Propagate ClickClack tool policy through reply dispatch by mmaps · Pull Request #89500 · openclaw/openclaw

mmaps · 2026-06-02T14:46:50Z

Summary

Propagates ClickClack account tool policy through inbound agent reply dispatch
Threads runtime tool restrictions through provider dispatchers, shared reply dispatch, and agent execution

Changes

Adds a runtime toolsAllow handoff on shared inbound dispatch params and exported provider-dispatcher wrappers
Carries the policy through reply options into embedded and CLI agent execution
Adds regression coverage for ClickClack dispatch, provider wrappers, shared dispatch, and embedded agent execution

Real behavior proof

Behavior or issue addressed: ClickClack account-level tool allowlists are carried through the exported provider dispatcher, shared reply dispatch, and agent reply runtime so the account policy remains the effective runtime tool set.
Real environment tested: Local OpenClaw worktree ~/Worktrees/openclaw/openclaw/fix/fix-708 at commit 46a21f0323, Node v22.22.2.
Exact steps or command run after this patch: Ran targeted terminal probes from the PR worktree after the patch: provider wrapper dispatch coverage, shared dispatch to agent execution coverage, and the production embedded-agent tool-policy boundary probe.
Evidence after fix (screenshot, recording, terminal capture, console output, redacted runtime log, linked artifact, or copied live output): Copied console output from the local OpenClaw run:

$ node scripts/run-vitest.mjs run src/auto-reply/reply/provider-dispatcher.test.ts --reporter=verbose
✓ provider dispatcher wrappers > forwards runtime toolsAllow through the buffered wrapper
✓ provider dispatcher wrappers > forwards runtime toolsAllow through the plain wrapper
Test Files  1 passed (1)
Tests  2 passed (2)

$ node scripts/run-vitest.mjs run src/auto-reply/dispatch.test.ts src/auto-reply/reply/agent-runner-execution.test.ts src/auto-reply/reply/provider-dispatcher.test.ts --reporter=verbose
✓ withReplyDispatcher > passes runtime toolsAllow from buffered dispatch into reply resolution
✓ runAgentTurnWithFallback > passes runtime toolsAllow to embedded agent runs
✓ provider dispatcher wrappers > forwards runtime toolsAllow through the buffered wrapper
✓ provider dispatcher wrappers > forwards runtime toolsAllow through the plain wrapper
Test Files  3 passed (3)
Tests  176 passed (176)

$ node --import tsx <production embedded-agent tool-policy boundary>
[proof-708] runtimeToolsAllow=["message"]
[proof-708] availableTools=["message","exec","read","web_search"]
[proof-708] allowedToolsAfterRuntimePolicy=["message"]
[proof-708] bundleMcpRuntimeCreated=false
[proof-708] result=pass

Observed result after fix: The exported provider wrappers preserve ["message"]; shared reply dispatch resolves that value into reply options; embedded agent execution receives it; and the production tool-policy boundary excludes exec, read, and web_search while leaving only message available.
What was not tested: Live ClickClack service delivery and a real model-provider turn were not run locally; those require external service credentials.
Proof limitations or environment constraints: The terminal proof uses focused local dispatch probes plus the production embedded-agent policy boundary rather than an external service account.

Validation

node scripts/run-vitest.mjs run --config test/vitest/vitest.extension-clickclack.config.ts extensions/clickclack/src/inbound.test.ts --reporter=verbose
node scripts/run-vitest.mjs run src/auto-reply/dispatch.test.ts src/auto-reply/reply/agent-runner-execution.test.ts src/auto-reply/reply/provider-dispatcher.test.ts --reporter=verbose
pnpm tsgo:core
pnpm tsgo:test:src
pnpm tsgo:extensions
pnpm tsgo:test:extensions
git diff --check
claude -p "/review 89500" returned approve

Notes

CLI-backed agent runs fail closed when a runtime tool allowlist is requested, because that backend cannot enforce the runtime policy.

clawsweeper · 2026-06-02T14:48:54Z

Codex review: needs maintainer review before merge. Reviewed June 2, 2026, 11:20 AM ET / 15:20 UTC.

