Commit Graph

1049 Commits

Author SHA1 Message Date
brokemac79
f4b92f5e6c fix(agents): simplify subagent completion handoff
Simplify native subagent completion handoff and remove manual subagent control surfaces.

Co-authored-by: brokemac79 <martin_cleary@yahoo.co.uk>
2026-05-23 13:50:08 +01:00
Vincent Koc
7f05be041e fix(diagnostics): harden observability exports and smokes (#85371)
* test(diagnostics): widen observability smokes

* fix(diagnostics): sanitize observability exports

* docs(diagnostics): format otel export docs
2026-05-23 15:27:43 +08:00
Kevin Lin
5656f687c1 Add Slack approval QA checkpoints (#85141)
* test: add slack approval qa checkpoints

* fix(slack): scope plugin approval session fallback

* ci(mantis): allow slack approval checkpoint dispatch

* ci(mantis): use on-demand aws slack desktops

* ci(mantis): run slack smoke from candidate checkout

* ci(mantis): pin aws ssh ingress to runner

* test(mantis): skip crabbox actions hydrate for slack desktop

* ci(mantis): use fresh pr checkout for slack desktop

* ci(mantis): start slack desktop smoke from source

* fix(mantis): use relative slack qa output dir

* test(mantis): surface slack smoke failure logs

* fix(mantis): write slack approval watcher script

* fix(mantis): accept successful slack qa metadata

* fix(mantis): tighten slack approval evidence

* fix(mantis): repair slack evidence manifest

* fix(mantis): render slack approval checkpoint proof

* fix(mantis): quote approval checkpoint renderer html

* fix(mantis): preserve slack approval failure artifacts

* fix(mantis): timeout silent slack desktop runs

* fix(mantis): keep slack desktop runs chatty

* fix(mantis): keep slack workflow harness trusted

* fix(qa-lab): make slack approval evidence robust

* fix(qa-lab): harden slack approval workflow proof

* test(qa-lab): surface slack approval diagnostics

* test(qa-lab): loosen slack approval readiness
2026-05-22 22:04:15 -07:00
Peter Steinberger
64d13c017a docs: refresh contributor docs
Co-authored-by: Quratulain-bilal <umayaimanshah@gmail.com>
Co-authored-by: Mariano Belinky <mbelinky@gmail.com>
Co-authored-by: tao <itaofe@gmail.com>
Co-authored-by: julian <julian@tencent.com>
Co-authored-by: xenouzik <xenouziq@gmail.com>
Co-authored-by: Olamiposi <56056759+posigit@users.noreply.github.com>
Co-authored-by: surlymochan <surlymo@apache.org>
Co-authored-by: Janaka A <contact@janaka.co.uk>
Co-authored-by: choiking <samsamuels1927@gmail.com>
2026-05-22 22:58:27 +01:00
Peter Steinberger
e0fda55cf7 docs: absorb maintainer docs sweep
Co-authored-by: Bob Du <i@bobdu.cc>
Co-authored-by: alitariksahin <alitariksah@gmail.com>
Co-authored-by: Jefsky <hwj3344@hotmail.com>
Co-authored-by: Musaab Hasan <m9.3b@Hotmail.com>
Co-authored-by: Intern Dev <dev@wukongai.io>
Co-authored-by: majin.nathan <majin.nathan@bytedance.com>
2026-05-22 20:29:10 +01:00
cassthebandit
bd04b1ea7c docs(memory): add guidance for action-sensitive memories (#82788) 2026-05-22 19:21:00 +01:00
Peter Steinberger
59aef2ff0d fix: apply docs sweep updates 2026-05-22 18:40:20 +01:00
Josh Lehman
cff5244a5b feat: add context-engine host capability requirements (#84994)
* feat(context-engine): add host capability requirements

* fix(context-engine): advertise pi host capabilities

* fix: repair incompatible context engine slots
2026-05-22 10:28:08 -04:00
fuller-stack-dev
65471a2da6 feat: add xai oauth web search and provider timeouts 2026-05-22 08:49:53 +01:00
Josh Avant
ba06376c79 fix: harden codex sandbox execution
Harden the Codex app-server native execution bridge for OpenClaw sandboxed runs. The change keeps core sandbox policy in OpenClaw while exposing the process, filesystem, and HTTP relay behavior Codex needs inside a scoped exec server.

