Commit Graph

106 Commits

Author SHA1 Message Date
mariosousa-finn
ac13b09b74 fix(agents,gateway): keep subagent announces in the original thread (#63143)
Merged via squash.

Prepared head SHA: 9aa5303b48
Co-authored-by: mariosousa-finn <244526439+mariosousa-finn@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-04-10 15:46:01 -07:00
Peter Steinberger
3174c6919d refactor: dedupe gateway memory trimmed readers 2026-04-08 01:36:39 +01:00
Peter Steinberger
134588fc17 refactor: dedupe gateway trimmed readers 2026-04-08 00:09:41 +01:00
Peter Steinberger
e51a00ffc7 refactor: dedupe gateway infra lowercase helpers 2026-04-07 20:57:03 +01:00
Peter Steinberger
679a393f6d refactor: dedupe metadata readers 2026-04-07 07:36:11 +01:00
Sam Padilla
f1b7dd6c0a fix: honor lightContext in spawned subagents (#62264) (thanks @theSamPadilla)
* Add lightContext support for spawned subagents

* Clarify and guard lightContext usage in sessions_spawn

* test: guard sessions_spawn lightContext acp misuse

* fix: honor lightContext in spawned subagents (#62264) (thanks @theSamPadilla)

---------

Co-authored-by: Jaz <jaz@bycrux.com>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
2026-04-07 11:05:45 +05:30
Peter Steinberger
d03985415d refactor: dedupe trimmed string readers 2026-04-07 05:06:54 +01:00
scoootscooob
f4fcaa09a3 feat(gateway): add compaction checkpoints (#62146)
Merged via squash.

Prepared head SHA: e37542554a
Co-authored-by: scoootscooob <167050519+scoootscooob@users.noreply.github.com>
Co-authored-by: scoootscooob <167050519+scoootscooob@users.noreply.github.com>
Reviewed-by: @scoootscooob
2026-04-06 17:27:43 -07:00
Peter Steinberger
c39f061003 Revert "refactor(cli): remove bundled cli text providers"
This reverts commit 05d351c430.
2026-04-06 13:40:41 +01:00
Peter Steinberger
124c4c85ab fix(tasks): hide internal completion wake rows 2026-04-06 03:03:53 +01:00
Peter Steinberger
05d351c430 refactor(cli): remove bundled cli text providers 2026-04-05 18:46:36 +01:00
Vincent Koc
7cd0ff2d88 refactor(tasks): add owner-key task access boundaries (#58516)
* refactor(tasks): add owner-key task access boundaries

* test(acp): update task owner-key assertion

* fix(tasks): align owner key checks and migration scope
2026-04-01 03:12:33 +09:00
Peter Steinberger
759d37635d Revert "refactor: move tasks behind plugin-sdk seam"
This reverts commit da6e9bb76f.
2026-04-01 01:30:22 +09:00
Peter Steinberger
da6e9bb76f refactor: move tasks behind plugin-sdk seam 2026-03-31 15:22:09 +01:00
Sean
c6f2db1506 fix: prevent gateway attachment offload regressions (#55513) (thanks @Syysean)
* feat(gateway): implement claim check pattern to prevent OOM on large attachments

* fix: sanitize mediaId, refine trimEnd, remove warn log, add threshold and absolute path

* fix: enforce maxBytes before decoding and use dynamic path from saveMediaBuffer

* fix: enforce absolute maxBytes limit before Buffer allocation and preserve file extensions

* fix: align saveMediaBuffer arguments and satisfy oxfmt linter

* chore: strictly enforce linting rules (curly braces, unused vars, and error typing)

* fix: restrict offload to mainstream mimes to avoid extension-loss bug in store.ts for BMP/TIFF

* fix: restrict offload to mainstream mimes to bypass store.ts extension-loss bug

* chore: document bmp/tiff exclusion from offload whitelist in MIME_TO_EXT

* feat: implement agent-side resolver for opaque media URIs and finalize contract