Summary
The PR propagates ClickClack account toolsAllow through inbound reply dispatch, provider dispatcher wrappers, shared dispatch options, and agent execution, with focused regression coverage.

PR surface: Source +30, Tests +157. Total +187 across 12 files.

Reproducibility: yes. Current main has ClickClack account toolsAllow config, but the ClickClack inbound call and exported provider wrappers do not forward it into reply dispatch.

Review metrics: 1 noteworthy metric.

Runtime policy handoff: 1 optional toolsAllow handoff added across shared reply dispatch contracts. This field carries account-level security policy through generic dispatch, so dropped callers are security-relevant.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
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

[P1] Existing ClickClack accounts that set toolsAllow and route to a CLI backend will now fail closed instead of running without enforceable runtime policy.
[P1] No live ClickClack service delivery or real provider turn was supplied; the proof is local terminal dispatch coverage plus an embedded-agent policy-boundary probe.

Maintainer options:

Accept stricter fail-closed behavior (recommended)
Merge after maintainers confirm that CLI-backed runs with account toolsAllow should stop rather than run with an unenforced policy.
Require live service proof
Ask for a live ClickClack/provider run only if maintainers want external-service proof beyond the local dispatch and embedded policy-boundary probes.

Next step before merge

No automated repair is needed; maintainers should make the merge call on the security-boundary and fail-closed compatibility impact.

Security
Cleared: No supply-chain or secret-handling concern was found; the diff tightens the intended runtime tool-policy propagation boundary.

Review details

Best possible solution:

Keep the narrow dispatch-layer fix, preserve the fail-closed CLI behavior for unenforceable runtime policy, and merge after maintainers accept the compatibility impact and checks are green.

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

Yes. Current main has ClickClack account toolsAllow config, but the ClickClack inbound call and exported provider wrappers do not forward it into reply dispatch.

Is this the best way to solve the issue?

Yes. The PR repairs the missing handoff at the owning channel, wrapper, shared dispatch, and agent-runner boundaries rather than adding a duplicate policy source.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 6c7644268f59.

Label changes

Label changes:

add merge-risk: 🚨 compatibility: Existing CLI-backed ClickClack accounts with toolsAllow can now fail closed because CLI backends cannot enforce the runtime policy.
add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes copied terminal output from the final head covering provider wrappers, shared dispatch, embedded execution, and a production embedded-agent boundary probe that leaves only message allowed.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (terminal): The PR body includes copied terminal output from the final head covering provider wrappers, shared dispatch, embedded execution, and a production embedded-agent boundary probe that leaves only message allowed.
remove rating: 🧂 unranked krab: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.
remove status: 📣 needs proof: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P1: The PR fixes a security-sensitive path where account tool allowlists could be dropped before agent execution.
merge-risk: 🚨 security-boundary: The diff changes enforcement plumbing for runtime tool policies, where incomplete propagation could expose disallowed tools.
merge-risk: 🚨 compatibility: Existing CLI-backed ClickClack accounts with toolsAllow can now fail closed because CLI backends cannot enforce the runtime policy.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (terminal): The PR body includes copied terminal output from the final head covering provider wrappers, shared dispatch, embedded execution, and a production embedded-agent boundary probe that leaves only message allowed.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes copied terminal output from the final head covering provider wrappers, shared dispatch, embedded execution, and a production embedded-agent boundary probe that leaves only message allowed.

Evidence reviewed

PR surface:

Source +30, Tests +157. Total +187 across 12 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	8	32	2	+30
Tests	4	157	0	+157
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	12	189	2	+187

Acceptance criteria:

[P1] node scripts/run-vitest.mjs run --config test/vitest/vitest.extension-clickclack.config.ts extensions/clickclack/src/inbound.test.ts --reporter=verbose.
[P1] node scripts/run-vitest.mjs run src/auto-reply/dispatch.test.ts src/auto-reply/reply/agent-runner-execution.test.ts src/auto-reply/reply/provider-dispatcher.test.ts --reporter=verbose.
[P1] pnpm tsgo:core.
[P1] pnpm tsgo:test:src.
[P1] pnpm tsgo:extensions.

