refactor(runtime): move Anthropic-Beta header setting to applyClaudeHeaders for better header management

- Added `response.output_item.done` event emission in OpenAI responses.
- Enhanced reasoning output finalization with additional response event for improved tracking.

config.example.yaml

@@ -24,10 +24,10 @@ api-keys:
 debug: false
 
 # When true, write application logs to rotating files instead of stdout
-logging-to-file: true
+logging-to-file: false
 
 # When false, disable in-memory usage statistics aggregation
-usage-statistics-enabled: true
+usage-statistics-enabled: false
 
 # Proxy URL. Supports socks5/http/https protocols. Example: socks5://user:pass@192.168.1.1:1080/
 proxy-url: ""
@@ -41,48 +41,48 @@ quota-exceeded:
   switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded
 
 # API keys for official Generative Language API
-generative-language-api-key:
-  - "AIzaSy...01"
-  - "AIzaSy...02"
-  - "AIzaSy...03"
-  - "AIzaSy...04"
+#generative-language-api-key:
+#  - "AIzaSy...01"
+#  - "AIzaSy...02"
+#  - "AIzaSy...03"
+#  - "AIzaSy...04"
 
 # Codex API keys
-codex-api-key:
-  - api-key: "sk-atSM..."
-    base-url: "https://www.example.com" # use the custom codex API endpoint
+#codex-api-key:
+#  - api-key: "sk-atSM..."
+#    base-url: "https://www.example.com" # use the custom codex API endpoint
 
 # Claude API keys
-claude-api-key:
-  - api-key: "sk-atSM..." # use the official claude API key, no need to set the base url
-  - api-key: "sk-atSM..."
-    base-url: "https://www.example.com" # use the custom claude API endpoint
+#claude-api-key:
+#  - api-key: "sk-atSM..." # use the official claude API key, no need to set the base url
+#  - api-key: "sk-atSM..."
+#    base-url: "https://www.example.com" # use the custom claude API endpoint
 
 # OpenAI compatibility providers
-openai-compatibility:
-  - name: "openrouter" # The name of the provider; it will be used in the user agent and other places.
-    base-url: "https://openrouter.ai/api/v1" # The base URL of the provider.
-    api-keys: # The API keys for the provider. Add multiple keys if needed. Omit if unauthenticated access is allowed.
-      - "sk-or-v1-...b780"
-      - "sk-or-v1-...b781"
-    models: # The models supported by the provider.
-      - name: "moonshotai/kimi-k2:free" # The actual model name.
-        alias: "kimi-k2" # The alias used in the API.
+#openai-compatibility:
+#  - name: "openrouter" # The name of the provider; it will be used in the user agent and other places.
+#    base-url: "https://openrouter.ai/api/v1" # The base URL of the provider.
+#    api-keys: # The API keys for the provider. Add multiple keys if needed. Omit if unauthenticated access is allowed.
+#      - "sk-or-v1-...b780"
+#      - "sk-or-v1-...b781"
+#    models: # The models supported by the provider.
+#      - name: "moonshotai/kimi-k2:free" # The actual model name.
+#        alias: "kimi-k2" # The alias used in the API.
 
 # Gemini Web settings
-gemini-web:
-    # Conversation reuse: set to true to enable (default), false to disable.
-    context: true
-    # Maximum characters per single request to Gemini Web. Requests exceeding this
-    # size split into chunks. Only the last chunk carries files and yields the final answer.
-    max-chars-per-request: 1000000
-    # Disable the short continuation hint appended to intermediate chunks
-    # when splitting long prompts. Default is false (hint enabled by default).
-    disable-continuation-hint: false
-    # Code mode:
-    #   - true: enable XML wrapping hint and attach the coding-partner Gem.
-    #           Thought merging (<think> into visible content) applies to STREAMING only;
-    #           non-stream responses keep reasoning/thought parts separate for clients
-    #           that expect explicit reasoning fields.
-    #   - false: disable XML hint and keep <think> separate
-    code-mode: false
+#gemini-web:
+#    # Conversation reuse: set to true to enable (default), false to disable.
+#    context: true
+#    # Maximum characters per single request to Gemini Web. Requests exceeding this
+#    # size split into chunks. Only the last chunk carries files and yields the final answer.
+#    max-chars-per-request: 1000000
+#    # Disable the short continuation hint appended to intermediate chunks
+#    # when splitting long prompts. Default is false (hint enabled by default).
+#    disable-continuation-hint: false
+#    # Code mode:
+#    #   - true: enable XML wrapping hint and attach the coding-partner Gem.
+#    #           Thought merging (<think> into visible content) applies to STREAMING only;
+#    #           non-stream responses keep reasoning/thought parts separate for clients
+#    #           that expect explicit reasoning fields.
+#    #   - false: disable XML hint and keep <think> separate
+#    code-mode: false

internal/runtime/executor/claude_executor.go

@@ -284,6 +284,7 @@ func hasZSTDEcoding(contentEncoding string) bool {
 func applyClaudeHeaders(r *http.Request, apiKey string, stream bool) {
 	r.Header.Set("Authorization", "Bearer "+apiKey)
 	r.Header.Set("Content-Type", "application/json")
+	r.Header.Set("Anthropic-Beta", "claude-code-20250219,oauth-2025-04-20,interleaved-thinking-2025-05-14,fine-grained-tool-streaming-2025-05-14")
 
 	var ginHeaders http.Header
 	if ginCtx, ok := r.Context().Value("gin").(*gin.Context); ok && ginCtx != nil && ginCtx.Request != nil {
@@ -292,7 +293,6 @@ func applyClaudeHeaders(r *http.Request, apiKey string, stream bool) {
 
 	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, "Anthropic-Beta", "claude-code-20250219,oauth-2025-04-20,interleaved-thinking-2025-05-14,fine-grained-tool-streaming-2025-05-14")
 	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")

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

@@ -78,12 +78,21 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
 		textDone, _ = sjson.Set(textDone, "output_index", st.ReasoningIndex)
 		textDone, _ = sjson.Set(textDone, "text", full)
 		out = append(out, emitEvent("response.reasoning_summary_text.done", textDone))
+
 		partDone := `{"type":"response.reasoning_summary_part.done","sequence_number":0,"item_id":"","output_index":0,"summary_index":0,"part":{"type":"summary_text","text":""}}`
 		partDone, _ = sjson.Set(partDone, "sequence_number", nextSeq())
 		partDone, _ = sjson.Set(partDone, "item_id", st.ReasoningItemID)
 		partDone, _ = sjson.Set(partDone, "output_index", st.ReasoningIndex)
 		partDone, _ = sjson.Set(partDone, "part.text", full)
 		out = append(out, emitEvent("response.reasoning_summary_part.done", partDone))
+
+		itemDone := `{"type":"response.output_item.done","sequence_number":0,"output_index":0,"item":{"id":"","type":"reasoning","encrypted_content":"","summary":[{"type":"summary_text","text":""}]}}`
+		itemDone, _ = sjson.Set(itemDone, "sequence_number", nextSeq())
+		itemDone, _ = sjson.Set(itemDone, "item.id", st.ReasoningItemID)
+		itemDone, _ = sjson.Set(itemDone, "output_index", st.ReasoningIndex)
+		itemDone, _ = sjson.Set(itemDone, "item.summary.0.text", full)
+		out = append(out, emitEvent("response.output_item.done", itemDone))
+
 		st.ReasoningClosed = true
 	}