Commit Graph

1107 Commits

Author SHA1 Message Date
FullerStackDev
b08eef0508 fix(discord): hydrate reply context metadata 2026-06-10 14:54:32 +05:30
Ayaan Zaidi
b9095bf70d refactor(channel): share draft chunking resolver 2026-06-10 13:35:19 +05:30
Vincent Koc
7f1d82ab25 revert(sessions): defer session metadata sqlite
Reverts 538d36eaaa while preserving subsequent main changes. The beta-only SQLite downgrade rescue and reverse migration remain excluded.
2026-06-10 16:34:06 +09:00
brokemac79
de4b8d8ebf feat(plugins): allow installed trusted policy contracts
Allow explicitly enabled installed plugins to register declared trusted tool policies and agent tool result middleware, with trusted policy ids scoped by plugin owner.\n\nVerification covered targeted plugin/agent tests, typecheck, build, lint, local autoreview, and a Blacksmith Testbox runtime proof (tbx_01ktr1nq0rhq47fjkwrepm7fd3).
2026-06-10 16:18:23 +10:00
Vincent Koc
69a73b6278 chore(codex): bump app-server to 0.139.0 2026-06-10 14:14:53 +09:00
mushuiyu_xydt
a36e05050a fix #88009: [Feature]: batched memory embedding should batch over files (#89138)
Merged via squash.

Prepared head SHA: 66d362a56d
Co-authored-by: mushuiyu886 <266724580+mushuiyu886@users.noreply.github.com>
Co-authored-by: jalehman <550978+jalehman@users.noreply.github.com>
Reviewed-by: @jalehman
2026-06-09 06:38:30 -04:00
Vincent Koc
f57c3b55fd fix(microsoft-foundry): repair CI validation issues 2026-06-09 15:45:19 +09:00
Vincent Koc
0c60bad890 fix(microsoft-foundry): require MAI image deployment defaults 2026-06-09 15:34:28 +09:00
Vincent Koc
a172db54b4 fix(microsoft-foundry): allow MAI deployment ids for image generation 2026-06-09 15:34:28 +09:00
Vincent Koc
5f13d0c817 docs(microsoft-foundry): document MAI image support 2026-06-09 15:34:28 +09:00
Onur Solmaz
3137110167 fix(memory): move local llama.cpp runtime to provider plugin
* fix(memory): move local llama.cpp runtime to provider plugin

* chore: ignore llama cpp dynamic dependency

* test: remove invalid local provider alias fixture

* chore: refresh llama cpp shrinkwrap

* chore: drop stale memory embedding defaults facade
2026-06-09 14:30:35 +08:00
Vincent Koc
634bcf6667 docs: clarify external app integration path 2026-06-09 14:56:17 +09:00
Dallin Romney
112e98faa2 chore: bump codex app-server to 0.137.0 (#91496) 2026-06-08 15:42:41 -07:00
Peter Steinberger
538d36eaaa refactor: move session metadata to SQLite (#91322)
* refactor: move session metadata to sqlite

* test: seed session stores with sqlite fixtures

* test: seed remaining session stores with sqlite fixtures

* fix: stabilize sqlite session cache freshness

* test: seed cli transcript metadata in sqlite
2026-06-07 23:17:35 -07:00
Jason (Json)
57e0bdaabe feat: add live provider model catalog helper
Summary:
- Add a shared live provider catalog runtime for SDK-backed providers.
- Route OpenAI, xAI, OpenCode Go, Chutes, DeepInfra, Venice, NVIDIA, and Vercel AI Gateway live model discovery through the shared helper.
- Remove duplicated provider-local live catalog caching and harden auth marker stripping, empty live-result retries, and OpenAI custom-base-url handling.

