fix: 协助卡停轮与提交防 409,隐藏配置向导会话,并限制岗位会商产物重复写入

澄清中间件改为 ToolMessage + after_model 停轮,前端提交前取消残留 run;系统/向导 thread_type 从对话列表排除;岗位总结席位加 write_file 上限。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-08-23 20:29:59 +08:00
1 parent 51afebb394
commit b81d200eca
31 files changed
+1459 -592

No files matched your search

@@ -531,6 +531,16 @@ Built-in summary and action-plan completion also preserves a visible report
answer when the model misses its final `write_file` call: the router writes
that exact answer as the required Markdown artifact in the owning thread's
`outputs/` directory, so users receive both chat text and a downloadable file.
**Per-turn outputs write cap (弱模型防重复产物)**: ordinary position-node chats
and the summary builtin send run-context `position_artifact_cap: 1` (whitelisted
in `services.merge_run_context_overrides`). `PositionArtifactCapMiddleware`
then keeps at most one successful `/mnt/user-data/outputs/` `write_file` per
user turn — truncates excess tool calls in the same model response (and syncs
raw provider `additional_kwargs.tool_calls`), rejects further writes after an
`OK` or an earlier sibling in the same batch, ends the turn when only excess
writes remain, and reminds the model to `present_files` / wrap up. **Action-plan
does not send the flag** (it must write report `.md` +
`action-plan-subtasks.json`). Tests: `tests/test_position_artifact_cap.py`.
### 岗位 (Position) Subscription System