When using thinking-enabled models (like Kimi K2.5, DeepSeek), the API expects reasoning_content on all assistant messages. The original ChatDeepSeek stores reasoning_content in additional_kwargs but doesn't include it when making subsequent API calls, causing "reasoning_content is missing" errors. This adds PatchedChatDeepSeek which overrides _get_request_payload to restore reasoning_content from additional_kwargs into the payload. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| .vscode | ||
| docs | ||
| src | ||
| tests | ||
| .gitignore | ||
| .python-version | ||
| AGENTS.md | ||
| CLAUDE.md | ||
| Dockerfile | ||
| Makefile | ||
| debug.py | ||
| langgraph.json | ||
| pyproject.toml | ||
| ruff.toml | ||
| uv.lock | ||