate != nil {
 		return nil, errValidate
 	}
 	toolsResult := gjson.GetBytes(body, "tools")

internal/runtime/executor/usage_helpers.go

@@ -19,7 +19,7 @@ type usageReporter struct {
 	provider    string
 	model       string
 	authID      string
-	authIndex   uint64
+	authIndex   string
 	apiKey      string
 	source      string
 	requestedAt time.Time
@@ -275,6 +275,20 @@ func parseClaudeStreamUsage(line []byte) (usage.Detail, bool) {
 	return detail, true
 }
 
+func parseGeminiFamilyUsageDetail(node gjson.Result) usage.Detail {
+	detail := usage.Detail{
+		InputTokens:     node.Get("promptTokenCount").Int(),
+		OutputTokens:    node.Get("candidatesTokenCount").Int(),
+		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
+		TotalTokens:     node.Get("totalTokenCount").Int(),
+		CachedTokens:    node.Get("cachedContentTokenCount").Int(),
+	}
+	if detail.TotalTokens == 0 {
+		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
+	}
+	return detail
+}
+
 func parseGeminiCLIUsage(data []byte) usage.Detail {
 	usageNode := gjson.ParseBytes(data)
 	node := usageNode.Get("response.usageMetadata")
@@ -284,16 +298,7 @@ func parseGeminiCLIUsage(data []byte) usage.Detail {
 	if !node.Exists() {
 		return usage.Detail{}
 	}
-	detail := usage.Detail{
-		InputTokens:     node.Get("promptTokenCount").Int(),
-		OutputTokens:    node.Get("candidatesTokenCount").Int(),
-		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
-		TotalTokens:     node.Get("totalTokenCount").Int(),
-	}
-	if detail.TotalTokens == 0 {
-		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
-	}
-	return detail
+	return parseGeminiFamilyUsageDetail(node)
 }
 
 func parseGeminiUsage(data []byte) usage.Detail {
@@ -305,16 +310,7 @@ func parseGeminiUsage(data []byte) usage.Detail {
 	if !node.Exists() {
 		return usage.Detail{}
 	}
-	detail := usage.Detail{
-		InputTokens:     node.Get("promptTokenCount").Int(),
-		OutputTokens:    node.Get("candidatesTokenCount").Int(),
-		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
-		TotalTokens:     node.Get("totalTokenCount").Int(),
-	}
-	if detail.TotalTokens == 0 {
-		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
-	}
-	return detail
+	return parseGeminiFamilyUsageDetail(node)
 }
 
 func parseGeminiStreamUsage(line []byte) (usage.Detail, bool) {
@@ -329,16 +325,7 @@ func parseGeminiStreamUsage(line []byte) (usage.Detail, bool) {
 	if !node.Exists() {
 		return usage.Detail{}, false
 	}
-	detail := usage.Detail{
-		InputTokens:     node.Get("promptTokenCount").Int(),
-		OutputTokens:    node.Get("candidatesTokenCount").Int(),
-		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
-		TotalTokens:     node.Get("totalTokenCount").Int(),
-	}
-	if detail.TotalTokens == 0 {
-		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
-	}
-	return detail, true
+	return parseGeminiFamilyUsageDetail(node), true
 }
 
 func parseGeminiCLIStreamUsage(line []byte) (usage.Detail, bool) {
@@ -353,16 +340,7 @@ func parseGeminiCLIStreamUsage(line []byte) (usage.Detail, bool) {
 	if !node.Exists() {
 		return usage.Detail{}, false
 	}
-	detail := usage.Detail{
-		InputTokens:     node.Get("promptTokenCount").Int(),
-		OutputTokens:    node.Get("candidatesTokenCount").Int(),
-		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
-		TotalTokens:     node.Get("totalTokenCount").Int(),
-	}
-	if detail.TotalTokens == 0 {
-		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
-	}
-	return detail, true
+	return parseGeminiFamilyUsageDetail(node), true
 }
 
 func parseAntigravityUsage(data []byte) usage.Detail {
@@ -377,16 +355,7 @@ func parseAntigravityUsage(data []byte) usage.Detail {
 	if !node.Exists() {
 		return usage.Detail{}
 	}
-	detail := usage.Detail{
-		InputTokens:     node.Get("promptTokenCount").Int(),
-		OutputTokens:    node.Get("candidatesTokenCount").Int(),
-		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
-		TotalTokens:     node.Get("totalTokenCount").Int(),
-	}
-	if detail.TotalTokens == 0 {
-		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
-	}
-	return detail
+	return parseGeminiFamilyUsageDetail(node)
 }
 
 func parseAntigravityStreamUsage(line []byte) (usage.Detail, bool) {
@@ -404,16 +373,7 @@ func parseAntigravityStreamUsage(line []byte) (usage.Detail, bool) {
 	if !node.Exists() {
 		return usage.Detail{}, false
 	}
-	detail := usage.Detail{
-		InputTokens:     node.Get("promptTokenCount").Int(),
-		OutputTokens:    node.Get("candidatesTokenCount").Int(),
-		ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
-		TotalTokens:     node.Get("totalTokenCount").Int(),
-	}
-	if detail.TotalTokens == 0 {
-		detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
-	}
-	return detail, true
+	return parseGeminiFamilyUsageDetail(node), true
 }
 
 var stopChunkWithoutUsage sync.Map
@@ -522,12 +482,16 @@ func StripUsageMetadataFromJSON(rawJSON []byte) ([]byte, bool) {
 	cleaned := jsonBytes
 	var changed bool
 
-	if gjson.GetBytes(cleaned, "usageMetadata").Exists() {
+	if usageMetadata = gjson.GetBytes(cleaned, "usageMetadata"); usageMetadata.Exists() {
+		// Rename usageMetadata to cpaUsageMetadata in the message_start event of Claude
+		cleaned, _ = sjson.SetRawBytes(cleaned, "cpaUsageMetadata", []byte(usageMetadata.Raw))
 		cleaned, _ = sjson.DeleteBytes(cleaned, "usageMetadata")
 		changed = true
 	}
 
-	if gjson.GetBytes(cleaned, "response.usageMetadata").Exists() {
+	if usageMetadata = gjson.GetBytes(cleaned, "response.usageMetadata"); usageMetadata.Exists() {
+		// Rename usageMetadata to cpaUsageMetadata in the message_start event of Claude
+		cleaned, _ = sjson.SetRawBytes(cleaned, "response.cpaUsageMetadata", []byte(usageMetadata.Raw))
 		cleaned, _ = sjson.DeleteBytes(cleaned, "response.usageMetadata")
 		changed = true
 	}

internal/translator/antigravity/claude/antigravity_claude_request.go

@@ -7,15 +7,40 @@ package claude
 
 import (
 	"bytes"
+	"crypto/sha256"
+	"encoding/hex"
 	"strings"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/cache"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
+	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
 
-const geminiCLIClaudeThoughtSignature = "skip_thought_signature_validator"
+// deriveSessionID generates a stable session ID from the request.
+// Uses the hash of the first user message to identify the conversation.
+func deriveSessionID(rawJSON []byte) string {
+	messages := gjson.GetBytes(rawJSON, "messages")
+	if !messages.IsArray() {
+		return ""
+	}
+	for _, msg := range messages.Array() {
+		if msg.Get("role").String() == "user" {
+			content := msg.Get("content").String()
+			if content == "" {
+				// Try to get text from content array
+				content = msg.Get("content.0.text").String()
+			}
+			if content != "" {
+				h := sha256.Sum256([]byte(content))
+				return hex.EncodeToString(h[:16])
+			}
+		}
+	}
+	return ""
+}
 
 // ConvertClaudeRequestToAntigravity parses and transforms a Claude Code API request into Gemini CLI API format.
 // It extracts the model name, system instruction, message contents, and tool declarations
@@ -37,7 +62,9 @@ const geminiCLIClaudeThoughtSignature = "skip_thought_signature_validator"
 //   - []byte: The transformed request data in Gemini CLI API format
 func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _ bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
-	rawJSON = bytes.Replace(rawJSON, []byte(`"url":{"type":"string","format":"uri",`), []byte(`"url":{"type":"string",`), -1)
+
+	// Derive session ID for signature caching
+	sessionID := deriveSessionID(rawJSON)
 
 	// system instruction
 	systemInstructionJSON := ""
@@ -59,21 +86,28 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 				hasSystemInstruction = true
 			}
 		}
+	} else if systemResult.Type == gjson.String {
+		systemInstructionJSON = `{"role":"user","parts":[{"text":""}]}`
+		systemInstructionJSON, _ = sjson.Set(systemInstructionJSON, "parts.0.text", systemResult.String())
+		hasSystemInstruction = true
 	}
 
 	// contents
 	contentsJSON := "[]"
 	hasContents := false
+
 	messagesResult := gjson.GetBytes(rawJSON, "messages")
 	if messagesResult.IsArray() {
 		messageResults := messagesResult.Array()
-		for i := 0; i < len(messageResults); i++ {
+		numMessages := len(messageResults)
+		for i := 0; i < numMessages; i++ {
 			messageResult := messageResults[i]
 			roleResult := messageResult.Get("role")
 			if roleResult.Type != gjson.String {
 				continue
 			}
-			role := roleResult.String()
+			originalRole := roleResult.String()
+			role := originalRole
 			if role == "assistant" {
 				role = "model"
 			}
@@ -82,20 +116,58 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 			contentsResult := messageResult.Get("content")
 			if contentsResult.IsArray() {
 				contentResults := contentsResult.Array()
-				for j := 0; j < len(contentResults); j++ {
+				numContents := len(contentResults)
+				var currentMessageThinkingSignature string
+				for j := 0; j < numContents; j++ {
 					contentResult := contentResults[j]
 					contentTypeResult := contentResult.Get("type")
 					if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "thinking" {
-						prompt := contentResult.Get("thinking").String()
+						// Use GetThinkingText to handle wrapped thinking objects
+						thinkingText := util.GetThinkingText(contentResult)
 						signatureResult := contentResult.Get("signature")
-						signature := geminiCLIClaudeThoughtSignature
-						if signatureResult.Exists() {
-							signature = signatureResult.String()
+						clientSignature := ""
+						if signatureResult.Exists() && signatureResult.String() != "" {
+							clientSignature = signatureResult.String()
 						}
+
+						// Always try cached signature first (more reliable than client-provided)
+						// Client may send stale or invalid signatures from different sessions
+						signature := ""
+						if sessionID != "" && thinkingText != "" {
+							if cachedSig := cache.GetCachedSignature(sessionID, thinkingText); cachedSig != "" {
+								signature = cachedSig
+								log.Debugf("Using cached signature for thinking block")
+							}
+						}
+
+						// Fallback to client signature only if cache miss and client signature is valid
+						if signature == "" && cache.HasValidSignature(clientSignature) {
+							signature = clientSignature
+							log.Debugf("Using client-provided signature for thinking block")
+						}
+
+						// Store for subsequent tool_use in the same message
+						if cache.HasValidSignature(signature) {
+							currentMessageThinkingSignature = signature
+						}
+
+						// Skip trailing unsigned thinking blocks on last assistant message
+						isUnsigned := !cache.HasValidSignature(signature)
+
+						// If unsigned, skip entirely (don't convert to text)
+						// Claude requires assistant messages to start with thinking blocks when thinking is enabled
+						// Converting to text would break this requirement
+						if isUnsigned {
+							// TypeScript plugin approach: drop unsigned thinking blocks entirely
+							log.Debugf("Dropping unsigned thinking block (no valid signature)")
+							continue
+						}
+
+						// Valid signature, send as thought block
 						partJSON := `{}`
 						partJSON, _ = sjson.Set(partJSON, "thought", true)
-						if prompt != "" {
-							partJSON, _ = sjson.Set(partJSON, "text", prompt)
+						if thinkingText != "" {
+							partJSON, _ = sjson.Set(partJSON, "text", thinkingText)
 						}
 						if signature != "" {
 							partJSON, _ = sjson.Set(partJSON, "thoughtSignature", signature)
@@ -109,24 +181,47 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 						}
 						clientContentJSON, _ = sjson.SetRaw(clientContentJSON, "parts.-1", partJSON)
 					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_use" {
+						// NOTE: Do NOT inject dummy thinking blocks here.
+						// Antigravity API validates signatures, so dummy values are rejected.
+						// The TypeScript plugin removes unsigned thinking blocks instead of injecting dummies.
+
 						functionName := contentResult.Get("name").String()
-						functionArgs := contentResult.Get("input").String()
+						argsResult := contentResult.Get("input")
 						functionID := contentResult.Get("id").String()
-						if gjson.Valid(functionArgs) {
-							argsResult := gjson.Parse(functionArgs)
-							if argsResult.IsObject() {
-								partJSON := `{}`
-								if !strings.Contains(modelName, "claude") {
-									partJSON, _ = sjson.Set(partJSON, "thoughtSignature", geminiCLIClaudeThoughtSignature)
-								}
-								if functionID != "" {
-									partJSON, _ = sjson.Set(partJSON, "functionCall.id", functionID)
-								}
-								partJSON, _ = sjson.Set(partJSON, "functionCall.name", functionName)
-								partJSON, _ = sjson.SetRaw(partJSON, "functionCall.args", argsResult.Raw)
-								clientContentJSON, _ = sjson.SetRaw(clientContentJSON, "parts.-1", partJSON)
+
+						// Handle both object and string input formats
+						var argsRaw string
+						if argsResult.IsObject() {
+							argsRaw = argsResult.Raw
+						} else if argsResult.Type == gjson.String {
+							// Input is a JSON string, parse and validate it
+							parsed := gjson.Parse(argsResult.String())
+							if parsed.IsObject() {
+								argsRaw = parsed.Raw
 							}
 						}
+
+						if argsRaw != "" {
+							partJSON := `{}`
+
+							// Use skip_thought_signature_validator for tool calls without valid thinking signature
+							// This is the approach used in opencode-google-antigravity-auth for Gemini
+							// and also works for Claude through Antigravity API
+							const skipSentinel = "skip_thought_signature_validator"
+							if cache.HasValidSignature(currentMessageThinkingSignature) {
+								partJSON, _ = sjson.Set(partJSON, "thoughtSignature", currentMessageThinkingSignature)
+							} else {
+								// No valid signature - use skip sentinel to bypass validation
+								partJSON, _ = sjson.Set(partJSON, "thoughtSignature", skipSentinel)
+							}
+
+							if functionID != "" {
+								partJSON, _ = sjson.Set(partJSON, "functionCall.id", functionID)
+							}
+							partJSON, _ = sjson.Set(partJSON, "functionCall.name", functionName)
+							partJSON, _ = sjson.SetRaw(partJSON, "functionCall.args", argsRaw)
+							clientContentJSON, _ = sjson.SetRaw(clientContentJSON, "parts.-1", partJSON)
+						}
 					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_result" {
 						toolCallID := contentResult.Get("tool_use_id").String()
 						if toolCallID != "" {
@@ -180,6 +275,37 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 						}
 					}
 				}
+
+				// Reorder parts for 'model' role to ensure thinking block is first
+				if role == "model" {
+					partsResult := gjson.Get(clientContentJSON, "parts")
+					if partsResult.IsArray() {
+						parts := partsResult.Array()
+						var thinkingParts []gjson.Result
+						var otherParts []gjson.Result
+						for _, part := range parts {
+							if part.Get("thought").Bool() {
+								thinkingParts = append(thinkingParts, part)
+							} else {
+								otherParts = append(otherParts, part)
+							}
+						}
+						if len(thinkingParts) > 0 {
+							firstPartIsThinking := parts[0].Get("thought").Bool()
+							if !firstPartIsThinking || len(thinkingParts) > 1 {
+								var newParts []interface{}
+								for _, p := range thinkingParts {
+									newParts = append(newParts, p.Value())
+								}
+								for _, p := range otherParts {
+									newParts = append(newParts, p.Value())
+								}
+								clientContentJSON, _ = sjson.Set(clientContentJSON, "parts", newParts)
+							}
+						}
+					}
+				}
+
 				contentsJSON, _ = sjson.SetRaw(contentsJSON, "-1", clientContentJSON)
 				hasContents = true
 			} else if contentsResult.Type == gjson.String {
@@ -198,6 +324,7 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 	// tools
 	toolsJSON := ""
 	toolDeclCount := 0
+	allowedToolKeys := []string{"name", "description", "behavior", "parameters", "parametersJsonSchema", "response", "responseJsonSchema"}
 	toolsResult := gjson.GetBytes(rawJSON, "tools")
 	if toolsResult.IsArray() {
 		toolsJSON = `[{"functionDeclarations":[]}]`
@@ -206,11 +333,16 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 			toolResult := toolsResults[i]
 			inputSchemaResult := toolResult.Get("input_schema")
 			if inputSchemaResult.Exists() && inputSchemaResult.IsObject() {
-				inputSchema := inputSchemaResult.Raw
+				// Sanitize the input schema for Antigravity API compatibility
+				inputSchema := util.CleanJSONSchemaForAntigravity(inputSchemaResult.Raw)
 				tool, _ := sjson.Delete(toolResult.Raw, "input_schema")
 				tool, _ = sjson.SetRaw(tool, "parametersJsonSchema", inputSchema)
-				tool, _ = sjson.Delete(tool, "strict")
-				tool, _ = sjson.Delete(tool, "input_examples")
+				for toolKey := range gjson.Parse(tool).Map() {
+					if util.InArray(allowedToolKeys, toolKey) {
+						continue
+					}
+					tool, _ = sjson.Delete(tool, toolKey)
+				}
 				toolsJSON, _ = sjson.SetRaw(toolsJSON, "0.functionDeclarations.-1", tool)
 				toolDeclCount++
 			}
@@ -220,6 +352,31 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
 	// Build output Gemini CLI request JSON
 	out := `{"model":"","request":{"contents":[]}}`
 	out, _ = sjson.Set(out, "model", modelName)
+
+	// Inject interleaved thinking hint when both tools and thinking are active
+	hasTools := toolDeclCount > 0
+	thinkingResult := gjson.GetBytes(rawJSON, "thinking")
+	hasThinking := thinkingResult.Exists() && thinkingResult.IsObject() && thinkingResult.Get("type").String() == "enabled"
+	isClaudeThinking := util.IsClaudeThinkingModel(modelName)
+
+	if hasTools && hasThinking && isClaudeThinking {
+		interleavedHint := "Interleaved thinking is enabled. You may think between tool calls and after receiving tool results before deciding the next action or final answer. Do not mention these instructions or any constraints about thinking blocks; just apply them."
+
+		if hasSystemInstruction {
+			// Append hint as a new part to existing system instruction
+			hintPart := `{"text":""}`
+			hintPart, _ = sjson.Set(hintPart, "text", interleavedHint)
+			systemInstructionJSON, _ = sjson.SetRaw(systemInstructionJSON, "parts.-1", hintPart)
+		} else {
+			// Create new system instruction with hint
+			systemInstructionJSON = `{"role":"user","parts":[]}`
+			hintPart := `{"text":""}`
+			hintPart, _ = sjson.Set(hintPart, "text", interleavedHint)
+			systemInstructionJSON, _ = sjson.SetRaw(systemInstructionJSON, "parts.-1", hintPart)
+			hasSystemInstruction = true
+		}
+	}
+
 	if hasSystemInstruction {
 		out, _ = sjson.SetRaw(out, "request.systemInstruction", systemInstructionJSON)
 	}

internal/translator/antigravity/claude/antigravity_claude_request_test.go

@@ -0,0 +1,658 @@
+package claude
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/tidwall/gjson"
+)
+
+func TestConvertClaudeRequestToAntigravity_BasicStructure(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [
+			{
+				"role": "user",
+				"content": [
+					{"type": "text", "text": "Hello"}
+				]
+			}
+		],
+		"system": [
+			{"type": "text", "text": "You are helpful"}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	// Check model
+	if gjson.Get(outputStr, "model").String() != "claude-sonnet-4-5" {
+		t.Errorf("Expected model 'claude-sonnet-4-5', got '%s'", gjson.Get(outputStr, "model").String())
+	}
+
+	// Check contents exist
+	contents := gjson.Get(outputStr, "request.contents")
+	if !contents.Exists() || !contents.IsArray() {
+		t.Error("request.contents should exist and be an array")
+	}
+
+	// Check role mapping (assistant -> model)
+	firstContent := gjson.Get(outputStr, "request.contents.0")
+	if firstContent.Get("role").String() != "user" {
+		t.Errorf("Expected role 'user', got '%s'", firstContent.Get("role").String())
+	}
+
+	// Check systemInstruction
+	sysInstruction := gjson.Get(outputStr, "request.systemInstruction")
+	if !sysInstruction.Exists() {
+		t.Error("systemInstruction should exist")
+	}
+	if sysInstruction.Get("parts.0.text").String() != "You are helpful" {
+		t.Error("systemInstruction text mismatch")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_RoleMapping(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [
+			{"role": "user", "content": [{"type": "text", "text": "Hi"}]},
+			{"role": "assistant", "content": [{"type": "text", "text": "Hello"}]}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	// assistant should be mapped to model
+	secondContent := gjson.Get(outputStr, "request.contents.1")
+	if secondContent.Get("role").String() != "model" {
+		t.Errorf("Expected role 'model' (mapped from 'assistant'), got '%s'", secondContent.Get("role").String())
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ThinkingBlocks(t *testing.T) {
+	// Valid signature must be at least 50 characters
+	validSignature := "abc123validSignature1234567890123456789012345678901234567890"
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "thinking", "thinking": "Let me think...", "signature": "` + validSignature + `"},
+					{"type": "text", "text": "Answer"}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// Check thinking block conversion
+	firstPart := gjson.Get(outputStr, "request.contents.0.parts.0")
+	if !firstPart.Get("thought").Bool() {
+		t.Error("thinking block should have thought: true")
+	}
+	if firstPart.Get("text").String() != "Let me think..." {
+		t.Error("thinking text mismatch")
+	}
+	if firstPart.Get("thoughtSignature").String() != validSignature {
+		t.Errorf("Expected thoughtSignature '%s', got '%s'", validSignature, firstPart.Get("thoughtSignature").String())
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ThinkingBlockWithoutSignature(t *testing.T) {
+	// Unsigned thinking blocks should be removed entirely (not converted to text)
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "thinking", "thinking": "Let me think..."},
+					{"type": "text", "text": "Answer"}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// Without signature, thinking block should be removed (not converted to text)
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 1 {
+		t.Fatalf("Expected 1 part (thinking removed), got %d", len(parts))
+	}
+
+	// Only text part should remain
+	if parts[0].Get("thought").Bool() {
+		t.Error("Thinking block should be removed, not preserved")
+	}
+	if parts[0].Get("text").String() != "Answer" {
+		t.Errorf("Expected text 'Answer', got '%s'", parts[0].Get("text").String())
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ToolDeclarations(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [],
+		"tools": [
+			{
+				"name": "test_tool",
+				"description": "A test tool",
+				"input_schema": {
+					"type": "object",
+					"properties": {
+						"name": {"type": "string"}
+					},
+					"required": ["name"]
+				}
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("gemini-1.5-pro", inputJSON, false)
+	outputStr := string(output)
+
+	// Check tools structure
+	tools := gjson.Get(outputStr, "request.tools")
+	if !tools.Exists() {
+		t.Error("Tools should exist in output")
+	}
+
+	funcDecl := gjson.Get(outputStr, "request.tools.0.functionDeclarations.0")
+	if funcDecl.Get("name").String() != "test_tool" {
+		t.Errorf("Expected tool name 'test_tool', got '%s'", funcDecl.Get("name").String())
+	}
+
+	// Check input_schema renamed to parametersJsonSchema
+	if funcDecl.Get("parametersJsonSchema").Exists() {
+		t.Log("parametersJsonSchema exists (expected)")
+	}
+	if funcDecl.Get("input_schema").Exists() {
+		t.Error("input_schema should be removed")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ToolUse(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{
+						"type": "tool_use",
+						"id": "call_123",
+						"name": "get_weather",
+						"input": "{\"location\": \"Paris\"}"
+					}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	// Now we expect only 1 part (tool_use), no dummy thinking block injected
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 1 {
+		t.Fatalf("Expected 1 part (tool only, no dummy injection), got %d", len(parts))
+	}
+
+	// Check function call conversion at parts[0]
+	funcCall := parts[0].Get("functionCall")
+	if !funcCall.Exists() {
+		t.Error("functionCall should exist at parts[0]")
+	}
+	if funcCall.Get("name").String() != "get_weather" {
+		t.Errorf("Expected function name 'get_weather', got '%s'", funcCall.Get("name").String())
+	}
+	if funcCall.Get("id").String() != "call_123" {
+		t.Errorf("Expected function id 'call_123', got '%s'", funcCall.Get("id").String())
+	}
+	// Verify skip_thought_signature_validator is added (bypass for tools without valid thinking)
+	expectedSig := "skip_thought_signature_validator"
+	actualSig := parts[0].Get("thoughtSignature").String()
+	if actualSig != expectedSig {
+		t.Errorf("Expected thoughtSignature '%s', got '%s'", expectedSig, actualSig)
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ToolUse_WithSignature(t *testing.T) {
+	validSignature := "abc123validSignature1234567890123456789012345678901234567890"
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "thinking", "thinking": "Let me think...", "signature": "` + validSignature + `"},
+					{
+						"type": "tool_use",
+						"id": "call_123",
+						"name": "get_weather",
+						"input": "{\"location\": \"Paris\"}"
+					}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// Check function call has the signature from the preceding thinking block
+	part := gjson.Get(outputStr, "request.contents.0.parts.1")
+	if part.Get("functionCall.name").String() != "get_weather" {
+		t.Errorf("Expected functionCall, got %s", part.Raw)
+	}
+	if part.Get("thoughtSignature").String() != validSignature {
+		t.Errorf("Expected thoughtSignature '%s' on tool_use, got '%s'", validSignature, part.Get("thoughtSignature").String())
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ReorderThinking(t *testing.T) {
+	// Case: text block followed by thinking block -> should be reordered to thinking first
+	validSignature := "abc123validSignature1234567890123456789012345678901234567890"
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "text", "text": "Here is the plan."},
+					{"type": "thinking", "thinking": "Planning...", "signature": "` + validSignature + `"}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// Verify order: Thinking block MUST be first
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 2 {
+		t.Fatalf("Expected 2 parts, got %d", len(parts))
+	}
+
+	if !parts[0].Get("thought").Bool() {
+		t.Error("First part should be thinking block after reordering")
+	}
+	if parts[1].Get("text").String() != "Here is the plan." {
+		t.Error("Second part should be text block")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ToolResult(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [
+			{
+				"role": "user",
+				"content": [
+					{
+						"type": "tool_result",
+						"tool_use_id": "get_weather-call-123",
+						"content": "22C sunny"
+					}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	// Check function response conversion
+	funcResp := gjson.Get(outputStr, "request.contents.0.parts.0.functionResponse")
+	if !funcResp.Exists() {
+		t.Error("functionResponse should exist")
+	}
+	if funcResp.Get("id").String() != "get_weather-call-123" {
+		t.Errorf("Expected function id, got '%s'", funcResp.Get("id").String())
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ThinkingConfig(t *testing.T) {
+	// Note: This test requires the model to be registered in the registry
+	// with Thinking metadata. If the registry is not populated in test environment,
+	// thinkingConfig won't be added. We'll test the basic structure only.
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [],
+		"thinking": {
+			"type": "enabled",
+			"budget_tokens": 8000
+		}
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// Check thinking config conversion (only if model supports thinking in registry)
+	thinkingConfig := gjson.Get(outputStr, "request.generationConfig.thinkingConfig")
+	if thinkingConfig.Exists() {
+		if thinkingConfig.Get("thinkingBudget").Int() != 8000 {
+			t.Errorf("Expected thinkingBudget 8000, got %d", thinkingConfig.Get("thinkingBudget").Int())
+		}
+		if !thinkingConfig.Get("include_thoughts").Bool() {
+			t.Error("include_thoughts should be true")
+		}
+	} else {
+		t.Log("thinkingConfig not present - model may not be registered in test registry")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ImageContent(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [
+			{
+				"role": "user",
+				"content": [
+					{
+						"type": "image",
+						"source": {
+							"type": "base64",
+							"media_type": "image/png",
+							"data": "iVBORw0KGgoAAAANSUhEUg=="
+						}
+					}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	// Check inline data conversion
+	inlineData := gjson.Get(outputStr, "request.contents.0.parts.0.inlineData")
+	if !inlineData.Exists() {
+		t.Error("inlineData should exist")
+	}
+	if inlineData.Get("mime_type").String() != "image/png" {
+		t.Error("mime_type mismatch")
+	}
+	if !strings.Contains(inlineData.Get("data").String(), "iVBORw0KGgo") {
+		t.Error("data mismatch")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_GenerationConfig(t *testing.T) {
+	inputJSON := []byte(`{
+		"model": "claude-3-5-sonnet-20240620",
+		"messages": [],
+		"temperature": 0.7,
+		"top_p": 0.9,
+		"top_k": 40,
+		"max_tokens": 2000
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	genConfig := gjson.Get(outputStr, "request.generationConfig")
+	if genConfig.Get("temperature").Float() != 0.7 {
+		t.Errorf("Expected temperature 0.7, got %f", genConfig.Get("temperature").Float())
+	}
+	if genConfig.Get("topP").Float() != 0.9 {
+		t.Errorf("Expected topP 0.9, got %f", genConfig.Get("topP").Float())
+	}
+	if genConfig.Get("topK").Float() != 40 {
+		t.Errorf("Expected topK 40, got %f", genConfig.Get("topK").Float())
+	}
+	if genConfig.Get("maxOutputTokens").Float() != 2000 {
+		t.Errorf("Expected maxOutputTokens 2000, got %f", genConfig.Get("maxOutputTokens").Float())
+	}
+}
+
+// ============================================================================
+// Trailing Unsigned Thinking Block Removal
+// ============================================================================
+
+func TestConvertClaudeRequestToAntigravity_TrailingUnsignedThinking_Removed(t *testing.T) {
+	// Last assistant message ends with unsigned thinking block - should be removed
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "user",
+				"content": [{"type": "text", "text": "Hello"}]
+			},
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "text", "text": "Here is my answer"},
+					{"type": "thinking", "thinking": "I should think more..."}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// The last part of the last assistant message should NOT be a thinking block
+	lastMessageParts := gjson.Get(outputStr, "request.contents.1.parts")
+	if !lastMessageParts.IsArray() {
+		t.Fatal("Last message should have parts array")
+	}
+	parts := lastMessageParts.Array()
+	if len(parts) == 0 {
+		t.Fatal("Last message should have at least one part")
+	}
+
+	// The unsigned thinking should be removed, leaving only the text
+	lastPart := parts[len(parts)-1]
+	if lastPart.Get("thought").Bool() {
+		t.Error("Trailing unsigned thinking block should be removed")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_TrailingSignedThinking_Kept(t *testing.T) {
+	// Last assistant message ends with signed thinking block - should be kept
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "user",
+				"content": [{"type": "text", "text": "Hello"}]
+			},
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "text", "text": "Here is my answer"},
+					{"type": "thinking", "thinking": "Valid thinking...", "signature": "abc123validSignature1234567890123456789012345678901234567890"}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// The signed thinking block should be preserved
+	lastMessageParts := gjson.Get(outputStr, "request.contents.1.parts")
+	parts := lastMessageParts.Array()
+	if len(parts) < 2 {
+		t.Error("Signed thinking block should be preserved")
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_MiddleUnsignedThinking_Removed(t *testing.T) {
+	// Middle message has unsigned thinking - should be removed entirely
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "thinking", "thinking": "Middle thinking..."},
+					{"type": "text", "text": "Answer"}
+				]
+			},
+			{
+				"role": "user",
+				"content": [{"type": "text", "text": "Follow up"}]
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// Unsigned thinking should be removed entirely
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 1 {
+		t.Fatalf("Expected 1 part (thinking removed), got %d", len(parts))
+	}
+
+	// Only text part should remain
+	if parts[0].Get("thought").Bool() {
+		t.Error("Thinking block should be removed, not preserved")
+	}
+	if parts[0].Get("text").String() != "Answer" {
+		t.Errorf("Expected text 'Answer', got '%s'", parts[0].Get("text").String())
+	}
+}
+
+// ============================================================================
+// Tool + Thinking System Hint Injection
+// ============================================================================
+
+func TestConvertClaudeRequestToAntigravity_ToolAndThinking_HintInjected(t *testing.T) {
+	// When both tools and thinking are enabled, hint should be injected into system instruction
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Hello"}]}],
+		"system": [{"type": "text", "text": "You are helpful."}],
+		"tools": [
+			{
+				"name": "get_weather",
+				"description": "Get weather",
+				"input_schema": {"type": "object", "properties": {"location": {"type": "string"}}}
+			}
+		],
+		"thinking": {"type": "enabled", "budget_tokens": 8000}
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// System instruction should contain the interleaved thinking hint
+	sysInstruction := gjson.Get(outputStr, "request.systemInstruction")
+	if !sysInstruction.Exists() {
+		t.Fatal("systemInstruction should exist")
+	}
+
+	// Check if hint is appended
+	sysText := sysInstruction.Get("parts").Array()
+	found := false
+	for _, part := range sysText {
+		if strings.Contains(part.Get("text").String(), "Interleaved thinking is enabled") {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Errorf("Interleaved thinking hint should be injected when tools and thinking are both active, got: %v", sysInstruction.Raw)
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ToolsOnly_NoHint(t *testing.T) {
+	// When only tools are present (no thinking), hint should NOT be injected
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5",
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Hello"}]}],
+		"system": [{"type": "text", "text": "You are helpful."}],
+		"tools": [
+			{
+				"name": "get_weather",
+				"description": "Get weather",
+				"input_schema": {"type": "object", "properties": {"location": {"type": "string"}}}
+			}
+		]
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5", inputJSON, false)
+	outputStr := string(output)
+
+	// System instruction should NOT contain the hint
+	sysInstruction := gjson.Get(outputStr, "request.systemInstruction")
+	if sysInstruction.Exists() {
+		for _, part := range sysInstruction.Get("parts").Array() {
+			if strings.Contains(part.Get("text").String(), "Interleaved thinking is enabled") {
+				t.Error("Hint should NOT be injected when only tools are present (no thinking)")
+			}
+		}
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ThinkingOnly_NoHint(t *testing.T) {
+	// When only thinking is enabled (no tools), hint should NOT be injected
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Hello"}]}],
+		"system": [{"type": "text", "text": "You are helpful."}],
+		"thinking": {"type": "enabled", "budget_tokens": 8000}
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// System instruction should NOT contain the hint (no tools)
+	sysInstruction := gjson.Get(outputStr, "request.systemInstruction")
+	if sysInstruction.Exists() {
+		for _, part := range sysInstruction.Get("parts").Array() {
+			if strings.Contains(part.Get("text").String(), "Interleaved thinking is enabled") {
+				t.Error("Hint should NOT be injected when only thinking is present (no tools)")
+			}
+		}
+	}
+}
+
+func TestConvertClaudeRequestToAntigravity_ToolAndThinking_NoExistingSystem(t *testing.T) {
+	// When tools + thinking but no system instruction, should create one with hint
+	inputJSON := []byte(`{
+		"model": "claude-sonnet-4-5-thinking",
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Hello"}]}],
+		"tools": [
+			{
+				"name": "get_weather",
+				"description": "Get weather",
+				"input_schema": {"type": "object", "properties": {"location": {"type": "string"}}}
+			}
+		],
+		"thinking": {"type": "enabled", "budget_tokens": 8000}
+	}`)
+
+	output := ConvertClaudeRequestToAntigravity("claude-sonnet-4-5-thinking", inputJSON, false)
+	outputStr := string(output)
+
+	// System instruction should be created with hint
+	sysInstruction := gjson.Get(outputStr, "request.systemInstruction")
+	if !sysInstruction.Exists() {
+		t.Fatal("systemInstruction should be created when tools + thinking are active")
+	}
+
+	sysText := sysInstruction.Get("parts").Array()
+	found := false
+	for _, part := range sysText {
+		if strings.Contains(part.Get("text").String(), "Interleaved thinking is enabled") {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Errorf("Interleaved thinking hint should be in created systemInstruction, got: %v", sysInstruction.Raw)
+	}
+}

internal/translator/antigravity/claude/antigravity_claude_response.go

@@ -14,6 +14,9 @@ import (
 	"sync/atomic"
 	"time"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/cache"
+	log "github.com/sirupsen/logrus"
+
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -32,9 +35,14 @@ type Params struct {
 	CandidatesTokenCount int64  // Cached candidate token count from usage metadata
 	ThoughtsTokenCount   int64  // Cached thinking token count from usage metadata
 	TotalTokenCount      int64  // Cached total token count from usage metadata
+	CachedTokenCount     int64  // Cached content token count (indicates prompt caching)
 	HasSentFinalEvents   bool   // Indicates if final content/message events have been sent
 	HasToolUse           bool   // Indicates if tool use was observed in the stream
 	HasContent           bool   // Tracks whether any content (text, thinking, or tool use) has been output
+
+	// Signature caching support
+	SessionID           string          // Session ID derived from request for signature caching
+	CurrentThinkingText strings.Builder // Accumulates thinking text for signature caching
 }
 
 // toolUseIDCounter provides a process-wide unique counter for tool use identifiers.
@@ -62,6 +70,7 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
 			HasFirstResponse: false,
 			ResponseType:     0,
 			ResponseIndex:    0,
+			SessionID:        deriveSessionID(originalRequestRawJSON),
 		}
 	}
 
