CLIProxyAPI/internal/runtime/executor/claude_executor.go

package executor

import (
	"bufio"
	"bytes"
	"compress/flate"
	"compress/gzip"
	"context"
	"fmt"
	"io"
	"net/http"
	"strings"
	"time"

	"github.com/andybalholm/brotli"
	"github.com/klauspost/compress/zstd"
	claudeauth "github.com/router-for-me/CLIProxyAPI/v6/internal/auth/claude"
	"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/registry"
	"github.com/router-for-me/CLIProxyAPI/v6/internal/thinking"
	"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"
	log "github.com/sirupsen/logrus"
	"github.com/tidwall/gjson"
	"github.com/tidwall/sjson"

	"github.com/gin-gonic/gin"
)

// ClaudeExecutor is a stateless executor for Anthropic Claude over the messages API.
// If api_key is unavailable on auth, it falls back to legacy via ClientAdapter.
type ClaudeExecutor struct {
	cfg *config.Config
}

const claudeToolPrefix = "proxy_"

func NewClaudeExecutor(cfg *config.Config) *ClaudeExecutor { return &ClaudeExecutor{cfg: cfg} }

func (e *ClaudeExecutor) Identifier() string { return "claude" }

// PrepareRequest injects Claude credentials into the outgoing HTTP request.
func (e *ClaudeExecutor) PrepareRequest(req *http.Request, auth *cliproxyauth.Auth) error {
	if req == nil {
		return nil
	}
	apiKey, _ := claudeCreds(auth)
	if strings.TrimSpace(apiKey) == "" {
		return nil
	}
	useAPIKey := auth != nil && auth.Attributes != nil && strings.TrimSpace(auth.Attributes["api_key"]) != ""
	isAnthropicBase := req.URL != nil && strings.EqualFold(req.URL.Scheme, "https") && strings.EqualFold(req.URL.Host, "api.anthropic.com")
	if isAnthropicBase && useAPIKey {
		req.Header.Del("Authorization")
		req.Header.Set("x-api-key", apiKey)
	} else {
		req.Header.Del("x-api-key")
		req.Header.Set("Authorization", "Bearer "+apiKey)
	}
	var attrs map[string]string
	if auth != nil {
		attrs = auth.Attributes
	}
	util.ApplyCustomHeadersFromAttrs(req, attrs)
	return nil
}

// HttpRequest injects Claude credentials into the request and executes it.
func (e *ClaudeExecutor) HttpRequest(ctx context.Context, auth *cliproxyauth.Auth, req *http.Request) (*http.Response, error) {
	if req == nil {
		return nil, fmt.Errorf("claude executor: request is nil")
	}
	if ctx == nil {
		ctx = req.Context()
	}
	httpReq := req.WithContext(ctx)
	if err := e.PrepareRequest(httpReq, auth); err != nil {
		return nil, err
	}
	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
	return httpClient.Do(httpReq)
}

func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
	baseModel := thinking.ParseSuffix(req.Model).ModelName

	apiKey, baseURL := claudeCreds(auth)
	if baseURL == "" {
		baseURL = "https://api.anthropic.com"
	}

	reporter := newUsageReporter(ctx, e.Identifier(), baseModel, auth)
	defer reporter.trackFailure(ctx, &err)
	from := opts.SourceFormat
	to := sdktranslator.FromString("claude")
	// Use streaming translation to preserve function calling, except for claude.
	stream := from != to
	originalPayload := bytes.Clone(req.Payload)
	if len(opts.OriginalRequest) > 0 {
		originalPayload = bytes.Clone(opts.OriginalRequest)
	}
	originalTranslated := sdktranslator.TranslateRequest(from, to, baseModel, originalPayload, stream)
	body := sdktranslator.TranslateRequest(from, to, baseModel, bytes.Clone(req.Payload), stream)
	body, _ = sjson.SetBytes(body, "model", baseModel)

	body, err = thinking.ApplyThinking(body, req.Model, "claude")
	if err != nil {
		return resp, err
	}

	if !strings.HasPrefix(baseModel, "claude-3-5-haiku") {
		body = checkSystemInstructions(body)
	}
	body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated)

	// 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(baseModel, body)

	// Extract betas from body and convert to header
	var extraBetas []string
	extraBetas, body = extractAndRemoveBetas(body)
	bodyForTranslation := body
	bodyForUpstream := body
	if isClaudeOAuthToken(apiKey) {
		bodyForUpstream = applyClaudeToolPrefix(body, claudeToolPrefix)
	}

	url := fmt.Sprintf("%s/v1/messages?beta=true", baseURL)
	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(bodyForUpstream))
	if err != nil {
		return resp, err
	}
	applyClaudeHeaders(httpReq, auth, apiKey, false, extraBetas)
	var authID, authLabel, authType, authValue string
	if auth != nil {
		authID = auth.ID
		authLabel = auth.Label
		authType, authValue = auth.AccountInfo()
	}
	recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
		URL:       url,
		Method:    http.MethodPost,
		Headers:   httpReq.Header.Clone(),
		Body:      bodyForUpstream,
		Provider:  e.Identifier(),
		AuthID:    authID,
		AuthLabel: authLabel,
		AuthType:  authType,
		AuthValue: authValue,
	})

	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
	httpResp, err := httpClient.Do(httpReq)
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		return resp, err
	}
	recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
		b, _ := io.ReadAll(httpResp.Body)
		appendAPIResponseChunk(ctx, e.cfg, b)
		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
		if errClose := httpResp.Body.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
		return resp, err
	}
	decodedBody, err := decodeResponseBody(httpResp.Body, httpResp.Header.Get("Content-Encoding"))
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		if errClose := httpResp.Body.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
		return resp, err
	}
	defer func() {
		if errClose := decodedBody.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
	}()
	data, err := io.ReadAll(decodedBody)
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		return resp, err
	}
	appendAPIResponseChunk(ctx, e.cfg, data)
	if stream {
		lines := bytes.Split(data, []byte("\n"))
		for _, line := range lines {
			if detail, ok := parseClaudeStreamUsage(line); ok {
				reporter.publish(ctx, detail)
			}
		}
	} else {
		reporter.publish(ctx, parseClaudeUsage(data))
	}
	if isClaudeOAuthToken(apiKey) {
		data = stripClaudeToolPrefixFromResponse(data, claudeToolPrefix)
	}
	var param any
	out := sdktranslator.TranslateNonStream(
		ctx,
		to,
		from,
		req.Model,
		bytes.Clone(opts.OriginalRequest),
		bodyForTranslation,
		data,
		&param,
	)
	resp = cliproxyexecutor.Response{Payload: []byte(out)}
	return resp, nil
}

func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (stream <-chan cliproxyexecutor.StreamChunk, err error) {
	baseModel := thinking.ParseSuffix(req.Model).ModelName

	apiKey, baseURL := claudeCreds(auth)
	if baseURL == "" {
		baseURL = "https://api.anthropic.com"
	}

	reporter := newUsageReporter(ctx, e.Identifier(), baseModel, auth)
	defer reporter.trackFailure(ctx, &err)
	from := opts.SourceFormat
	to := sdktranslator.FromString("claude")
	originalPayload := bytes.Clone(req.Payload)
	if len(opts.OriginalRequest) > 0 {
		originalPayload = bytes.Clone(opts.OriginalRequest)
	}
	originalTranslated := sdktranslator.TranslateRequest(from, to, baseModel, originalPayload, true)
	body := sdktranslator.TranslateRequest(from, to, baseModel, bytes.Clone(req.Payload), true)
	body, _ = sjson.SetBytes(body, "model", baseModel)

	body, err = thinking.ApplyThinking(body, req.Model, "claude")
	if err != nil {
		return nil, err
	}

	body = checkSystemInstructions(body)
	body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated)

	// 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(baseModel, body)

	// Extract betas from body and convert to header
	var extraBetas []string
	extraBetas, body = extractAndRemoveBetas(body)
	bodyForTranslation := body
	bodyForUpstream := body
	if isClaudeOAuthToken(apiKey) {
		bodyForUpstream = applyClaudeToolPrefix(body, claudeToolPrefix)
	}

	url := fmt.Sprintf("%s/v1/messages?beta=true", baseURL)
	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(bodyForUpstream))
	if err != nil {
		return nil, err
	}
	applyClaudeHeaders(httpReq, auth, apiKey, true, extraBetas)
	var authID, authLabel, authType, authValue string
	if auth != nil {
		authID = auth.ID
		authLabel = auth.Label
		authType, authValue = auth.AccountInfo()
	}
	recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
		URL:       url,
		Method:    http.MethodPost,
		Headers:   httpReq.Header.Clone(),
		Body:      bodyForUpstream,
		Provider:  e.Identifier(),
		AuthID:    authID,
		AuthLabel: authLabel,
		AuthType:  authType,
		AuthValue: authValue,
	})

	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
	httpResp, err := httpClient.Do(httpReq)
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		return nil, err
	}
	recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
	if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
		b, _ := io.ReadAll(httpResp.Body)
		appendAPIResponseChunk(ctx, e.cfg, b)
		log.Debugf("request error, error status: %d, error body: %s", httpResp.StatusCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
		if errClose := httpResp.Body.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
		err = statusErr{code: httpResp.StatusCode, msg: string(b)}
		return nil, err
	}
	decodedBody, err := decodeResponseBody(httpResp.Body, httpResp.Header.Get("Content-Encoding"))
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		if errClose := httpResp.Body.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
		return nil, err
	}
	out := make(chan cliproxyexecutor.StreamChunk)
	stream = out
	go func() {
		defer close(out)
		defer func() {
			if errClose := decodedBody.Close(); errClose != nil {
				log.Errorf("response body close error: %v", errClose)
			}
		}()

		// If from == to (Claude → Claude), directly forward the SSE stream without translation
		if from == to {
			scanner := bufio.NewScanner(decodedBody)
			scanner.Buffer(nil, 52_428_800) // 50MB
			for scanner.Scan() {
				line := scanner.Bytes()
				appendAPIResponseChunk(ctx, e.cfg, line)
				if detail, ok := parseClaudeStreamUsage(line); ok {
					reporter.publish(ctx, detail)
				}
				if isClaudeOAuthToken(apiKey) {
					line = stripClaudeToolPrefixFromStreamLine(line, claudeToolPrefix)
				}
				// Forward the line as-is to preserve SSE format
				cloned := make([]byte, len(line)+1)
				copy(cloned, line)
				cloned[len(line)] = '\n'
				out <- cliproxyexecutor.StreamChunk{Payload: cloned}
			}
			if errScan := scanner.Err(); errScan != nil {
				recordAPIResponseError(ctx, e.cfg, errScan)
				reporter.publishFailure(ctx)
				out <- cliproxyexecutor.StreamChunk{Err: errScan}
			}
			return
		}

		// For other formats, use translation
		scanner := bufio.NewScanner(decodedBody)
		scanner.Buffer(nil, 52_428_800) // 50MB
		var param any
		for scanner.Scan() {
			line := scanner.Bytes()
			appendAPIResponseChunk(ctx, e.cfg, line)
			if detail, ok := parseClaudeStreamUsage(line); ok {
				reporter.publish(ctx, detail)
			}
			if isClaudeOAuthToken(apiKey) {
				line = stripClaudeToolPrefixFromStreamLine(line, claudeToolPrefix)
			}
			chunks := sdktranslator.TranslateStream(
				ctx,
				to,
				from,
				req.Model,
				bytes.Clone(opts.OriginalRequest),
				bodyForTranslation,
				bytes.Clone(line),
				&param,
			)
			for i := range chunks {
				out <- cliproxyexecutor.StreamChunk{Payload: []byte(chunks[i])}
			}
		}
		if errScan := scanner.Err(); errScan != nil {
			recordAPIResponseError(ctx, e.cfg, errScan)
			reporter.publishFailure(ctx)
			out <- cliproxyexecutor.StreamChunk{Err: errScan}
		}
	}()
	return stream, nil
}

