vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-07-16 17:31:42 +00:00
Code Issues Packages Projects Releases Wiki Activity
65,965 Commits 1,843 Branches 149 Tags
8d5f7e27b2ffd233e262fbe4e00f09bc201ce068
Commit Graph

751 Commits

Author SHA1 Message Date
JC
59e95fe3fd feat: support GPT-5.6 Ultra across OpenClaw and Codex runtimes (#98021) 
* feat: support GPT-5.6 Ultra across agent runtimes

Co-authored-by: J Cai <anyech@gmail.com>

* fix: keep harness projections discovery-free

* fix(codex): mirror V2 native subagent tasks

* chore: refresh plugin SDK surface budgets

* test: expose Ultra wire effort proof

* test(cron): avoid hoisted mock initialization race

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-07-10 15:23:24 +01:00
Peter Steinberger
ab5d143d59 feat(openai): default new setups to GPT-5.6 (#103581) 
* feat(openai): default fresh setup to GPT-5.6

* test(crestodian): expect GPT-5.6 Codex defaults

* test(crestodian): expect GPT-5.6 bootstrap default
 2026-07-10 10:22:58 +01:00
Peter Steinberger
461772868d fix(computer): prevent stale, replayed, and post-cancel desktop actions (#103422) 
* fix(ai): preserve streamed tool-call identity

* fix(computer): bind actions to current tool authority

* fix(macos): serialize computer control lifecycle

* docs(computer): document hardened control contract

* chore: follow release-owned changelog policy

* test(agents): cover node list cancellation
 2026-07-10 06:47:56 +01:00
Peter Steinberger
4a40f5d7f0 fix(xai): align image and video capability contracts (#103384) 
* fix(xai): align media capability contracts

* chore: move xai media release note to pr
 2026-07-10 06:06:50 +01:00
Peter Steinberger
75dfd3dc09 feat(xai): support Grok Imagine Video 1.5 (#103316) 
* feat(media): add per-model generation catalog metadata

* feat(xai): support Grok Imagine Video 1.5

* test(plugin-sdk): update public surface budget
 2026-07-10 04:49:42 +01:00
Peter Steinberger
d8624a4e1b fix: fail release performance when reports do not publish (#103126) 
* fix(ci): harden performance report publishing

* ci: use scoped app token for reports

* ci: pin Kova readiness probe fix

* ci: pin latest Kova readiness checks

* ci: pin Kova startup sequencing fix

* ci: pin calibrated Kova release policy
 2026-07-10 01:27:26 +01:00
Peter Steinberger
fc5a4defaf feat(cohere): add current Command models (#102563) 
* feat(cohere): add current Command models

* docs: keep release notes out of PR
 2026-07-09 11:07:50 +01:00
Peter Steinberger
eae3fc1a79 feat(xai): add Grok 4.5 support (#102316) 
* feat(xai): add Grok 4.5 support

* chore: leave release notes to release automation
 2026-07-09 01:39:03 +01:00
Peter Steinberger
21d919deb8 fix(onboard): keep the wizard alive through provider auth failures and polish standalone install UX (#100632) 
Fixes rough edges in the standalone install flow (install.sh -> openclaw onboard), found and verified by running the flow in a clean container and on a clean macOS Tahoe VM:

- Provider auth setup failures (e.g. the preselected "Anthropic Claude CLI" option on a host without a Claude CLI login) no longer kill the whole wizard. The interactive wizard notes the error and returns to the provider picker; explicit --auth-choice automation still fails fast.
- Onboarding config now persists before the channel/search/skills steps, so a crash or cancel during channel pairing no longer loses auth + gateway decisions.
- With model auth skipped, finalize no longer auto-sends the "Wake up, my friend!" message (which always failed with a provider auth error). The hatch seed is gated on usable model credentials and a "Model auth missing" note explains the next step.
- Search provider picker no longer labels non-key credentials (e.g. SearXNG base URL) as "API key required".
- install.sh no longer warns "PATH missing npm global bin dir" with manual fix steps after it already persisted the export line; it reports the PATH was updated and how to reload the current shell.
- Removed the dead interactive hooks onboarding step (setupInternalHooks); quickstart enables default hooks silently.

