feat: implement support for thinking blocks in Gemini API and enable thinking by default for supported models

internal/httpapi/claude/deps_injection_test.go

@@ -27,11 +27,32 @@ func TestNormalizeClaudeRequestUsesGlobalAliasMapping(t *testing.T) {
 	if out.Standard.ResolvedModel != "deepseek-v4-pro-search" {
 		t.Fatalf("resolved model mismatch: got=%q", out.Standard.ResolvedModel)
 	}
-	if out.Standard.Thinking || !out.Standard.Search {
+	if !out.Standard.Thinking || !out.Standard.Search {
 		t.Fatalf("unexpected flags: thinking=%v search=%v", out.Standard.Thinking, out.Standard.Search)
 	}
 }
 
+func TestNormalizeClaudeRequestDisablesThinkingWhenRequested(t *testing.T) {
+	req := map[string]any{
+		"model": "claude-opus-4-6",
+		"messages": []any{
+			map[string]any{"role": "user", "content": "hello"},
+		},
+		"thinking": map[string]any{"type": "disabled"},
+	}
+	out, err := normalizeClaudeRequest(mockClaudeConfig{
+		aliases: map[string]string{
+			"claude-opus-4-6": "deepseek-v4-pro",
+		},
+	}, req)
+	if err != nil {
+		t.Fatalf("normalizeClaudeRequest error: %v", err)
+	}
+	if out.Standard.Thinking {
+		t.Fatalf("expected explicit Claude thinking disable to win")
+	}
+}
+
 func TestNormalizeClaudeRequestEnablesThinkingWhenRequested(t *testing.T) {
 	req := map[string]any{
 		"model": "claude-opus-4-6",

internal/httpapi/claude/handler_messages.go

@@ -67,17 +67,12 @@ func (h *Handler) handleClaudeDirect(w http.ResponseWriter, r *http.Request) boo
 		writeClaudeError(w, http.StatusBadRequest, "invalid json")
 		return true
 	}
-	exposeThinking := false
-	if enabled, ok := util.ResolveThinkingOverride(req); ok && enabled {
-		exposeThinking = true
-	} else if _, ok := util.ResolveThinkingOverride(req); !ok && !util.ToBool(req["stream"]) {
-		req["thinking"] = map[string]any{"type": "enabled"}
-	}
 	norm, err := normalizeClaudeRequest(h.Store, req)
 	if err != nil {
 		writeClaudeError(w, http.StatusBadRequest, err.Error())
 		return true
 	}
+	exposeThinking := norm.Standard.Thinking
 	a, err := h.Auth.Determine(r)
 	if err != nil {
 		writeClaudeError(w, http.StatusUnauthorized, err.Error())
@@ -140,7 +135,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, store C
 		}
 	}
 	translatedReq := translatorcliproxy.ToOpenAI(sdktranslator.FormatClaude, translateModel, raw, stream)
-	translatedReq, exposeThinking := applyClaudeThinkingPolicyToOpenAIRequest(translatedReq, req, stream)
+	translatedReq, exposeThinking := applyClaudeThinkingPolicyToOpenAIRequest(translatedReq, req)
 
 	isVercelPrepare := strings.TrimSpace(r.URL.Query().Get("__stream_prepare")) == "1"
 	isVercelRelease := strings.TrimSpace(r.URL.Query().Get("__stream_release")) == "1"
@@ -215,7 +210,7 @@ func (h *Handler) proxyViaOpenAI(w http.ResponseWriter, r *http.Request, store C
 	return true
 }
 
-func applyClaudeThinkingPolicyToOpenAIRequest(translated []byte, original map[string]any, stream bool) ([]byte, bool) {
+func applyClaudeThinkingPolicyToOpenAIRequest(translated []byte, original map[string]any) ([]byte, bool) {
 	req := map[string]any{}
 	if err := json.Unmarshal(translated, &req); err != nil {
 		return translated, false
@@ -225,7 +220,7 @@ func applyClaudeThinkingPolicyToOpenAIRequest(translated []byte, original map[st
 		if _, translatedHasOverride := util.ResolveThinkingOverride(req); translatedHasOverride {
 			return translated, false
 		}
-		enabled = !stream
+		enabled = true
 	}
 	typ := "disabled"
 	if enabled {
@@ -234,9 +229,9 @@ func applyClaudeThinkingPolicyToOpenAIRequest(translated []byte, original map[st
 	req["thinking"] = map[string]any{"type": typ}
 	out, err := json.Marshal(req)
 	if err != nil {
-		return translated, ok && enabled
+		return translated, enabled
 	}
-	return out, ok && enabled
+	return out, enabled
 }
 