func (e *ClaudeExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
	baseModel := thinking.ParseSuffix(req.Model).ModelName

	apiKey, baseURL := claudeCreds(auth)
	if baseURL == "" {
		baseURL = "https://api.anthropic.com"
	}

	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, baseModel, bytes.Clone(req.Payload), stream)
	body, _ = sjson.SetBytes(body, "model", baseModel)

	if !strings.HasPrefix(baseModel, "claude-3-5-haiku") {
		body = checkSystemInstructions(body)
	}

	// Extract betas from body and convert to header (for count_tokens too)
	var extraBetas []string
	extraBetas, body = extractAndRemoveBetas(body)
	if isClaudeOAuthToken(apiKey) {
		body = applyClaudeToolPrefix(body, claudeToolPrefix)
	}

	url := fmt.Sprintf("%s/v1/messages/count_tokens?beta=true", baseURL)
	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(body))
	if err != nil {
		return cliproxyexecutor.Response{}, err
	}
	applyClaudeHeaders(httpReq, auth, apiKey, false, extraBetas)
	var authID, authLabel, authType, authValue string
	if auth != nil {
		authID = auth.ID
		authLabel = auth.Label
		authType, authValue = auth.AccountInfo()
	}
	recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
		URL:       url,
		Method:    http.MethodPost,
		Headers:   httpReq.Header.Clone(),
		Body:      body,
		Provider:  e.Identifier(),
		AuthID:    authID,
		AuthLabel: authLabel,
		AuthType:  authType,
		AuthValue: authValue,
	})

	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
	resp, err := httpClient.Do(httpReq)
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		return cliproxyexecutor.Response{}, err
	}
	recordAPIResponseMetadata(ctx, e.cfg, resp.StatusCode, resp.Header.Clone())
	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		b, _ := io.ReadAll(resp.Body)
		appendAPIResponseChunk(ctx, e.cfg, b)
		if errClose := resp.Body.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
		return cliproxyexecutor.Response{}, statusErr{code: resp.StatusCode, msg: string(b)}
	}
	decodedBody, err := decodeResponseBody(resp.Body, resp.Header.Get("Content-Encoding"))
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		if errClose := resp.Body.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
		return cliproxyexecutor.Response{}, err
	}
	defer func() {
		if errClose := decodedBody.Close(); errClose != nil {
			log.Errorf("response body close error: %v", errClose)
		}
	}()
	data, err := io.ReadAll(decodedBody)
	if err != nil {
		recordAPIResponseError(ctx, e.cfg, err)
		return cliproxyexecutor.Response{}, err
	}
	appendAPIResponseChunk(ctx, e.cfg, data)
	count := gjson.GetBytes(data, "input_tokens").Int()
	out := sdktranslator.TranslateTokenCount(ctx, to, from, count, data)
	return cliproxyexecutor.Response{Payload: []byte(out)}, nil
}

func (e *ClaudeExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {
	log.Debugf("claude executor: refresh called")
	if auth == nil {
		return nil, fmt.Errorf("claude executor: auth is nil")
	}
	var refreshToken string
	if auth.Metadata != nil {
		if v, ok := auth.Metadata["refresh_token"].(string); ok && v != "" {
			refreshToken = v
		}
	}
	if refreshToken == "" {
		return auth, nil
	}
	svc := claudeauth.NewClaudeAuth(e.cfg)
	td, err := svc.RefreshTokens(ctx, refreshToken)
	if err != nil {
		return nil, err
	}
	if auth.Metadata == nil {
		auth.Metadata = make(map[string]any)
	}
	auth.Metadata["access_token"] = td.AccessToken
	if td.RefreshToken != "" {
		auth.Metadata["refresh_token"] = td.RefreshToken
	}
	auth.Metadata["email"] = td.Email
	auth.Metadata["expired"] = td.Expire
	auth.Metadata["type"] = "claude"
	now := time.Now().Format(time.RFC3339)
	auth.Metadata["last_refresh"] = now
	return auth, nil
}

