Policy: add policy file comparison command by giodl73-repo · Pull Request #86768 · openclaw/openclaw

giodl73-repo · 2026-05-26T05:54:03Z

Summary

Adds openclaw policy compare so an operator policy file can be checked against an organization-authored baseline policy file. This is policy-file conformance only: it compares policy syntax to policy syntax and does not inspect OpenClaw runtime state, evidence, credentials, or secrets.

The command is intended for lifecycle review such as "does this workspace policy remain at least as strict as the approved baseline?"

Usage

openclaw policy compare --baseline official.policy.jsonc
openclaw policy compare --baseline official.policy.jsonc --policy policy.jsonc --json

Example clean JSON output:

{
  "ok": true,
  "baselinePath": "official.policy.jsonc",
  "policyPath": "policy.jsonc",
  "rulesChecked": 3,
  "findings": []
}

Contract

policy compare uses the same policy rule metadata that governs scoped overlays:

Rule kind	Conformance behavior
Allowlists	Checked policy must be equal or narrower.
Denylists	Checked policy must be equal or broader.
Required booleans	Checked policy must keep the required value.
Ordered strings	Checked policy can only move toward the more restrictive end of the configured order.
Exact lists	Checked policy must match.

The checked policy can use stricter values or add extra policy rules. A top-level checked rule can satisfy a scoped baseline rule when it is equally or more restrictive, because top-level policy applies broadly. Scope names do not need to match; scoped comparison is keyed by selector value such as agentIds or channelIds and by the policy field being checked.

New check IDs:

Check ID	Meaning
`policy/policy-conformance-invalid`	A baseline or checked policy file has invalid comparison syntax.
`policy/policy-conformance-missing`	A checked policy file is missing a rule required by the baseline policy file.
`policy/policy-conformance-weaker`	A checked policy file has a weaker value than the baseline policy file.

Exit codes:

Command	`0`	`1`	`2`
`policy compare`	The policy file is at least as strict as the baseline.	The policy file is invalid, missing, or weaker than baseline rules.	Argument or runtime failure.

Validation

CLI coverage for clean compare, missing/weaker rules, invalid files, malformed baseline syntax, scoped selector comparison, stricter top-level satisfaction of scoped baseline rules, and weaker scoped overrides.
Policy docs updated with compare syntax, strictness behavior, check IDs, JSON output, and exit-code behavior.

clawsweeper · 2026-05-26T05:56:35Z

Codex review: needs maintainer review before merge. Reviewed May 29, 2026, 2:10 AM ET / 06:10 UTC.

Summary
Adds openclaw policy compare with metadata-backed policy-file strictness comparison, focused Policy plugin tests, and CLI/plugin documentation.

PR surface: Source +890, Tests +576, Docs +42. Total +1508 across 6 files.

Reproducibility: not applicable. this is a feature PR, not a bug report. The contributor supplied live policyCompareCommand output and focused test coverage for the new behavior.

Review metrics: 1 noteworthy metric.

CLI Surface: 1 command added, 3 options. The new operator-visible command and flags become a documented workflow contract that maintainers should review before merge.

Merge readiness
Overall: 🦞 diamond lobster
Proof: 🦞 diamond lobster
Patch quality: 🦞 diamond lobster
Result: ready for maintainer review.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Risk before merge

[P1] A false clean result from policy compare could give operators incorrect assurance that a workspace policy satisfies an organization baseline, so the strictness metadata and scoped comparison semantics need policy/security owner review before merge.

Maintainer options:

Confirm The Policy Contract (recommended)
A policy/security owner should review the strictness metadata, scoped-rule matching, and false-clean failure modes before accepting the new operator assurance command.
Require Contract Hardening First
If owner review wants unsupported-key or other fail-closed semantics in the same landing path, require the narrow policy validation patch and regression tests before merge.
Pause The Policy Compare Surface
If maintainers are not ready to own a baseline-comparison command as operator assurance, keep the PR open or close it until the policy contract is decided.

Next step before merge

[P2] The PR is protected by the maintainer label and the remaining action is policy/security owner review of the comparison contract, not an automated repair.

Security
Cleared: No dependency, lockfile, secret-handling, or supply-chain regression was found; the security-sensitive concern is contract correctness and is tracked as merge risk.

Review details

Best possible solution:

Land only after a policy/security owner accepts the strictness and scoped-matching semantics and exact-head required checks finish green, keeping the command plugin-local and documented.

Do we have a high-confidence way to reproduce the issue?

Not applicable: this is a feature PR, not a bug report. The contributor supplied live policyCompareCommand output and focused test coverage for the new behavior.

Is this the best way to solve the issue?

Yes, the plugin-local command plus shared Policy metadata is a maintainable implementation shape. The remaining question is owner acceptance of the exact conformance contract, not a narrow code defect.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against f212176e9164.

Label changes

Label justifications:

P2: This is a normal-priority Policy plugin feature with a security-sensitive review requirement but no confirmed runtime regression.
merge-risk: 🚨 security-boundary: Merging this PR adds a policy conformance command whose false clean results could weaken operators' security-posture decisions.
rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): Contributor comments include after-change live output for weaker and strict real policy-file comparisons, and the current head keeps the same compare surface under review.
proof: sufficient: Contributor real behavior proof is sufficient. Contributor comments include after-change live output for weaker and strict real policy-file comparisons, and the current head keeps the same compare surface under review.

Evidence reviewed

PR surface:

Source +890, Tests +576, Docs +42. Total +1508 across 6 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	3	897	7	+890
Tests	1	577	1	+576
Docs	2	48	6	+42
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	6	1522	14	+1508

What I checked:

Repository policy read: Read the full root AGENTS.md plus scoped docs/AGENTS.md and extensions/AGENTS.md; the review applied protected-label handling, plugin-boundary guidance, and security-sensitive policy-contract review guidance. (AGENTS.md:1, f212176e9164)
Scoped docs policy read: docs/AGENTS.md requires Mintlify-safe docs links/content and consistent plugin terminology for docs changes. Public docs: docs/AGENTS.md. (docs/AGENTS.md:1, f212176e9164)
Scoped plugin policy read: extensions/AGENTS.md confirms bundled plugin code should stay inside the plugin boundary and use plugin SDK/public seams; this PR keeps the command in the Policy plugin. (extensions/AGENTS.md:1, f212176e9164)
gitcrawl unavailable, live fallback used: gitcrawl was not installed in this environment, so live GitHub API reads and the current checkout were used for PR state, comments, files, and checks.
Current main does not already implement the command: A current-main search found no policy compare, policyCompareCommand, or buildPolicyConformanceReport; only existing tool-policy conformance imports matched the broader policy-conformance substring. (f212176e9164)
Live PR state: The PR is open, not draft, mergeable with unstable checks, has head 2023e8c, and still carries the protected maintainer label plus proof: sufficient and merge-risk: 🚨 security-boundary. (2023e8cba189)

Likely related people:

giodl73-repo: Current-main history shows Gio Della-Libera authored the recently merged Policy ingress conformance work that added adjacent strictness metadata and docs this PR builds on. (role: recent area contributor; confidence: high; commits: 5fb83af3e389; files: extensions/policy/src/doctor/register.ts, extensions/policy/src/doctor/register.test.ts, docs/cli/policy.md)
steipete: Blame on the base Policy CLI and metadata area in this checkout points to Peter Steinberger's current-main commits, making him a useful routing candidate for the existing Policy plugin surface. (role: adjacent area contributor; confidence: medium; commits: adabff1bf067, f212176e9164; files: extensions/policy/src/cli.ts, extensions/policy/src/doctor/register.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

clawsweeper · 2026-05-26T06:06:54Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Mossy Proofling

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

Merged PRs are hatchable.
Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 🥚 common.
Trait: polishes edge cases.
Image traits: location proof lagoon; accessory lint brush; palette amber, ink, and glacier blue; mood curious; pose pointing at a small proof artifact; shell frosted glass shell; lighting gentle morning glow; background small review tokens.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Mossy Proofling in ClawSweeper.

What is this egg doing here?

Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

giodl73-repo · 2026-05-27T18:43:18Z

Updated this branch on top of the rebased ingress policy branch (14c9bd4689f) and kept the compare metadata aligned with the shared sandbox descriptor table plus ingress channel metadata.

I did not find any Galin review or inline comments on this PR via the GitHub review/comment APIs.

Fresh validation after the rebase:

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-policy-conformance-rebase OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs extensions/policy/src/cli.test.ts extensions/policy/src/doctor/register.test.ts -- --reporter=dot --testTimeout=30000 -> 2 files, 270 tests passed
pnpm tsgo:extensions
pnpm exec oxfmt --check --threads=1 docs/cli/policy.md docs/plugins/reference/policy.md extensions/policy/src/cli.test.ts extensions/policy/src/cli.ts extensions/policy/src/doctor/register.ts extensions/policy/src/policy-conformance.ts && git diff --check
node scripts/run-bundled-extension-oxlint.mjs
pnpm docs:check-mdx docs/cli/policy.md docs/plugins/reference/policy.md

@clawsweeper re-review

clawsweeper · 2026-05-27T18:43:20Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26531473034
Updated: 2026-05-27T18:51:49.359Z

giodl73-repo · 2026-05-27T22:29:34Z

Updated #86768 on top of the rebased ingress PR and marked it ready for review.

Current signed head: a9158bba3a9.

Fix made during rebase validation:

Updated the model-provider compare normalization regression to match the current OpenClaw provider-id contract. normalizeProviderId now normalizes casing only; it no longer aliases bedrock / aws-bedrock to amazon-bedrock, so policy compare should not invent that alias layer.

Fresh validation:

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-86768-compare-rebase-fix2 OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs extensions/policy/src/cli.test.ts extensions/policy/src/doctor/register.test.ts -- --reporter=dot --testTimeout=30000 -> 2 files, 273 tests passed
pnpm tsgo:extensions
node scripts/run-bundled-extension-oxlint.mjs -> 0 warnings, 0 errors
pnpm exec oxfmt --check --threads=1 CHANGELOG.md docs/cli/policy.md docs/plugins/reference/policy.md extensions/policy/src/cli.test.ts extensions/policy/src/cli.ts extensions/policy/src/doctor/register.ts extensions/policy/src/policy-conformance.ts && git diff --check
pnpm docs:check-mdx docs/cli/policy.md docs/plugins/reference/policy.md

Real behavior proof was run with real baseline/candidate policy files through policyCompareCommand({ json: true }):

weaker candidate: exitCode: 1, ok: false, rulesChecked: 6, with expected weaker/missing findings
strict candidate: exitCode: 0, ok: true, rulesChecked: 6, with no findings

@clawsweeper re-review

clawsweeper · 2026-05-27T22:29:36Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26542566381
Updated: 2026-05-27T22:39:07.522Z

giodl73-repo · 2026-05-29T05:17:03Z

Refreshed #86768 after #85744 landed.

Current signed head: 294b6f26d6d826e4cbbb5bb4cfea37260f538edb.

Branch cleanup:

rebuilt on current origin/main
removed the old stacked sandbox/ingress commits that are now already on main
replayed only the policy-compare commits:
- feat(policy): add policy file comparison
- test(policy): align provider compare normalization
PR is now mergeable from GitHub's view; CI is rerunning on the refreshed head

Fresh validation on the rebuilt head:

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-86768-refresh OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs extensions/policy/src/cli.test.ts extensions/policy/src/doctor/register.test.ts -- --reporter=dot --testTimeout=30000 -> 2 files, 273 tests passed
pnpm exec oxfmt --check --threads=1 docs/cli/policy.md docs/plugins/reference/policy.md extensions/policy/src/cli.test.ts extensions/policy/src/cli.ts extensions/policy/src/doctor/register.ts extensions/policy/src/policy-conformance.ts && git diff --check -> passed
node scripts/run-bundled-extension-oxlint.mjs -> 0 warnings, 0 errors
pnpm docs:check-mdx docs/cli/policy.md docs/plugins/reference/policy.md -> passed

Known local validation note: pnpm tsgo:extensions currently fails on unrelated current-main code, src/gateway/session-utils.fs.ts, with TS6133: 'maxMessages' is declared but its value is never read. This PR does not touch that file.

