fix(copilot): Use correct OpenRouter reasoning API format

Addresses review comments from CodeRabbit and Sentry:

- Change reasoning format from {"enabled": True} (invalid) to
  {"max_tokens": config.thinking_budget_tokens} per OpenRouter docs
- Add missing thinking_budget_tokens config field (default: 10000)
- Extract duplicate code into _apply_thinking_config() helper function
- Update description from 'adaptive' to 'extended' thinking for clarity

References:
- OpenRouter reasoning docs: https://openrouter.ai/docs/reasoning-tokens

autogpt_platform/backend/backend/api/features/chat/config.py

@@ -93,6 +93,18 @@ class ChatConfig(BaseSettings):
         description="Name of the prompt in Langfuse to fetch",
     )
 
+    # Extended thinking configuration for Claude models
+    thinking_enabled: bool = Field(
+        default=True,
+        description="Enable extended thinking for Claude models via OpenRouter",
+    )
+    thinking_budget_tokens: int = Field(
+        default=10000,
+        ge=1000,
+        le=100000,
+        description="Maximum tokens for extended thinking (budget_tokens for Claude)",
+    )
+
     @field_validator("api_key", mode="before")
     @classmethod
     def get_api_key(cls, v):

autogpt_platform/backend/backend/api/features/chat/service.py

@@ -80,6 +80,19 @@ settings = Settings()
 client = openai.AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
 
 
+def _apply_thinking_config(extra_body: dict[str, Any], model: str) -> None:
+    """Apply extended thinking configuration for Anthropic models via OpenRouter.
+
+    OpenRouter's reasoning API expects either:
+    - {"max_tokens": N} for explicit token budget
+    - {"effort": "high"} for automatic budget
+
+    See: https://openrouter.ai/docs/reasoning-tokens
+    """
+    if config.thinking_enabled and "anthropic" in model.lower():
+        extra_body["reasoning"] = {"max_tokens": config.thinking_budget_tokens}
+
+
 langfuse = get_client()
 
 # Redis key prefix for tracking running long-running operations
@@ -1066,6 +1079,9 @@ async def _stream_chat_chunks(
                         :128
                     ]  # OpenRouter limit
 
+                # Enable extended thinking for Anthropic models via OpenRouter
+                _apply_thinking_config(extra_body, model)
+
                 api_call_start = time_module.perf_counter()
                 stream = await client.chat.completions.create(
                     model=model,
@@ -1829,6 +1845,9 @@ async def _generate_llm_continuation(
         if session_id:
             extra_body["session_id"] = session_id[:128]
 
+        # Enable extended thinking for Anthropic models via OpenRouter
+        _apply_thinking_config(extra_body, config.model)
+
         retry_count = 0
         last_error: Exception | None = None
         response = None
@@ -1959,6 +1978,9 @@ async def _generate_llm_continuation_with_streaming(
         if session_id:
             extra_body["session_id"] = session_id[:128]
 
+        # Enable extended thinking for Anthropic models via OpenRouter
+        _apply_thinking_config(extra_body, config.model)
+
         # Make streaming LLM call (no tools - just text response)
         from typing import cast