// extractAndRemoveBetas extracts the "betas" array from the body and removes it.
// Returns the extracted betas as a string slice and the modified body.
func extractAndRemoveBetas(body []byte) ([]string, []byte) {
	betasResult := gjson.GetBytes(body, "betas")
	if !betasResult.Exists() {
		return nil, body
	}
	var betas []string
	if betasResult.IsArray() {
		for _, item := range betasResult.Array() {
			if s := strings.TrimSpace(item.String()); s != "" {
				betas = append(betas, s)
			}
		}
	} else if s := strings.TrimSpace(betasResult.String()); s != "" {
		betas = append(betas, s)
	}
	body, _ = sjson.DeleteBytes(body, "betas")
	return betas, body
}

// 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.
// It looks up the model's MaxCompletionTokens from the registry to use as the cap.
func ensureMaxTokensForThinking(modelName string, body []byte) []byte {
	thinkingType := gjson.GetBytes(body, "thinking.type").String()
	if thinkingType != "enabled" {
		return body
	}

	budgetTokens := gjson.GetBytes(body, "thinking.budget_tokens").Int()
	if budgetTokens <= 0 {
		return body
	}

	maxTokens := gjson.GetBytes(body, "max_tokens").Int()

	// Look up the model's max completion tokens from the registry
	maxCompletionTokens := 0
	if modelInfo := registry.LookupModelInfo(modelName); modelInfo != nil {
		maxCompletionTokens = modelInfo.MaxCompletionTokens
	}

	// Fall back to budget + buffer if registry lookup fails or returns 0
	const fallbackBuffer = 4000
	requiredMaxTokens := budgetTokens + fallbackBuffer
	if maxCompletionTokens > 0 {
		requiredMaxTokens = int64(maxCompletionTokens)
	}

	if maxTokens < requiredMaxTokens {
		body, _ = sjson.SetBytes(body, "max_tokens", requiredMaxTokens)
	}
	return body
}

func (e *ClaudeExecutor) resolveClaudeConfig(auth *cliproxyauth.Auth) *config.ClaudeKey {
	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.ClaudeKey {
		entry := &e.cfg.ClaudeKey[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.ClaudeKey {
			entry := &e.cfg.ClaudeKey[i]
			if strings.EqualFold(strings.TrimSpace(entry.APIKey), attrKey) {
				return entry
			}
		}
	}
	return nil
}

type compositeReadCloser struct {
	io.Reader
	closers []func() error
}

func (c *compositeReadCloser) Close() error {
	var firstErr error
	for i := range c.closers {
		if c.closers[i] == nil {
			continue
		}
		if err := c.closers[i](); err != nil && firstErr == nil {
			firstErr = err
		}
	}
	return firstErr
}

func decodeResponseBody(body io.ReadCloser, contentEncoding string) (io.ReadCloser, error) {
	if body == nil {
		return nil, fmt.Errorf("response body is nil")
	}
	if contentEncoding == "" {
		return body, nil
	}
	encodings := strings.Split(contentEncoding, ",")
	for _, raw := range encodings {
		encoding := strings.TrimSpace(strings.ToLower(raw))
		switch encoding {
		case "", "identity":
			continue
		case "gzip":
			gzipReader, err := gzip.NewReader(body)
			if err != nil {
				_ = body.Close()
				return nil, fmt.Errorf("failed to create gzip reader: %w", err)
			}
			return &compositeReadCloser{
				Reader: gzipReader,
				closers: []func() error{
					gzipReader.Close,
					func() error { return body.Close() },
				},
			}, nil
		case "deflate":
			deflateReader := flate.NewReader(body)
			return &compositeReadCloser{
				Reader: deflateReader,
				closers: []func() error{
					deflateReader.Close,
					func() error { return body.Close() },
				},
			}, nil
		case "br":
			return &compositeReadCloser{
				Reader: brotli.NewReader(body),
				closers: []func() error{
					func() error { return body.Close() },
				},
			}, nil
		case "zstd":
			decoder, err := zstd.NewReader(body)
			if err != nil {
				_ = body.Close()
				return nil, fmt.Errorf("failed to create zstd reader: %w", err)
			}
			return &compositeReadCloser{
				Reader: decoder,
				closers: []func() error{
					func() error { decoder.Close(); return nil },
					func() error { return body.Close() },
				},
			}, nil
		default:
			continue
		}
	}
	return body, nil
}