What I checked:

ClickClack account policy handoff: The PR head passes params.account.toolsAllow into the shared inbound reply dispatch object. (extensions/clickclack/src/inbound.ts:177, 46a21f032302)
Provider wrapper blocker fixed: Both exported provider dispatcher wrappers forward params.toolsAllow into the shared dispatch helpers on the final PR head. (src/auto-reply/reply/provider-dispatcher.ts:21, 46a21f032302)
Shared reply dispatch preserves runtime policy: dispatchInboundMessage merges the runtime toolsAllow into reply options before calling dispatchReplyFromConfig; both buffered and plain helper paths pass the field through. (src/auto-reply/dispatch.ts:473, 46a21f032302)
Embedded agent execution receives policy: The PR head forwards params.opts?.toolsAllow into both CLI and embedded run parameter objects; CLI preparation already rejects runtime allowlists it cannot enforce. (src/auto-reply/reply/agent-runner-execution.ts:2324, 46a21f032302)
Tool filtering boundary: Current main filters constructed embedded-agent tools by runtime allowlist, treats an empty allowlist as no tools, and uses the filtered tool names for context-engine availableTools. (src/agents/embedded-agent-runner/run/attempt-tool-construction-plan.ts:92, 6c7644268f59)
CLI fail-closed contract: Current main rejects toolsAllow during CLI preparation because CLI backends cannot enforce runtime allowlists, and the existing test covers that behavior. (src/agents/cli-runner/prepare.ts:163, 6c7644268f59)

Likely related people:

Bek: Current-main blame ties the central ClickClack inbound dispatch, provider wrapper, shared dispatch, embedded allowlist collection, and CLI fail-closed guard to bce3d5b. (role: introduced adjacent dispatch/runtime surface; confidence: high; commits: bce3d5bf92d5; files: extensions/clickclack/src/inbound.ts, src/auto-reply/reply/provider-dispatcher.ts, src/auto-reply/dispatch.ts)
@andyk-ms: Commit 4d8c07b added the original per-run toolsAllow feature surface for cron agent turns, which is the same runtime allowlist concept this PR now threads through reply dispatch. (role: introduced toolsAllow feature surface; confidence: medium; commits: 4d8c07b97c0b; files: src/agents/pi-embedded-runner/run/attempt.ts, src/agents/pi-embedded-runner/run/params.ts)
Jordan Brant Baker: Commit b4e4f96 repaired a prior dropped optional-parameter forwarding bug for toolsAllow and related embedded-run fields, making this area relevant routing context. (role: adjacent forwarding owner; confidence: medium; commits: b4e4f96fd568; files: src/agents/embedded-agent-runner/run/attempt.ts, src/agents/embedded-agent-runner/run/params.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.

mmaps · 2026-06-02T15:13:18Z

@clawsweeper re-review

clawsweeper · 2026-06-02T15:13:22Z

🦞🧹
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/26829230653
Updated: 2026-06-02T15:21:39.354Z

Propagate ClickClack account-level runtime tool allowlists through inbound reply dispatch so restricted ClickClack accounts keep their tool policy when model/agent replies are generated. This threads `toolsAllow` through shared dispatch, provider wrappers, embedded agent execution, and ACP hook events. ACP-bound sessions now fail closed for restrictive runtime allowlists because ACPX cannot enforce per-turn tool allowlists on reused persistent sessions. Verification: - Live ClickClack E2E on Crabbox AWS `run_6a0472ed7e71`, provider `aws`, id `cbx_dace25addcaa`. - `node scripts/run-vitest.mjs run src/auto-reply/reply/dispatch-acp.test.ts src/plugin-sdk/acp-runtime.test.ts src/auto-reply/reply/dispatch-from-config.reply-dispatch.test.ts src/auto-reply/dispatch.test.ts src/auto-reply/reply/agent-runner-execution.test.ts src/auto-reply/reply/provider-dispatcher.test.ts extensions/clickclack/src/inbound.test.ts --reporter=verbose` - Crabbox changed gate `run_d32af37fb265`, provider `aws`, id `cbx_8236876017c9`: `corepack pnpm check:changed` - Autoreview clean: `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main` Supersedes #89500. Co-authored-by: Michael Appel <mappel@nvidia.com>

steipete · 2026-06-05T15:41:23Z

Landed this via #90405 in commit 797bcd5.