The large exec-server/test files were split into focused modules before landing, and the PR was rebased onto current main with focused tests, Testbox changed checks, CI, and Codex autoreview green.

Co-authored-by: joshavant <830519+joshavant@users.noreply.github.com>
2026-05-21 23:47:32 +01:00
Firas Alswihry
229323d37a test(qa-lab): add personal failure recovery scenario 2026-05-21 23:22:35 +08:00
Peter Steinberger
e0b53cae41 docs: remove stale owner tool wording 2026-05-21 15:14:48 +01:00
Peter Steinberger
a13468320c fix: clarify pinned session model status 2026-05-20 15:59:24 +01:00
clawsweeper[bot]
7811e313b3 fix(channels): suppress verbose failed-tool dumps (#84354)
Summary:
- The branch suppresses regular verbose failed-tool raw output after final replies across shared dispatch, Codex, Telegram, and Discord paths, keeps raw detail under `/verbose full`, and updates tests, docs, and changelog.
- Reproducibility: yes. The current-main source path and supplied before screenshot show failed text-only tool ... ping after a final reply; I did not rerun a live Telegram or Discord reproduction in this read-only review.

Automerge notes:
- PR branch already contained follow-up commit before automerge: fix message-tool delivery gating
- PR branch already contained follow-up commit before automerge: fix(channels): keep verbose tool failures compact
- PR branch already contained follow-up commit before automerge: fix(channels): suppress in-flight final progress
- PR branch already contained follow-up commit before automerge: fix(replies): suppress failed tool dumps in message-only mode
- PR branch already contained follow-up commit before automerge: fix(replies): avoid duplicate exec failure warnings
- PR branch already contained follow-up commit before automerge: Revert "fix(replies): avoid duplicate exec failure warnings"

Validation:
- ClawSweeper review passed for head d15ae6951b.
- Required merge gates passed before the squash merge.

Prepared head SHA: d15ae6951b
Review: https://github.com/openclaw/openclaw/pull/84354#issuecomment-4493007024

Co-authored-by: VACInc <3279061+VACInc@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
2026-05-20 05:09:38 +00:00
pash-openai
e0d1a2a9b9 Move Codex soul context to developer instructions (#84331)
* Move Codex soul context to developer instructions

* Route Codex workspace context by lifetime

* Refresh Codex prompt snapshots

* Update prompt snapshot expectations

* Fix Codex workspace context diagnostics
2026-05-19 16:47:32 -07:00
Dave Morin
a00e7d3898 docs: clarify xai oauth setup (#84350) 2026-05-19 16:33:18 -07:00
Bob
13c97c5a8d feat(agents): support per-agent local model lean mode (#84073)
Summary:
- The branch adds per-agent `agents.list[].experimental.localModelLean` config and applies lean tool filtering through agent, session, and default-agent resolution.
- Reproducibility: not applicable. this is a feature/config PR rather than a current-main bug report. The chan ... or is supported by source review, focused tests in the branch, and the PR body's redacted live runtime log.

Automerge notes:
- PR branch already contained follow-up commit before automerge: feat(agents): support per-agent local model lean mode
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8407…

Validation:
- ClawSweeper review passed for head 1f9a9554da.
- Required merge gates passed before the squash merge.

