fix(gateway): skip deleted-agent guard for ACP harness session keys#91219
Conversation
|
Codex review: needs maintainer review before merge. Reviewed June 7, 2026, 2:21 PM ET / 18:21 UTC. Summary PR surface: Source +4, Tests +79. Total +83 across 4 files. Reproducibility: yes. source-reproducible: current main parses agent:claude:acp:* as agent claude and the resolver/send paths call the deleted-agent helper. I did not run local tests because this review was required to keep the checkout read-only. Review metrics: 1 noteworthy metric.
Merge readiness Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch. Rank-up moves:
Risk before merge
Maintainer options:
Next step before merge
Security Review detailsBest possible solution: Merge the shared helper exemption after maintainer security-boundary confirmation and required CI, preserving deleted-agent rejection for non-ACP session keys. Do we have a high-confidence way to reproduce the issue? Yes, source-reproducible: current main parses agent:claude:acp:* as agent claude and the resolver/send paths call the deleted-agent helper. I did not run local tests because this review was required to keep the checkout read-only. Is this the best way to solve the issue? Yes, this appears to be the best narrow fix: the shared helper is the common owner boundary for sessions.resolve, sessions.send, sessions.steer, and chat.send. A resolver-only bypass would be too narrow, while changing parseAgentSessionKey would affect unrelated agent-key semantics. AGENTS.md: found and applied where relevant. Codex review notes: model gpt-5.5, reasoning high; reviewed against 0c33f4e0786e. Label changesLabel changes:
Label justifications:
Evidence reviewedPR surface: Source +4, Tests +79. Total +83 across 4 files. View PR surface stats
What I checked:
Likely related people:
What the crustacean ranks mean
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 re-review |
|
🦞🧹 I asked ClawSweeper to review this item again. Re-review progress:
|
fed9faa to
ad8b7fd
Compare
ACP session keys use agent:<harnessId>:acp:<uuid>, so sessions_send and sessions.resolve must not treat harness ids as agents.list owners.
ad8b7fd to
c09c475
Compare
|
Merged with rebase. What landed:
Verification:
Thanks @scotthuang. |
…26.6.6) (#1040) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.5` → `2026.6.6` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.6`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202666) [Compare Source](openclaw/openclaw@v2026.6.5...v2026.6.6) ##### Highlights - Security boundaries are substantially tighter across transcripts, sandbox binds, host environment inheritance, MCP stdio, Codex HTTP access, native search policy, elevated sender checks, deleted-agent ACP bypasses, loopback tools, Discord moderation, and Teams group actions; exec approvals now fail closed on timeout. ([#​91529](openclaw/openclaw#91529), [#​91618](openclaw/openclaw#91618), [#​91615](openclaw/openclaw#91615), [#​91619](openclaw/openclaw#91619), [#​91741](openclaw/openclaw#91741), [#​91745](openclaw/openclaw#91745), [#​91746](openclaw/openclaw#91746), [#​91748](openclaw/openclaw#91748), [#​91749](openclaw/openclaw#91749), [#​91750](openclaw/openclaw#91750), [#​91751](openclaw/openclaw#91751), [#​91752](openclaw/openclaw#91752), [#​91763](openclaw/openclaw#91763), [#​89938](openclaw/openclaw#89938)) Thanks [@​joshavant](https://github.com/joshavant), [@​pgondhi987](https://github.com/pgondhi987), [@​mmaps](https://github.com/mmaps), [@​eleqtrizit](https://github.com/eleqtrizit), [@​shakkernerd](https://github.com/shakkernerd), and [@​drobison00](https://github.com/drobison00). - Telegram delivery is safer and more coherent: account-scoped topics route to the right agent, streamed text survives tool calls, `/compact` works on generic ingress, callback handling uses concrete APIs, draft chunking is shared, durable dispatch dedupe moved into the SDK, and unauthorized DM text stays out of cache and prompt context. ([#​91189](openclaw/openclaw#91189), [#​88682](openclaw/openclaw#88682), [#​89588](openclaw/openclaw#89588), [#​90212](openclaw/openclaw#90212), [#​91876](openclaw/openclaw#91876), [#​91874](openclaw/openclaw#91874), [#​91904](openclaw/openclaw#91904), [#​91478](openclaw/openclaw#91478), [#​91915](openclaw/openclaw#91915)) Thanks [@​codysai001](https://github.com/codysai001), [@​alexzhu0](https://github.com/alexzhu0), [@​joelnishanth](https://github.com/joelnishanth), [@​snowzlm](https://github.com/snowzlm), [@​obviyus](https://github.com/obviyus), and [@​sallyom](https://github.com/sallyom). - iMessage recovery and delivery now cover always-on inbound restart, durable echo markers, block streaming, idle approval discovery, hardened outbound transport, and actionable inbound startup diagnostics. ([#​91335](openclaw/openclaw#91335), [#​91449](openclaw/openclaw#91449), [#​88969](openclaw/openclaw#88969), [#​88530](openclaw/openclaw#88530), [#​91783](openclaw/openclaw#91783), [#​91785](openclaw/openclaw#91785)) Thanks [@​omarshahine](https://github.com/omarshahine), [@​jmissig](https://github.com/jmissig), and [@​colmbrogan](https://github.com/colmbrogan). - Browser and MCP connectivity gained existing-session CDP support, discovered WebSocket validation, default-profile `cdpUrl` handling, safer browser-output boundaries, Streamable HTTP loopback transport, corrected OAuth/SSE authorization handling, and broader schema compatibility. ([#​91422](openclaw/openclaw#91422), [#​89851](openclaw/openclaw#89851), [#​91736](openclaw/openclaw#91736), [#​91747](openclaw/openclaw#91747), [#​91451](openclaw/openclaw#91451), [#​80143](openclaw/openclaw#80143)) Thanks [@​pgondhi987](https://github.com/pgondhi987), [@​anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia), [@​lifuyue](https://github.com/lifuyue), [@​eleqtrizit](https://github.com/eleqtrizit), [@​LiuwqGit](https://github.com/LiuwqGit), and [@​HemantSudarshan](https://github.com/HemantSudarshan). - Control UI startup and first-reply latency are lower through cached model metadata, removal of the startup catalog wait, lazy slash-command loading, and first-event tracing with slow-reply diagnostics. ([#​91531](openclaw/openclaw#91531), [#​91538](openclaw/openclaw#91538), [#​91568](openclaw/openclaw#91568), [#​91583](openclaw/openclaw#91583), [#​91598](openclaw/openclaw#91598)) - Provider support expands with OpenRouter OAuth onboarding and Claude Fable 5 adaptive thinking, while Codex sessions keep correct compaction ownership, local models skip guardian review, dynamic tool progress normalizes cleanly, and Gemma 4 reasoning replay is preserved. ([#​91830](openclaw/openclaw#91830), [#​91882](openclaw/openclaw#91882), [#​91590](openclaw/openclaw#91590), [#​88630](openclaw/openclaw#88630), [#​88768](openclaw/openclaw#88768), [#​91696](openclaw/openclaw#91696)) Thanks [@​Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@​joshavant](https://github.com/joshavant), [@​bdjben](https://github.com/bdjben), and [@​Coder-Wangyankun](https://github.com/Coder-Wangyankun). ##### Changes - CLI progress: emit Claude CLI commentary progress events and bridge inter-tool commentary into channel progress without exposing internal protocol scaffolding. ([#​89834](openclaw/openclaw#89834), [#​90883](openclaw/openclaw#90883)) Thanks [@​anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia). - Observability: allow trusted diagnostics channels to capture tool input/output content, add first-assistant-event traces, and warn on slow initial replies. ([#​91256](openclaw/openclaw#91256), [#​91568](openclaw/openclaw#91568), [#​91583](openclaw/openclaw#91583)) Thanks [@​amknight](https://github.com/amknight). - Plugins/ClawHub: dogfood reusable package publishing, let dry runs skip publish approval, allow declared installed trusted hooks, report managed plugin version drift, and warn instead of failing on retired Skill Workshop configuration. ([#​91574](openclaw/openclaw#91574), [#​91591](openclaw/openclaw#91591), [#​90004](openclaw/openclaw#90004), [#​90927](openclaw/openclaw#90927), [#​90838](openclaw/openclaw#90838)) Thanks [@​Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@​brokemac79](https://github.com/brokemac79), and [@​lonexreb](https://github.com/lonexreb). - Memory/providers: move the local llama.cpp runtime into its provider plugin, batch embeddings across files, persist the agent model catalog cache, and keep QMD JSON search one-shot while filtering stale REM recall previews. ([#​91324](openclaw/openclaw#91324), [#​89138](openclaw/openclaw#89138), [#​90457](openclaw/openclaw#90457), [#​91837](openclaw/openclaw#91837), [#​91851](openclaw/openclaw#91851)) Thanks [@​osolmaz](https://github.com/osolmaz), [@​mushuiyu886](https://github.com/mushuiyu886), [@​ai-hpc](https://github.com/ai-hpc), and [@​TurboTheTurtle](https://github.com/TurboTheTurtle). - Channels/mobile: add the QQBot group mention toggle, improve iPad and iPhone control surfaces, and expose the active connection host in the TUI footer. ([#​91423](openclaw/openclaw#91423), [#​91557](openclaw/openclaw#91557), [#​89909](openclaw/openclaw#89909)) Thanks [@​cxyhhhhh](https://github.com/cxyhhhhh), [@​Solvely-Colin](https://github.com/Solvely-Colin), and [@​baskduf](https://github.com/baskduf). - Performance: prewarm TUI runtime plugins, deduplicate plugin auto-enable fanout, trim dense text-delta snapshots, and reuse prepared startup model metadata. ([#​90782](openclaw/openclaw#90782), [#​89978](openclaw/openclaw#89978), [#​91580](openclaw/openclaw#91580), [#​91531](openclaw/openclaw#91531)) Thanks [@​RomneyDa](https://github.com/RomneyDa) and [@​ai-hpc](https://github.com/ai-hpc). ##### Fixes - Agent/session recovery: drop stale approval follow-ups after session rebind, remove drained reply-queue items by identity, recover stale main and visible replies, preserve Codex context-engine compaction ownership, lower the default compaction timeout to 180 seconds while respecting explicit configuration, and keep provider-failure terminal lifecycle state correct. ([#​85679](openclaw/openclaw#85679), [#​91450](openclaw/openclaw#91450), [#​91566](openclaw/openclaw#91566), [#​91840](openclaw/openclaw#91840), [#​91590](openclaw/openclaw#91590), [#​91361](openclaw/openclaw#91361), [#​91895](openclaw/openclaw#91895)) Thanks [@​openperf](https://github.com/openperf), [@​yetval](https://github.com/yetval), [@​joshavant](https://github.com/joshavant), [@​wangmiao0668000666](https://github.com/wangmiao0668000666), and [@​TurboTheTurtle](https://github.com/TurboTheTurtle). - User-visible content boundaries: suppress Codex/Harmony protocol artifacts, neutralize browser and LanceDB memory media directives, redact transcript images, and preserve native `/compact` replies through source suppression. ([#​89151](openclaw/openclaw#89151), [#​91422](openclaw/openclaw#91422), [#​91425](openclaw/openclaw#91425), [#​91529](openclaw/openclaw#91529), [#​90212](openclaw/openclaw#90212)) Thanks [@​joelnishanth](https://github.com/joelnishanth), [@​pgondhi987](https://github.com/pgondhi987), [@​joshavant](https://github.com/joshavant), and [@​snowzlm](https://github.com/snowzlm). - Channel delivery: keep WhatsApp captured replies attached to the successor controller after restart, retry Feishu rate limits, preserve Mattermost thread replies, canonicalize LINE webhook paths, restore Discord reply hydration and runtime timeout exports, and show OpenAI Realtime WebRTC assistant