From 32d3809f8c2e09f57c7b04369e215e4902187272 Mon Sep 17 00:00:00 2001
From: auroraflux <14947763+auroraflux@users.noreply.github.com>
Date: Sun, 30 Nov 2025 00:29:50 -0800
Subject: [PATCH] **feat(util): add -reasoning suffix support for Gemini
 models**

Adds support for the `-reasoning` model name suffix which enables
thinking/reasoning mode with dynamic budget. This allows clients to
request reasoning-enabled inference using model names like
`gemini-2.5-flash-reasoning` without explicit configuration.

The suffix is normalized to the base model (e.g., gemini-2.5-flash)
with thinkingBudget=-1 (dynamic) and include_thoughts=true.

Follows the existing pattern established by -nothinking and
-thinking-N suffixes.
---
 .../runtime/executor/antigravity_executor.go  | 19 +++++++++++++++++++
 internal/util/gemini_thinking.go              |  9 +++++++++
 2 files changed, 28 insertions(+)

diff --git a/internal/runtime/executor/antigravity_executor.go b/internal/runtime/executor/antigravity_executor.go
index 13373537..bcc64310 100644
--- a/internal/runtime/executor/antigravity_executor.go
+++ b/internal/runtime/executor/antigravity_executor.go
@@ -17,6 +17,7 @@ import (
 	"github.com/google/uuid"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+	"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"
@@ -58,6 +59,20 @@ func (e *AntigravityExecutor) Identifier() string { return antigravityAuthType }
 // PrepareRequest implements ProviderExecutor.
 func (e *AntigravityExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error { return nil }
 
+// applyThinkingMetadata applies thinking config from model suffix metadata (e.g., -reasoning, -thinking-N).
+// It trusts user intent when suffix is used, even if registry doesn't have Thinking metadata.
+func applyThinkingMetadata(translated []byte, metadata map[string]any, model string) []byte {
+	budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(metadata)
+	if !ok {
+		return translated
+	}
+	if budgetOverride != nil && util.ModelSupportsThinking(model) {
+		norm := util.NormalizeThinkingBudget(model, *budgetOverride)
+		budgetOverride = &norm
+	}
+	return util.ApplyGeminiCLIThinkingConfig(translated, budgetOverride, includeOverride)
+}
+
 // Execute handles non-streaming requests via the antigravity generate endpoint.
 func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
 	token, updatedAuth, errToken := e.ensureAccessToken(ctx, auth)
@@ -75,6 +90,8 @@ 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 = applyThinkingMetadata(translated, req.Metadata, req.Model)
+
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
@@ -166,6 +183,8 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
 	to := sdktranslator.FromString("antigravity")
 	translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
 
+	translated = applyThinkingMetadata(translated, req.Metadata, req.Model)
+
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
diff --git a/internal/util/gemini_thinking.go b/internal/util/gemini_thinking.go
index d7481621..14077fa0 100644
--- a/internal/util/gemini_thinking.go
+++ b/internal/util/gemini_thinking.go
@@ -34,6 +34,15 @@ func ParseGeminiThinkingSuffix(model string) (string, *int, *bool, bool) {
 		return base, &budgetValue, &include, true
 	}
 
+	// Handle "-reasoning" suffix: enables thinking with dynamic budget (-1)
+	// Maps: gemini-2.5-flash-reasoning -> gemini-2.5-flash with thinkingBudget=-1
+	if strings.HasSuffix(lower, "-reasoning") {
+		base := model[:len(model)-len("-reasoning")]
+		budgetValue := -1 // Dynamic budget
+		include := true
+		return base, &budgetValue, &include, true
+	}
+
 	idx := strings.LastIndex(lower, "-thinking-")
 	if idx == -1 {
 		return model, nil, nil, false