Prepared head SHA: 1f9a9554da
Review: https://github.com/openclaw/openclaw/pull/84073#issuecomment-4486397570

Co-authored-by: Bob <dutifulbob@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: osolmaz
Co-authored-by: osolmaz <2453968+osolmaz@users.noreply.github.com>
2026-05-19 14:11:38 +00:00
Patrick Erichsen
d60ab48511 Add Telegram progress preview flows (#83847)
* feat(telegram): add progress preview flow tooling

* docs: add channel flow preview skill

* test(telegram): exercise native draft flow fixture

* fix(telegram): remove progress label ellipsis animation

* fix(telegram): address progress preview review
2026-05-18 21:23:55 -07:00
Firas Alswihry
a9eaf0c993 test(qa-lab): add personal no-fake-progress scenario (#83824)
Summary:
- The PR adds a personal-agent QA-Lab no-fake-progress scenario, registers it in the personal-agent pack, teaches mock-openai the scripted path, and updates focused tests, docs, and changelog.
- Reproducibility: not applicable. This PR adds QA coverage rather than reporting a current-main bug; the branch supplies concrete after-patch QA-Lab/mock-openai commands and copied pass output.

Automerge notes:
- PR branch already contained follow-up commit before automerge: test(qa-lab): add personal no-fake-progress scenario

Validation:
- ClawSweeper review passed for head 95d2e46288.
- Required merge gates passed before the squash merge.

Prepared head SHA: 95d2e46288
Review: https://github.com/openclaw/openclaw/pull/83824#issuecomment-4483439200

Co-authored-by: Firas Alswihry <itzfiras@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
2026-05-19 01:16:00 +00:00
clawsweeper[bot]
70f580041f test(qa-lab): add personal share-safe diagnostics scenario (#83717)
Summary:
- Adds a personal-agent QA-Lab share-safe diagnostics scenario with mock-openai support, pack registration/tests, docs, and changelog coverage.
- Reproducibility: not applicable. This PR adds a new QA-Lab scenario rather than fixing a current-main bug. T ... ce PR provides a clear after-patch validation path using qa-channel, a real gateway child, and mock-openai.

Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.

Validation:
- ClawSweeper review passed for head 46eb0af9e4.
- Required merge gates passed before the squash merge.

Prepared head SHA: 46eb0af9e4
Review: https://github.com/openclaw/openclaw/pull/83717#issuecomment-4480393933

Co-authored-by: Firas Alswihry <itzfiras@gmail.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
2026-05-18 18:56:25 +00:00
Firas Alswihry
46c622aa3b test(qa-lab): add dreaming shadow trial report scenario 2026-05-19 00:44:39 +08:00
Firas Alswihry
94c012b2ec test(qa-lab): add personal task followthrough scenario 2026-05-18 14:35:03 +08:00
Ayaan Zaidi
cd15ce35a0 fix(qa): keep telegram user creds mantis-only 2026-05-18 10:04:58 +05:30
Vincent Koc
1300b22630 fix(qa-lab): classify runtime token efficiency 2026-05-18 11:09:08 +08:00
Peter Steinberger
9da0f80356 fix(openai): allow available Codex OAuth models 2026-05-18 01:04:14 +01:00
Tak Hoffman
f349fb82aa fix(mantis): remove ambiguous github trigger mention (#83179) 2026-05-17 11:24:23 -05:00
Firas Alswihry
45a434fb23 test(qa-lab): add personal approval denial scenario 2026-05-17 23:33:09 +08:00
Vincent Koc
1926982c4c fix(qa-lab): refresh parity model targets 2026-05-17 23:12:26 +08:00
Peter Steinberger
77547226ce fix: improve progress draft truncation 2026-05-17 08:13:39 +01:00
Vincent Koc
da8afe359d feat(qa-lab): add scenario pack selector 2026-05-17 09:23:48 +08:00
Peter Steinberger
07f05e972e refactor: move inbound event classification into core 2026-05-17 00:10:29 +01:00
Gio Della-Libera
a136cafe98 Default bootstrap truncation warnings to always (#81918)
* Default bootstrap truncation warnings to always

Make bootstrap truncation warnings surface on every affected run by default while preserving explicit off and once configuration.