func applyClaudeHeaders(r *http.Request, auth *cliproxyauth.Auth, apiKey string, stream bool, extraBetas []string) {
	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
	if ginCtx, ok := r.Context().Value("gin").(*gin.Context); ok && ginCtx != nil && ginCtx.Request != nil {
		ginHeaders = ginCtx.Request.Header
	}

	baseBetas := "claude-code-20250219,oauth-2025-04-20,interleaved-thinking-2025-05-14,fine-grained-tool-streaming-2025-05-14"
	if val := strings.TrimSpace(ginHeaders.Get("Anthropic-Beta")); val != "" {
		baseBetas = val
		if !strings.Contains(val, "oauth") {
			baseBetas += ",oauth-2025-04-20"
		}
	}

	// Merge extra betas from request body
	if len(extraBetas) > 0 {
		existingSet := make(map[string]bool)
		for _, b := range strings.Split(baseBetas, ",") {
			existingSet[strings.TrimSpace(b)] = true
		}
		for _, beta := range extraBetas {
			beta = strings.TrimSpace(beta)
			if beta != "" && !existingSet[beta] {
				baseBetas += "," + beta
				existingSet[beta] = true
			}
		}
	}
	r.Header.Set("Anthropic-Beta", baseBetas)

	misc.EnsureHeader(r.Header, ginHeaders, "Anthropic-Version", "2023-06-01")
	misc.EnsureHeader(r.Header, ginHeaders, "Anthropic-Dangerous-Direct-Browser-Access", "true")
	misc.EnsureHeader(r.Header, ginHeaders, "X-App", "cli")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Helper-Method", "stream")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Retry-Count", "0")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Runtime-Version", "v24.3.0")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Package-Version", "0.55.1")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Runtime", "node")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Lang", "js")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Arch", "arm64")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Os", "MacOS")
	misc.EnsureHeader(r.Header, ginHeaders, "X-Stainless-Timeout", "60")
	misc.EnsureHeader(r.Header, ginHeaders, "User-Agent", "claude-cli/1.0.83 (external, cli)")
	r.Header.Set("Connection", "keep-alive")
	r.Header.Set("Accept-Encoding", "gzip, deflate, br, zstd")
	if stream {
		r.Header.Set("Accept", "text/event-stream")
	} else {
		r.Header.Set("Accept", "application/json")
	}
	var attrs map[string]string
	if auth != nil {
		attrs = auth.Attributes
	}
	util.ApplyCustomHeadersFromAttrs(r, attrs)
}

func claudeCreds(a *cliproxyauth.Auth) (apiKey, baseURL string) {
	if a == nil {
		return "", ""
	}
	if a.Attributes != nil {
		apiKey = a.Attributes["api_key"]
		baseURL = a.Attributes["base_url"]
	}
	if apiKey == "" && a.Metadata != nil {
		if v, ok := a.Metadata["access_token"].(string); ok {
			apiKey = v
		}
	}
	return
}

func checkSystemInstructions(payload []byte) []byte {
	system := gjson.GetBytes(payload, "system")
	claudeCodeInstructions := `[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude."}]`
	if system.IsArray() {
		if gjson.GetBytes(payload, "system.0.text").String() != "You are Claude Code, Anthropic's official CLI for Claude." {
			system.ForEach(func(_, part gjson.Result) bool {
				if part.Get("type").String() == "text" {
					claudeCodeInstructions, _ = sjson.SetRaw(claudeCodeInstructions, "-1", part.Raw)
				}
				return true
			})
			payload, _ = sjson.SetRawBytes(payload, "system", []byte(claudeCodeInstructions))
		}
	} else {
		payload, _ = sjson.SetRawBytes(payload, "system", []byte(claudeCodeInstructions))
	}
	return payload
}

func isClaudeOAuthToken(apiKey string) bool {
	return strings.Contains(apiKey, "sk-ant-oat")
}

func applyClaudeToolPrefix(body []byte, prefix string) []byte {
	if prefix == "" {
		return body
	}

	if tools := gjson.GetBytes(body, "tools"); tools.Exists() && tools.IsArray() {
		tools.ForEach(func(index, tool gjson.Result) bool {
			name := tool.Get("name").String()
			if name == "" || strings.HasPrefix(name, prefix) {
				return true
			}
			path := fmt.Sprintf("tools.%d.name", index.Int())
			body, _ = sjson.SetBytes(body, path, prefix+name)
			return true
		})
	}

	if gjson.GetBytes(body, "tool_choice.type").String() == "tool" {
		name := gjson.GetBytes(body, "tool_choice.name").String()
		if name != "" && !strings.HasPrefix(name, prefix) {
			body, _ = sjson.SetBytes(body, "tool_choice.name", prefix+name)
		}
	}

	if messages := gjson.GetBytes(body, "messages"); messages.Exists() && messages.IsArray() {
		messages.ForEach(func(msgIndex, msg gjson.Result) bool {
			content := msg.Get("content")
			if !content.Exists() || !content.IsArray() {
				return true
			}
			content.ForEach(func(contentIndex, part gjson.Result) bool {
				if part.Get("type").String() != "tool_use" {
					return true
				}
				name := part.Get("name").String()
				if name == "" || strings.HasPrefix(name, prefix) {
					return true
				}
				path := fmt.Sprintf("messages.%d.content.%d.name", msgIndex.Int(), contentIndex.Int())
				body, _ = sjson.SetBytes(body, path, prefix+name)
				return true
			})
			return true
		})
	}

	return body
}

func stripClaudeToolPrefixFromResponse(body []byte, prefix string) []byte {
	if prefix == "" {
		return body
	}
	content := gjson.GetBytes(body, "content")
	if !content.Exists() || !content.IsArray() {
		return body
	}
	content.ForEach(func(index, part gjson.Result) bool {
		if part.Get("type").String() != "tool_use" {
			return true
		}
		name := part.Get("name").String()
		if !strings.HasPrefix(name, prefix) {
			return true
		}
		path := fmt.Sprintf("content.%d.name", index.Int())
		body, _ = sjson.SetBytes(body, path, strings.TrimPrefix(name, prefix))
		return true
	})
	return body
}

func stripClaudeToolPrefixFromStreamLine(line []byte, prefix string) []byte {
	if prefix == "" {
		return line
	}
	payload := jsonPayload(line)
	if len(payload) == 0 || !gjson.ValidBytes(payload) {
		return line
	}
	contentBlock := gjson.GetBytes(payload, "content_block")
	if !contentBlock.Exists() || contentBlock.Get("type").String() != "tool_use" {
		return line
	}
	name := contentBlock.Get("name").String()
	if !strings.HasPrefix(name, prefix) {
		return line
	}
	updated, err := sjson.SetBytes(payload, "content_block.name", strings.TrimPrefix(name, prefix))
	if err != nil {
		return line
	}

	trimmed := bytes.TrimSpace(line)
	if bytes.HasPrefix(trimmed, []byte("data:")) {
		return append([]byte("data: "), updated...)
	}
	return updated
}