@@ -90,6 +99,14 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
 		// This follows the Claude Code API specification for streaming message initialization
 		messageStartTemplate := `{"type": "message_start", "message": {"id": "msg_1nZdL29xx5MUA1yADyHTEsnR8uuvGzszyY", "type": "message", "role": "assistant", "content": [], "model": "claude-3-5-sonnet-20241022", "stop_reason": null, "stop_sequence": null, "usage": {"input_tokens": 0, "output_tokens": 0}}}`
 
+		// Use cpaUsageMetadata within the message_start event for Claude.
+		if promptTokenCount := gjson.GetBytes(rawJSON, "response.cpaUsageMetadata.promptTokenCount"); promptTokenCount.Exists() {
+			messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.usage.input_tokens", promptTokenCount.Int())
+		}
+		if candidatesTokenCount := gjson.GetBytes(rawJSON, "response.cpaUsageMetadata.candidatesTokenCount"); candidatesTokenCount.Exists() {
+			messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.usage.output_tokens", candidatesTokenCount.Int())
+		}
+
 		// Override default values with actual response metadata if available from the Gemini CLI response
 		if modelVersionResult := gjson.GetBytes(rawJSON, "response.modelVersion"); modelVersionResult.Exists() {
 			messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.model", modelVersionResult.String())
@@ -119,11 +136,20 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
 				// Process thinking content (internal reasoning)
 				if partResult.Get("thought").Bool() {
 					if thoughtSignature := partResult.Get("thoughtSignature"); thoughtSignature.Exists() && thoughtSignature.String() != "" {
+						log.Debug("Branch: signature_delta")
+
+						if params.SessionID != "" && params.CurrentThinkingText.Len() > 0 {
+							cache.CacheSignature(params.SessionID, params.CurrentThinkingText.String(), thoughtSignature.String())
+							log.Debugf("Cached signature for thinking block (sessionID=%s, textLen=%d)", params.SessionID, params.CurrentThinkingText.Len())
+							params.CurrentThinkingText.Reset()
+						}
+
 						output = output + "event: content_block_delta\n"
 						data, _ := sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"signature_delta","signature":""}}`, params.ResponseIndex), "delta.signature", thoughtSignature.String())
 						output = output + fmt.Sprintf("data: %s\n\n\n", data)
 						params.HasContent = true
 					} else if params.ResponseType == 2 { // Continue existing thinking block if already in thinking state
+						params.CurrentThinkingText.WriteString(partTextResult.String())
 						output = output + "event: content_block_delta\n"
 						data, _ := sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"thinking_delta","thinking":""}}`, params.ResponseIndex), "delta.thinking", partTextResult.String())
 						output = output + fmt.Sprintf("data: %s\n\n\n", data)
@@ -152,6 +178,9 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
 						output = output + fmt.Sprintf("data: %s\n\n\n", data)
 						params.ResponseType = 2 // Set state to thinking
 						params.HasContent = true
+						// Start accumulating thinking text for signature caching
+						params.CurrentThinkingText.Reset()
+						params.CurrentThinkingText.WriteString(partTextResult.String())
 					}
 				} else {
 					finishReasonResult := gjson.GetBytes(rawJSON, "response.candidates.0.finishReason")
@@ -250,7 +279,8 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
 
 	if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
 		params.HasUsageMetadata = true
-		params.PromptTokenCount = usageResult.Get("promptTokenCount").Int()
+		params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
+		params.PromptTokenCount = usageResult.Get("promptTokenCount").Int() - params.CachedTokenCount
 		params.CandidatesTokenCount = usageResult.Get("candidatesTokenCount").Int()
 		params.ThoughtsTokenCount = usageResult.Get("thoughtsTokenCount").Int()
 		params.TotalTokenCount = usageResult.Get("totalTokenCount").Int()
@@ -302,6 +332,14 @@ func appendFinalEvents(params *Params, output *string, force bool) {
 	*output = *output + "event: message_delta\n"
 	*output = *output + "data: "
 	delta := fmt.Sprintf(`{"type":"message_delta","delta":{"stop_reason":"%s","stop_sequence":null},"usage":{"input_tokens":%d,"output_tokens":%d}}`, stopReason, params.PromptTokenCount, usageOutputTokens)
+	// Add cache_read_input_tokens if cached tokens are present (indicates prompt caching is working)
+	if params.CachedTokenCount > 0 {
+		var err error
+		delta, err = sjson.Set(delta, "usage.cache_read_input_tokens", params.CachedTokenCount)
+		if err != nil {
+			log.Warnf("antigravity claude response: failed to set cache_read_input_tokens: %v", err)
+		}
+	}
 	*output = *output + delta + "\n\n\n"
 
 	params.HasSentFinalEvents = true
@@ -341,6 +379,7 @@ func ConvertAntigravityResponseToClaudeNonStream(_ context.Context, _ string, or
 	candidateTokens := root.Get("response.usageMetadata.candidatesTokenCount").Int()
 	thoughtTokens := root.Get("response.usageMetadata.thoughtsTokenCount").Int()
 	totalTokens := root.Get("response.usageMetadata.totalTokenCount").Int()
+	cachedTokens := root.Get("response.usageMetadata.cachedContentTokenCount").Int()
 	outputTokens := candidateTokens + thoughtTokens
 	if outputTokens == 0 && totalTokens > 0 {
 		outputTokens = totalTokens - promptTokens
@@ -354,6 +393,14 @@ func ConvertAntigravityResponseToClaudeNonStream(_ context.Context, _ string, or
 	responseJSON, _ = sjson.Set(responseJSON, "model", root.Get("response.modelVersion").String())
 	responseJSON, _ = sjson.Set(responseJSON, "usage.input_tokens", promptTokens)
 	responseJSON, _ = sjson.Set(responseJSON, "usage.output_tokens", outputTokens)
+	// Add cache_read_input_tokens if cached tokens are present (indicates prompt caching is working)
+	if cachedTokens > 0 {
+		var err error
+		responseJSON, err = sjson.Set(responseJSON, "usage.cache_read_input_tokens", cachedTokens)
+		if err != nil {
+			log.Warnf("antigravity claude response: failed to set cache_read_input_tokens: %v", err)
+		}
+	}
 
 	contentArrayInitialized := false
 	ensureContentArray := func() {
@@ -432,7 +479,7 @@ func ConvertAntigravityResponseToClaudeNonStream(_ context.Context, _ string, or
 				toolBlock, _ = sjson.Set(toolBlock, "id", fmt.Sprintf("tool_%d", toolIDCounter))
 				toolBlock, _ = sjson.Set(toolBlock, "name", name)
 
-				if args := functionCall.Get("args"); args.Exists() && args.Raw != "" && gjson.Valid(args.Raw) {
+				if args := functionCall.Get("args"); args.Exists() && args.Raw != "" && gjson.Valid(args.Raw) && args.IsObject() {
 					toolBlock, _ = sjson.SetRaw(toolBlock, "input", args.Raw)
 				}
 

internal/translator/antigravity/claude/antigravity_claude_response_test.go

@@ -0,0 +1,316 @@
+package claude
+
+import (
+	"context"
+	"strings"
+	"testing"
+
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/cache"
+)
+
+// ============================================================================
+// Signature Caching Tests
+// ============================================================================
+
+func TestConvertAntigravityResponseToClaude_SessionIDDerived(t *testing.T) {
+	cache.ClearSignatureCache("")
+
+	// Request with user message - should derive session ID
+	requestJSON := []byte(`{
+		"messages": [
+			{"role": "user", "content": [{"type": "text", "text": "Hello world"}]}
+		]
+	}`)
+
+	// First response chunk with thinking
+	responseJSON := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "Let me think...", "thought": true}]
+				}
+			}]
+		}
+	}`)
+
+	var param any
+	ctx := context.Background()
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, responseJSON, &param)
+
+	// Verify session ID was set
+	params := param.(*Params)
+	if params.SessionID == "" {
+		t.Error("SessionID should be derived from request")
+	}
+}
+
+func TestConvertAntigravityResponseToClaude_ThinkingTextAccumulated(t *testing.T) {
+	cache.ClearSignatureCache("")
+
+	requestJSON := []byte(`{
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Test"}]}]
+	}`)
+
+	// First thinking chunk
+	chunk1 := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "First part of thinking...", "thought": true}]
+				}
+			}]
+		}
+	}`)
+
+	// Second thinking chunk (continuation)
+	chunk2 := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": " Second part of thinking...", "thought": true}]
+				}
+			}]
+		}
+	}`)
+
+	var param any
+	ctx := context.Background()
+
+	// Process first chunk - starts new thinking block
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, chunk1, &param)
+	params := param.(*Params)
+
+	if params.CurrentThinkingText.Len() == 0 {
+		t.Error("Thinking text should be accumulated after first chunk")
+	}
+
+	// Process second chunk - continues thinking block
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, chunk2, &param)
+
+	text := params.CurrentThinkingText.String()
+	if !strings.Contains(text, "First part") || !strings.Contains(text, "Second part") {
+		t.Errorf("Thinking text should accumulate both parts, got: %s", text)
+	}
+}
+
+func TestConvertAntigravityResponseToClaude_SignatureCached(t *testing.T) {
+	cache.ClearSignatureCache("")
+
+	requestJSON := []byte(`{
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Cache test"}]}]
+	}`)
+
+	// Thinking chunk
+	thinkingChunk := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "My thinking process here", "thought": true}]
+				}
+			}]
+		}
+	}`)
+
+	// Signature chunk
+	validSignature := "abc123validSignature1234567890123456789012345678901234567890"
+	signatureChunk := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "", "thought": true, "thoughtSignature": "` + validSignature + `"}]
+				}
+			}]
+		}
+	}`)
+
+	var param any
+	ctx := context.Background()
+
+	// Process thinking chunk
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, thinkingChunk, &param)
+	params := param.(*Params)
+	sessionID := params.SessionID
+	thinkingText := params.CurrentThinkingText.String()
+
+	if sessionID == "" {
+		t.Fatal("SessionID should be set")
+	}
+	if thinkingText == "" {
+		t.Fatal("Thinking text should be accumulated")
+	}
+
+	// Process signature chunk - should cache the signature
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, signatureChunk, &param)
+
+	// Verify signature was cached
+	cachedSig := cache.GetCachedSignature(sessionID, thinkingText)
+	if cachedSig != validSignature {
+		t.Errorf("Expected cached signature '%s', got '%s'", validSignature, cachedSig)
+	}
+
+	// Verify thinking text was reset after caching
+	if params.CurrentThinkingText.Len() != 0 {
+		t.Error("Thinking text should be reset after signature is cached")
+	}
+}
+
+func TestConvertAntigravityResponseToClaude_MultipleThinkingBlocks(t *testing.T) {
+	cache.ClearSignatureCache("")
+
+	requestJSON := []byte(`{
+		"messages": [{"role": "user", "content": [{"type": "text", "text": "Multi block test"}]}]
+	}`)
+
+	validSig1 := "signature1_12345678901234567890123456789012345678901234567"
+	validSig2 := "signature2_12345678901234567890123456789012345678901234567"
+
+	// First thinking block with signature
+	block1Thinking := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "First thinking block", "thought": true}]
+				}
+			}]
+		}
+	}`)
+	block1Sig := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "", "thought": true, "thoughtSignature": "` + validSig1 + `"}]
+				}
+			}]
+		}
+	}`)
+
+	// Text content (breaks thinking)
+	textBlock := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "Regular text output"}]
+				}
+			}]
+		}
+	}`)
+
+	// Second thinking block with signature
+	block2Thinking := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "Second thinking block", "thought": true}]
+				}
+			}]
+		}
+	}`)
+	block2Sig := []byte(`{
+		"response": {
+			"candidates": [{
+				"content": {
+					"parts": [{"text": "", "thought": true, "thoughtSignature": "` + validSig2 + `"}]
+				}
+			}]
+		}
+	}`)
+
+	var param any
+	ctx := context.Background()
+
+	// Process first thinking block
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, block1Thinking, &param)
+	params := param.(*Params)
+	sessionID := params.SessionID
+	firstThinkingText := params.CurrentThinkingText.String()
+
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, block1Sig, &param)
+
+	// Verify first signature cached
+	if cache.GetCachedSignature(sessionID, firstThinkingText) != validSig1 {
+		t.Error("First thinking block signature should be cached")
+	}
+
+	// Process text (transitions out of thinking)
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, textBlock, &param)
+
+	// Process second thinking block
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, block2Thinking, &param)
+	secondThinkingText := params.CurrentThinkingText.String()
+
+	ConvertAntigravityResponseToClaude(ctx, "claude-sonnet-4-5-thinking", requestJSON, requestJSON, block2Sig, &param)
+
+	// Verify second signature cached
+	if cache.GetCachedSignature(sessionID, secondThinkingText) != validSig2 {
+		t.Error("Second thinking block signature should be cached")
+	}
+}
+
+func TestDeriveSessionIDFromRequest(t *testing.T) {
+	tests := []struct {
+		name      string
+		input     []byte
+		wantEmpty bool
+	}{
+		{
+			name:      "valid user message",
+			input:     []byte(`{"messages": [{"role": "user", "content": "Hello"}]}`),
+			wantEmpty: false,
+		},
+		{
+			name:      "user message with content array",
+			input:     []byte(`{"messages": [{"role": "user", "content": [{"type": "text", "text": "Hello"}]}]}`),
+			wantEmpty: false,
+		},
+		{
+			name:      "no user message",
+			input:     []byte(`{"messages": [{"role": "assistant", "content": "Hi"}]}`),
+			wantEmpty: true,
+		},
+		{
+			name:      "empty messages",
+			input:     []byte(`{"messages": []}`),
+			wantEmpty: true,
+		},
+		{
+			name:      "no messages field",
+			input:     []byte(`{}`),
+			wantEmpty: true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := deriveSessionID(tt.input)
+			if tt.wantEmpty && result != "" {
+				t.Errorf("Expected empty session ID, got '%s'", result)
+			}
+			if !tt.wantEmpty && result == "" {
+				t.Error("Expected non-empty session ID")
+			}
+		})
+	}
+}
+
+func TestDeriveSessionIDFromRequest_Deterministic(t *testing.T) {
+	input := []byte(`{"messages": [{"role": "user", "content": "Same message"}]}`)
+
+	id1 := deriveSessionID(input)
+	id2 := deriveSessionID(input)
+
+	if id1 != id2 {
+		t.Errorf("Session ID should be deterministic: '%s' != '%s'", id1, id2)
+	}
+}
+
+func TestDeriveSessionIDFromRequest_DifferentMessages(t *testing.T) {
+	input1 := []byte(`{"messages": [{"role": "user", "content": "Message A"}]}`)
+	input2 := []byte(`{"messages": [{"role": "user", "content": "Message B"}]}`)
+
+	id1 := deriveSessionID(input1)
+	id2 := deriveSessionID(input2)
+
+	if id1 == id2 {
+		t.Error("Different messages should produce different session IDs")
+	}
+}

internal/translator/antigravity/gemini/antigravity_gemini_request.go

@@ -7,7 +7,6 @@ package gemini
 
 import (
 	"bytes"
-	"encoding/json"
 	"fmt"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
@@ -98,16 +97,34 @@ func ConvertGeminiRequestToAntigravity(_ string, inputRawJSON []byte, _ bool) []
 		}
 	}
 
-	gjson.GetBytes(rawJSON, "request.contents").ForEach(func(key, content gjson.Result) bool {
+	// Gemini-specific handling: add skip_thought_signature_validator to functionCall parts
+	// and remove thinking blocks entirely (Gemini doesn't need to preserve them)
+	const skipSentinel = "skip_thought_signature_validator"
+
+	gjson.GetBytes(rawJSON, "request.contents").ForEach(func(contentIdx, content gjson.Result) bool {
 		if content.Get("role").String() == "model" {
-			content.Get("parts").ForEach(func(partKey, part gjson.Result) bool {
+			// First pass: collect indices of thinking parts to remove
+			var thinkingIndicesToRemove []int64
+			content.Get("parts").ForEach(func(partIdx, part gjson.Result) bool {
+				// Mark thinking blocks for removal
+				if part.Get("thought").Bool() {
+					thinkingIndicesToRemove = append(thinkingIndicesToRemove, partIdx.Int())
+				}
+				// Add skip sentinel to functionCall parts
 				if part.Get("functionCall").Exists() {
-					rawJSON, _ = sjson.SetBytes(rawJSON, fmt.Sprintf("request.contents.%d.parts.%d.thoughtSignature", key.Int(), partKey.Int()), "skip_thought_signature_validator")
-				} else if part.Get("thoughtSignature").Exists() {
-					rawJSON, _ = sjson.SetBytes(rawJSON, fmt.Sprintf("request.contents.%d.parts.%d.thoughtSignature", key.Int(), partKey.Int()), "skip_thought_signature_validator")
+					existingSig := part.Get("thoughtSignature").String()
+					if existingSig == "" || len(existingSig) < 50 {
+						rawJSON, _ = sjson.SetBytes(rawJSON, fmt.Sprintf("request.contents.%d.parts.%d.thoughtSignature", contentIdx.Int(), partIdx.Int()), skipSentinel)
+					}
 				}
 				return true
 			})
+
+			// Remove thinking blocks in reverse order to preserve indices
+			for i := len(thinkingIndicesToRemove) - 1; i >= 0; i-- {
+				idx := thinkingIndicesToRemove[i]
+				rawJSON, _ = sjson.DeleteBytes(rawJSON, fmt.Sprintf("request.contents.%d.parts.%d", contentIdx.Int(), idx))
+			}
 		}
 		return true
 	})
@@ -117,41 +134,31 @@ func ConvertGeminiRequestToAntigravity(_ string, inputRawJSON []byte, _ bool) []
 
 // FunctionCallGroup represents a group of function calls and their responses
 type FunctionCallGroup struct {
-	ModelContent    map[string]interface{}
-	FunctionCalls   []gjson.Result
 	ResponsesNeeded int
 }
 
-// parseFunctionResponse attempts to unmarshal a function response part.
-// Falls back to gjson extraction if standard json.Unmarshal fails.
-func parseFunctionResponse(response gjson.Result) map[string]interface{} {
-	var responseMap map[string]interface{}
-	err := json.Unmarshal([]byte(response.Raw), &responseMap)
-	if err == nil {
-		return responseMap
+// parseFunctionResponseRaw attempts to normalize a function response part into a JSON object string.
+// Falls back to a minimal "functionResponse" object when parsing fails.
+func parseFunctionResponseRaw(response gjson.Result) string {
+	if response.IsObject() && gjson.Valid(response.Raw) {
+		return response.Raw
 	}
 
-	log.Debugf("unmarshal function response failed, using fallback: %v", err)
+	log.Debugf("parse function response failed, using fallback")
 	funcResp := response.Get("functionResponse")
 	if funcResp.Exists() {
-		fr := map[string]interface{}{
-			"name": funcResp.Get("name").String(),
-			"response": map[string]interface{}{
-				"result": funcResp.Get("response").String(),
-			},
-		}
+		fr := `{"functionResponse":{"name":"","response":{"result":""}}}`
+		fr, _ = sjson.Set(fr, "functionResponse.name", funcResp.Get("name").String())
+		fr, _ = sjson.Set(fr, "functionResponse.response.result", funcResp.Get("response").String())
 		if id := funcResp.Get("id").String(); id != "" {
-			fr["id"] = id
+			fr, _ = sjson.Set(fr, "functionResponse.id", id)
 		}
-		return map[string]interface{}{"functionResponse": fr}
+		return fr
 	}
 
-	return map[string]interface{}{
-		"functionResponse": map[string]interface{}{
-			"name":     "unknown",
-			"response": map[string]interface{}{"result": response.String()},
-		},
-	}
+	fr := `{"functionResponse":{"name":"unknown","response":{"result":""}}}`
+	fr, _ = sjson.Set(fr, "functionResponse.response.result", response.String())
+	return fr
 }
 
 // fixCLIToolResponse performs sophisticated tool response format conversion and grouping.
@@ -178,7 +185,7 @@ func fixCLIToolResponse(input string) (string, error) {
 	}
 
 	// Initialize data structures for processing and grouping
-	var newContents []interface{}          // Final processed contents array
+	contentsWrapper := `{"contents":[]}`
 	var pendingGroups []*FunctionCallGroup // Groups awaiting completion with responses
 	var collectedResponses []gjson.Result  // Standalone responses to be matched
 
@@ -210,17 +217,16 @@ func fixCLIToolResponse(input string) (string, error) {
 					collectedResponses = collectedResponses[group.ResponsesNeeded:]
 
 					// Create merged function response content
-					var responseParts []interface{}
+					functionResponseContent := `{"parts":[],"role":"function"}`
 					for _, response := range groupResponses {
-						responseParts = append(responseParts, parseFunctionResponse(response))
+						partRaw := parseFunctionResponseRaw(response)
+						if partRaw != "" {
+							functionResponseContent, _ = sjson.SetRaw(functionResponseContent, "parts.-1", partRaw)
+						}
 					}
 
-					if len(responseParts) > 0 {
-						functionResponseContent := map[string]interface{}{
-							"parts": responseParts,
-							"role":  "function",
-						}
-						newContents = append(newContents, functionResponseContent)
+					if gjson.Get(functionResponseContent, "parts.#").Int() > 0 {
+						contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", functionResponseContent)
 					}
 
 					// Remove this group as it's been satisfied
@@ -234,50 +240,42 @@ func fixCLIToolResponse(input string) (string, error) {
 
 		// If this is a model with function calls, create a new group
 		if role == "model" {
-			var functionCallsInThisModel []gjson.Result
+			functionCallsCount := 0
 			parts.ForEach(func(_, part gjson.Result) bool {
 				if part.Get("functionCall").Exists() {
-					functionCallsInThisModel = append(functionCallsInThisModel, part)
+					functionCallsCount++
 				}
 				return true
 			})
 
-			if len(functionCallsInThisModel) > 0 {
+			if functionCallsCount > 0 {
 				// Add the model content
-				var contentMap map[string]interface{}
-				errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
-				if errUnmarshal != nil {
-					log.Warnf("failed to unmarshal model content: %v\n", errUnmarshal)
+				if !value.IsObject() {
+					log.Warnf("failed to parse model content")
 					return true
 				}
-				newContents = append(newContents, contentMap)
+				contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", value.Raw)
 
 				// Create a new group for tracking responses
 				group := &FunctionCallGroup{
-					ModelContent:    contentMap,
-					FunctionCalls:   functionCallsInThisModel,
-					ResponsesNeeded: len(functionCallsInThisModel),
+					ResponsesNeeded: functionCallsCount,
 				}
 				pendingGroups = append(pendingGroups, group)
 			} else {
 				// Regular model content without function calls
-				var contentMap map[string]interface{}
-				errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
-				if errUnmarshal != nil {
-					log.Warnf("failed to unmarshal content: %v\n", errUnmarshal)
+				if !value.IsObject() {
+					log.Warnf("failed to parse content")
 					return true
 				}
-				newContents = append(newContents, contentMap)
+				contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", value.Raw)
 			}
 		} else {
 			// Non-model content (user, etc.)
-			var contentMap map[string]interface{}
-			errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
-			if errUnmarshal != nil {
-				log.Warnf("failed to unmarshal content: %v\n", errUnmarshal)
+			if !value.IsObject() {
+				log.Warnf("failed to parse content")
 				return true
 			}
-			newContents = append(newContents, contentMap)
+			contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", value.Raw)
 		}
 
 		return true
@@ -289,25 +287,23 @@ func fixCLIToolResponse(input string) (string, error) {
 			groupResponses := collectedResponses[:group.ResponsesNeeded]
 			collectedResponses = collectedResponses[group.ResponsesNeeded:]
 
-			var responseParts []interface{}
+			functionResponseContent := `{"parts":[],"role":"function"}`
 			for _, response := range groupResponses {
-				responseParts = append(responseParts, parseFunctionResponse(response))
+				partRaw := parseFunctionResponseRaw(response)
+				if partRaw != "" {
+					functionResponseContent, _ = sjson.SetRaw(functionResponseContent, "parts.-1", partRaw)
+				}
 			}
 
-			if len(responseParts) > 0 {
-				functionResponseContent := map[string]interface{}{
-					"parts": responseParts,
-					"role":  "function",
-				}
-				newContents = append(newContents, functionResponseContent)
+			if gjson.Get(functionResponseContent, "parts.#").Int() > 0 {
+				contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", functionResponseContent)
 			}
 		}
 	}
 
 	// Update the original JSON with the new contents
 	result := input
-	newContentsJSON, _ := json.Marshal(newContents)
-	result, _ = sjson.Set(result, "request.contents", json.RawMessage(newContentsJSON))
+	result, _ = sjson.SetRaw(result, "request.contents", gjson.Get(contentsWrapper, "contents").Raw)
 
 	return result, nil
 }

internal/translator/antigravity/gemini/antigravity_gemini_request_test.go

@@ -0,0 +1,129 @@
+package gemini
+
+import (
+	"fmt"
+	"testing"
+
+	"github.com/tidwall/gjson"
+)
+
+func TestConvertGeminiRequestToAntigravity_PreserveValidSignature(t *testing.T) {
+	// Valid signature on functionCall should be preserved
+	validSignature := "abc123validSignature1234567890123456789012345678901234567890"
+	inputJSON := []byte(fmt.Sprintf(`{
+		"model": "gemini-3-pro-preview",
+		"contents": [
+			{
+				"role": "model",
+				"parts": [
+					{"functionCall": {"name": "test_tool", "args": {}}, "thoughtSignature": "%s"}
+				]
+			}
+		]
+	}`, validSignature))
+
+	output := ConvertGeminiRequestToAntigravity("gemini-3-pro-preview", inputJSON, false)
+	outputStr := string(output)
+
+	// Check that valid thoughtSignature is preserved
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 1 {
+		t.Fatalf("Expected 1 part, got %d", len(parts))
+	}
+
+	sig := parts[0].Get("thoughtSignature").String()
+	if sig != validSignature {
+		t.Errorf("Expected thoughtSignature '%s', got '%s'", validSignature, sig)
+	}
+}
+
+func TestConvertGeminiRequestToAntigravity_AddSkipSentinelToFunctionCall(t *testing.T) {
+	// functionCall without signature should get skip_thought_signature_validator
+	inputJSON := []byte(`{
+		"model": "gemini-3-pro-preview",
+		"contents": [
+			{
+				"role": "model",
+				"parts": [
+					{"functionCall": {"name": "test_tool", "args": {}}}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertGeminiRequestToAntigravity("gemini-3-pro-preview", inputJSON, false)
+	outputStr := string(output)
+
+	// Check that skip_thought_signature_validator is added to functionCall
+	sig := gjson.Get(outputStr, "request.contents.0.parts.0.thoughtSignature").String()
+	expectedSig := "skip_thought_signature_validator"
+	if sig != expectedSig {
+		t.Errorf("Expected skip sentinel '%s', got '%s'", expectedSig, sig)
+	}
+}
+
+func TestConvertGeminiRequestToAntigravity_RemoveThinkingBlocks(t *testing.T) {
+	// Thinking blocks should be removed entirely for Gemini
+	validSignature := "abc123validSignature1234567890123456789012345678901234567890"
+	inputJSON := []byte(fmt.Sprintf(`{
+		"model": "gemini-3-pro-preview",
+		"contents": [
+			{
+				"role": "model",
+				"parts": [
+					{"thought": true, "text": "Thinking...", "thoughtSignature": "%s"},
+					{"text": "Here is my response"}
+				]
+			}
+		]
+	}`, validSignature))
+
+	output := ConvertGeminiRequestToAntigravity("gemini-3-pro-preview", inputJSON, false)
+	outputStr := string(output)
+
+	// Check that thinking block is removed
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 1 {
+		t.Fatalf("Expected 1 part (thinking removed), got %d", len(parts))
+	}
+
+	// Only text part should remain
+	if parts[0].Get("thought").Bool() {
+		t.Error("Thinking block should be removed for Gemini")
+	}
+	if parts[0].Get("text").String() != "Here is my response" {
+		t.Errorf("Expected text 'Here is my response', got '%s'", parts[0].Get("text").String())
+	}
+}
+
+func TestConvertGeminiRequestToAntigravity_ParallelFunctionCalls(t *testing.T) {
+	// Multiple functionCalls should all get skip_thought_signature_validator
+	inputJSON := []byte(`{
+		"model": "gemini-3-pro-preview",
+		"contents": [
+			{
+				"role": "model",
+				"parts": [
+					{"functionCall": {"name": "tool_one", "args": {"a": "1"}}},
+					{"functionCall": {"name": "tool_two", "args": {"b": "2"}}}
+				]
+			}
+		]
+	}`)
+
+	output := ConvertGeminiRequestToAntigravity("gemini-3-pro-preview", inputJSON, false)
+	outputStr := string(output)
+
+	parts := gjson.Get(outputStr, "request.contents.0.parts").Array()
+	if len(parts) != 2 {
+		t.Fatalf("Expected 2 parts, got %d", len(parts))
+	}
+
+	expectedSig := "skip_thought_signature_validator"
+	for i, part := range parts {
+		sig := part.Get("thoughtSignature").String()
+		if sig != expectedSig {
+			t.Errorf("Part %d: Expected '%s', got '%s'", i, expectedSig, sig)
+		}
+	}
+}

internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go

@@ -192,6 +192,14 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 				} else if content.IsObject() && content.Get("type").String() == "text" {
 					out, _ = sjson.SetBytes(out, "request.systemInstruction.role", "user")
 					out, _ = sjson.SetBytes(out, "request.systemInstruction.parts.0.text", content.Get("text").String())
+				} else if content.IsArray() {
+					contents := content.Array()
+					if len(contents) > 0 {
+						out, _ = sjson.SetBytes(out, "request.systemInstruction.role", "user")
+						for j := 0; j < len(contents); j++ {
+							out, _ = sjson.SetBytes(out, fmt.Sprintf("request.systemInstruction.parts.%d.text", j), contents[j].Get("text").String())
+						}
+					}
 				}
 			} else if role == "user" || (role == "system" && len(arr) == 1) {
 				// Build single user content node to avoid splitting into multiple contents
@@ -239,10 +247,30 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 			} else if role == "assistant" {
 				node := []byte(`{"role":"model","parts":[]}`)
 				p := 0
-				if content.Type == gjson.String {
+				if content.Type == gjson.String && content.String() != "" {
 					node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
-					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 					p++
+				} else if content.IsArray() {
+					// Assistant multimodal content (e.g. text + image) -> single model content with parts
+					for _, item := range content.Array() {
+						switch item.Get("type").String() {
+						case "text":
+							p++
+						case "image_url":
+							// If the assistant returned an inline data URL, preserve it for history fidelity.
+							imageURL := item.Get("image_url.url").String()
+							if len(imageURL) > 5 { // expect data:...
+								pieces := strings.SplitN(imageURL[5:], ";", 2)
+								if len(pieces) == 2 && len(pieces[1]) > 7 {
+									mime := pieces[0]
+									data := pieces[1][7:]
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.mime_type", mime)
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.data", data)
+									p++
+								}
+							}
+						}
+					}
 				}
 
 				// Tool calls -> single model content with functionCall parts
@@ -258,7 +286,11 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 						fargs := tc.Get("function.arguments").String()
 						node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".functionCall.id", fid)
 						node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".functionCall.name", fname)
-						node, _ = sjson.SetRawBytes(node, "parts."+itoa(p)+".functionCall.args", []byte(fargs))
+						if gjson.Valid(fargs) {
+							node, _ = sjson.SetRawBytes(node, "parts."+itoa(p)+".functionCall.args", []byte(fargs))
+						} else {
+							node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".functionCall.args.params", []byte(fargs))
+						}
 						node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".thoughtSignature", geminiCLIFunctionThoughtSignature)
 						p++
 						if fid != "" {
@@ -293,6 +325,8 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 					if pp > 0 {
 						out, _ = sjson.SetRawBytes(out, "request.contents.-1", toolNode)
 					}
+				} else {
+					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 				}
 			}
 		}
@@ -319,7 +353,7 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 								log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
 								continue
 							}
-							fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+							fnRaw, errSet = sjson.SetRaw(fnRaw, "parametersJsonSchema.properties", `{}`)
 							if errSet != nil {
 								log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
 								continue
@@ -334,7 +368,7 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 							log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
 							continue
 						}
-						fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+						fnRaw, errSet = sjson.SetRaw(fnRaw, "parametersJsonSchema.properties", `{}`)
 						if errSet != nil {
 							log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
 							continue

internal/translator/antigravity/openai/chat-completions/antigravity_openai_response.go

@@ -8,12 +8,13 @@ package chat_completions
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 	"sync/atomic"
 	"time"
 
+	log "github.com/sirupsen/logrus"
+
 	. "github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/openai/chat-completions"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
@@ -86,18 +87,27 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
 
 	// Extract and set usage metadata (token counts).
 	if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
+		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
 		}
 		if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
 		}
-		promptTokenCount := usageResult.Get("promptTokenCount").Int()
+		promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
 		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
 		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
 		if thoughtsTokenCount > 0 {
 			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
 		}
+		// Include cached token count if present (indicates prompt caching is working)
+		if cachedTokenCount > 0 {
+			var err error
+			template, err = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cachedTokenCount)
+			if err != nil {
+				log.Warnf("antigravity openai response: failed to set cached_tokens: %v", err)
+			}
+		}
 	}
 
 	// Process the main content part of the response.
@@ -171,21 +181,16 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload, err := json.Marshal(map[string]any{
-					"type": "image_url",
-					"image_url": map[string]string{
-						"url": imageURL,
-					},
-				})
-				if err != nil {
-					continue
-				}
 				imagesResult := gjson.Get(template, "choices.0.delta.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
-				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", string(imagePayload))
+				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
 			}
 		}
 	}

internal/translator/claude/gemini/claude_gemini_request.go

@@ -194,7 +194,7 @@ func ConvertGeminiRequestToClaude(modelName string, inputRawJSON []byte, stream
 						if name := fc.Get("name"); name.Exists() {
 							toolUse, _ = sjson.Set(toolUse, "name", name.String())
 						}
-						if args := fc.Get("args"); args.Exists() {
+						if args := fc.Get("args"); args.Exists() && args.IsObject() {
 							toolUse, _ = sjson.SetRaw(toolUse, "input", args.Raw)
 						}
 						msg, _ = sjson.SetRaw(msg, "content.-1", toolUse)
@@ -314,11 +314,11 @@ func ConvertGeminiRequestToClaude(modelName string, inputRawJSON []byte, stream
 			if mode := funcCalling.Get("mode"); mode.Exists() {
 				switch mode.String() {
 				case "AUTO":
-					out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "auto"})
+					out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"auto"}`)
 				case "NONE":
-					out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "none"})
+					out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"none"}`)
 				case "ANY":
-					out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "any"})
+					out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"any"}`)
 				}
 			}
 		}

internal/translator/claude/gemini/claude_gemini_response.go

@@ -263,51 +263,6 @@ func ConvertClaudeResponseToGemini(_ context.Context, modelName string, original
 	}
 }
 
-// convertArrayToJSON converts []interface{} to JSON array string
-func convertArrayToJSON(arr []interface{}) string {
-	result := "[]"
-	for _, item := range arr {
-		switch itemData := item.(type) {
-		case map[string]interface{}:
-			itemJSON := convertMapToJSON(itemData)
-			result, _ = sjson.SetRaw(result, "-1", itemJSON)
-		case string:
-			result, _ = sjson.Set(result, "-1", itemData)
-		case bool:
-			result, _ = sjson.Set(result, "-1", itemData)
-		case float64, int, int64:
-			result, _ = sjson.Set(result, "-1", itemData)
-		default:
-			result, _ = sjson.Set(result, "-1", itemData)
-		}
-	}
-	return result
-}
-
-// convertMapToJSON converts map[string]interface{} to JSON object string
-func convertMapToJSON(m map[string]interface{}) string {
-	result := "{}"
-	for key, value := range m {
-		switch val := value.(type) {
-		case map[string]interface{}:
-			nestedJSON := convertMapToJSON(val)
-			result, _ = sjson.SetRaw(result, key, nestedJSON)
-		case []interface{}:
-			arrayJSON := convertArrayToJSON(val)
-			result, _ = sjson.SetRaw(result, key, arrayJSON)
-		case string:
-			result, _ = sjson.Set(result, key, val)
-		case bool:
-			result, _ = sjson.Set(result, key, val)
-		case float64, int, int64:
-			result, _ = sjson.Set(result, key, val)
-		default:
-			result, _ = sjson.Set(result, key, val)
-		}
-	}
-	return result
-}
-
 // ConvertClaudeResponseToGeminiNonStream converts a non-streaming Claude Code response to a non-streaming Gemini response.
 // This function processes the complete Claude Code response and transforms it into a single Gemini-compatible
 // JSON response. It handles message content, tool calls, reasoning content, and usage metadata, combining all
@@ -356,8 +311,8 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 	}
 
 	// Process each streaming event and collect parts
-	var allParts []interface{}
-	var finalUsage map[string]interface{}
+	var allParts []string
+	var finalUsageJSON string
 	var responseID string
 	var createdAt int64
 