* Refresh checks after proof formatting fix

* Refresh checks after live proof update

* docs: align bootstrap warning default reference

Update the public agent config reference to match the new default bootstrapPromptTruncationWarning mode and recommended example.
2026-05-16 15:46:44 -07:00
Peter Steinberger
4b0f16d496 fix(agents): announce auto model fallback transitions (#82676)
* fix(agents): announce model fallback transitions

* docs(agents): explain model fallback notices

# Conflicts:
#	docs/concepts/model-failover.md

* fix(agents): use five minute fallback probe cadence

* fix(agents): keep fallback notices out of ACP transcripts
2026-05-16 21:56:31 +01:00
Peter Steinberger
c8782d18eb fix(agents): probe primary after auto fallback pin (#82707) 2026-05-16 20:03:09 +01:00
Vincent Koc
440333125c test(qa-lab): add personal agent scenarios 2026-05-17 02:56:53 +08:00
Vincent Koc
ac2e3a23b9 fix(qa): preserve RTT samples with Convex credentials 2026-05-17 02:17:35 +08:00
Peter Steinberger
b08e0da25b fix: clarify provider timeout ceiling 2026-05-16 01:08:07 +01:00
Peter Steinberger
445ed9b0b4 fix(auto-reply): clean up no-reply migration paths 2026-05-15 21:29:39 +01:00
Peter Steinberger
f0ceb3c5aa fix(auto-reply): restrict no-reply to automatic groups 2026-05-15 21:29:39 +01:00
Peter Steinberger
628c753f3b docs: document wildcard runtime policy 2026-05-15 20:50:49 +01:00
Peter Steinberger
b3d9bef38d [codex] Fix Codex OAuth refresh fallback (#82117)
* fix: fall back to Codex CLI OAuth after refresh failure

* fix: support Codex CLI fallback for named profiles
2026-05-15 12:32:00 +01:00
Ayaan Zaidi
f1b92c8885 fix(mantis): publish evidence to r2 (#81845)
* fix(mantis): publish evidence to r2

* ci(mantis): pass r2 artifact credentials

* ci(mantis): pin artifact bucket config

* fix(mantis): link raw evidence index
2026-05-15 16:23:53 +05:30
Kaspre
44840007d4 fix(agents): scope custom provider baseUrl SSRF trust by origin (#80751)
* fix(agents): scope provider SSRF trust by origin

* fix(provider): preserve explicit private-network deny

* docs(provider): document exact-origin SSRF trust

* test(provider): cover exact-origin SSRF edges

* docs(provider): align local model private-origin guidance

* refactor(ssrf): keep policy merging in infra

* test(ssrf): cover exact-origin trust through guard

* test(ssrf): block sibling private-origin redirects

* fix(provider): keep loopback trust origin-scoped

* fix(provider): block metadata origin trust

* fix(ssrf): keep metadata rebinding blocked

* fix(ssrf): block cloud metadata origins

* fix(ssrf): block ipv6 metadata origins

* fix(ssrf): block embedded metadata origins

* test(ssrf): cover embedded link-local metadata

* test(provider): cover custom anthropic proxy classification

* test(provider): widen transport policy mock

* test(plugin-sdk): assert metadata-IP allowedOrigins entries are rejected

Plugin authors can construct an SsrFPolicy that lists any well-formed
http(s) origin in allowedOrigins. The abuse-resistance lives one layer
deeper, in resolvePinnedHostnameWithPolicy's metadata/link-local block.
Add an SDK-level smoke test asserting that contract directly:

- AWS/Alibaba IMDS IPv4 literals, GCP metadata canonical hostname,
  IPv6 ULA metadata literal, and non-metadata link-local IPv4 entries
  build a policy via ssrfPolicyFromHttpBaseUrlAllowedOrigin and are
  then rejected at resolvePinnedHostnameWithPolicy.
- DNS rebinding from a trusted private DNS origin to a metadata IP is
  rejected even when the request hostname is origin-trusted.

This would fail if the SDK helper or resolveSsrFPolicyForUrl ever
short-circuited past the metadata block.

