fix(exec): hide unavailable durable approval actions by jesse-merhi · Pull Request #86359 · openclaw/openclaw

jesse-merhi · 2026-05-25T06:52:27Z

Summary

teach the macOS native exec approval prompt to consume allowedDecisions directly, with ask only as a legacy fallback
pass allowedDecisions through the Control UI approval parser and render only allowed dashboard actions
keep durable approvals available for on-miss approvals and legacy payloads that do not include an allowed decision list
fall back safely when native allowedDecisions is malformed instead of dropping the prompt
keep modal cancel from sending deny when denial is not an allowed decision

Verification

node scripts/run-vitest.mjs ui/src/ui/controllers/exec-approval.test.ts ui/src/ui/views/exec-approval.test.ts ui/src/ui/views/exec-approval.browser.test.ts
swift test --package-path apps/macos --filter ExecApprovalPromptLayoutTests
swift test --package-path apps/macos --filter ExecApprovalsSocketAuthTests --filter ExecApprovalsGatewayPrompterTests
git diff --check 4beadbf9519ef45d2b9cf74dbb60c4b75af3a48e..HEAD
.agents/skills/autoreview/scripts/autoreview --mode commit --commit HEAD clean: no accepted/actionable findings
Rebuilt BAD and GOOD mac apps from current origin/main base 4beadbf951 with real signing identity jessesCert

Real behavior proof

Behavior addressed: Ask mode: always approvals no longer offer durable Always Allow in the native macOS prompt or the Control UI approval modal.
Real environment tested: local macOS A/B apps, signed with jessesCert; BAD from current main, GOOD from this PR.
Exact steps or command run after this patch: triggered system.run for /bin/sh -lc pwd through the local Gateway/native app approval path.
Evidence after fix: BAD showed Allow Once, Always Allow, and Don't Allow; GOOD showed only Don't Allow and Allow Once in the native prompt. Focused Control UI tests prove allowedDecisions: ["allow-once", "deny"] renders only Allow once and Deny. Focused Swift tests prove malformed native allowedDecisions falls back and native modal close does not synthesize deny when it was not rendered.
Observed result after fix: GOOD no longer exposes durable approval for ask: always.
What was not tested: broad full-suite CI; GitHub checks had not reported yet after the latest push.

Agent Transcript

Redacted local agent transcript

Scope:
- PR #86359: fix unavailable durable exec approval actions.
- Branch: jm/fix-macos-ask-always-approval.
- Primary surfaces:
  - macOS native exec approval prompt.
  - Control UI exec/plugin approval prompt.
  - Gateway approval-decision contract.
  - JSONL socket close handling for native prompt cancellation.
  - Control UI warning text and i18n fallback files.

Redaction note:
- This transcript is a curated local work log, not a raw chat export.
- Personal/casual wording, local machine details, auth/session details, raw tool output, prompts, secrets, browser state, and unrelated turns were omitted.
- User input is summarized as maintainer direction and verification feedback.
- Multiple related local sessions were reviewed. Duplicate subagent reviews and unrelated branch-review turns were not included directly; only the parts that explain how this PR was discovered, scoped, tested, and fixed are summarized.

Origin context before this PR:
- Before PR #86359 existed, a separate heavy review session investigated PR #84172, the broader command-authorization rewrite.
- The maintainer asked that review to look hard at old exec-approval behavior, especially approval fallbacks, durable "allow always" persistence, native macOS parity, and behavior that had grown from earlier security patching.
- That review found several real approval-contract issues in the broader branch. Two were especially relevant to this PR:
  - request-specific approval choices were being modeled as `allowedDecisions`;
  - native/macOS approval paths still had to prove they respected the same approval-decision contract as the gateway.
- One origin sub-review explicitly checked exec approvals, allow-always persistence, approval fallback behavior, node-host/gateway/system.run/native macOS parity, UI/native `allowedDecisions`, and `requiresInteractiveApproval`.
- That sub-review found a native macOS gap: caller-supplied `approved` or `approvalDecision` fields could bypass an interactive-only approval path even when the prompt hid `allow-always`.
- The same origin review showed the intended server contract:
  - `ask=always` resolves to `["allow-once", "deny"]`;
  - other approval modes can include `["allow-once", "allow-always", "deny"]`;
  - the gateway rejects unavailable decisions such as `allow-always` when the effective policy requires approval every time.
- This was the context that led to carving out PR #86359 as a narrow shipped-behavior fix: make the approval UIs show only the choices the request/server contract allows, instead of waiting for the much larger PR #84172.

Initial goal:
- Review PR #86359 and explain what it changed.
- Find related issues and PRs that had raised similar approval-policy problems.
- Fix review findings.
- Build and test bad/good local macOS app variants for A/B behavior checks.
- Use the dashboard/manual test flow so the maintainer could personally verify behavior.

How the issue was found:
- The earlier discovery work started in the PR #84172 review, where the maintainer was searching for approval behavior that should be removed or tightened.
- That review showed `allowedDecisions` was the approval UI contract, not just a helper for one client.
- PR #86359 was then created to fix the smaller shipped mismatch exposed by that work.
- The later PR #86359 review compared the PR description against current shipped behavior and the gateway approval contract.
- Current-main and PR source showed a mismatch:
  - the gateway already computed `allowedDecisions`;
  - the gateway already rejected decisions outside that list;
  - approval consumers could still render choices such as `Always allow` without using that list.
- The earlier PR #84172 work showed the intended shape more clearly:
  - approval requests carry `allowedDecisions`;
  - UI clients should render from the allowed list;
  - server-side resolution remains the final enforcement point.
- This is what turned the review from "macOS hides one button based on ask" into "all approval clients should respect the request's allowed-decision contract."
- The maintainer then pushed on whether this was only macOS or also the dashboard, which led to explicitly including the Control UI in the fix.

Related session candidates reviewed:
- Origin heavy review session for PR #84172:
  - predates PR #86359 and contains the broader approval-policy investigation that led to carving this fix out.
  - covered command authorization, exact-command durable fallback removal, `allow-always` persistence, fallback behavior, native macOS parity, UI/native `allowedDecisions`, and `requiresInteractiveApproval`.
- Origin sub-review for PR #84172:
  - focused on the native macOS approval boundary and confirmed the request-specific decision list was the contract approval clients should respect.
  - reported that native macOS could still bypass interactive-only approval through caller-supplied approval flags, showing that native parity was still an open approval-boundary concern.
- Earlier fallback review around the same branch:
  - found that "Allow Always unavailable" and "interactive approval required" should not be conflated.
  - helped separate the durable-button visibility question from timeout/fallback denial behavior.
- Main PR review and implementation session:
  - contained the initial PR review, related-issue search, local A/B testing, fixes, review loops, and final push.
- Broader command-authorization review sessions:
  - showed where the `allowedDecisions` contract was being introduced and how sibling approval clients were expected to use it.
- Related PR/issue discovery sessions:
  - identified the broader normalized command authorization PR as overlapping context, but not a reason to close this standalone shipped bugfix.
- Local testing sessions:
  - captured the bad/good app setup, dashboard testing, repeated rebuilds from latest main, and manual prompt behavior checks.
- Cold-review sessions:
  - independently checked the final approval/socket behavior, but were mostly excluded from the transcript body because they duplicated the same findings and validation targets.

Initial PR understanding:
- The PR aimed to hide the durable "Always allow" action when the effective exec approval policy requires approval every time.
- The expected `ask=always` choices were:
  - `Allow once`
  - `Deny`
- The expected durable-approval-capable choices remained:
  - `Allow once`
  - `Always allow`
  - `Deny`
- The gateway already computed and enforced allowed approval decisions. The bug was that one or more UI consumers could still show choices the gateway would reject.