Verification:
- node scripts/run-vitest.mjs extensions/openai/openai-provider.test.ts src/plugin-sdk/provider-catalog-live-runtime.test.ts src/commands/models/list.source-plan.test.ts extensions/opencode-go/index.test.ts extensions/nvidia/provider-catalog.test.ts
- pnpm plugin-sdk:api:check
- pnpm lint --threads=8
- pnpm run lint:extensions:bundled
- pnpm run test:extensions:package-boundary:compile
- pnpm check:import-cycles
- pnpm exec oxfmt --check extensions/openai/openai-provider.ts extensions/openai/openai-provider.test.ts
- git diff --check origin/main...HEAD
- autoreview clean: no accepted/actionable findings reported
- AWS Crabbox focused remote proof: run_364680d1bff8 / cbx_2456fffafe01
- Earlier same-PR AWS Crabbox live proof: run_1f05ccab368e / cbx_7375c79fcf9b

Known proof gap:
- Final current-code true live-provider smoke was blocked by Crabbox secret hydration, documented in the PR proof comment.
2026-06-07 14:16:00 -07:00
Jason (Json)
cf378e4cc8 fix(codex): preserve post-tool reasoning liveness
Preserve the Codex post-tool continuation guard for raw reasoning completions and streamed reasoning progress so valid post-tool synthesis stays on the intended completion watchdog instead of falling through to terminal idle behavior.

Verified with focused Codex watchdog tests, test typecheck, scripts lint, autoreview, and CI run 27086637988.

Thanks @fuller-stack-dev.

Co-authored-by: FullerStackDev <263060202+fuller-stack-dev@users.noreply.github.com>
2026-06-07 00:57:14 -07:00
Peter Steinberger
08ae0e6d29 refactor: store Zalo hosted media in plugin state
Move Zalo hosted outbound media metadata and expiry into plugin state, add SDK chunked hosted media storage, and keep CI/type/lint gates green after rebase.
2026-06-06 22:56:48 -07:00
the sun gif man
47cfacbb87 docs: improve plugin inventory layout (#90922)
Summary:
- The branch changes plugin inventory generation from wide Markdown tables to per-plugin list entries, shorten ... nerated plugin reference landing page, routes Parallel to its setup page, and updates zh-CN glossary terms.
- PR surface: Docs +9, Other +20. Total +29 across 4 files.
- Reproducibility: not applicable. this is a docs layout PR rather than a reproducible runtime bug. Current ma ... and the PR body plus prior review discussion documents before/after screenshot proof for the layout change.

Automerge notes:
- PR branch already contained follow-up commit before automerge: docs: improve plugin inventory layout

Validation:
- ClawSweeper review passed for head c94b7a4bbc.
- Required merge gates passed before the squash merge.

Prepared head SHA: c94b7a4bbc
Review: https://github.com/openclaw/openclaw/pull/90922#issuecomment-4638524853

Co-authored-by: joshp123 <joshp123@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: joshp123
Co-authored-by: joshp123 <1497361+joshp123@users.noreply.github.com>
2026-06-06 16:37:39 +00:00
Kevin Lin
ab7c922825 fix(codex): report completion timeout diagnostics
Surface Codex-specific completion-timeout outcomes and structural diagnostics while preserving the existing replay-safe retry behavior.\n\nVerified with focused Vitest coverage, live forced-timeout Showboat proof, and green PR CI.
2026-06-05 22:00:38 -07:00
Kevin Lin
fce002ad03 revert(codex): revert first-party marketplace allowlist
Reverts openclaw/openclaw#82219.
2026-06-03 15:35:35 -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
Val Alexander
be336cc1e4 feat(ui): add workboard keyboard movement controls
Add compact keyboard-accessible Workboard status movement controls for writable operators. The control reuses the existing workboard.cards.move path, preserves drag/drop as the pointer enhancement, and suppresses mutation controls for read-only operators.\n\nVerification:\n- node scripts/run-vitest.mjs ui/src/ui/views/workboard.test.ts\n- corepack pnpm exec oxfmt --check --threads=1 ui/src/ui/views/workboard.ts ui/src/ui/views/workboard.test.ts ui/src/styles/workboard.css docs/plugins/workboard.md\n- git diff --check origin/main...HEAD\n- Chromium Control UI mock Gateway keyboard movement proof\n- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main --no-web-search
2026-06-02 16:08:29 -05:00
Gio Della-Libera
1d3cfc4b01 Policy: add data handling conformance checks (#87056)
Merged via squash.

