Commit graph

4 commits

Author SHA1 Message Date
Taylor Mullen
f2f2ecf9d8 feat: Allow cancellation of in-progress Gemini requests and pre-execution checks
- Implements cancellation for Gemini requests while they are actively being processed by the model.
- Extends cancellation support to the  logic within tools. This allows users to cancel operations during the phase where the system is determining if a tool execution requires user confirmation, which can include potentially long-running pre-flight checks or LLM-based corrections.
- Underlying LLM calls for edit corrections (within  and ) and next speaker checks can now also be cancelled.
- Previously, cancellation of the main request was not possible until text started streaming, and pre-execution checks were not cancellable.
- This change leverages the updated SDK's ability to accept an abort token and threads s throughout the request, tool execution, and pre-execution check lifecycle.

Fixes https://github.com/google-gemini/gemini-cli/issues/531
2025-05-27 23:46:37 -07:00
Taylor Mullen
9e1cfca53f Fix(chat): Finalize next speaker detection logic
- Enhance `checkNextSpeaker` to handle cases where the last message is a function response or an empty model message.
- If the last message is a function response, the model should speak next.
- If the last message is an empty model message, the model should speak next.
- This ensures more robust and accurate determination of the next speaker in the conversation, completing the fix for the issue.
- Updated tests.

Fixes https://github.com/google-gemini/gemini-cli/issues/551
2025-05-26 15:21:45 -07:00
Taylor Mullen
480549e02e Refactor(chat): Introduce custom Chat class for future modifications
- Copied the `Chat` class from `@google/genai` into `packages/server/src/core/geminiChat.ts`.
- This change is in preparation for future modifications to the chat handling logic.
- Updated relevant files to use the new `GeminiChat` class.

Part of https://github.com/google-gemini/gemini-cli/issues/551
2025-05-26 14:20:28 -07:00
Taylor Mullen
d159a1507e Don't prematurely end convo w/ Gemini.
- There seems to be a root model bug where the model will preemptively bail on conversations without trying harder. Typically the stops are VERY obvious and bug-looking where you need to prmopt the model to "continue".
- This PR attempts to fix the above by running a 2.0-flash request (don't need somethign more powerful) at the end of every full interaction to see who should speak (user or model).
- Add tests for nextSpeakerChecker

Fixes https://b.corp.google.com/issues/416826051
2025-05-10 14:05:58 -07:00