holetron-lab/fleet-memory
1
0
Fork 0
Code Releases Packages Activity Actions
fleet-memory/hindsight-api-slim/hindsight_api/engine/providers
History
Nicolò Boschi 21f9f46ca3
fix: support gemini-3.1-flash-lite-preview by preserving thought_signature in tool calls (#568) 
Gemini 3.1+ thinking models include a thought_signature field in functionCall
parts. When reconstructing conversation history for subsequent turns, this
signature must be preserved or the API returns 400 INVALID_ARGUMENT.

- Add optional thought_signature field to LLMToolCall
- Capture thought_signature from Gemini response parts
- Pass thought_signature back when reconstructing multi-turn history
- Add gemini-3.1-flash-lite-preview to the LLM provider test matrix
2026-03-13 16:43:01 +01:00
..
__init__.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
anthropic_llm.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
claude_code_llm.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
codex_llm.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
gemini_llm.py fix: support gemini-3.1-flash-lite-preview by preserving thought_signature in tool calls (#568) 2026-03-13 16:43:01 +01:00
mock_llm.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00
openai_compatible_llm.py feat: introduce hindsight-api-slim and hindsight-all-slim packages (#560) 2026-03-13 13:50:03 +01:00