 func stripClaudeThinkingBlocks(raw []byte) []byte {

internal/httpapi/claude/proxy_vercel_test.go

@@ -166,7 +166,7 @@ func TestClaudeProxyViaOpenAIEnablesThinkingWhenRequested(t *testing.T) {
 	}
 }
 
-func TestClaudeProxyViaOpenAIKeepsStreamDefaultThinkingDisabled(t *testing.T) {
+func TestClaudeProxyViaOpenAIEnablesStreamThinkingByDefault(t *testing.T) {
 	openAI := &openAIProxyCaptureStub{}
 	h := &Handler{
 		Store:  claudeProxyStoreStub{aliases: map[string]string{"claude-sonnet-4-6": "deepseek-v4-flash"}},
@@ -178,12 +178,12 @@ func TestClaudeProxyViaOpenAIKeepsStreamDefaultThinkingDisabled(t *testing.T) {
 	h.Messages(rec, req)
 
 	thinking, _ := openAI.seenReq["thinking"].(map[string]any)
-	if thinking["type"] != "disabled" {
-		t.Fatalf("expected Claude stream default to keep downstream thinking disabled, got %#v", openAI.seenReq)
+	if thinking["type"] != "enabled" {
+		t.Fatalf("expected Claude stream default to enable downstream thinking, got %#v", openAI.seenReq)
 	}
 }
 
-func TestClaudeProxyViaOpenAIStripsThinkingBlocksFromNonStreamResponse(t *testing.T) {
+func TestClaudeProxyViaOpenAIExposesThinkingBlocksByDefault(t *testing.T) {
 	body := `{"id":"chatcmpl_1","object":"chat.completion","created":1,"model":"claude-sonnet-4-5","choices":[{"index":0,"message":{"role":"assistant","content":null,"reasoning_content":"internal reasoning","tool_calls":[{"id":"call_1","type":"function","function":{"name":"search","arguments":"{\"q\":\"x\"}"}}]},"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":1,"completion_tokens":1,"total_tokens":2}}`
 	h := &Handler{OpenAI: openAIProxyStub{status: 200, body: body}}
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", strings.NewReader(`{"model":"claude-sonnet-4-5","messages":[{"role":"user","content":"hi"}],"stream":false}`))
@@ -195,14 +195,31 @@ func TestClaudeProxyViaOpenAIStripsThinkingBlocksFromNonStreamResponse(t *testin
 		t.Fatalf("unexpected status: %d body=%s", rec.Code, rec.Body.String())
 	}
 	got := rec.Body.String()
-	if strings.Contains(got, `"type":"thinking"`) {
-		t.Fatalf("expected converted Claude response to strip thinking block, got %s", got)
+	if !strings.Contains(got, `"type":"thinking"`) {
+		t.Fatalf("expected converted Claude response to expose thinking block, got %s", got)
 	}
 	if !strings.Contains(got, `"tool_use"`) {
 		t.Fatalf("expected converted Claude response to preserve tool_use, got %s", got)
 	}
 }
 
+func TestClaudeProxyViaOpenAIStripsThinkingBlocksWhenDisabled(t *testing.T) {
+	body := `{"id":"chatcmpl_1","object":"chat.completion","created":1,"model":"claude-sonnet-4-5","choices":[{"index":0,"message":{"role":"assistant","content":"ok","reasoning_content":"internal reasoning"},"finish_reason":"stop"}],"usage":{"prompt_tokens":1,"completion_tokens":1,"total_tokens":2}}`
+	h := &Handler{OpenAI: openAIProxyStub{status: 200, body: body}}
+	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", strings.NewReader(`{"model":"claude-sonnet-4-5","messages":[{"role":"user","content":"hi"}],"thinking":{"type":"disabled"},"stream":false}`))
+	rec := httptest.NewRecorder()
+
+	h.Messages(rec, req)
+
+	if rec.Code != http.StatusOK {
+		t.Fatalf("unexpected status: %d body=%s", rec.Code, rec.Body.String())
+	}
+	got := rec.Body.String()
+	if strings.Contains(got, `"type":"thinking"`) {
+		t.Fatalf("expected disabled thinking to strip thinking block, got %s", got)
+	}
+}
+
 func TestClaudeProxyTranslatesInlineImageToOpenAIDataURL(t *testing.T) {
 	openAI := &openAIProxyCaptureStub{}
 	h := &Handler{OpenAI: openAI}