Prepared head SHA: 6a0e9730aa
Co-authored-by: giodl73-repo <
>
Co-authored-by: giodl73-repo <235387111+giodl73-repo@users.noreply.github.com>
Reviewed-by: @giodl73-repo
2026-06-02 10:48:07 -07:00
兰之
10d10faa25 feat(plugin-sdk): add resolve_exec_env hook
Summary:
- Add the plugin SDK `resolve_exec_env` hook for bounded exec environment contributions.
- Wire resolved exec env through exec preparation/final execution without exposing plugin env values to generic tool hooks.
- Cover lazy exec loading, host and command rewrites, node/gateway execution, filtering, and EXEC shell snapshot cache behavior.

Verification:
- `pnpm changed:lanes --json`
- `node scripts/run-vitest.mjs src/agents/bash-tools.exec.resolve-env-hook.test.ts src/agents/agent-tool-definition-adapter.test.ts src/agents/agent-tool-definition-adapter.after-tool-call.test.ts src/agents/shell-snapshot.test.ts src/plugins/hook-resolve-exec-env.test.ts`
- `pnpm check:test-types`
- `pnpm lint src/agents/bash-tools.exec.ts src/agents/bash-tools.exec.resolve-env-hook.test.ts`
- `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main`
- PR CI clean on 1bbad8d071: https://github.com/openclaw/openclaw/actions/runs/26817910293

Co-authored-by: Lanzhi <lizhan3@xiaomi.com>
2026-06-02 08:00:42 -04:00
Yzx
b1bdc29d33 fix(providers): use native reasoning mode for Gemini instead of tagged (#89379)
* fix(providers): use native reasoning mode for direct Gemini API, keep CLI tagged

Gemini 2.5+ delivers reasoning via native thinkingParts (thinkingConfig.
includeThoughts). Having tagged mode active at the same time injects a
<think>…</think>/<final>…</final> directive into the system prompt; the
model opens a <think> block before a tool call, never closes it, and
returns an empty post-tool turn (content:[], payloads=0 error, #69220).

Fix: override resolveReasoningOutputMode in buildGoogleProvider() only —
not in the shared GOOGLE_GEMINI_PROVIDER_HOOKS. The Gemini CLI backend
(google-gemini-cli) runs gemini --output-format json and parses a text
response field, not native thought parts; it must stay on tagged mode.
A regression test confirms google-gemini-cli remains "tagged".

Also remove the dead BUILTIN_REASONING_OUTPUT_MODES entry keyed on
"google-generative-ai" from provider-utils.ts — that string is only
ever the transport model.api value, never the provider id passed to
resolveReasoningOutputMode, so the map was unreachable.

Fixes #69220

* docs: clarify Gemini reasoning output modes

* fix(google): keep Antigravity reasoning tagged

* fix(google): default direct reasoning checks to native

* fix(google): import reasoning context from plugin entry

---------

Co-authored-by: Peter Steinberger <steipete@gmail.com>
2026-06-02 07:46:08 -04:00
Ayaan Zaidi
db576c4a2d refactor(agents): trim native compaction ownership follow-up 2026-06-02 14:39:35 +05:30
Cameron Beeley
5e52a9b513 docs(cli-backends): document ownsNativeCompaction opt-out contract 2026-06-02 14:39:35 +05:30
Peter Steinberger
8e28c773fe chore(release): prepare 2026.6.1 2026-06-01 10:30:15 +01:00
Vincent Koc
f8e9ba3718 fix(codex): prevent aborted app-server turn handles 2026-06-01 10:12:36 +01:00
Peter Steinberger
db4990d260 refactor: compact copilot sessions through sdk state
Route Copilot compaction through SDK-backed state, remove marker sidecars, preserve auth/session binding behavior in SQLite-backed plugin state, and route Copilot CLI budget compaction through native harness compaction.
2026-06-01 01:18:46 -04:00
amittell
945faf8e67 fix(memory-lancedb): reject envelope metadata sludge
Summary:
- Strip memory-lancedb envelope and metadata sludge before auto-capture/recall, including pending history wrappers, current-message reply context, message-tool delivery hints, media annotations, and marker-free channel envelopes.
- Expose bundled chat-channel IDs/prefixes through the plugin SDK so sanitizer matching follows the channel catalog.
- Refactor cron tool schemas to fresh factory instances while preserving runtime nullable clears and provider-facing OpenAPI projection.