Verified live per fix in a clean Debian/Node 24 container and on a clean macOS 26.5 Parallels VM (wizard re-prompt, SearXNG label), plus wizard/onboard test suites and tsgo:core.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
 2026-07-07 04:11:23 +01:00
ianchen08
a27e3f3a99 fix(auto-reply): stop treating wait as abort trigger (#98639) 
* fix(auto-reply): stop treating wait as abort trigger

* test(channels): treat wait as debounced text

* docs: remove wait from abort phrases

---------

Co-authored-by: Ian Chen <ianchen@IandeMBP.home>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-07-07 03:03:23 +01:00
Dallin Romney
b29d472e41 refactor(qa): add canonical live channel adapters (#99707) 2026-07-06 09:24:34 -07:00
Peter Steinberger
3cf0d00d90 docs: align source contract wording (#100186) 2026-07-05 01:41:40 -04:00
Peter Steinberger
53bdac249d docs: restore source-backed contract details (#100182) 2026-07-05 01:26:25 -04:00
Peter Steinberger
f7d7148cf0 docs: rewrite published docs grounded in current source (#100142) 
Source-grounded rewrite of 529 published docs pages with per-unit information-loss verification: 1,713 factual corrections cited to src/**, generated surfaces regenerated, frontmatter titles preserved for i18n, release notes pages untouched. All docs gates green.

Closes #100141
 2026-07-05 00:32:47 -04:00
Kevin Lin
d214622320 feat(update): support extended-stable package updates (#99811) 
* feat(update): add extended-stable channel contract

* feat(update): implement extended-stable package flow

* docs(update): document extended-stable behavior

* fix(update): preserve extended-stable preflight guarantees

* fix(update): reject extended-stable Git repair

* fix(update): support loopback extended-stable canaries

* fix(update): preserve scoped package roots
 2026-07-04 12:34:29 -07:00
Vincent Koc
f53fdb688d fix(qa): restore package docker gates 2026-07-04 01:56:21 +02:00
Jesse Merhi
64318d7624 Rework Android gateway onboarding setup (#98752) 
* feat(android): rework gateway onboarding setup

* fix(android): restore protocol mismatch onboarding guidance

* fix(android): sync onboarding native i18n

* fix(android): preserve LAN manual setup prefill

* fix(android): refine onboarding node approval step

* fix(android): polish onboarding recovery actions

* test(android): cover onboarding protocol mismatch copy

* fix(android): separate onboarding node approval

* fix(android): guard onboarding node approval transitions

* fix(android): keep onboarding approval states reachable

* fix(android): wait for node access before onboarding continue

* fix(android): refresh node approval after operator handoff

* fix(android): refresh onboarding approval states

* fix(android): require approval after onboarding permission changes

* fix(android): keep onboarding approval gates active

* fix(android): preserve permission reapproval state

* fix(android): skip node approval on legacy gateways

* fix(android): wait for node approval refresh

* fix(android): preserve camera setting on upgrade

* fix(android): avoid stuck approval check spinner

* fix(android): request talk secrets on operator connects

* fix(android): avoid missed node approval completion

* fix(android): keep nearby LAN setup local

* fix(android): complete onboarding after node approval

* fix(android): reconcile onboarding with gateway auth plans

* chore(android): refresh native i18n inventory after rebase

* Fix Android onboarding review edge cases

* Fix native i18n onboarding sentinels
 2026-07-03 21:20:12 +10:00
Mason Huang
5ff247b99e test: prefer auto-cleaning temp dir helper (#93209) 
Summary:
- The branch adds `useAutoCleanupTempDirTracker()`, broadens the temp-dir warning reporter to flag new manual helper imports/usages, updates docs, and migrates two script tests to the new helper.
- PR surface: Tests +301, Docs +1, Other +248. Total +550 across 8 files.
- Reproducibility: not applicable. this is test/tooling cleanup, and the changed behavior is exercised through helper/reporter tests and CI evidence rather than a user reproduction path.

Automerge notes:
- PR branch already contained follow-up commit before automerge: test: harden temp dir helper guard
- PR branch already contained follow-up commit before automerge: test: clarify auto cleanup temp dir helper name
- PR branch already contained follow-up commit before automerge: test: cover existing mkdtemp temp dir forms
- PR branch already contained follow-up commit before automerge: test: read staged temp helper source from index

Validation:
- ClawSweeper review passed for head 1fdd7d2a9a.
- Required merge gates passed before the squash merge.

Prepared head SHA: 1fdd7d2a9a
Review: https://github.com/openclaw/openclaw/pull/93209#issuecomment-4705653665

Co-authored-by: Mason Huang <masonxhuang@tencent.com>
Approved-by: hxy91819
 2026-07-02 02:46:28 +00:00
Tirion Prole
928aa3ea7e [codex] Update Claude CLI billing docs (#96848) 
* Update Claude CLI billing docs

* Sync Claude live testing billing note
 2026-06-28 11:03:17 -07:00
Ben.Li
a5379472f7 feat(onboard): show setup timeline note (#97482) 
* feat(onboard): show setup timeline note

* test(agents): stabilize retained lock CI flakes
 2026-06-28 10:47:11 -07:00
Dallin Romney
4a503ed45e docs: add maturity docs routes (#91483) 2026-06-23 23:59:47 -07:00
Vincent Koc
9d381d4530 docs(testing): document openshell e2e prerequisites 2026-06-24 14:07:30 +08:00
Patrick Erichsen
f66e83154b docs: update ClawHub skill route references 
Update OpenClaw ClawHub docs and user-facing copy for canonical owner-qualified skill routes.\n\nEvidence:\n- pnpm docs:list\n- pnpm test src/plugins/clawhub.test.ts src/cli/plugins-cli.install.test.ts src/gateway/server-methods/skills.clawhub.test.ts ui/src/ui/views/skills.test.ts\n- pnpm exec oxfmt --check --threads=1 docs/clawhub/cli.md docs/clawhub/publishing.md docs/cli/skills.md docs/help/faq.md docs/start/showcase.md docs/tools/creating-skills.md docs/tools/skills.md src/gateway/server-methods/skills.clawhub.test.ts src/plugins/clawhub.test.ts src/plugins/clawhub.ts ui/src/ui/views/skills.test.ts\n- git diff --check\n- exact-head hosted CI passed for 8530374388d8a73235b2ac8444b95a4a4c7d0f1c\n\nNote: repo-native scripts/pr prepare-run was attempted; local broad pnpm test was stopped after unrelated existing failures in agent/media/provider shards, while hosted exact-head CI and targeted ClawHub route/copy validation were green.
 2026-06-22 22:27:57 -07:00
Dallin Romney
4460fa78c3 feat(qa): add "all" taxonomy profile (#95947) 
* qa: add all maturity profile

* test: update qa coverage profile expectations
 2026-06-22 20:49:08 -07:00
Vincent Koc
2b75806197 feat: forward-port fast talks auto mode (#85104) 2026-06-22 09:37:09 +08:00
Vincent Koc
21728777df feat(plugins): externalize official provider batch 2026-06-19 01:05:52 +08:00
Vincent Koc
beea31a6b5 feat(firecrawl): add keyless scrape support (#94551) 
Merged under maintainer approval while exact-head CI was queue-bound.

Co-authored-by: Developers Digest <124798203+developersdigest@users.noreply.github.com>
Co-authored-by: Vincent Koc <vincentkoc@users.noreply.github.com>
 2026-06-19 00:23:41 +08:00
Vincent Koc
1ae0eacf4b fix(scripts): avoid downgrade release upgrade baselines 2026-06-16 09:35:39 +02:00
Dallin Romney
e32929e12c Add slim evidence mode for QA profile evidence (#93179) 
* test(qa): compact profile evidence execution metadata

* docs(qa): document compact profile evidence

* test(qa): support compact evidence mode

* test(qa): rename compact evidence mode to slim

* docs(qa): trim slim evidence wording

* fix(qa): avoid commander runtime import
 2026-06-15 14:50:40 -07:00
Mason Huang
06431fd99b test: add temp directory helper guidance (#87298) 
Summary:
- Merged test: add temp directory helper guidance after ClawSweeper review.

Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(scripts): honor temp report failure mode
- PR branch already contained follow-up commit before automerge: fix(scripts): reduce temp report noise
- PR branch already contained follow-up commit before automerge: fix(scripts): cover test support temp reports
- PR branch already contained follow-up commit before automerge: fix(scripts): report temp use in test helpers
- PR branch already contained follow-up commit before automerge: fix(scripts): broaden temp report test surface
- PR branch already contained follow-up commit before automerge: fix(scripts): cover nested test temp reports

Validation:
- ClawSweeper review passed for head 132f14a381.
- Required merge gates passed before the squash merge.

Prepared head SHA: 132f14a381
Review: https://github.com/openclaw/openclaw/pull/87298#issuecomment-4704338581

Co-authored-by: masonxhuang <masonxhuang@tencent.com>
Co-authored-by: Mason Huang <masonxhuang@tencent.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: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
 2026-06-15 03:51:43 +00:00
Dallin Romney
3d38c9a633 test(qa): embed profile scorecard evidence (#93109) 
* test(qa): embed profile scorecard evidence

* test(qa): fix profile runner return lint

* test(qa): satisfy suite command lint return
 2026-06-14 20:51:38 -07:00
Dallin Romney
e8db9c3bc0 test(qa): add qa run --profile and unified output summary/evidence (#91587) 
* test(qa): add mapped qa run profiles

* test(qa): document mapped profile runner

* test(qa): validate run profiles from mapping

* test(qa): preserve root profile parsing

* test(qa): simplify taxonomy profile dispatch

* test(qa): align tool coverage CLI expectation

* test(qa): fix profile dispatch fixture type

* test(qa): share profile runner option types

* test(qa): split shared cli runner options

* test(qa): unify profile suite artifacts

* fix(qa): filter profile scenarios by provider lane

* test(qa): drop native scenario subreports

* fix(qa): keep native log refs repo-relative

* fix(cli): preserve qa run root profile parsing

* fix(qa): avoid qa profile flag collision

* fix(qa): reject profile flags without qa profile
 2026-06-14 18:08:42 -07:00
Dallin Romney
1affe4fcdf Fold Telegram RTT sampling into live QA evidence (#92550) 
* refactor(qa): fold telegram rtt into live evidence

* test: default package telegram rtt samples

* refactor(qa-lab): fold telegram rtt into live evidence

* fix(qa-lab): keep package telegram rtt optional for focused runs

* fix(qa-lab): avoid stale rtt evidence on failed samples

* fix(qa-lab): pass telegram live env into credential leasing

* fix(qa-lab): update telegram canary remediation artifacts

* docs(qa): remove stale telegram observed artifact guidance

* fix(qa-lab): clarify telegram empty-reply remediation

* fix(qa-lab): honor telegram rtt timeout

* ci(qa): drop stale telegram capture env

* refactor: align telegram evidence coverage fields

* fix: ignore stale telegram observed artifacts

* fix: preserve telegram rtt coverage mapping

* fix: omit unused telegram rtt catch binding

* docs: document telegram rtt check selector
 2026-06-14 17:02:33 +08:00
Peter Steinberger
735f59af73 feat(providers): add GLM-5.2 support (#92796) 
* feat(providers): add GLM-5.2 support

* ci(live): add GLM-5.2 provider shard
 2026-06-13 14:33:28 -07:00
Vincent Koc
f5a7f613ee fix(release): use monthly patch versions 
Switch release train handling to YYYY.M.PATCH monthly patch numbering, preserve pre-transition compatibility, and pin the June 2026 stable/beta floor at 2026.6.5 after the published beta.

Verification:
- node scripts/run-vitest.mjs run test/appcast.test.ts test/release-check.test.ts test/scripts/package-mac-app.test.ts test/scripts/package-mac-dist.test.ts test/openclaw-npm-release-check.test.ts test/npm-publish-plan.test.ts src/infra/npm-registry-spec.test.ts src/infra/clawhub.test.ts src/plugins/clawhub.test.ts test/plugin-npm-release.test.ts test/scripts/ios-version.test.ts test/scripts/ios-pin-version.test.ts
- node --import tsx scripts/plugin-npm-release-check.ts --base-ref origin/main --head-ref HEAD
- node --import tsx scripts/plugin-clawhub-release-check.ts --base-ref origin/main --head-ref HEAD
- git diff --check origin/main...HEAD
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --no-web-search
 2026-06-06 12:26:32 -07:00
Vincent Koc
51488bf914 test(gateway): add small model live profile 
Add the small-model selector to the gateway live-model profile harness and document the OPENCLAW_LIVE_GATEWAY_MODELS=small recipe.\n\nVerification: node scripts/run-vitest.mjs run --config test/vitest/vitest.live.config.ts src/gateway/gateway-models.profiles.live.test.ts; GitHub Actions CI run 27064309683; CodeQL run 27064309687; OpenGrep PR Diff run 27064309689.
 2026-06-06 07:10:26 -07:00
Vincent Koc
1d19d7ec46 fix(auto-reply): skip commented heartbeat scaffolding 2026-06-04 17:03:40 -07:00
Vincent Koc
023427b1d5 test(docker): cap npm scheduler concurrency 2026-06-04 12:04:45 -07:00
Peter Steinberger
116bc2a0f0 docs: surface Windows Hub across docs 2026-06-03 16:09:24 -07:00
Peter Steinberger
190fd034d5 docs: refresh Windows Hub platform guide 2026-06-03 15:52:00 -07:00
joshavant
10830bc4a7 docs: warn about install policy plugin update footguns 2026-06-03 14:51:45 -07:00
Josh Avant
154f439c81 Add operator install policy and remove dangerous-code install scanners (#89516) 
* feat: add operator install policy

* test: cover plain-file plugin install code

* fix: preserve locationless install policy findings

* refactor: remove install-time plugin scanner

* test: remove stale plugin install helper

* fix: preserve before-install builtin scan type

* fix: preserve plugin dependency denylist

---------

Co-authored-by: Mainframe <mainframe@MainfraacStudio.localdomain>
 2026-06-03 14:17:29 -07:00
Peter Steinberger
6deded6698 fix: raise bootstrap file default limit 2026-06-01 04:02:51 +01:00
Peter Steinberger
0369672691 feat(minimax): add m3 model support (#88860) 2026-05-31 21:47:47 -04:00
Vincent Koc
b6bac3cc2b test(agents): include Ollama in small live model matrix (#87838) 
* test(agents): include Ollama in small live model matrix

* test: avoid Ollama cloud key in local live runs

* test: recognize Ollama env secret refs

* test: type Ollama live key fixtures

* test: prevent Ollama cloud auth in local live probes

* test: preserve equivalent Ollama live credentials

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
 2026-05-31 21:38:31 -04:00
Peter Steinberger
e014145ac1 docs: mention markdown host-local media sends (#79658) 2026-05-31 18:51:45 +01:00
Clever
9f7eaf06e1 docs: clarify host-local text media boundary 2026-05-31 18:51:45 +01:00
Clever
7d3fc6f924 docs: update host-local media text policy 2026-05-31 18:51:45 +01:00
Peter Steinberger
6b1b2ff20a feat: default exec shell snapshots 2026-05-31 16:09:43 +01:00
Peter Steinberger
c389839d30 feat: add exec shell snapshot cache 
Add an opt-in bash/zsh shell snapshot cache for host exec runs, consolidate shell helper ownership into src/agents/shell-utils.ts, document OPENCLAW_EXEC_SHELL_SNAPSHOT, and keep Windows config command execution on the bash resolver. Also removes a redundant Discord gateway close-code type branch that was blocking test type checks.
 2026-05-31 15:39:53 +01:00