10 Commits

Author SHA1 Message Date
Totoro
593ba49458
feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)
* feat(subagents): continue native batches and honor item dependencies

* docs: link native batch follow-up changelog entries

* test(migrations): pin isolated history-seed upgrade to 0050

* fix(subagents): preserve follow-up scope, blockers and fair scheduling

* test(memory): freeze capacity evaluation time

* fix(subagents): guard follow-up admission and retain run controls

* fix(subagents): enforce runs:cancel on tool cancellation of follow-up batches

* style(tests): format test_batch_followup_host with ruff

* fix(subagents): drop the admission checkpoint check and keep SDK cancel compatible

The checkpoint check inside run admission waited on the checkpoint saver's
lock while holding the SQLite write lock, which could make another chat's
checkpoint write fail. Remove it; dispatch still checks the conversation
before admission.

A follow-up waiting for an unanswered question now keeps its claim until the
lease expires instead of rereading the conversation every poll. Cancel passes
the caller's run authority only to submitters that take it, so existing SDK
submitters keep the two-argument call. Document that retrying a prerequisite
by hand does not requeue its blocked items, and list 0052 as the migration head.

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-05 15:10:21 +08:00
Hyeonsang Cho
7fd0c0cb3e
fix(harness): keep a cancelled batch cancelled when retrying a failed item (#7792)
* fix(harness): keep a cancelled batch cancelled when retrying a failed item

retry_item only kept a paused batch as it was, so retrying a failed item
of a cancelled batch reset the batch to queued and the worker claimed and
ran the item. A cancelled batch now rejects the retry (409), re-checked
under the write lock because SQLite ignores FOR UPDATE, and the workspace
no longer offers Retry there.

* docs(changelog): reference #7792 for the cancelled batch retry fix
2026-11-02 10:05:05 +08:00
jswSpace
882433ae50
fix(subagents): recover expired attempts in paused batches (#7686)
* fix(subagents): recover expired attempts in paused batches

* test(subagents): target item reads in lease recovery race

---------

Co-authored-by: jswSpace <198684035+jswSpace@users.noreply.github.com>
2026-10-30 21:50:39 +08:00
yi-coding
3db2fc8bb4
fix(subagents): fence durable batch lease lifecycles (#6764)
* fix(subagents): fence durable batch lease lifecycles

* fix(subagents): fence batch claims and require captured lease owners

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-15 12:02:00 +08:00
Hyeonsang Cho
75245e4b73
fix(subagents): leave full results out of the polled batch item list (#6781)
* fix(subagents): leave full results out of the polled batch item list

The item list endpoint returns only previews, but list_items selected
whole rows, so every page loaded and decoded each item's full report,
evidence JSON and prompt before discarding them. The workspace polls
this list every 2 seconds while a batch runs; with the default
max_result_chars a 100-item page held about 34 MB and blocked the event
loop for about 70 ms (170 MB and 300 ms at limit=500).

Defer those columns unless the caller asks for them, with raiseload so
an accidental read fails loudly instead of lazy-loading. A 100-item page
now peaks under 1 MB; responses are unchanged.

* test(subagents): pin the item list route to compact columns

Drive list_batch_items against a real SQLite repository so a route that
starts requesting full results fails, not only a repository change.

* docs(changelog): reference #6781

* test(subagents): scope the route test's seed update to its batch
2026-10-14 08:25:57 +08:00
Guo-Yixin
3182ecb1e4
feat(subagents): preserve RAG evidence in durable batch exports (#6413)
* feat(subagents): preserve RAG evidence in durable batch exports

* docs(subagents): clarify evidence omissions and migration head

* docs(persistence): update the migration chain head

* test(persistence): track the new batch evidence migration head

* test(persistence): verify batch evidence migration on PostgreSQL

* docs(subagents): retain evidence migration compatibility guidance

* fix(subagents): propagate cited evidence forwarding omissions

* fix(tests): adapt batch evidence PostgreSQL CI connection options

* fix(tests): preserve TLS policy in batch evidence migration fixture
2026-10-07 18:37:31 +08:00
Yufeng He
a9e5b6a853
fix(harness): keep a paused batch paused when retrying one failed item (#6417)
retry_item unconditionally flipped batch.status to queued, and claim_items
only schedules queued or running batches. Retrying one failed item in a
paused batch therefore lifted the pause barrier and let the scheduler
take every unrelated pending item without an explicit resume.

Leave the batch row untouched when it is paused; the retried item is
still reset to pending and waits for resume_batch like its siblings.
Non paused batches keep the existing requeue behavior.

Fixes #6411

Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>
2026-10-07 17:24:12 +08:00
theater
85acf643c0
fix(subagents): terminalize batches after exhausted leases expire (#5897)
* fix(subagents): terminalize batches after exhausted leases expire

* docs(subagents): stay within agent guidance budget
2026-09-28 15:29:18 +08:00
Wenchao An
0b3dadbc9b
feat(subagents): add acceptance checks to durable batch items (#5289)
* feat(subagents): check and persist durable batch acceptance

Carry optional per-item criteria into native subagents, reuse the deterministic checker, and expose separate verdicts through item queries and exports. Preserve execution and retry semantics, renew leases during checks, and migrate existing batch rows with nullable acceptance fields.

* fix(subagents): align batch acceptance normalization and sandbox admission

* test(auth): include project permissions in the full-stack contract
2026-09-09 08:45:20 +08:00
Aari
ff0a6768c2
feat(subagents): add unified capacity and durable batch execution (#4998)
* feat(subagents): add capacity controls and durable batches

* fix(helm): sync subagent config schema version

* fix(subagents): preserve batch history without worker

* fix(subagents): support explicit factory runtimes

* fix: address durable batch review findings
2026-08-25 07:49:38 +08:00