Verification:
- git diff --check origin/main...HEAD
- ./node_modules/.bin/oxfmt --check src/plugin-sdk/chat-channel-ids.ts src/plugin-sdk/chat-channel-ids.test.ts extensions/memory-lancedb/index.ts extensions/memory-lancedb/index.test.ts src/agents/tools/cron-tool.ts src/agents/tools/cron-tool.schema.test.ts
- pnpm plugin-sdk:api:check
- node scripts/run-vitest.mjs run src/plugin-sdk/chat-channel-ids.test.ts extensions/memory-lancedb src/agents/tools/cron-tool.schema.test.ts src/agents/tools/cron-tool.test.ts --reporter=dot
- pnpm lint:extensions --threads=8
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
- GitHub checks on 62d1da1257: 139 pass, 0 pending, 0 fail, 22 skipped.
2026-06-01 00:57:25 -04:00
Peter Steinberger
ebcdb637bb perf(memory-core): defer embedding engine startup imports 2026-06-01 04:22:22 +01:00
Dallin Romney
78165cc387 docs: clarify diffs language pack additions (#88865) 2026-05-31 19:24:45 -07:00
Andy Ye
921598442a fix(hooks): expose inbound reply metadata before dispatch
Fixes #88521.

Expose finalized inbound reply metadata on plugin-visible hook payloads so before_dispatch and message hooks can implement reply-aware behavior without channel-specific workarounds.
2026-05-31 22:15:17 -04:00
Peter Steinberger
5443baa852 Persist plugin install index in SQLite (#88794)
* refactor: persist plugin install index in sqlite

* fix: merge legacy plugin index records into sqlite

* test: update plugin index sqlite fixtures

* fix: migrate custom plugin install indexes

* test: update plugin index sentinel

* fix: exclude migrated plugin index archives

* fix: read post-upgrade plugin index from sqlite

* fix: migrate legacy plugin index before agent runs

* fix: respect disabled persisted plugin registry reads

* test: type plugin install record fixtures

* fix: simplify plugin index record reader type

* test: fix sqlite plugin index CI fallout

* test: mock provider normalization in agent command tests

# Conflicts:
#	src/commands/agent-command.test-mocks.ts

* build: remove unused ui three dependency
2026-05-31 20:51:33 -04:00
Vincent Koc
82d24b26ea fix(workboard): wire task-backed board runs
Summary:
- remove the leftover Workboard mini-game/prototype surface
- wire autonomous Workboard card starts through Gateway task-backed agent runs
- reconcile card task/session lifecycle for starts, stops, stale tasks, reassignment, and default-agent sessions
- clarify dispatch summary copy and admin-only model override behavior

Verification:
- autoreview clean: no accepted/actionable findings
- targeted Workboard/UI Vitest: 72 tests passed
- Workboard extension Vitest: 9 tests passed
- UI build, docs list, docs format, diff check, and focused oxlint passed
- PR CI checks: 50 ok, 0 attention
- Testbox tbx_01kt07mk5sjyj2whjq2sc967hg: pnpm verify check phase passed; broad test phase exposed unrelated latest-main failures/stalls in memory, Codex app-server, provider timeout, command daemon env, Telegram worker OOM, and gateway-client timeout suites
2026-06-01 01:41:21 +01:00
Peter Steinberger
d641126c1d feat(plugin-sdk): add typed presentation command actions (#88721)
* feat(plugin-sdk): add typed presentation command actions

* test: use shared env helper in telegram bot tests

* test: expect typed approval actions

* test: expect typed sdk approval actions
2026-05-31 18:48:45 +01:00
zhang-guiping
b6e9473e9f fix(auth): skip Anthropic API keys for usage status
Fixes #85124.

