Fix sub-agent cwd/workspace separation by mbelinky · Pull Request #87218 · openclaw/openclaw

mbelinky · 2026-05-27T08:15:54Z

Summary

Fixes sub-agent runs that need to work in a task repository while still loading agent bootstrap/context files from the configured agent workspace.

threads cwd separately from workspaceDir through native sub-agent, CLI runner, Codex app-server, session metadata, and transcript mirroring paths
records spawnedCwd / transcript header cwd so child sessions reflect the task working directory without treating it as the agent workspace
keeps the cwd override on sessions_spawn / stored child-session lineage instead of exposing a generic public agent cwd override
updates the sessions protocol schema, generated Swift protocol model, and sub-agent docs for the new child cwd metadata/parameter
adds regression coverage for native and Codex child runs using a separate task cwd

Release note context: this touches runtime/session/protocol behavior. Maintainers should decide whether the active release/2026.5.26 line needs inclusion.

Verification

pnpm protocol:gen && pnpm protocol:gen:swift
node scripts/run-vitest.mjs extensions/codex/src/app-server/run-attempt.test.ts src/config/sessions/transcript.test.ts src/agents/pi-embedded-runner/run/attempt.cwd-split.test.ts src/agents/pi-embedded-runner/session-manager-init.test.ts src/gateway/server-methods/agent.test.ts — 7 files, 520 tests passed on the pre-review head
node scripts/run-vitest.mjs src/agents/subagent-spawn.test.ts src/gateway/server-methods/agent.test.ts — 4 files, 274 tests passed after the review hardening change
node scripts/run-tsgo.mjs -p tsconfig.core.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core-pr87218-review-fix.tsbuildinfo
node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.test.src.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/test-src-pr87218-review-fix.tsbuildinfo
git diff --check

Real behavior proof

Behavior addressed: A sub-agent can now load bootstrap files from its configured agent workspace while executing delegated work from a separate task cwd.

Real environment tested: Local current-main source checkout plus a live gateway-style sub-agent run against a temporary task directory; a remote Linux Testbox lane also passed the focused test set earlier in the repair cycle.

Exact steps or command run after this patch: The focused commands listed in Verification were rerun after rebasing onto current origin/main; after review, the public agent cwd override was removed and the affected sub-agent/gateway tests plus type probes were rerun.

Evidence after fix: The child run reported the task cwd, read the task marker from that cwd, and did not require bootstrap files to exist in the task directory. Transcript/session metadata preserved the task cwd while workspace bootstrap loading stayed tied to the agent workspace. The final branch head is 6b505a7325.

Observed result after fix: Focused tests passed, protocol artifacts regenerated cleanly, and type probes passed on the final branch head.

What was not tested: Full repository test suite and full release CI were not run locally. AWS Crabbox was attempted earlier but blocked before command execution by validation-provider capacity, so the remote proof used the available Testbox lane instead.

clawsweeper · 2026-05-27T08:19:30Z

Codex review: needs real behavior proof before merge. Reviewed May 27, 2026, 10:09 AM ET / 14:09 UTC.

Summary
The PR threads a separate task cwd alongside agent workspaceDir through native/Codex sub-agent runs, session metadata/protocol, transcripts, compaction, docs, and regression tests.

PR surface: Source +230, Tests +618, Docs +4, Other +4. Total +856 across 79 files.

Reproducibility: yes. for the review finding from source inspection: current main maps sessions_spawn.cwd to the child workspace, while the PR adds sandboxed cwd rejection paths. I did not run tests because this was a read-only review.

Review metrics: 2 noteworthy metrics.

Gateway session metadata fields: 1 added (spawnedCwd). The additive protocol/session field affects operator clients and stored session lineage, so upgrade semantics need review before merge.
Sandboxed cwd rejection paths: 4 added. The PR adds fail-closed cwd override checks across native spawn, embedded agent, embedded compaction, and Codex app-server paths.

Merge readiness
Overall: 🧂 unranked krab
Proof: 🦪 silver shellfish
Patch quality: 🦐 gold shrimp
Result: blocked until stronger real behavior proof is added.

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

Rank-up moves:

Preserve sandboxed task-cwd delegation or get explicit maintainer approval for the fail-closed break.
Add inspectable redacted real behavior proof, such as terminal output or logs from a live gateway-style sub-agent run.
Remove the normal-PR CHANGELOG.md edit.

Proof guidance:
Needs stronger real behavior proof before merge: The PR body gives a narrative and test output summary, but no inspectable terminal output, logs, recording, or linked artifact showing the after-fix live cwd/workspace split; add redacted proof before merge. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Risk before merge

Existing sandboxed sessions_spawn.cwd callers that currently run by treating cwd as the child workspace would receive a forbidden response after this PR.
The cwd/workspace split crosses runtime filesystem roots and sandbox policy; maintainers need explicit upgrade and boundary proof before accepting a fail-closed path.
The PR still needs inspectable real behavior proof beyond tests and narrative before merge.

