Commit Graph

7856 Commits

Author SHA1 Message Date
Mariano
7299c56953 Fix sub-agent cwd/workspace separation (#87218)
Merged via squash.

Prepared head SHA: f47b073830
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-05-27 23:55:24 +02:00
Kevin Lin
bb752c2b47 Revert "feat: expose plugin approval action metadata" (#87419)
This reverts commit 0c867eef75.

# Conflicts:
#	docs/.generated/plugin-sdk-api-baseline.sha256
2026-05-27 14:48:06 -07:00
Mariano Belinky
a7d2d9c6df fix: migrate legacy memory auto provider 2026-05-27 23:03:32 +02:00
GarlicGo
2900c1c25c fix(inbound-meta): include seconds in timestamps
Include second-level precision in inbound metadata and auto-reply envelope timestamps, matching the timestamp helper contract used by providers and channel adapters.

Docs now show the weekday plus seconds form in date-time and timezone examples.

Verification:
- node scripts/run-vitest.mjs src/auto-reply/envelope.test.ts src/auto-reply/reply/inbound-meta.test.ts
- pnpm docs:list >/tmp/openclaw-docs-list-87360.log
- git diff --check origin/main...HEAD
- pnpm format:docs:check
- pnpm lint:docs
- pnpm lint:extensions:bundled
- pnpm lint
- PR CI green on 495bb6c10f

Fixes #87257

Co-authored-by: GarlicGo <582149912@qq.com>
2026-05-27 21:18:08 +01:00
Peter Steinberger
d93524d1cc fix(codex): route workspace memory through tools (#87383)
* fix(codex): route workspace memory through tools

* fix(codex): preserve extra memory bootstrap files

* fix(codex): support memory_get-only context routing

* fix(codex): only tool-route canonical workspace memory

* fix(codex): keep memory fallback for sandbox workspaces
2026-05-27 20:55:27 +01:00
keshavbotagent
e339586750 fix(plugin-state): evict current namespace on plugin row cap
Make plugin-state enforce the plugin-wide live-row fuse by evicting only from the namespace currently being written, preserving sibling namespace rows and still failing atomically when the current namespace cannot free enough rows.

Raise the plugin-wide cap to 6,000 rows, keep Telegram's persistent message-cache namespace at 3,000 entries, and document the updated SDK runtime contract. Harden legacy plugin-state import so capacity pressure cannot archive a source after losing imported keys, with focused regression coverage for Telegram-shaped namespaces and migration rollback.

Also restore the Docker runtime-assets preflight step in full release validation so release workflow contract tests stay aligned.

Verification: focused plugin-state, migration, Telegram, workflow-contract, lint, deprecated-API, diff-check, Blacksmith Testbox, CI, CodeQL, Workflow Sanity, OpenGrep, and autoreview all passed on PR head fee021cfa6.

Co-authored-by: Keshav's Bot <keshavbotagent@gmail.com>
2026-05-27 20:33:40 +01:00
Patrick Erichsen
ee57f341f0 Add ClawHub skill verification and trust surfaces (#86699)
* feat(skills): fetch ClawHub skill verification

* feat(skills): resolve ClawHub verification targets

* feat(skills): add ClawHub verify command

* docs(skills): document ClawHub verification

* test(skills): type verify CLI fixture

* fix(skills): fetch verified skill card URL

* fix(skills): bound verified card downloads

* fix(skills): fail closed on malformed verification

* fix(skills): corroborate ClawHub install origins

* feat(skills): surface ClawHub trust in control UI

* chore(protocol): refresh generated gateway models

* chore(ui): refresh i18n raw copy baseline

* docs: clarify skills verify wording

* fix: fail closed on skill trust mismatches

* fix: reject incomplete clawhub provenance

* fix: satisfy trust verdict lint

* fix: restore ci checks after main merge
2026-05-27 14:23:24 -05:00
Peter Steinberger
6727985365 docs: add macOS gateway sleep troubleshooting
Refs: #87337
Co-authored-by: Arunjeet Singh <arunjeetsingh@gmail.com>
2026-05-27 19:52:56 +01:00
Peter Steinberger
da1a3434f4 docs: document native Codex hook relay recovery 2026-05-27 19:46:56 +01:00
Peter Steinberger
bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* refactor: extract agent core package

Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.

