deer-flow

mirror of https://gitee.com/wanwujie/deer-flow synced 2026-04-03 22:32:12 +08:00

Files

大猫子 423f5c829c fix: strip <think> tags from reporter output to prevent thinking text leakage (#781 ) (#862 )

* fix: strip <think> tags from LLM output to prevent thinking text leakage (#781)

Some models (e.g. DeepSeek-R1, QwQ via ollama) embed reasoning in
content using <think>...</think> tags instead of the separate
reasoning_content field. This causes thinking text to leak into
both streamed messages and the final report.

Fix at two layers:
- server/app.py: strip <think> tags in _create_event_stream_message
  so ALL streamed content is filtered (coordinator, planner, etc.)
- graph/nodes.py: strip <think> tags in reporter_node before storing
  final_report (which is not streamed through the event layer)

The regex uses a fast-path check ("<think>" in content) to avoid
unnecessary regex calls on normal content.

* refactor: add defensive check for think tag stripping and add reporter_node tests (#781)

- Add isinstance and fast-path check in reporter_node before regex, consistent with app.py
- Add TestReporterNodeThinkTagStripping with 5 test cases covering various scenarios

* chore: re-trigger review

2026-02-16 09:38:17 +08:00

test_app.py

fix: strip <think> tags from reporter output to prevent thinking text leakage (#781 ) (#862 )

2026-02-16 09:38:17 +08:00

test_chat_request.py

feat(server): add MCP server configuration validation (#830 )

2026-01-24 17:32:17 +08:00

test_mcp_request.py

fix(config): Add support for MCP server configuration parameters (#812 )

2026-01-10 15:59:49 +08:00

test_mcp_utils.py

feat(server): add MCP server configuration validation (#830 )