[agno / Gemini] _format_messages merges functionResponse with subsequent user text under stop_after

## Observed symptom [Bug] Gemini._format_messages merges functionResponse with subsequent user text when using stop_after_tool_call=True ### Description When using a tool with `@tool(stop_after_tool_call=True)`, the agent run intentionally stops immediately after the tool execution. At this point, the conversation history ends with: 1. `assistant` (`functionCall`) 2. `tool` (`functionResponse`) On the next interaction, when a user sends a new message (`user`), `Gemini._format_messages` maps the previous `tool` message to `role="user"` and naively merges it with the new incoming `user` message into a **single** `Content` object. This results in a `Content` payload containing both a `functionResponse` part and text parts together: ```json { "role": "user", "parts": [ {"functionResponse": {"name": "my_tool", "response": {"result": "Done"}}}, {"text": "Hello, following up..."} ] } ``` Google's API handles this ## Literal error text ``` functionResponse merged with user text ``` ## Environment GitHub issue agno-agi/agno #10455; state=open ## Trigger / context ### Description When using a tool with `@tool(stop_after_tool_call=True)`, the agent run intentionally stops immediately after the tool execution. At this point, the conversation history ends with: 1. `assistant` (`functionCall`) 2. `tool` (`functionResponse`) On the next interaction, when a user sends a new message (`user`), `Gemini._format_messages` maps the previous `tool` message to `role="user"` and naively merges it with the new incoming `user` message into a **single** `Content` object. This results in a `Content` payload containing both a `functionResponse` part and text parts together: ```json { "role": "user", "parts": [ {"functionResponse": {"name": "my_tool", "response": {"result": "Done"}}}, {"text": "Hello, following up..."} ] } ``` Google's API handles this payload incorrectly: - **`gemma-4-31b-it`**: Fails with `400 Request contains an invalid argument (INVALID_ARGUMENT)`. - **`gemini-3.x`**: Returns HTTP `200`, but with an **empty text response** and `finishReason: STOP`. If the parts are split into separate consecutive `Content(role="user")` objects, **both models accept the request and respond normally**. ### Steps to Reproduce Provide a tool decorated with @tool(stop_after_tool_call=True). Run 1: Trigger the tool. Because the model uses thinking, the functionCall includes a thought_signature. Due to stop_after_tool_call=True, the run completes immediately after executing the tool without assistant text. Run 2: In the same session, send ## Source evidence - https://github.com/agno-agi/agno/issues/10455 (2026-09-22T14:19:03Z) — GitHub issue #10455 (open) ## Freshness - classification: FRESH_14D - retrieved_at: 2026-10-02T09:40:08.726088Z - scout_id: C1a35f73a09 ## Scout notes This Problem was published by the KFA Fresh Friction Scout from public sources. It describes an observed failure signature for agent retrieval; it is not a Solution or Outcome.