transcripts. ([#​85823](openclaw/openclaw#85823), [#​89659](openclaw/openclaw#89659), [#​91684](openclaw/openclaw#91684), [#​91649](openclaw/openclaw#91649), [#​90263](openclaw/openclaw#90263), [#​91686](openclaw/openclaw#91686), [#​90426](openclaw/openclaw#90426)) Thanks [@​itsuzef](https://github.com/itsuzef), [@​ladygege](https://github.com/ladygege), [@​jacobtomlinson](https://github.com/jacobtomlinson), [@​fuller-stack-dev](https://github.com/fuller-stack-dev), and [@​shushushv](https://github.com/shushushv). - Cron: cancel active task runs cleanly, preserve terminal timeout/cancel state, and recover no-deliver tool warnings instead of silently losing the outcome. ([#​90666](openclaw/openclaw#90666), [#​90678](openclaw/openclaw#90678)) Thanks [@​ai-hpc](https://github.com/ai-hpc). - Gateway/config/auth: share the approval runtime socket token, replace arrays explicitly in `config.patch`, skip the deleted-agent guard only for valid ACP harness sessions, surface headless LaunchAgent state, verify SQLite auth migration before cleanup, and arm QMD startup maintenance. ([#​87105](openclaw/openclaw#87105), [#​91551](openclaw/openclaw#91551), [#​91219](openclaw/openclaw#91219), [#​91614](openclaw/openclaw#91614), [#​91740](openclaw/openclaw#91740), [#​91978](openclaw/openclaw#91978)) Thanks [@​fuller-stack-dev](https://github.com/fuller-stack-dev) and [@​scotthuang](https://github.com/scotthuang). - Providers/Codex: clarify quota errors, restore the Codex synthetic usage line, canonicalize Codex protocol assets, require API-key auth for realtime voice, normalize ACP model refs, preserve Gemma 4 `reasoning_content`, and avoid guardian review for local models. ([#​91390](openclaw/openclaw#91390), [#​91709](openclaw/openclaw#91709), [#​91507](openclaw/openclaw#91507), [#​91567](openclaw/openclaw#91567), [#​88630](openclaw/openclaw#88630), [#​91696](openclaw/openclaw#91696)) Thanks [@​hxy91819](https://github.com/hxy91819), [@​brokemac79](https://github.com/brokemac79), [@​RomneyDa](https://github.com/RomneyDa), [@​joshavant](https://github.com/joshavant), and [@​Coder-Wangyankun](https://github.com/Coder-Wangyankun). - Updates/builds: recover package Gateway restarts after refresh failure, expose plugin convergence repair, fall back to Corepack in PATH-less pnpm environments, seed the correct Docker store packages, and keep ClawHub dry-run and publish paths reusable. ([#​91581](openclaw/openclaw#91581), [#​91599](openclaw/openclaw#91599), [#​91547](openclaw/openclaw#91547), [#​91591](openclaw/openclaw#91591)) Thanks [@​fuller-stack-dev](https://github.com/fuller-stack-dev), [@​sallyom](https://github.com/sallyom), and [@​Patrick-Erichsen](https://github.com/Patrick-Erichsen). - UI: require explicit user intent before opening chat sessions and drain restored chat queues after session switches. ([#​91480](openclaw/openclaw#91480)) Thanks [@​TurboTheTurtle](https://github.com/TurboTheTurtle). - Android: avoid the `dataSync` foreground-service type for persistent nodes. ([#​80082](openclaw/openclaw#80082)) Thanks [@​davelutztx](https://github.com/davelutztx). - Native hooks: bound relay lifetimes so abandoned native hook connections cannot linger indefinitely. ([#​91550](openclaw/openclaw#91550)) Thanks [@​joshavant](https://github.com/joshavant). </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. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0My4xMDEuMSIsInVwZGF0ZWRJblZlciI6IjQzLjEwMS4xIiwidGFyZ2V0QnJhbmNoIjoibWFpbiIsImxhYmVscyI6WyJyZW5vdmF0ZS9jb250YWluZXIiLCJ0eXBlL3BhdGNoIl19--> Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/1040
Summary
What problem does this PR solve?
agent:<harnessId>:acp:<uuid>(for exampleagent:claude:acp:...), but<harnessId>is not anagents.listentry.sessions.resolve,sessions_send, and other deleted-agent-guarded paths to reject valid ACP workers withAgent "claude" no longer exists in configuration.Why does this matter now?
What is the intended outcome?
resolveDeletedAgentIdFromSessionKeyreturnsnullfor ACP harness session keys, so existing ACP sessions keep working while true deleted-agent protection remains for normal agent keys.sessions.resolvekey/sessionId/label paths, directsessions.send/chat.sendguards).What is intentionally out of scope?
sessions.resolve,sessions.send, orchat.send; noparseAgentSessionKeyspecial-casing; no ACP metadata hydration gate.What does success look like?
sessions.resolve({ key: "agent:claude:acp:<uuid>" })succeeds when the session exists, even ifclaudeis not inagents.list.agent:deleted-agent:mainare still rejected.What should reviewers focus on?
isAcpSessionKey(sessionKey)bypass inresolveDeletedAgentIdFromSessionKey(src/gateway/session-utils.ts) — shared owner boundary, not a single-entry workaround.parseAgentSessionKeyACP special-case (too wide), metadata-hydration gate (heavier than needed for guard-layer false positives).Linked context
Which issue does this close?
Closes #
Which issues, PRs, or discussions are related?
Was this requested by a maintainer or owner?
Local dogfood while testing ACP worker follow-up after the deleted-agent guard landed on
main.Real behavior proof (required for external PRs)
claude,codex) is absent fromagents.list.ws://127.0.0.1:18789; config at~/.openclaw/openclaw.jsonwithagents.listidsmainandcursoronly (noclaude).Copied live terminal output from the local gateway RPC:
sessions.resolveaccepts the existing ACP harness session key even thoughclaudeis not configured inagents.list; no deleted-agent error is returned for this key.OPENCLAW_LIVE_ACP_BINDsuite.~/.openclaw/agents/claude/sessions/sessions.json.agents.list.Tests and validation
Which commands did you run?
What regression coverage was added or updated?
src/gateway/session-utils.test.ts— ACP harness keys bypass deleted-agent detection.src/gateway/sessions-resolve.test.ts— key-basedsessions.resolvesucceeds for ACP harness keys when harness id is not inagents.list.src/gateway/sessions-resolve-store.test.ts— real store integration for ACP key/sessionId/label resolve without mocking the deleted-agent guard.What failed before this fix, if known?
agent:claude:acp:<uuid>could be treated as belonging to deleted agentclaude, causing resolver/send paths to fail even though the ACP session store entry existed.If no test was added, why not?
N/A — regression tests were added for helper, resolver path, and store integration.
Risk checklist
Did user-visible behavior change? (
Yes)Yes. ACP sessions that were incorrectly blocked by the deleted-agent guard can be resolved/sent again.
Did config, environment, or migration behavior change? (
No)No.
Did security, auth, secrets, network, or tool execution behavior change? (
No)No new surfaces. This removes a false positive from an existing guard; true deleted-agent rejection for normal agent session keys remains.
What is the highest-risk area?
Accidentally exempting too many session-key shapes from deleted-agent checks.
How is that risk mitigated?
isAcpSessionKey(sessionKey)only — an existing session-key class; the guard should not reinterpretagent:<harnessId>:acp:*'s second segment as anagents.listowner.Current review state
What is the next action?
Refresh PR #91219 with store integration test + updated Real behavior proof.
What is still waiting on author, maintainer, CI, or external proof?
Which bot or reviewer comments were addressed?
resolveDeletedAgentIdFromSessionKeybypass for ACP keys is the correct owner boundary; coverssessions.resolve(key/sessionId/label) viavalidateSessionAgentExistsand directsessions.send/chat.sendguards.session-utils.ts,sessions-resolve.ts,server-methods/sessions.ts,server-methods/chat.ts,session-key-utils.ts, adjacent tests.