增强 Deep Research 可靠性,并接入 8BF 任务卡片与会商上下文。

修复 MySQL 读写分离下的持久化与 SSE 重连问题,报告完成前先落库;8BF 嵌入页支持 taskId 任务卡与独立意图 metadata;前端统一 createClientId 并更新 runtime 配置。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-08-17 18:16:05 +08:00
1 parent 47faa9bcdf
commit 771957429a
36 files changed
+2038 -300

No files matched your search

@@ -1147,6 +1147,10 @@ Automatic conversation summarization when approaching token limits:
the config flag. `config.summarization.enabled` now defaults to **false**.
- `config.yaml` `summarization` still supplies the **tuning**: trigger types
(tokens, messages, or fraction of max input) and the keep policy.
- A compressed request must retain the latest non-empty `HumanMessage`, even
when it has already been folded into the hidden summary. This keeps strict
OpenAI-compatible gateways from rejecting a tool-continuation call with
`No user query found in message`.
- Keeps recent messages while summarizing older ones.
Tests: `tests/test_summarization_toggle.py` (gating + whitelist),
@@ -1284,6 +1288,31 @@ The per-user Deep Research concurrency guard counts only session statuses
consume a slot; otherwise saved drafts make `POST /sessions/{id}/jobs` return
429 permanently. Regression: `test_saved_draft_sessions_do_not_consume_research_concurrency`.
`POST /api/deep-research/sessions/{id}/jobs` is retry-safe under MySQL
read/write splitting. Deep Research session/job/event/source/message writes
must serialise their changed row while the write transaction is still open
(`flush` for inserts, select-after-update **before** commit), never through a
post-commit `session.refresh()` or a fresh pooled read. Replica lag otherwise
turns a committed job into a misleading 500, can make dispatcher `claim_job()`
lose its snapshot, or can fail report/follow-up persistence after the model has
already completed. Always nudge the dispatcher for both a newly created job and
an idempotently reused queued job; otherwise a retry after such an interrupted
response returns the old job but leaves it waiting for the periodic scan. The
SSE replay generator must catch temporary event/job-store reads, emit a
recoverable warning, and keep the connection open so the next poll can repair
the cursor instead of surfacing an ASGI `ExceptionGroup`. Regressions:
`test_deep_research_writes_never_depend_on_post_commit_refresh`,
`test_job_create_never_reads_back_after_commit`,
`test_retry_of_existing_queued_job_nudges_dispatcher`, and
`test_stream_stays_open_when_durable_replay_has_a_transient_failure`.
At ordinary report completion, persist and confirm the session's
`report_markdown` projection **before** marking the Job `completed`. Retry a
short transient projection failure; if it cannot be confirmed, let the job
become failed rather than reporting a report that vanishes on refresh.
`test_report_is_persisted_before_job_is_marked_completed` and
`test_report_projection_failure_never_marks_job_completed` cover the ordering.
The chat-collection frontend must keep report-writing progress in the existing
workspace `MessageList` / `MessageGroup` tool-step renderer: inject only
virtual `deep_research_progress` tool calls for the durable phases, keep the