* fix: support unicode media URIs and allow consecutive dots in safe IDs based on Codex review

* fix(gateway): enforce strict fail-fast for oversized media to prevent OOM bypass

* refactor(gateway): harden media offload with performance and security optimizations

This update refines the Claim Check pattern with industrial-grade guards:

- Performance: Implemented sampled Base64 validation for large payloads (>4KB) to prevent event loop blocking.
- Security: Added null-byte (\u0000) detection and reinforced path traversal guards.
- I18n: Updated media-uri regex to a blacklist-based character class for Unicode/Chinese filename support, with oxlint bypass for intentional control regex.
- Robustness: Enhanced error diagnostics with JSON-serialized IDs.

* fix: add HEIC/HEIF to offload allowlist and pass maxBytes to saveMediaBuffer

* fix(gateway): clean up offloaded media files on attachment parse failure

Address Codex review feedback: track saved media IDs and implement best-effort cleanup via deleteMediaBuffer if subsequent attachments fail validation, preventing orphaned files on disk.

* fix(gateway): enforce full base64 validation to prevent whitespace padding bypass

Address Codex review feedback: remove early return in isValidBase64 so padded payloads cannot bypass offload thresholds and reintroduce memory pressure. Updated related comments.

* fix(gateway): preserve offloaded media metadata and fix validation error mapping

Address Codex review feedback:
- Add \offloadedRefs\ to \ParsedMessageWithImages\ to expose structured metadata for offloaded attachments, preventing transcript media loss.
- Move \erifyDecodedSize\ outside the storage try-catch block to correctly surface client base64 validation failures as 4xx errors instead of 5xx \MediaOffloadError\.
- Add JSDoc TODOs indicating that upstream callers (chat.ts, agent.ts, server-node-events.ts) must explicitly pass the \supportsImages\ flag.

* fix(agents): explicitly allow media store dir when loading offloaded images

Address Codex review feedback: Pass getMediaDir() to loadWebMedia's localRoots for media-uri refs to prevent legacy path resolution mismatches from silently dropping large attachments.

* fix(gateway): resolve attachment offload regressions and error mapping

Address Codex review feedback:
- Pass \supportsImages\ dynamically in \chat.ts\ and \gent.ts\ based on model catalog, and explicitly in \server-node-events.ts\.
- Persist \offloadedRefs\ into the transcript pipeline in \chat.ts\ to preserve media metadata for >2MB attachments.
- Correctly map \MediaOffloadError\ to 5xx (UNAVAILABLE) to differentiate server storage faults from 4xx client validation errors.

* fix(gateway): dynamically compute supportsImages for overrides and node events

Address follow-up Codex review feedback:

- Use effective model (including overrides) to compute \supportsImages\ in \gent.ts\.

- Move session load earlier in \server-node-events.ts\ to dynamically compute \supportsImages\ rather than hardcoding true.

* fix(gateway): resolve capability edge cases reported by codex

Address final Codex edge cases:
- Refactor \gent.ts\ to compute \supportsImages\ even when no session key is present, ensuring text-only override requests without sessions safely drop attachments.
- Update catalog lookups in \chat.ts\, \gent.ts\, and \server-node-events.ts\ to strictly match both \id\ and \provider\ to prevent cross-provider model collisions.

* fix(agents): restore before_install hook for skill installs

Restore the plugin scanner security hook that was accidentally dropped during merge conflict resolution.

* fix: resolve attachment pathing, defer parsing after auth gates, and clean up node-event mocks

* fix: resolve syntax errors in test-env, fix missing helper imports, and optimize parsing sequence in node events

* fix(gateway): re-enforce message length limit after attachment parsing

Adds a secondary check to ensure the 20,000-char cap remains effective even after media markers are appended during the offload flow.