Maintainer options:

Preserve sandboxed cwd delegation (recommended)
Repair the branch so sandboxed native/Codex child runs can still execute in the requested task cwd while bootstrap files remain rooted in the agent workspace, with focused sandbox coverage.
Approve the fail-closed contract
Maintainers can intentionally accept the sandboxed cwd rejection, but the PR should document the break and provide upgrade/release-note context before merge.
Pause for sandbox design
If preserving cwd inside sandbox needs a larger filesystem-mapping design, pause this PR rather than landing a partial behavior change.

Next step before merge
Manual review is needed because the remaining blocker is a sandbox compatibility and security-boundary contract decision plus contributor-supplied real behavior proof.

Security
Cleared: No concrete secret, dependency, or supply-chain regression was found, but the sandbox/filesystem cwd boundary remains a merge-risk decision.

Review findings

[P1] Preserve sandboxed cwd spawns — src/agents/subagent-spawn.ts:894-900
[P3] Remove the release-owned changelog entry — CHANGELOG.md:15

Review details

Best possible solution:

Land a version that preserves sandboxed task-cwd delegation by safely mapping the task cwd into the sandbox while keeping bootstrap files in the agent workspace, or get explicit maintainer approval and docs for a fail-closed break; keep release-note context in the PR body instead of CHANGELOG.md.

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

Yes for the review finding from source inspection: current main maps sessions_spawn.cwd to the child workspace, while the PR adds sandboxed cwd rejection paths. I did not run tests because this was a read-only review.

Is this the best way to solve the issue?

No: separating runtime cwd from bootstrap workspace is the right direction, but the current fail-closed sandbox behavior is not the safest compatibility path without maintainer approval and upgrade proof.

Full review comments:

[P1] Preserve sandboxed cwd spawns — src/agents/subagent-spawn.ts:894-900
Current main treats sessions_spawn.cwd as the child workspace, so sandboxed child runs can execute in that requested cwd through the existing sandboxed workspace path. This new rejection turns those calls into forbidden instead of preserving the behavior with a safe task-cwd sandbox mapping, which can break existing sandboxed delegation workflows.
Confidence: 0.87
[P3] Remove the release-owned changelog entry — CHANGELOG.md:15
CHANGELOG.md is release-owned in this repo, and normal PRs should keep release-note context in the PR body or commit message instead. Please drop this entry so release generation remains the source of truth.
Confidence: 0.93

Overall correctness: patch is incorrect
Overall confidence: 0.86

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 4d099c354b69.

Label changes

Label justifications:

P1: The PR changes a core sub-agent runtime path and can break sandboxed delegated work for existing users.
merge-risk: 🚨 compatibility: Sandboxed sessions_spawn.cwd requests that current main accepts can become forbidden after merge.
merge-risk: 🚨 security-boundary: The patch changes filesystem cwd routing across native/Codex tools and sandboxed paths, so the sandbox boundary needs maintainer review beyond green tests.
rating: 🧂 unranked krab: Overall readiness is 🧂 unranked krab; proof is 🦪 silver shellfish and patch quality is 🦐 gold shrimp.
status: 📣 needs proof: The PR needs real behavior proof before ClawSweeper can clear the contributor ask. Needs stronger real behavior proof before merge: The PR body gives a narrative and test output summary, but no inspectable terminal output, logs, recording, or linked artifact showing the after-fix live cwd/workspace split; add redacted proof before merge. After adding proof, update the PR body; ClawSweeper should re-review automatically. If it does not, the PR author or someone with repository write access can comment @clawsweeper re-review.

Evidence reviewed

PR surface:

Source +230, Tests +618, Docs +4, Other +4. Total +856 across 79 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	49	302	72	+230
Tests	27	631	13	+618
Docs	2	4	0	+4
Config	0	0	0	0
Generated	0	0	0	0
Other	1	4	0	+4
Total	79	941	85	+856

Acceptance criteria:

node scripts/run-vitest.mjs src/agents/subagent-spawn.test.ts src/agents/subagent-spawn.workspace.test.ts src/agents/pi-embedded-runner/run/attempt.cwd-split.test.ts src/gateway/server-methods/agent.test.ts
node scripts/run-vitest.mjs extensions/codex/src/app-server/run-attempt.test.ts src/agents/pi-embedded-runner/compact.hooks.test.ts src/agents/command/cli-compaction.test.ts
node scripts/run-tsgo.mjs -p tsconfig.core.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core-pr87218-review.tsbuildinfo

What I checked:

Current main cwd behavior: Current main maps sessions_spawn params.cwd into explicitWorkspaceDir, so a caller-provided cwd becomes the child workspace instead of being rejected at spawn time. (src/agents/subagent-spawn.ts:818, 4d099c354b69)
Current sandbox policy: Current docs only say sandboxed requester sessions reject unsandboxed targets; they do not define a sandboxed-cwd rejection for sessions_spawn. Public docs: docs/tools/subagents.md. (docs/tools/subagents.md:350, 4d099c354b69)
PR fail-closed behavior: The PR adds a childRuntime.sandboxed && spawnedCwd !== spawnedWorkspaceCwd rejection in native sub-agent spawn, and similar cwd-override rejection points for Codex app-server, embedded runs, and embedded compaction. (src/agents/subagent-spawn.ts:894, 85b92d638d6d)
Repository compatibility policy: Root review policy treats fail-closed changes, stricter validation, provider/plugin behavior changes, and fallback changes as compatibility-sensitive merge risk even with green CI. (AGENTS.md:26, 4d099c354b69)
Changelog policy: Root policy says CHANGELOG.md is release-owned and should not be edited for normal PRs; this branch adds a normal PR release-note line there. (AGENTS.md:191, 4d099c354b69)
Real behavior proof gap: The PR body lists focused test and typecheck commands and narrates a live gateway-style run, but it does not attach inspectable terminal output, logs, a recording, or a linked artifact showing the after-fix cwd/workspace split. (85b92d638d6d)

Likely related people:

Vincent Koc: Blame in the current checkout points the central sub-agent spawn, Pi tools, and gateway agent handling code to commit 1d4537a; history is grafted, so this is a routing signal rather than full ownership proof. (role: current area contributor; confidence: low; commits: 1d4537add32f; files: src/agents/subagent-spawn.ts, src/agents/pi-tools.ts, src/gateway/server-methods/agent.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 · 2026-05-27T08:25:18Z

ClawSweeper PR egg

🎁 Pass real behavior proof to wake the egg and unlock a hatchable treat.

Where did the egg go?

The egg game starts only after the PR passes the real-behavior proof check.
Before that, no creature or rarity is rolled. The treat waits for real proof.
This is still just collectible flavor: proof affects review readiness, not creature quality.

mbelinky · 2026-05-27T21:55:32Z

Merged via squash.

Prepared head SHA: f47b073830f5f158153ad472eb09286b971f89fb
Merge commit: 7299c5695317f74ddbe4a1a68efafd723a38c6c1

Thanks @mbelinky!

@mbelinky

Merged via squash. Prepared head SHA: f47b073 Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com> Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com> Reviewed-by: @mbelinky

…026.5.27) (#698) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.26` → `2026.5.27` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.27`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026527) [Compare Source](openclaw/openclaw@v2026.5.26...v2026.5.27) ##### Highlights - Safer local/runtime boundaries: OpenClaw now rejects unsafe command wrappers, malformed CLI numeric options, unsafe Node runtime env overrides, no-auth Tailscale exposure, and non-admin device-role pairing approvals before they can affect live runs. ([#87308](openclaw/openclaw#87308), [#87305](openclaw/openclaw#87305), [#87292](openclaw/openclaw#87292), [#87146](openclaw/openclaw#87146)) - Matrix and auto-reply delivery are steadier: mention previews stay inert, final mention replies deliver normally, shared-DM notices are awaited, MXID parsing ignores filenames, and reasoning-prefixed `NO_REPLY` responses stay suppressed. - Provider and agent reliability improved across OpenAI-compatible embeddings, cached token usage, Anthropic/Codex/Claude runtime state, unsupported tool-schema quarantine, heartbeat templates, and session fallback errors. ([#85269](openclaw/openclaw#85269), [#82062](openclaw/openclaw#82062), [#85416](openclaw/openclaw#85416), [#86855](openclaw/openclaw#86855)) - Plugin and package release paths got tighter: Pixverse ships as an external video plugin with region selection, package exclusions and shrinkwrap inventory match the published npm shape, and release/package smoke commands fail bounded instead of hanging. - Gateway hot paths do less rediscovery by reusing current plugin metadata fingerprints, stable plugin index fingerprints, read-only session metadata, active working stores, status fast paths, and auth/env snapshots. ([#86439](openclaw/openclaw#86439)) ##### Changes - Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. ([#85269](openclaw/openclaw#85269)) Thanks [@dutifulbob](https://github.com/dutifulbob). - Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. ([#85072](openclaw/openclaw#85072)) Thanks [@mbelinky](https://github.com/mbelinky). - Pixverse: add video generation provider support, API region selection, and external plugin publishing. - Plugins: expose approval action metadata for plugin-driven approval surfaces. ##### Fixes - Security/CLI/runtime: harden hostname normalization for repeated trailing dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject loose numeric CLI and gateway options, require admin approval for node device-role pairing, and reject no-auth Tailscale exposure. ([#87305](openclaw/openclaw#87305), [#87292](openclaw/openclaw#87292), [#87308](openclaw/openclaw#87308), [#87146](openclaw/openclaw#87146)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Doctor: validate runtime tool schemas for every configured embedded agent while skipping ACP-only profiles, so bad non-default plugin or MCP tools are reported before assistant turns. - Telegram: route `sendMessage` action replies through durable outbound delivery so completed agent responses remain retryable when the gateway send path times out. ([#87261](openclaw/openclaw#87261)) Thanks [@mbelinky](https://github.com/mbelinky). - Matrix/auto-reply: keep draft previews mention-inert, preserve final mention delivery, send mention finals normally, await shared DM notices, ignore filename-embedded MXIDs, and suppress reasoning-prefixed `NO_REPLY` responses. - Agents/providers: add OpenAI-compatible cache retention, forward cached token usage in chat completions, preserve runtime context before active user turns, strip stale Anthropic thinking, load Claude CLI OAuth for Pi auth profiles, avoid false Codex runtime live switches, and quarantine unsupported tool schemas. ([#82062](openclaw/openclaw#82062), [#87167](openclaw/openclaw#87167), [#86855](openclaw/openclaw#86855)) - Gateway/performance: cache plugin metadata fingerprints and stable plugin index fingerprints, borrow read-only session metadata safely, keep the active session working store hot, keep status on a bounded fast path, and preserve model auth profile suffixes. ([#86439](openclaw/openclaw#86439)) - Package/install/release: align npm package exclusions and inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, cap tsdown heap in containers, bound install/release smoke waits, and harden post-publish verification. - Codex/Auth: bound ChatGPT OAuth token exchange and refresh requests, and honor cancellation across Codex and Anthropic OAuth login flows. - QA/E2E/CI: bound Telegram, kitchen-sink, Open WebUI, ClawHub, MCP, Discord, realtime, labeler, and GitHub API waits; fail empty explicit test, live-media, gateway CPU, startup benchmark, plugin gauntlet, and beta-smoke runs instead of false-greening. - Agents/Codex: keep spawned agent bootstrap files rooted in the agent workspace while running task commands, transcripts, and compaction from the requested cwd. ([#87218](openclaw/openclaw#87218)) Thanks [@mbelinky](https://github.com/mbelinky). </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/698

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

@mbelinky

Merged via squash. Prepared head SHA: f47b073 Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com> Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com> Reviewed-by: @mbelinky

@mbelinky

Merged via squash. Prepared head SHA: f47b073 Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com> Co-authored-by: mbelinky <132747814+mbelinky@users.noreply.github.com> Reviewed-by: @mbelinky

openclaw-barnacle Bot added docs Improvements or additions to documentation app: web-ui App: web-ui gateway Gateway runtime agents Agent runtime and tooling extensions: codex size: L maintainer Maintainer-authored PR labels May 27, 2026

mbelinky force-pushed the codex/cdx-workspace-fix-current branch 2 times, most recently from 6b505a7 to f891a31 Compare May 27, 2026 13:55

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

mbelinky force-pushed the codex/cdx-workspace-fix-current branch 3 times, most recently from e9ed96e to 5f3e43c Compare May 27, 2026 21:51

fix: split subagent cwd from workspace

f47b073

mbelinky force-pushed the codex/cdx-workspace-fix-current branch from 5f3e43c to f47b073 Compare May 27, 2026 21:54

mbelinky merged commit 7299c56 into main May 27, 2026
23 checks passed

mbelinky deleted the codex/cdx-workspace-fix-current branch May 27, 2026 21:55

github-actions Bot mentioned this pull request May 27, 2026

📡 Upstream Digest — 2026-05-27 23:10 UTC curtismercier/openclaw-mods#960

Open

This was referenced May 28, 2026

perf(plugins) refactor plugin SDK declarations for flat package types #87165

Merged

fix(codex): project MCP OAuth config #87478

Open

martingarramon mentioned this pull request May 28, 2026

Guard subagent spawns from direct OpenAI overrides #81466

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Fix sub-agent cwd/workspace separation#87218

Fix sub-agent cwd/workspace separation#87218
mbelinky merged 1 commit into
mainfrom
codex/cdx-workspace-fix-current

mbelinky commented May 27, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 27, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 27, 2026

Uh oh!

Uh oh!

mbelinky commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

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

Uh oh!

Summary

Verification

Real behavior proof

Uh oh!

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

Uh oh!

Uh oh!

clawsweeper Bot commented May 27, 2026

Uh oh!

Uh oh!

mbelinky commented May 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

mbelinky commented May 27, 2026 •

edited

Loading

clawsweeper Bot commented May 27, 2026 •

edited

Loading