* refactor: extract shared llm runtime

Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.

* refactor: remove pi runtime internals

Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.

* refactor: tighten agent session runtime

Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.

* refactor: remove static model and pi auth paths

Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.

* refactor: remove legacy provider compat paths

* docs: remove agent parity notes

* fix: skip provider wildcard metadata parsing

* refactor: share session extension sdk loading

* refactor: inline acpx proxy error formatter

* refactor: fold edit recovery into edit tool

* fix: accept extension batch separator

* test: align startup provider plugin expectations

* fix: restore provider-scoped release discovery

* test: align static asset packaging expectations

* fix: run static provider catalogs during scoped discovery

* fix: add provider entry catalogs for scoped live discovery

* fix: load lightweight provider catalog entries

* fix: refresh provider-scoped plugin metadata

* fix: keep provider catalog entries on release live path

* fix: keep static manifest models in release live checks

* fix: harden release model discovery

* fix: reduce OpenAI live cache probe reasoning

* fix: disable OpenAI cache probe reasoning

* ci: extend OpenAI gateway live timeout

* fix: extend live gateway model budget

* fix: stabilize release validation regressions

* fix: honor provider aliases in model rows

* fix: stabilize release validation lanes

* fix: stabilize release memory qa

* ci: stabilize release validation lanes

* ci: prefer ipv4 for live docker node calls

* fix: restore shared tool-call stream wrapper

* ci: remove legacy pi test shard alias

* fix: clean up embedded agent test drift

* fix: stabilize runtime alias status

* fix: clean up embedded agent ci drift

* fix: restore release ci invariants

* fix: clean up post-rebase runtime drift

* fix: restore release ci checks

* fix: restore release ci after rebase

* fix: remove stale pi runtime path

* test: align compaction runtime expectations

* test: update plugin prerelease expectations

* fix: handle claude live tool approvals

* fix: stabilize release validation gates

* fix: finish agent runtime import

* test: finish post-rebase agent runtime mocks

* fix: keep codex compaction native

* fix: stabilize codex app-server hook tests

* test: isolate codex diagnostic active run

* test: remove codex diagnostic completion race

# Conflicts:
#	extensions/codex/src/app-server/run-attempt.test.ts

* ci: fix full release manifest performance run id

* refactor: narrow llm plugin sdk boundary

* chore: drop generated google boundary stamps

* fix: repair rebase fallout

* fix: clean up rebased runtime references

* fix: decode codex jwt payloads as base64url

* fix: preserve shipped pi runtime alias

* fix: add scoped sdk virtual modules

* fix: decode llm codex oauth jwt as base64url

* fix: avoid stale vertex adc negative cache

* fix: harden tool arg decoding and codeql path

* fix: keep vertex adc negative checks live

* refactor: consolidate codex jwt and edit helpers

* fix: await codex oauth node runtime imports

* fix: preserve sdk tool and notice contracts

* fix: preserve shipped compat config boundaries

* fix: align codex oauth callback host

* fix: terminate agent-core loop streams on failure

* fix: keep codex oauth callback alive during fallback

* ci: include session tools in critical codeql scans

* fix: keep Cloudflare Anthropic provider auth header

* docs: redirect legacy pi runtime pages

* fix: honor bundled web provider compat discovery

* fix: protect session output spill files

* fix: keep legacy agent dir env blocked

* fix: contain auto-discovered skill symlinks

* fix: harden agent core sdk proxy surfaces

* fix: restore approval reaction sdk compat

* fix: keep live docker runs bounded

* fix: keep codex oauth redirect host aligned

* fix: resolve post-rebase agent runtime drift

* fix: redact anthropic oauth parse failures

* fix: preserve responses strict tool shaping