@clawsweeper re-review

clawsweeper · 2026-05-29T05:17:07Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Failed
Detail: The targeted re-review did not finish cleanly. Check the workflow run for details.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26620294636
Updated: 2026-05-29T05:41:24.120Z

giodl73-repo · 2026-05-29T05:20:38Z

Fresh proof on current PR head after the GitHub-side main update:

Current head: daa4520fa4cfd42dbbc161e870b8bcda2e0a1e6f

The PR diff remains scoped to the policy compare files only:

docs/cli/policy.md
docs/plugins/reference/policy.md
extensions/policy/src/cli.test.ts
extensions/policy/src/cli.ts
extensions/policy/src/doctor/register.ts
extensions/policy/src/policy-conformance.ts

Fresh validation on this exact head:

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-86768-daa4520 OPENCLAW_VITEST_MAX_WORKERS=1 node scripts/run-vitest.mjs extensions/policy/src/cli.test.ts extensions/policy/src/doctor/register.test.ts -- --reporter=dot --testTimeout=30000 -> 2 files, 273 tests passed

The earlier format/oxlint/docs checks passed on the rebuilt compare-only branch before GitHub merged latest main into it. The GitHub-side update did not change the PR diff.

@clawsweeper re-review

clawsweeper · 2026-05-29T05:20:40Z

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

Re-review progress:

State: Superseded
Detail: A newer re-review for this item started before this run finished, so GitHub cancelled this older run. Check the latest ClawSweeper run for the current result.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26619656507
Updated: 2026-05-29T05:23:49.117Z

clawsweeper · 2026-05-29T05:47:46Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Failed
Detail: The targeted re-review did not finish cleanly. Check the workflow run for details.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26620550754
Updated: 2026-05-29T05:48:56.220Z

giodl73-repo · 2026-05-29T05:49:10Z

Author/maintainer follow-up for ClawSweeper on current head 438f6255d2770f464db4fe864a3cd915ec6ec358:

I reviewed the policy conformance strictness metadata and docs for the current PR shape.

The intended contract is:

allowlists: candidate must be equal or narrower
denylists: candidate must be equal or broader
required booleans: candidate must preserve the required value
ordered strings: candidate may only move toward the more restrictive end of the configured order
exact lists: candidate must match

I also checked that policy compare remains policy-file syntax conformance only. It does not inspect runtime state, credentials, or secret values, and it does not add runtime enforcement or new config/plugin public surface.

Maintainer autoreview using the maintainers repo review-pr skill found no actionable findings. Fresh wrapper validation on this exact head passed:

OPENCLAW_VITEST_FS_MODULE_CACHE_PATH=/tmp/openclaw-86768-review-438f6255 OPENCLAW_VITEST_MAX_WORKERS=1 scripts/pr review-tests 86768 extensions/policy/src/cli.test.ts extensions/policy/src/doctor/register.test.ts

Result: pnpm test passed and both requested policy test targets were observed in output.

@clawsweeper re-review

clawsweeper · 2026-05-29T05:49:12Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Superseded
Detail: A newer re-review for this item started before this run finished, so GitHub cancelled this older run. Check the latest ClawSweeper run for the current result.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26620612964
Updated: 2026-05-29T05:53:00.268Z

@giodl73-repo

Merged via squash. Prepared head SHA: 2023e8c Co-authored-by: giodl73-repo <235387111+giodl73-repo@users.noreply.github.com> Reviewed-by: @giodl73-repo

…026.5.28) (#759) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.27` → `2026.5.28` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.28`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026528) [Compare Source](openclaw/openclaw@v2026.5.27...v2026.5.28) ##### Highlights - Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive cleanup, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#87409](openclaw/openclaw#87409), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#88129](openclaw/openclaw#88129)) - Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, runtime-config message actions, WhatsApp profile auth roots, Telegram polling, and Microsoft Teams service URL trust checks. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#82492](openclaw/openclaw#82492), [#83304](openclaw/openclaw#83304), [#87160](openclaw/openclaw#87160)) - Mobile and chat surfaces got a broader refresh: the iOS Pro UI, hosted push relay default, realtime Talk tab playback, Gateway chat transport, onboarding, Talk permissions, WebChat reconnect delivery, and session picker behavior now preserve more state across reconnects and empty searches. ([#87367](openclaw/openclaw#87367), [#87531](openclaw/openclaw#87531), [#87682](openclaw/openclaw#87682), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@ngutman](https://github.com/ngutman) and [@BunsDev](https://github.com/BunsDev). - Browser, channel, and automation inputs are stricter: Browser tool timeouts, viewport/tab indices, Gateway ports, cron retry handling, Discord component ids, schema array refs, Telegram callback pages, and channel progress callbacks now reject malformed values earlier and preserve the intended delivery context. ([#82887](openclaw/openclaw#82887)) - Provider, media, and document coverage expands with Claude Opus 4.8, Fal Krea image schemas, NVIDIA featured models, MiniMax streaming music responses, encrypted PDF extraction, voice model catalogs, GitHub Copilot agent runtime support, and a Codex Supervisor plugin path for delegated Codex workflows. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87751](openclaw/openclaw#87751), [#87794](openclaw/openclaw#87794)) - CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, workspace dotenv provider credentials are ignored, heartbeat defaults, OAuth/token lifetimes, and local service startup requests are bounded, agent auth health labels are clearer, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924)) Thanks [@vincentkoc](https://github.com/vincentkoc) and [@giodl73-repo](https://github.com/giodl73-repo). - Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, viewer assets, and release-split external plugin packages. ([#86699](openclaw/openclaw#86699)) - Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening. ##### Changes - Status: show active subagent details in status output. - Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. ([#87370](openclaw/openclaw#87370), [#87372](openclaw/openclaw#87372)) Thanks [@RomneyDa](https://github.com/RomneyDa). - ClawHub: add plugin display names plus skill verification and trust surfaces. ([#87354](openclaw/openclaw#87354), [#86699](openclaw/openclaw#86699)) Thanks [@thewilloftheshadow](https://github.com/thewilloftheshadow) and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - iOS: refresh the dev app with Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback wired to gateway sessions, diagnostics, chat, and realtime Talk. ([#87367](openclaw/openclaw#87367), [#88096](openclaw/openclaw#88096), [#88105](openclaw/openclaw#88105)) Thanks [@Solvely-Colin](https://github.com/Solvely-Colin) and [@ngutman](https://github.com/ngutman). - Docs: clarify Codex computer-use setup, paste-token stdin auth setup, macOS gateway sleep troubleshooting, native Codex hook relay recovery, container model auth, install deployment cards, device-token admin gating, CLI setup flow compatibility, Notte cloud browser CDP setup, and backport targets. ([#87313](openclaw/openclaw#87313), [#63050](openclaw/openclaw#63050), [#87685](openclaw/openclaw#87685)) Thanks [@bdjben](https://github.com/bdjben), [@liaoandi](https://github.com/liaoandi), and [@thewilloftheshadow](https://github.com/thewilloftheshadow). - PDF/tools: use ClawPDF for PDF extraction, support encrypted PDF extraction, and surface MCP structured content in agent tool results. ([#87670](openclaw/openclaw#87670), [#87751](openclaw/openclaw#87751)) - Providers: add Claude Opus 4.8 support, Fal Krea image model schemas, NVIDIA featured model catalogs, MiniMax streaming music responses, and provider-backed voice model catalogs. ([#87845](openclaw/openclaw#87845), [#87890](openclaw/openclaw#87890), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764), [#87794](openclaw/openclaw#87794)) Thanks [@eleqtrizit](https://github.com/eleqtrizit) and [@vincentkoc](https://github.com/vincentkoc). - Codex/GitHub: add the GitHub Copilot agent runtime and the Codex Supervisor plugin package. - Plugins: externalize GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata. - Workboard: add agent coordination tools for tracking and handing off active agent work. - Discord: show commentary in progress drafts so live Discord runs expose useful in-progress context. ([#85200](openclaw/openclaw#85200)) - Plugin SDK: add a reply payload sending hook for plugins that need to deliver channel-owned replies and flatten package types for SDK declarations. ([#82823](openclaw/openclaw#82823), [#87165](openclaw/openclaw#87165)) Thanks [@piersonr](https://github.com/piersonr) and [@RomneyDa](https://github.com/RomneyDa). - Policy: add policy comparison, ingress-channel conformance, and sandbox-posture conformance checks. ([#85572](openclaw/openclaw#85572), [#85744](openclaw/openclaw#85744), [#86768](openclaw/openclaw#86768)) ##### Fixes - Agents: fall back to local config pruning when the optional `agents delete` Gateway probe cannot authenticate, so offline installs can still delete agents without removing shared workspaces. - Tighten phone-control mutation authorization \[AI]. ([#87150](openclaw/openclaw#87150)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Clarify directive persistence authorization policy \[AI]. ([#86369](openclaw/openclaw#86369)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Agents/Codex: keep spawned agent cwd/workspace state separated, forward ACP spawn attachments, keep hook context prompt-local, release session locks on timeout abort and runtime teardown without deleting live OpenClaw-owned locks during cleanup, avoid session event queue self-wait, clean up exec abort listeners, stream assistant deltas incrementally, recover raw missing-thread compaction failures, preserve rotated compaction session identity, keep compaction-timeout snapshots continuable, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts and prune stale bridge files, close native hook relay replacement races, keep Claude live tool progress visible for watchdog recovery, suppress abandoned requester completion handoff, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, bind node auto-review to prepared plans, retry Claude CLI transcript probes, and bound compaction/steering retries. ([#87218](openclaw/openclaw#87218), [#86875](openclaw/openclaw#86875), [#86123](openclaw/openclaw#86123), [#88129](openclaw/openclaw#88129), [#87399](openclaw/openclaw#87399), [#87375](openclaw/openclaw#87375), [#72574](openclaw/openclaw#72574), [#87383](openclaw/openclaw#87383), [#87400](openclaw/openclaw#87400), [#83022](openclaw/openclaw#83022), [#87671](openclaw/openclaw#87671), [#87738](openclaw/openclaw#87738), [#87747](openclaw/openclaw#87747), [#87706](openclaw/openclaw#87706), [#87546](openclaw/openclaw#87546), [#87541](openclaw/openclaw#87541), [#81048](openclaw/openclaw#81048)) Thanks [@mbelinky](https://github.com/mbelinky), [@Alix-007](https://github.com/Alix-007), [@luoyanglang](https://github.com/luoyanglang), [@yetval](https://github.com/yetval), [@sjf](https://github.com/sjf), [@joshavant](https://github.com/joshavant), [@benjamin1492](https://github.com/benjamin1492), [@c19354837](https://github.com/c19354837), [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@pfrederiksen](https://github.com/pfrederiksen), and [@dodge1218](https://github.com/dodge1218). - Codex Supervisor: keep real-home app-server MCP session listing on the loaded state path, bound stored history scans, and close WebSocket probes cleanly. - Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, resolve Gateway message actions against the active runtime config, preserve Telegram SecretRef prompt config and polling keepalives, preserve WhatsApp profile auth roots, QR display, document filenames, and plugin hook config, suppress Discord recovered tool warnings, preserve the Discord voice outbound helper, cap Discord/Signal/Zalo channel request and container timeouts, and block untrusted Teams service URLs while keeping TeamsSDK patterns aligned. ([#73706](openclaw/openclaw#73706), [#75670](openclaw/openclaw#75670), [#87366](openclaw/openclaw#87366), [#87451](openclaw/openclaw#87451), [#87465](openclaw/openclaw#87465), [#87334](openclaw/openclaw#87334), [#84535](openclaw/openclaw#84535), [#76262](openclaw/openclaw#76262), [#83304](openclaw/openclaw#83304), [#82492](openclaw/openclaw#82492), [#87581](openclaw/openclaw#87581), [#77114](openclaw/openclaw#77114), [#86426](openclaw/openclaw#86426), [#85529](openclaw/openclaw#85529), [#87160](openclaw/openclaw#87160)) Thanks [@zeroaltitude](https://github.com/zeroaltitude), [@lukeboyett](https://github.com/lukeboyett), [@jarvis-mns1](https://github.com/jarvis-mns1), [@xiaotian](https://github.com/xiaotian), [@funmerlin](https://github.com/funmerlin), [@joshavant](https://github.com/joshavant), [@eleqtrizit](https://github.com/eleqtrizit), [@heyitsaamir](https://github.com/heyitsaamir), [@amittell](https://github.com/amittell), [@lidge-jun](https://github.com/lidge-jun), [@liorb-mountapps](https://github.com/liorb-mountapps), [@masatohoshino](https://github.com/masatohoshino), [@bladin](https://github.com/bladin), and [@giodl73-repo](https://github.com/giodl73-repo). - CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, ignore workspace dotenv provider credentials, wait for respawn child shutdown, bound heartbeat defaults plus Codex, GitHub Copilot, OpenAI, Anthropic, Google, Feishu, LM Studio, MiniMax, Xiaomi TTS, and local-provider OAuth/token/model requests, harden Codex auth probes, label auth health by agent, preserve explicit agentRuntime pins during Codex model migration, warm provider auth off the main thread, honor Codex response timeouts, stop migrating current Claude Haiku 4.5 profiles to Sonnet, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. ([#87398](openclaw/openclaw#87398), [#86281](openclaw/openclaw#86281), [#87361](openclaw/openclaw#87361), [#88133](openclaw/openclaw#88133), [#83655](openclaw/openclaw#83655), [#87559](openclaw/openclaw#87559), [#87719](openclaw/openclaw#87719), [#88088](openclaw/openclaw#88088), [#85924](openclaw/openclaw#85924), [#84362](openclaw/openclaw#84362)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@samzong](https://github.com/samzong), [@giodl73-repo](https://github.com/giodl73-repo), [@alkor2000](https://github.com/alkor2000), [@mmaps](https://github.com/mmaps), [@nxmxbbd](https://github.com/nxmxbbd), and [@vincentkoc](https://github.com/vincentkoc). - Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks and stale rate-limit cooldown probes, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, clear completed session active runs, clear stale chat stream buffers, and evict current plugin-state namespaces at row caps. ([#87810](openclaw/openclaw#87810), [#87833](openclaw/openclaw#87833), [#75089](openclaw/openclaw#75089)) Thanks [@joshavant](https://github.com/joshavant) and [@litang9](https://github.com/litang9). - Config/parsing/network: reject partial numeric parsing, parse provider/Discord retry headers and dates strictly, honor IPv6 and bare IPv6 `no_proxy` entries, preserve empty plugin allowlists, canonicalize secret target array indexes, and reject malformed media content lengths, inspected TCP ports, marketplace content lengths, cron epochs, sandbox stat fields, unsafe duration values, empty config path segments, noncanonical schema array refs, unsafe Telegram callback pages, and invalid Teams attachment-fetch DNS targets. ([#87883](openclaw/openclaw#87883)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Browser/input hardening: reject invalid tab indexes, excessive viewport resizes, explicit zero CDP ports, malformed geolocation options, unsafe screenshot or permission-grant timeouts, loose response-body limits, invalid cookie expiries, and non-finite Browser tool delays/timeouts. - Cron/automation: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot, and preflight model fallbacks before skipping scheduled work. ([#82887](openclaw/openclaw#82887)) Thanks [@chen-zhang-cs-code](https://github.com/chen-zhang-cs-code). - Auto-reply/directives: respect provider and relayed channel metadata during directive persistence so channel-originated decisions keep their intended context. ([#87683](openclaw/openclaw#87683)) - WhatsApp: resolve the auth directory from the active profile so profile-scoped WhatsApp installs do not drift to the wrong credential root. ([#82492](openclaw/openclaw#82492)) Thanks [@lidge-jun](https://github.com/lidge-jun). - Gateway/session state: clear completed session active runs, avoid cold-loading providers for MCP inventory, cache single-session child indexes, cap handshake timers, and bound preauth, auth-guard, media, transcript, readiness, and port options. - Channels/replies: preserve channel-owned progress callbacks when verbose output is off, keep group-room progress suppression intact, prefer external session delivery context, escape Discord component id delimiters, force final TUI chat repaints, show Slack reasoning previews, and normalize Discord/Matrix/Mattermost channel numeric options. ([#87476](openclaw/openclaw#87476), [#87423](openclaw/openclaw#87423)) - Agents/tool args: harden smart-quoted argument repair for edit arrays and exact escaped arguments so model-produced tool calls recover without corrupting valid input. ([#86611](openclaw/openclaw#86611)) Thanks [@ferminquant](https://github.com/ferminquant). - Providers/agents: preserve seeded Anthropic signatures, preserve signed thinking payloads, concatenate signature-delta chunks, preserve DeepSeek `reasoning_content` replay across tier suffixes, apply OpenRouter strict9 ids to Mistral routes, promote Ollama plain-text tool calls, load NVIDIA featured model catalogs, stream MiniMax music generation responses, and recover empty preflight compaction. ([#87593](openclaw/openclaw#87593), [#87493](openclaw/openclaw#87493), [#80775](openclaw/openclaw#80775), [#84764](openclaw/openclaw#84764)) Thanks [@Pluviobyte](https://github.com/Pluviobyte) and [@eleqtrizit](https://github.com/eleqtrizit). - Media/images: skip CLI image cache refs when resolving generated images, allow trusted generated HTML attachments, and bound generated video downloads so stale refs and slow providers fail cleanly. ([#87523](openclaw/openclaw#87523), [#87982](openclaw/openclaw#87982)) - File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled. - Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, reuse gateway session and plugin metadata paths, skip unchanged store serialization, patch single-entry session writes, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, avoid full session snapshots for entry reads, defer configured Slack full startup, prefer bundled plugin dist entries, and slim current metadata identity caches. ([#87760](openclaw/openclaw#87760)) - Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, isolate npm plugin installs per package, reject incompatible package plugin API installs, drop the leftover root Sharp dependency from package manifests after the Rastermill migration, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, QA-Lab credential broker calls, QA Matrix substrate requests, and release scenario logs, and keep release/google live guards current. ([#87647](openclaw/openclaw#87647), [#87477](openclaw/openclaw#87477)) Thanks [@rohitjavvadi](https://github.com/rohitjavvadi) and [@vincentkoc](https://github.com/vincentkoc). - Release/CI: bound manual git fetches, ClawHub verifier responses, ClawHub owner metadata, dependency-guard error bodies, Parallels limits, startup/test/memory budget parsing, and diffs viewer build warnings so release lanes fail with useful proof instead of hanging. ([#87839](openclaw/openclaw#87839)) </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/759