internal/httpapi/claude/standard_request.go

@@ -32,11 +32,11 @@ func normalizeClaudeRequest(store ConfigReader, req map[string]any) (claudeNorma
 
 	dsPayload := convertClaudeToDeepSeek(payload, store)
 	dsModel, _ := dsPayload["model"].(string)
-	_, searchEnabled, ok := config.GetModelConfig(dsModel)
+	defaultThinkingEnabled, searchEnabled, ok := config.GetModelConfig(dsModel)
 	if !ok {
 		searchEnabled = false
 	}
-	thinkingEnabled := util.ResolveThinkingEnabled(req, false)
+	thinkingEnabled := util.ResolveThinkingEnabled(req, defaultThinkingEnabled)
 	if config.IsNoThinkingModel(dsModel) {
 		thinkingEnabled = false
 	}

internal/httpapi/gemini/handler_generate.go

@@ -343,8 +343,17 @@ func buildGeminiGenerateContentResponseFromTurn(turn assistantturn.Turn) map[str
 }
 
 func buildGeminiPartsFromTurn(turn assistantturn.Turn) []map[string]any {
+	thinkingPart := func() []map[string]any {
+		if turn.Thinking == "" {
+			return nil
+		}
+		return []map[string]any{{"text": turn.Thinking, "thought": true}}
+	}
 	if len(turn.ToolCalls) > 0 {
-		parts := make([]map[string]any, 0, len(turn.ToolCalls))
+		parts := thinkingPart()
+		if parts == nil {
+			parts = make([]map[string]any, 0, len(turn.ToolCalls))
+		}
 		for _, tc := range turn.ToolCalls {
 			parts = append(parts, map[string]any{
 				"functionCall": map[string]any{
@@ -355,11 +364,14 @@ func buildGeminiPartsFromTurn(turn assistantturn.Turn) []map[string]any {
 		}
 		return parts
 	}
-	text := turn.Text
-	if text == "" {
-		text = turn.Thinking
+	parts := thinkingPart()
+	if turn.Text != "" {
+		parts = append(parts, map[string]any{"text": turn.Text})
 	}
-	return []map[string]any{{"text": text}}
+	if len(parts) == 0 {
+		parts = append(parts, map[string]any{"text": ""})
+	}
+	return parts
 }
 
 //nolint:unused // retained for native Gemini non-stream handling path.
@@ -380,8 +392,17 @@ func buildGeminiPartsFromFinal(finalText, finalThinking string, toolNames []stri
 	if len(detected) == 0 && finalThinking != "" {
 		detected = toolcall.ParseToolCalls(finalThinking, toolNames)
 	}
+	thinkingPart := func() []map[string]any {
+		if finalThinking == "" {
+			return nil
+		}
+		return []map[string]any{{"text": finalThinking, "thought": true}}
+	}
 	if len(detected) > 0 {
-		parts := make([]map[string]any, 0, len(detected))
+		parts := thinkingPart()
+		if parts == nil {
+			parts = make([]map[string]any, 0, len(detected))
+		}
 		for _, tc := range detected {
 			parts = append(parts, map[string]any{
 				"functionCall": map[string]any{
@@ -393,9 +414,12 @@ func buildGeminiPartsFromFinal(finalText, finalThinking string, toolNames []stri
 		return parts
 	}
 