Anthropic standard API keys no longer resolve as provider usage auth for `openclaw status --usage`, so valid inference keys are not sent to Anthropic's OAuth usage endpoint and surfaced as misleading invalid bearer-token errors.

The provider usage-auth SDK result now has an explicit handled/no-token shape so provider hooks can suppress generic fallback without widening the OAuth helper contract. Docs, Plugin SDK API baseline, and extension package-boundary cache inputs were updated with the new contract.

Thanks @zhangguiping-xydt.

Proof:
- node scripts/run-vitest.mjs src/infra/provider-usage.auth.normalizes-keys.test.ts src/infra/provider-usage.auth.plugin.test.ts extensions/anthropic/index.test.ts
- pnpm plugin-sdk:api:check
- pnpm plugin-sdk:check-exports
- git diff --check origin/main...HEAD
- pnpm docs:list
- pnpm run test:extensions:package-boundary:compile
- autoreview clean: no accepted/actionable findings
- PR CI rollup green: 131 success, 22 skipped, 1 neutral, 0 failures

Co-authored-by: 张贵萍0668001030 <zhang.guiping@xydigit.com>
2026-05-31 18:26:03 +01:00
litang9
d446c26acb feat(deepseek): show provider balance in usage status
Show DeepSeek API-key account balance in status/auth-status usage surfaces by adding a summary-only provider usage snapshot path, a DeepSeek balance fetcher, SDK/docs coverage, and focused regression tests.

Maintainer verification accepted the additive provider-usage/status contract and the DeepSeek balance visibility boundary for authenticated status surfaces.

Proof:
- Live DeepSeek balance proof via 1Password-backed DEEPSEEK_API_KEY against https://api.deepseek.com/user/balance; key and balance amount redacted.
- GitHub CI run 26717953383 passed on the current head.
- Real behavior proof run 26718215605 passed after the PR body was refreshed.
- Local clean PR clone: git diff --check; node --max-old-space-size=8192 --import tsx scripts/generate-plugin-sdk-api-baseline.ts --check; node scripts/run-vitest.mjs run src/agents/bash-tools.exec.path.test.ts.

Co-authored-by: Alex Tang <tangli1987118@hotmail.com>
Co-authored-by: litang9 <141409885+litang9@users.noreply.github.com>
2026-05-31 17:35:41 +01:00
Peter Steinberger
729712d194 docs(codex): clarify first-party plugin marketplaces 2026-05-31 13:22:00 +01:00
Peter Steinberger
242eab9d20 fix(media): use typed auth for no-auth media providers 2026-05-31 12:56:38 +01:00
sqsge
a76db8cff3 fix(media): allow explicit synthetic auth for media providers
Allow media understanding providers to opt into synthetic non-secret auth for local or self-hosted no-auth audio/video execution.

This preserves configured env/profile/literal provider credentials first, keeps explicit profile failures hard-fail, and leaves unmarked remote providers fail-closed.

Fixes #74644.
2026-05-31 12:20:50 +01:00
Peter Steinberger
9dc4c9ec2e fix: expose Feishu tools for named accounts 2026-05-31 11:36:48 +01:00
Soham Patankar
4f3d8a57dd fix(codex): accept first-party OpenAI plugin marketplaces
Allow Codex native plugin config to target first-party OpenAI marketplaces, including openai-curated, openai-bundled, and openai-primary-runtime.

Fixes #82216.
Thanks @yaanfpv for the contribution.

