fix(ai_client): Add missing response_received events for gemini streaming and non-streaming paths

project_history.toml

@@ -8,5 +8,5 @@ active = "main"
 
 [discussions.main]
 git_commit = ""
-last_updated = "2026-03-05T19:00:38"
+last_updated = "2026-03-05T19:13:27"
 history = []

src/ai_client.py

@@ -712,6 +712,7 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str,
     txt = "".join(txt_chunks)
     # Final validation of response object for subsequent code
     resp = final_resp 
+    events.emit("response_received", payload={"provider": "gemini", "model": _model, "usage": usage, "round": r_idx})
    else:
     config = types.GenerateContentConfig(
      tools=[types.Tool(function_declarations=[types.FunctionDeclaration(**s) for s in mcp_client.get_tool_schemas()])] if enable_tools else [],
@@ -728,6 +729,7 @@ def _send_gemini(md_content: str, user_message: str, base_dir: str,
      "cache_read_input_tokens": getattr(resp.usage_metadata, "cached_content_token_count", 0)
     }
     reason = resp.candidates[0].finish_reason.name if (resp.candidates and hasattr(resp.candidates[0], "finish_reason")) else "STOP"
+   events.emit("response_received", payload={"provider": "gemini", "model": _model, "usage": usage, "round": r_idx})
 
    _append_comms("IN", "response", {"round": r_idx, "stop_reason": reason, "text": txt, "tool_calls": [{"name": c.name, "args": dict(c.args)} for c in calls], "usage": usage})
    total_in = usage.get("input_tokens", 0)

tests/test_api_events.py

@@ -60,7 +60,7 @@ def test_send_emits_events_proper() -> None:
         ai_client.events.on("request_start", start_callback)
         ai_client.events.on("response_received", response_callback)
         ai_client.set_provider("gemini", "gemini-2.5-flash-lite")
-        ai_client.send("context", "message", stream_callback=lambda x: None)
+        ai_client.send("context", "message", )
         assert start_callback.called
         assert response_callback.called
         args, kwargs = start_callback.call_args