Related-work review:
- The broader command authorization work was inspected as related context.
- That work had the same core concept: approval requests carry an `allowedDecisions` list, and UIs should render from that list.
- That context made it clear that `allowedDecisions` was not just a web UI helper. It was the protocol shape approval consumers should use when deciding which actions to show.
- The standalone PR remained justified because this was a shipped approval UI mismatch that could be fixed narrowly without waiting for the broader branch.
- The maintainer asked specifically whether anything already fixed the bug on latest main. Main still needed this fix for the shipped behavior.

Maintainer-driven manual testing:
- The maintainer requested a true A/B setup with separate bad and good macOS apps.
- Both apps were rebuilt from a current main base with a real signing identity so native permission prompts would behave realistically.
- The maintainer tested simple commands such as `pwd` from the local UI/dashboard flow.
- During A/B testing, the maintainer reported that prompts did not always appear as expected, the bad app behavior was confusing, and one flow appeared to flash an approval request and then disappear.
- The test setup was refreshed by pulling latest main and rebuilding both variants to confirm the bug was not just stale local state.
- The maintainer confirmed the dashboard path should be part of the real validation, not only the native app path.

Behavior clarified during review:
- This was not a command-specific rule. The same command can show different actions depending on the approval policy and request metadata.
- For `ask=always`, even a harmless command like `pwd` should not offer durable approval.
- For `ask=on-miss`, a command that misses the allowlist may legitimately offer durable approval.
- Plugin approval requests can also restrict decisions, but their reasons are not necessarily exec-policy reasons.
- The server remains the source of truth and rejects unavailable decisions even if a client tries to send them.

Main implementation work:
- macOS native prompt:
  - Decoded `allowedDecisions` from the approval request.
  - Filtered malformed decision values.
  - Rendered buttons from the explicit allowed-decision list when present.
  - Preserved fallback behavior for older/malformed payloads:
    - `ask=always` falls back to `Allow once` and `Deny`.
    - other/missing ask values preserve previous durable-approval behavior.
  - Mapped AppKit modal button indexes back through the same ordered decision list.
  - Avoided returning a hidden decision when a prompt closes and `deny` is not available.

- macOS native callers:
  - Passed ask-derived allowed decisions into local native prompt paths.
  - Treated prompt close without a decision as denial/unavailable, so commands do not run after an unresolved close.

- Control UI:
  - Parsed `allowedDecisions` from exec approval events.
  - Parsed `allowedDecisions` from plugin approval events.
  - Rendered only allowed buttons.
  - Preserved explicit decision order.
  - Fell back from missing/malformed data using the same ask-aware behavior.
  - Prevented Escape/cancel from sending `deny` when `deny` is not an available decision.

- JSONL socket handling:
  - Review found that native prompt close without a response could leave Node socket clients waiting for the full timeout.
  - The socket client was changed to settle on peer `end`/`close`.
  - Timeout cleanup was moved into the shared finish path so all outcomes clear the timer.
  - A focused regression test was added for close-without-accepted-response.

Maintainer-policy discussion:
- Review called out a policy choice around legacy/malformed payload fallback.
- Current behavior preserves compatibility:
  - missing/malformed `allowedDecisions` plus `ask=always` omits durable approval.
  - missing/malformed `allowedDecisions` plus missing/unknown/non-always ask preserves old durable-approval behavior.
- The maintainer asked for plain-English clarification of whether fallback exists and what it means.
- The conclusion was that this is an intentional compatibility fallback unless maintainers choose a stricter fail-closed policy.

GitHub review follow-up:
- A maintainer comment asked the Control UI to mirror channel-message behavior by explaining why "Allow Always" is unavailable.
- The existing channel copy was:
  "The effective approval policy requires approval every time, so Allow Always is unavailable."
- The Control UI was updated to show that warning for exec approvals when `allow-always` is absent.
- The warning was scoped away from plugin approvals because plugin restrictions can be request-scoped and unrelated to exec policy.
- Tests were added for:
  - restricted exec approval shows the warning.
  - unrestricted exec approval does not show the warning.
  - restricted plugin approval does not show the exec-policy warning.
- Adding the English i18n key triggered a review finding about generated locale drift.
- `ui:i18n:sync` was run and generated locale fallback/meta updates were committed.
- `ui:i18n:check` then passed.

Review findings fixed:
- Swift formatting issue on the original PR head.
- Native prompt initially deriving decisions from raw `ask` instead of the gateway decision contract.
- Native prompt close/cancel behavior producing or attempting hidden decisions.
- Control UI lint/return-shape issue in approval action rendering.
- JSONL socket timeout behavior after native close without a response.
- Control UI warning initially applying too broadly to plugin approvals.
- i18n generated file drift after adding the warning string.

Focused validation run after fixes:
- Vitest:
  - `src/infra/jsonl-socket.test.ts`
  - `src/infra/exec-host.test.ts`
  - `src/infra/exec-approvals-store.test.ts`
  - `ui/src/ui/controllers/exec-approval.test.ts`
  - `ui/src/ui/views/exec-approval.test.ts`
  - `ui/src/ui/views/exec-approval.browser.test.ts`
- Result:
  - 6 files passed.
  - 57 tests passed.

- Swift:
  - `ExecApprovalPromptLayoutTests`
  - Result: 7 tests passed.
  - Covered allowed decision lists, ask fallback, malformed allowed decisions, modal close behavior, and prompt layout.

- Swift:
  - `ExecApprovalsSocketAuthTests`
  - `ExecApprovalsGatewayPrompterTests`
  - Result: 12 tests passed.

- Control UI follow-up tests:
  - `ui/src/ui/controllers/exec-approval.test.ts`
  - `ui/src/ui/views/exec-approval.test.ts`
  - `ui/src/ui/views/exec-approval.browser.test.ts`
  - Result after warning work: 3 files passed, 27 tests passed.

- i18n:
  - `pnpm ui:i18n:check`
  - Result: clean for all configured locales with fallback entries updated.

- Lint/format:
  - `node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json ...`
  - Result: passed for touched UI files.
  - `git diff --check`
  - Result: passed.

Review process:
- Repeated review passes were run after each accepted fix.
- Independent cold review passes were run on the final approval/socket fix.
- A follow-up autoreview found the i18n sync gap; it was fixed.
- A follow-up autoreview found the plugin-warning scope bug; it was fixed.
- Final autoreview on the warning follow-up reported no accepted/actionable findings.

Pushed commits:
- `fix(macos): align ask always approval actions`
- `fix(macos): harden approval prompt decisions`
- `fix(ui): satisfy approval action lint`
- `fix(infra): settle jsonl sockets on close`
- `fix(ui): explain unavailable durable approvals`

Outcome:
- The PR branch was pushed to the live PR.
- The final pushed head included the macOS native fix, Control UI fix, JSONL socket close fix, dashboard warning, i18n generated updates, and focused tests.
- CI restarted on the final pushed head; no failures were reported at the time of handoff.

Copilot

Pull request overview

This PR updates the macOS exec-approval prompt so that “Always Allow” (durable approval) is not offered when the ask policy is always, while keeping durable approvals available for on-miss. It also adds focused test coverage around the prompt decision set.

