bug fix sending component

app/core/llm.py

@@ -23,10 +23,15 @@ from openai import AsyncOpenAI
 import litellm
 
 from langchain_openai import ChatOpenAI
+from langchain_litellm import ChatLiteLLM
 from litellm import get_supported_openai_params  # noqa: F401 – validates install
 
 from app.config.settings import settings
 
+# Some models (e.g. gpt-5, o-series) reject unsupported params like temperature.
+# Drop them silently instead of raising UnsupportedParamsError.
+litellm.drop_params = True
+
 
 def _api_key_for_model(model: str) -> str | None:
     """Return the most appropriate API key for the given LiteLLM model string."""
@@ -48,7 +53,7 @@ def get_llm(
     *,
     model: str | None = None,
     temperature: float = 0,
-) -> ChatOpenAI:
+) -> ChatOpenAI | ChatLiteLLM:
     """Return a LangChain chat model backed by LiteLLM.
 
     LiteLLM exposes an OpenAI-compatible API, so we use ``ChatOpenAI`` pointed
@@ -69,6 +74,11 @@ def get_llm(
     if settings.GITHUB_COPILOT_TOKEN_DIR:
         os.environ.setdefault("GITHUB_COPILOT_TOKEN_DIR", settings.GITHUB_COPILOT_TOKEN_DIR)
 
+    # Use ChatLiteLLM for provider-prefixed models (github_copilot/, anthropic/, etc.)
+    # so LiteLLM handles routing and auth. ChatOpenAI for plain OpenAI model names.
+    if "/" in model:
+        return ChatLiteLLM(model=model, temperature=temperature)
+
     return ChatOpenAI(
         model=model,
         temperature=temperature,
@@ -79,7 +89,7 @@ def get_llm(
 def get_router_llm(
     *,
     temperature: float = 0,
-) -> ChatOpenAI:
+) -> ChatOpenAI | ChatLiteLLM:
     """Return the lighter model used for intent classification / routing."""
     return get_llm(model=settings.LLM_ROUTER_MODEL, temperature=temperature)
 

app/core/orchestrator.py

@@ -162,17 +162,23 @@ async def orchestrate_v3_stream(
     message: str,
     context: dict[str, Any],
     reg: AgentRegistry | None = None,
+    agent_holder: list | None = None,
 ) -> AsyncGenerator[tuple[str, str], None]:
     """v3 streaming orchestration — yields (agent_name, token) pairs.
 
     The first yield always carries the agent_name with an empty token so that
     callers (e.g. FloatingFormatter) can detect the routing domain before any text
     tokens arrive.
+
+    If *agent_holder* is provided (a list), the agent instance is appended so
+    callers can access ``agent.tool_results`` after the stream completes.
     """
     if reg is None:
         reg = _default_registry
     agent_name = await classify_intent(message, context, reg)
     agent = reg.get(agent_name)
+    if agent_holder is not None:
+        agent_holder.append(agent)
     yield agent_name, ""  # domain signal — no token yet
     async for token in agent.handle_stream(message, context):
         yield agent_name, token

app/core/ws_context.py

@@ -84,5 +84,9 @@ async def execute_on_client(
     result = await callback(payload)
     collector = _tool_result_collector.get(None)
     if collector is not None:
-        collector.append(result)
+        collector.append({
+            "action": action,
+            "table": table,
+            "data": result,
+        })
     return result