@giodl73-repo

Merged via squash. Prepared head SHA: 2023e8c Co-authored-by: giodl73-repo <235387111+giodl73-repo@users.noreply.github.com> Reviewed-by: @giodl73-repo

@giodl73-repo

Merged via squash. Prepared head SHA: 2023e8c Co-authored-by: giodl73-repo <235387111+giodl73-repo@users.noreply.github.com> Reviewed-by: @giodl73-repo

openclaw-barnacle Bot added docs Improvements or additions to documentation extensions: policy size: XL maintainer Maintainer-authored PR labels May 26, 2026

clawsweeper Bot added the rating: 🌊 off-meta tidepool PR readiness rating does not apply to this item. label May 26, 2026

This was referenced May 26, 2026

Policy: add data handling conformance checks #87056

Merged

fix(policy): reject unsupported policy keys #87074

Merged

test(policy): add config coverage report #87081

Open

giodl73-repo force-pushed the policy-policy-conformance branch from a1b3d70 to eb95494 Compare May 27, 2026 18:42

clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. and removed rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. labels May 27, 2026

giodl73-repo force-pushed the policy-policy-conformance branch from eb95494 to a9158bb Compare May 27, 2026 22:28

giodl73-repo marked this pull request as ready for review May 27, 2026 22:29

Merge branch 'main' into policy-policy-conformance

daa4520

Merge branch 'main' into policy-policy-conformance

438f625

Merge branch 'main' into policy-policy-conformance

d24ca55

Merge branch 'main' into policy-policy-conformance

16ba31f

giodl73-repo added 2 commits May 28, 2026 22:59

Merge branch 'main' into policy-policy-conformance

1b6ef87

Merge branch 'main' into policy-policy-conformance

2023e8c

giodl73-repo merged commit 08beb6b into openclaw:main May 29, 2026
93 checks passed

github-actions Bot mentioned this pull request May 29, 2026

📡 Upstream Digest — 2026-05-29 07:47 UTC curtismercier/openclaw-mods#969

Open

Uh oh!

Conversation

giodl73-repo commented May 26, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Usage

Contract

Validation

Uh oh!

clawsweeper Bot commented May 26, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 26, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Hatch command

Uh oh!

giodl73-repo commented May 27, 2026

Uh oh!

clawsweeper Bot commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

giodl73-repo commented May 27, 2026

Uh oh!

clawsweeper Bot commented May 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

giodl73-repo commented May 29, 2026

Uh oh!

clawsweeper Bot commented May 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

giodl73-repo commented May 29, 2026

Uh oh!

clawsweeper Bot commented May 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

giodl73-repo commented May 29, 2026

Uh oh!

clawsweeper Bot commented May 29, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

giodl73-repo commented May 26, 2026 •

edited

Loading

clawsweeper Bot commented May 26, 2026 •

edited

Loading

clawsweeper Bot commented May 26, 2026 •

edited

Loading

clawsweeper Bot commented May 27, 2026 •

edited

Loading

clawsweeper Bot commented May 27, 2026 •

edited

Loading

clawsweeper Bot commented May 29, 2026 •

edited

Loading

clawsweeper Bot commented May 29, 2026 •

edited

Loading

clawsweeper Bot commented May 29, 2026 •

edited

Loading

clawsweeper Bot commented May 29, 2026 •

edited

Loading