Changes:

Drive NSAlert button creation from a computed decision list (instead of hardcoding 3 buttons).
Add allowedPromptDecisions to omit .allowAlways when ask == always.
Add unit tests validating decision sets for always vs on-miss, and make ExecApprovalDecision Equatable to support assertions.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

File	Description
apps/macos/Tests/OpenClawIPCTests/ExecApprovalPromptLayoutTests.swift	Adds tests covering which decisions/buttons are allowed for `ask=always` vs `ask=on-miss`.
apps/macos/Sources/OpenClaw/ExecApprovalsSocket.swift	Refactors prompt button generation to be decision-driven and introduces the decision-filtering logic.
apps/macos/Sources/OpenClaw/ExecApprovals.swift	Adds `Equatable` conformance to `ExecApprovalDecision` for test comparisons.

+    static func allowedPromptDecisions(_ request: ExecApprovalPromptRequest) -> [ExecApprovalDecision] {
+        request.ask == ExecAsk.always.rawValue
+            ? [.allowOnce, .deny]
+            : [.allowOnce, .allowAlways, .deny]
+    }


clawsweeper · 2026-05-25T06:54:36Z

Codex review: needs maintainer review before merge. Reviewed May 26, 2026, 11:57 PM ET / 03:57 UTC.

Summary
Threads allowedDecisions through macOS native and Control UI approval prompts, adjusts cancel/socket-close handling, adds focused Swift/Vitest coverage, and regenerates UI i18n fallback output.

PR surface: Source +122, Tests +152, Other +246. Total +520 across 49 files.

Reproducibility: yes. Current-main source shows the gateway emits allowedDecisions without allow-always for ask=always, while the current Control UI hardcodes an Always allow button; the PR body also reports signed macOS BAD/GOOD A/B proof.

Review metrics: 1 noteworthy metric.

Approval prompt clients: 2 changed. Both the macOS native prompt and Control UI now render from the request's allowed-decision list, which is the security-sensitive behavior maintainers need to review.

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

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

Rank-up moves:

none

Risk before merge

This PR intentionally changes a command-approval security boundary in both native macOS and Control UI prompts, so maintainers should explicitly confirm the UI contract before merge.
The PR body reports focused tests and signed macOS A/B proof, but broad full-suite CI was not part of the stated after-fix proof and should gate the exact head.

Maintainer options:

Land after security-boundary review (recommended)
A maintainer can land this after confirming allowedDecisions is the prompt-rendering contract and exact-head checks are acceptable.
Ask for broader visual proof
If the PR-body A/B proof is not enough, ask for additional native macOS and Control UI visual proof before merge.
Defer to the larger exec branch
Pause only if maintainers reverse the current discussion and decide this standalone approval bugfix should not land separately.

Next step before merge
Protected MEMBER-authored security-boundary PR: the remaining action is maintainer review and exact-head validation, not an automated repair.

Security
Cleared: No concrete supply-chain or secrets-handling issue was found; the approval-boundary behavior is captured as merge risk for maintainer review.

Review details

Best possible solution:

Keep the standalone bugfix, complete maintainer security-boundary review plus exact-head checks, then let the broader normalized auto-mode work rebase on this behavior.

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

Yes. Current-main source shows the gateway emits allowedDecisions without allow-always for ask=always, while the current Control UI hardcodes an Always allow button; the PR body also reports signed macOS BAD/GOOD A/B proof.

Is this the best way to solve the issue?

Yes. Rendering from server-provided allowedDecisions is the narrow maintainable fix, with ask-mode fallback only for legacy payloads rather than adding a separate UI policy source.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against d58f864e23dc.

Label changes

Label justifications:

P2: This is a normal-priority approval UI/security-boundary bugfix with focused blast radius across macOS and Control UI prompts.
merge-risk: 🚨 security-boundary: Merging changes which command-approval actions users can choose and how prompt cancellation resolves, so the approval boundary needs maintainer confirmation.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes after-fix signed macOS BAD/GOOD A/B proof plus focused Control UI and Swift verification for the changed approval behavior.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix signed macOS BAD/GOOD A/B proof plus focused Control UI and Swift verification for the changed approval behavior.

Evidence reviewed

PR surface:

Source +122, Tests +152, Other +246. Total +520 across 49 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	41	199	77	+122
Tests	3	153	1	+152
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	5	268	22	+246
Total	49	620	100	+520

What I checked:

Current main still hardcodes durable Control UI action: Current main renders Allow once, Always allow, and Deny buttons unconditionally in the exec approval modal, so it ignores the gateway-provided allowed decision list. (ui/src/ui/views/exec-approval.ts:151, d58f864e23dc)
Current main gateway contract already carries allowed decisions: Exec approval requests on current main include allowedDecisions: resolveExecApprovalAllowedDecisions({ ask }), and resolve validation rejects decisions outside resolveExecApprovalRequestAllowedDecisions. (src/gateway/server-methods/exec-approval.ts:325, d58f864e23dc)
Allowed-decision resolver omits allow-always for ask=always: Current main's resolveExecApprovalAllowedDecisions returns only allow-once and deny when ask normalizes to always. (src/infra/exec-approvals.ts:1286, d58f864e23dc)
PR makes Control UI render from allowedDecisions: The PR parses allowedDecisions, resolves fallback decisions from ask, renders only those decisions, and suppresses cancel-as-deny when deny is unavailable. (ui/src/ui/views/exec-approval.ts:141, 1c73fa13ed71)
PR makes macOS native prompt render from allowedDecisions: The PR decodes valid native allowedDecisions, falls back by ask mode for legacy payloads, maps modal button indexes through the decision list, and returns nil when no rendered denial exists. (apps/macos/Sources/OpenClaw/ExecApprovalsSocket.swift:53, 1c73fa13ed71)
Focused regression coverage is present: The PR adds Swift coverage for ask=always, legacy fallback, malformed native decisions, and modal close behavior, plus Control UI tests for hidden unavailable decisions and cancel handling. (apps/macos/Tests/OpenClawIPCTests/ExecApprovalPromptLayoutTests.swift:5, 1c73fa13ed71)

Likely related people:

vincentkoc: Local blame/log on the current-main approval UI, macOS prompt, and gateway request contract points to commit 8fa5ecb as the available current-main provenance in this checkout. (role: current-main introducer and recent area contributor; confidence: medium; commits: 8fa5ecb81d02; files: ui/src/ui/views/exec-approval.ts, apps/macos/Sources/OpenClaw/ExecApprovalsSocket.swift, src/gateway/server-methods/exec-approval.ts)
jesse-merhi: The hydrated PR context and related command-authorization work show active ownership of this approval-decision boundary beyond a one-off branch proposal. (role: active approval-boundary contributor; confidence: medium; commits: 73ef69a1cbd0, b60e7a10f1a3, 1c73fa13ed71; files: apps/macos/Sources/OpenClaw/ExecApprovalsSocket.swift, apps/macos/Sources/OpenClaw/NodeMode/MacNodeRuntime.swift, ui/src/ui/views/exec-approval.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 · 2026-05-25T07:03:27Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Cosmic Test Hopper

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: keeps receipts.
Image traits: location merge queue dock; accessory tiny test log scroll; palette cobalt, lime, and pearl; mood curious; pose nestled inside a glowing shell; shell soft velvet shell; lighting moonlit rim light; background quiet workflow signs.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Cosmic Test Hopper 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.

jesse-merhi · 2026-05-25T07:28:16Z

Closing: per follow-up we are keeping these fixes in the original normalized auto mode PR branch instead.

jesse-merhi · 2026-05-25T07:30:28Z

Reopening: this standalone main bugfix should remain separate from PR #70543.