* fix: repair agent runtime rebase cleanup

* docs: redirect retired parity pages

* fix: bound auto-discovered resources to roots

* fix: repair post-rebase agent test drift

* fix: preserve bundled provider allowlist migration

* fix: preserve manifest-owned provider aliases

* fix: declare photon image dependency

* fix: keep provider headers out of proxy body

* fix: preserve shipped env aliases

* fix: refresh control ui i18n generated state

* fix: quote read fallback paths

* fix: preview edits through configured backend

* test: satisfy core test typecheck

* fix: preserve ZAI usage auth fallback

* test: repair codex diagnostic test

* fix: repair agent runtime rebase drift

* test: finish embedded runner import rename

* fix: repair agent runtime rebase integrations

* test: align compaction oauth fallback expectations

* fix: allow sdk-auth session models

* fix: update doctor tool schema import

* fix: preserve bedrock plugin region

* fix: stream harmony-like prose immediately

* ci: include session runtime in codeql shards

* fix: repair latest rebase integrations

* fix: honor explicit codex websocket transport

* fix: keep openai-compatible credentials provider-scoped

* fix: refresh sdk api baseline after rebase

* fix: route cli runtime aliases through openclaw harness

* test: rename stale harness mock expectation

* test: rename embedded agent overflow calls

* test: clean embedded auth test wording

* test: use openclaw stream types in deepinfra cache test

* fix: refresh sdk api baseline on latest main

* fix: honor bundled discovery compat allowlists

* fix: refresh sdk api baseline after latest rebase

* fix: remove stale rebase imports

* test: rename stale model catalog mock

* test: mock renamed doctor runtime modules

* fix: map canonical kimi env auth

* fix: use internal model registry in bench script

* fix: migrate deepinfra provider catalog entry

* fix: enforce builtin tool suppression

* fix: route compaction auth and proxy payloads safely

* refactor: prune unused llm registry leftovers

* test: update codex hooks session import

* test: fix model picker ci coverage

* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00
Dallin Romney
cff8e4383c expand default diffs languages (#87372) 2026-05-27 11:14:16 -07:00
Peter Steinberger
a4d33fd81b docs: clarify container model auth 2026-05-27 19:04:04 +01:00
Andi Liao
085228c961 fix(auth): document paste-token stdin setup (#63050)
Document that automation should pipe `models auth paste-token` credentials over stdin instead of passing token material in argv, keeping the existing secret-handling path explicit in the CLI docs.

Also include accepted auth-profile credential types in invalid-profile warning logs so malformed local auth stores are easier to repair.

Fixes #63042.

Thanks @liaoandi.
2026-05-27 18:44:44 +01:00
Peter Steinberger
c3b7e91f26 docs: clarify device token admin gate 2026-05-27 18:35:27 +01:00
Ben Badejo
7691a8a9a3 docs(codex): clarify computer use setup (#87313)
Clarify the Codex Computer Use docs around inferred opt-in, read-only status checks, and marketplace root versus marketplace JSON path setup.

The docs now match current source-backed behavior: autoInstall opts Computer Use in, status does not mutate plugin setup, and marketplacePath is for a local marketplace JSON file while source registers a marketplace root.

Verification:
- pnpm docs:list
- GitHub CI check-docs passed
- Real behavior proof passed via maintainer proof override for this docs-only PR

Thanks @bdjben.

Co-authored-by: Benjamin Badejo <ben@benbadejo.com>
Co-authored-by: Sally O'Malley <somalley@redhat.com>
2026-05-27 18:35:21 +01:00
Dallin Romney
d638611684 feat: split diffs language pack
Split the diffs viewer Shiki language pack into an external publishable plugin.

The diffs plugin keeps the default curated syntax set, while the new @openclaw/diffs-language-pack package carries the extended Shiki languages for npm and ClawHub distribution. The install metadata includes the external ClawHub spec, and the curated C# alias set keeps both c# and cs supported without the language pack.

Co-authored-by: Dallin Romney <dallinromney@gmail.com>
2026-05-27 18:08:40 +01:00
Shadow
930d9f63ad docs: expand install deployment cards 2026-05-27 11:54:12 -05:00
Peter Steinberger
7aaca4a8a6 chore(release): prepare 2026.5.27 2026-05-27 16:53:50 +01:00
Agustin Rivera
0d0bddf032 fix(gateway): require admin for device role approvals (#87146)
* fix(gateway): require admin for device role approvals

* fix(gateway): add trusted-proxy approval proof
2026-05-27 08:08:51 -07:00
Pavan Kumar Gondhi
91590132f6 Block unsafe Node runtime env overrides [AI] (#87308)
* fix: block unsafe node runtime env overrides

* fix: block node env path redirects

* docs: add changelog entry for PR merge
2026-05-27 20:34:12 +05:30
Mariano
c9d4f7e35c Deprecate memory-specific embedding provider registration (#85072)
Merged via squash.

Prepared head SHA: 661eb99066
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-05-27 15:24:17 +02:00
Peter Steinberger
8e5183c60d refactor: move channel message sdk compat into core 2026-05-27 13:59:33 +01:00
Yuval Dinodia
ef77428c95 fix(openai): normalize responses replay tool ids
Fixes #74665.

Normalize replayed OpenAI Responses tool call identifiers before same-model pi-ai replay sends them back to the provider. This keeps canonical `call_*|fc_*` pairs intact when valid, rewrites overlong or malformed `function_call.call_id`, `function_call.id`, and matching `function_call_output.call_id` values into OpenAI's accepted 64-character shape, and preserves the reasoning replay path.

Verification:
- Live OpenAI E2E with maintainer key: raw replay payload failed with HTTP 400 for overlong `input[1].id`; normalized replay succeeded with HTTP 200 and `LIVE_OK`.
- `pnpm exec oxfmt --check --threads=1 src/agents/pi-embedded-helpers/openai.ts`
- `CI=1 OPENCLAW_VITEST_FS_MODULE_CACHE_PATH="$(mktemp -d /tmp/openclaw-vitest-cache.XXXXXX)" fnm exec --using 24.15.0 -- pnpm test src/agents/pi-embedded-runner/run/attempt.tool-call-normalization.test.ts -- --run --reporter=verbose --maxWorkers=1`
- `CI=1 OPENCLAW_VITEST_FS_MODULE_CACHE_PATH="$(mktemp -d /tmp/openclaw-vitest-cache.XXXXXX)" fnm exec --using 24.15.0 -- pnpm test src/agents/pi-embedded-runner.openai-tool-id-preservation.test.ts src/agents/openai-responses.reasoning-replay.test.ts -- --run --reporter=verbose --maxWorkers=2`
- `autoreview --mode branch --base origin/main`: clean, no accepted/actionable findings.
- GitHub CI green on c675b35ade.

Co-authored-by: Yuval Dinodia <yetvald@gmail.com>
2026-05-27 13:51:57 +01:00
Bob
4d89e00c50 feat(embeddings): add OpenAI-compatible core provider (#85269)
Merged via squash.

Prepared head SHA: dc9a5d5397
Co-authored-by: dutifulbob <261991368+dutifulbob@users.noreply.github.com>
Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com>
Reviewed-by: @mbelinky
2026-05-27 14:37:17 +02:00
rendrag-git
e153eceea5 fix(vllm): wire configured thinking params
Move vLLM Qwen thinking control onto configured model compat metadata and carry it through catalog/model-selection/runtime thinking contexts.

Also migrate legacy provider/default request params in doctor and keep Pi/runtime model rows buildable with explicit reasoning defaults.

Thanks @rendrag-git.

Co-authored-by: rendrag-git <253747599+rendrag-git@users.noreply.github.com>
2026-05-27 13:32:18 +01:00
Mason Huang
75221e0550 fix(agents): separate heartbeat runtime template (#85416)
Summary:
- The PR moves the runtime `HEARTBEAT.md` bootstrap template into `src/agents/templates`, keeps docs templates ... or other workspace files, adds a legacy heartbeat-template doctor repair, and updates package guards/tests.
- PR surface: Source +281, Tests +283, Docs +11, Config +1, Other 0. Total +576 across 15 files.
- Reproducibility: yes. from source inspection: current main loads `HEARTBEAT.md` from the docs template, and  ... pty heartbeat file non-empty to the runtime. I did not run a live heartbeat repro in this read-only review.

Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(doctor): recognize heartbeat docs boilerplate
- PR branch already contained follow-up commit before automerge: fix(agents): update heartbeat workspace test
- PR branch already contained follow-up commit before automerge: fix(doctor): tighten heartbeat template repair

Validation:
- ClawSweeper review passed for head e34e85864c.
- Required merge gates passed before the squash merge.

Prepared head SHA: e34e85864c
Review: https://github.com/openclaw/openclaw/pull/85416#issuecomment-4519851630

Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
2026-05-27 12:30:22 +00:00
Peter Steinberger
3e351b718e fix(agents): honor OpenAI-compatible cache retention
Carry over #82973 and fix #81281 by preserving explicit cacheRetention for OpenAI-compatible completions providers that opt into prompt-cache-key support.

The change keeps explicit cacheRetention suppressed for OpenAI-compatible providers without compat.supportsPromptCacheKey, adds regression coverage for both paths, and updates prompt-caching docs for prompt_cache_key / prompt_cache_retention behavior.

Fixes #81281.
Supersedes #82973.

Co-authored-by: lonexreb <reach2shubhankar@gmail.com>
2026-05-27 13:21:23 +01:00
Peter Steinberger
517ce3df75 fix: require admin for node device approvals 2026-05-27 13:18:50 +01:00
Vincent Koc
53662094c3 chore(pixverse): publish as external plugin 2026-05-27 12:41:10 +02:00
Vincent Koc
b3083de4f2 feat(pixverse): add api region selection 2026-05-27 12:41:10 +02:00
Vincent Koc
c18370574e feat(pixverse): add video generation provider 2026-05-27 12:41:10 +02:00
Peter Steinberger
6c3740255f refactor: remove channel turn runtime aliases 2026-05-27 11:37:23 +01:00
Georgi Atsev
9e7c2b356b fix(deepinfra): load all DeepInfra models when user wants to browse t… (#84549)
* fix(deepinfra): load all DeepInfra models when user wants to browse them during onboarding

* docs(deepinfra): align TTS default

* fix(deepinfra): refresh video fallbacks

* fix(deepinfra): share credential-aware catalog discovery

* test(deepinfra): narrow catalog regression types

* test(deepinfra): keep catalog narrowing across callback

* fix(deepinfra): preserve default model in live catalog

* fix(deepinfra): align default model pricing

* fix(deepinfra): keep pixverse as video default

* docs(deepinfra): match video fallback default

* fix(deepinfra): honor config api keys for live catalog

* test(e2e): wait for watchdog stdio close

* test(media): align live harness provider expectation

* fix(deepinfra): always augment custom catalogs

* test(e2e): resolve watchdog commands before spawning

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-05-27 10:43:37 +01:00
Peter Steinberger
c89298f9f8 fix: preserve channel runResolved mock compatibility 2026-05-27 10:36:33 +01:00
Sebastien Tardif
527b7c2eed fix(install): skip Homebrew until macOS packages need it
Keep macOS Homebrew setup lazy so users with supported Node and Git can install without admin/Homebrew, while still installing Homebrew before macOS Node or Git package installs.

Updates installer docs and adds focused install.sh coverage for the lazy Git path. Also aligns the live-media provider expectation with current main so built-artifact checks stay green.

Fixes #83232

Co-authored-by: Sebastien Tardif <sebtardif@ncf.ca>
2026-05-27 09:48:04 +01:00
Peter Steinberger
1507a9701b refactor: centralize inbound supplemental context
* refactor: centralize inbound supplemental context

* refactor: trim supplemental finalizer typing

* docs: clarify supplemental context projection

* refactor: move inbound finalization into core

* refactor: simplify channel inbound facts

* refactor: fold supplemental media into inbound finalizer

* refactor: migrate channel inbound callers to builder

* docs: mark inbound finalizer compat types deprecated

* refactor: wire runtime turn context builder

* refactor: replace channel turn runtime API

* fix: respect discord quote visibility

* fix: avoid deprecated line dispatch helper

* refactor: deprecate channel message SDK seams

* docs: trim channel outbound SDK page

* test: migrate irc inbound assertion

* refactor: deprecate outbound SDK facades

* refactor: deprecate channel helper SDK facades

* refactor: deprecate channel streaming SDK facade

* refactor: move direct dm helpers into inbound SDK

* chore: mark legacy test-utils SDK alias deprecated

* refactor: remove unused allow-from read helper

* refactor: route remaining channel dispatch through core

* refactor: enforce modern extension SDK imports

* test: give slow image root tests more time

* ci: support node fallback on windows

* fix: add transcripts tool display metadata

* refactor: trim legacy channel test seams

* fix: preserve channel compat after rebase

* fix: keep deprecated channel inbound aliases

* fix: preserve discord thread context visibility

* fix: clean final rebase conflicts

* fix: preserve channel message dispatch aliases

* fix: sync channel refactor after rebase

* fix: sync channel refactor after latest main

* fix: dedupe memory-core subagent mock

* test: align clickclack inbound dispatch assertions

* fix: sync plugin sdk api hash after rebase

* fix: sync channel refactor after latest main

* fix: sync plugin sdk api hash after rebase

* fix: sync plugin sdk api hash after latest main

* test: remove stale inbound context awaits
2026-05-27 09:26:06 +01:00
Shubhankar Tripathy
717003aaff docs(providers/openai): clarify OpenAI Realtime Platform credits
Clarify that OpenAI Realtime voice is billed through OpenAI Platform credits, not Codex/ChatGPT subscription quota, for Voice Call and Control UI Talk.

Document the direct Platform API key path, the `openai-codex` OAuth client-secret path, the quota symptom, and the Platform billing fix. Keep the changelog note crediting @lonexreb.

Closes #76498.

Co-authored-by: lonexreb <reach2shubhankar@gmail.com>
2026-05-27 08:51:26 +01:00
Agustin Rivera
08a73dbe4b fix(qqbot): gate fallback approval buttons (#87154)
QQBot fallback approval buttons now reuse the same slash-command authorization path as real commands, including access groups and default-account config merging.

Verification:
- node scripts/test-extension.mjs qqbot
- node --max-old-space-size=8192 --import tsx scripts/generate-plugin-sdk-api-baseline.ts --check && git diff --check
- pnpm lint --threads=8
- node scripts/run-vitest.mjs src/agents/agent-command.live-model-switch.test.ts
- GitHub PR checks for 7cc0f15031: passed

Thanks @eleqtrizit.

Co-authored-by: Agustin Rivera <agustin@rivera-web.com>
2026-05-27 08:44:55 +01:00
clawsweeper[bot]
f4e20f806e fix(agents): avoid duplicate Claude CLI skill prompts
Fix Claude CLI skill prompt handling so native skill plugin materialization is prepared before prompt suppression, with the prompt fallback preserved when plugin args are unavailable. Also keeps direct prepared-run callers covered by an execute-time fallback.

Fixes #87063.

Co-authored-by: uday <udaymanish.thumma@gmail.com>
2026-05-27 08:34:34 +01:00
Dallin Romney
780bc79147 fix(plugin-sdk): stop exporting vitest test helpers (#87120) 2026-05-26 23:10:41 -07:00
Agustin Rivera
2c88547254 fix(prompt): route untrusted group prompts outside system prompt [AI] (#87144)
* fix(prompt): route untrusted group prompts outside system prompt

* fix(prompt): align untrusted group prompt helpers
2026-05-26 22:47:54 -07:00
Pablo Guardiola
0c867eef75 feat: expose plugin approval action metadata
Expose plugin approval action metadata so plugins can describe richer approval actions across gateway, SDK, channel, and UI surfaces.
2026-05-26 22:46:09 -07:00
Agustin Rivera
e72621e566 fix(hooks): enforce default hook agent allowlist
Enforce hook allowedAgentIds against the effective default agent when hook payloads omit or blank agentId, while preserving omitted-agent dispatch semantics for default/global routing.