That PR preserves your two ClickClack tool-policy dispatch commits and adds the missing ACP fail-closed path for sessions where restrictive runtime tool policy cannot be enforced. Thanks @mmaps.

Closing this PR as superseded by the landed maintainer branch.

Propagate ClickClack account-level runtime tool allowlists through inbound reply dispatch so restricted ClickClack accounts keep their tool policy when model/agent replies are generated. This threads `toolsAllow` through shared dispatch, provider wrappers, embedded agent execution, and ACP hook events. ACP-bound sessions now fail closed for restrictive runtime allowlists because ACPX cannot enforce per-turn tool allowlists on reused persistent sessions. Verification: - Live ClickClack E2E on Crabbox AWS `run_6a0472ed7e71`, provider `aws`, id `cbx_dace25addcaa`. - `node scripts/run-vitest.mjs run src/auto-reply/reply/dispatch-acp.test.ts src/plugin-sdk/acp-runtime.test.ts src/auto-reply/reply/dispatch-from-config.reply-dispatch.test.ts src/auto-reply/dispatch.test.ts src/auto-reply/reply/agent-runner-execution.test.ts src/auto-reply/reply/provider-dispatcher.test.ts extensions/clickclack/src/inbound.test.ts --reporter=verbose` - Crabbox changed gate `run_d32af37fb265`, provider `aws`, id `cbx_8236876017c9`: `corepack pnpm check:changed` - Autoreview clean: `.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main` Supersedes openclaw#89500. Co-authored-by: Michael Appel <mappel@nvidia.com>