* chore(docs): regenerate baselines after upstream rebase

upstream/main moved between rebases; the merged source state for the
PR's `src/config/schema.help.ts` change and the upstream plugin-sdk
surface changes both produce different hashes than the committed
baselines, so `config:docs:check` and `plugin-sdk:api:check` would fail.

Regenerated via `pnpm config:docs:gen` + `pnpm plugin-sdk:api:gen` on
Crabbox; both baselines verified with their respective `--check`
generators.

* test(plugin-sdk): assert SSRF blocked error class

* fix(lint): satisfy exact-origin PR lint rules

* docs: clarify custom provider origin trust

* chore(docs): refresh plugin sdk api baseline

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-05-15 11:00:29 +01:00
Peter Steinberger
e30be460e1 fix: shorten stalled Codex recovery window 2026-05-15 10:19:37 +01:00
pashpashpash
1a5548203e Stream Codex preambles in channel progress drafts (#81887)
* codex: stream preambles in progress drafts

* test: update preamble progress PR checks

* test: refresh plugin sdk api baseline
2026-05-15 05:32:42 +09:00
Peter Steinberger
c9b6b0be0e fix(mantis): stop git-backed evidence publishing 2026-05-14 18:34:31 +01:00
Peter Steinberger
a0f35574d0 Remove codex-cli backend and migrate to Codex runtime
Remove the bundled codex-cli backend, migrate legacy codex-cli refs and runtime pins to the Codex app-server runtime, and update live/backend workflow coverage for the supported CLI lanes.
2026-05-14 10:07:18 +01:00
Jack Storment
b79c41d252 fix(memory): discover slugged daily memory files alongside date-only files
Widen daily memory filename discovery so slugged session-memory files flow through Dreaming, rem-backfill, rem-harness, doctor, and short-term promotion.

Preserve exact slugged source paths during historical seeding and rem-backfill attribution, including multiple files for the same day.

Add regression coverage for slugged ingestion, rem-backfill, rem-harness preview paths, and doctor backfill day extraction.

Fixes #69536.

Co-authored-by: Jack Storment <crazycoder131@gmail.com>
2026-05-14 09:17:44 +01:00
Jason
70df2b8fe2 feat: steer mid-turn prompts by default (#77023)
Summary:
- Default active-run queueing to steer while preserving explicit followup/collect modes.
- Keep `/steer` fallback behavior and migrate retired queue steering config.
- Await Codex app-server steering acceptance so rejected/aborted steering can fall back safely.
- Route active subagent announcements through intentional acceptance-aware steering, with legacy queue helpers deprecated for delivery decisions.

Verification:
- git diff --check
- rg -n "^(<<<<<<<|=======|>>>>>>>|\|\|\|\|\|\|\|)" CHANGELOG.md docs src extensions || true
- pnpm test src/agents/subagent-announce-dispatch.test.ts src/agents/subagent-announce-delivery.test.ts src/agents/pi-embedded-runner/runs.test.ts src/agents/subagent-announce.format.e2e.test.ts src/agents/subagent-announce.test.ts
- pnpm test src/auto-reply/reply/commands-steer.test.ts src/auto-reply/reply/queue/settings.test.ts src/auto-reply/reply/queue-policy.test.ts src/auto-reply/reply/agent-runner.runreplyagent.e2e.test.ts src/auto-reply/reply/get-reply-run.media-only.test.ts extensions/codex/src/app-server/run-attempt.test.ts -- -t "queued steering|explicit all-mode steering|flushes pending default queued steering|rejects queued steering|resolveActiveRunQueueAction|resolveQueueSettings|handleSteerCommand"

Co-authored-by: fuller-stack-dev <263060202+fuller-stack-dev@users.noreply.github.com>
2026-05-13 14:00:11 +01:00
Peter Steinberger
694ca50e97 Revert "refactor: move runtime state to SQLite"
This reverts commit f91de52f0d.
2026-05-13 13:33:38 +01:00