-	text := finalText
-	if text == "" {
-		text = finalThinking
+	parts := thinkingPart()
+	if finalText != "" {
+		parts = append(parts, map[string]any{"text": finalText})
 	}
-	return []map[string]any{{"text": text}}
+	if len(parts) == 0 {
+		parts = append(parts, map[string]any{"text": ""})
+	}
+	return parts
 }

internal/httpapi/gemini/handler_stream_runtime.go

@@ -134,6 +134,21 @@ func (s *geminiStreamRuntime) onParsed(parsed sse.LineResult) streamengine.Parse
 	accumulated := s.accumulator.Apply(parsed)
 	for _, p := range accumulated.Parts {
 		if p.Type == "thinking" {
+			if p.VisibleText == "" || s.bufferContent {
+				continue
+			}
+			s.sendChunk(map[string]any{
+				"candidates": []map[string]any{
+					{
+						"index": 0,
+						"content": map[string]any{
+							"role":  "model",
+							"parts": []map[string]any{{"text": p.VisibleText, "thought": true}},
+						},
+					},
+				},
+				"modelVersion": s.model,
+			})
 			continue
 		}
 		if p.RawText == "" || p.CitationOnly || p.VisibleText == "" {

internal/httpapi/gemini/handler_test.go

@@ -257,6 +257,56 @@ func TestStreamGenerateContentEmitsSSE(t *testing.T) {
 	}
 }
 
+func TestNativeStreamGenerateContentEmitsThoughtParts(t *testing.T) {
+	h := &Handler{}
+	resp := makeGeminiUpstreamResponse(
+		`data: {"p":"response/thinking_content","v":"think"}`,
+		`data: {"p":"response/content","v":"answer"}`,
+		`data: [DONE]`,
+	)
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequest(http.MethodPost, "/v1beta/models/gemini-2.5-pro:streamGenerateContent", nil)
+
+	h.handleStreamGenerateContent(rec, req, resp, "gemini-2.5-pro", "prompt", true, false, nil, nil)
+
+	frames := extractGeminiSSEFrames(t, rec.Body.String())
+	if len(frames) < 2 {
+		t.Fatalf("expected thought and text stream frames, body=%s", rec.Body.String())
+	}
+	var gotThought, gotText string
+	for _, frame := range frames {
+		for _, part := range geminiPartsFromFrame(frame) {
+			if part["thought"] == true {
+				gotThought += asString(part["text"])
+			} else {
+				gotText += asString(part["text"])
+			}
+		}
+	}
+	if gotThought != "think" {
+		t.Fatalf("expected thought part, got %q body=%s", gotThought, rec.Body.String())
+	}
+	if !strings.Contains(gotText, "answer") {
+		t.Fatalf("expected text part answer, got %q body=%s", gotText, rec.Body.String())
+	}
+}
+
+func TestBuildGeminiPartsFromFinalIncludesThoughtPart(t *testing.T) {
+	parts := buildGeminiPartsFromFinal("answer", "think", nil)
+	if len(parts) != 2 {
+		t.Fatalf("expected thought + answer parts, got %#v", parts)
+	}
+	if parts[0]["thought"] != true || parts[0]["text"] != "think" {
+		t.Fatalf("expected first part to be thought, got %#v", parts[0])
+	}
+	if _, ok := parts[1]["thought"]; ok {
+		t.Fatalf("expected second part to be visible text, got %#v", parts[1])
+	}
+	if parts[1]["text"] != "answer" {
+		t.Fatalf("expected answer text, got %#v", parts[1])
+	}
+}
+
 func TestGeminiProxyTranslatesInlineImageToOpenAIDataURL(t *testing.T) {
 	openAI := &geminiOpenAISuccessStub{}
 	h := &Handler{Store: testGeminiConfig{}, OpenAI: openAI}
@@ -396,3 +446,21 @@ func extractGeminiSSEFrames(t *testing.T, body string) []map[string]any {
 	}
 	return out
 }
+
+func geminiPartsFromFrame(frame map[string]any) []map[string]any {
+	candidates, _ := frame["candidates"].([]any)
+	if len(candidates) == 0 {
+		return nil
+	}
+	c0, _ := candidates[0].(map[string]any)
+	content, _ := c0["content"].(map[string]any)
+	rawParts, _ := content["parts"].([]any)
+	parts := make([]map[string]any, 0, len(rawParts))
+	for _, raw := range rawParts {
+		part, _ := raw.(map[string]any)
+		if part != nil {
+			parts = append(parts, part)
+		}
+	}
+	return parts
+}