…26.6.5) (#963) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.1` → `2026.6.5` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.5`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202665) [Compare Source](openclaw/openclaw@v2026.6.1...v2026.6.5) ##### Highlights - QQBot now strips model reasoning/thinking scaffolding before native delivery, preventing raw `<thinking>` content from leaking into channel replies. ([#89913](openclaw/openclaw#89913), [#90132](openclaw/openclaw#90132)) Thanks [@openperf](https://github.com/openperf). - MCP tool results now coerce `resource_link`, `resource`, `audio`, malformed image, and future non-text/image blocks at the materialize boundary, preventing Anthropic 400s and poisoned session history after a tool returns richer MCP content. ([#90710](openclaw/openclaw#90710), [#90728](openclaw/openclaw#90728)) Thanks [@RanSHammer](https://github.com/RanSHammer) and [@849261680](https://github.com/849261680). - Anthropic extended-thinking sessions recover after prompt-cache expiry or Gateway restart because stream start events wait for `message_start`, letting pre-generation signature errors trigger the existing recovery retry. ([#90667](openclaw/openclaw#90667), [#90697](openclaw/openclaw#90697)) Thanks [@openperf](https://github.com/openperf). - Parallel is now a bundled `web_search` provider with `PARALLEL_API_KEY` discovery, guarded endpoint handling, cache-safe session ids, onboarding picker support, and docs. ([#85158](openclaw/openclaw#85158)) Thanks [@NormallyGaussian](https://github.com/NormallyGaussian). - Google Vertex ADC users get static catalog rows and runtime model resolution again, while single-provider cooldown recovery and memory adapter status checks are more reliable. ([#90506](openclaw/openclaw#90506), [#90609](openclaw/openclaw#90609), [#90717](openclaw/openclaw#90717), [#90816](openclaw/openclaw#90816)) Thanks [@849261680](https://github.com/849261680). - Matrix can preflight voice notes before mention gating, preserve thread reads/replies through Matrix relations pagination, and carry QA coverage for voice and thread flows. ([#78016](openclaw/openclaw#78016), [#90415](openclaw/openclaw#90415)) - Auth and plugin install state is more durable: auth profiles now live in SQLite, official npm plugin install records keep their trusted pins, and prerelease fallback integrity checks avoid carrying stale integrity forward. ([#89102](openclaw/openclaw#89102), [#88585](openclaw/openclaw#88585)) - macOS node mode no longer silently self-reconnects away from a healthy direct Gateway session, reducing unexpected companion app session churn. ([#90668](openclaw/openclaw#90668), [#90815](openclaw/openclaw#90815)) Thanks [@vrurg](https://github.com/vrurg). - Upgrade and service paths are safer: cron legacy JSON stores migrate during doctor preflight, service env placeholders no longer mask state-dir secrets, WhatsApp startup waits are bounded, and disabled WhatsApp accounts tear down on config reload. ([#90072](openclaw/openclaw#90072), [#90208](openclaw/openclaw#90208), [#90277](openclaw/openclaw#90277), [#90488](openclaw/openclaw#90488), [#90486](openclaw/openclaw#90486), [#87951](openclaw/openclaw#87951), [#87965](openclaw/openclaw#87965)) Thanks [@MonkeyLeeT](https://github.com/MonkeyLeeT), [@sallyom](https://github.com/sallyom), [@mcaxtr](https://github.com/mcaxtr), and [@MukundaKatta](https://github.com/MukundaKatta). ##### Changes - Search/providers: add the Parallel bundled web-search plugin, live provider tests, registration contracts, onboarding/docs wiring, and guarded `api.parallel.ai/v1/search` support. ([#85158](openclaw/openclaw#85158)) Thanks [@NormallyGaussian](https://github.com/NormallyGaussian). - Matrix/channels: add voice-message preflight and thread-aware read/reply behavior, including Matrix QA scenario wiring and docs for voice-message behavior. ([#78016](openclaw/openclaw#78016), [#90415](openclaw/openclaw#90415)) - Skills/ClawHub: install ClawHub skills backed by GitHub repositories through the resolved install API, download the pinned GitHub commit, keep install-policy checks, and report install telemetry after success. ([#90478](openclaw/openclaw#90478)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - Google Chat/channels: add native approval card actions and click handling so Google Chat approvals use platform-native cards instead of generic message flow. - Mobile: Android provider/model screens now surface expiring, unavailable, unresolved, and attention states more clearly, while iOS settings and Talk tabs keep diagnostics, gateway rows, attachment labels, and unavailable Talk controls reachable. - Memory: QMD search can use the new rerank toggle, and memory adapter status uses the resolved default model identity when checking plain status. ([#61834](openclaw/openclaw#61834)) - Docs/tooling: add Parallel search docs, refresh weather-skill guidance toward `web_fetch`, clarify legacy `openai-codex` auth, document release/test helper scripts, and tighten changed-test routing docs for CI/debugging work. ([#90028](openclaw/openclaw#90028), [#90250](openclaw/openclaw#90250)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Release/process: switch release trains to `YYYY.M.PATCH` monthly patch numbering, keep pre-transition tags compatible, and pin the June 2026 floor at `2026.6.5` after the published beta. - Platform maintenance: refresh Android, Swift/macOS, Docker, CodeQL, Buildx, Docker build/push, and Codex Action dependencies for this release train. ([#74980](openclaw/openclaw#74980), [#81757](openclaw/openclaw#81757), [#86481](openclaw/openclaw#86481), [#86483](openclaw/openclaw#86483), [#90601](openclaw/openclaw#90601)) - QQBot: add `/bot-group-allways on|off` slash command (with named-account and default-account support) to toggle whether group messages require an `@mention` before the bot replies, and clear the runtime config snapshot after the write so the new account-level `defaultRequireMention` takes effect immediately without restart. ([#91423](openclaw/openclaw#91423)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh). ##### Fixes - Channel content boundaries: QQBot now strips reasoning/thinking tags before sending, preserving final answers while hiding internal model narration from users. ([#89913](openclaw/openclaw#89913), [#90132](openclaw/openclaw#90132)) Thanks [@openperf](https://github.com/openperf). - Agents/MCP/providers: coerce non-text/image MCP tool-result blocks before they reach provider converters, preserving valid images and turning richer MCP content into text instead of malformed image blocks. ([#90710](openclaw/openclaw#90710), [#90728](openclaw/openclaw#90728)) Thanks [@RanSHammer](https://github.com/RanSHammer) and [@849261680](https://github.com/849261680). - Anthropic/Codex/ACP/agent recovery: defer Anthropic stream start events until `message_start`, strip stale compaction thinking signatures before Anthropic replay, detect unsigned thinking-only stalls, refresh prompt fences after compaction writes, reject empty completion handoffs, preserve parent streaming-off overrides/shared progress commentary, forward heartbeat metadata to context-engine hooks, and cover Codex session/thread migration edge cases. ([#90667](openclaw/openclaw#90667), [#90697](openclaw/openclaw#90697), [#90163](openclaw/openclaw#90163), [#90108](openclaw/openclaw#90108), [#89874](openclaw/openclaw#89874), [#89505](openclaw/openclaw#89505), [#90632](openclaw/openclaw#90632), [#89302](openclaw/openclaw#89302), [#90729](openclaw/openclaw#90729), [#90317](openclaw/openclaw#90317), [#90319](openclaw/openclaw#90319)) Thanks [@openperf](https://github.com/openperf), [@100yenadmin](https://github.com/100yenadmin), and [@ooiuuii](https://github.com/ooiuuii). - Provider/model resolution: preserve Google Vertex ADC auth markers in generated catalogs, re-probe a single-provider primary after cooldown, share Codex model visibility, fail closed for unknown model auth, preserve Codex alias availability, keep unresolved profile refs unknown, and avoid resolving auth while listing models. ([#90506](openclaw/openclaw#90506), [#90609](openclaw/openclaw#90609), [#90717](openclaw/openclaw#90717), [#90702](openclaw/openclaw#90702)) Thanks [@849261680](https://github.com/849261680). - Gateway/macOS/mobile: avoid duplicate Gateway probe warnings by identity, rate-limit node pairing requests while preserving paired-node reconnects, keep macOS node mode on a healthy direct Gateway session, keep iOS diagnostics and gateway rows reachable, and avoid Linux ARM Gradle resource tasks during Android builds. ([#85791](openclaw/openclaw#85791), [#90147](openclaw/openclaw#90147), [#90668](openclaw/openclaw#90668), [#90815](openclaw/openclaw#90815)) Thanks [@giodl73-repo](https://github.com/giodl73-repo) and [@vrurg](https://github.com/vrurg). - TUI/chat/Workboard/auto-reply: optimistic user messages stay stable across stale history reloads, runId reassignment, and abort windows instead of disappearing, jumping, or lingering as ghost rows; Workboard stale lifecycle bulk updates no longer overwrite newer status/provenance; message-tool sends now count as delivery. ([#86205](openclaw/openclaw#86205), [#89600](openclaw/openclaw#89600), [#88592](openclaw/openclaw#88592), [#90123](openclaw/openclaw#90123)) Thanks [@RomneyDa](https://github.com/RomneyDa). - Cron/update/service env: doctor config preflight now migrates legacy cron JSON stores into SQLite before runtime reads, service env planning skips unresolved placeholders that would mask state-dir `.env` values, and session transcript rewrites keep registry markers/discriminants consistent. ([#90072](openclaw/openclaw#90072), [#90208](openclaw/openclaw#90208), [#90277](openclaw/openclaw#90277), [#90488](openclaw/openclaw#90488)) Thanks [@MonkeyLeeT](https://github.com/MonkeyLeeT) and [@sallyom](https://github.com/sallyom). - Security/config/tooling: guard MCP HTTP redirects, protect global agent config defaults, and keep release/test/tooling proof failures bounded and explicit. ([#89732](openclaw/openclaw#89732), [#90145](openclaw/openclaw#90145)) - Channels: WhatsApp restarts when per-account config changes, bounds background startup waits, closes failed sockets, and preserves reconnect behavior; Mattermost slash commands keep their state on `globalThis`; Feishu streaming cards preserve full merged content; voice-call tracks Twilio streams after connect; ClickClack reply tools respect `toolsAllow`. ([#87951](openclaw/openclaw#87951), [#87965](openclaw/openclaw#87965), [#90486](openclaw/openclaw#90486), [#68113](openclaw/openclaw#68113), [#90534](openclaw/openclaw#90534), [#90181](openclaw/openclaw#90181), [#90607](openclaw/openclaw#90607), [#89500](openclaw/openclaw#89500)) Thanks [@MukundaKatta](https://github.com/MukundaKatta), [@mcaxtr](https://github.com/mcaxtr), [@infoanton](https://github.com/infoanton), [@mushuiyu886](https://github.com/mushuiyu886), and [@sahibzada-allahyar](https://github.com/sahibzada-allahyar). - Feishu: retry transient send rate-limit errors (HTTP 429, per-chat code 230020, tenant-level code 11232) with linear backoff, including SDK responses that fulfill with rate-limit bodies instead of throwing, and route streaming-card sends through the retry wrapper. ([#89659](openclaw/openclaw#89659)) Thanks [@ladygege](https://github.com/ladygege). - Release/CI/E2E: main CI guard drift, PR merge diff scoping, live Docker credential staging, base-image qualification, installer Docker classification, Playwright dependency install recovery, API-key auth for Codex live Docker lanes, Parallels option terminators, and JSON-mode progress handling are tighter so release proof fails cleaner. ([#90532](openclaw/openclaw#90532), [#90287](openclaw/openclaw#90287), [#90058](openclaw/openclaw#90058)) Thanks [@RomneyDa](https://github.com/RomneyDa), [@hxy91819](https://github.com/hxy91819), and [@mrunalp](https://github.com/mrunalp). - Release/CI/E2E: Docker E2E and live Docker harness runs now apply default memory, CPU, and process ceilings while preserving explicit per-lane overrides. - Release/CI/E2E: plugin lifecycle matrix resource sampling now fails phases that exceed RSS, wall-clock, or CPU ceilings instead of only logging the measurements. - Release/CI/E2E: Codex npm plugin live assertions now cap transcript discovery and diagnostic log reads so failure proof stays bounded. - Tests/state isolation: QA Lab valid-tool-call metrics now require runtime tool-call evidence when runtime parity data is available instead of counting tool-backed scenario pass status alone. - Tests/state isolation: QA Lab runtime parity now fails planned-only tool-call rows without matching tool results instead of treating matching mock plans as real tool evidence. - Tests/state isolation: provider, media, auth, cron, task, session, sandbox, Gateway, and Codex timeout fixtures now scope more home/state/env data per test, reducing cross-test leakage and making release validation failures less noisy. ([#90027](openclaw/openclaw#90027), [#89974](openclaw/openclaw#89974)) </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/963

Propagate ClickClack tool policy through reply dispatch

8a5cc59

openclaw-barnacle Bot added size: S triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 2, 2026

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 2, 2026

Forward runtime tool policy through provider dispatchers

46a21f0

steipete mentioned this pull request Jun 4, 2026

Fix ClickClack toolsAllow reply dispatch #90405

Merged

steipete closed this Jun 5, 2026

eleqtrizit self-requested a review June 9, 2026 19:27

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Propagate ClickClack tool policy through reply dispatch#89500

Propagate ClickClack tool policy through reply dispatch#89500
mmaps wants to merge 2 commits into
openclaw:mainfrom
mmaps:clickclack-tool-policy-dispatch

mmaps commented Jun 2, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

Uh oh!

mmaps commented Jun 2, 2026

Uh oh!

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

Uh oh!

steipete commented Jun 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

mmaps commented Jun 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Changes

Real behavior proof

Validation

Notes

Uh oh!

clawsweeper Bot commented Jun 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

mmaps commented Jun 2, 2026

Uh oh!

clawsweeper Bot commented Jun 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

steipete commented Jun 5, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

mmaps commented Jun 2, 2026 •

edited

Loading

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading

clawsweeper Bot commented Jun 2, 2026 •

edited

Loading