* fix(macos): align ask always approval actions * fix(macos): harden approval prompt decisions * fix(ui): satisfy approval action lint * fix(infra): settle jsonl sockets on close * fix(ui): explain unavailable durable approvals * test(macos): document legacy approval fallback

…026.5.26) (#682) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.22` → `2026.5.26` | --- > ⚠️ **Warning** > > Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/567) for more information. --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.26`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026526) [Compare Source](https://github.com/openclaw/openclaw/compare/v2026.5.22...v2026.5.26) ##### Highlights - Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under load. - Transcripts are core: transcript-backed meeting summaries, source-provider chunks, cleaned user turns, media provenance, Codex mirrors, WebChat replies, and CLI/TUI replay now use one more reliable transcript path. - More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots, remote media staging, and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage/WhatsApp get reaction approvals. - Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents. - Safer content boundaries: Browser snapshot reads honor SSRF policy, system-event text cannot spoof nested prompt markers, fetched file text is wrapped as external content, ClickClack inbound sender allowlists run before agent dispatch, stale device tokens are rejected, and serialized tool-call text is scrubbed from replies. - Providers, Codex, and local models are steadier: named auth profiles, OpenAI sampling params, Codex app-server resume/timeout/usage-limit recovery, dynamic tool-schema guards, xAI usage-limit surfacing, Ollama top-p normalization, and local approval resolution reduce provider-specific dead ends. - More reliable install/update/release paths: Alpine installs, trusted runtime fallback roots, stable update channels, Docker/package timeouts, Windows Scheduled Tasks, Windows/macOS proof lanes, Testbox/Crabbox delegation, plugin publish checks, and macOS runner bootstraps all got hardened. - Better observability: Activity tab, gateway secret-prep traces, tool/model stream progress, explicit fast-mode status, systemd Gateway hygiene, OpenTelemetry LLM spans, release performance evidence, and richer telemetry signals make failures easier to inspect. ##### Changes - Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs, CLI surface, source-provider chunks, and cleaned user-turn persistence. - Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. ([#85667](https://github.com/openclaw/openclaw/issues/85667)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. ([#83019](https://github.com/openclaw/openclaw/issues/83019), [#80370](https://github.com/openclaw/openclaw/issues/80370), [#86191](https://github.com/openclaw/openclaw/issues/86191)) - Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual `/approve` commands. ([#85894](https://github.com/openclaw/openclaw/issues/85894), [#85952](https://github.com/openclaw/openclaw/issues/85952), [#85477](https://github.com/openclaw/openclaw/issues/85477)) - Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. ([#84094](https://github.com/openclaw/openclaw/issues/84094)) - TUI/status: queue prompts submitted while an agent is busy and show explicit fast-mode state plus richer systemd Gateway hygiene in status output. ([#86722](https://github.com/openclaw/openclaw/issues/86722), [#87115](https://github.com/openclaw/openclaw/issues/87115), [#86976](https://github.com/openclaw/openclaw/issues/86976)) - Exec approvals: hide durable approval actions that are unavailable for the current prompt and keep approval runtime tokens local-only so stale prompts cannot offer misleading controls. ([#86270](https://github.com/openclaw/openclaw/issues/86270), [#86359](https://github.com/openclaw/openclaw/issues/86359)) - Plugin SDK: add reaction approval helpers and keep diagnostic event root exports discoverable across function-name and alias-bound module graphs. ([#86735](https://github.com/openclaw/openclaw/issues/86735), [#87084](https://github.com/openclaw/openclaw/issues/87084)) - Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. ([#86798](https://github.com/openclaw/openclaw/issues/86798), [#86355](https://github.com/openclaw/openclaw/issues/86355)) Thanks [@ngutman](https://github.com/ngutman). - Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. ([#84649](https://github.com/openclaw/openclaw/issues/84649), [#85843](https://github.com/openclaw/openclaw/issues/85843), [#86517](https://github.com/openclaw/openclaw/issues/86517), [#86678](https://github.com/openclaw/openclaw/issues/86678)) - Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery. - Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection. - Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions. - Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths. - Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation. - Cron: default `cron.maxConcurrentRuns` to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration. - QA-Lab: add `qa coverage --match <query>` so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes. - Discord/model picker: surface an alpha-bucket select (e.g. `A–G (12) · H–N (18) · O–Z (5)`) when the provider list or a provider's model list exceeds 25 items, so configs with `provider/*` wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter. - Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes [#12831](https://github.com/openclaw/openclaw/issues/12831). Thanks [@BunsDev](https://github.com/BunsDev). - Build: include `ui:build` in the `full` and `ciArtifacts` profiles of `scripts/build-all.mjs` so `pnpm build` always rebuilds `dist/control-ui` after `tsdown` cleans `dist`, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. ([#85206](https://github.com/openclaw/openclaw/issues/85206)) - iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. ([#86355](https://github.com/openclaw/openclaw/issues/86355)) Thanks [@ngutman](https://github.com/ngutman). - Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. ([#86437](https://github.com/openclaw/openclaw/issues/86437)) - Codex: update the bundled Codex CLI to 0.134.0 and keep native compaction disabled for budget-triggered app-server turns so OpenClaw owns the recovery boundary. ([#86772](https://github.com/openclaw/openclaw/issues/86772)) ##### Fixes - Memory/security: reject prompt-like text submitted through the explicit `memory_store` tool before embedding or storage, matching the existing auto-capture prompt-injection filter. ([#87142](https://github.com/openclaw/openclaw/issues/87142)) - Gateway/security: enable the default auth rate limiter for remote non-browser and HTTP gateway auth failures when `gateway.auth.rateLimit` is unset, while preserving the loopback exemption. ([#87148](https://github.com/openclaw/openclaw/issues/87148)) - Prompt hardening: route untrusted group prompt metadata through sanitized untrusted structured context while preserving trusted operator-configured group system prompts and aligning the plugin SDK docs/test helpers. ([#87144](https://github.com/openclaw/openclaw/issues/87144)) - Security/content boundaries: validate Browser snapshot tab URLs against SSRF policy before ChromeMCP or direct CDP reads, sanitize queued system-event text so untrusted plugin/channel labels cannot spoof nested prompt markers, wrap fetched file text and metadata as external content, apply ClickClack `allowFrom` sender allowlists before agent dispatch, reject RPCs from invalidated device-token clients during rotation, require staged sandbox media refs, and scrub serialized tool-call text from replies. ([#78526](https://github.com/openclaw/openclaw/issues/78526), [#87094](https://github.com/openclaw/openclaw/issues/87094), [#87062](https://github.com/openclaw/openclaw/issues/87062), [#83741](https://github.com/openclaw/openclaw/issues/83741), [#70707](https://github.com/openclaw/openclaw/issues/70707), [#86924](https://github.com/openclaw/openclaw/issues/86924)) Thanks [@zsxsoft](https://github.com/zsxsoft), [@ttzero25](https://github.com/ttzero25), and [@mmaps](https://github.com/mmaps). - Transcripts/user turns: persist CLI, WebChat, media, follow-up, hook, and Codex-mirror user turns to the admitted session target; keep cleaned transcript text, inline image routing, provenance metadata, replay hooks, and fallback paths idempotent when runtimes fail or restart. - TUI/status/onboarding/UI: queue busy TUI prompts instead of dropping them, preserve the configured default model during onboarding, show failed tool results as errors, show config-open failures in Control UI, keep status JSON plugin scans healthy, preserve xAI usage-limit errors locally, and expose explicit fast-mode/systemd state. ([#86722](https://github.com/openclaw/openclaw/issues/86722), [#87000](https://github.com/openclaw/openclaw/issues/87000), [#85786](https://github.com/openclaw/openclaw/issues/85786), [#87108](https://github.com/openclaw/openclaw/issues/87108), [#87001](https://github.com/openclaw/openclaw/issues/87001), [#86614](https://github.com/openclaw/openclaw/issues/86614), [#87115](https://github.com/openclaw/openclaw/issues/87115), [#86976](https://github.com/openclaw/openclaw/issues/86976)) - Plugin commands/SDK: preserve plugin LLM command auth, bind native plugin command dispatch to the host agent's LLM auth, keep `onDiagnosticEvent` exports discoverable through `Function.name`, stabilize diagnostic event root aliases, correlate pathless read diagnostics, suppress transient runner failures in channel command paths, and repair local approval resolution. ([#85936](https://github.com/openclaw/openclaw/issues/85936), [#87084](https://github.com/openclaw/openclaw/issues/87084), [#86977](https://github.com/openclaw/openclaw/issues/86977), [#87069](https://github.com/openclaw/openclaw/issues/87069), [#86771](https://github.com/openclaw/openclaw/issues/86771)) - Codex/providers: keep WebChat delivery hints out of user prompts, avoid false queued-terminal idle timeouts, share the native hook relay registry, quarantine unsupported dynamic tool schemas, preserve Claude resumed-session system prompts, normalize greedy Ollama `top_p`, preserve per-agent thinking defaults for ingress runs, and avoid native compaction takeover on budget-triggered Codex turns. ([#87096](https://github.com/openclaw/openclaw/issues/87096), [#73950](https://github.com/openclaw/openclaw/issues/73950), [#87049](https://github.com/openclaw/openclaw/issues/87049), [#86689](https://github.com/openclaw/openclaw/issues/86689), [#86772](https://github.com/openclaw/openclaw/issues/86772)) - Gateway/perf/release: reuse startup-warning metadata and prepared auth stores, avoid cloning live-switch and lifecycle session caches on read paths, defer warning and scheduled-service fallback imports, trim Gateway session/startup/runtime CPU churn, skip duplicate turn session touches, stop chat timeout fallback cascades, drop stale subagent announce history, bound benchmark/watch/kitchen-sink teardown waits, bound macOS/package/onboarding/plugin smoke commands, bound install finalization probes, resolve Parallels npm-update commands from guest `PATH`, and bootstrap raw AWS macOS Node/pnpm commands through `/usr/bin/env`. ([#86997](https://github.com/openclaw/openclaw/issues/86997)) - Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. ([#86989](https://github.com/openclaw/openclaw/issues/86989), [#86990](https://github.com/openclaw/openclaw/issues/86990), [#86991](https://github.com/openclaw/openclaw/issues/86991), [#86992](https://github.com/openclaw/openclaw/issues/86992), [#86993](https://github.com/openclaw/openclaw/issues/86993), [#86994](https://github.com/openclaw/openclaw/issues/86994)) Thanks [@keshavbotagent](https://github.com/keshavbotagent). - Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts. - Agents/replay: repair legacy tool results before replay, preserve `sessions_spawn` transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. ([#82203](https://github.com/openclaw/openclaw/issues/82203), [#86934](https://github.com/openclaw/openclaw/issues/86934), [#87025](https://github.com/openclaw/openclaw/issues/87025)) Thanks [@martingarramon](https://github.com/martingarramon), [@vincentkoc](https://github.com/vincentkoc), and [@joshavant](https://github.com/joshavant). - Agents/sessions: handle active-fallback failures in `sessions_send` so fallback routing reports the real failure and does not leave callers with an ambiguous dropped send. ([#86638](https://github.com/openclaw/openclaw/issues/86638)) - Agents/hooks/subagents: enforce default hook agent allowlists, recover failed subagent lifecycle completions, and keep node task lifecycle cleanup from closing the Gateway listener. ([#86101](https://github.com/openclaw/openclaw/issues/86101)) - Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. ([#86677](https://github.com/openclaw/openclaw/issues/86677), [#86476](https://github.com/openclaw/openclaw/issues/86476)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle) and [@pashpashpash](https://github.com/pashpashpash). - Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. ([#87030](https://github.com/openclaw/openclaw/issues/87030), [#86818](https://github.com/openclaw/openclaw/issues/86818), [#86559](https://github.com/openclaw/openclaw/issues/86559)) Thanks [@joshavant](https://github.com/joshavant), [@luoyanglang](https://github.com/luoyanglang), and [@stevenepalmer](https://github.com/stevenepalmer). - Doctor/runtime: validate active bundled MCP tool schemas through the same runtime projection path so unsupported MCP input schemas are reported and quarantined instead of poisoning assistant startup. - CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. ([#87031](https://github.com/openclaw/openclaw/issues/87031), [#85387](https://github.com/openclaw/openclaw/issues/85387)) Thanks [@giodl73-repo](https://github.com/giodl73-repo) and [@vincentkoc](https://github.com/vincentkoc). - Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. ([#86814](https://github.com/openclaw/openclaw/issues/86814), [#86964](https://github.com/openclaw/openclaw/issues/86964)) Thanks [@Alix-007](https://github.com/Alix-007) and [@vincentkoc](https://github.com/vincentkoc). - Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates. - QA/Telegram: bound Telegram user credential tar and broker calls so live proof setup fails with a timeout instead of waiting for the outer Crabbox job deadline. - QA/Tool Search: bound gateway E2E HTTP probes, run only the fixture plugin, and clean up temporary fixture trees after the compact tool-catalog proof completes. - Telegram/network: treat `ENETDOWN` as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. ([#86762](https://github.com/openclaw/openclaw/issues/86762)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. ([#83873](https://github.com/openclaw/openclaw/issues/83873), [#85361](https://github.com/openclaw/openclaw/issues/85361), [#85555](https://github.com/openclaw/openclaw/issues/85555), [#85656](https://github.com/openclaw/openclaw/issues/85656), [#85709](https://github.com/openclaw/openclaw/issues/85709), [#86299](https://github.com/openclaw/openclaw/issues/86299), [#86553](https://github.com/openclaw/openclaw/issues/86553)) Thanks [@SebTardif](https://github.com/SebTardif), [@luoyanglang](https://github.com/luoyanglang), and [@neeravmakwana](https://github.com/neeravmakwana). - iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. ([#82642](https://github.com/openclaw/openclaw/issues/82642), [#85475](https://github.com/openclaw/openclaw/issues/85475), [#86569](https://github.com/openclaw/openclaw/issues/86569), [#86705](https://github.com/openclaw/openclaw/issues/86705), [#86706](https://github.com/openclaw/openclaw/issues/86706), [#86770](https://github.com/openclaw/openclaw/issues/86770)) Thanks [@homer-byte](https://github.com/homer-byte), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@swang430](https://github.com/swang430), and [@OmarShahine](https://github.com/OmarShahine). - WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect `OPENCLAW_HOME`, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. ([#83833](https://github.com/openclaw/openclaw/issues/83833), [#85309](https://github.com/openclaw/openclaw/issues/85309), [#85777](https://github.com/openclaw/openclaw/issues/85777), [#85794](https://github.com/openclaw/openclaw/issues/85794), [#85906](https://github.com/openclaw/openclaw/issues/85906), [#86318](https://github.com/openclaw/openclaw/issues/86318), [#86697](https://github.com/openclaw/openclaw/issues/86697)) Thanks [@sliverp](https://github.com/sliverp), [@neeravmakwana](https://github.com/neeravmakwana), and [@Kailigithub](https://github.com/Kailigithub). - Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. ([#80227](https://github.com/openclaw/openclaw/issues/80227), [#86238](https://github.com/openclaw/openclaw/issues/86238), [#86487](https://github.com/openclaw/openclaw/issues/86487), [#86571](https://github.com/openclaw/openclaw/issues/86571), [#86595](https://github.com/openclaw/openclaw/issues/86595), [#86601](https://github.com/openclaw/openclaw/issues/86601)) - Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. ([#85378](https://github.com/openclaw/openclaw/issues/85378), [#85542](https://github.com/openclaw/openclaw/issues/85542), [#85891](https://github.com/openclaw/openclaw/issues/85891), [#85909](https://github.com/openclaw/openclaw/issues/85909), [#86408](https://github.com/openclaw/openclaw/issues/86408)) - Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. ([#70473](https://github.com/openclaw/openclaw/issues/70473), [#85764](https://github.com/openclaw/openclaw/issues/85764), [#86014](https://github.com/openclaw/openclaw/issues/86014), [#86134](https://github.com/openclaw/openclaw/issues/86134), [#86427](https://github.com/openclaw/openclaw/issues/86427), [#86944](https://github.com/openclaw/openclaw/issues/86944)) Thanks [@openperf](https://github.com/openperf), [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@zhangguiping-xydt](https://github.com/zhangguiping-xydt), and [@ferminquant](https://github.com/ferminquant). - Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. ([#85739](https://github.com/openclaw/openclaw/issues/85739), [#85787](https://github.com/openclaw/openclaw/issues/85787), [#86060](https://github.com/openclaw/openclaw/issues/86060), [#86260](https://github.com/openclaw/openclaw/issues/86260), [#86384](https://github.com/openclaw/openclaw/issues/86384), [#86533](https://github.com/openclaw/openclaw/issues/86533)) Thanks [@liaoyl830](https://github.com/liaoyl830). - Install/release: support Alpine CLI installs and runtime floors, prefer trusted startup argv runtime fallback roots, reject stale CLI node runtimes, avoid npm `min-release-age` installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, make release/plugin prerelease checks fail closed instead of hanging or false-greening, and use host-visible Crabbox local work roots for Docker-backed proof. ([#85491](https://github.com/openclaw/openclaw/issues/85491)) - Windows daemon: keep Scheduled Task gateway launches running on battery power and avoid workgroup-machine prompts for a domain user during task installation. ([#59299](https://github.com/openclaw/openclaw/issues/59299)) - Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. ([#85849](https://github.com/openclaw/openclaw/issues/85849), [#85934](https://github.com/openclaw/openclaw/issues/85934), [#86046](https://github.com/openclaw/openclaw/issues/86046), [#86557](https://github.com/openclaw/openclaw/issues/86557)) - Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. ([#85776](https://github.com/openclaw/openclaw/issues/85776), [#86037](https://github.com/openclaw/openclaw/issues/86037), [#86437](https://github.com/openclaw/openclaw/issues/86437), [#86857](https://github.com/openclaw/openclaw/issues/86857), [#86923](https://github.com/openclaw/openclaw/issues/86923)) - Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. ([#80613](https://github.com/openclaw/openclaw/issues/80613), [#82928](https://github.com/openclaw/openclaw/issues/82928), [#85060](https://github.com/openclaw/openclaw/issues/85060), [#85704](https://github.com/openclaw/openclaw/issues/85704), [#85967](https://github.com/openclaw/openclaw/issues/85967), [#86701](https://github.com/openclaw/openclaw/issues/86701)) Thanks [@brokemac79](https://github.com/brokemac79), [@openperf](https://github.com/openperf), and [@yaaboo-gif](https://github.com/yaaboo-gif). - Agents/sessions: include visibility metadata on restricted `sessions_list` results so scoped counts are clearly reported without widening access or exposing hidden-session counts. ([#86944](https://github.com/openclaw/openclaw/issues/86944)) Thanks [@ferminquant](https://github.com/ferminquant). - Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid `discovery.wideArea.domain` and `dns setup --domain` values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors. Thanks [@mmaps](https://github.com/mmaps). - Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. ([#86312](https://github.com/openclaw/openclaw/issues/86312)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Telegram: treat `/command@TargetBot` bot-command entities as explicit mentions for the addressed bot so `requireMention` groups no longer drop targeted commands or captions. Fixes [#84462](https://github.com/openclaw/openclaw/issues/84462). ([#86553](https://github.com/openclaw/openclaw/issues/86553)) Thanks [@luoyanglang](https://github.com/luoyanglang). - CI: bound Docker/Bash E2E tarball npm installs with `OPENCLAW_E2E_NPM_INSTALL_TIMEOUT` so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install. - CI: fail Parallels npm-update smoke jobs after the guest command timeout and cleanup backstop instead of only logging a timeout line. - CI: bound kitchen-sink RPC HTTP probes so stalled gateway readiness or response bodies fail and retry instead of wedging the walker. - CI: bound Telegram user Crabbox proof Bot API calls so stalled Telegram responses fail instead of wedging credential and desktop proof cleanup. - CI: bound MCP channel stdio client initialization so Docker channel proof fails and closes the bridge transport instead of waiting for the outer job timeout. - CI: keep `OPENCLAW_TESTBOX=1 pnpm check:changed` delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command. - CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged `git fetch`. - CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped `openclaw` child processes cannot wedge the scheduled install smoke. - iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including the wildcard `/Users/*/Library/Messages/Attachments` root) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Literal `localRoots` stays workspace-scoped. Fixes [#30170](https://github.com/openclaw/openclaw/issues/30170). ([#86569](https://github.com/openclaw/openclaw/issues/86569)) - QQ Bot: respect `OPENCLAW_HOME` for outbound media path resolution so `<qqmedia>` sends no longer silently fail when `HOME` and `OPENCLAW_HOME` differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes [#83562](https://github.com/openclaw/openclaw/issues/83562). Thanks [@sliverp](https://github.com/sliverp). - Update: report the primary malformed `openclaw.extensions` payload error without adding a duplicate missing-main diagnostic. ([#86596](https://github.com/openclaw/openclaw/issues/86596)) Thanks [@ferminquant](https://github.com/ferminquant). - Control UI: keep host-local Markdown file paths inert while preserving app-relative links. ([#86620](https://github.com/openclaw/openclaw/issues/86620)) Thanks [@BryanTegomoh](https://github.com/BryanTegomoh). - Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. ([#86575](https://github.com/openclaw/openclaw/issues/86575)) Thanks [@ferminquant](https://github.com/ferminquant). - IRC: store inbound channel routes with the canonical `channel:#name` target and join transient channel sends before writing. ([#85906](https://github.com/openclaw/openclaw/issues/85906)) Thanks [@Kailigithub](https://github.com/Kailigithub). - Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident `$0` total. ([#85882](https://github.com/openclaw/openclaw/issues/85882)) Thanks [@MichaelZelbel](https://github.com/MichaelZelbel). - Agents/Codex: honor yolo app-server approval policy only for the full `never` plus `danger-full-access` case. ([#85909](https://github.com/openclaw/openclaw/issues/85909)) Thanks [@earlvanze](https://github.com/earlvanze). - Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. ([#82947](https://github.com/openclaw/openclaw/issues/82947)) Thanks [@SebTardif](https://github.com/SebTardif). - Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. ([#80059](https://github.com/openclaw/openclaw/issues/80059)) Thanks [@pavelzak](https://github.com/pavelzak). - Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. ([#85934](https://github.com/openclaw/openclaw/issues/85934)) Thanks [@SebTardif](https://github.com/SebTardif). - Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. ([#86046](https://github.com/openclaw/openclaw/issues/86046)) Thanks [@SebTardif](https://github.com/SebTardif). - Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct `discord.com` connections before opening the WebSocket. Fixes [#80227](https://github.com/openclaw/openclaw/issues/80227). Thanks [@Clivilwalker](https://github.com/Clivilwalker). - Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. ([#84812](https://github.com/openclaw/openclaw/issues/84812)) Thanks [@marchpure](https://github.com/marchpure). - Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. ([#86501](https://github.com/openclaw/openclaw/issues/86501)) Thanks [@tianxiaochannel-oss88](https://github.com/tianxiaochannel-oss88). - Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. ([#86529](https://github.com/openclaw/openclaw/issues/86529)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Gateway: emit plugin `session_end`/`session_start` hooks when `agent.send` rotates or replaces a session id, keeping hook lifecycle state aligned with `sessions.changed` notifications. Fixes [#83507](https://github.com/openclaw/openclaw/issues/83507). ([#85875](https://github.com/openclaw/openclaw/issues/85875)) Thanks [@brokemac79](https://github.com/brokemac79). - OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes [#72373](https://github.com/openclaw/openclaw/issues/72373). Thanks [@brokemac79](https://github.com/brokemac79). - Google: stop normalizing `gemini-3.1-flash-lite` to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes [#86151](https://github.com/openclaw/openclaw/issues/86151). ([#86240](https://github.com/openclaw/openclaw/issues/86240)) Thanks [@SebTardif](https://github.com/SebTardif). - Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try `nodejs-current`, and report Alpine version guidance when repositories only provide older Node packages. - Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes [#80184](https://github.com/openclaw/openclaw/issues/80184). ([#86570](https://github.com/openclaw/openclaw/issues/86570)) Thanks [@brokemac79](https://github.com/brokemac79). - Agents/media: send direct fallback for generated media still missing after an active requester wake fails. ([#85489](https://github.com/openclaw/openclaw/issues/85489)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. ([#70473](https://github.com/openclaw/openclaw/issues/70473)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. ([#85542](https://github.com/openclaw/openclaw/issues/85542)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents/Codex: allow Codex app-server runs to bootstrap from `CODEX_API_KEY` or `OPENAI_API_KEY` when no Codex auth profile is configured. - Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. ([#86408](https://github.com/openclaw/openclaw/issues/86408)) Thanks [@funmerlin](https://github.com/funmerlin) and [@VACInc](https://github.com/VACInc). - Agent transcript: include OpenClaw agent session logs when finding local transcript candidates. - Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute `time` paths so RSS probes can run Node and pnpm on fresh macOS runners. - Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage. - TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster. - Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale `sessions.json.