* fix(gateway): prevent dropping valid small images and clean up orphaned media on size rejection

* fix(gateway): share attachment image capability checks

* fix(gateway): preserve mixed attachment order

* fix: fail closed on unknown image capability (#55513) (thanks @Syysean)

* fix: classify offloaded attachment refs explicitly (#55513) (thanks @Syysean)

---------

Co-authored-by: Ayaan Zaidi <hi@obviy.us>
2026-03-30 20:54:40 +05:30
Vincent Koc
8fb247c528 refactor(tasks): guard executor-only producer writes (#57486)
* refactor(tasks): add executor facade

* refactor(tasks): extract delivery policy

* refactor(tasks): route acp through executor

* refactor(tasks): route subagents through executor

* refactor(cron): split main and detached dispatch

* refactor(tasks): guard executor-only producer writes
2026-03-30 14:00:25 +09:00
Josh Avant
5e4a64848f fix(exec): harden async approval followup delivery in webchat-only sessions (#57359)
* fix(exec): harden approval followup delivery fallback

* refactor(delivery): share best-effort followup routing helpers

* test(subagents): cover webchat-only completion announce delivery

* docs(exec): clarify async followup delivery behavior

* fix(exec): harden delivery downgrade logging

* test(gateway): cover multi-channel best-effort fallback

* fix(exec): preserve webchat origin on session-only followups

* fix(subagents): keep internal announces channel-less
2026-03-29 20:54:13 -05:00
Vincent Koc
53bcd5769e refactor(tasks): unify the shared task run registry (#57324)
* refactor(tasks): simplify shared task run registry

* refactor(tasks): remove legacy task registry aliases

* fix(cron): normalize timeout task status and harden ledger writes

* fix(cron): keep manual runs resilient to ledger failures
2026-03-30 08:28:17 +09:00
Peter Steinberger
63e5c3349e refactor(config): drop obsolete legacy config aliases 2026-03-29 22:00:56 +01:00
Mariano
17c36b5093 Gateway: track background task lifecycle (#52518)
Merged via squash.

Prepared head SHA: 7c4554204e
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-03-29 12:48:02 +02:00
Tak Hoffman
ae9b9575c5 fix(regression): preserve gateway subagent session change metadata 2026-03-27 20:28:58 -05:00
Tak Hoffman
f4a45071e3 fix: preserve session thread ids in agent send events 2026-03-27 20:24:35 -05:00
Tak Hoffman
c326083ad8 fix: keep session settings in gateway live events 2026-03-26 20:11:13 -05:00
Peter Steinberger
4b40d4dfa8 perf: optimize cold import paths 2026-03-26 23:11:00 +00:00
Vincent Koc
50f6a2f136 fix(gateway): require admin for agent session reset 2026-03-23 09:31:39 -07:00
clay-datacurve
7b61ca1b06 Session management improvements and dashboard API (#50101)
* fix: make cleanup "keep" persist subagent sessions indefinitely

* feat: expose subagent session metadata in sessions list

* fix: include status and timing in sessions_list tool

* fix: hide injected timestamp prefixes in chat ui

* feat: push session list updates over websocket

* feat: expose child subagent sessions in subagents list

* feat: add admin http endpoint to kill sessions

* Emit session.message websocket events for transcript updates

* Estimate session costs in sessions list

* Add direct session history HTTP and SSE endpoints

* Harden dashboard session events and history APIs

* Add session lifecycle gateway methods

* Add dashboard session API improvements

* Add dashboard session model and parent linkage support

* fix: tighten dashboard session API metadata

* Fix dashboard session cost metadata

* Persist accumulated session cost

* fix: stop followup queue drain cfg crash

* Fix dashboard session create and model metadata

* fix: stop guessing session model costs

* Gateway: cache OpenRouter pricing for configured models

* Gateway: add timeout session status

* Fix subagent spawn test config loading

* Gateway: preserve operator scopes without device identity

* Emit user message transcript events and deduplicate plugin warnings

* feat: emit sessions.changed lifecycle event on subagent spawn

Adds a session-lifecycle-events module (similar to transcript-events)
that emits create events when subagents are spawned. The gateway
server.impl.ts listens for these events and broadcasts sessions.changed
with reason=create to SSE subscribers, so dashboards can pick up new
subagent sessions without polling.

* Gateway: allow persistent dashboard orchestrator sessions

* fix: preserve operator scopes for token-authenticated backend clients

Backend clients (like agent-dashboard) that authenticate with a valid gateway
token but don't present a device identity were getting their scopes stripped.
The scope-clearing logic ran before checking the device identity decision,
so even when evaluateMissingDeviceIdentity returned 'allow' (because
roleCanSkipDeviceIdentity passed for token-authed operators), scopes were
already cleared.

Fix: also check decision.kind before clearing scopes, so token-authenticated
operators keep their requested scopes.

* Gateway: allow operator-token session kills

* Fix stale active subagent status after follow-up runs

* Fix dashboard image attachments in sessions send

* Fix completed session follow-up status updates

* feat: stream session tool events to operator UIs

* Add sessions.steer gateway coverage

* Persist subagent timing in session store

* Fix subagent session transcript event keys

* Fix active subagent session status in gateway

* bump session label max to 512

* Fix gateway send session reactivation

* fix: publish terminal session lifecycle state

* feat: change default session reset to effectively never

- Change DEFAULT_RESET_MODE from "daily" to "idle"
- Change DEFAULT_IDLE_MINUTES from 60 to 0 (0 = disabled/never)
- Allow idleMinutes=0 through normalization (don't clamp to 1)
- Treat idleMinutes=0 as "no idle expiry" in evaluateSessionFreshness
- Default behavior: mode "idle" + idleMinutes 0 = sessions never auto-reset
- Update test assertion for new default mode

* fix: prep session management followups (#50101) (thanks @clay-datacurve)

---------

Co-authored-by: Tyler Yust <TYTYYUST@YAHOO.COM>
2026-03-19 12:12:30 +09:00
Josh Lehman
1399ca5fcb fix(plugins): forward plugin subagent overrides (#48277)
Merged via squash.

Prepared head SHA: ffa45893e0
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-17 07:20:27 -07:00
Peter Steinberger
198c2482ee refactor: share gateway session store migration 2026-03-13 18:38:12 +00:00
Peter Steinberger
d5bffcdeab feat: add fast mode toggle for OpenAI models 2026-03-12 23:31:31 +00:00
Vincent Koc
46a332385d Gateway: keep spawned workspace overrides internal (#43801)
* Gateway: keep spawned workspace overrides internal

* Changelog: note GHSA-2rqg agent boundary fix

* Gateway: persist spawned workspace inheritance in sessions

* Agents: clean failed lineage spawn state

* Tests: cover lineage attachment cleanup

* Tests: cover lineage thread cleanup
2026-03-12 04:20:00 -04:00
Peter Steinberger
c91d1622d5 fix(gateway): split conversation reset from admin reset 2026-03-11 02:50:44 +00:00
Peter Steinberger
eed403dc74 refactor(agents): unify spawned metadata and extract attachments service 2026-03-08 00:23:45 +00:00
Peter Steinberger
ab54532c8f fix(agents): land #39247 from @jasonQin6 (subagent workspace inheritance)
Propagate parent workspace directories into spawned subagent runs, keep workspace override internal-only, and add regression tests for forwarding boundaries.

Co-authored-by: jasonQin6 <991262382@qq.com>
2026-03-07 23:56:37 +00:00
Bob
61f7cea48b fix: kill stuck ACP child processes on startup and harden sessions in discord threads (#33699)
* Gateway: resolve agent.wait for chat.send runs

* Discord: harden ACP thread binding + listener timeout

* ACPX: handle already-exited child wait

* Gateway/Discord: address PR review findings

* Discord: keep ACP error-state thread bindings on startup

* gateway: make agent.wait dedupe bridge event-driven

* discord: harden ACP probe classification and cap startup fan-out

* discord: add cooperative timeout cancellation

* discord: fix startup probe concurrency helper typing

* plugin-sdk: avoid Windows root-alias shard timeout

* plugin-sdk: keep root alias reflection path non-blocking

* discord+gateway: resolve remaining PR review findings

* gateway+discord: fix codex review regressions

* Discord/Gateway: address Codex review findings

* Gateway: keep agent.wait lifecycle active with shared run IDs

* Discord: clean up status reactions on aborted runs

* fix: add changelog note for ACP/Discord startup hardening (#33699) (thanks @dutifulbob)

---------

Co-authored-by: Onur <2453968+osolmaz@users.noreply.github.com>
2026-03-04 10:52:28 +01:00
chengzhichao-xydt
53727c72f4 fix: substitute YYYY-MM-DD at session startup and post-compaction (#32363) (#32381)
Merged via squash.

Prepared head SHA: aee998a2c1
Co-authored-by: chengzhichao-xydt <264300353+chengzhichao-xydt@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-03-03 06:21:26 -08:00
Peter Steinberger
b8b8a5f314 fix(security): enforce explicit ingress owner context 2026-03-02 23:50:36 +00:00
Peter Steinberger
58659b931b fix(gateway): enforce owner boundary for agent runs 2026-03-02 00:27:44 +00:00
Peter Steinberger
4c43fccb3e feat(agents): use structured internal completion events 2026-03-01 23:11:48 +00:00
Peter Steinberger
6fd9ec97de fix(gateway): preserve turn-origin messageChannel in agent runs 2026-02-26 17:25:56 +01:00
Onur Solmaz
a7d56e3554 feat: ACP thread-bound agents (#23580)
* docs: add ACP thread-bound agents plan doc

* docs: expand ACP implementation specification

* feat(acp): route ACP sessions through core dispatch and lifecycle cleanup

* feat(acp): add /acp commands and Discord spawn gate

* ACP: add acpx runtime plugin backend

* fix(subagents): defer transient lifecycle errors before announce

* Agents: harden ACP sessions_spawn and tighten spawn guidance

* Agents: require explicit ACP target for runtime spawns

* docs: expand ACP control-plane implementation plan

* ACP: harden metadata seeding and spawn guidance

* ACP: centralize runtime control-plane manager and fail-closed dispatch

* ACP: harden runtime manager and unify spawn helpers

* Commands: route ACP sessions through ACP runtime in agent command

* ACP: require persisted metadata for runtime spawns

* Sessions: preserve ACP metadata when updating entries

* Plugins: harden ACP backend registry across loaders

* ACPX: make availability probe compatible with adapters

* E2E: add manual Discord ACP plain-language smoke script

* ACPX: preserve streamed spacing across Discord delivery

* Docs: add ACP Discord streaming strategy

* ACP: harden Discord stream buffering for thread replies

* ACP: reuse shared block reply pipeline for projector

* ACP: unify streaming config and adopt coalesceIdleMs

* Docs: add temporary ACP production hardening plan

* Docs: trim temporary ACP hardening plan goals

* Docs: gate ACP thread controls by backend capabilities

* ACP: add capability-gated runtime controls and /acp operator commands

* Docs: remove temporary ACP hardening plan

* ACP: fix spawn target validation and close cache cleanup

* ACP: harden runtime dispatch and recovery paths

* ACP: split ACP command/runtime internals and centralize policy

* ACP: harden runtime lifecycle, validation, and observability

* ACP: surface runtime and backend session IDs in thread bindings

* docs: add temp plan for binding-service migration

* ACP: migrate thread binding flows to SessionBindingService

* ACP: address review feedback and preserve prompt wording

* ACPX plugin: pin runtime dependency and prefer bundled CLI

* Discord: complete binding-service migration cleanup and restore ACP plan

* Docs: add standalone ACP agents guide

* ACP: route harness intents to thread-bound ACP sessions

* ACP: fix spawn thread routing and queue-owner stall

* ACP: harden startup reconciliation and command bypass handling

* ACP: fix dispatch bypass type narrowing

* ACP: align runtime metadata to agentSessionId

* ACP: normalize session identifier handling and labels

* ACP: mark thread banner session ids provisional until first reply

* ACP: stabilize session identity mapping and startup reconciliation

* ACP: add resolved session-id notices and cwd in thread intros

* Discord: prefix thread meta notices consistently

* Discord: unify ACP/thread meta notices with gear prefix

* Discord: split thread persona naming from meta formatting

* Extensions: bump acpx plugin dependency to 0.1.9

* Agents: gate ACP prompt guidance behind acp.enabled

* Docs: remove temp experiment plan docs

* Docs: scope streaming plan to holy grail refactor

* Docs: refactor ACP agents guide for human-first flow

* Docs/Skill: add ACP feature-flag guidance and direct acpx telephone-game flow

* Docs/Skill: add OpenCode and Pi to ACP harness lists

* Docs/Skill: align ACP harness list with current acpx registry

* Dev/Test: move ACP plain-language smoke script and mark as keep

* Docs/Skill: reorder ACP harness lists with Pi first

* ACP: split control-plane manager into core/types/utils modules

* Docs: refresh ACP thread-bound agents plan

* ACP: extract dispatch lane and split manager domains

* ACP: centralize binding context and remove reverse deps

* Infra: unify system message formatting

* ACP: centralize error boundaries and session id rendering

* ACP: enforce init concurrency cap and strict meta clear

* Tests: fix ACP dispatch binding mock typing

* Tests: fix Discord thread-binding mock drift and ACP request id

* ACP: gate slash bypass and persist cleared overrides

* ACPX: await pre-abort cancel before runTurn return

* Extension: pin acpx runtime dependency to 0.1.11

* Docs: add pinned acpx install strategy for ACP extension

* Extensions/acpx: enforce strict local pinned startup

* Extensions/acpx: tighten acp-router install guidance

* ACPX: retry runtime test temp-dir cleanup

* Extensions/acpx: require proactive ACPX repair for thread spawns

* Extensions/acpx: require restart offer after acpx reinstall

* extensions/acpx: remove workspace protocol devDependency

* extensions/acpx: bump pinned acpx to 0.1.13

* extensions/acpx: sync lockfile after dependency bump

* ACPX: make runtime spawn Windows-safe

* fix: align doctor-config-flow repair tests with default-account migration (#23580) (thanks @osolmaz)
2026-02-26 11:00:09 +01:00
Peter Steinberger
885452f5c1 fix: fail-closed shared-session reply routing (#24571) (thanks @brandonwise) 2026-02-25 02:11:34 +00:00
Ayaan Zaidi
03122e5933 fix(cron): preserve telegram announce target + delivery truth 2026-02-23 11:45:18 +05:30
Peter Steinberger
1152b25866 fix(gateway): guard trim crashes in subagent flow 2026-02-22 13:21:26 +01:00
Peter Steinberger
1cd3b30907 fix: stop hardcoded channel fallback and auto-pick sole configured channel (#23357) (thanks @lbo728)
Co-authored-by: lbo728 <extreme0728@gmail.com>
2026-02-22 11:21:43 +01:00
Peter Steinberger
b8b43175c5 style: align formatting with oxfmt 0.33 2026-02-18 01:34:35 +00:00
Peter Steinberger
31f9be126c style: run oxfmt and fix gate failures 2026-02-18 01:29:02 +00:00
cpojer
d0cb8c19b2 chore: wtf. 2026-02-17 13:36:48 +09:00
Sebastian
ed11e93cf2 chore(format) 2026-02-16 23:20:16 -05:00
cpojer
90ef2d6bdf chore: Update formatting. 2026-02-17 09:18:40 +09:00
Rodrigo Uroz
df95ddc771 Fix/agent session key normalization (openclaw#15707) thanks @rodrigouroz
Verified:
- pnpm build
- pnpm check
- pnpm test:macmini

Co-authored-by: rodrigouroz <384037+rodrigouroz@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-02-15 09:46:14 -06:00