@@ -407,16 +362,14 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 					if text := delta.Get("text"); text.Exists() && text.String() != "" {
 						partJSON := `{"text":""}`
 						partJSON, _ = sjson.Set(partJSON, "text", text.String())
-						part := gjson.Parse(partJSON).Value().(map[string]interface{})
-						allParts = append(allParts, part)
+						allParts = append(allParts, partJSON)
 					}
 				case "thinking_delta":
 					// Process reasoning/thinking content
 					if text := delta.Get("thinking"); text.Exists() && text.String() != "" {
 						partJSON := `{"thought":true,"text":""}`
 						partJSON, _ = sjson.Set(partJSON, "text", text.String())
-						part := gjson.Parse(partJSON).Value().(map[string]interface{})
-						allParts = append(allParts, part)
+						allParts = append(allParts, partJSON)
 					}
 				case "input_json_delta":
 					// accumulate args partial_json for this index
@@ -456,9 +409,7 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 				if argsTrim != "" {
 					functionCallJSON, _ = sjson.SetRaw(functionCallJSON, "functionCall.args", argsTrim)
 				}
-				// Parse back to interface{} for allParts
-				functionCall := gjson.Parse(functionCallJSON).Value().(map[string]interface{})
-				allParts = append(allParts, functionCall)
+				allParts = append(allParts, functionCallJSON)
 				// cleanup used state for this index
 				if newParam.ToolUseArgs != nil {
 					delete(newParam.ToolUseArgs, idx)
@@ -501,8 +452,7 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 				// Set traffic type (required by Gemini API)
 				usageJSON, _ = sjson.Set(usageJSON, "trafficType", "PROVISIONED_THROUGHPUT")
 
-				// Convert to map[string]interface{} using gjson
-				finalUsage = gjson.Parse(usageJSON).Value().(map[string]interface{})
+				finalUsageJSON = usageJSON
 			}
 		}
 	}
@@ -520,12 +470,16 @@ func ConvertClaudeResponseToGeminiNonStream(_ context.Context, modelName string,
 
 	// Set the consolidated parts array
 	if len(consolidatedParts) > 0 {
-		template, _ = sjson.SetRaw(template, "candidates.0.content.parts", convertToJSONString(consolidatedParts))
+		partsJSON := "[]"
+		for _, partJSON := range consolidatedParts {
+			partsJSON, _ = sjson.SetRaw(partsJSON, "-1", partJSON)
+		}
+		template, _ = sjson.SetRaw(template, "candidates.0.content.parts", partsJSON)
 	}
 
 	// Set usage metadata
-	if finalUsage != nil {
-		template, _ = sjson.SetRaw(template, "usageMetadata", convertToJSONString(finalUsage))
+	if finalUsageJSON != "" {
+		template, _ = sjson.SetRaw(template, "usageMetadata", finalUsageJSON)
 	}
 
 	return template
@@ -539,12 +493,12 @@ func GeminiTokenCount(ctx context.Context, count int64) string {
 // This function processes the parts array to combine adjacent text elements and thinking elements
 // into single consolidated parts, which results in a more readable and efficient response structure.
 // Tool calls and other non-text parts are preserved as separate elements.
-func consolidateParts(parts []interface{}) []interface{} {
+func consolidateParts(parts []string) []string {
 	if len(parts) == 0 {
 		return parts
 	}
 
-	var consolidated []interface{}
+	var consolidated []string
 	var currentTextPart strings.Builder
 	var currentThoughtPart strings.Builder
 	var hasText, hasThought bool
@@ -554,8 +508,7 @@ func consolidateParts(parts []interface{}) []interface{} {
 		if hasText && currentTextPart.Len() > 0 {
 			textPartJSON := `{"text":""}`
 			textPartJSON, _ = sjson.Set(textPartJSON, "text", currentTextPart.String())
-			textPart := gjson.Parse(textPartJSON).Value().(map[string]interface{})
-			consolidated = append(consolidated, textPart)
+			consolidated = append(consolidated, textPartJSON)
 			currentTextPart.Reset()
 			hasText = false
 		}
@@ -566,42 +519,42 @@ func consolidateParts(parts []interface{}) []interface{} {
 		if hasThought && currentThoughtPart.Len() > 0 {
 			thoughtPartJSON := `{"thought":true,"text":""}`
 			thoughtPartJSON, _ = sjson.Set(thoughtPartJSON, "text", currentThoughtPart.String())
-			thoughtPart := gjson.Parse(thoughtPartJSON).Value().(map[string]interface{})
-			consolidated = append(consolidated, thoughtPart)
+			consolidated = append(consolidated, thoughtPartJSON)
 			currentThoughtPart.Reset()
 			hasThought = false
 		}
 	}
 
-	for _, part := range parts {
-		partMap, ok := part.(map[string]interface{})
-		if !ok {
+	for _, partJSON := range parts {
+		part := gjson.Parse(partJSON)
+		if !part.Exists() || !part.IsObject() {
 			// Flush any pending parts and add this non-text part
 			flushText()
 			flushThought()
-			consolidated = append(consolidated, part)
+			consolidated = append(consolidated, partJSON)
 			continue
 		}
 
-		if thought, isThought := partMap["thought"]; isThought && thought == true {
+		thought := part.Get("thought")
+		if thought.Exists() && thought.Type == gjson.True {
 			// This is a thinking part - flush any pending text first
 			flushText() // Flush any pending text first
 
-			if text, hasTextContent := partMap["text"].(string); hasTextContent {
-				currentThoughtPart.WriteString(text)
+			if text := part.Get("text"); text.Exists() && text.Type == gjson.String {
+				currentThoughtPart.WriteString(text.String())
 				hasThought = true
 			}
-		} else if text, hasTextContent := partMap["text"].(string); hasTextContent {
+		} else if text := part.Get("text"); text.Exists() && text.Type == gjson.String {
 			// This is a regular text part - flush any pending thought first
 			flushThought() // Flush any pending thought first
 
-			currentTextPart.WriteString(text)
+			currentTextPart.WriteString(text.String())
 			hasText = true
 		} else {
 			// This is some other type of part (like function call) - flush both text and thought
 			flushText()
 			flushThought()
-			consolidated = append(consolidated, part)
+			consolidated = append(consolidated, partJSON)
 		}
 	}
 
@@ -611,20 +564,3 @@ func consolidateParts(parts []interface{}) []interface{} {
 
 	return consolidated
 }
-
-// convertToJSONString converts interface{} to JSON string using sjson/gjson.
-// This function provides a consistent way to serialize different data types to JSON strings
-// for inclusion in the Gemini API response structure.
-func convertToJSONString(v interface{}) string {
-	switch val := v.(type) {
-	case []interface{}:
-		return convertArrayToJSON(val)
-	case map[string]interface{}:
-		return convertMapToJSON(val)
-	default:
-		// For simple types, create a temporary JSON and extract the value
-		temp := `{"temp":null}`
-		temp, _ = sjson.Set(temp, "temp", val)
-		return gjson.Get(temp, "temp").Raw
-	}
-}

internal/translator/claude/openai/chat-completions/claude_openai_request.go

@@ -10,7 +10,6 @@ import (
 	"crypto/rand"
 	"crypto/sha256"
 	"encoding/hex"
-	"encoding/json"
 	"fmt"
 	"math/big"
 	"strings"
@@ -137,9 +136,6 @@ func ConvertOpenAIRequestToClaude(modelName string, inputRawJSON []byte, stream
 	out, _ = sjson.Set(out, "stream", stream)
 
 	// Process messages and transform them to Claude Code format
-	var anthropicMessages []interface{}
-	var toolCallIDs []string // Track tool call IDs for matching with tool results
-
 	if messages := root.Get("messages"); messages.Exists() && messages.IsArray() {
 		messages.ForEach(func(_, message gjson.Result) bool {
 			role := message.Get("role").String()
@@ -152,33 +148,23 @@ func ConvertOpenAIRequestToClaude(modelName string, inputRawJSON []byte, stream
 					role = "user"
 				}
 
-				msg := map[string]interface{}{
-					"role":    role,
-					"content": []interface{}{},
-				}
+				msg := `{"role":"","content":[]}`
+				msg, _ = sjson.Set(msg, "role", role)
 
 				// Handle content based on its type (string or array)
 				if contentResult.Exists() && contentResult.Type == gjson.String && contentResult.String() != "" {
-					// Simple text content conversion
-					msg["content"] = []interface{}{
-						map[string]interface{}{
-							"type": "text",
-							"text": contentResult.String(),
-						},
-					}
+					part := `{"type":"text","text":""}`
+					part, _ = sjson.Set(part, "text", contentResult.String())
+					msg, _ = sjson.SetRaw(msg, "content.-1", part)
 				} else if contentResult.Exists() && contentResult.IsArray() {
-					// Array of content parts processing
-					var contentParts []interface{}
 					contentResult.ForEach(func(_, part gjson.Result) bool {
 						partType := part.Get("type").String()
 
 						switch partType {
 						case "text":
-							// Text part conversion
-							contentParts = append(contentParts, map[string]interface{}{
-								"type": "text",
-								"text": part.Get("text").String(),
-							})
+							textPart := `{"type":"text","text":""}`
+							textPart, _ = sjson.Set(textPart, "text", part.Get("text").String())
+							msg, _ = sjson.SetRaw(msg, "content.-1", textPart)
 
 						case "image_url":
 							// Convert OpenAI image format to Claude Code format
@@ -191,132 +177,95 @@ func ConvertOpenAIRequestToClaude(modelName string, inputRawJSON []byte, stream
 									mediaType := strings.TrimPrefix(mediaTypePart, "data:")
 									data := parts[1]
 
-									contentParts = append(contentParts, map[string]interface{}{
-										"type": "image",
-										"source": map[string]interface{}{
-											"type":       "base64",
-											"media_type": mediaType,
-											"data":       data,
-										},
-									})
+									imagePart := `{"type":"image","source":{"type":"base64","media_type":"","data":""}}`
+									imagePart, _ = sjson.Set(imagePart, "source.media_type", mediaType)
+									imagePart, _ = sjson.Set(imagePart, "source.data", data)
+									msg, _ = sjson.SetRaw(msg, "content.-1", imagePart)
 								}
 							}
 						}
 						return true
 					})
-					if len(contentParts) > 0 {
-						msg["content"] = contentParts
-					}
-				} else {
-					// Initialize empty content array for tool calls
-					msg["content"] = []interface{}{}
 				}
 
 				// Handle tool calls (for assistant messages)
 				if toolCalls := message.Get("tool_calls"); toolCalls.Exists() && toolCalls.IsArray() && role == "assistant" {
-					var contentParts []interface{}
-
-					// Add existing text content if any
-					if existingContent, ok := msg["content"].([]interface{}); ok {
-						contentParts = existingContent
-					}
-
 					toolCalls.ForEach(func(_, toolCall gjson.Result) bool {
 						if toolCall.Get("type").String() == "function" {
 							toolCallID := toolCall.Get("id").String()
 							if toolCallID == "" {
 								toolCallID = genToolCallID()
 							}
-							toolCallIDs = append(toolCallIDs, toolCallID)
 
 							function := toolCall.Get("function")
-							toolUse := map[string]interface{}{
-								"type": "tool_use",
-								"id":   toolCallID,
-								"name": function.Get("name").String(),
-							}
+							toolUse := `{"type":"tool_use","id":"","name":"","input":{}}`
+							toolUse, _ = sjson.Set(toolUse, "id", toolCallID)
+							toolUse, _ = sjson.Set(toolUse, "name", function.Get("name").String())
 
 							// Parse arguments for the tool call
 							if args := function.Get("arguments"); args.Exists() {
 								argsStr := args.String()
-								if argsStr != "" {
-									var argsMap map[string]interface{}
-									if err := json.Unmarshal([]byte(argsStr), &argsMap); err == nil {
-										toolUse["input"] = argsMap
+								if argsStr != "" && gjson.Valid(argsStr) {
+									argsJSON := gjson.Parse(argsStr)
+									if argsJSON.IsObject() {
+										toolUse, _ = sjson.SetRaw(toolUse, "input", argsJSON.Raw)
 									} else {
-										toolUse["input"] = map[string]interface{}{}
+										toolUse, _ = sjson.SetRaw(toolUse, "input", "{}")
 									}
 								} else {
-									toolUse["input"] = map[string]interface{}{}
+									toolUse, _ = sjson.SetRaw(toolUse, "input", "{}")
 								}
 							} else {
-								toolUse["input"] = map[string]interface{}{}
+								toolUse, _ = sjson.SetRaw(toolUse, "input", "{}")
 							}
 
-							contentParts = append(contentParts, toolUse)
+							msg, _ = sjson.SetRaw(msg, "content.-1", toolUse)
 						}
 						return true
 					})
-					msg["content"] = contentParts
 				}
 
-				anthropicMessages = append(anthropicMessages, msg)
+				out, _ = sjson.SetRaw(out, "messages.-1", msg)
 
 			case "tool":
 				// Handle tool result messages conversion
 				toolCallID := message.Get("tool_call_id").String()
 				content := message.Get("content").String()
 
-				// Create tool result message in Claude Code format
-				msg := map[string]interface{}{
-					"role": "user",
-					"content": []interface{}{
-						map[string]interface{}{
-							"type":        "tool_result",
-							"tool_use_id": toolCallID,
-							"content":     content,
-						},
-					},
-				}
-
-				anthropicMessages = append(anthropicMessages, msg)
+				msg := `{"role":"user","content":[{"type":"tool_result","tool_use_id":"","content":""}]}`
+				msg, _ = sjson.Set(msg, "content.0.tool_use_id", toolCallID)
+				msg, _ = sjson.Set(msg, "content.0.content", content)
+				out, _ = sjson.SetRaw(out, "messages.-1", msg)
 			}
 			return true
 		})
 	}
 
-	// Set messages in the output template
-	if len(anthropicMessages) > 0 {
-		messagesJSON, _ := json.Marshal(anthropicMessages)
-		out, _ = sjson.SetRaw(out, "messages", string(messagesJSON))
-	}
-
 	// Tools mapping: OpenAI tools -> Claude Code tools
 	if tools := root.Get("tools"); tools.Exists() && tools.IsArray() && len(tools.Array()) > 0 {
-		var anthropicTools []interface{}
+		hasAnthropicTools := false
 		tools.ForEach(func(_, tool gjson.Result) bool {
 			if tool.Get("type").String() == "function" {
 				function := tool.Get("function")
-				anthropicTool := map[string]interface{}{
-					"name":        function.Get("name").String(),
-					"description": function.Get("description").String(),
-				}
+				anthropicTool := `{"name":"","description":""}`
+				anthropicTool, _ = sjson.Set(anthropicTool, "name", function.Get("name").String())
+				anthropicTool, _ = sjson.Set(anthropicTool, "description", function.Get("description").String())
 
 				// Convert parameters schema for the tool
 				if parameters := function.Get("parameters"); parameters.Exists() {
-					anthropicTool["input_schema"] = parameters.Value()
-				} else if parameters = function.Get("parametersJsonSchema"); parameters.Exists() {
-					anthropicTool["input_schema"] = parameters.Value()
+					anthropicTool, _ = sjson.SetRaw(anthropicTool, "input_schema", parameters.Raw)
+				} else if parameters := function.Get("parametersJsonSchema"); parameters.Exists() {
+					anthropicTool, _ = sjson.SetRaw(anthropicTool, "input_schema", parameters.Raw)
 				}
 
-				anthropicTools = append(anthropicTools, anthropicTool)
+				out, _ = sjson.SetRaw(out, "tools.-1", anthropicTool)
+				hasAnthropicTools = true
 			}
 			return true
 		})
 
-		if len(anthropicTools) > 0 {
-			toolsJSON, _ := json.Marshal(anthropicTools)
-			out, _ = sjson.SetRaw(out, "tools", string(toolsJSON))
+		if !hasAnthropicTools {
+			out, _ = sjson.Delete(out, "tools")
 		}
 	}
 
@@ -329,18 +278,17 @@ func ConvertOpenAIRequestToClaude(modelName string, inputRawJSON []byte, stream
 			case "none":
 				// Don't set tool_choice, Claude Code will not use tools
 			case "auto":
-				out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "auto"})
+				out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"auto"}`)
 			case "required":
-				out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "any"})
+				out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"any"}`)
 			}
 		case gjson.JSON:
 			// Specific tool choice mapping
 			if toolChoice.Get("type").String() == "function" {
 				functionName := toolChoice.Get("function.name").String()
-				out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{
-					"type": "tool",
-					"name": functionName,
-				})
+				toolChoiceJSON := `{"type":"tool","name":""}`
+				toolChoiceJSON, _ = sjson.Set(toolChoiceJSON, "name", functionName)
+				out, _ = sjson.SetRaw(out, "tool_choice", toolChoiceJSON)
 			}
 		default:
 		}

internal/translator/claude/openai/chat-completions/claude_openai_response.go

@@ -8,7 +8,7 @@ package chat_completions
 import (
 	"bytes"
 	"context"
-	"encoding/json"
+	"fmt"
 	"strings"
 	"time"
 
@@ -178,18 +178,11 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
 				if arguments == "" {
 					arguments = "{}"
 				}
-
-				toolCall := map[string]interface{}{
-					"index": index,
-					"id":    accumulator.ID,
-					"type":  "function",
-					"function": map[string]interface{}{
-						"name":      accumulator.Name,
-						"arguments": arguments,
-					},
-				}
-
-				template, _ = sjson.Set(template, "choices.0.delta.tool_calls", []interface{}{toolCall})
+				template, _ = sjson.Set(template, "choices.0.delta.tool_calls.0.index", index)
+				template, _ = sjson.Set(template, "choices.0.delta.tool_calls.0.id", accumulator.ID)
+				template, _ = sjson.Set(template, "choices.0.delta.tool_calls.0.type", "function")
+				template, _ = sjson.Set(template, "choices.0.delta.tool_calls.0.function.name", accumulator.Name)
+				template, _ = sjson.Set(template, "choices.0.delta.tool_calls.0.function.arguments", arguments)
 
 				// Clean up the accumulator for this index
 				delete((*param).(*ConvertAnthropicResponseToOpenAIParams).ToolCallsAccumulator, index)
@@ -210,12 +203,14 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
 
 		// Handle usage information for token counts
 		if usage := root.Get("usage"); usage.Exists() {
-			usageObj := map[string]interface{}{
-				"prompt_tokens":     usage.Get("input_tokens").Int(),
-				"completion_tokens": usage.Get("output_tokens").Int(),
-				"total_tokens":      usage.Get("input_tokens").Int() + usage.Get("output_tokens").Int(),
-			}
-			template, _ = sjson.Set(template, "usage", usageObj)
+			inputTokens := usage.Get("input_tokens").Int()
+			outputTokens := usage.Get("output_tokens").Int()
+			cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
+			cacheCreationInputTokens := usage.Get("cache_creation_input_tokens").Int()
+			template, _ = sjson.Set(template, "usage.prompt_tokens", inputTokens+cacheCreationInputTokens)
+			template, _ = sjson.Set(template, "usage.completion_tokens", outputTokens)
+			template, _ = sjson.Set(template, "usage.total_tokens", inputTokens+outputTokens)
+			template, _ = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
 		}
 		return []string{template}
 
@@ -230,14 +225,10 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
 	case "error":
 		// Error event - format and return error response
 		if errorData := root.Get("error"); errorData.Exists() {
-			errorResponse := map[string]interface{}{
-				"error": map[string]interface{}{
-					"message": errorData.Get("message").String(),
-					"type":    errorData.Get("type").String(),
-				},
-			}
-			errorJSON, _ := json.Marshal(errorResponse)
-			return []string{string(errorJSON)}
+			errorJSON := `{"error":{"message":"","type":""}}`
+			errorJSON, _ = sjson.Set(errorJSON, "error.message", errorData.Get("message").String())
+			errorJSON, _ = sjson.Set(errorJSON, "error.type", errorData.Get("type").String())
+			return []string{errorJSON}
 		}
 		return []string{}
 
@@ -293,15 +284,10 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 	var messageID string
 	var model string
 	var createdAt int64
-	var inputTokens, outputTokens int64
-	var reasoningTokens int64
 	var stopReason string
 	var contentParts []string
 	var reasoningParts []string
-	// Use map to track tool calls by index for proper merging
-	toolCallsMap := make(map[int]map[string]interface{})
-	// Track tool call arguments accumulation
-	toolCallArgsMap := make(map[int]strings.Builder)
+	toolCallsAccumulator := make(map[int]*ToolCallAccumulator)
 
 	for _, chunk := range chunks {
 		root := gjson.ParseBytes(chunk)
@@ -314,9 +300,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 				messageID = message.Get("id").String()
 				model = message.Get("model").String()
 				createdAt = time.Now().Unix()
-				if usage := message.Get("usage"); usage.Exists() {
-					inputTokens = usage.Get("input_tokens").Int()
-				}
 			}
 
 		case "content_block_start":
@@ -327,18 +310,12 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 					// Start of thinking/reasoning content - skip for now as it's handled in delta
 					continue
 				} else if blockType == "tool_use" {
-					// Initialize tool call tracking for this index
+					// Initialize tool call accumulator for this index
 					index := int(root.Get("index").Int())
-					toolCallsMap[index] = map[string]interface{}{
-						"id":   contentBlock.Get("id").String(),
-						"type": "function",
-						"function": map[string]interface{}{
-							"name":      contentBlock.Get("name").String(),
-							"arguments": "",
-						},
+					toolCallsAccumulator[index] = &ToolCallAccumulator{
+						ID:   contentBlock.Get("id").String(),
+						Name: contentBlock.Get("name").String(),
 					}
-					// Initialize arguments builder for this tool call
-					toolCallArgsMap[index] = strings.Builder{}
 				}
 			}
 
@@ -361,9 +338,8 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 					// Accumulate tool call arguments
 					if partialJSON := delta.Get("partial_json"); partialJSON.Exists() {
 						index := int(root.Get("index").Int())
-						if builder, exists := toolCallArgsMap[index]; exists {
-							builder.WriteString(partialJSON.String())
-							toolCallArgsMap[index] = builder
+						if accumulator, exists := toolCallsAccumulator[index]; exists {
+							accumulator.Arguments.WriteString(partialJSON.String())
 						}
 					}
 				}
@@ -372,14 +348,9 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 		case "content_block_stop":
 			// Finalize tool call arguments for this index when content block ends
 			index := int(root.Get("index").Int())
-			if toolCall, exists := toolCallsMap[index]; exists {
-				if builder, argsExists := toolCallArgsMap[index]; argsExists {
-					// Set the accumulated arguments for the tool call
-					arguments := builder.String()
-					if arguments == "" {
-						arguments = "{}"
-					}
-					toolCall["function"].(map[string]interface{})["arguments"] = arguments
+			if accumulator, exists := toolCallsAccumulator[index]; exists {
+				if accumulator.Arguments.Len() == 0 {
+					accumulator.Arguments.WriteString("{}")
 				}
 			}
 
@@ -391,11 +362,14 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 				}
 			}
 			if usage := root.Get("usage"); usage.Exists() {
-				outputTokens = usage.Get("output_tokens").Int()
-				// Estimate reasoning tokens from accumulated thinking content
-				if len(reasoningParts) > 0 {
-					reasoningTokens = int64(len(strings.Join(reasoningParts, "")) / 4) // Rough estimation
-				}
+				inputTokens := usage.Get("input_tokens").Int()
+				outputTokens := usage.Get("output_tokens").Int()
+				cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
+				cacheCreationInputTokens := usage.Get("cache_creation_input_tokens").Int()
+				out, _ = sjson.Set(out, "usage.prompt_tokens", inputTokens+cacheCreationInputTokens)
+				out, _ = sjson.Set(out, "usage.completion_tokens", outputTokens)
+				out, _ = sjson.Set(out, "usage.total_tokens", inputTokens+outputTokens)
+				out, _ = sjson.Set(out, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
 			}
 		}
 	}
@@ -417,24 +391,35 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 	}
 
 	// Set tool calls if any were accumulated during processing
-	if len(toolCallsMap) > 0 {
-		// Convert tool calls map to array, preserving order by index
-		var toolCallsArray []interface{}
-		// Find the maximum index to determine the range
+	if len(toolCallsAccumulator) > 0 {
+		toolCallsCount := 0
 		maxIndex := -1
-		for index := range toolCallsMap {
+		for index := range toolCallsAccumulator {
 			if index > maxIndex {
 				maxIndex = index
 			}
 		}
-		// Iterate through all possible indices up to maxIndex
+
 		for i := 0; i <= maxIndex; i++ {
-			if toolCall, exists := toolCallsMap[i]; exists {
-				toolCallsArray = append(toolCallsArray, toolCall)
+			accumulator, exists := toolCallsAccumulator[i]
+			if !exists {
+				continue
 			}
+
+			arguments := accumulator.Arguments.String()
+
+			idPath := fmt.Sprintf("choices.0.message.tool_calls.%d.id", toolCallsCount)
+			typePath := fmt.Sprintf("choices.0.message.tool_calls.%d.type", toolCallsCount)
+			namePath := fmt.Sprintf("choices.0.message.tool_calls.%d.function.name", toolCallsCount)
+			argumentsPath := fmt.Sprintf("choices.0.message.tool_calls.%d.function.arguments", toolCallsCount)
+
+			out, _ = sjson.Set(out, idPath, accumulator.ID)
+			out, _ = sjson.Set(out, typePath, "function")
+			out, _ = sjson.Set(out, namePath, accumulator.Name)
+			out, _ = sjson.Set(out, argumentsPath, arguments)
+			toolCallsCount++
 		}
-		if len(toolCallsArray) > 0 {
-			out, _ = sjson.Set(out, "choices.0.message.tool_calls", toolCallsArray)
+		if toolCallsCount > 0 {
 			out, _ = sjson.Set(out, "choices.0.finish_reason", "tool_calls")
 		} else {
 			out, _ = sjson.Set(out, "choices.0.finish_reason", mapAnthropicStopReasonToOpenAI(stopReason))
@@ -443,16 +428,5 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
 		out, _ = sjson.Set(out, "choices.0.finish_reason", mapAnthropicStopReasonToOpenAI(stopReason))
 	}
 
-	// Set usage information including prompt tokens, completion tokens, and total tokens
-	totalTokens := inputTokens + outputTokens
-	out, _ = sjson.Set(out, "usage.prompt_tokens", inputTokens)
-	out, _ = sjson.Set(out, "usage.completion_tokens", outputTokens)
-	out, _ = sjson.Set(out, "usage.total_tokens", totalTokens)
-
-	// Add reasoning tokens to usage details if any reasoning content was processed
-	if reasoningTokens > 0 {
-		out, _ = sjson.Set(out, "usage.completion_tokens_details.reasoning_tokens", reasoningTokens)
-	}
-
 	return out
 }

internal/translator/claude/openai/responses/claude_openai-responses_request.go

@@ -114,13 +114,16 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
 					var builder strings.Builder
 					if parts := item.Get("content"); parts.Exists() && parts.IsArray() {
 						parts.ForEach(func(_, part gjson.Result) bool {
-							text := part.Get("text").String()
+							textResult := part.Get("text")
+							text := textResult.String()
 							if builder.Len() > 0 && text != "" {
 								builder.WriteByte('\n')
 							}
 							builder.WriteString(text)
 							return true
 						})
+					} else if parts.Type == gjson.String {
+						builder.WriteString(parts.String())
 					}
 					instructionsText = builder.String()
 					if instructionsText != "" {
@@ -207,6 +210,8 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
 						}
 						return true
 					})
+				} else if parts.Type == gjson.String {
+					textAggregate.WriteString(parts.String())
 				}
 
 				// Fallback to given role if content types not decisive
@@ -254,7 +259,10 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
 				toolUse, _ = sjson.Set(toolUse, "id", callID)
 				toolUse, _ = sjson.Set(toolUse, "name", name)
 				if argsStr != "" && gjson.Valid(argsStr) {
-					toolUse, _ = sjson.SetRaw(toolUse, "input", argsStr)
+					argsJSON := gjson.Parse(argsStr)
+					if argsJSON.IsObject() {
+						toolUse, _ = sjson.SetRaw(toolUse, "input", argsJSON.Raw)
+					}
 				}
 
 				asst := `{"role":"assistant","content":[]}`
@@ -309,16 +317,18 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
 		case gjson.String:
 			switch toolChoice.String() {
 			case "auto":
-				out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "auto"})
+				out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"auto"}`)
 			case "none":
 				// Leave unset; implies no tools
 			case "required":
-				out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "any"})
+				out, _ = sjson.SetRaw(out, "tool_choice", `{"type":"any"}`)
 			}
 		case gjson.JSON:
 			if toolChoice.Get("type").String() == "function" {
 				fn := toolChoice.Get("function.name").String()
-				out, _ = sjson.Set(out, "tool_choice", map[string]interface{}{"type": "tool", "name": fn})
+				toolChoiceJSON := `{"name":"","type":"tool"}`
+				toolChoiceJSON, _ = sjson.Set(toolChoiceJSON, "name", fn)
+				out, _ = sjson.SetRaw(out, "tool_choice", toolChoiceJSON)
 			}
 		default:
 

internal/translator/claude/openai/responses/claude_openai-responses_response.go

@@ -95,7 +95,7 @@ func ConvertClaudeResponseToOpenAIResponses(ctx context.Context, modelName strin
 				}
 			}
 			// response.created
-			created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"instructions":""}}`
+			created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"output":[]}}`
 			created, _ = sjson.Set(created, "sequence_number", nextSeq())
 			created, _ = sjson.Set(created, "response.id", st.ResponseID)
 			created, _ = sjson.Set(created, "response.created_at", st.CreatedAt)
@@ -197,11 +197,11 @@ func ConvertClaudeResponseToOpenAIResponses(ctx context.Context, modelName strin
 			if st.ReasoningActive {
 				if t := d.Get("thinking"); t.Exists() {
 					st.ReasoningBuf.WriteString(t.String())
-					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"text":""}`
+					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"delta":""}`
 					msg, _ = sjson.Set(msg, "sequence_number", nextSeq())
 					msg, _ = sjson.Set(msg, "item_id", st.ReasoningItemID)
 					msg, _ = sjson.Set(msg, "output_index", st.ReasoningIndex)
-					msg, _ = sjson.Set(msg, "text", t.String())
+					msg, _ = sjson.Set(msg, "delta", t.String())
 					out = append(out, emitEvent("response.reasoning_summary_text.delta", msg))
 				}
 			}
@@ -344,31 +344,20 @@ func ConvertClaudeResponseToOpenAIResponses(ctx context.Context, modelName strin
 		}
 
 		// Build response.output from aggregated state
-		var outputs []interface{}
+		outputsWrapper := `{"arr":[]}`
 		// reasoning item (if any)
 		if st.ReasoningBuf.Len() > 0 || st.ReasoningPartAdded {
-			r := map[string]interface{}{
-				"id":      st.ReasoningItemID,
-				"type":    "reasoning",
-				"summary": []interface{}{map[string]interface{}{"type": "summary_text", "text": st.ReasoningBuf.String()}},
-			}
-			outputs = append(outputs, r)
+			item := `{"id":"","type":"reasoning","summary":[{"type":"summary_text","text":""}]}`
+			item, _ = sjson.Set(item, "id", st.ReasoningItemID)
+			item, _ = sjson.Set(item, "summary.0.text", st.ReasoningBuf.String())
+			outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 		}
 		// assistant message item (if any text)
 		if st.TextBuf.Len() > 0 || st.InTextBlock || st.CurrentMsgID != "" {
-			m := map[string]interface{}{
-				"id":     st.CurrentMsgID,
-				"type":   "message",
-				"status": "completed",
-				"content": []interface{}{map[string]interface{}{
-					"type":        "output_text",
-					"annotations": []interface{}{},
-					"logprobs":    []interface{}{},
-					"text":        st.TextBuf.String(),
-				}},
-				"role": "assistant",
-			}
-			outputs = append(outputs, m)
+			item := `{"id":"","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":""}],"role":"assistant"}`
+			item, _ = sjson.Set(item, "id", st.CurrentMsgID)
+			item, _ = sjson.Set(item, "content.0.text", st.TextBuf.String())
+			outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 		}
 		// function_call items (in ascending index order for determinism)
 		if len(st.FuncArgsBuf) > 0 {
@@ -395,19 +384,16 @@ func ConvertClaudeResponseToOpenAIResponses(ctx context.Context, modelName strin
 				if callID == "" && st.CurrentFCID != "" {
 					callID = st.CurrentFCID
 				}
-				item := map[string]interface{}{
-					"id":        fmt.Sprintf("fc_%s", callID),
-					"type":      "function_call",
-					"status":    "completed",
-					"arguments": args,
-					"call_id":   callID,
-					"name":      name,
-				}
-				outputs = append(outputs, item)
+				item := `{"id":"","type":"function_call","status":"completed","arguments":"","call_id":"","name":""}`
+				item, _ = sjson.Set(item, "id", fmt.Sprintf("fc_%s", callID))
+				item, _ = sjson.Set(item, "arguments", args)
+				item, _ = sjson.Set(item, "call_id", callID)
+				item, _ = sjson.Set(item, "name", name)
+				outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 			}
 		}
-		if len(outputs) > 0 {
-			completed, _ = sjson.Set(completed, "response.output", outputs)
+		if gjson.Get(outputsWrapper, "arr.#").Int() > 0 {
+			completed, _ = sjson.SetRaw(completed, "response.output", gjson.Get(outputsWrapper, "arr").Raw)
 		}
 
 		reasoningTokens := int64(0)
@@ -628,27 +614,18 @@ func ConvertClaudeResponseToOpenAIResponsesNonStream(_ context.Context, _ string
 	}
 
 	// Build output array
-	var outputs []interface{}
+	outputsWrapper := `{"arr":[]}`
 	if reasoningBuf.Len() > 0 {
-		outputs = append(outputs, map[string]interface{}{
-			"id":      reasoningItemID,
-			"type":    "reasoning",
-			"summary": []interface{}{map[string]interface{}{"type": "summary_text", "text": reasoningBuf.String()}},
-		})
+		item := `{"id":"","type":"reasoning","summary":[{"type":"summary_text","text":""}]}`
+		item, _ = sjson.Set(item, "id", reasoningItemID)
+		item, _ = sjson.Set(item, "summary.0.text", reasoningBuf.String())
+		outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 	}
 	if currentMsgID != "" || textBuf.Len() > 0 {
-		outputs = append(outputs, map[string]interface{}{
-			"id":     currentMsgID,
-			"type":   "message",
-			"status": "completed",
-			"content": []interface{}{map[string]interface{}{
-				"type":        "output_text",
-				"annotations": []interface{}{},
-				"logprobs":    []interface{}{},
-				"text":        textBuf.String(),
-			}},
-			"role": "assistant",
-		})
+		item := `{"id":"","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":""}],"role":"assistant"}`
+		item, _ = sjson.Set(item, "id", currentMsgID)
+		item, _ = sjson.Set(item, "content.0.text", textBuf.String())
+		outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 	}
 	if len(toolCalls) > 0 {
 		// Preserve index order
@@ -669,18 +646,16 @@ func ConvertClaudeResponseToOpenAIResponsesNonStream(_ context.Context, _ string
 			if args == "" {
 				args = "{}"
 			}
-			outputs = append(outputs, map[string]interface{}{
-				"id":        fmt.Sprintf("fc_%s", st.id),
-				"type":      "function_call",
-				"status":    "completed",
-				"arguments": args,
-				"call_id":   st.id,
-				"name":      st.name,
-			})
+			item := `{"id":"","type":"function_call","status":"completed","arguments":"","call_id":"","name":""}`
+			item, _ = sjson.Set(item, "id", fmt.Sprintf("fc_%s", st.id))
+			item, _ = sjson.Set(item, "arguments", args)
+			item, _ = sjson.Set(item, "call_id", st.id)
+			item, _ = sjson.Set(item, "name", st.name)
+			outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 		}
 	}
-	if len(outputs) > 0 {
-		out, _ = sjson.Set(out, "output", outputs)
+	if gjson.Get(outputsWrapper, "arr.#").Int() > 0 {
+		out, _ = sjson.SetRaw(out, "output", gjson.Get(outputsWrapper, "arr").Raw)
 	}
 
 	// Usage

internal/translator/codex/claude/codex_claude_response.go

@@ -9,7 +9,6 @@ package claude
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 
@@ -191,21 +190,12 @@ func ConvertCodexResponseToClaudeNonStream(_ context.Context, _ string, original
 		return ""
 	}
 
-	response := map[string]interface{}{
-		"id":            responseData.Get("id").String(),
-		"type":          "message",
-		"role":          "assistant",
-		"model":         responseData.Get("model").String(),
-		"content":       []interface{}{},
-		"stop_reason":   nil,
-		"stop_sequence": nil,
-		"usage": map[string]interface{}{
-			"input_tokens":  responseData.Get("usage.input_tokens").Int(),
-			"output_tokens": responseData.Get("usage.output_tokens").Int(),
-		},
-	}
+	out := `{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}`
+	out, _ = sjson.Set(out, "id", responseData.Get("id").String())
+	out, _ = sjson.Set(out, "model", responseData.Get("model").String())
+	out, _ = sjson.Set(out, "usage.input_tokens", responseData.Get("usage.input_tokens").Int())
+	out, _ = sjson.Set(out, "usage.output_tokens", responseData.Get("usage.output_tokens").Int())
 
-	var contentBlocks []interface{}
 	hasToolCall := false
 
 	if output := responseData.Get("output"); output.Exists() && output.IsArray() {
@@ -244,10 +234,9 @@ func ConvertCodexResponseToClaudeNonStream(_ context.Context, _ string, original
 					}
 				}
 				if thinkingBuilder.Len() > 0 {
-					contentBlocks = append(contentBlocks, map[string]interface{}{
-						"type":     "thinking",
-						"thinking": thinkingBuilder.String(),
-					})
+					block := `{"type":"thinking","thinking":""}`
+					block, _ = sjson.Set(block, "thinking", thinkingBuilder.String())
+					out, _ = sjson.SetRaw(out, "content.-1", block)
 				}
 			case "message":
 				if content := item.Get("content"); content.Exists() {
@@ -256,10 +245,9 @@ func ConvertCodexResponseToClaudeNonStream(_ context.Context, _ string, original
 							if part.Get("type").String() == "output_text" {
 								text := part.Get("text").String()
 								if text != "" {
-									contentBlocks = append(contentBlocks, map[string]interface{}{
-										"type": "text",
-										"text": text,
-									})
+									block := `{"type":"text","text":""}`
+									block, _ = sjson.Set(block, "text", text)
+									out, _ = sjson.SetRaw(out, "content.-1", block)
 								}
 							}
 							return true
@@ -267,10 +255,9 @@ func ConvertCodexResponseToClaudeNonStream(_ context.Context, _ string, original
 					} else {
 						text := content.String()
 						if text != "" {
-							contentBlocks = append(contentBlocks, map[string]interface{}{
-								"type": "text",
-								"text": text,
-							})
+							block := `{"type":"text","text":""}`
+							block, _ = sjson.Set(block, "text", text)
+							out, _ = sjson.SetRaw(out, "content.-1", block)
 						}
 					}
 				}
@@ -281,54 +268,41 @@ func ConvertCodexResponseToClaudeNonStream(_ context.Context, _ string, original
 					name = original
 				}
 
-				toolBlock := map[string]interface{}{
-					"type":  "tool_use",
-					"id":    item.Get("call_id").String(),
-					"name":  name,
-					"input": map[string]interface{}{},
-				}
-
-				if argsStr := item.Get("arguments").String(); argsStr != "" {
-					var args interface{}
-					if err := json.Unmarshal([]byte(argsStr), &args); err == nil {
-						toolBlock["input"] = args
+				toolBlock := `{"type":"tool_use","id":"","name":"","input":{}}`
+				toolBlock, _ = sjson.Set(toolBlock, "id", item.Get("call_id").String())
+				toolBlock, _ = sjson.Set(toolBlock, "name", name)
+				inputRaw := "{}"
+				if argsStr := item.Get("arguments").String(); argsStr != "" && gjson.Valid(argsStr) {
+					argsJSON := gjson.Parse(argsStr)
+					if argsJSON.IsObject() {
+						inputRaw = argsJSON.Raw
 					}
 				}
-
-				contentBlocks = append(contentBlocks, toolBlock)
+				toolBlock, _ = sjson.SetRaw(toolBlock, "input", inputRaw)
+				out, _ = sjson.SetRaw(out, "content.-1", toolBlock)
 			}
 			return true
 		})
 	}
 
-	if len(contentBlocks) > 0 {
-		response["content"] = contentBlocks
-	}
-
 	if stopReason := responseData.Get("stop_reason"); stopReason.Exists() && stopReason.String() != "" {
-		response["stop_reason"] = stopReason.String()
+		out, _ = sjson.Set(out, "stop_reason", stopReason.String())
 	} else if hasToolCall {
-		response["stop_reason"] = "tool_use"
+		out, _ = sjson.Set(out, "stop_reason", "tool_use")
 	} else {
-		response["stop_reason"] = "end_turn"
+		out, _ = sjson.Set(out, "stop_reason", "end_turn")
 	}
 
 	if stopSequence := responseData.Get("stop_sequence"); stopSequence.Exists() && stopSequence.String() != "" {
-		response["stop_sequence"] = stopSequence.Value()
+		out, _ = sjson.SetRaw(out, "stop_sequence", stopSequence.Raw)
 	}
 
 	if responseData.Get("usage.input_tokens").Exists() || responseData.Get("usage.output_tokens").Exists() {
-		response["usage"] = map[string]interface{}{
-			"input_tokens":  responseData.Get("usage.input_tokens").Int(),
-			"output_tokens": responseData.Get("usage.output_tokens").Int(),
-		}
+		out, _ = sjson.Set(out, "usage.input_tokens", responseData.Get("usage.input_tokens").Int())
+		out, _ = sjson.Set(out, "usage.output_tokens", responseData.Get("usage.output_tokens").Int())
 	}
 
-	responseJSON, err := json.Marshal(response)
-	if err != nil {
-		return ""
-	}
-	return string(responseJSON)
+	return out
 }
 
 // buildReverseMapFromClaudeOriginalShortToOriginal builds a map[short]original from original Claude request tools.

internal/translator/codex/gemini/codex_gemini_response.go

@@ -7,7 +7,6 @@ package gemini
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"time"
 
@@ -190,19 +189,19 @@ func ConvertCodexResponseToGeminiNonStream(_ context.Context, modelName string,
 		}
 
 		// Process output content to build parts array
-		var parts []interface{}
 		hasToolCall := false
-		var pendingFunctionCalls []interface{}
+		var pendingFunctionCalls []string
 
 		flushPendingFunctionCalls := func() {
-			if len(pendingFunctionCalls) > 0 {
-				// Add all pending function calls as individual parts
-				// This maintains the original Gemini API format while ensuring consecutive calls are grouped together
-				for _, fc := range pendingFunctionCalls {
-					parts = append(parts, fc)
-				}
-				pendingFunctionCalls = nil
+			if len(pendingFunctionCalls) == 0 {
+				return
 			}
+			// Add all pending function calls as individual parts
+			// This maintains the original Gemini API format while ensuring consecutive calls are grouped together
+			for _, fc := range pendingFunctionCalls {
+				template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", fc)
+			}
+			pendingFunctionCalls = nil
 		}
 
 		if output := responseData.Get("output"); output.Exists() && output.IsArray() {
@@ -216,11 +215,9 @@ func ConvertCodexResponseToGeminiNonStream(_ context.Context, modelName string,
 
 					// Add thinking content
 					if content := value.Get("content"); content.Exists() {
-						part := map[string]interface{}{
-							"thought": true,
-							"text":    content.String(),
-						}
-						parts = append(parts, part)
+						part := `{"text":"","thought":true}`
+						part, _ = sjson.Set(part, "text", content.String())
+						template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", part)
 					}
 
 				case "message":
@@ -232,10 +229,9 @@ func ConvertCodexResponseToGeminiNonStream(_ context.Context, modelName string,
 						content.ForEach(func(_, contentItem gjson.Result) bool {
 							if contentItem.Get("type").String() == "output_text" {
 								if text := contentItem.Get("text"); text.Exists() {
-									part := map[string]interface{}{
-										"text": text.String(),
-									}
-									parts = append(parts, part)
+									part := `{"text":""}`
+									part, _ = sjson.Set(part, "text", text.String())
+									template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", part)
 								}
 							}
 							return true
@@ -245,28 +241,21 @@ func ConvertCodexResponseToGeminiNonStream(_ context.Context, modelName string,
 				case "function_call":
 					// Collect function call for potential merging with consecutive ones
 					hasToolCall = true
-					functionCall := map[string]interface{}{
-						"functionCall": map[string]interface{}{
-							"name": func() string {
-								n := value.Get("name").String()
-								rev := buildReverseMapFromGeminiOriginal(originalRequestRawJSON)
-								if orig, ok := rev[n]; ok {
-									return orig
-								}
-								return n
-							}(),
-							"args": map[string]interface{}{},
-						},
+					functionCall := `{"functionCall":{"args":{},"name":""}}`
+					{
+						n := value.Get("name").String()
+						rev := buildReverseMapFromGeminiOriginal(originalRequestRawJSON)
+						if orig, ok := rev[n]; ok {
+							n = orig
+						}
+						functionCall, _ = sjson.Set(functionCall, "functionCall.name", n)
 					}
 
 					// Parse and set arguments
 					if argsStr := value.Get("arguments").String(); argsStr != "" {
 						argsResult := gjson.Parse(argsStr)
 						if argsResult.IsObject() {
-							var args map[string]interface{}
-							if err := json.Unmarshal([]byte(argsStr), &args); err == nil {
-								functionCall["functionCall"].(map[string]interface{})["args"] = args
-							}
+							functionCall, _ = sjson.SetRaw(functionCall, "functionCall.args", argsStr)
 						}
 					}
 
@@ -279,11 +268,6 @@ func ConvertCodexResponseToGeminiNonStream(_ context.Context, modelName string,
 			flushPendingFunctionCalls()
 		}
 
-		// Set the parts array
-		if len(parts) > 0 {
-			template, _ = sjson.SetRaw(template, "candidates.0.content.parts", mustMarshalJSON(parts))
-		}
-
 		// Set finish reason based on whether there were tool calls
 		if hasToolCall {
 			template, _ = sjson.Set(template, "candidates.0.finishReason", "STOP")
@@ -323,15 +307,6 @@ func buildReverseMapFromGeminiOriginal(original []byte) map[string]string {
 	return rev
 }
 
-// mustMarshalJSON marshals a value to JSON, panicking on error.
-func mustMarshalJSON(v interface{}) string {
-	data, err := json.Marshal(v)
-	if err != nil {
-		return ""
-	}
-	return string(data)
-}
-
 func GeminiTokenCount(ctx context.Context, count int64) string {
 	return fmt.Sprintf(`{"totalTokens":%d,"promptTokensDetails":[{"modality":"TEXT","tokenCount":%d}]}`, count, count)
 }

internal/translator/gemini-cli/claude/gemini-cli_claude_request.go

@@ -7,10 +7,8 @@ package claude
 
 import (
 	"bytes"
-	"encoding/json"
 	"strings"
 
-	client "github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
@@ -41,92 +39,102 @@ func ConvertClaudeRequestToCLI(modelName string, inputRawJSON []byte, _ bool) []
 	rawJSON := bytes.Clone(inputRawJSON)
 	rawJSON = bytes.Replace(rawJSON, []byte(`"url":{"type":"string","format":"uri",`), []byte(`"url":{"type":"string",`), -1)
 
+	// Build output Gemini CLI request JSON
+	out := `{"model":"","request":{"contents":[]}}`
+	out, _ = sjson.Set(out, "model", modelName)
+
 	// system instruction
-	var systemInstruction *client.Content
-	systemResult := gjson.GetBytes(rawJSON, "system")
-	if systemResult.IsArray() {
-		systemResults := systemResult.Array()
-		systemInstruction = &client.Content{Role: "user", Parts: []client.Part{}}
-		for i := 0; i < len(systemResults); i++ {
-			systemPromptResult := systemResults[i]
-			systemTypePromptResult := systemPromptResult.Get("type")
-			if systemTypePromptResult.Type == gjson.String && systemTypePromptResult.String() == "text" {
-				systemPrompt := systemPromptResult.Get("text").String()
-				systemPart := client.Part{Text: systemPrompt}
-				systemInstruction.Parts = append(systemInstruction.Parts, systemPart)
+	if systemResult := gjson.GetBytes(rawJSON, "system"); systemResult.IsArray() {
+		systemInstruction := `{"role":"user","parts":[]}`
+		hasSystemParts := false
+		systemResult.ForEach(func(_, systemPromptResult gjson.Result) bool {
+			if systemPromptResult.Get("type").String() == "text" {
+				textResult := systemPromptResult.Get("text")
+				if textResult.Type == gjson.String {
+					part := `{"text":""}`
+					part, _ = sjson.Set(part, "text", textResult.String())
+					systemInstruction, _ = sjson.SetRaw(systemInstruction, "parts.-1", part)
+					hasSystemParts = true
+				}
 			}
+			return true
+		})
+		if hasSystemParts {
+			out, _ = sjson.SetRaw(out, "request.systemInstruction", systemInstruction)
 		}
-		if len(systemInstruction.Parts) == 0 {
-			systemInstruction = nil
-		}
+	} else if systemResult.Type == gjson.String {
+		out, _ = sjson.Set(out, "request.systemInstruction.parts.-1.text", systemResult.String())
 	}
 
 	// contents
-	contents := make([]client.Content, 0)
-	messagesResult := gjson.GetBytes(rawJSON, "messages")
-	if messagesResult.IsArray() {
-		messageResults := messagesResult.Array()
-		for i := 0; i < len(messageResults); i++ {
-			messageResult := messageResults[i]
+	if messagesResult := gjson.GetBytes(rawJSON, "messages"); messagesResult.IsArray() {
+		messagesResult.ForEach(func(_, messageResult gjson.Result) bool {
 			roleResult := messageResult.Get("role")
 			if roleResult.Type != gjson.String {
-				continue
+				return true
 			}
 			role := roleResult.String()
 			if role == "assistant" {
 				role = "model"
 			}
-			clientContent := client.Content{Role: role, Parts: []client.Part{}}
+
+			contentJSON := `{"role":"","parts":[]}`
+			contentJSON, _ = sjson.Set(contentJSON, "role", role)
+
 			contentsResult := messageResult.Get("content")
 			if contentsResult.IsArray() {
-				contentResults := contentsResult.Array()
-				for j := 0; j < len(contentResults); j++ {
-					contentResult := contentResults[j]
-					contentTypeResult := contentResult.Get("type")
-					if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "text" {
-						prompt := contentResult.Get("text").String()
-						clientContent.Parts = append(clientContent.Parts, client.Part{Text: prompt})
-					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_use" {
+				contentsResult.ForEach(func(_, contentResult gjson.Result) bool {
+					switch contentResult.Get("type").String() {
+					case "text":
+						part := `{"text":""}`
+						part, _ = sjson.Set(part, "text", contentResult.Get("text").String())
+						contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
+
+					case "tool_use":
 						functionName := contentResult.Get("name").String()
 						functionArgs := contentResult.Get("input").String()
-						var args map[string]any
-						if err := json.Unmarshal([]byte(functionArgs), &args); err == nil {
-							clientContent.Parts = append(clientContent.Parts, client.Part{
-								FunctionCall:     &client.FunctionCall{Name: functionName, Args: args},
-								ThoughtSignature: geminiCLIClaudeThoughtSignature,
-							})
+						argsResult := gjson.Parse(functionArgs)
+						if argsResult.IsObject() && gjson.Valid(functionArgs) {
+							part := `{"thoughtSignature":"","functionCall":{"name":"","args":{}}}`
+							part, _ = sjson.Set(part, "thoughtSignature", geminiCLIClaudeThoughtSignature)
+							part, _ = sjson.Set(part, "functionCall.name", functionName)
+							part, _ = sjson.SetRaw(part, "functionCall.args", functionArgs)
+							contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
 						}
-					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_result" {
+
+					case "tool_result":
 						toolCallID := contentResult.Get("tool_use_id").String()
-						if toolCallID != "" {
-							funcName := toolCallID
-							toolCallIDs := strings.Split(toolCallID, "-")
-							if len(toolCallIDs) > 1 {
-								funcName = strings.Join(toolCallIDs[0:len(toolCallIDs)-1], "-")
-							}
-							responseData := contentResult.Get("content").Raw
-							functionResponse := client.FunctionResponse{Name: funcName, Response: map[string]interface{}{"result": responseData}}
-							clientContent.Parts = append(clientContent.Parts, client.Part{FunctionResponse: &functionResponse})
+						if toolCallID == "" {
+							return true
 						}
+						funcName := toolCallID
+						toolCallIDs := strings.Split(toolCallID, "-")
+						if len(toolCallIDs) > 1 {
+							funcName = strings.Join(toolCallIDs[0:len(toolCallIDs)-1], "-")
+						}
+						responseData := contentResult.Get("content").Raw
+						part := `{"functionResponse":{"name":"","response":{"result":""}}}`
+						part, _ = sjson.Set(part, "functionResponse.name", funcName)
+						part, _ = sjson.Set(part, "functionResponse.response.result", responseData)
+						contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
 					}
-				}
-				contents = append(contents, clientContent)
+					return true
+				})
+				out, _ = sjson.SetRaw(out, "request.contents.-1", contentJSON)
 			} else if contentsResult.Type == gjson.String {
-				prompt := contentsResult.String()
-				contents = append(contents, client.Content{Role: role, Parts: []client.Part{{Text: prompt}}})
+				part := `{"text":""}`
+				part, _ = sjson.Set(part, "text", contentsResult.String())
+				contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
+				out, _ = sjson.SetRaw(out, "request.contents.-1", contentJSON)
 			}
-		}
+			return true
+		})
 	}
 
 	// tools
-	var tools []client.ToolDeclaration
-	toolsResult := gjson.GetBytes(rawJSON, "tools")
-	if toolsResult.IsArray() {
-		tools = make([]client.ToolDeclaration, 1)
-		tools[0].FunctionDeclarations = make([]any, 0)
-		toolsResults := toolsResult.Array()
-		for i := 0; i < len(toolsResults); i++ {
-			toolResult := toolsResults[i]
+	if toolsResult := gjson.GetBytes(rawJSON, "tools"); toolsResult.IsArray() {
+		hasTools := false
+		toolsResult.ForEach(func(_, toolResult gjson.Result) bool {
 			inputSchemaResult := toolResult.Get("input_schema")
 			if inputSchemaResult.Exists() && inputSchemaResult.IsObject() {
 				inputSchema := inputSchemaResult.Raw
@@ -134,30 +142,21 @@ func ConvertClaudeRequestToCLI(modelName string, inputRawJSON []byte, _ bool) []
 				tool, _ = sjson.SetRaw(tool, "parametersJsonSchema", inputSchema)
 				tool, _ = sjson.Delete(tool, "strict")
 				tool, _ = sjson.Delete(tool, "input_examples")
-				var toolDeclaration any
-				if err := json.Unmarshal([]byte(tool), &toolDeclaration); err == nil {
-					tools[0].FunctionDeclarations = append(tools[0].FunctionDeclarations, toolDeclaration)
+				tool, _ = sjson.Delete(tool, "type")
+				tool, _ = sjson.Delete(tool, "cache_control")
+				if gjson.Valid(tool) && gjson.Parse(tool).IsObject() {
+					if !hasTools {
+						out, _ = sjson.SetRaw(out, "request.tools", `[{"functionDeclarations":[]}]`)
+						hasTools = true
+					}
+					out, _ = sjson.SetRaw(out, "request.tools.0.functionDeclarations.-1", tool)
 				}
 			}
+			return true
+		})
+		if !hasTools {
+			out, _ = sjson.Delete(out, "request.tools")
 		}
-	} else {
-		tools = make([]client.ToolDeclaration, 0)
-	}
-
-	// Build output Gemini CLI request JSON
-	out := `{"model":"","request":{"contents":[]}}`
-	out, _ = sjson.Set(out, "model", modelName)
-	if systemInstruction != nil {
-		b, _ := json.Marshal(systemInstruction)
-		out, _ = sjson.SetRaw(out, "request.systemInstruction", string(b))
-	}
-	if len(contents) > 0 {
-		b, _ := json.Marshal(contents)
-		out, _ = sjson.SetRaw(out, "request.contents", string(b))
-	}
-	if len(tools) > 0 && len(tools[0].FunctionDeclarations) > 0 {
-		b, _ := json.Marshal(tools)
-		out, _ = sjson.SetRaw(out, "request.tools", string(b))
 	}
 
 	// Map Anthropic thinking -> Gemini thinkingBudget/include_thoughts when type==enabled

internal/translator/gemini-cli/claude/gemini-cli_claude_response.go

@@ -9,7 +9,6 @@ package claude
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 	"sync/atomic"
@@ -276,22 +275,16 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 
 	root := gjson.ParseBytes(rawJSON)
 
-	response := map[string]interface{}{
-		"id":            root.Get("response.responseId").String(),
-		"type":          "message",
-		"role":          "assistant",
-		"model":         root.Get("response.modelVersion").String(),
-		"content":       []interface{}{},
-		"stop_reason":   nil,
-		"stop_sequence": nil,
-		"usage": map[string]interface{}{
-			"input_tokens":  root.Get("response.usageMetadata.promptTokenCount").Int(),
-			"output_tokens": root.Get("response.usageMetadata.candidatesTokenCount").Int() + root.Get("response.usageMetadata.thoughtsTokenCount").Int(),
-		},
-	}
+	out := `{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}`
+	out, _ = sjson.Set(out, "id", root.Get("response.responseId").String())
+	out, _ = sjson.Set(out, "model", root.Get("response.modelVersion").String())
+
+	inputTokens := root.Get("response.usageMetadata.promptTokenCount").Int()
+	outputTokens := root.Get("response.usageMetadata.candidatesTokenCount").Int() + root.Get("response.usageMetadata.thoughtsTokenCount").Int()
+	out, _ = sjson.Set(out, "usage.input_tokens", inputTokens)
+	out, _ = sjson.Set(out, "usage.output_tokens", outputTokens)
 
 	parts := root.Get("response.candidates.0.content.parts")
-	var contentBlocks []interface{}
 	textBuilder := strings.Builder{}
 	thinkingBuilder := strings.Builder{}
 	toolIDCounter := 0
@@ -301,10 +294,9 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 		if textBuilder.Len() == 0 {
 			return
 		}
-		contentBlocks = append(contentBlocks, map[string]interface{}{
-			"type": "text",
-			"text": textBuilder.String(),
-		})
+		block := `{"type":"text","text":""}`
+		block, _ = sjson.Set(block, "text", textBuilder.String())
+		out, _ = sjson.SetRaw(out, "content.-1", block)
 		textBuilder.Reset()
 	}
 
@@ -312,10 +304,9 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 		if thinkingBuilder.Len() == 0 {
 			return
 		}
-		contentBlocks = append(contentBlocks, map[string]interface{}{
-			"type":     "thinking",
-			"thinking": thinkingBuilder.String(),
-		})
+		block := `{"type":"thinking","thinking":""}`
+		block, _ = sjson.Set(block, "thinking", thinkingBuilder.String())
+		out, _ = sjson.SetRaw(out, "content.-1", block)
 		thinkingBuilder.Reset()
 	}
 
@@ -339,21 +330,15 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 
 				name := functionCall.Get("name").String()
 				toolIDCounter++
-				toolBlock := map[string]interface{}{
-					"type":  "tool_use",
-					"id":    fmt.Sprintf("tool_%d", toolIDCounter),
-					"name":  name,
-					"input": map[string]interface{}{},
+				toolBlock := `{"type":"tool_use","id":"","name":"","input":{}}`
+				toolBlock, _ = sjson.Set(toolBlock, "id", fmt.Sprintf("tool_%d", toolIDCounter))
+				toolBlock, _ = sjson.Set(toolBlock, "name", name)
+				inputRaw := "{}"
+				if args := functionCall.Get("args"); args.Exists() && gjson.Valid(args.Raw) && args.IsObject() {
+					inputRaw = args.Raw
 				}
-
-				if args := functionCall.Get("args"); args.Exists() {
-					var parsed interface{}
-					if err := json.Unmarshal([]byte(args.Raw), &parsed); err == nil {
-						toolBlock["input"] = parsed
-					}
-				}
-
-				contentBlocks = append(contentBlocks, toolBlock)
+				toolBlock, _ = sjson.SetRaw(toolBlock, "input", inputRaw)
+				out, _ = sjson.SetRaw(out, "content.-1", toolBlock)
 				continue
 			}
 		}
@@ -362,8 +347,6 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 	flushThinking()
 	flushText()
 
-	response["content"] = contentBlocks
-
 	stopReason := "end_turn"
 	if hasToolCall {
 		stopReason = "tool_use"
@@ -379,19 +362,13 @@ func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, orig
 			}
 		}
 	}
-	response["stop_reason"] = stopReason
+	out, _ = sjson.Set(out, "stop_reason", stopReason)
 
-	if usage := response["usage"].(map[string]interface{}); usage["input_tokens"] == int64(0) && usage["output_tokens"] == int64(0) {
-		if usageMeta := root.Get("response.usageMetadata"); !usageMeta.Exists() {
-			delete(response, "usage")
-		}
+	if inputTokens == int64(0) && outputTokens == int64(0) && !root.Get("response.usageMetadata").Exists() {
+		out, _ = sjson.Delete(out, "usage")
 	}
 
-	encoded, err := json.Marshal(response)
-	if err != nil {
-		return ""
-	}
-	return string(encoded)
+	return out
 }
 
 func ClaudeTokenCount(ctx context.Context, count int64) string {

internal/translator/gemini-cli/gemini/gemini-cli_gemini_request.go

@@ -7,7 +7,6 @@ package gemini
 
 import (
 	"bytes"
-	"encoding/json"
 	"fmt"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
@@ -117,8 +116,6 @@ func ConvertGeminiRequestToGeminiCLI(_ string, inputRawJSON []byte, _ bool) []by
 
 // FunctionCallGroup represents a group of function calls and their responses
 type FunctionCallGroup struct {
-	ModelContent    map[string]interface{}
-	FunctionCalls   []gjson.Result
 	ResponsesNeeded int
 }
 
@@ -146,7 +143,7 @@ func fixCLIToolResponse(input string) (string, error) {
 	}
 
 	// Initialize data structures for processing and grouping
-	var newContents []interface{}          // Final processed contents array
+	contentsWrapper := `{"contents":[]}`
 	var pendingGroups []*FunctionCallGroup // Groups awaiting completion with responses
 	var collectedResponses []gjson.Result  // Standalone responses to be matched
 
@@ -178,23 +175,17 @@ func fixCLIToolResponse(input string) (string, error) {
 					collectedResponses = collectedResponses[group.ResponsesNeeded:]
 
 					// Create merged function response content
-					var responseParts []interface{}
+					functionResponseContent := `{"parts":[],"role":"function"}`
 					for _, response := range groupResponses {
-						var responseMap map[string]interface{}
-						errUnmarshal := json.Unmarshal([]byte(response.Raw), &responseMap)
-						if errUnmarshal != nil {
-							log.Warnf("failed to unmarshal function response: %v\n", errUnmarshal)
+						if !response.IsObject() {
+							log.Warnf("failed to parse function response")
 							continue
 						}
-						responseParts = append(responseParts, responseMap)
+						functionResponseContent, _ = sjson.SetRaw(functionResponseContent, "parts.-1", response.Raw)
 					}
 
-					if len(responseParts) > 0 {
-						functionResponseContent := map[string]interface{}{
-							"parts": responseParts,
-							"role":  "function",
-						}
-						newContents = append(newContents, functionResponseContent)
+					if gjson.Get(functionResponseContent, "parts.#").Int() > 0 {
+						contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", functionResponseContent)
 					}
 
 					// Remove this group as it's been satisfied
@@ -208,50 +199,42 @@ func fixCLIToolResponse(input string) (string, error) {
 
 		// If this is a model with function calls, create a new group
 		if role == "model" {
-			var functionCallsInThisModel []gjson.Result
+			functionCallsCount := 0
 			parts.ForEach(func(_, part gjson.Result) bool {
 				if part.Get("functionCall").Exists() {
-					functionCallsInThisModel = append(functionCallsInThisModel, part)
+					functionCallsCount++
 				}
 				return true
 			})
 
-			if len(functionCallsInThisModel) > 0 {
+			if functionCallsCount > 0 {
 				// Add the model content
-				var contentMap map[string]interface{}
-				errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
-				if errUnmarshal != nil {
-					log.Warnf("failed to unmarshal model content: %v\n", errUnmarshal)
+				if !value.IsObject() {
+					log.Warnf("failed to parse model content")
 					return true
 				}
-				newContents = append(newContents, contentMap)
+				contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", value.Raw)
 
 				// Create a new group for tracking responses
 				group := &FunctionCallGroup{
-					ModelContent:    contentMap,
-					FunctionCalls:   functionCallsInThisModel,
-					ResponsesNeeded: len(functionCallsInThisModel),
+					ResponsesNeeded: functionCallsCount,
 				}
 				pendingGroups = append(pendingGroups, group)
 			} else {
 				// Regular model content without function calls
-				var contentMap map[string]interface{}
-				errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
-				if errUnmarshal != nil {
-					log.Warnf("failed to unmarshal content: %v\n", errUnmarshal)
+				if !value.IsObject() {
+					log.Warnf("failed to parse content")
 					return true
 				}
-				newContents = append(newContents, contentMap)
+				contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", value.Raw)
 			}
 		} else {
 			// Non-model content (user, etc.)
-			var contentMap map[string]interface{}
-			errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
-			if errUnmarshal != nil {
-				log.Warnf("failed to unmarshal content: %v\n", errUnmarshal)
+			if !value.IsObject() {
+				log.Warnf("failed to parse content")
 				return true
 			}
-			newContents = append(newContents, contentMap)
+			contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", value.Raw)
 		}
 
 		return true
@@ -263,31 +246,24 @@ func fixCLIToolResponse(input string) (string, error) {
 			groupResponses := collectedResponses[:group.ResponsesNeeded]
 			collectedResponses = collectedResponses[group.ResponsesNeeded:]
 
-			var responseParts []interface{}
+			functionResponseContent := `{"parts":[],"role":"function"}`
 			for _, response := range groupResponses {
-				var responseMap map[string]interface{}
-				errUnmarshal := json.Unmarshal([]byte(response.Raw), &responseMap)
-				if errUnmarshal != nil {
-					log.Warnf("failed to unmarshal function response: %v\n", errUnmarshal)
+				if !response.IsObject() {
+					log.Warnf("failed to parse function response")
 					continue
 				}
-				responseParts = append(responseParts, responseMap)
+				functionResponseContent, _ = sjson.SetRaw(functionResponseContent, "parts.-1", response.Raw)
 			}
 
-			if len(responseParts) > 0 {
-				functionResponseContent := map[string]interface{}{
-					"parts": responseParts,
-					"role":  "function",
-				}
-				newContents = append(newContents, functionResponseContent)
+			if gjson.Get(functionResponseContent, "parts.#").Int() > 0 {
+				contentsWrapper, _ = sjson.SetRaw(contentsWrapper, "contents.-1", functionResponseContent)
 			}
 		}
 	}
 
 	// Update the original JSON with the new contents
 	result := input
-	newContentsJSON, _ := json.Marshal(newContents)
-	result, _ = sjson.Set(result, "request.contents", json.RawMessage(newContentsJSON))
+	result, _ = sjson.SetRaw(result, "request.contents", gjson.Get(contentsWrapper, "contents").Raw)
 
 	return result, nil
 }

internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go

@@ -160,6 +160,14 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 				} else if content.IsObject() && content.Get("type").String() == "text" {
 					out, _ = sjson.SetBytes(out, "request.systemInstruction.role", "user")
 					out, _ = sjson.SetBytes(out, "request.systemInstruction.parts.0.text", content.Get("text").String())
+				} else if content.IsArray() {
+					contents := content.Array()
+					if len(contents) > 0 {
+						out, _ = sjson.SetBytes(out, "request.systemInstruction.role", "user")
+						for j := 0; j < len(contents); j++ {
+							out, _ = sjson.SetBytes(out, fmt.Sprintf("request.systemInstruction.parts.%d.text", j), contents[j].Get("text").String())
+						}
+					}
 				}
 			} else if role == "user" || (role == "system" && len(arr) == 1) {
 				// Build single user content node to avoid splitting into multiple contents
@@ -210,8 +218,29 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 				if content.Type == gjson.String {
 					// Assistant text -> single model content
 					node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
-					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 					p++
+				} else if content.IsArray() {
+					// Assistant multimodal content (e.g. text + image) -> single model content with parts
+					for _, item := range content.Array() {
+						switch item.Get("type").String() {
+						case "text":
+							node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".text", item.Get("text").String())
+							p++
+						case "image_url":
+							// If the assistant returned an inline data URL, preserve it for history fidelity.
+							imageURL := item.Get("image_url.url").String()
+							if len(imageURL) > 5 { // expect data:...
+								pieces := strings.SplitN(imageURL[5:], ";", 2)
+								if len(pieces) == 2 && len(pieces[1]) > 7 {
+									mime := pieces[0]
+									data := pieces[1][7:]
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.mime_type", mime)
+									node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.data", data)
+									p++
+								}
+							}
+						}
+					}
 				}
 
 				// Tool calls -> single model content with functionCall parts
@@ -236,7 +265,7 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 
 					// Append a single tool content combining name + response per function
-					toolNode := []byte(`{"role":"tool","parts":[]}`)
+					toolNode := []byte(`{"role":"user","parts":[]}`)
 					pp := 0
 					for _, fid := range fIDs {
 						if name, ok := tcID2Name[fid]; ok {
@@ -252,6 +281,8 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 					if pp > 0 {
 						out, _ = sjson.SetRawBytes(out, "request.contents.-1", toolNode)
 					}
+				} else {
+					out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
 				}
 			}
 		}
@@ -278,7 +309,7 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 								log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
 								continue
 							}
-							fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+							fnRaw, errSet = sjson.SetRaw(fnRaw, "parametersJsonSchema.properties", `{}`)
 							if errSet != nil {
 								log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
 								continue
@@ -293,7 +324,7 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 							log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
 							continue
 						}
-						fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+						fnRaw, errSet = sjson.SetRaw(fnRaw, "parametersJsonSchema.properties", `{}`)
 						if errSet != nil {
 							log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
 							continue

internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_response.go

@@ -8,7 +8,6 @@ package chat_completions
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 	"sync/atomic"
@@ -171,21 +170,16 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload, err := json.Marshal(map[string]any{
-					"type": "image_url",
-					"image_url": map[string]string{
-						"url": imageURL,
-					},
-				})
-				if err != nil {
-					continue
-				}
 				imagesResult := gjson.Get(template, "choices.0.delta.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
-				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", string(imagePayload))
+				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
 			}
 		}
 	}

internal/translator/gemini/claude/gemini_claude_request.go

@@ -7,10 +7,8 @@ package claude
 
 import (
 	"bytes"
-	"encoding/json"
 	"strings"
 
-	client "github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	"github.com/tidwall/gjson"
@@ -34,92 +32,102 @@ func ConvertClaudeRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 	rawJSON := bytes.Clone(inputRawJSON)
 	rawJSON = bytes.Replace(rawJSON, []byte(`"url":{"type":"string","format":"uri",`), []byte(`"url":{"type":"string",`), -1)
 
+	// Build output Gemini CLI request JSON
+	out := `{"contents":[]}`
+	out, _ = sjson.Set(out, "model", modelName)
+
 	// system instruction
-	var systemInstruction *client.Content
-	systemResult := gjson.GetBytes(rawJSON, "system")
-	if systemResult.IsArray() {
-		systemResults := systemResult.Array()
-		systemInstruction = &client.Content{Role: "user", Parts: []client.Part{}}
-		for i := 0; i < len(systemResults); i++ {
-			systemPromptResult := systemResults[i]
-			systemTypePromptResult := systemPromptResult.Get("type")
-			if systemTypePromptResult.Type == gjson.String && systemTypePromptResult.String() == "text" {
-				systemPrompt := systemPromptResult.Get("text").String()
-				systemPart := client.Part{Text: systemPrompt}
-				systemInstruction.Parts = append(systemInstruction.Parts, systemPart)
+	if systemResult := gjson.GetBytes(rawJSON, "system"); systemResult.IsArray() {
+		systemInstruction := `{"role":"user","parts":[]}`
+		hasSystemParts := false
+		systemResult.ForEach(func(_, systemPromptResult gjson.Result) bool {
+			if systemPromptResult.Get("type").String() == "text" {
+				textResult := systemPromptResult.Get("text")
+				if textResult.Type == gjson.String {
+					part := `{"text":""}`
+					part, _ = sjson.Set(part, "text", textResult.String())
+					systemInstruction, _ = sjson.SetRaw(systemInstruction, "parts.-1", part)
+					hasSystemParts = true
+				}
 			}
+			return true
+		})
+		if hasSystemParts {
+			out, _ = sjson.SetRaw(out, "system_instruction", systemInstruction)
 		}
-		if len(systemInstruction.Parts) == 0 {
-			systemInstruction = nil
-		}
+	} else if systemResult.Type == gjson.String {
+		out, _ = sjson.Set(out, "system_instruction.parts.-1.text", systemResult.String())
 	}
 
 	// contents
-	contents := make([]client.Content, 0)
-	messagesResult := gjson.GetBytes(rawJSON, "messages")
-	if messagesResult.IsArray() {
-		messageResults := messagesResult.Array()
-		for i := 0; i < len(messageResults); i++ {
-			messageResult := messageResults[i]
+	if messagesResult := gjson.GetBytes(rawJSON, "messages"); messagesResult.IsArray() {
+		messagesResult.ForEach(func(_, messageResult gjson.Result) bool {
 			roleResult := messageResult.Get("role")
 			if roleResult.Type != gjson.String {
-				continue
+				return true
 			}
 			role := roleResult.String()
 			if role == "assistant" {
 				role = "model"
 			}
-			clientContent := client.Content{Role: role, Parts: []client.Part{}}
+
+			contentJSON := `{"role":"","parts":[]}`
+			contentJSON, _ = sjson.Set(contentJSON, "role", role)
+
 			contentsResult := messageResult.Get("content")
 			if contentsResult.IsArray() {
-				contentResults := contentsResult.Array()
-				for j := 0; j < len(contentResults); j++ {
-					contentResult := contentResults[j]
-					contentTypeResult := contentResult.Get("type")
-					if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "text" {
-						prompt := contentResult.Get("text").String()
-						clientContent.Parts = append(clientContent.Parts, client.Part{Text: prompt})
-					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_use" {
+				contentsResult.ForEach(func(_, contentResult gjson.Result) bool {
+					switch contentResult.Get("type").String() {
+					case "text":
+						part := `{"text":""}`
+						part, _ = sjson.Set(part, "text", contentResult.Get("text").String())
+						contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
+
+					case "tool_use":
 						functionName := contentResult.Get("name").String()
 						functionArgs := contentResult.Get("input").String()
-						var args map[string]any
-						if err := json.Unmarshal([]byte(functionArgs), &args); err == nil {
-							clientContent.Parts = append(clientContent.Parts, client.Part{
-								FunctionCall:     &client.FunctionCall{Name: functionName, Args: args},
-								ThoughtSignature: geminiClaudeThoughtSignature,
-							})
+						argsResult := gjson.Parse(functionArgs)
+						if argsResult.IsObject() && gjson.Valid(functionArgs) {
+							part := `{"thoughtSignature":"","functionCall":{"name":"","args":{}}}`
+							part, _ = sjson.Set(part, "thoughtSignature", geminiClaudeThoughtSignature)
+							part, _ = sjson.Set(part, "functionCall.name", functionName)
+							part, _ = sjson.SetRaw(part, "functionCall.args", functionArgs)
+							contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
 						}
-					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_result" {
+
+					case "tool_result":
 						toolCallID := contentResult.Get("tool_use_id").String()
-						if toolCallID != "" {
-							funcName := toolCallID
-							toolCallIDs := strings.Split(toolCallID, "-")
-							if len(toolCallIDs) > 1 {
-								funcName = strings.Join(toolCallIDs[0:len(toolCallIDs)-1], "-")
-							}
-							responseData := contentResult.Get("content").Raw
-							functionResponse := client.FunctionResponse{Name: funcName, Response: map[string]interface{}{"result": responseData}}
-							clientContent.Parts = append(clientContent.Parts, client.Part{FunctionResponse: &functionResponse})
+						if toolCallID == "" {
+							return true
 						}
+						funcName := toolCallID
+						toolCallIDs := strings.Split(toolCallID, "-")
+						if len(toolCallIDs) > 1 {
+							funcName = strings.Join(toolCallIDs[0:len(toolCallIDs)-1], "-")
+						}
+						responseData := contentResult.Get("content").Raw
+						part := `{"functionResponse":{"name":"","response":{"result":""}}}`
+						part, _ = sjson.Set(part, "functionResponse.name", funcName)
+						part, _ = sjson.Set(part, "functionResponse.response.result", responseData)
+						contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
 					}
-				}
-				contents = append(contents, clientContent)
+					return true
+				})
+				out, _ = sjson.SetRaw(out, "contents.-1", contentJSON)
 			} else if contentsResult.Type == gjson.String {
-				prompt := contentsResult.String()
-				contents = append(contents, client.Content{Role: role, Parts: []client.Part{{Text: prompt}}})
+				part := `{"text":""}`
+				part, _ = sjson.Set(part, "text", contentsResult.String())
+				contentJSON, _ = sjson.SetRaw(contentJSON, "parts.-1", part)
+				out, _ = sjson.SetRaw(out, "contents.-1", contentJSON)
 			}
-		}
+			return true
+		})
 	}
 
 	// tools
-	var tools []client.ToolDeclaration
-	toolsResult := gjson.GetBytes(rawJSON, "tools")
-	if toolsResult.IsArray() {
-		tools = make([]client.ToolDeclaration, 1)
-		tools[0].FunctionDeclarations = make([]any, 0)
-		toolsResults := toolsResult.Array()
-		for i := 0; i < len(toolsResults); i++ {
-			toolResult := toolsResults[i]
+	if toolsResult := gjson.GetBytes(rawJSON, "tools"); toolsResult.IsArray() {
+		hasTools := false
+		toolsResult.ForEach(func(_, toolResult gjson.Result) bool {
 			inputSchemaResult := toolResult.Get("input_schema")
 			if inputSchemaResult.Exists() && inputSchemaResult.IsObject() {
 				inputSchema := inputSchemaResult.Raw
@@ -127,30 +135,21 @@ func ConvertClaudeRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 				tool, _ = sjson.SetRaw(tool, "parametersJsonSchema", inputSchema)
 				tool, _ = sjson.Delete(tool, "strict")
 				tool, _ = sjson.Delete(tool, "input_examples")
-				var toolDeclaration any
-				if err := json.Unmarshal([]byte(tool), &toolDeclaration); err == nil {
-					tools[0].FunctionDeclarations = append(tools[0].FunctionDeclarations, toolDeclaration)
+				tool, _ = sjson.Delete(tool, "type")
+				tool, _ = sjson.Delete(tool, "cache_control")
+				if gjson.Valid(tool) && gjson.Parse(tool).IsObject() {
+					if !hasTools {
+						out, _ = sjson.SetRaw(out, "tools", `[{"functionDeclarations":[]}]`)
+						hasTools = true
+					}
+					out, _ = sjson.SetRaw(out, "tools.0.functionDeclarations.-1", tool)
 				}
 			}
+			return true
+		})
+		if !hasTools {
+			out, _ = sjson.Delete(out, "tools")
 		}
-	} else {
-		tools = make([]client.ToolDeclaration, 0)
-	}
-
-	// Build output Gemini CLI request JSON
-	out := `{"contents":[]}`
-	out, _ = sjson.Set(out, "model", modelName)
-	if systemInstruction != nil {
-		b, _ := json.Marshal(systemInstruction)
-		out, _ = sjson.SetRaw(out, "system_instruction", string(b))
-	}
-	if len(contents) > 0 {
-		b, _ := json.Marshal(contents)
-		out, _ = sjson.SetRaw(out, "contents", string(b))
-	}
-	if len(tools) > 0 && len(tools[0].FunctionDeclarations) > 0 {
-		b, _ := json.Marshal(tools)
-		out, _ = sjson.SetRaw(out, "tools", string(b))
 	}
 
 	// Map Anthropic thinking -> Gemini thinkingBudget/include_thoughts when enabled

internal/translator/gemini/claude/gemini_claude_response.go

@@ -9,7 +9,6 @@ package claude
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 	"sync/atomic"
@@ -282,22 +281,16 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 
 	root := gjson.ParseBytes(rawJSON)
 
-	response := map[string]interface{}{
-		"id":            root.Get("responseId").String(),
-		"type":          "message",
-		"role":          "assistant",
-		"model":         root.Get("modelVersion").String(),
-		"content":       []interface{}{},
-		"stop_reason":   nil,
-		"stop_sequence": nil,
-		"usage": map[string]interface{}{
-			"input_tokens":  root.Get("usageMetadata.promptTokenCount").Int(),
-			"output_tokens": root.Get("usageMetadata.candidatesTokenCount").Int() + root.Get("usageMetadata.thoughtsTokenCount").Int(),
-		},
-	}
+	out := `{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}`
+	out, _ = sjson.Set(out, "id", root.Get("responseId").String())
+	out, _ = sjson.Set(out, "model", root.Get("modelVersion").String())
+
+	inputTokens := root.Get("usageMetadata.promptTokenCount").Int()
+	outputTokens := root.Get("usageMetadata.candidatesTokenCount").Int() + root.Get("usageMetadata.thoughtsTokenCount").Int()
+	out, _ = sjson.Set(out, "usage.input_tokens", inputTokens)
+	out, _ = sjson.Set(out, "usage.output_tokens", outputTokens)
 
 	parts := root.Get("candidates.0.content.parts")
-	var contentBlocks []interface{}
 	textBuilder := strings.Builder{}
 	thinkingBuilder := strings.Builder{}
 	toolIDCounter := 0
@@ -307,10 +300,9 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 		if textBuilder.Len() == 0 {
 			return
 		}
-		contentBlocks = append(contentBlocks, map[string]interface{}{
-			"type": "text",
-			"text": textBuilder.String(),
-		})
+		block := `{"type":"text","text":""}`
+		block, _ = sjson.Set(block, "text", textBuilder.String())
+		out, _ = sjson.SetRaw(out, "content.-1", block)
 		textBuilder.Reset()
 	}
 
@@ -318,10 +310,9 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 		if thinkingBuilder.Len() == 0 {
 			return
 		}
-		contentBlocks = append(contentBlocks, map[string]interface{}{
-			"type":     "thinking",
-			"thinking": thinkingBuilder.String(),
-		})
+		block := `{"type":"thinking","thinking":""}`
+		block, _ = sjson.Set(block, "thinking", thinkingBuilder.String())
+		out, _ = sjson.SetRaw(out, "content.-1", block)
 		thinkingBuilder.Reset()
 	}
 
@@ -345,21 +336,15 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 
 				name := functionCall.Get("name").String()
 				toolIDCounter++
-				toolBlock := map[string]interface{}{
-					"type":  "tool_use",
-					"id":    fmt.Sprintf("tool_%d", toolIDCounter),
-					"name":  name,
-					"input": map[string]interface{}{},
+				toolBlock := `{"type":"tool_use","id":"","name":"","input":{}}`
+				toolBlock, _ = sjson.Set(toolBlock, "id", fmt.Sprintf("tool_%d", toolIDCounter))
+				toolBlock, _ = sjson.Set(toolBlock, "name", name)
+				inputRaw := "{}"
+				if args := functionCall.Get("args"); args.Exists() && gjson.Valid(args.Raw) && args.IsObject() {
+					inputRaw = args.Raw
 				}
-
-				if args := functionCall.Get("args"); args.Exists() {
-					var parsed interface{}
-					if err := json.Unmarshal([]byte(args.Raw), &parsed); err == nil {
-						toolBlock["input"] = parsed
-					}
-				}
-
-				contentBlocks = append(contentBlocks, toolBlock)
+				toolBlock, _ = sjson.SetRaw(toolBlock, "input", inputRaw)
+				out, _ = sjson.SetRaw(out, "content.-1", toolBlock)
 				continue
 			}
 		}
@@ -368,8 +353,6 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 	flushThinking()
 	flushText()
 
-	response["content"] = contentBlocks
-
 	stopReason := "end_turn"
 	if hasToolCall {
 		stopReason = "tool_use"
@@ -385,19 +368,13 @@ func ConvertGeminiResponseToClaudeNonStream(_ context.Context, _ string, origina
 			}
 		}
 	}
-	response["stop_reason"] = stopReason
+	out, _ = sjson.Set(out, "stop_reason", stopReason)
 
-	if usage := response["usage"].(map[string]interface{}); usage["input_tokens"] == int64(0) && usage["output_tokens"] == int64(0) {
-		if usageMeta := root.Get("usageMetadata"); !usageMeta.Exists() {
-			delete(response, "usage")
-		}
+	if inputTokens == int64(0) && outputTokens == int64(0) && !root.Get("usageMetadata").Exists() {
+		out, _ = sjson.Delete(out, "usage")
 	}
 
-	encoded, err := json.Marshal(response)
-	if err != nil {
-		return ""
-	}
-	return string(encoded)
+	return out
 }
 
 func ClaudeTokenCount(ctx context.Context, count int64) string {

internal/translator/gemini/openai/chat-completions/gemini_openai_request.go

@@ -178,6 +178,14 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 				} else if content.IsObject() && content.Get("type").String() == "text" {
 					out, _ = sjson.SetBytes(out, "system_instruction.role", "user")
 					out, _ = sjson.SetBytes(out, "system_instruction.parts.0.text", content.Get("text").String())
+				} else if content.IsArray() {
+					contents := content.Array()
+					if len(contents) > 0 {
+						out, _ = sjson.SetBytes(out, "request.systemInstruction.role", "user")
+						for j := 0; j < len(contents); j++ {
+							out, _ = sjson.SetBytes(out, fmt.Sprintf("request.systemInstruction.parts.%d.text", j), contents[j].Get("text").String())
+						}
+					}
 				}
 			} else if role == "user" || (role == "system" && len(arr) == 1) {
 				// Build single user content node to avoid splitting into multiple contents
@@ -225,18 +233,15 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 			} else if role == "assistant" {
 				node := []byte(`{"role":"model","parts":[]}`)
 				p := 0
-
 				if content.Type == gjson.String {
 					// Assistant text -> single model content
 					node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
-					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 					p++
 				} else if content.IsArray() {
 					// Assistant multimodal content (e.g. text + image) -> single model content with parts
 					for _, item := range content.Array() {
 						switch item.Get("type").String() {
 						case "text":
-							node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".text", item.Get("text").String())
 							p++
 						case "image_url":
 							// If the assistant returned an inline data URL, preserve it for history fidelity.
@@ -253,7 +258,6 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 							}
 						}
 					}
-					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 				}
 
 				// Tool calls -> single model content with functionCall parts
@@ -278,7 +282,7 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 
 					// Append a single tool content combining name + response per function
-					toolNode := []byte(`{"role":"tool","parts":[]}`)
+					toolNode := []byte(`{"role":"user","parts":[]}`)
 					pp := 0
 					for _, fid := range fIDs {
 						if name, ok := tcID2Name[fid]; ok {
@@ -294,6 +298,8 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 					if pp > 0 {
 						out, _ = sjson.SetRawBytes(out, "contents.-1", toolNode)
 					}
+				} else {
+					out, _ = sjson.SetRawBytes(out, "contents.-1", node)
 				}
 			}
 		}
@@ -320,7 +326,7 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 								log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
 								continue
 							}
-							fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+							fnRaw, errSet = sjson.SetRaw(fnRaw, "parametersJsonSchema.properties", `{}`)
 							if errSet != nil {
 								log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
 								continue
@@ -335,7 +341,7 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 							log.Warnf("Failed to set default schema type for tool '%s': %v", fn.Get("name").String(), errSet)
 							continue
 						}
-						fnRaw, errSet = sjson.Set(fnRaw, "parametersJsonSchema.properties", map[string]interface{}{})
+						fnRaw, errSet = sjson.SetRaw(fnRaw, "parametersJsonSchema.properties", `{}`)
 						if errSet != nil {
 							log.Warnf("Failed to set default schema properties for tool '%s': %v", fn.Get("name").String(), errSet)
 							continue

internal/translator/gemini/openai/chat-completions/gemini_openai_response.go

@@ -8,12 +8,12 @@ package chat_completions
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 	"sync/atomic"
 	"time"
 
+	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -89,18 +89,27 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 
 	// Extract and set usage metadata (token counts).
 	if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() {
+		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
 		}
 		if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
 			template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
 		}
-		promptTokenCount := usageResult.Get("promptTokenCount").Int()
+		promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
 		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
 		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
 		if thoughtsTokenCount > 0 {
 			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
 		}
+		// Include cached token count if present (indicates prompt caching is working)
+		if cachedTokenCount > 0 {
+			var err error
+			template, err = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cachedTokenCount)
+			if err != nil {
+				log.Warnf("gemini openai response: failed to set cached_tokens in streaming: %v", err)
+			}
+		}
 	}
 
 	// Process the main content part of the response.
@@ -173,21 +182,16 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload, err := json.Marshal(map[string]any{
-					"type": "image_url",
-					"image_url": map[string]string{
-						"url": imageURL,
-					},
-				})
-				if err != nil {
-					continue
-				}
 				imagesResult := gjson.Get(template, "choices.0.delta.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
-				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", string(imagePayload))
+				template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
 			}
 		}
 	}
@@ -248,10 +252,19 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
 		}
 		promptTokenCount := usageResult.Get("promptTokenCount").Int()
 		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
+		cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
 		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
 		if thoughtsTokenCount > 0 {
 			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
 		}
+		// Include cached token count if present (indicates prompt caching is working)
+		if cachedTokenCount > 0 {
+			var err error
+			template, err = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cachedTokenCount)
+			if err != nil {
+				log.Warnf("gemini openai response: failed to set cached_tokens in non-streaming: %v", err)
+			}
+		}
 	}
 
 	// Process the main content part of the response.
@@ -305,21 +318,16 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
 					mimeType = "image/png"
 				}
 				imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
-				imagePayload, err := json.Marshal(map[string]any{
-					"type": "image_url",
-					"image_url": map[string]string{
-						"url": imageURL,
-					},
-				})
-				if err != nil {
-					continue
-				}
 				imagesResult := gjson.Get(template, "choices.0.message.images")
 				if !imagesResult.Exists() || !imagesResult.IsArray() {
 					template, _ = sjson.SetRaw(template, "choices.0.message.images", `[]`)
 				}
+				imageIndex := len(gjson.Get(template, "choices.0.message.images").Array())
+				imagePayload := `{"type":"image_url","image_url":{"url":""}}`
+				imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
+				imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
 				template, _ = sjson.Set(template, "choices.0.message.role", "assistant")
-				template, _ = sjson.SetRaw(template, "choices.0.message.images.-1", string(imagePayload))
+				template, _ = sjson.SetRaw(template, "choices.0.message.images.-1", imagePayload)
 			}
 		}
 	}

internal/translator/gemini/openai/responses/gemini_openai-responses_response.go

@@ -23,6 +23,7 @@ type geminiToResponsesState struct {
 	MsgIndex     int
 	CurrentMsgID string
 	TextBuf      strings.Builder
+	ItemTextBuf  strings.Builder
 
 	// reasoning aggregation
 	ReasoningOpened bool
@@ -117,7 +118,7 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 			st.CreatedAt = time.Now().Unix()
 		}
 
-		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null}}`
+		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"output":[]}}`
 		created, _ = sjson.Set(created, "sequence_number", nextSeq())
 		created, _ = sjson.Set(created, "response.id", st.ResponseID)
 		created, _ = sjson.Set(created, "response.created_at", st.CreatedAt)
@@ -160,11 +161,11 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 				}
 				if t := part.Get("text"); t.Exists() && t.String() != "" {
 					st.ReasoningBuf.WriteString(t.String())
-					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"text":""}`
+					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"delta":""}`
 					msg, _ = sjson.Set(msg, "sequence_number", nextSeq())
 					msg, _ = sjson.Set(msg, "item_id", st.ReasoningItemID)
 					msg, _ = sjson.Set(msg, "output_index", st.ReasoningIndex)
-					msg, _ = sjson.Set(msg, "text", t.String())
+					msg, _ = sjson.Set(msg, "delta", t.String())
 					out = append(out, emitEvent("response.reasoning_summary_text.delta", msg))
 				}
 				return true
@@ -189,6 +190,8 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 					partAdded, _ = sjson.Set(partAdded, "item_id", st.CurrentMsgID)
 					partAdded, _ = sjson.Set(partAdded, "output_index", st.MsgIndex)
 					out = append(out, emitEvent("response.content_part.added", partAdded))
+					st.ItemTextBuf.Reset()
+					st.ItemTextBuf.WriteString(t.String())
 				}
 				st.TextBuf.WriteString(t.String())
 				msg := `{"type":"response.output_text.delta","sequence_number":0,"item_id":"","output_index":0,"content_index":0,"delta":"","logprobs":[]}`
@@ -250,20 +253,24 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 		finalizeReasoning()
 		// Close message output if opened
 		if st.MsgOpened {
+			fullText := st.ItemTextBuf.String()
 			done := `{"type":"response.output_text.done","sequence_number":0,"item_id":"","output_index":0,"content_index":0,"text":"","logprobs":[]}`
 			done, _ = sjson.Set(done, "sequence_number", nextSeq())
 			done, _ = sjson.Set(done, "item_id", st.CurrentMsgID)
 			done, _ = sjson.Set(done, "output_index", st.MsgIndex)
+			done, _ = sjson.Set(done, "text", fullText)
 			out = append(out, emitEvent("response.output_text.done", done))
 			partDone := `{"type":"response.content_part.done","sequence_number":0,"item_id":"","output_index":0,"content_index":0,"part":{"type":"output_text","annotations":[],"logprobs":[],"text":""}}`
 			partDone, _ = sjson.Set(partDone, "sequence_number", nextSeq())
 			partDone, _ = sjson.Set(partDone, "item_id", st.CurrentMsgID)
 			partDone, _ = sjson.Set(partDone, "output_index", st.MsgIndex)
+			partDone, _ = sjson.Set(partDone, "part.text", fullText)
 			out = append(out, emitEvent("response.content_part.done", partDone))
 			final := `{"type":"response.output_item.done","sequence_number":0,"output_index":0,"item":{"id":"","type":"message","status":"completed","content":[{"type":"output_text","text":""}],"role":"assistant"}}`
 			final, _ = sjson.Set(final, "sequence_number", nextSeq())
 			final, _ = sjson.Set(final, "output_index", st.MsgIndex)
 			final, _ = sjson.Set(final, "item.id", st.CurrentMsgID)
+			final, _ = sjson.Set(final, "item.content.0.text", fullText)
 			out = append(out, emitEvent("response.output_item.done", final))
 		}
 
@@ -377,27 +384,18 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 		}
 
 		// Compose outputs in encountered order: reasoning, message, function_calls
-		var outputs []interface{}
+		outputsWrapper := `{"arr":[]}`
 		if st.ReasoningOpened {
-			outputs = append(outputs, map[string]interface{}{
-				"id":      st.ReasoningItemID,
-				"type":    "reasoning",
-				"summary": []interface{}{map[string]interface{}{"type": "summary_text", "text": st.ReasoningBuf.String()}},
-			})
+			item := `{"id":"","type":"reasoning","summary":[{"type":"summary_text","text":""}]}`
+			item, _ = sjson.Set(item, "id", st.ReasoningItemID)
+			item, _ = sjson.Set(item, "summary.0.text", st.ReasoningBuf.String())
+			outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 		}
 		if st.MsgOpened {
-			outputs = append(outputs, map[string]interface{}{
-				"id":     st.CurrentMsgID,
-				"type":   "message",
-				"status": "completed",
-				"content": []interface{}{map[string]interface{}{
-					"type":        "output_text",
-					"annotations": []interface{}{},
-					"logprobs":    []interface{}{},
-					"text":        st.TextBuf.String(),
-				}},
-				"role": "assistant",
-			})
+			item := `{"id":"","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":""}],"role":"assistant"}`
+			item, _ = sjson.Set(item, "id", st.CurrentMsgID)
+			item, _ = sjson.Set(item, "content.0.text", st.TextBuf.String())
+			outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 		}
 		if len(st.FuncArgsBuf) > 0 {
 			idxs := make([]int, 0, len(st.FuncArgsBuf))
@@ -416,18 +414,16 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 				if b := st.FuncArgsBuf[idx]; b != nil {
 					args = b.String()
 				}
-				outputs = append(outputs, map[string]interface{}{
-					"id":        fmt.Sprintf("fc_%s", st.FuncCallIDs[idx]),
-					"type":      "function_call",
-					"status":    "completed",
-					"arguments": args,
-					"call_id":   st.FuncCallIDs[idx],
-					"name":      st.FuncNames[idx],
-				})
+				item := `{"id":"","type":"function_call","status":"completed","arguments":"","call_id":"","name":""}`
+				item, _ = sjson.Set(item, "id", fmt.Sprintf("fc_%s", st.FuncCallIDs[idx]))
+				item, _ = sjson.Set(item, "arguments", args)
+				item, _ = sjson.Set(item, "call_id", st.FuncCallIDs[idx])
+				item, _ = sjson.Set(item, "name", st.FuncNames[idx])
+				outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 			}
 		}
-		if len(outputs) > 0 {
-			completed, _ = sjson.Set(completed, "response.output", outputs)
+		if gjson.Get(outputsWrapper, "arr.#").Int() > 0 {
+			completed, _ = sjson.SetRaw(completed, "response.output", gjson.Get(outputsWrapper, "arr").Raw)
 		}
 
 		// usage mapping
@@ -558,11 +554,24 @@ func ConvertGeminiResponseToOpenAIResponsesNonStream(_ context.Context, _ string
 	}
 
 	// Build outputs from candidates[0].content.parts
-	var outputs []interface{}
 	var reasoningText strings.Builder
 	var reasoningEncrypted string
 	var messageText strings.Builder
 	var haveMessage bool
+
+	haveOutput := false
+	ensureOutput := func() {
+		if haveOutput {
+			return
+		}
+		resp, _ = sjson.SetRaw(resp, "output", "[]")
+		haveOutput = true
+	}
+	appendOutput := func(itemJSON string) {
+		ensureOutput()
+		resp, _ = sjson.SetRaw(resp, "output.-1", itemJSON)
+	}
+
 	if parts := root.Get("candidates.0.content.parts"); parts.Exists() && parts.IsArray() {
 		parts.ForEach(func(_, p gjson.Result) bool {
 			if p.Get("thought").Bool() {
@@ -583,19 +592,16 @@ func ConvertGeminiResponseToOpenAIResponsesNonStream(_ context.Context, _ string
 				name := fc.Get("name").String()
 				args := fc.Get("args")
 				callID := fmt.Sprintf("call_%x_%d", time.Now().UnixNano(), atomic.AddUint64(&funcCallIDCounter, 1))
-				outputs = append(outputs, map[string]interface{}{
-					"id":     fmt.Sprintf("fc_%s", callID),
-					"type":   "function_call",
-					"status": "completed",
-					"arguments": func() string {
-						if args.Exists() {
-							return args.Raw
-						}
-						return ""
-					}(),
-					"call_id": callID,
-					"name":    name,
-				})
+				itemJSON := `{"id":"","type":"function_call","status":"completed","arguments":"","call_id":"","name":""}`
+				itemJSON, _ = sjson.Set(itemJSON, "id", fmt.Sprintf("fc_%s", callID))
+				itemJSON, _ = sjson.Set(itemJSON, "call_id", callID)
+				itemJSON, _ = sjson.Set(itemJSON, "name", name)
+				argsStr := ""
+				if args.Exists() {
+					argsStr = args.Raw
+				}
+				itemJSON, _ = sjson.Set(itemJSON, "arguments", argsStr)
+				appendOutput(itemJSON)
 				return true
 			}
 			return true
@@ -605,42 +611,24 @@ func ConvertGeminiResponseToOpenAIResponsesNonStream(_ context.Context, _ string
 	// Reasoning output item
 	if reasoningText.Len() > 0 || reasoningEncrypted != "" {
 		rid := strings.TrimPrefix(id, "resp_")
-		item := map[string]interface{}{
-			"id":                fmt.Sprintf("rs_%s", rid),
-			"type":              "reasoning",
-			"encrypted_content": reasoningEncrypted,
-		}
-		var summaries []interface{}
+		itemJSON := `{"id":"","type":"reasoning","encrypted_content":""}`
+		itemJSON, _ = sjson.Set(itemJSON, "id", fmt.Sprintf("rs_%s", rid))
+		itemJSON, _ = sjson.Set(itemJSON, "encrypted_content", reasoningEncrypted)
 		if reasoningText.Len() > 0 {
-			summaries = append(summaries, map[string]interface{}{
-				"type": "summary_text",
-				"text": reasoningText.String(),
-			})
+			summaryJSON := `{"type":"summary_text","text":""}`
+			summaryJSON, _ = sjson.Set(summaryJSON, "text", reasoningText.String())
+			itemJSON, _ = sjson.SetRaw(itemJSON, "summary", "[]")
+			itemJSON, _ = sjson.SetRaw(itemJSON, "summary.-1", summaryJSON)
 		}
-		if summaries != nil {
-			item["summary"] = summaries
-		}
-		outputs = append(outputs, item)
+		appendOutput(itemJSON)
 	}
 
 	// Assistant message output item
 	if haveMessage {
-		outputs = append(outputs, map[string]interface{}{
-			"id":     fmt.Sprintf("msg_%s_0", strings.TrimPrefix(id, "resp_")),
-			"type":   "message",
-			"status": "completed",
-			"content": []interface{}{map[string]interface{}{
-				"type":        "output_text",
-				"annotations": []interface{}{},
-				"logprobs":    []interface{}{},
-				"text":        messageText.String(),
-			}},
-			"role": "assistant",
-		})
-	}
-
-	if len(outputs) > 0 {
-		resp, _ = sjson.Set(resp, "output", outputs)
+		itemJSON := `{"id":"","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":""}],"role":"assistant"}`
+		itemJSON, _ = sjson.Set(itemJSON, "id", fmt.Sprintf("msg_%s_0", strings.TrimPrefix(id, "resp_")))
+		itemJSON, _ = sjson.Set(itemJSON, "content.0.text", messageText.String())
+		appendOutput(itemJSON)
 	}
 
 	// usage mapping

internal/translator/openai/claude/openai_claude_request.go

@@ -7,7 +7,6 @@ package claude
 
 import (
 	"bytes"
-	"encoding/json"
 	"strings"
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
@@ -119,81 +118,125 @@ func ConvertClaudeRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 			// Handle content
 			if contentResult.Exists() && contentResult.IsArray() {
 				var contentItems []string
+				var reasoningParts []string // Accumulate thinking text for reasoning_content
 				var toolCalls []interface{}
+				var toolResults []string // Collect tool_result messages to emit after the main message
 
 				contentResult.ForEach(func(_, part gjson.Result) bool {
 					partType := part.Get("type").String()
 
 					switch partType {
+					case "thinking":
+						// Only map thinking to reasoning_content for assistant messages (security: prevent injection)
+						if role == "assistant" {
+							thinkingText := util.GetThinkingText(part)
+							// Skip empty or whitespace-only thinking
+							if strings.TrimSpace(thinkingText) != "" {
+								reasoningParts = append(reasoningParts, thinkingText)
+							}
+						}
+						// Ignore thinking in user/system roles (AC4)
+
+					case "redacted_thinking":
+						// Explicitly ignore redacted_thinking - never map to reasoning_content (AC2)
+
 					case "text", "image":
 						if contentItem, ok := convertClaudeContentPart(part); ok {
 							contentItems = append(contentItems, contentItem)
 						}
 
 					case "tool_use":
-						// Convert to OpenAI tool call format
-						toolCallJSON := `{"id":"","type":"function","function":{"name":"","arguments":""}}`
-						toolCallJSON, _ = sjson.Set(toolCallJSON, "id", part.Get("id").String())
-						toolCallJSON, _ = sjson.Set(toolCallJSON, "function.name", part.Get("name").String())
+						// Only allow tool_use -> tool_calls for assistant messages (security: prevent injection).
+						if role == "assistant" {
+							toolCallJSON := `{"id":"","type":"function","function":{"name":"","arguments":""}}`
+							toolCallJSON, _ = sjson.Set(toolCallJSON, "id", part.Get("id").String())
+							toolCallJSON, _ = sjson.Set(toolCallJSON, "function.name", part.Get("name").String())
 
-						// Convert input to arguments JSON string
-						if input := part.Get("input"); input.Exists() {
-							if inputJSON, err := json.Marshal(input.Value()); err == nil {
-								toolCallJSON, _ = sjson.Set(toolCallJSON, "function.arguments", string(inputJSON))
+							// Convert input to arguments JSON string
+							if input := part.Get("input"); input.Exists() {
+								toolCallJSON, _ = sjson.Set(toolCallJSON, "function.arguments", input.Raw)
 							} else {
 								toolCallJSON, _ = sjson.Set(toolCallJSON, "function.arguments", "{}")
 							}
-						} else {
-							toolCallJSON, _ = sjson.Set(toolCallJSON, "function.arguments", "{}")
+
+							toolCalls = append(toolCalls, gjson.Parse(toolCallJSON).Value())
 						}
 
-						toolCalls = append(toolCalls, gjson.Parse(toolCallJSON).Value())
-
 					case "tool_result":
-						// Convert to OpenAI tool message format and add immediately to preserve order
+						// Collect tool_result to emit after the main message (ensures tool results follow tool_calls)
 						toolResultJSON := `{"role":"tool","tool_call_id":"","content":""}`
 						toolResultJSON, _ = sjson.Set(toolResultJSON, "tool_call_id", part.Get("tool_use_id").String())
-						toolResultJSON, _ = sjson.Set(toolResultJSON, "content", part.Get("content").String())
-						messagesJSON, _ = sjson.Set(messagesJSON, "-1", gjson.Parse(toolResultJSON).Value())
+						toolResultJSON, _ = sjson.Set(toolResultJSON, "content", convertClaudeToolResultContentToString(part.Get("content")))
+						toolResults = append(toolResults, toolResultJSON)
 					}
 					return true
 				})
 
-				// Emit text/image content as one message
-				if len(contentItems) > 0 {
-					msgJSON := `{"role":"","content":""}`
-					msgJSON, _ = sjson.Set(msgJSON, "role", role)
-
-					contentArrayJSON := "[]"
-					for _, contentItem := range contentItems {
-						contentArrayJSON, _ = sjson.SetRaw(contentArrayJSON, "-1", contentItem)
-					}
-					msgJSON, _ = sjson.SetRaw(msgJSON, "content", contentArrayJSON)
-
-					contentValue := gjson.Get(msgJSON, "content")
-					hasContent := false
-					switch {
-					case !contentValue.Exists():
-						hasContent = false
-					case contentValue.Type == gjson.String:
-						hasContent = contentValue.String() != ""
-					case contentValue.IsArray():
-						hasContent = len(contentValue.Array()) > 0
-					default:
-						hasContent = contentValue.Raw != "" && contentValue.Raw != "null"
-					}
-
-					if hasContent {
-						messagesJSON, _ = sjson.Set(messagesJSON, "-1", gjson.Parse(msgJSON).Value())
-					}
+				// Build reasoning content string
+				reasoningContent := ""
+				if len(reasoningParts) > 0 {
+					reasoningContent = strings.Join(reasoningParts, "\n\n")
 				}
 
-				// Emit tool calls in a separate assistant message
-				if role == "assistant" && len(toolCalls) > 0 {
-					toolCallMsgJSON := `{"role":"assistant","tool_calls":[]}`
-					toolCallsJSON, _ := json.Marshal(toolCalls)
-					toolCallMsgJSON, _ = sjson.SetRaw(toolCallMsgJSON, "tool_calls", string(toolCallsJSON))
-					messagesJSON, _ = sjson.Set(messagesJSON, "-1", gjson.Parse(toolCallMsgJSON).Value())
+				hasContent := len(contentItems) > 0
+				hasReasoning := reasoningContent != ""
+				hasToolCalls := len(toolCalls) > 0
+				hasToolResults := len(toolResults) > 0
+
+				// OpenAI requires: tool messages MUST immediately follow the assistant message with tool_calls.
+				// Therefore, we emit tool_result messages FIRST (they respond to the previous assistant's tool_calls),
+				// then emit the current message's content.
+				for _, toolResultJSON := range toolResults {
+					messagesJSON, _ = sjson.Set(messagesJSON, "-1", gjson.Parse(toolResultJSON).Value())
+				}
+
+				// For assistant messages: emit a single unified message with content, tool_calls, and reasoning_content
+				// This avoids splitting into multiple assistant messages which breaks OpenAI tool-call adjacency
+				if role == "assistant" {
+					if hasContent || hasReasoning || hasToolCalls {
+						msgJSON := `{"role":"assistant"}`
+
+						// Add content (as array if we have items, empty string if reasoning-only)
+						if hasContent {
+							contentArrayJSON := "[]"
+							for _, contentItem := range contentItems {
+								contentArrayJSON, _ = sjson.SetRaw(contentArrayJSON, "-1", contentItem)
+							}
+							msgJSON, _ = sjson.SetRaw(msgJSON, "content", contentArrayJSON)
+						} else {
+							// Ensure content field exists for OpenAI compatibility
+							msgJSON, _ = sjson.Set(msgJSON, "content", "")
+						}
+
+						// Add reasoning_content if present
+						if hasReasoning {
+							msgJSON, _ = sjson.Set(msgJSON, "reasoning_content", reasoningContent)
+						}
+
+						// Add tool_calls if present (in same message as content)
+						if hasToolCalls {
+							msgJSON, _ = sjson.Set(msgJSON, "tool_calls", toolCalls)
+						}
+
+						messagesJSON, _ = sjson.Set(messagesJSON, "-1", gjson.Parse(msgJSON).Value())
+					}
+				} else {
+					// For non-assistant roles: emit content message if we have content
+					// If the message only contains tool_results (no text/image), we still processed them above
+					if hasContent {
+						msgJSON := `{"role":""}`
+						msgJSON, _ = sjson.Set(msgJSON, "role", role)
+
+						contentArrayJSON := "[]"
+						for _, contentItem := range contentItems {
+							contentArrayJSON, _ = sjson.SetRaw(contentArrayJSON, "-1", contentItem)
+						}
+						msgJSON, _ = sjson.SetRaw(msgJSON, "content", contentArrayJSON)
+
+						messagesJSON, _ = sjson.Set(messagesJSON, "-1", gjson.Parse(msgJSON).Value())
+					} else if hasToolResults && !hasContent {
+						// tool_results already emitted above, no additional user message needed
+					}
 				}
 
 			} else if contentResult.Exists() && contentResult.Type == gjson.String {
@@ -313,3 +356,43 @@ func convertClaudeContentPart(part gjson.Result) (string, bool) {
 		return "", false
 	}
 }
+
+func convertClaudeToolResultContentToString(content gjson.Result) string {
+	if !content.Exists() {
+		return ""
+	}
+
+	if content.Type == gjson.String {
+		return content.String()
+	}
+
+	if content.IsArray() {
+		var parts []string
+		content.ForEach(func(_, item gjson.Result) bool {
+			switch {
+			case item.Type == gjson.String:
+				parts = append(parts, item.String())
+			case item.IsObject() && item.Get("text").Exists() && item.Get("text").Type == gjson.String:
+				parts = append(parts, item.Get("text").String())
+			default:
+				parts = append(parts, item.Raw)
+			}
+			return true
+		})
+
+		joined := strings.Join(parts, "\n\n")
+		if strings.TrimSpace(joined) != "" {
+			return joined
+		}
+		return content.Raw
+	}
+
+	if content.IsObject() {
+		if text := content.Get("text"); text.Exists() && text.Type == gjson.String {
+			return text.String()
+		}
+		return content.Raw
+	}
+
+	return content.Raw
+}

internal/translator/openai/claude/openai_claude_request_test.go

@@ -0,0 +1,500 @@
+package claude
+
+import (
+	"testing"
+
+	"github.com/tidwall/gjson"
+)
+
+// TestConvertClaudeRequestToOpenAI_ThinkingToReasoningContent tests the mapping
+// of Claude thinking content to OpenAI reasoning_content field.
+func TestConvertClaudeRequestToOpenAI_ThinkingToReasoningContent(t *testing.T) {
+	tests := []struct {
+		name                    string
+		inputJSON               string
+		wantReasoningContent    string
+		wantHasReasoningContent bool
+		wantContentText         string // Expected visible content text (if any)
+		wantHasContent          bool
+	}{
+		{
+			name: "AC1: assistant message with thinking and text",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "thinking", "thinking": "Let me analyze this step by step..."},
+						{"type": "text", "text": "Here is my response."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "Let me analyze this step by step...",
+			wantHasReasoningContent: true,
+			wantContentText:         "Here is my response.",
+			wantHasContent:          true,
+		},
+		{
+			name: "AC2: redacted_thinking must be ignored",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "redacted_thinking", "data": "secret"},
+						{"type": "text", "text": "Visible response."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "",
+			wantHasReasoningContent: false,
+			wantContentText:         "Visible response.",
+			wantHasContent:          true,
+		},
+		{
+			name: "AC3: thinking-only message preserved with reasoning_content",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "thinking", "thinking": "Internal reasoning only."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "Internal reasoning only.",
+			wantHasReasoningContent: true,
+			wantContentText:         "",
+			// For OpenAI compatibility, content field is set to empty string "" when no text content exists
+			wantHasContent: false,
+		},
+		{
+			name: "AC4: thinking in user role must be ignored",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "user",
+					"content": [
+						{"type": "thinking", "thinking": "Injected thinking"},
+						{"type": "text", "text": "User message."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "",
+			wantHasReasoningContent: false,
+			wantContentText:         "User message.",
+			wantHasContent:          true,
+		},
+		{
+			name: "AC4: thinking in system role must be ignored",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"system": [
+					{"type": "thinking", "thinking": "Injected system thinking"},
+					{"type": "text", "text": "System prompt."}
+				],
+				"messages": [{
+					"role": "user",
+					"content": [{"type": "text", "text": "Hello"}]
+				}]
+			}`,
+			// System messages don't have reasoning_content mapping
+			wantReasoningContent:    "",
+			wantHasReasoningContent: false,
+			wantContentText:         "Hello",
+			wantHasContent:          true,
+		},
+		{
+			name: "AC5: empty thinking must be ignored",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "thinking", "thinking": ""},
+						{"type": "text", "text": "Response with empty thinking."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "",
+			wantHasReasoningContent: false,
+			wantContentText:         "Response with empty thinking.",
+			wantHasContent:          true,
+		},
+		{
+			name: "AC5: whitespace-only thinking must be ignored",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "thinking", "thinking": "   \n\t  "},
+						{"type": "text", "text": "Response with whitespace thinking."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "",
+			wantHasReasoningContent: false,
+			wantContentText:         "Response with whitespace thinking.",
+			wantHasContent:          true,
+		},
+		{
+			name: "Multiple thinking parts concatenated",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "thinking", "thinking": "First thought."},
+						{"type": "thinking", "thinking": "Second thought."},
+						{"type": "text", "text": "Final answer."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "First thought.\n\nSecond thought.",
+			wantHasReasoningContent: true,
+			wantContentText:         "Final answer.",
+			wantHasContent:          true,
+		},
+		{
+			name: "Mixed thinking and redacted_thinking",
+			inputJSON: `{
+				"model": "claude-3-opus",
+				"messages": [{
+					"role": "assistant",
+					"content": [
+						{"type": "thinking", "thinking": "Visible thought."},
+						{"type": "redacted_thinking", "data": "hidden"},
+						{"type": "text", "text": "Answer."}
+					]
+				}]
+			}`,
+			wantReasoningContent:    "Visible thought.",
+			wantHasReasoningContent: true,
+			wantContentText:         "Answer.",
+			wantHasContent:          true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := ConvertClaudeRequestToOpenAI("test-model", []byte(tt.inputJSON), false)
+			resultJSON := gjson.ParseBytes(result)
+
+			// Find the relevant message (skip system message at index 0)
+			messages := resultJSON.Get("messages").Array()
+			if len(messages) < 2 {
+				if tt.wantHasReasoningContent || tt.wantHasContent {
+					t.Fatalf("Expected at least 2 messages (system + user/assistant), got %d", len(messages))
+				}
+				return
+			}
+
+			// Check the last non-system message
+			var targetMsg gjson.Result
+			for i := len(messages) - 1; i >= 0; i-- {
+				if messages[i].Get("role").String() != "system" {
+					targetMsg = messages[i]
+					break
+				}
+			}
+
+			// Check reasoning_content
+			gotReasoningContent := targetMsg.Get("reasoning_content").String()
+			gotHasReasoningContent := targetMsg.Get("reasoning_content").Exists()
+
+			if gotHasReasoningContent != tt.wantHasReasoningContent {
+				t.Errorf("reasoning_content existence = %v, want %v", gotHasReasoningContent, tt.wantHasReasoningContent)
+			}
+
+			if gotReasoningContent != tt.wantReasoningContent {
+				t.Errorf("reasoning_content = %q, want %q", gotReasoningContent, tt.wantReasoningContent)
+			}
+
+			// Check content
+			content := targetMsg.Get("content")
+			// content has meaningful content if it's a non-empty array, or a non-empty string
+			var gotHasContent bool
+			switch {
+			case content.IsArray():
+				gotHasContent = len(content.Array()) > 0
+			case content.Type == gjson.String:
+				gotHasContent = content.String() != ""
+			default:
+				gotHasContent = false
+			}
+
+			if gotHasContent != tt.wantHasContent {
+				t.Errorf("content existence = %v, want %v", gotHasContent, tt.wantHasContent)
+			}
+
+			if tt.wantHasContent && tt.wantContentText != "" {
+				// Find text content
+				var foundText string
+				content.ForEach(func(_, v gjson.Result) bool {
+					if v.Get("type").String() == "text" {
+						foundText = v.Get("text").String()
+						return false
+					}
+					return true
+				})
+				if foundText != tt.wantContentText {
+					t.Errorf("content text = %q, want %q", foundText, tt.wantContentText)
+				}
+			}
+		})
+	}
+}
+
+// TestConvertClaudeRequestToOpenAI_ThinkingOnlyMessagePreserved tests AC3:
+// that a message with only thinking content is preserved (not dropped).
+func TestConvertClaudeRequestToOpenAI_ThinkingOnlyMessagePreserved(t *testing.T) {
+	inputJSON := `{
+		"model": "claude-3-opus",
+		"messages": [
+			{
+				"role": "user",
+				"content": [{"type": "text", "text": "What is 2+2?"}]
+			},
+			{
+				"role": "assistant",
+				"content": [{"type": "thinking", "thinking": "Let me calculate: 2+2=4"}]
+			},
+			{
+				"role": "user",
+				"content": [{"type": "text", "text": "Thanks"}]
+			}
+		]
+	}`
+
+	result := ConvertClaudeRequestToOpenAI("test-model", []byte(inputJSON), false)
+	resultJSON := gjson.ParseBytes(result)
+
+	messages := resultJSON.Get("messages").Array()
+
+	// Should have: system (auto-added) + user + assistant (thinking-only) + user = 4 messages
+	if len(messages) != 4 {
+		t.Fatalf("Expected 4 messages, got %d. Messages: %v", len(messages), resultJSON.Get("messages").Raw)
+	}
+
+	// Check the assistant message (index 2) has reasoning_content
+	assistantMsg := messages[2]
+	if assistantMsg.Get("role").String() != "assistant" {
+		t.Errorf("Expected message[2] to be assistant, got %s", assistantMsg.Get("role").String())
+	}
+
+	if !assistantMsg.Get("reasoning_content").Exists() {
+		t.Error("Expected assistant message to have reasoning_content")
+	}
+
+	if assistantMsg.Get("reasoning_content").String() != "Let me calculate: 2+2=4" {
+		t.Errorf("Unexpected reasoning_content: %s", assistantMsg.Get("reasoning_content").String())
+	}
+}
+
+func TestConvertClaudeRequestToOpenAI_ToolResultOrderAndContent(t *testing.T) {
+	inputJSON := `{
+		"model": "claude-3-opus",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "tool_use", "id": "call_1", "name": "do_work", "input": {"a": 1}}
+				]
+			},
+			{
+				"role": "user",
+				"content": [
+					{"type": "text", "text": "before"},
+					{"type": "tool_result", "tool_use_id": "call_1", "content": [{"type":"text","text":"tool ok"}]},
+					{"type": "text", "text": "after"}
+				]
+			}
+		]
+	}`
+
+	result := ConvertClaudeRequestToOpenAI("test-model", []byte(inputJSON), false)
+	resultJSON := gjson.ParseBytes(result)
+	messages := resultJSON.Get("messages").Array()
+
+	// OpenAI requires: tool messages MUST immediately follow assistant(tool_calls).
+	// Correct order: system + assistant(tool_calls) + tool(result) + user(before+after)
+	if len(messages) != 4 {
+		t.Fatalf("Expected 4 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	}
+
+	if messages[0].Get("role").String() != "system" {
+		t.Fatalf("Expected messages[0] to be system, got %s", messages[0].Get("role").String())
+	}
+
+	if messages[1].Get("role").String() != "assistant" || !messages[1].Get("tool_calls").Exists() {
+		t.Fatalf("Expected messages[1] to be assistant tool_calls, got %s: %s", messages[1].Get("role").String(), messages[1].Raw)
+	}
+
+	// tool message MUST immediately follow assistant(tool_calls) per OpenAI spec
+	if messages[2].Get("role").String() != "tool" {
+		t.Fatalf("Expected messages[2] to be tool (must follow tool_calls), got %s", messages[2].Get("role").String())
+	}
+	if got := messages[2].Get("tool_call_id").String(); got != "call_1" {
+		t.Fatalf("Expected tool_call_id %q, got %q", "call_1", got)
+	}
+	if got := messages[2].Get("content").String(); got != "tool ok" {
+		t.Fatalf("Expected tool content %q, got %q", "tool ok", got)
+	}
+
+	// User message comes after tool message
+	if messages[3].Get("role").String() != "user" {
+		t.Fatalf("Expected messages[3] to be user, got %s", messages[3].Get("role").String())
+	}
+	// User message should contain both "before" and "after" text
+	if got := messages[3].Get("content.0.text").String(); got != "before" {
+		t.Fatalf("Expected user text[0] %q, got %q", "before", got)
+	}
+	if got := messages[3].Get("content.1.text").String(); got != "after" {
+		t.Fatalf("Expected user text[1] %q, got %q", "after", got)
+	}
+}
+
+func TestConvertClaudeRequestToOpenAI_ToolResultObjectContent(t *testing.T) {
+	inputJSON := `{
+		"model": "claude-3-opus",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "tool_use", "id": "call_1", "name": "do_work", "input": {"a": 1}}
+				]
+			},
+			{
+				"role": "user",
+				"content": [
+					{"type": "tool_result", "tool_use_id": "call_1", "content": {"foo": "bar"}}
+				]
+			}
+		]
+	}`
+
+	result := ConvertClaudeRequestToOpenAI("test-model", []byte(inputJSON), false)
+	resultJSON := gjson.ParseBytes(result)
+	messages := resultJSON.Get("messages").Array()
+
+	// system + assistant(tool_calls) + tool(result)
+	if len(messages) != 3 {
+		t.Fatalf("Expected 3 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	}
+
+	if messages[2].Get("role").String() != "tool" {
+		t.Fatalf("Expected messages[2] to be tool, got %s", messages[2].Get("role").String())
+	}
+
+	toolContent := messages[2].Get("content").String()
+	parsed := gjson.Parse(toolContent)
+	if parsed.Get("foo").String() != "bar" {
+		t.Fatalf("Expected tool content JSON foo=bar, got %q", toolContent)
+	}
+}
+
+func TestConvertClaudeRequestToOpenAI_AssistantTextToolUseTextOrder(t *testing.T) {
+	inputJSON := `{
+		"model": "claude-3-opus",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "text", "text": "pre"},
+					{"type": "tool_use", "id": "call_1", "name": "do_work", "input": {"a": 1}},
+					{"type": "text", "text": "post"}
+				]
+			}
+		]
+	}`
+
+	result := ConvertClaudeRequestToOpenAI("test-model", []byte(inputJSON), false)
+	resultJSON := gjson.ParseBytes(result)
+	messages := resultJSON.Get("messages").Array()
+
+	// New behavior: content + tool_calls unified in single assistant message
+	// Expect: system + assistant(content[pre,post] + tool_calls)
+	if len(messages) != 2 {
+		t.Fatalf("Expected 2 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	}
+
+	if messages[0].Get("role").String() != "system" {
+		t.Fatalf("Expected messages[0] to be system, got %s", messages[0].Get("role").String())
+	}
+
+	assistantMsg := messages[1]
+	if assistantMsg.Get("role").String() != "assistant" {
+		t.Fatalf("Expected messages[1] to be assistant, got %s", assistantMsg.Get("role").String())
+	}
+
+	// Should have both content and tool_calls in same message
+	if !assistantMsg.Get("tool_calls").Exists() {
+		t.Fatalf("Expected assistant message to have tool_calls")
+	}
+	if got := assistantMsg.Get("tool_calls.0.id").String(); got != "call_1" {
+		t.Fatalf("Expected tool_call id %q, got %q", "call_1", got)
+	}
+	if got := assistantMsg.Get("tool_calls.0.function.name").String(); got != "do_work" {
+		t.Fatalf("Expected tool_call name %q, got %q", "do_work", got)
+	}
+
+	// Content should have both pre and post text
+	if got := assistantMsg.Get("content.0.text").String(); got != "pre" {
+		t.Fatalf("Expected content[0] text %q, got %q", "pre", got)
+	}
+	if got := assistantMsg.Get("content.1.text").String(); got != "post" {
+		t.Fatalf("Expected content[1] text %q, got %q", "post", got)
+	}
+}
+
+func TestConvertClaudeRequestToOpenAI_AssistantThinkingToolUseThinkingSplit(t *testing.T) {
+	inputJSON := `{
+		"model": "claude-3-opus",
+		"messages": [
+			{
+				"role": "assistant",
+				"content": [
+					{"type": "thinking", "thinking": "t1"},
+					{"type": "text", "text": "pre"},
+					{"type": "tool_use", "id": "call_1", "name": "do_work", "input": {"a": 1}},
+					{"type": "thinking", "thinking": "t2"},
+					{"type": "text", "text": "post"}
+				]
+			}
+		]
+	}`
+
+	result := ConvertClaudeRequestToOpenAI("test-model", []byte(inputJSON), false)
+	resultJSON := gjson.ParseBytes(result)
+	messages := resultJSON.Get("messages").Array()
+
+	// New behavior: all content, thinking, and tool_calls unified in single assistant message
+	// Expect: system + assistant(content[pre,post] + tool_calls + reasoning_content[t1+t2])
+	if len(messages) != 2 {
+		t.Fatalf("Expected 2 messages, got %d. Messages: %s", len(messages), resultJSON.Get("messages").Raw)
+	}
+
+	assistantMsg := messages[1]
+	if assistantMsg.Get("role").String() != "assistant" {
+		t.Fatalf("Expected messages[1] to be assistant, got %s", assistantMsg.Get("role").String())
+	}
+
+	// Should have content with both pre and post
+	if got := assistantMsg.Get("content.0.text").String(); got != "pre" {
+		t.Fatalf("Expected content[0] text %q, got %q", "pre", got)
+	}
+	if got := assistantMsg.Get("content.1.text").String(); got != "post" {
+		t.Fatalf("Expected content[1] text %q, got %q", "post", got)
+	}
+
+	// Should have tool_calls
+	if !assistantMsg.Get("tool_calls").Exists() {
+		t.Fatalf("Expected assistant message to have tool_calls")
+	}
+
+	// Should have combined reasoning_content from both thinking blocks
+	if got := assistantMsg.Get("reasoning_content").String(); got != "t1\n\nt2" {
+		t.Fatalf("Expected reasoning_content %q, got %q", "t1\n\nt2", got)
+	}
+}

internal/translator/openai/claude/openai_claude_response.go

@@ -8,7 +8,6 @@ package claude
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strings"
 
@@ -133,24 +132,10 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 	if delta := root.Get("choices.0.delta"); delta.Exists() {
 		if !param.MessageStarted {
 			// Send message_start event
-			messageStart := map[string]interface{}{
-				"type": "message_start",
-				"message": map[string]interface{}{
-					"id":            param.MessageID,
-					"type":          "message",
-					"role":          "assistant",
-					"model":         param.Model,
-					"content":       []interface{}{},
-					"stop_reason":   nil,
-					"stop_sequence": nil,
-					"usage": map[string]interface{}{
-						"input_tokens":  0,
-						"output_tokens": 0,
-					},
-				},
-			}
-			messageStartJSON, _ := json.Marshal(messageStart)
-			results = append(results, "event: message_start\ndata: "+string(messageStartJSON)+"\n\n")
+			messageStartJSON := `{"type":"message_start","message":{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}}`
+			messageStartJSON, _ = sjson.Set(messageStartJSON, "message.id", param.MessageID)
+			messageStartJSON, _ = sjson.Set(messageStartJSON, "message.model", param.Model)
+			results = append(results, "event: message_start\ndata: "+messageStartJSON+"\n\n")
 			param.MessageStarted = true
 
 			// Don't send content_block_start for text here - wait for actual content
@@ -168,29 +153,16 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 						param.ThinkingContentBlockIndex = param.NextContentBlockIndex
 						param.NextContentBlockIndex++
 					}
-					contentBlockStart := map[string]interface{}{
-						"type":  "content_block_start",
-						"index": param.ThinkingContentBlockIndex,
-						"content_block": map[string]interface{}{
-							"type":     "thinking",
-							"thinking": "",
-						},
-					}
-					contentBlockStartJSON, _ := json.Marshal(contentBlockStart)
-					results = append(results, "event: content_block_start\ndata: "+string(contentBlockStartJSON)+"\n\n")
+					contentBlockStartJSON := `{"type":"content_block_start","index":0,"content_block":{"type":"thinking","thinking":""}}`
+					contentBlockStartJSON, _ = sjson.Set(contentBlockStartJSON, "index", param.ThinkingContentBlockIndex)
+					results = append(results, "event: content_block_start\ndata: "+contentBlockStartJSON+"\n\n")
 					param.ThinkingContentBlockStarted = true
 				}
 
-				thinkingDelta := map[string]interface{}{
-					"type":  "content_block_delta",
-					"index": param.ThinkingContentBlockIndex,
-					"delta": map[string]interface{}{
-						"type":     "thinking_delta",
-						"thinking": reasoningText,
-					},
-				}
-				thinkingDeltaJSON, _ := json.Marshal(thinkingDelta)
-				results = append(results, "event: content_block_delta\ndata: "+string(thinkingDeltaJSON)+"\n\n")
+				thinkingDeltaJSON := `{"type":"content_block_delta","index":0,"delta":{"type":"thinking_delta","thinking":""}}`
+				thinkingDeltaJSON, _ = sjson.Set(thinkingDeltaJSON, "index", param.ThinkingContentBlockIndex)
+				thinkingDeltaJSON, _ = sjson.Set(thinkingDeltaJSON, "delta.thinking", reasoningText)
+				results = append(results, "event: content_block_delta\ndata: "+thinkingDeltaJSON+"\n\n")
 			}
 		}
 
@@ -203,29 +175,16 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 					param.TextContentBlockIndex = param.NextContentBlockIndex
 					param.NextContentBlockIndex++
 				}
-				contentBlockStart := map[string]interface{}{
-					"type":  "content_block_start",
-					"index": param.TextContentBlockIndex,
-					"content_block": map[string]interface{}{
-						"type": "text",
-						"text": "",
-					},
-				}
-				contentBlockStartJSON, _ := json.Marshal(contentBlockStart)
-				results = append(results, "event: content_block_start\ndata: "+string(contentBlockStartJSON)+"\n\n")
+				contentBlockStartJSON := `{"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}`
+				contentBlockStartJSON, _ = sjson.Set(contentBlockStartJSON, "index", param.TextContentBlockIndex)
+				results = append(results, "event: content_block_start\ndata: "+contentBlockStartJSON+"\n\n")
 				param.TextContentBlockStarted = true
 			}
 
-			contentDelta := map[string]interface{}{
-				"type":  "content_block_delta",
-				"index": param.TextContentBlockIndex,
-				"delta": map[string]interface{}{
-					"type": "text_delta",
-					"text": content.String(),
-				},
-			}
-			contentDeltaJSON, _ := json.Marshal(contentDelta)
-			results = append(results, "event: content_block_delta\ndata: "+string(contentDeltaJSON)+"\n\n")
+			contentDeltaJSON := `{"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":""}}`
+			contentDeltaJSON, _ = sjson.Set(contentDeltaJSON, "index", param.TextContentBlockIndex)
+			contentDeltaJSON, _ = sjson.Set(contentDeltaJSON, "delta.text", content.String())
+			results = append(results, "event: content_block_delta\ndata: "+contentDeltaJSON+"\n\n")
 
 			// Accumulate content
 			param.ContentAccumulator.WriteString(content.String())
@@ -263,18 +222,11 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 						stopTextContentBlock(param, &results)
 
 						// Send content_block_start for tool_use
-						contentBlockStart := map[string]interface{}{
-							"type":  "content_block_start",
-							"index": blockIndex,
-							"content_block": map[string]interface{}{
-								"type":  "tool_use",
-								"id":    accumulator.ID,
-								"name":  accumulator.Name,
-								"input": map[string]interface{}{},
-							},
-						}
-						contentBlockStartJSON, _ := json.Marshal(contentBlockStart)
-						results = append(results, "event: content_block_start\ndata: "+string(contentBlockStartJSON)+"\n\n")
+						contentBlockStartJSON := `{"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"","name":"","input":{}}}`
+						contentBlockStartJSON, _ = sjson.Set(contentBlockStartJSON, "index", blockIndex)
+						contentBlockStartJSON, _ = sjson.Set(contentBlockStartJSON, "content_block.id", accumulator.ID)
+						contentBlockStartJSON, _ = sjson.Set(contentBlockStartJSON, "content_block.name", accumulator.Name)
+						results = append(results, "event: content_block_start\ndata: "+contentBlockStartJSON+"\n\n")
 					}
 
 					// Handle function arguments
@@ -298,12 +250,9 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 
 		// Send content_block_stop for thinking content if needed
 		if param.ThinkingContentBlockStarted {
-			contentBlockStop := map[string]interface{}{
-				"type":  "content_block_stop",
-				"index": param.ThinkingContentBlockIndex,
-			}
-			contentBlockStopJSON, _ := json.Marshal(contentBlockStop)
-			results = append(results, "event: content_block_stop\ndata: "+string(contentBlockStopJSON)+"\n\n")
+			contentBlockStopJSON := `{"type":"content_block_stop","index":0}`
+			contentBlockStopJSON, _ = sjson.Set(contentBlockStopJSON, "index", param.ThinkingContentBlockIndex)
+			results = append(results, "event: content_block_stop\ndata: "+contentBlockStopJSON+"\n\n")
 			param.ThinkingContentBlockStarted = false
 			param.ThinkingContentBlockIndex = -1
 		}
@@ -319,24 +268,15 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 
 				// Send complete input_json_delta with all accumulated arguments
 				if accumulator.Arguments.Len() > 0 {
-					inputDelta := map[string]interface{}{
-						"type":  "content_block_delta",
-						"index": blockIndex,
-						"delta": map[string]interface{}{
-							"type":         "input_json_delta",
-							"partial_json": util.FixJSON(accumulator.Arguments.String()),
-						},
-					}
-					inputDeltaJSON, _ := json.Marshal(inputDelta)
-					results = append(results, "event: content_block_delta\ndata: "+string(inputDeltaJSON)+"\n\n")
+					inputDeltaJSON := `{"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}}`
+					inputDeltaJSON, _ = sjson.Set(inputDeltaJSON, "index", blockIndex)
+					inputDeltaJSON, _ = sjson.Set(inputDeltaJSON, "delta.partial_json", util.FixJSON(accumulator.Arguments.String()))
+					results = append(results, "event: content_block_delta\ndata: "+inputDeltaJSON+"\n\n")
 				}
 
-				contentBlockStop := map[string]interface{}{
-					"type":  "content_block_stop",
-					"index": blockIndex,
-				}
-				contentBlockStopJSON, _ := json.Marshal(contentBlockStop)
-				results = append(results, "event: content_block_stop\ndata: "+string(contentBlockStopJSON)+"\n\n")
+				contentBlockStopJSON := `{"type":"content_block_stop","index":0}`
+				contentBlockStopJSON, _ = sjson.Set(contentBlockStopJSON, "index", blockIndex)
+				results = append(results, "event: content_block_stop\ndata: "+contentBlockStopJSON+"\n\n")
 				delete(param.ToolCallBlockIndexes, index)
 			}
 			param.ContentBlocksStopped = true
@@ -361,20 +301,11 @@ func convertOpenAIStreamingChunkToAnthropic(rawJSON []byte, param *ConvertOpenAI
 			}
 		}
 		// Send message_delta with usage
-		messageDelta := map[string]interface{}{
-			"type": "message_delta",
-			"delta": map[string]interface{}{
-				"stop_reason":   mapOpenAIFinishReasonToAnthropic(param.FinishReason),
-				"stop_sequence": nil,
-			},
-			"usage": map[string]interface{}{
-				"input_tokens":  inputTokens,
-				"output_tokens": outputTokens,
-			},
-		}
-
-		messageDeltaJSON, _ := json.Marshal(messageDelta)
-		results = append(results, "event: message_delta\ndata: "+string(messageDeltaJSON)+"\n\n")
+		messageDeltaJSON := `{"type":"message_delta","delta":{"stop_reason":"","stop_sequence":null},"usage":{"input_tokens":0,"output_tokens":0}}`
+		messageDeltaJSON, _ = sjson.Set(messageDeltaJSON, "delta.stop_reason", mapOpenAIFinishReasonToAnthropic(param.FinishReason))
+		messageDeltaJSON, _ = sjson.Set(messageDeltaJSON, "usage.input_tokens", inputTokens)
+		messageDeltaJSON, _ = sjson.Set(messageDeltaJSON, "usage.output_tokens", outputTokens)
+		results = append(results, "event: message_delta\ndata: "+messageDeltaJSON+"\n\n")
 		param.MessageDeltaSent = true
 
 		emitMessageStopIfNeeded(param, &results)
@@ -390,12 +321,9 @@ func convertOpenAIDoneToAnthropic(param *ConvertOpenAIResponseToAnthropicParams)
 
 	// Ensure all content blocks are stopped before final events
 	if param.ThinkingContentBlockStarted {
-		contentBlockStop := map[string]interface{}{
-			"type":  "content_block_stop",
-			"index": param.ThinkingContentBlockIndex,
-		}
-		contentBlockStopJSON, _ := json.Marshal(contentBlockStop)
-		results = append(results, "event: content_block_stop\ndata: "+string(contentBlockStopJSON)+"\n\n")
+		contentBlockStopJSON := `{"type":"content_block_stop","index":0}`
+		contentBlockStopJSON, _ = sjson.Set(contentBlockStopJSON, "index", param.ThinkingContentBlockIndex)
+		results = append(results, "event: content_block_stop\ndata: "+contentBlockStopJSON+"\n\n")
 		param.ThinkingContentBlockStarted = false
 		param.ThinkingContentBlockIndex = -1
 	}
@@ -408,24 +336,15 @@ func convertOpenAIDoneToAnthropic(param *ConvertOpenAIResponseToAnthropicParams)
 			blockIndex := param.toolContentBlockIndex(index)
 
 			if accumulator.Arguments.Len() > 0 {
-				inputDelta := map[string]interface{}{
-					"type":  "content_block_delta",
-					"index": blockIndex,
-					"delta": map[string]interface{}{
-						"type":         "input_json_delta",
-						"partial_json": util.FixJSON(accumulator.Arguments.String()),
-					},
-				}
-				inputDeltaJSON, _ := json.Marshal(inputDelta)
-				results = append(results, "event: content_block_delta\ndata: "+string(inputDeltaJSON)+"\n\n")
+				inputDeltaJSON := `{"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}}`
+				inputDeltaJSON, _ = sjson.Set(inputDeltaJSON, "index", blockIndex)
+				inputDeltaJSON, _ = sjson.Set(inputDeltaJSON, "delta.partial_json", util.FixJSON(accumulator.Arguments.String()))
+				results = append(results, "event: content_block_delta\ndata: "+inputDeltaJSON+"\n\n")
 			}
 
-			contentBlockStop := map[string]interface{}{
-				"type":  "content_block_stop",
-				"index": blockIndex,
-			}
-			contentBlockStopJSON, _ := json.Marshal(contentBlockStop)
-			results = append(results, "event: content_block_stop\ndata: "+string(contentBlockStopJSON)+"\n\n")
+			contentBlockStopJSON := `{"type":"content_block_stop","index":0}`
+			contentBlockStopJSON, _ = sjson.Set(contentBlockStopJSON, "index", blockIndex)
+			results = append(results, "event: content_block_stop\ndata: "+contentBlockStopJSON+"\n\n")
 			delete(param.ToolCallBlockIndexes, index)
 		}
 		param.ContentBlocksStopped = true
@@ -433,16 +352,9 @@ func convertOpenAIDoneToAnthropic(param *ConvertOpenAIResponseToAnthropicParams)
 
 	// If we haven't sent message_delta yet (no usage info was received), send it now
 	if param.FinishReason != "" && !param.MessageDeltaSent {
-		messageDelta := map[string]interface{}{
-			"type": "message_delta",
-			"delta": map[string]interface{}{
-				"stop_reason":   mapOpenAIFinishReasonToAnthropic(param.FinishReason),
-				"stop_sequence": nil,
-			},
-		}
-
-		messageDeltaJSON, _ := json.Marshal(messageDelta)
-		results = append(results, "event: message_delta\ndata: "+string(messageDeltaJSON)+"\n\n")
+		messageDeltaJSON := `{"type":"message_delta","delta":{"stop_reason":"","stop_sequence":null}}`
+		messageDeltaJSON, _ = sjson.Set(messageDeltaJSON, "delta.stop_reason", mapOpenAIFinishReasonToAnthropic(param.FinishReason))
+		results = append(results, "event: message_delta\ndata: "+messageDeltaJSON+"\n\n")
 		param.MessageDeltaSent = true
 	}
 
@@ -455,105 +367,73 @@ func convertOpenAIDoneToAnthropic(param *ConvertOpenAIResponseToAnthropicParams)
 func convertOpenAINonStreamingToAnthropic(rawJSON []byte) []string {
 	root := gjson.ParseBytes(rawJSON)
 
-	// Build Anthropic response
-	response := map[string]interface{}{
-		"id":            root.Get("id").String(),
-		"type":          "message",
-		"role":          "assistant",
-		"model":         root.Get("model").String(),
-		"content":       []interface{}{},
-		"stop_reason":   nil,
-		"stop_sequence": nil,
-		"usage": map[string]interface{}{
-			"input_tokens":  0,
-			"output_tokens": 0,
-		},
-	}
+	out := `{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}`
+	out, _ = sjson.Set(out, "id", root.Get("id").String())
+	out, _ = sjson.Set(out, "model", root.Get("model").String())
 
 	// Process message content and tool calls
-	var contentBlocks []interface{}
-
-	if choices := root.Get("choices"); choices.Exists() && choices.IsArray() {
+	if choices := root.Get("choices"); choices.Exists() && choices.IsArray() && len(choices.Array()) > 0 {
 		choice := choices.Array()[0] // Take first choice
-		reasoningNode := choice.Get("message.reasoning_content")
-		allReasoning := collectOpenAIReasoningTexts(reasoningNode)
 
-		for _, reasoningText := range allReasoning {
+		reasoningNode := choice.Get("message.reasoning_content")
+		for _, reasoningText := range collectOpenAIReasoningTexts(reasoningNode) {
 			if reasoningText == "" {
 				continue
 			}
-			contentBlocks = append(contentBlocks, map[string]interface{}{
-				"type":     "thinking",
-				"thinking": reasoningText,
-			})
+			block := `{"type":"thinking","thinking":""}`
+			block, _ = sjson.Set(block, "thinking", reasoningText)
+			out, _ = sjson.SetRaw(out, "content.-1", block)
 		}
 
 		// Handle text content
 		if content := choice.Get("message.content"); content.Exists() && content.String() != "" {
-			textBlock := map[string]interface{}{
-				"type": "text",
-				"text": content.String(),
-			}
-			contentBlocks = append(contentBlocks, textBlock)
+			block := `{"type":"text","text":""}`
+			block, _ = sjson.Set(block, "text", content.String())
+			out, _ = sjson.SetRaw(out, "content.-1", block)
 		}
 
 		// Handle tool calls
 		if toolCalls := choice.Get("message.tool_calls"); toolCalls.Exists() && toolCalls.IsArray() {
 			toolCalls.ForEach(func(_, toolCall gjson.Result) bool {
-				toolUseBlock := map[string]interface{}{
-					"type": "tool_use",
-					"id":   toolCall.Get("id").String(),
-					"name": toolCall.Get("function.name").String(),
-				}
+				toolUseBlock := `{"type":"tool_use","id":"","name":"","input":{}}`
+				toolUseBlock, _ = sjson.Set(toolUseBlock, "id", toolCall.Get("id").String())
+				toolUseBlock, _ = sjson.Set(toolUseBlock, "name", toolCall.Get("function.name").String())
 
-				// Parse arguments
-				argsStr := toolCall.Get("function.arguments").String()
-				argsStr = util.FixJSON(argsStr)
-				if argsStr != "" {
-					var args interface{}
-					if err := json.Unmarshal([]byte(argsStr), &args); err == nil {
-						toolUseBlock["input"] = args
+				argsStr := util.FixJSON(toolCall.Get("function.arguments").String())
+				if argsStr != "" && gjson.Valid(argsStr) {
+					argsJSON := gjson.Parse(argsStr)
+					if argsJSON.IsObject() {
+						toolUseBlock, _ = sjson.SetRaw(toolUseBlock, "input", argsJSON.Raw)
 					} else {
-						toolUseBlock["input"] = map[string]interface{}{}
+						toolUseBlock, _ = sjson.SetRaw(toolUseBlock, "input", "{}")
 					}
 				} else {
-					toolUseBlock["input"] = map[string]interface{}{}
+					toolUseBlock, _ = sjson.SetRaw(toolUseBlock, "input", "{}")
 				}
 
-				contentBlocks = append(contentBlocks, toolUseBlock)
+				out, _ = sjson.SetRaw(out, "content.-1", toolUseBlock)
 				return true
 			})
 		}
 
 		// Set stop reason
 		if finishReason := choice.Get("finish_reason"); finishReason.Exists() {
-			response["stop_reason"] = mapOpenAIFinishReasonToAnthropic(finishReason.String())
+			out, _ = sjson.Set(out, "stop_reason", mapOpenAIFinishReasonToAnthropic(finishReason.String()))
 		}
 	}
 
-	response["content"] = contentBlocks
-
 	// Set usage information
 	if usage := root.Get("usage"); usage.Exists() {
-		response["usage"] = map[string]interface{}{
-			"input_tokens":  usage.Get("prompt_tokens").Int(),
-			"output_tokens": usage.Get("completion_tokens").Int(),
-			"reasoning_tokens": func() int64 {
-				if v := usage.Get("completion_tokens_details.reasoning_tokens"); v.Exists() {
-					return v.Int()
-				}
-				return 0
-			}(),
-		}
-	} else {
-		response["usage"] = map[string]interface{}{
-			"input_tokens":  0,
-			"output_tokens": 0,
+		out, _ = sjson.Set(out, "usage.input_tokens", usage.Get("prompt_tokens").Int())
+		out, _ = sjson.Set(out, "usage.output_tokens", usage.Get("completion_tokens").Int())
+		reasoningTokens := int64(0)
+		if v := usage.Get("completion_tokens_details.reasoning_tokens"); v.Exists() {
+			reasoningTokens = v.Int()
 		}
+		out, _ = sjson.Set(out, "usage.reasoning_tokens", reasoningTokens)
 	}
 
-	responseJSON, _ := json.Marshal(response)
-	return []string{string(responseJSON)}
+	return []string{out}
 }
 