*.tmp` sidecars. Fixes [#56827](https://github.com/openclaw/openclaw/issues/56827). Thanks [@openperf](https://github.com/openperf). - Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs. - Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn. - Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace. - Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes [#86518](https://github.com/openclaw/openclaw/issues/86518). ([#86533](https://github.com/openclaw/openclaw/issues/86533)) Thanks [@liaoyl830](https://github.com/liaoyl830). - Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume. - Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates. - Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run `ENOENT` failures. Fixes [#82928](https://github.com/openclaw/openclaw/issues/82928). Thanks [@galiniliev](https://github.com/galiniliev). - Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. ([#86487](https://github.com/openclaw/openclaw/issues/86487)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session. - Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated. - Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw. - Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. ([#86177](https://github.com/openclaw/openclaw/issues/86177)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work. - Kilo Gateway: send string `stop` sequences as arrays so Kilo accepts OpenAI-compatible chat completions. ([#86461](https://github.com/openclaw/openclaw/issues/86461)) Thanks [@SebTardif](https://github.com/SebTardif). - Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated. - Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. ([#86037](https://github.com/openclaw/openclaw/issues/86037)) - Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind `SessionWriteLockTimeoutError`. Fixes [#86014](https://github.com/openclaw/openclaw/issues/86014). Thanks [@openperf](https://github.com/openperf). - Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error. - Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. ([#86327](https://github.com/openclaw/openclaw/issues/86327)) Thanks [@abnershang](https://github.com/abnershang). - Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. ([#84409](https://github.com/openclaw/openclaw/issues/84409)) Thanks [@samzong](https://github.com/samzong). - Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. ([#85733](https://github.com/openclaw/openclaw/issues/85733)) - Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. ([#85348](https://github.com/openclaw/openclaw/issues/85348)) Thanks [@osolmaz](https://github.com/osolmaz). - Gateway: clear the runtime config snapshot before `SIGUSR1` in-process restarts so config changes survive the next gateway loop. ([#86388](https://github.com/openclaw/openclaw/issues/86388)) Thanks [@XuZehan-iCenter](https://github.com/XuZehan-iCenter). - Models: show OAuth delegation markers as configured `models.json` auth while keeping runtime route usability checks strict. ([#86378](https://github.com/openclaw/openclaw/issues/86378)) Thanks [@rohitjavvadi](https://github.com/rohitjavvadi). - Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. ([#86313](https://github.com/openclaw/openclaw/issues/86313)) Thanks [@ferminquant](https://github.com/ferminquant). - Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes [#84922](https://github.com/openclaw/openclaw/issues/84922). ([#86415](https://github.com/openclaw/openclaw/issues/86415)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. ([#86260](https://github.com/openclaw/openclaw/issues/86260)) Thanks [@stevenepalmer](https://github.com/stevenepalmer). - Security/Audit: flag webhook `hooks.token` reuse of active Gateway password auth in `openclaw security audit` while keeping password-mode startup compatibility. ([#84338](https://github.com/openclaw/openclaw/issues/84338)) Thanks [@coygeek](https://github.com/coygeek). - QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes [#85267](https://github.com/openclaw/openclaw/issues/85267). ([#85271](https://github.com/openclaw/openclaw/issues/85271)) Thanks [@SymbolStar](https://github.com/SymbolStar). - Agents/heartbeat: stop heartbeat turns after the first valid `heartbeat_respond` so repeated response loops do not burn tokens. ([#86357](https://github.com/openclaw/openclaw/issues/86357)) Thanks [@udaymanish6](https://github.com/udaymanish6). - Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention. - Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. ([#86302](https://github.com/openclaw/openclaw/issues/86302)) Thanks [@SebTardif](https://github.com/SebTardif). - Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. ([#85704](https://github.com/openclaw/openclaw/issues/85704)) Thanks [@yaaboo-gif](https://github.com/yaaboo-gif). - Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. ([#86299](https://github.com/openclaw/openclaw/issues/86299)) Thanks [@SebTardif](https://github.com/SebTardif). - Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. ([#86318](https://github.com/openclaw/openclaw/issues/86318)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Cron: accept leading-plus relative durations such as `+5m` for one-shot `--at` schedules. ([#86341](https://github.com/openclaw/openclaw/issues/86341)) Thanks [@mushuiyu886](https://github.com/mushuiyu886). - Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. ([#85933](https://github.com/openclaw/openclaw/issues/85933)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily. - QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path. - Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run `pnpm check:changed` from the intended diff. - xAI/LM Studio: avoid buffering ordinary bracketed or `final` prose until stream completion while watching for plain-text tool-call fallbacks. - Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes [#86102](https://github.com/openclaw/openclaw/issues/86102). ([#86384](https://github.com/openclaw/openclaw/issues/86384)) Thanks [@1052326311](https://github.com/1052326311). - Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. ([#86238](https://github.com/openclaw/openclaw/issues/86238)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. ([#86571](https://github.com/openclaw/openclaw/issues/86571)) Thanks [@joshavant](https://github.com/joshavant). - Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs. - Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`. - Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs. - Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget. - QA-Lab: make the synthetic OpenAI provider honor generic `reply exactly:` directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose. - Gateway: abort active `agent` RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts. - Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted. - Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`. - Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching. - Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof. - Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. ([#84749](https://github.com/openclaw/openclaw/issues/84749)) Thanks [@TeodoroRodrigo](https://github.com/TeodoroRodrigo). - Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes [#85639](https://github.com/openclaw/openclaw/issues/85639). Thanks [@openperf](https://github.com/openperf). - WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes [#86347](https://github.com/openclaw/openclaw/issues/86347). Thanks [@shakkernerd](https://github.com/shakkernerd). - Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes. - Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes. - Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import. - Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. ([#81153](https://github.com/openclaw/openclaw/issues/81153)) Thanks [@ai-hpc](https://github.com/ai-hpc). - xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. ([#86222](https://github.com/openclaw/openclaw/issues/86222)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - CLI: suppress benign self-update version-skew warnings during package post-update finalization. - Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or `n/a` results. - Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned. - Docker: restore writable `~/.config` in runtime images. Fixes [#85968](https://github.com/openclaw/openclaw/issues/85968). Thanks [@hkoessler](https://github.com/hkoessler) and [@Bartok9](https://github.com/Bartok9). - Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph. - Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings. - Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior. - Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. ([#86287](https://github.com/openclaw/openclaw/issues/86287)) Thanks [@ferminquant](https://github.com/ferminquant). - Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active. - Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs. - Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on `control_request`, and document that OpenClaw exec policy is authoritative. Fixes [#80819](https://github.com/openclaw/openclaw/issues/80819). ([#86330](https://github.com/openclaw/openclaw/issues/86330), from [#81971](https://github.com/openclaw/openclaw/issues/81971)) Thanks [@guthirry](https://github.com/guthirry) and [@sallyom](https://github.com/sallyom). - Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude `--permission-mode` for managed live sessions. ([#86557](https://github.com/openclaw/openclaw/issues/86557)) Thanks [@sallyom](https://github.com/sallyom). - Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics. - Codex: log when implicit app-server `never` approvals are promoted for OpenClaw tool policy, including whether the trigger was a `before_tool_call` hook or trusted tool policy. - Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider. Thanks [@amknight](https://github.com/amknight). - Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. ([#83971](https://github.com/openclaw/openclaw/issues/83971)) Thanks [@damianFelixPago](https://github.com/damianFelixPago). - Telegram: route normal `[telegram][diag]` polling diagnostics through `runtime.log` while keeping non-diag warnings and persistence failures on `runtime.error`, so healthy polling startup no longer looks like an error. Fixes [#82957](https://github.com/openclaw/openclaw/issues/82957). ([#82958](https://github.com/openclaw/openclaw/issues/82958)) Thanks [@galiniliev](https://github.com/galiniliev). - Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. ([#86286](https://github.com/openclaw/openclaw/issues/86286)) Thanks [@jason-allen-oneal](https://github.com/jason-allen-oneal). - Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. ([#85690](https://github.com/openclaw/openclaw/issues/85690)) Thanks [@ngutman](https://github.com/ngutman). - Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. ([#86134](https://github.com/openclaw/openclaw/issues/86134)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account that point at the same local Messages source, so the gateway no longer spawns two `imsg rpc` processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and `openclaw doctor` flags the redundant account with a rebinding hint. Fixes [#65141](https://github.com/openclaw/openclaw/issues/65141). ([#86705](https://github.com/openclaw/openclaw/issues/86705)) Thanks [@swang430](https://github.com/swang430). </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/682

* fix(macos): align ask always approval actions * fix(macos): harden approval prompt decisions * fix(ui): satisfy approval action lint * fix(infra): settle jsonl sockets on close * fix(ui): explain unavailable durable approvals * test(macos): document legacy approval fallback

Copilot AI review requested due to automatic review settings May 25, 2026 06:52

openclaw-barnacle Bot added app: macos App: macos size: S maintainer Maintainer-authored PR labels May 25, 2026

Copilot started reviewing on behalf of jesse-merhi May 25, 2026 06:53 View session

Copilot AI reviewed May 25, 2026

View reviewed changes

jesse-merhi mentioned this pull request May 25, 2026

feat(exec): add normalized auto mode #86367

Closed

jesse-merhi closed this May 25, 2026

jesse-merhi reopened this May 25, 2026

jesse-merhi self-assigned this May 25, 2026

clawsweeper Bot added rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. and removed rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. labels May 25, 2026

clawsweeper Bot mentioned this pull request May 25, 2026

feat(exec): add normalized auto mode #70543

Merged

jesse-merhi force-pushed the jm/fix-macos-ask-always-approval branch from fc8c865 to 59e51c1 Compare May 26, 2026 07:27

openclaw-barnacle Bot added app: web-ui App: web-ui size: M and removed size: S labels May 26, 2026

jesse-merhi changed the title ~~fix(macos): hide durable exec approval for ask always~~ fix(exec): hide unavailable durable approval actions May 26, 2026

jesse-merhi force-pushed the jm/fix-macos-ask-always-approval branch from 59e51c1 to 4168b13 Compare May 26, 2026 13:05

clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. merge-risk: 🚨 security-boundary 🚨 May affect sandboxing, authorization, credentials, or sensitive data. labels May 26, 2026

jesse-merhi force-pushed the jm/fix-macos-ask-always-approval branch from 4168b13 to 8cc1990 Compare May 26, 2026 13:21

clawsweeper Bot removed the rating: 🦞 diamond lobster Very strong PR readiness with only minor maintainer review expected. label May 26, 2026

clawsweeper Bot added the rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. label May 26, 2026

kevinslin reviewed May 27, 2026

View reviewed changes

Comment thread ui/src/ui/views/exec-approval.ts

openclaw-barnacle Bot added size: L and removed size: M labels May 27, 2026

jesse-merhi added 6 commits May 27, 2026 13:44

fix(macos): align ask always approval actions

73ef69a

fix(macos): harden approval prompt decisions

b60e7a1

fix(ui): satisfy approval action lint

a53a4de

fix(infra): settle jsonl sockets on close

32530a7

fix(ui): explain unavailable durable approvals

59b80df

test(macos): document legacy approval fallback

1c73fa1

jesse-merhi force-pushed the jm/fix-macos-ask-always-approval branch from 7d9f957 to 1c73fa1 Compare May 27, 2026 03:50

jesse-merhi merged commit 42f0822 into main May 27, 2026
97 of 100 checks passed

jesse-merhi deleted the jm/fix-macos-ask-always-approval branch May 27, 2026 04:58

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(exec): hide unavailable durable approval actions#86359

fix(exec): hide unavailable durable approval actions#86359
jesse-merhi merged 6 commits into
mainfrom
jm/fix-macos-ask-always-approval

jesse-merhi commented May 25, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026

Uh oh!

jesse-merhi commented May 25, 2026

Uh oh!

jesse-merhi commented May 25, 2026

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

jesse-merhi commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Agent Transcript

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 25, 2026

Hatch command

Uh oh!

jesse-merhi commented May 25, 2026

Uh oh!

jesse-merhi commented May 25, 2026

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

jesse-merhi commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading