getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-22 03:03:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix Gemini multimodal tool results causing flaky responses

Browse source 
For Gemini 3, images are now nested inside functionResponse.parts per the docs.
For older models, images are sent in a separate user message.

See: https://ai.google.dev/gemini-api/docs/function-calling#multimodal
This commit is contained in:
Mario Zechner 2025-12-21 02:41:27 +01:00
parent ce950ae96e
commit bf51dd4126
2 changed files with 29 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

4
packages/ai/CHANGELOG.md
View file

@ -1,6 +1,6 @@
# Changelog
## [Unreleased]
## [0.25.1] - 2025-12-21
### Added
@ -8,6 +8,8 @@
### Fixed
- **Gemini multimodal tool results**: Fixed images in tool results causing flaky/broken responses with Gemini models. For Gemini 3, images are now nested inside `functionResponse.parts` per the [docs](https://ai.google.dev/gemini-api/docs/function-calling#multimodal). For older models (which don't support multimodal function responses), images are sent in a separate user message.
- **Queued message steering**: When `getQueuedMessages` is provided, the agent loop now checks for queued user messages after each tool call and skips remaining tool calls in the current assistant message when a queued message arrives (emitting error tool results).
- **Double API version path in Google provider URL**: Fixed Gemini API calls returning 404 after baseUrl support was added. The SDK was appending its default apiVersion to baseUrl which already included the version path. ([#251](https://github.com/badlogic/pi-mono/pull/251) by [@shellfyred](https://github.com/shellfyred))