alanhuangyoo 23cc4f4d00

fix(agents): close delegations a stopped run left in progress (#5507) ...

* fix(agents): close delegations a stopped run left in progress

Every task call is recorded in the delegation ledger as in_progress and
only moves on when its ToolMessage arrives. When the user stops a run
while a subagent is running, the task tool re-raises the cancellation
and no ToolMessage is written, so the entry stayed in_progress for the
rest of the thread and every later model call was told "already
delegated; do NOT delegate again; wait for or build on the result".

When a run starts with a new user message, mark entries that an earlier
run left in_progress and that have no ToolMessage as cancelled. Resumed
runs, which have no new user message, keep the current behaviour.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* refactor(agents): share the run-opening boundary between capture and closure

Also pin that in_progress entries without a run_id are never closed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* test(agents): clarify legacy delegation reply handling

---------

Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-09-19 10:40:22 +08:00

..

deerflow

fix(agents): close delegations a stopped run left in progress (#5507)

2026-09-19 10:40:22 +08:00

pyproject.toml

feat(extensions): expose incremental run evidence reader (#5405)

2026-09-16 21:18:05 +08:00