Also updates the affected generated hook config docs from the contributor change and fixes the current-main memory-core test mock after rebasing the PR branch.

Verification:
- pnpm format:check extensions/memory-core/src/dreaming.test.ts src/gateway/hooks.ts src/gateway/hooks.test.ts src/gateway/server/hooks-request-handler.ts src/gateway/server.hooks.test.ts && git diff --check
- node scripts/run-vitest.mjs run --config test/vitest/vitest.gateway-server.config.ts src/gateway/hooks.test.ts src/gateway/server.hooks.test.ts --reporter=dot --pool=forks --no-file-parallelism --testTimeout=120000
- node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.extensions.test.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/extensions-test-local-pr87124.tsbuildinfo
- pnpm check:test-types
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- GitHub PR merge state CLEAN; CodeQL Critical Quality rerun succeeded after first runner checkout wedged

Co-authored-by: Agustin Rivera <agustin@rivera-web.com>
2026-05-27 05:05:18 +01:00
Peter Steinberger
231a812276 build(codex): update Codex CLI to 0.134.0 2026-05-27 04:42:12 +01:00
Peter Steinberger
0cfccdb0c7 fix(codex): keep WebChat delivery hints out of user requests
Land PR #87003 from @ragesaq with a maintainer fix for routed room events.

Co-authored-by: Forge <forge@psiclawops.dev>
2026-05-27 03:44:27 +01:00
Samuel Soares da Silva
286964cd6a fix(diagnostics): recover orphaned session activity
Recover idle queued sessions whose diagnostic activity retained stale ownerless model or tool calls by classifying them as recoverable session.stuck after the usual recovery gates. Yield the event loop before stale session-lock process inspection so sync process lookup cannot monopolize lock contention paths.

Docs now describe the widened session.stuck telemetry contract for recoverable stale bookkeeping, including ownerless activity. Thanks @samuelsoaress.

Refs #84903.

Co-authored-by: samuelsoaress <samuelsoares177778@gmail.com>
2026-05-27 02:47:42 +01:00
uday
0f18d52f16 fix(codex): raise dynamic tool timeout 2026-05-27 01:25:48 +01:00
Peter Steinberger
a1934e9d0e fix(cli): handle Bun launcher module misses
Fixes #86198.

Co-authored-by: Gio Della-Libera <giodl73@gmail.com>
2026-05-27 01:20:14 +01:00
Peter Steinberger
69d84d775b fix(docs): use Cloudflare docs search API 2026-05-27 00:58:09 +01:00
Abdel Gomez-Perez
474b1e0386 fix(cli-runner): scale Claude CLI reseed history automatically
Remove the proposed public `maxReseedHistoryChars` config surface and scale Claude CLI reseed history automatically from the resolved context tier instead.

Claude CLI 200K-context runs now keep a 64K-character reseed slice, 1M Opus/Sonnet runs use the bounded 256KiB cap, and non-Claude CLI backends keep the existing 12KiB default. This preserves the intended long-context behavior without adding another config option.

Verification:
- `node scripts/run-vitest.mjs src/agents/cli-runner/session-history.test.ts src/agents/cli-runner/prepare.test.ts`
- `node scripts/run-vitest.mjs src/agents/cli-runner/prepare.test.ts -t "automatic Claude CLI cap"`
- `node scripts/run-oxlint.mjs src/agents/cli-runner/prepare.ts src/agents/cli-runner/prepare.test.ts src/agents/cli-runner/session-history.ts src/agents/cli-runner/session-history.test.ts src/config/types.agent-defaults.ts src/config/zod-schema.core.ts`
- `pnpm check:changed` via Testbox `tbx_01kska2twjxb925xft9dj82hvb`
- GitHub PR checks green

Closes #83985
Co-authored-by: Abdel Gomez-Perez <nabdel07@icloud.com>
2026-05-27 00:41:01 +01:00