 // mapOpenAIFinishReasonToAnthropic maps OpenAI finish reasons to Anthropic equivalents
@@ -600,15 +480,15 @@ func collectOpenAIReasoningTexts(node gjson.Result) []string {
 
 	switch node.Type {
 	case gjson.String:
-		if text := strings.TrimSpace(node.String()); text != "" {
+		if text := node.String(); text != "" {
 			texts = append(texts, text)
 		}
 	case gjson.JSON:
 		if text := node.Get("text"); text.Exists() {
-			if trimmed := strings.TrimSpace(text.String()); trimmed != "" {
-				texts = append(texts, trimmed)
+			if textStr := text.String(); textStr != "" {
+				texts = append(texts, textStr)
 			}
-		} else if raw := strings.TrimSpace(node.Raw); raw != "" && !strings.HasPrefix(raw, "{") && !strings.HasPrefix(raw, "[") {
+		} else if raw := node.Raw; raw != "" && !strings.HasPrefix(raw, "{") && !strings.HasPrefix(raw, "[") {
 			texts = append(texts, raw)
 		}
 	}
@@ -620,12 +500,9 @@ func stopThinkingContentBlock(param *ConvertOpenAIResponseToAnthropicParams, res
 	if !param.ThinkingContentBlockStarted {
 		return
 	}
-	contentBlockStop := map[string]interface{}{
-		"type":  "content_block_stop",
-		"index": param.ThinkingContentBlockIndex,
-	}
-	contentBlockStopJSON, _ := json.Marshal(contentBlockStop)
-	*results = append(*results, "event: content_block_stop\ndata: "+string(contentBlockStopJSON)+"\n\n")
+	contentBlockStopJSON := `{"type":"content_block_stop","index":0}`
+	contentBlockStopJSON, _ = sjson.Set(contentBlockStopJSON, "index", param.ThinkingContentBlockIndex)
+	*results = append(*results, "event: content_block_stop\ndata: "+contentBlockStopJSON+"\n\n")
 	param.ThinkingContentBlockStarted = false
 	param.ThinkingContentBlockIndex = -1
 }
@@ -642,12 +519,9 @@ func stopTextContentBlock(param *ConvertOpenAIResponseToAnthropicParams, results
 	if !param.TextContentBlockStarted {
 		return
 	}
-	contentBlockStop := map[string]interface{}{
-		"type":  "content_block_stop",
-		"index": param.TextContentBlockIndex,
-	}
-	contentBlockStopJSON, _ := json.Marshal(contentBlockStop)
-	*results = append(*results, "event: content_block_stop\ndata: "+string(contentBlockStopJSON)+"\n\n")
+	contentBlockStopJSON := `{"type":"content_block_stop","index":0}`
+	contentBlockStopJSON, _ = sjson.Set(contentBlockStopJSON, "index", param.TextContentBlockIndex)
+	*results = append(*results, "event: content_block_stop\ndata: "+contentBlockStopJSON+"\n\n")
 	param.TextContentBlockStarted = false
 	param.TextContentBlockIndex = -1
 }
@@ -667,29 +541,19 @@ func ConvertOpenAIResponseToClaudeNonStream(_ context.Context, _ string, origina
 	_ = requestRawJSON
 
 	root := gjson.ParseBytes(rawJSON)
+	out := `{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}`
+	out, _ = sjson.Set(out, "id", root.Get("id").String())
+	out, _ = sjson.Set(out, "model", root.Get("model").String())
 
-	response := map[string]interface{}{
-		"id":            root.Get("id").String(),
-		"type":          "message",
-		"role":          "assistant",
-		"model":         root.Get("model").String(),
-		"content":       []interface{}{},
-		"stop_reason":   nil,
-		"stop_sequence": nil,
-		"usage": map[string]interface{}{
-			"input_tokens":  0,
-			"output_tokens": 0,
-		},
-	}
-
-	contentBlocks := make([]interface{}, 0)
 	hasToolCall := false
+	stopReasonSet := false
 
 	if choices := root.Get("choices"); choices.Exists() && choices.IsArray() && len(choices.Array()) > 0 {
 		choice := choices.Array()[0]
 
 		if finishReason := choice.Get("finish_reason"); finishReason.Exists() {
-			response["stop_reason"] = mapOpenAIFinishReasonToAnthropic(finishReason.String())
+			out, _ = sjson.Set(out, "stop_reason", mapOpenAIFinishReasonToAnthropic(finishReason.String()))
+			stopReasonSet = true
 		}
 
 		if message := choice.Get("message"); message.Exists() {
@@ -702,10 +566,9 @@ func ConvertOpenAIResponseToClaudeNonStream(_ context.Context, _ string, origina
 						if textBuilder.Len() == 0 {
 							return
 						}
-						contentBlocks = append(contentBlocks, map[string]interface{}{
-							"type": "text",
-							"text": textBuilder.String(),
-						})
+						block := `{"type":"text","text":""}`
+						block, _ = sjson.Set(block, "text", textBuilder.String())
+						out, _ = sjson.SetRaw(out, "content.-1", block)
 						textBuilder.Reset()
 					}
 
@@ -713,16 +576,14 @@ func ConvertOpenAIResponseToClaudeNonStream(_ context.Context, _ string, origina
 						if thinkingBuilder.Len() == 0 {
 							return
 						}
-						contentBlocks = append(contentBlocks, map[string]interface{}{
-							"type":     "thinking",
-							"thinking": thinkingBuilder.String(),
-						})
+						block := `{"type":"thinking","thinking":""}`
+						block, _ = sjson.Set(block, "thinking", thinkingBuilder.String())
+						out, _ = sjson.SetRaw(out, "content.-1", block)
 						thinkingBuilder.Reset()
 					}
 
 					for _, item := range contentResult.Array() {
-						typeStr := item.Get("type").String()
-						switch typeStr {
+						switch item.Get("type").String() {
 						case "text":
 							flushThinking()
 							textBuilder.WriteString(item.Get("text").String())
@@ -733,25 +594,23 @@ func ConvertOpenAIResponseToClaudeNonStream(_ context.Context, _ string, origina
 							if toolCalls.IsArray() {
 								toolCalls.ForEach(func(_, tc gjson.Result) bool {
 									hasToolCall = true
-									toolUse := map[string]interface{}{
-										"type": "tool_use",
-										"id":   tc.Get("id").String(),
-										"name": tc.Get("function.name").String(),
-									}
+									toolUse := `{"type":"tool_use","id":"","name":"","input":{}}`
+									toolUse, _ = sjson.Set(toolUse, "id", tc.Get("id").String())
+									toolUse, _ = sjson.Set(toolUse, "name", tc.Get("function.name").String())
 
 									argsStr := util.FixJSON(tc.Get("function.arguments").String())
-									if argsStr != "" {
-										var parsed interface{}
-										if err := json.Unmarshal([]byte(argsStr), &parsed); err == nil {
-											toolUse["input"] = parsed
+									if argsStr != "" && gjson.Valid(argsStr) {
+										argsJSON := gjson.Parse(argsStr)
+										if argsJSON.IsObject() {
+											toolUse, _ = sjson.SetRaw(toolUse, "input", argsJSON.Raw)
 										} else {
-											toolUse["input"] = map[string]interface{}{}
+											toolUse, _ = sjson.SetRaw(toolUse, "input", "{}")
 										}
 									} else {
-										toolUse["input"] = map[string]interface{}{}
+										toolUse, _ = sjson.SetRaw(toolUse, "input", "{}")
 									}
 
-									contentBlocks = append(contentBlocks, toolUse)
+									out, _ = sjson.SetRaw(out, "content.-1", toolUse)
 									return true
 								})
 							}
@@ -771,10 +630,9 @@ func ConvertOpenAIResponseToClaudeNonStream(_ context.Context, _ string, origina
 				} else if contentResult.Type == gjson.String {
 					textContent := contentResult.String()
 					if textContent != "" {
-						contentBlocks = append(contentBlocks, map[string]interface{}{
-							"type": "text",
-							"text": textContent,
-						})
+						block := `{"type":"text","text":""}`
+						block, _ = sjson.Set(block, "text", textContent)
+						out, _ = sjson.SetRaw(out, "content.-1", block)
 					}
 				}
 			}
@@ -784,81 +642,52 @@ func ConvertOpenAIResponseToClaudeNonStream(_ context.Context, _ string, origina
 					if reasoningText == "" {
 						continue
 					}
-					contentBlocks = append(contentBlocks, map[string]interface{}{
-						"type":     "thinking",
-						"thinking": reasoningText,
-					})
+					block := `{"type":"thinking","thinking":""}`
+					block, _ = sjson.Set(block, "thinking", reasoningText)
+					out, _ = sjson.SetRaw(out, "content.-1", block)
 				}
 			}
 
 			if toolCalls := message.Get("tool_calls"); toolCalls.Exists() && toolCalls.IsArray() {
 				toolCalls.ForEach(func(_, toolCall gjson.Result) bool {
 					hasToolCall = true
-					toolUseBlock := map[string]interface{}{
-						"type": "tool_use",
-						"id":   toolCall.Get("id").String(),
-						"name": toolCall.Get("function.name").String(),
-					}
+					toolUseBlock := `{"type":"tool_use","id":"","name":"","input":{}}`
+					toolUseBlock, _ = sjson.Set(toolUseBlock, "id", toolCall.Get("id").String())
+					toolUseBlock, _ = sjson.Set(toolUseBlock, "name", toolCall.Get("function.name").String())
 
-					argsStr := toolCall.Get("function.arguments").String()
-					argsStr = util.FixJSON(argsStr)
-					if argsStr != "" {
-						var args interface{}
-						if err := json.Unmarshal([]byte(argsStr), &args); err == nil {
-							toolUseBlock["input"] = args
+					argsStr := util.FixJSON(toolCall.Get("function.arguments").String())
+					if argsStr != "" && gjson.Valid(argsStr) {
+						argsJSON := gjson.Parse(argsStr)
+						if argsJSON.IsObject() {
+							toolUseBlock, _ = sjson.SetRaw(toolUseBlock, "input", argsJSON.Raw)
 						} else {
-							toolUseBlock["input"] = map[string]interface{}{}
+							toolUseBlock, _ = sjson.SetRaw(toolUseBlock, "input", "{}")
 						}
 					} else {
-						toolUseBlock["input"] = map[string]interface{}{}
+						toolUseBlock, _ = sjson.SetRaw(toolUseBlock, "input", "{}")
 					}
 
-					contentBlocks = append(contentBlocks, toolUseBlock)
+					out, _ = sjson.SetRaw(out, "content.-1", toolUseBlock)
 					return true
 				})
 			}
 		}
 	}
 
-	response["content"] = contentBlocks
-
 	if respUsage := root.Get("usage"); respUsage.Exists() {
-		usageJSON := `{}`
-		usageJSON, _ = sjson.Set(usageJSON, "input_tokens", respUsage.Get("prompt_tokens").Int())
-		usageJSON, _ = sjson.Set(usageJSON, "output_tokens", respUsage.Get("completion_tokens").Int())
-		parsedUsage := gjson.Parse(usageJSON).Value().(map[string]interface{})
-		response["usage"] = parsedUsage
-	} else {
-		response["usage"] = `{"input_tokens":0,"output_tokens":0}`
+		out, _ = sjson.Set(out, "usage.input_tokens", respUsage.Get("prompt_tokens").Int())
+		out, _ = sjson.Set(out, "usage.output_tokens", respUsage.Get("completion_tokens").Int())
 	}
 
-	if response["stop_reason"] == nil {
+	if !stopReasonSet {
 		if hasToolCall {
-			response["stop_reason"] = "tool_use"
+			out, _ = sjson.Set(out, "stop_reason", "tool_use")
 		} else {
-			response["stop_reason"] = "end_turn"
+			out, _ = sjson.Set(out, "stop_reason", "end_turn")
 		}
 	}
 
-	if !hasToolCall {
-		if toolBlocks := response["content"].([]interface{}); len(toolBlocks) > 0 {
-			for _, block := range toolBlocks {
-				if m, ok := block.(map[string]interface{}); ok && m["type"] == "tool_use" {
-					hasToolCall = true
-					break
-				}
-			}
-		}
-		if hasToolCall {
-			response["stop_reason"] = "tool_use"
-		}
-	}
-
-	responseJSON, err := json.Marshal(response)
-	if err != nil {
-		return ""
-	}
-	return string(responseJSON)
+	return out
 }
 
 func ClaudeTokenCount(ctx context.Context, count int64) string {

internal/translator/openai/gemini/openai_gemini_request.go

@@ -8,7 +8,6 @@ package gemini
 import (
 	"bytes"
 	"crypto/rand"
-	"encoding/json"
 	"fmt"
 	"math/big"
 	"strings"
@@ -94,7 +93,6 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 	out, _ = sjson.Set(out, "stream", stream)
 
 	// Process contents (Gemini messages) -> OpenAI messages
-	var openAIMessages []interface{}
 	var toolCallIDs []string // Track tool call IDs for matching with tool results
 
 	// System instruction -> OpenAI system message
@@ -105,22 +103,17 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 	}
 	if systemInstruction.Exists() {
 		parts := systemInstruction.Get("parts")
-		msg := map[string]interface{}{
-			"role":    "system",
-			"content": []interface{}{},
-		}
-
-		var aggregatedParts []interface{}
+		msg := `{"role":"system","content":[]}`
+		hasContent := false
 
 		if parts.Exists() && parts.IsArray() {
 			parts.ForEach(func(_, part gjson.Result) bool {
 				// Handle text parts
 				if text := part.Get("text"); text.Exists() {
-					formattedText := text.String()
-					aggregatedParts = append(aggregatedParts, map[string]interface{}{
-						"type": "text",
-						"text": formattedText,
-					})
+					contentPart := `{"type":"text","text":""}`
+					contentPart, _ = sjson.Set(contentPart, "text", text.String())
+					msg, _ = sjson.SetRaw(msg, "content.-1", contentPart)
+					hasContent = true
 				}
 
 				// Handle inline data (e.g., images)
@@ -132,20 +125,17 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 					data := inlineData.Get("data").String()
 					imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
 
-					aggregatedParts = append(aggregatedParts, map[string]interface{}{
-						"type": "image_url",
-						"image_url": map[string]interface{}{
-							"url": imageURL,
-						},
-					})
+					contentPart := `{"type":"image_url","image_url":{"url":""}}`
+					contentPart, _ = sjson.Set(contentPart, "image_url.url", imageURL)
+					msg, _ = sjson.SetRaw(msg, "content.-1", contentPart)
+					hasContent = true
 				}
 				return true
 			})
 		}
 
-		if len(aggregatedParts) > 0 {
-			msg["content"] = aggregatedParts
-			openAIMessages = append(openAIMessages, msg)
+		if hasContent {
+			out, _ = sjson.SetRaw(out, "messages.-1", msg)
 		}
 	}
 
@@ -159,16 +149,15 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 				role = "assistant"
 			}
 
-			// Create OpenAI message
-			msg := map[string]interface{}{
-				"role":    role,
-				"content": "",
-			}
+			msg := `{"role":"","content":""}`
+			msg, _ = sjson.Set(msg, "role", role)
 
 			var textBuilder strings.Builder
-			var aggregatedParts []interface{}
+			contentWrapper := `{"arr":[]}`
+			contentPartsCount := 0
 			onlyTextContent := true
-			var toolCalls []interface{}
+			toolCallsWrapper := `{"arr":[]}`
+			toolCallsCount := 0
 
 			if parts.Exists() && parts.IsArray() {
 				parts.ForEach(func(_, part gjson.Result) bool {
@@ -176,10 +165,10 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 					if text := part.Get("text"); text.Exists() {
 						formattedText := text.String()
 						textBuilder.WriteString(formattedText)
-						aggregatedParts = append(aggregatedParts, map[string]interface{}{
-							"type": "text",
-							"text": formattedText,
-						})
+						contentPart := `{"type":"text","text":""}`
+						contentPart, _ = sjson.Set(contentPart, "text", formattedText)
+						contentWrapper, _ = sjson.SetRaw(contentWrapper, "arr.-1", contentPart)
+						contentPartsCount++
 					}
 
 					// Handle inline data (e.g., images)
@@ -193,12 +182,10 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 						data := inlineData.Get("data").String()
 						imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
 
-						aggregatedParts = append(aggregatedParts, map[string]interface{}{
-							"type": "image_url",
-							"image_url": map[string]interface{}{
-								"url": imageURL,
-							},
-						})
+						contentPart := `{"type":"image_url","image_url":{"url":""}}`
+						contentPart, _ = sjson.Set(contentPart, "image_url.url", imageURL)
+						contentWrapper, _ = sjson.SetRaw(contentWrapper, "arr.-1", contentPart)
+						contentPartsCount++
 					}
 
 					// Handle function calls (Gemini) -> tool calls (OpenAI)
@@ -206,44 +193,32 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 						toolCallID := genToolCallID()
 						toolCallIDs = append(toolCallIDs, toolCallID)
 
-						toolCall := map[string]interface{}{
-							"id":   toolCallID,
-							"type": "function",
-							"function": map[string]interface{}{
-								"name": functionCall.Get("name").String(),
-							},
-						}
+						toolCall := `{"id":"","type":"function","function":{"name":"","arguments":""}}`
+						toolCall, _ = sjson.Set(toolCall, "id", toolCallID)
+						toolCall, _ = sjson.Set(toolCall, "function.name", functionCall.Get("name").String())
 
 						// Convert args to arguments JSON string
 						if args := functionCall.Get("args"); args.Exists() {
-							argsJSON, _ := json.Marshal(args.Value())
-							toolCall["function"].(map[string]interface{})["arguments"] = string(argsJSON)
+							toolCall, _ = sjson.Set(toolCall, "function.arguments", args.Raw)
 						} else {
-							toolCall["function"].(map[string]interface{})["arguments"] = "{}"
+							toolCall, _ = sjson.Set(toolCall, "function.arguments", "{}")
 						}
 
-						toolCalls = append(toolCalls, toolCall)
+						toolCallsWrapper, _ = sjson.SetRaw(toolCallsWrapper, "arr.-1", toolCall)
+						toolCallsCount++
 					}
 
 					// Handle function responses (Gemini) -> tool role messages (OpenAI)
 					if functionResponse := part.Get("functionResponse"); functionResponse.Exists() {
 						// Create tool message for function response
-						toolMsg := map[string]interface{}{
-							"role":         "tool",
-							"tool_call_id": "", // Will be set based on context
-							"content":      "",
-						}
+						toolMsg := `{"role":"tool","tool_call_id":"","content":""}`
 
 						// Convert response.content to JSON string
 						if response := functionResponse.Get("response"); response.Exists() {
-							if content = response.Get("content"); content.Exists() {
-								// Use the content field from the response
-								contentJSON, _ := json.Marshal(content.Value())
-								toolMsg["content"] = string(contentJSON)
+							if contentField := response.Get("content"); contentField.Exists() {
+								toolMsg, _ = sjson.Set(toolMsg, "content", contentField.Raw)
 							} else {
-								// Fallback to entire response
-								responseJSON, _ := json.Marshal(response.Value())
-								toolMsg["content"] = string(responseJSON)
+								toolMsg, _ = sjson.Set(toolMsg, "content", response.Raw)
 							}
 						}
 
@@ -252,13 +227,13 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 						if len(toolCallIDs) > 0 {
 							// Use the last tool call ID (simple matching by function name)
 							// In a real implementation, you might want more sophisticated matching
-							toolMsg["tool_call_id"] = toolCallIDs[len(toolCallIDs)-1]
+							toolMsg, _ = sjson.Set(toolMsg, "tool_call_id", toolCallIDs[len(toolCallIDs)-1])
 						} else {
 							// Generate a tool call ID if none available
-							toolMsg["tool_call_id"] = genToolCallID()
+							toolMsg, _ = sjson.Set(toolMsg, "tool_call_id", genToolCallID())
 						}
 
-						openAIMessages = append(openAIMessages, toolMsg)
+						out, _ = sjson.SetRaw(out, "messages.-1", toolMsg)
 					}
 
 					return true
@@ -266,170 +241,46 @@ func ConvertGeminiRequestToOpenAI(modelName string, inputRawJSON []byte, stream
 			}
 
 			// Set content
-			if len(aggregatedParts) > 0 {
+			if contentPartsCount > 0 {
 				if onlyTextContent {
-					msg["content"] = textBuilder.String()
+					msg, _ = sjson.Set(msg, "content", textBuilder.String())
 				} else {
-					msg["content"] = aggregatedParts
+					msg, _ = sjson.SetRaw(msg, "content", gjson.Get(contentWrapper, "arr").Raw)
 				}
 			}
 
 			// Set tool calls if any
-			if len(toolCalls) > 0 {
-				msg["tool_calls"] = toolCalls
+			if toolCallsCount > 0 {
+				msg, _ = sjson.SetRaw(msg, "tool_calls", gjson.Get(toolCallsWrapper, "arr").Raw)
 			}
 
-			openAIMessages = append(openAIMessages, msg)
-
-			// switch role {
-			// case "user", "model":
-			// 	// Convert role: model -> assistant
-			// 	if role == "model" {
-			// 		role = "assistant"
-			// 	}
-			//
-			// 	// Create OpenAI message
-			// 	msg := map[string]interface{}{
-			// 		"role":    role,
-			// 		"content": "",
-			// 	}
-			//
-			// 	var contentParts []string
-			// 	var toolCalls []interface{}
-			//
-			// 	if parts.Exists() && parts.IsArray() {
-			// 		parts.ForEach(func(_, part gjson.Result) bool {
-			// 			// Handle text parts
-			// 			if text := part.Get("text"); text.Exists() {
-			// 				contentParts = append(contentParts, text.String())
-			// 			}
-			//
-			// 			// Handle function calls (Gemini) -> tool calls (OpenAI)
-			// 			if functionCall := part.Get("functionCall"); functionCall.Exists() {
-			// 				toolCallID := genToolCallID()
-			// 				toolCallIDs = append(toolCallIDs, toolCallID)
-			//
-			// 				toolCall := map[string]interface{}{
-			// 					"id":   toolCallID,
-			// 					"type": "function",
-			// 					"function": map[string]interface{}{
-			// 						"name": functionCall.Get("name").String(),
-			// 					},
-			// 				}
-			//
-			// 				// Convert args to arguments JSON string
-			// 				if args := functionCall.Get("args"); args.Exists() {
-			// 					argsJSON, _ := json.Marshal(args.Value())
-			// 					toolCall["function"].(map[string]interface{})["arguments"] = string(argsJSON)
-			// 				} else {
-			// 					toolCall["function"].(map[string]interface{})["arguments"] = "{}"
-			// 				}
-			//
-			// 				toolCalls = append(toolCalls, toolCall)
-			// 			}
-			//
-			// 			return true
-			// 		})
-			// 	}
-			//
-			// 	// Set content
-			// 	if len(contentParts) > 0 {
-			// 		msg["content"] = strings.Join(contentParts, "")
-			// 	}
-			//
-			// 	// Set tool calls if any
-			// 	if len(toolCalls) > 0 {
-			// 		msg["tool_calls"] = toolCalls
-			// 	}
-			//
-			// 	openAIMessages = append(openAIMessages, msg)
-			//
-			// case "function":
-			// 	// Handle Gemini function role -> OpenAI tool role
-			// 	if parts.Exists() && parts.IsArray() {
-			// 		parts.ForEach(func(_, part gjson.Result) bool {
-			// 			// Handle function responses (Gemini) -> tool role messages (OpenAI)
-			// 			if functionResponse := part.Get("functionResponse"); functionResponse.Exists() {
-			// 				// Create tool message for function response
-			// 				toolMsg := map[string]interface{}{
-			// 					"role":         "tool",
-			// 					"tool_call_id": "", // Will be set based on context
-			// 					"content":      "",
-			// 				}
-			//
-			// 				// Convert response.content to JSON string
-			// 				if response := functionResponse.Get("response"); response.Exists() {
-			// 					if content = response.Get("content"); content.Exists() {
-			// 						// Use the content field from the response
-			// 						contentJSON, _ := json.Marshal(content.Value())
-			// 						toolMsg["content"] = string(contentJSON)
-			// 					} else {
-			// 						// Fallback to entire response
-			// 						responseJSON, _ := json.Marshal(response.Value())
-			// 						toolMsg["content"] = string(responseJSON)
-			// 					}
-			// 				}
-			//
-			// 				// Try to match with previous tool call ID
-			// 				_ = functionResponse.Get("name").String() // functionName not used for now
-			// 				if len(toolCallIDs) > 0 {
-			// 					// Use the last tool call ID (simple matching by function name)
-			// 					// In a real implementation, you might want more sophisticated matching
-			// 					toolMsg["tool_call_id"] = toolCallIDs[len(toolCallIDs)-1]
-			// 				} else {
-			// 					// Generate a tool call ID if none available
-			// 					toolMsg["tool_call_id"] = genToolCallID()
-			// 				}
-			//
-			// 				openAIMessages = append(openAIMessages, toolMsg)
-			// 			}
-			//
-			// 			return true
-			// 		})
-			// 	}
-			// }
+			out, _ = sjson.SetRaw(out, "messages.-1", msg)
 			return true
 		})
 	}
 
-	// Set messages
-	if len(openAIMessages) > 0 {
-		messagesJSON, _ := json.Marshal(openAIMessages)
-		out, _ = sjson.SetRaw(out, "messages", string(messagesJSON))
-	}
-
 	// Tools mapping: Gemini tools -> OpenAI tools
 	if tools := root.Get("tools"); tools.Exists() && tools.IsArray() {
-		var openAITools []interface{}
 		tools.ForEach(func(_, tool gjson.Result) bool {
 			if functionDeclarations := tool.Get("functionDeclarations"); functionDeclarations.Exists() && functionDeclarations.IsArray() {
 				functionDeclarations.ForEach(func(_, funcDecl gjson.Result) bool {
-					openAITool := map[string]interface{}{
-						"type": "function",
-						"function": map[string]interface{}{
-							"name":        funcDecl.Get("name").String(),
-							"description": funcDecl.Get("description").String(),
-						},
-					}
+					openAITool := `{"type":"function","function":{"name":"","description":""}}`
+					openAITool, _ = sjson.Set(openAITool, "function.name", funcDecl.Get("name").String())
+					openAITool, _ = sjson.Set(openAITool, "function.description", funcDecl.Get("description").String())
 
 					// Convert parameters schema
 					if parameters := funcDecl.Get("parameters"); parameters.Exists() {
-						openAITool["function"].(map[string]interface{})["parameters"] = parameters.Value()
-					} else if parameters = funcDecl.Get("parametersJsonSchema"); parameters.Exists() {
-						openAITool["function"].(map[string]interface{})["parameters"] = parameters.Value()
+						openAITool, _ = sjson.SetRaw(openAITool, "function.parameters", parameters.Raw)
+					} else if parameters := funcDecl.Get("parametersJsonSchema"); parameters.Exists() {
+						openAITool, _ = sjson.SetRaw(openAITool, "function.parameters", parameters.Raw)
 					}
 
-					openAITools = append(openAITools, openAITool)
+					out, _ = sjson.SetRaw(out, "tools.-1", openAITool)
 					return true
 				})
 			}
 			return true
 		})
-
-		if len(openAITools) > 0 {
-			toolsJSON, _ := json.Marshal(openAITools)
-			out, _ = sjson.SetRaw(out, "tools", string(toolsJSON))
-		}
 	}
 
 	// Tool choice mapping (Gemini doesn't have direct equivalent, but we can handle it)

internal/translator/openai/gemini/openai_gemini_response.go

@@ -8,7 +8,6 @@ package gemini
 import (
 	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"strconv"
 	"strings"
@@ -84,15 +83,12 @@ func ConvertOpenAIResponseToGemini(_ context.Context, _ string, originalRequestR
 					template, _ = sjson.Set(template, "model", model.String())
 				}
 
-				usageObj := map[string]interface{}{
-					"promptTokenCount":     usage.Get("prompt_tokens").Int(),
-					"candidatesTokenCount": usage.Get("completion_tokens").Int(),
-					"totalTokenCount":      usage.Get("total_tokens").Int(),
-				}
+				template, _ = sjson.Set(template, "usageMetadata.promptTokenCount", usage.Get("prompt_tokens").Int())
+				template, _ = sjson.Set(template, "usageMetadata.candidatesTokenCount", usage.Get("completion_tokens").Int())
+				template, _ = sjson.Set(template, "usageMetadata.totalTokenCount", usage.Get("total_tokens").Int())
 				if reasoningTokens := reasoningTokensFromUsage(usage); reasoningTokens > 0 {
-					usageObj["thoughtsTokenCount"] = reasoningTokens
+					template, _ = sjson.Set(template, "usageMetadata.thoughtsTokenCount", reasoningTokens)
 				}
-				template, _ = sjson.Set(template, "usageMetadata", usageObj)
 				return []string{template}
 			}
 			return []string{}
@@ -133,13 +129,8 @@ func ConvertOpenAIResponseToGemini(_ context.Context, _ string, originalRequestR
 						continue
 					}
 					reasoningTemplate := baseTemplate
-					parts := []interface{}{
-						map[string]interface{}{
-							"thought": true,
-							"text":    reasoningText,
-						},
-					}
-					reasoningTemplate, _ = sjson.Set(reasoningTemplate, "candidates.0.content.parts", parts)
+					reasoningTemplate, _ = sjson.Set(reasoningTemplate, "candidates.0.content.parts.0.thought", true)
+					reasoningTemplate, _ = sjson.Set(reasoningTemplate, "candidates.0.content.parts.0.text", reasoningText)
 					chunkOutputs = append(chunkOutputs, reasoningTemplate)
 				}
 			}
@@ -150,13 +141,8 @@ func ConvertOpenAIResponseToGemini(_ context.Context, _ string, originalRequestR
 				(*param).(*ConvertOpenAIResponseToGeminiParams).ContentAccumulator.WriteString(contentText)
 
 				// Create text part for this delta
-				parts := []interface{}{
-					map[string]interface{}{
-						"text": contentText,
-					},
-				}
 				contentTemplate := baseTemplate
-				contentTemplate, _ = sjson.Set(contentTemplate, "candidates.0.content.parts", parts)
+				contentTemplate, _ = sjson.Set(contentTemplate, "candidates.0.content.parts.0.text", contentText)
 				chunkOutputs = append(chunkOutputs, contentTemplate)
 			}
 
@@ -225,24 +211,13 @@ func ConvertOpenAIResponseToGemini(_ context.Context, _ string, originalRequestR
 
 				// If we have accumulated tool calls, output them now
 				if len((*param).(*ConvertOpenAIResponseToGeminiParams).ToolCallsAccumulator) > 0 {
-					var parts []interface{}
+					partIndex := 0
 					for _, accumulator := range (*param).(*ConvertOpenAIResponseToGeminiParams).ToolCallsAccumulator {
-						argsStr := accumulator.Arguments.String()
-						var argsMap map[string]interface{}
-
-						argsMap = parseArgsToMap(argsStr)
-
-						functionCallPart := map[string]interface{}{
-							"functionCall": map[string]interface{}{
-								"name": accumulator.Name,
-								"args": argsMap,
-							},
-						}
-						parts = append(parts, functionCallPart)
-					}
-
-					if len(parts) > 0 {
-						template, _ = sjson.Set(template, "candidates.0.content.parts", parts)
+						namePath := fmt.Sprintf("candidates.0.content.parts.%d.functionCall.name", partIndex)
+						argsPath := fmt.Sprintf("candidates.0.content.parts.%d.functionCall.args", partIndex)
+						template, _ = sjson.Set(template, namePath, accumulator.Name)
+						template, _ = sjson.SetRaw(template, argsPath, parseArgsToObjectRaw(accumulator.Arguments.String()))
+						partIndex++
 					}
 
 					// Clear accumulators
@@ -255,15 +230,12 @@ func ConvertOpenAIResponseToGemini(_ context.Context, _ string, originalRequestR
 
 			// Handle usage information
 			if usage := root.Get("usage"); usage.Exists() {
-				usageObj := map[string]interface{}{
-					"promptTokenCount":     usage.Get("prompt_tokens").Int(),
-					"candidatesTokenCount": usage.Get("completion_tokens").Int(),
-					"totalTokenCount":      usage.Get("total_tokens").Int(),
-				}
+				template, _ = sjson.Set(template, "usageMetadata.promptTokenCount", usage.Get("prompt_tokens").Int())
+				template, _ = sjson.Set(template, "usageMetadata.candidatesTokenCount", usage.Get("completion_tokens").Int())
+				template, _ = sjson.Set(template, "usageMetadata.totalTokenCount", usage.Get("total_tokens").Int())
 				if reasoningTokens := reasoningTokensFromUsage(usage); reasoningTokens > 0 {
-					usageObj["thoughtsTokenCount"] = reasoningTokens
+					template, _ = sjson.Set(template, "usageMetadata.thoughtsTokenCount", reasoningTokens)
 				}
-				template, _ = sjson.Set(template, "usageMetadata", usageObj)
 				results = append(results, template)
 				return true
 			}
@@ -291,46 +263,54 @@ func mapOpenAIFinishReasonToGemini(openAIReason string) string {
 	}
 }
 
-// parseArgsToMap safely parses a JSON string of function arguments into a map.
-// It returns an empty map if the input is empty or cannot be parsed as a JSON object.
-func parseArgsToMap(argsStr string) map[string]interface{} {
+// parseArgsToObjectRaw safely parses a JSON string of function arguments into an object JSON string.
+// It returns "{}" if the input is empty or cannot be parsed as a JSON object.
+func parseArgsToObjectRaw(argsStr string) string {
 	trimmed := strings.TrimSpace(argsStr)
 	if trimmed == "" || trimmed == "{}" {
-		return map[string]interface{}{}
+		return "{}"
 	}
 
 	// First try strict JSON
-	var out map[string]interface{}
-	if errUnmarshal := json.Unmarshal([]byte(trimmed), &out); errUnmarshal == nil {
-		return out
+	if gjson.Valid(trimmed) {
+		strict := gjson.Parse(trimmed)
+		if strict.IsObject() {
+			return strict.Raw
+		}
 	}
 
 	// Tolerant parse: handle streams where values are barewords (e.g., 北京, celsius)
-	tolerant := tolerantParseJSONMap(trimmed)
-	if len(tolerant) > 0 {
+	tolerant := tolerantParseJSONObjectRaw(trimmed)
+	if tolerant != "{}" {
 		return tolerant
 	}
 
 	// Fallback: return empty object when parsing fails
-	return map[string]interface{}{}
+	return "{}"
 }
 
-// tolerantParseJSONMap attempts to parse a JSON-like object string into a map, tolerating
+func escapeSjsonPathKey(key string) string {
+	key = strings.ReplaceAll(key, `\`, `\\`)
+	key = strings.ReplaceAll(key, `.`, `\.`)
+	return key
+}
+
+// tolerantParseJSONObjectRaw attempts to parse a JSON-like object string into a JSON object string, tolerating
 // bareword values (unquoted strings) commonly seen during streamed tool calls.
 // Example input: {"location": 北京, "unit": celsius}
-func tolerantParseJSONMap(s string) map[string]interface{} {
+func tolerantParseJSONObjectRaw(s string) string {
 	// Ensure we operate within the outermost braces if present
 	start := strings.Index(s, "{")
 	end := strings.LastIndex(s, "}")
 	if start == -1 || end == -1 || start >= end {
-		return map[string]interface{}{}
+		return "{}"
 	}
 	content := s[start+1 : end]
 
 	runes := []rune(content)
 	n := len(runes)
 	i := 0
-	result := make(map[string]interface{})
+	result := "{}"
 
 	for i < n {
 		// Skip whitespace and commas
@@ -356,6 +336,7 @@ func tolerantParseJSONMap(s string) map[string]interface{} {
 			break
 		}
 		keyName := jsonStringTokenToRawString(keyToken)
+		sjsonKey := escapeSjsonPathKey(keyName)
 		i = nextIdx
 
 		// Skip whitespace
@@ -375,17 +356,16 @@ func tolerantParseJSONMap(s string) map[string]interface{} {
 		}
 
 		// Parse value (string, number, object/array, bareword)
-		var value interface{}
 		switch runes[i] {
 		case '"':
 			// JSON string
 			valToken, ni := parseJSONStringRunes(runes, i)
 			if ni == -1 {
 				// Malformed; treat as empty string
-				value = ""
+				result, _ = sjson.Set(result, sjsonKey, "")
 				i = n
 			} else {
-				value = jsonStringTokenToRawString(valToken)
+				result, _ = sjson.Set(result, sjsonKey, jsonStringTokenToRawString(valToken))
 				i = ni
 			}
 		case '{', '[':
@@ -394,11 +374,10 @@ func tolerantParseJSONMap(s string) map[string]interface{} {
 			if ni == -1 {
 				i = n
 			} else {
-				var anyVal interface{}
-				if errUnmarshal := json.Unmarshal([]byte(seg), &anyVal); errUnmarshal == nil {
-					value = anyVal
+				if gjson.Valid(seg) {
+					result, _ = sjson.SetRaw(result, sjsonKey, seg)
 				} else {
-					value = seg
+					result, _ = sjson.Set(result, sjsonKey, seg)
 				}
 				i = ni
 			}
@@ -411,21 +390,19 @@ func tolerantParseJSONMap(s string) map[string]interface{} {
 			token := strings.TrimSpace(string(runes[i:j]))
 			// Interpret common JSON atoms and numbers; otherwise treat as string
 			if token == "true" {
-				value = true
+				result, _ = sjson.Set(result, sjsonKey, true)
 			} else if token == "false" {
-				value = false
+				result, _ = sjson.Set(result, sjsonKey, false)
 			} else if token == "null" {
-				value = nil
+				result, _ = sjson.Set(result, sjsonKey, nil)
 			} else if numVal, ok := tryParseNumber(token); ok {
-				value = numVal
+				result, _ = sjson.Set(result, sjsonKey, numVal)
 			} else {
-				value = token
+				result, _ = sjson.Set(result, sjsonKey, token)
 			}
 			i = j
 		}
 
-		result[keyName] = value
-
 		// Skip trailing whitespace and optional comma before next pair
 		for i < n && (runes[i] == ' ' || runes[i] == '\n' || runes[i] == '\r' || runes[i] == '\t') {
 			i++
@@ -463,9 +440,9 @@ func parseJSONStringRunes(runes []rune, start int) (string, int) {
 
 // jsonStringTokenToRawString converts a JSON string token (including quotes) to a raw Go string value.
 func jsonStringTokenToRawString(token string) string {
-	var s string
-	if errUnmarshal := json.Unmarshal([]byte(token), &s); errUnmarshal == nil {
-		return s
+	r := gjson.Parse(token)
+	if r.Type == gjson.String {
+		return r.String()
 	}
 	// Fallback: strip surrounding quotes if present
 	if len(token) >= 2 && token[0] == '"' && token[len(token)-1] == '"' {
@@ -579,7 +556,7 @@ func ConvertOpenAIResponseToGeminiNonStream(_ context.Context, _ string, origina
 				}
 			}
 
-			var parts []interface{}
+			partIndex := 0
 
 			// Handle reasoning content before visible text
 			if reasoning := message.Get("reasoning_content"); reasoning.Exists() {
@@ -587,18 +564,16 @@ func ConvertOpenAIResponseToGeminiNonStream(_ context.Context, _ string, origina
 					if reasoningText == "" {
 						continue
 					}
-					parts = append(parts, map[string]interface{}{
-						"thought": true,
-						"text":    reasoningText,
-					})
+					out, _ = sjson.Set(out, fmt.Sprintf("candidates.0.content.parts.%d.thought", partIndex), true)
+					out, _ = sjson.Set(out, fmt.Sprintf("candidates.0.content.parts.%d.text", partIndex), reasoningText)
+					partIndex++
 				}
 			}
 
 			// Handle content first
 			if content := message.Get("content"); content.Exists() && content.String() != "" {
-				parts = append(parts, map[string]interface{}{
-					"text": content.String(),
-				})
+				out, _ = sjson.Set(out, fmt.Sprintf("candidates.0.content.parts.%d.text", partIndex), content.String())
+				partIndex++
 			}
 
 			// Handle tool calls
@@ -609,27 +584,16 @@ func ConvertOpenAIResponseToGeminiNonStream(_ context.Context, _ string, origina
 						functionName := function.Get("name").String()
 						functionArgs := function.Get("arguments").String()
 
-						// Parse arguments
-						var argsMap map[string]interface{}
-						argsMap = parseArgsToMap(functionArgs)
-
-						functionCallPart := map[string]interface{}{
-							"functionCall": map[string]interface{}{
-								"name": functionName,
-								"args": argsMap,
-							},
-						}
-						parts = append(parts, functionCallPart)
+						namePath := fmt.Sprintf("candidates.0.content.parts.%d.functionCall.name", partIndex)
+						argsPath := fmt.Sprintf("candidates.0.content.parts.%d.functionCall.args", partIndex)
+						out, _ = sjson.Set(out, namePath, functionName)
+						out, _ = sjson.SetRaw(out, argsPath, parseArgsToObjectRaw(functionArgs))
+						partIndex++
 					}
 					return true
 				})
 			}
 
-			// Set parts
-			if len(parts) > 0 {
-				out, _ = sjson.Set(out, "candidates.0.content.parts", parts)
-			}
-
 			// Handle finish reason
 			if finishReason := choice.Get("finish_reason"); finishReason.Exists() {
 				geminiFinishReason := mapOpenAIFinishReasonToGemini(finishReason.String())
@@ -645,15 +609,12 @@ func ConvertOpenAIResponseToGeminiNonStream(_ context.Context, _ string, origina
 
 	// Handle usage information
 	if usage := root.Get("usage"); usage.Exists() {
-		usageObj := map[string]interface{}{
-			"promptTokenCount":     usage.Get("prompt_tokens").Int(),
-			"candidatesTokenCount": usage.Get("completion_tokens").Int(),
-			"totalTokenCount":      usage.Get("total_tokens").Int(),
-		}
+		out, _ = sjson.Set(out, "usageMetadata.promptTokenCount", usage.Get("prompt_tokens").Int())
+		out, _ = sjson.Set(out, "usageMetadata.candidatesTokenCount", usage.Get("completion_tokens").Int())
+		out, _ = sjson.Set(out, "usageMetadata.totalTokenCount", usage.Get("total_tokens").Int())
 		if reasoningTokens := reasoningTokensFromUsage(usage); reasoningTokens > 0 {
-			usageObj["thoughtsTokenCount"] = reasoningTokens
+			out, _ = sjson.Set(out, "usageMetadata.thoughtsTokenCount", reasoningTokens)
 		}
-		out, _ = sjson.Set(out, "usageMetadata", usageObj)
 	}
 
 	return out

internal/translator/openai/openai/responses/openai_openai-responses_response.go

@@ -143,7 +143,7 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 		st.ReasoningTokens = 0
 		st.UsageSeen = false
 		// response.created
-		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null}}`
+		created := `{"type":"response.created","sequence_number":0,"response":{"id":"","object":"response","created_at":0,"status":"in_progress","background":false,"error":null,"output":[]}}`
 		created, _ = sjson.Set(created, "sequence_number", nextSeq())
 		created, _ = sjson.Set(created, "response.id", st.ResponseID)
 		created, _ = sjson.Set(created, "response.created_at", st.Created)
@@ -216,11 +216,11 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 					}
 					// Append incremental text to reasoning buffer
 					st.ReasoningBuf.WriteString(rc.String())
-					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"text":""}`
+					msg := `{"type":"response.reasoning_summary_text.delta","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"delta":""}`
 					msg, _ = sjson.Set(msg, "sequence_number", nextSeq())
 					msg, _ = sjson.Set(msg, "item_id", st.ReasoningID)
 					msg, _ = sjson.Set(msg, "output_index", st.ReasoningIndex)
-					msg, _ = sjson.Set(msg, "text", rc.String())
+					msg, _ = sjson.Set(msg, "delta", rc.String())
 					out = append(out, emitRespEvent("response.reasoning_summary_text.delta", msg))
 				}
 
@@ -484,16 +484,12 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 					}
 				}
 				// Build response.output using aggregated buffers
-				var outputs []interface{}
+				outputsWrapper := `{"arr":[]}`
 				if st.ReasoningBuf.Len() > 0 {
-					outputs = append(outputs, map[string]interface{}{
-						"id":   st.ReasoningID,
-						"type": "reasoning",
-						"summary": []interface{}{map[string]interface{}{
-							"type": "summary_text",
-							"text": st.ReasoningBuf.String(),
-						}},
-					})
+					item := `{"id":"","type":"reasoning","summary":[{"type":"summary_text","text":""}]}`
+					item, _ = sjson.Set(item, "id", st.ReasoningID)
+					item, _ = sjson.Set(item, "summary.0.text", st.ReasoningBuf.String())
+					outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 				}
 				// Append message items in ascending index order
 				if len(st.MsgItemAdded) > 0 {
@@ -513,18 +509,10 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 						if b := st.MsgTextBuf[i]; b != nil {
 							txt = b.String()
 						}
-						outputs = append(outputs, map[string]interface{}{
-							"id":     fmt.Sprintf("msg_%s_%d", st.ResponseID, i),
-							"type":   "message",
-							"status": "completed",
-							"content": []interface{}{map[string]interface{}{
-								"type":        "output_text",
-								"annotations": []interface{}{},
-								"logprobs":    []interface{}{},
-								"text":        txt,
-							}},
-							"role": "assistant",
-						})
+						item := `{"id":"","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":""}],"role":"assistant"}`
+						item, _ = sjson.Set(item, "id", fmt.Sprintf("msg_%s_%d", st.ResponseID, i))
+						item, _ = sjson.Set(item, "content.0.text", txt)
+						outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 					}
 				}
 				if len(st.FuncArgsBuf) > 0 {
@@ -547,18 +535,16 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponses(ctx context.Context,
 						}
 						callID := st.FuncCallIDs[i]
 						name := st.FuncNames[i]
-						outputs = append(outputs, map[string]interface{}{
-							"id":        fmt.Sprintf("fc_%s", callID),
-							"type":      "function_call",
-							"status":    "completed",
-							"arguments": args,
-							"call_id":   callID,
-							"name":      name,
-						})
+						item := `{"id":"","type":"function_call","status":"completed","arguments":"","call_id":"","name":""}`
+						item, _ = sjson.Set(item, "id", fmt.Sprintf("fc_%s", callID))
+						item, _ = sjson.Set(item, "arguments", args)
+						item, _ = sjson.Set(item, "call_id", callID)
+						item, _ = sjson.Set(item, "name", name)
+						outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 					}
 				}
-				if len(outputs) > 0 {
-					completed, _ = sjson.Set(completed, "response.output", outputs)
+				if gjson.Get(outputsWrapper, "arr.#").Int() > 0 {
+					completed, _ = sjson.SetRaw(completed, "response.output", gjson.Get(outputsWrapper, "arr").Raw)
 				}
 				if st.UsageSeen {
 					completed, _ = sjson.Set(completed, "response.usage.input_tokens", st.PromptTokens)
@@ -681,7 +667,7 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream(_ context.Co
 	}
 
 	// Build output list from choices[...]
-	var outputs []interface{}
+	outputsWrapper := `{"arr":[]}`
 	// Detect and capture reasoning content if present
 	rcText := gjson.GetBytes(rawJSON, "choices.0.message.reasoning_content").String()
 	includeReasoning := rcText != ""
@@ -693,21 +679,14 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream(_ context.Co
 		if strings.HasPrefix(rid, "resp_") {
 			rid = strings.TrimPrefix(rid, "resp_")
 		}
-		reasoningItem := map[string]interface{}{
-			"id":                fmt.Sprintf("rs_%s", rid),
-			"type":              "reasoning",
-			"encrypted_content": "",
-		}
 		// Prefer summary_text from reasoning_content; encrypted_content is optional
-		var summaries []interface{}
+		reasoningItem := `{"id":"","type":"reasoning","encrypted_content":"","summary":[]}`
+		reasoningItem, _ = sjson.Set(reasoningItem, "id", fmt.Sprintf("rs_%s", rid))
 		if rcText != "" {
-			summaries = append(summaries, map[string]interface{}{
-				"type": "summary_text",
-				"text": rcText,
-			})
+			reasoningItem, _ = sjson.Set(reasoningItem, "summary.0.type", "summary_text")
+			reasoningItem, _ = sjson.Set(reasoningItem, "summary.0.text", rcText)
 		}
-		reasoningItem["summary"] = summaries
-		outputs = append(outputs, reasoningItem)
+		outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", reasoningItem)
 	}
 
 	if choices := root.Get("choices"); choices.Exists() && choices.IsArray() {
@@ -716,18 +695,10 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream(_ context.Co
 			if msg.Exists() {
 				// Text message part
 				if c := msg.Get("content"); c.Exists() && c.String() != "" {
-					outputs = append(outputs, map[string]interface{}{
-						"id":     fmt.Sprintf("msg_%s_%d", id, int(choice.Get("index").Int())),
-						"type":   "message",
-						"status": "completed",
-						"content": []interface{}{map[string]interface{}{
-							"type":        "output_text",
-							"annotations": []interface{}{},
-							"logprobs":    []interface{}{},
-							"text":        c.String(),
-						}},
-						"role": "assistant",
-					})
+					item := `{"id":"","type":"message","status":"completed","content":[{"type":"output_text","annotations":[],"logprobs":[],"text":""}],"role":"assistant"}`
+					item, _ = sjson.Set(item, "id", fmt.Sprintf("msg_%s_%d", id, int(choice.Get("index").Int())))
+					item, _ = sjson.Set(item, "content.0.text", c.String())
+					outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 				}
 
 				// Function/tool calls
@@ -736,14 +707,12 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream(_ context.Co
 						callID := tc.Get("id").String()
 						name := tc.Get("function.name").String()
 						args := tc.Get("function.arguments").String()
-						outputs = append(outputs, map[string]interface{}{
-							"id":        fmt.Sprintf("fc_%s", callID),
-							"type":      "function_call",
-							"status":    "completed",
-							"arguments": args,
-							"call_id":   callID,
-							"name":      name,
-						})
+						item := `{"id":"","type":"function_call","status":"completed","arguments":"","call_id":"","name":""}`
+						item, _ = sjson.Set(item, "id", fmt.Sprintf("fc_%s", callID))
+						item, _ = sjson.Set(item, "arguments", args)
+						item, _ = sjson.Set(item, "call_id", callID)
+						item, _ = sjson.Set(item, "name", name)
+						outputsWrapper, _ = sjson.SetRaw(outputsWrapper, "arr.-1", item)
 						return true
 					})
 				}
@@ -751,8 +720,8 @@ func ConvertOpenAIChatCompletionsResponseToOpenAIResponsesNonStream(_ context.Co
 			return true
 		})
 	}
-	if len(outputs) > 0 {
-		resp, _ = sjson.Set(resp, "output", outputs)
+	if gjson.Get(outputsWrapper, "arr.#").Int() > 0 {
+		resp, _ = sjson.SetRaw(resp, "output", gjson.Get(outputsWrapper, "arr").Raw)
 	}
 
 	// usage mapping

internal/usage/logger_plugin.go

@@ -6,6 +6,7 @@ package usage
 import (
 	"context"
 	"fmt"
+	"strings"
 	"sync"
 	"sync/atomic"
 	"time"
@@ -90,7 +91,7 @@ type modelStats struct {
 type RequestDetail struct {
 	Timestamp time.Time  `json:"timestamp"`
 	Source    string     `json:"source"`
-	AuthIndex uint64     `json:"auth_index"`
+	AuthIndex string     `json:"auth_index"`
 	Tokens    TokenStats `json:"tokens"`
 	Failed    bool       `json:"failed"`
 }
@@ -281,6 +282,118 @@ func (s *RequestStatistics) Snapshot() StatisticsSnapshot {
 	return result
 }
 
+type MergeResult struct {
+	Added   int64 `json:"added"`
+	Skipped int64 `json:"skipped"`
+}
+
+// MergeSnapshot merges an exported statistics snapshot into the current store.
+// Existing data is preserved and duplicate request details are skipped.
+func (s *RequestStatistics) MergeSnapshot(snapshot StatisticsSnapshot) MergeResult {
+	result := MergeResult{}
+	if s == nil {
+		return result
+	}
+
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	seen := make(map[string]struct{})
+	for apiName, stats := range s.apis {
+		if stats == nil {
+			continue
+		}
+		for modelName, modelStatsValue := range stats.Models {
+			if modelStatsValue == nil {
+				continue
+			}
+			for _, detail := range modelStatsValue.Details {
+				seen[dedupKey(apiName, modelName, detail)] = struct{}{}
+			}
+		}
+	}
+
+	for apiName, apiSnapshot := range snapshot.APIs {
+		apiName = strings.TrimSpace(apiName)
+		if apiName == "" {
+			continue
+		}
+		stats, ok := s.apis[apiName]
+		if !ok || stats == nil {
+			stats = &apiStats{Models: make(map[string]*modelStats)}
+			s.apis[apiName] = stats
+		} else if stats.Models == nil {
+			stats.Models = make(map[string]*modelStats)
+		}
+		for modelName, modelSnapshot := range apiSnapshot.Models {
+			modelName = strings.TrimSpace(modelName)
+			if modelName == "" {
+				modelName = "unknown"
+			}
+			for _, detail := range modelSnapshot.Details {
+				detail.Tokens = normaliseTokenStats(detail.Tokens)
+				if detail.Timestamp.IsZero() {
+					detail.Timestamp = time.Now()
+				}
+				key := dedupKey(apiName, modelName, detail)
+				if _, exists := seen[key]; exists {
+					result.Skipped++
+					continue
+				}
+				seen[key] = struct{}{}
+				s.recordImported(apiName, modelName, stats, detail)
+				result.Added++
+			}
+		}
+	}
+
+	return result
+}
+
+func (s *RequestStatistics) recordImported(apiName, modelName string, stats *apiStats, detail RequestDetail) {
+	totalTokens := detail.Tokens.TotalTokens
+	if totalTokens < 0 {
+		totalTokens = 0
+	}
+
+	s.totalRequests++
+	if detail.Failed {
+		s.failureCount++
+	} else {
+		s.successCount++
+	}
+	s.totalTokens += totalTokens
+
+	s.updateAPIStats(stats, modelName, detail)
+
+	dayKey := detail.Timestamp.Format("2006-01-02")
+	hourKey := detail.Timestamp.Hour()
+
+	s.requestsByDay[dayKey]++
+	s.requestsByHour[hourKey]++
+	s.tokensByDay[dayKey] += totalTokens
+	s.tokensByHour[hourKey] += totalTokens
+}
+
+func dedupKey(apiName, modelName string, detail RequestDetail) string {
+	timestamp := detail.Timestamp.UTC().Format(time.RFC3339Nano)
+	tokens := normaliseTokenStats(detail.Tokens)
+	return fmt.Sprintf(
+		"%s|%s|%s|%s|%s|%t|%d|%d|%d|%d|%d",
+		apiName,
+		modelName,
+		timestamp,
+		detail.Source,
+		detail.AuthIndex,
+		detail.Failed,
+		tokens.InputTokens,
+		tokens.OutputTokens,
+		tokens.ReasoningTokens,
+		tokens.CachedTokens,
+		tokens.TotalTokens,
+	)
+}
+
 func resolveAPIIdentifier(ctx context.Context, record coreusage.Record) string {
 	if ctx != nil {
 		if ginCtx, ok := ctx.Value("gin").(*gin.Context); ok && ginCtx != nil {
@@ -340,6 +453,16 @@ func normaliseDetail(detail coreusage.Detail) TokenStats {
 	return tokens
 }
 
+func normaliseTokenStats(tokens TokenStats) TokenStats {
+	if tokens.TotalTokens == 0 {
+		tokens.TotalTokens = tokens.InputTokens + tokens.OutputTokens + tokens.ReasoningTokens
+	}
+	if tokens.TotalTokens == 0 {
+		tokens.TotalTokens = tokens.InputTokens + tokens.OutputTokens + tokens.ReasoningTokens + tokens.CachedTokens
+	}
+	return tokens
+}
+
 func formatHour(hour int) string {
 	if hour < 0 {
 		hour = 0

internal/util/claude_model.go

@@ -0,0 +1,10 @@
+package util
+
+import "strings"
+
+// IsClaudeThinkingModel checks if the model is a Claude thinking model
+// that requires the interleaved-thinking beta header.
+func IsClaudeThinkingModel(model string) bool {
+	lower := strings.ToLower(model)
+	return strings.Contains(lower, "claude") && strings.Contains(lower, "thinking")
+}

internal/util/claude_model_test.go

@@ -0,0 +1,41 @@
+package util
+
+import "testing"
+
+func TestIsClaudeThinkingModel(t *testing.T) {
+	tests := []struct {
+		name     string
+		model    string
+		expected bool
+	}{
+		// Claude thinking models - should return true
+		{"claude-sonnet-4-5-thinking", "claude-sonnet-4-5-thinking", true},
+		{"claude-opus-4-5-thinking", "claude-opus-4-5-thinking", true},
+		{"Claude-Sonnet-Thinking uppercase", "Claude-Sonnet-4-5-Thinking", true},
+		{"claude thinking mixed case", "Claude-THINKING-Model", true},
+
+		// Non-thinking Claude models - should return false
+		{"claude-sonnet-4-5 (no thinking)", "claude-sonnet-4-5", false},
+		{"claude-opus-4-5 (no thinking)", "claude-opus-4-5", false},
+		{"claude-3-5-sonnet", "claude-3-5-sonnet-20240620", false},
+
+		// Non-Claude models - should return false
+		{"gemini-3-pro-preview", "gemini-3-pro-preview", false},
+		{"gemini-thinking model", "gemini-3-pro-thinking", false}, // not Claude
+		{"gpt-4o", "gpt-4o", false},
+		{"empty string", "", false},
+
+		// Edge cases
+		{"thinking without claude", "thinking-model", false},
+		{"claude without thinking", "claude-model", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := IsClaudeThinkingModel(tt.model)
+			if result != tt.expected {
+				t.Errorf("IsClaudeThinkingModel(%q) = %v, expected %v", tt.model, result, tt.expected)
+			}
+		})
+	}
+}

internal/util/gemini_schema.go

@@ -12,10 +12,10 @@ import (
 
 var gjsonPathKeyReplacer = strings.NewReplacer(".", "\\.", "*", "\\*", "?", "\\?")
 
-// CleanJSONSchemaForGemini transforms a JSON schema to be compatible with Gemini/Antigravity API.
+// CleanJSONSchemaForAntigravity transforms a JSON schema to be compatible with Antigravity API.
 // It handles unsupported keywords, type flattening, and schema simplification while preserving
 // semantic information as description hints.
-func CleanJSONSchemaForGemini(jsonStr string) string {
+func CleanJSONSchemaForAntigravity(jsonStr string) string {
 	// Phase 1: Convert and add hints
 	jsonStr = convertRefsToHints(jsonStr)
 	jsonStr = convertConstToEnum(jsonStr)
@@ -32,6 +32,9 @@ func CleanJSONSchemaForGemini(jsonStr string) string {
 	jsonStr = removeUnsupportedKeywords(jsonStr)
 	jsonStr = cleanupRequiredFields(jsonStr)
 
+	// Phase 4: Add placeholder for empty object schemas (Claude VALIDATED mode requirement)
+	jsonStr = addEmptySchemaPlaceholder(jsonStr)
+
 	return jsonStr
 }
 
@@ -105,7 +108,8 @@ func addAdditionalPropertiesHints(jsonStr string) string {
 
 var unsupportedConstraints = []string{
 	"minLength", "maxLength", "exclusiveMinimum", "exclusiveMaximum",
-	"pattern", "minItems", "maxItems",
+	"pattern", "minItems", "maxItems", "format",
+	"default", "examples", // Claude rejects these in VALIDATED mode
 }
 
 func moveConstraintsToDescription(jsonStr string) string {
@@ -296,6 +300,7 @@ func flattenTypeArrays(jsonStr string) string {
 func removeUnsupportedKeywords(jsonStr string) string {
 	keywords := append(unsupportedConstraints,
 		"$schema", "$defs", "definitions", "const", "$ref", "additionalProperties",
+		"propertyNames", // Gemini doesn't support property name validation
 	)
 	for _, key := range keywords {
 		for _, p := range findPaths(jsonStr, key) {
@@ -338,6 +343,69 @@ func cleanupRequiredFields(jsonStr string) string {
 	return jsonStr
 }
 
+// addEmptySchemaPlaceholder adds a placeholder "reason" property to empty object schemas.
+// Claude VALIDATED mode requires at least one required property in tool schemas.
+func addEmptySchemaPlaceholder(jsonStr string) string {
+	// Find all "type" fields
+	paths := findPaths(jsonStr, "type")
+
+	// Process from deepest to shallowest (to handle nested objects properly)
+	sortByDepth(paths)
+
+	for _, p := range paths {
+		typeVal := gjson.Get(jsonStr, p)
+		if typeVal.String() != "object" {
+			continue
+		}
+
+		// Get the parent path (the object containing "type")
+		parentPath := trimSuffix(p, ".type")
+
+		// Check if properties exists and is empty or missing
+		propsPath := joinPath(parentPath, "properties")
+		propsVal := gjson.Get(jsonStr, propsPath)
+		reqPath := joinPath(parentPath, "required")
+		reqVal := gjson.Get(jsonStr, reqPath)
+		hasRequiredProperties := reqVal.IsArray() && len(reqVal.Array()) > 0
+
+		needsPlaceholder := false
+		if !propsVal.Exists() {
+			// No properties field at all
+			needsPlaceholder = true
+		} else if propsVal.IsObject() && len(propsVal.Map()) == 0 {
+			// Empty properties object
+			needsPlaceholder = true
+		}
+
+		if needsPlaceholder {
+			// Add placeholder "reason" property
+			reasonPath := joinPath(propsPath, "reason")
+			jsonStr, _ = sjson.Set(jsonStr, reasonPath+".type", "string")
+			jsonStr, _ = sjson.Set(jsonStr, reasonPath+".description", "Brief explanation of why you are calling this tool")
+
+			// Add to required array
+			jsonStr, _ = sjson.Set(jsonStr, reqPath, []string{"reason"})
+			continue
+		}
+
+		// If schema has properties but none are required, add a minimal placeholder.
+		if propsVal.IsObject() && !hasRequiredProperties {
+			// DO NOT add placeholder if it's a top-level schema (parentPath is empty)
+			// or if we've already added a placeholder reason above.
+			if parentPath == "" {
+				continue
+			}
+			placeholderPath := joinPath(propsPath, "_")
+			if !gjson.Get(jsonStr, placeholderPath).Exists() {
+				jsonStr, _ = sjson.Set(jsonStr, placeholderPath+".type", "boolean")
+			}
+			jsonStr, _ = sjson.Set(jsonStr, reqPath, []string{"_"})
+		}
+	}
+
+	return jsonStr
+}
+
 // --- Helpers ---
 
 func findPaths(jsonStr, field string) []string {

internal/util/gemini_schema_test.go

@@ -5,9 +5,11 @@ import (
 	"reflect"
 	"strings"
 	"testing"
+
+	"github.com/tidwall/gjson"
 )
 
-func TestCleanJSONSchemaForGemini_ConstToEnum(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_ConstToEnum(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -28,11 +30,11 @@ func TestCleanJSONSchemaForGemini_ConstToEnum(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_TypeFlattening_Nullable(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_TypeFlattening_Nullable(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -60,11 +62,11 @@ func TestCleanJSONSchemaForGemini_TypeFlattening_Nullable(t *testing.T) {
 		"required": ["other"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_ConstraintsToDescription(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_ConstraintsToDescription(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -81,7 +83,7 @@ func TestCleanJSONSchemaForGemini_ConstraintsToDescription(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	// minItems should be REMOVED and moved to description
 	if strings.Contains(result, `"minItems"`) {
@@ -100,7 +102,7 @@ func TestCleanJSONSchemaForGemini_ConstraintsToDescription(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_AnyOfFlattening_SmartSelection(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_AnyOfFlattening_SmartSelection(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -125,17 +127,19 @@ func TestCleanJSONSchemaForGemini_AnyOfFlattening_SmartSelection(t *testing.T) {
 				"type": "object",
 				"description": "Accepts: null | object",
 				"properties": {
+					"_": { "type": "boolean" },
 					"kind": { "type": "string" }
-				}
+				},
+				"required": ["_"]
 			}
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_OneOfFlattening(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_OneOfFlattening(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -158,11 +162,11 @@ func TestCleanJSONSchemaForGemini_OneOfFlattening(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_AllOfMerging(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_AllOfMerging(t *testing.T) {
 	input := `{
 		"type": "object",
 		"allOf": [
@@ -190,11 +194,11 @@ func TestCleanJSONSchemaForGemini_AllOfMerging(t *testing.T) {
 		"required": ["a", "b"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_RefHandling(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_RefHandling(t *testing.T) {
 	input := `{
 		"definitions": {
 			"User": {
@@ -210,21 +214,29 @@ func TestCleanJSONSchemaForGemini_RefHandling(t *testing.T) {
 		}
 	}`
 
+	// After $ref is converted to placeholder object, empty schema placeholder is also added
 	expected := `{
 		"type": "object",
 		"properties": {
 			"customer": {
 				"type": "object",
-				"description": "See: User"
+				"description": "See: User",
+				"properties": {
+					"reason": {
+						"type": "string",
+						"description": "Brief explanation of why you are calling this tool"
+					}
+				},
+				"required": ["reason"]
 			}
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_RefHandling_DescriptionEscaping(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_RefHandling_DescriptionEscaping(t *testing.T) {
 	input := `{
 		"definitions": {
 			"User": {
@@ -243,21 +255,29 @@ func TestCleanJSONSchemaForGemini_RefHandling_DescriptionEscaping(t *testing.T)
 		}
 	}`
 
+	// After $ref is converted, empty schema placeholder is also added
 	expected := `{
 		"type": "object",
 		"properties": {
 			"customer": {
 				"type": "object",
-				"description": "He said \"hi\"\\nsecond line (See: User)"
+				"description": "He said \"hi\"\\nsecond line (See: User)",
+				"properties": {
+					"reason": {
+						"type": "string",
+						"description": "Brief explanation of why you are calling this tool"
+					}
+				},
+				"required": ["reason"]
 			}
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_CyclicRefDefaults(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_CyclicRefDefaults(t *testing.T) {
 	input := `{
 		"definitions": {
 			"Node": {
@@ -270,7 +290,7 @@ func TestCleanJSONSchemaForGemini_CyclicRefDefaults(t *testing.T) {
 		"$ref": "#/definitions/Node"
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	var resMap map[string]interface{}
 	json.Unmarshal([]byte(result), &resMap)
@@ -285,7 +305,7 @@ func TestCleanJSONSchemaForGemini_CyclicRefDefaults(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_RequiredCleanup(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_RequiredCleanup(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -304,11 +324,11 @@ func TestCleanJSONSchemaForGemini_RequiredCleanup(t *testing.T) {
 		"required": ["a", "b"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_AllOfMerging_DotKeys(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_AllOfMerging_DotKeys(t *testing.T) {
 	input := `{
 		"type": "object",
 		"allOf": [
@@ -336,11 +356,11 @@ func TestCleanJSONSchemaForGemini_AllOfMerging_DotKeys(t *testing.T) {
 		"required": ["my.param", "b"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_PropertyNameCollision(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_PropertyNameCollision(t *testing.T) {
 	// A tool has an argument named "pattern" - should NOT be treated as a constraint
 	input := `{
 		"type": "object",
@@ -364,7 +384,7 @@ func TestCleanJSONSchemaForGemini_PropertyNameCollision(t *testing.T) {
 		"required": ["pattern"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 
 	var resMap map[string]interface{}
@@ -375,7 +395,7 @@ func TestCleanJSONSchemaForGemini_PropertyNameCollision(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_DotKeys(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_DotKeys(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -389,7 +409,7 @@ func TestCleanJSONSchemaForGemini_DotKeys(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	var resMap map[string]interface{}
 	if err := json.Unmarshal([]byte(result), &resMap); err != nil {
@@ -414,7 +434,7 @@ func TestCleanJSONSchemaForGemini_DotKeys(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_AnyOfAlternativeHints(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_AnyOfAlternativeHints(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -428,7 +448,7 @@ func TestCleanJSONSchemaForGemini_AnyOfAlternativeHints(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	if !strings.Contains(result, "Accepts:") {
 		t.Errorf("Expected alternative types hint, got: %s", result)
@@ -438,7 +458,7 @@ func TestCleanJSONSchemaForGemini_AnyOfAlternativeHints(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_NullableHint(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_NullableHint(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -450,7 +470,7 @@ func TestCleanJSONSchemaForGemini_NullableHint(t *testing.T) {
 		"required": ["name"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	if !strings.Contains(result, "(nullable)") {
 		t.Errorf("Expected nullable hint, got: %s", result)
@@ -460,7 +480,7 @@ func TestCleanJSONSchemaForGemini_NullableHint(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_TypeFlattening_Nullable_DotKey(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_TypeFlattening_Nullable_DotKey(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -488,11 +508,11 @@ func TestCleanJSONSchemaForGemini_TypeFlattening_Nullable_DotKey(t *testing.T) {
 		"required": ["other"]
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_EnumHint(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_EnumHint(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -504,7 +524,7 @@ func TestCleanJSONSchemaForGemini_EnumHint(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	if !strings.Contains(result, "Allowed:") {
 		t.Errorf("Expected enum values hint, got: %s", result)
@@ -514,7 +534,7 @@ func TestCleanJSONSchemaForGemini_EnumHint(t *testing.T) {
 	}
 }
 
-func TestCleanJSONSchemaForGemini_AdditionalPropertiesHint(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_AdditionalPropertiesHint(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -523,14 +543,14 @@ func TestCleanJSONSchemaForGemini_AdditionalPropertiesHint(t *testing.T) {
 		"additionalProperties": false
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	if !strings.Contains(result, "No extra properties allowed") {
 		t.Errorf("Expected additionalProperties hint, got: %s", result)
 	}
 }
 
-func TestCleanJSONSchemaForGemini_AnyOfFlattening_PreservesDescription(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_AnyOfFlattening_PreservesDescription(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -554,11 +574,11 @@ func TestCleanJSONSchemaForGemini_AnyOfFlattening_PreservesDescription(t *testin
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 	compareJSON(t, expected, result)
 }
 
-func TestCleanJSONSchemaForGemini_SingleEnumNoHint(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_SingleEnumNoHint(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -569,14 +589,14 @@ func TestCleanJSONSchemaForGemini_SingleEnumNoHint(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	if strings.Contains(result, "Allowed:") {
 		t.Errorf("Single value enum should not add Allowed hint, got: %s", result)
 	}
 }
 
-func TestCleanJSONSchemaForGemini_MultipleNonNullTypes(t *testing.T) {
+func TestCleanJSONSchemaForAntigravity_MultipleNonNullTypes(t *testing.T) {
 	input := `{
 		"type": "object",
 		"properties": {
@@ -586,7 +606,7 @@ func TestCleanJSONSchemaForGemini_MultipleNonNullTypes(t *testing.T) {
 		}
 	}`
 
-	result := CleanJSONSchemaForGemini(input)
+	result := CleanJSONSchemaForAntigravity(input)
 
 	if !strings.Contains(result, "Accepts:") {
 		t.Errorf("Expected multiple types hint, got: %s", result)
@@ -611,3 +631,190 @@ func compareJSON(t *testing.T, expectedJSON, actualJSON string) {
 		t.Errorf("JSON mismatch:\nExpected:\n%s\n\nActual:\n%s", string(expBytes), string(actBytes))
 	}
 }
+
+// ============================================================================
+// Empty Schema Placeholder Tests
+// ============================================================================
+
+func TestCleanJSONSchemaForAntigravity_EmptySchemaPlaceholder(t *testing.T) {
+	// Empty object schema with no properties should get a placeholder
+	input := `{
+		"type": "object"
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// Should have placeholder property added
+	if !strings.Contains(result, `"reason"`) {
+		t.Errorf("Empty schema should have 'reason' placeholder property, got: %s", result)
+	}
+	if !strings.Contains(result, `"required"`) {
+		t.Errorf("Empty schema should have 'required' with 'reason', got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForAntigravity_EmptyPropertiesPlaceholder(t *testing.T) {
+	// Object with empty properties object
+	input := `{
+		"type": "object",
+		"properties": {}
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// Should have placeholder property added
+	if !strings.Contains(result, `"reason"`) {
+		t.Errorf("Empty properties should have 'reason' placeholder, got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForAntigravity_NonEmptySchemaUnchanged(t *testing.T) {
+	// Schema with properties should NOT get placeholder
+	input := `{
+		"type": "object",
+		"properties": {
+			"name": {"type": "string"}
+		},
+		"required": ["name"]
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// Should NOT have placeholder property
+	if strings.Contains(result, `"reason"`) {
+		t.Errorf("Non-empty schema should NOT have 'reason' placeholder, got: %s", result)
+	}
+	// Original properties should be preserved
+	if !strings.Contains(result, `"name"`) {
+		t.Errorf("Original property 'name' should be preserved, got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForAntigravity_NestedEmptySchema(t *testing.T) {
+	// Nested empty object in items should also get placeholder
+	input := `{
+		"type": "object",
+		"properties": {
+			"items": {
+				"type": "array",
+				"items": {
+					"type": "object"
+				}
+			}
+		}
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// Nested empty object should also get placeholder
+	// Check that the nested object has a reason property
+	parsed := gjson.Parse(result)
+	nestedProps := parsed.Get("properties.items.items.properties")
+	if !nestedProps.Exists() || !nestedProps.Get("reason").Exists() {
+		t.Errorf("Nested empty object should have 'reason' placeholder, got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForAntigravity_EmptySchemaWithDescription(t *testing.T) {
+	// Empty schema with description should preserve description and add placeholder
+	input := `{
+		"type": "object",
+		"description": "An empty object"
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// Should have both description and placeholder
+	if !strings.Contains(result, `"An empty object"`) {
+		t.Errorf("Description should be preserved, got: %s", result)
+	}
+	if !strings.Contains(result, `"reason"`) {
+		t.Errorf("Empty schema should have 'reason' placeholder, got: %s", result)
+	}
+}
+
+// ============================================================================
+// Format field handling (ad-hoc patch removal)
+// ============================================================================
+
+func TestCleanJSONSchemaForAntigravity_FormatFieldRemoval(t *testing.T) {
+	// format:"uri" should be removed and added as hint
+	input := `{
+		"type": "object",
+		"properties": {
+			"url": {
+				"type": "string",
+				"format": "uri",
+				"description": "A URL"
+			}
+		}
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// format should be removed
+	if strings.Contains(result, `"format"`) {
+		t.Errorf("format field should be removed, got: %s", result)
+	}
+	// hint should be added to description
+	if !strings.Contains(result, "format: uri") {
+		t.Errorf("format hint should be added to description, got: %s", result)
+	}
+	// original description should be preserved
+	if !strings.Contains(result, "A URL") {
+		t.Errorf("Original description should be preserved, got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForAntigravity_FormatFieldNoDescription(t *testing.T) {
+	// format without description should create description with hint
+	input := `{
+		"type": "object",
+		"properties": {
+			"email": {
+				"type": "string",
+				"format": "email"
+			}
+		}
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// format should be removed
+	if strings.Contains(result, `"format"`) {
+		t.Errorf("format field should be removed, got: %s", result)
+	}
+	// hint should be added
+	if !strings.Contains(result, "format: email") {
+		t.Errorf("format hint should be added, got: %s", result)
+	}
+}
+
+func TestCleanJSONSchemaForAntigravity_MultipleFormats(t *testing.T) {
+	// Multiple format fields should all be handled
+	input := `{
+		"type": "object",
+		"properties": {
+			"url": {"type": "string", "format": "uri"},
+			"email": {"type": "string", "format": "email"},
+			"date": {"type": "string", "format": "date-time"}
+		}
+	}`
+
+	result := CleanJSONSchemaForAntigravity(input)
+
+	// All format fields should be removed
+	if strings.Contains(result, `"format"`) {
+		t.Errorf("All format fields should be removed, got: %s", result)
+	}
+	// All hints should be added
+	if !strings.Contains(result, "format: uri") {
+		t.Errorf("uri format hint should be added, got: %s", result)
+	}
+	if !strings.Contains(result, "format: email") {
+		t.Errorf("email format hint should be added, got: %s", result)
+	}
+	if !strings.Contains(result, "format: date-time") {
+		t.Errorf("date-time format hint should be added, got: %s", result)
+	}
+}