Verification:
- node scripts/run-vitest.mjs test/scripts/lint-suppressions.test.ts
- pnpm build:ci-artifacts
- OPENCLAW_VITEST_MAX_WORKERS=2 node scripts/run-vitest.mjs run --config test/vitest/vitest.full-core-support-boundary.config.ts test/scripts/lint-suppressions.test.ts
- node scripts/run-vitest.mjs extensions/codex/src/app-server/config.test.ts extensions/codex/src/app-server/plugin-activation.test.ts extensions/codex/src/app-server/session-binding.test.ts extensions/codex/src/migration/provider.test.ts extensions/sms/src/channel.test.ts extensions/sms/src/inbound.test.ts
- git diff --check
- ./.agents/skills/autoreview/scripts/autoreview --mode local
- GitHub PR CI on head 896640060b, including build-artifacts run 26709647050
2026-05-31 11:08:42 +01:00
Peter Steinberger
ed46e62bcc feat(workboard): add worker dispatch CLI
* feat(workboard): add worker dispatch CLI

* fix(workboard): avoid new unsafe assertions

* fix(workboard): keep remote dispatch failures remote
2026-05-31 10:31:56 +01:00
Peter Steinberger
3513e8bfd9 feat: add Twilio SMS channel
Add a bundled SMS channel backed by Twilio inbound webhooks and outbound text delivery.

Includes signed webhook validation, pairing/allowlist access, Messaging Service sender support, chunked plain-text SMS delivery, default target support, docs, config metadata, labeler updates, and focused SMS coverage.

Verification:
- pnpm exec tsgo -p extensions/sms/tsconfig.json --noEmit
- OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-vitest-sms-land-fix2 node scripts/run-vitest.mjs extensions/sms/src/phone.test.ts extensions/sms/src/accounts.test.ts extensions/sms/src/twilio.test.ts extensions/sms/src/inbound.test.ts extensions/sms/src/gateway.test.ts extensions/sms/src/channel.test.ts extensions/sms/src/send.test.ts extensions/sms/src/webhook.test.ts --reporter=verbose
- pnpm config:channels:check
- pnpm plugins:inventory:check
- git diff --check
- .agents/skills/autoreview/scripts/autoreview --mode local
- .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main
2026-05-31 09:22:31 +01:00
Peter Steinberger
ae651e7210 docs: add permission modes page 2026-05-31 08:47:02 +01:00
Peter Steinberger
4c33aaa86c refactor: unify OpenAI provider identity (#88451)
* refactor: unify OpenAI provider identity

* refactor: move legacy oauth sidecar doctor helpers

* test: align OpenAI fixtures after rebase

* test: clean OpenAI provider unification

* fix: finish OpenAI provider cleanup

* fix: finish OpenAI cleanup follow-through

* fix: finish OpenAI CI cleanup
2026-05-31 00:29:44 +01:00
Peter Steinberger
8d6a6e9d03 feat: move workboard to relational sqlite
Move Workboard durable data into a relational SQLite database and add extension doctor migration for .28 plugin-state rows. Preserve attachment lifecycle behavior, SQLite permissions/WAL settings, and scoped plugin migration access.
2026-05-31 00:02:23 +01:00
Peter Steinberger
3fc0df953c refactor(agents): bind subagent threads in core (#88416)
Move subagent thread binding ownership into core so session-mode spawns prepare channel bindings before launching the child agent. Deprecate the legacy subagent_spawning SDK hook in code, compatibility metadata, diagnostics, and plugin docs; plugin authors should observe subagent_spawned instead.

Verification:
- node scripts/run-vitest.mjs src/agents/sessions-spawn-hooks.test.ts src/agents/subagent-spawn.thread-binding.test.ts src/agents/subagent-spawn.workspace.test.ts src/agents/subagent-spawn.mode-session-diagnostics.test.ts
- node scripts/run-tsgo.mjs -p tsconfig.core.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core.tsbuildinfo
- git diff --check
- .agents/skills/autoreview/scripts/autoreview --mode local
- CI run 26693808952 green, including checks-node-agentic-agents-core and checks-node-agentic-plugin-sdk
2026-05-30 21:19:09 +01:00