wanwu/deer-flow
1
0
Fork 0
mirror of https://gitee.com/wanwujie/deer-flow synced 2026-04-03 06:12:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(LLM): fixing Gemini thinking + tool calls via OpenAI gateway (#1180) (#1205)

Browse Source 
* fix(LLM): fixing Gemini thinking + tool calls via OpenAI gateway (#1180)

When using Gemini with thinking enabled through an OpenAI-compatible gateway,
the API requires that  fields on thinking content blocks are
preserved and echoed back verbatim in subsequent requests. Standard
 silently drops these signatures when serializing
messages, causing HTTP 400 errors:

Changes:
- Add PatchedChatOpenAI adapter that re-injects signed thinking blocks into
  request payloads, preserving the signature chain across multi-turn
  conversations with tool calls.
- Support two LangChain storage patterns: additional_kwargs.thinking_blocks
  and content list.
- Add 11 unit tests covering signed/unsigned blocks, storage patterns, edge
  cases, and precedence rules.
- Update config.example.yaml with Gemini + thinking gateway example.
- Update CONFIGURATION.md with detailed guidance and error explanation.

Fixes: #1180

* Updated the patched_openai.py with thought_signature of function call

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* docs: fix inaccurate thought_signature description in CONFIGURATION.md (#1220)

* Initial plan

* docs: fix CONFIGURATION.md wording for thought_signature - tool-call objects, not thinking blocks

Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>
Agent-Logs-Url: https://github.com/bytedance/deer-flow/sessions/360f5226-4631-48a7-a050-189094af8ffe

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: WillemJiang <219644+WillemJiang@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
This commit is contained in:
Willem Jiang
2026-03-26 15:07:05 +08:00
committed by GitHub
parent 080a03f3bc
commit a087fe7bcc
4 changed files with 360 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
backend/docs/CONFIGURATION.md
View File

@@ -136,6 +136,36 @@ models:
type: enabled
```
**Gemini with thinking via OpenAI-compatible gateway**:
When routing Gemini through an OpenAI-compatible proxy (Vertex AI OpenAI compat endpoint, AI Studio, or third-party gateways) with thinking enabled, the API attaches a `thought_signature` to each tool-call object returned in the response. Every subsequent request that replays those assistant messages **must** echo those signatures back on the tool-call entries or the API returns:
```
HTTP 400 INVALID_ARGUMENT: function call `<tool>` in the N. content block is
missing a `thought_signature`.
```
Standard `langchain_openai:ChatOpenAI` silently drops `thought_signature` when serialising messages. Use `deerflow.models.patched_openai:PatchedChatOpenAI` instead — it re-injects the tool-call signatures (sourced from `AIMessage.additional_kwargs["tool_calls"]`) into every outgoing payload:
```yaml
models:
- name: gemini-2.5-pro-thinking
display_name: Gemini 2.5 Pro (Thinking)
use: deerflow.models.patched_openai:PatchedChatOpenAI
model: google/gemini-2.5-pro-preview # model name as expected by your gateway
api_key: $GEMINI_API_KEY
base_url: https://<your-openai-compat-gateway>/v1
max_tokens: 16384
supports_thinking: true
supports_vision: true
when_thinking_enabled:
extra_body:
thinking:
type: enabled
```
For Gemini accessed **without** thinking (e.g. via OpenRouter where thinking is not activated), the plain `langchain_openai:ChatOpenAI` with `supports_thinking: false` is sufficient and no patch is needed.
### Tool Groups
Organize tools into logical groups: