Commit Graph
57 Commits
Author SHA1 Message Date
BiFangKNT ce5b7ffea1 fix(agent): preserve terminal events when cancelling runner execution
Emit and persist a Host cancellation event before closing the runner stream.
Preserve existing terminal events and record cancelled runs consistently.

Serialize Host event sequence allocation to prevent conflicts with admin
cancellation audits, and notify observers with the persisted sequence.

Add deterministic cancellation and concurrent event allocation regressions.
2026-10-23 17:23:44 +08:00
huanghuoguoguo cc19395f5c perf(core): reduce execution projection and dispatch overhead (#2746)
* perf(core): join execution projection and reuse authorized tool schemas

* perf(pipeline): avoid duplicate checks before stage output validation

* perf(plugin): reuse reconciled settings within event dispatch

* fix(workspace): keep execution projection reads free of unrelated flushes
2026-10-22 20:00:42 +08:00
huanghuoguoguo 7a410bcb31 test(core): strengthen handler contracts and report source quality (#2632) 2026-10-22 17:33:09 +08:00
彼方 1baba1b9f9 Merge pull request #2725 from langbot-app/fix/session-summary-persistence
fix(monitoring): persist session summaries to avoid history scans
2026-10-20 11:53:06 +08:00
BiFangKNT 810d053df9 fix(monitoring): persist session summaries to avoid history scans
- Maintain counts and display snapshots in source transactions with replay-safe deduplication.
- Read session lists exclusively from summaries and remove execution-only filters.
- Automatically initialize historical summaries in bounded, resumable batches during OSS startup.
- Add behavioral contracts covering accounting, retention, query cost and PostgreSQL concurrency.

Verified with the required session_summary suite and real container upgrade startup.
2026-10-20 06:12:00 +08:00
RockChinQandmultica-agent d9e4e7d9df fix(pipeline): decouple Runner from extension permissions (LANG-54) (#2723)
* fix(pipeline): decouple runner from extension allowlist

Co-authored-by: multica-agent <[email protected]>

* fix(pipeline): complete runner diagnostics and real runtime coverage

Co-authored-by: multica-agent <[email protected]>

---------

Co-authored-by: multica-agent <[email protected]>
2026-10-19 23:07:11 +08:00
BiFangKNT 57077740bd chore(merge): sync master and preserve monitoring test coverage 2026-10-18 12:43:44 +08:00
BiFangKNT b73f66a234 feat(persistence): enforce image reference storage contract
- Reject structured inline images on ORM and Core writes
- Route plugin run results through the media-aware journal
- Redact legacy inline images before merging run metadata
- Cover storage contracts and regressions on SQLite and PostgreSQL
2026-10-18 12:26:09 +08:00
BiFangKNT cbc849d4e2 fix(storage): unify CAS persistence for inline images
- Externalize inline images in messages and run events before persistence
- Keep snapshots, transcripts, and metadata free of inline payloads
- Serialize messages after externalization to reduce peak memory usage
- Preserve live messages, URL-only images, and SDK image retrieval behavior
- Add regression tests for deduplication, redaction, storage failures, and serialization order
2026-10-18 00:04:20 +08:00
huanghuoguoguo 13b8edeace Merge pull request #2705 from langbot-app/test/required-contract-suites
test(ci): decouple required suites from test names and counts
2026-10-17 23:12:59 +08:00
huanghuoguoguo ec57b6a51d Merge pull request #2684 from langbot-app/test/quality-agent-plugin-oracles-20261017
test: verify persisted Agent and Plugin behavior boundaries
2026-10-17 20:11:24 +08:00
huanghuoguoguo ecea4c3d41 Merge pull request #2675 from langbot-app/test/quality-self-duplicates-20261017
test: remove redundant backend checks and migration aliases
2026-10-17 20:10:30 +08:00
huanghuoguoguo e0c738557a test(agent): verify persistence and denied action side effects 2026-10-17 15:35:33 +08:00
RockChinQ c05aac538f fix(discord): complete streaming media and event delivery 2026-10-17 15:11:29 +08:00
huanghuoguoguo 4afd86c1f6 test: consolidate duplicate backend contracts and strengthen stage checks 2026-10-17 15:03:50 +08:00
huanghuoguoguo bbf517edbc test(auth): exercise knowledge and event action boundaries (#2667) 2026-10-17 12:46:41 +08:00
huanghuoguoguo 5641637d3d Merge pull request #2665 from langbot-app/test/regression-boundary-cleanup-20261017
test: remove self-confirming tests and strengthen regression boundaries
2026-10-17 11:26:46 +08:00
huanghuoguoguo 3f2d52e557 Merge pull request #2512 from langbot-app/feat/2410-sdk-skill-store
feat(skill): decouple read-only skills from Box execution
2026-10-17 10:13:26 +08:00
huanghuoguoguo d54e533985 fix(skill): pin revisions per run and preserve shared Box state 2026-10-17 09:32:41 +08:00
huanghuoguoguo 438cbd41a9 test(core): provision real plugin, CLI and SeekDB contracts (#2636)
* test(core): provision official plugin CLI and SeekDB contracts

* test(core): trigger report guard tests and trim fixture checks
2026-10-17 09:13:44 +08:00
RockChinQ 0b5b4cca59 fix(telegram): resolve real-client event and media delivery regressions 2026-10-11 10:14:11 +08:00
Hyu 3ff849d243 test: align processor fixtures with current creation and startup behavior 2026-10-11 01:03:31 +08:00
Hyu 40a3a941a3 fix(monitoring): unify execution records and stabilize streaming cleanup 2026-10-08 03:02:37 +08:00
RockChinQ 30585c8657 refactor: remove beta diagnostics collection and reporting (#2616) 2026-09-30 20:24:35 +08:00
huanghuoguoguo c56fa0ba2e fix(skill): reconcile rebase with runner contracts 2026-09-28 10:54:31 +08:00
RockChinQ ee90ec61d0 fix(agent): preserve configured prompts in debug runs
[verified] Independently reviewed debug-only Query initialization, explicit-empty prompt semantics, scoped Runner schema/config, trusted execution metadata and MCP projection. Focused RED/GREEN and 249 regression tests pass. No shared orchestration or nondebug behavior changes.
2026-09-21 19:18:30 +00:00
RockChinQ 79cac0c6a3 fix(reasoning): apply explicit per-call levels without runner config caching 2026-09-19 00:05:49 +08:00
RockChinQ a6ac25cf84 feat(agent): add task-oriented run logs and execution details 2026-09-18 00:59:17 +08:00
RockChinQ b264d46d77 feat: delegate sandbox policy to runners and simplify pipeline migration 2026-09-17 23:05:27 +08:00
RockChinQ 8c119bc4b6 feat: add verified manual pipeline migration for plugin runners 2026-09-16 18:13:11 +00:00
dadachann f8123ead0a feat(telemetry): add isolated beta quality diagnostics and release identity 2026-09-15 09:35:01 +00:00
RockChinQ 1277c6da07 feat(runner): filter marketplace recommendations by explicit usage 2026-09-12 12:51:16 +08:00
Hyuanddadachann e631da0073 fix(runner): align SDK pin and complete real runtime verification (#2525)
* fix(runner): align SDK pin and workspace-aware integration fixtures

* fix(ci): format sources and resolve current migration head

* test(persistence): align standalone migration fixtures with current models

* test(web): align smoke fixtures with current processor UI

---------

Co-authored-by: dadachann <[email protected]>
2026-09-11 12:57:29 +08:00
RockChinQ d93e44d82d feat(runner): authorize contextual platform APIs 2026-09-11 00:02:44 +08:00
RockChinQ f24a7c9bb2 feat(runner): unify plugin execution across agents and event processors 2026-09-10 18:04:38 +08:00
RockChinQ 8903a40c41 fix(runtime): preserve explicit replies and report bot configuration errors 2026-09-10 17:21:22 +08:00
RockChinQ ea3e32c904 feat(processors): streamline event debugging and run inspection 2026-09-08 02:30:59 +08:00
RockChinQ 237fa6545d feat(processors): add explicitly bound plugin event processors 2026-09-08 00:43:35 +08:00
RockChinQ f5d6a3b348 fix(agent): tolerate intent annotations on no-argument platform tools 2026-09-05 17:15:20 +08:00
Hyu 8f0a55a1f4 fix(agent-debug): stream execution traces with platform mocks and coverage 2026-09-05 15:34:29 +08:00
Hyu a4d36aa2db feat(agent): add event-aware tool permissions 2026-09-04 15:37:41 +08:00
RockChinQ 2aceefce47 test(agent): remove obsolete enabled fixture 2026-08-25 23:28:37 +08:00
RockChinQ 80f1790e1d refactor(agent): remove enabled state 2026-08-25 23:27:45 +08:00
RockChinQ 6a6a2b865b fix(web): make processor debugging reliable 2026-08-25 15:52:59 +08:00
huanghuoguoguo 444024c5b4 fix(agent): stabilize post-merge release paths 2026-08-04 17:04:40 +08:00
huanghuoguoguo 79611a5513 fix(agent): harden runner integration and QA 2026-08-01 09:23:41 +08:00
huanghuoguoguo 55f42a4ebc chore(merge): sync master into dev/4.11.x 2026-07-31 19:29:38 +08:00
fdc310 6b13c37c3b feat(agent): integrate structured runner interactions 2026-07-22 11:32:17 +08:00
huanghuoguoguo 9f28d6949a fix(agent-runner): unify streamed completion delivery 2026-07-19 22:46:01 +08:00
huanghuoguoguo 8a7c3fcefe fix(agent-runner): aggregate non-streaming replies 2026-07-19 22:46:01 +08:00