fix(codex): route workspace memory through tools by steipete · Pull Request #87383 · openclaw/openclaw

steipete · 2026-05-27T18:33:42Z

Summary

Route native Codex workspace MEMORY.md through a small pointer when memory_search is actually exposed, keeping raw memory out of the turn prompt budget.
Preserve bounded prompt fallback when memory tools are unavailable, including correct truncation diagnostics for budget-dropped fallback memory.
Update Codex/system-prompt/token-use docs and regression coverage for routed, fallback, and budgeted MEMORY.md paths.

Verification

Behavior addressed: Native Codex no longer pastes raw MEMORY.md into normal tool-enabled turns, while tool-disabled turns still receive bounded fallback memory.

Real environment tested: Local macOS checkout; focused Codex tests under Node 24.15.0.

Exact steps or command run after this patch:

fnm exec --using 24.15.0 -- node scripts/run-vitest.mjs run --config test/vitest/vitest.extension-codex.config.ts --configLoader runner extensions/codex/src/app-server/run-attempt.test.ts -t "MEMORY.md" --reporter=verbose
pnpm check:docs
git diff --check
node scripts/run-tsgo.mjs -p tsconfig.core.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core.tsbuildinfo
node scripts/run-tsgo.mjs -p tsconfig.extensions.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/extensions.tsbuildinfo
node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.extensions.test.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/extensions-test.tsbuildinfo
node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.extensions.json extensions/codex/src/app-server/run-attempt.ts extensions/codex/src/app-server/run-attempt.test.ts
node scripts/run-oxlint.mjs --tsconfig config/tsconfig/oxlint.core.json src/plugin-sdk/agent-harness-runtime.ts
node scripts/run-oxlint-shards.mjs --split-core --only core:src:music-generation
.agents/skills/autoreview/scripts/autoreview --mode local

Evidence after fix: Focused Codex test file reported 4 passed MEMORY.md tests; docs check passed with 0 markdown errors and 0 broken internal links; autoreview reported no accepted/actionable findings.

Observed result after fix: Tool-enabled Codex turns show only the workspace-memory pointer and report MEMORY.md as 0 injected chars; no-tool turns inject bounded MEMORY.md fallback; no-tool budget omissions report truncated: true.

What was not tested: Live Codex app-server run against a real Codex model. Full env -u OPENCLAW_TESTBOX pnpm check:changed was not completed cleanly after the final patch because lint core hit a tsgolint SIGSEGV while parsing node_modules/lit/development/directives/style-map.d.ts; the exact crashed shard, touched-file lint, typecheck lanes, docs, tests, and autoreview passed.

clawsweeper · 2026-05-27T18:35:18Z

Codex review: needs real behavior proof before merge. Reviewed May 27, 2026, 3:06 PM ET / 19:06 UTC.

Summary
The PR routes native Codex MEMORY.md through a workspace-memory pointer when memory tools are detected, keeps bounded prompt fallback without memory tools, updates docs/tests, and adds bootstrap helper exports to agent-harness-runtime.

PR surface: Source +119, Tests +146, Docs +11. Total +276 across 7 files.

Reproducibility: yes. at source level for the review findings: the PR-head code filters all basename MEMORY.md bootstrap files and only detects memory_search, while current memory-core and hook code show supported get-only and extra-bootstrap paths. I did not run tests because this review is read-only.

Review metrics: 1 noteworthy metric.

Plugin SDK Exports: 2 added on agent-harness-runtime. This expands a public SDK entrypoint, so maintainers need API approval and baseline alignment before merge.

Merge readiness
Overall: 🦪 silver shellfish
Proof: 🦪 silver shellfish
Patch quality: 🦐 gold shrimp
Result: blocked until real behavior proof from a real setup is added.

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

Rank-up moves:

Add redacted real behavior proof from a live Codex app-server run showing tool-enabled routing and no-tool fallback behavior.
Fix the hook-added MEMORY.md and memory_get-only routing cases.
Resolve the public SDK export decision and update the Plugin SDK API baseline if the exports remain public.

Proof guidance:
Needs real behavior proof before merge: The PR body reports focused tests and checks but explicitly says no live Codex app-server run against a real Codex model was tested, so contributor-supplied real behavior proof is still needed 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

Merging as-is can silently drop configured extra MEMORY.md bootstrap context in Codex tool-enabled turns.
The public Plugin SDK entrypoint expands without baseline/docs alignment or explicit API approval.
The contributor has not shown after-fix behavior in a real Codex app-server run with a real model.

Maintainer options:

Resolve SDK Surface Before Merge (recommended)
Remove the new public exports if they are only Codex-internal, or land them with maintainer approval plus Plugin SDK API baseline and docs alignment.
Accept The API Expansion
Maintainers can intentionally accept the new helper exports as third-party API after documenting the contract and upgrade expectations.

Next step before merge
Manual review is needed because the PR has a protected maintainer label, missing real behavior proof, and an unresolved public Plugin SDK surface decision.

Security
Cleared: No concrete security or supply-chain issue was found; the diff does not change workflows, lockfiles, dependencies, secrets handling, or downloaded code execution.

Review findings

[P2] Keep hook-added MEMORY.md files injectable — extensions/codex/src/app-server/attempt-context.ts:236
[P2] Route memory_get-only runs through memory tools — extensions/codex/src/app-server/attempt-context.ts:777
[P2] Lock down the new SDK exports before merge — src/plugin-sdk/agent-harness-runtime.ts:186-189

Review details

Best possible solution:

Land this only after memory routing handles canonical MEMORY.md without dropping hook-added context, recognizes whichever memory tools are actually exposed, and resolves the SDK surface with baseline approval or a private helper path.

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

Yes at source level for the review findings: the PR-head code filters all basename MEMORY.md bootstrap files and only detects memory_search, while current memory-core and hook code show supported get-only and extra-bootstrap paths. I did not run tests because this review is read-only.

Is this the best way to solve the issue?

No, not yet. The maintainable path is to narrow the memory routing to covered files/tools, keep configured bootstrap context available, and settle the public SDK surface before merge.

Full review comments:

[P2] Keep hook-added MEMORY.md files injectable — extensions/codex/src/app-server/attempt-context.ts:236
This removes every bootstrap file whose basename is MEMORY.md when memory tools are present. The bootstrap-extra-files hook can intentionally add paths like packages/*/MEMORY.md as Project Context, but those files are not covered by the default memory-search corpus, so they can silently disappear from Codex turns; filter only the canonical workspace memory file or keep hook-supplied MEMORY.md files injectable.
Confidence: 0.9
[P2] Route memory_get-only runs through memory tools — extensions/codex/src/app-server/attempt-context.ts:777
This returns false unless memory_search is present. Runs narrowed to memory_get still expose an exact memory reader and memory-core has get-only guidance, but the PR will paste raw MEMORY.md instead of using on-demand retrieval; recognize either available memory tool and render only tool names that are actually present.
Confidence: 0.88
[P2] Lock down the new SDK exports before merge — src/plugin-sdk/agent-harness-runtime.ts:186-189
These new exports change the public agent-harness-runtime SDK entrypoint listed in scripts/lib/plugin-sdk-entrypoints.json. The PR does not update the Plugin SDK API baseline or document/approve the new contract, so either avoid the public export or update the SDK baseline/docs with maintainer approval.
Confidence: 0.86

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 2f710f560450.

Label changes

Label changes:

add P2: The PR addresses a bounded Codex prompt/context behavior but still has normal-priority runtime and SDK-surface blockers.
add merge-risk: 🚨 compatibility: The diff changes a public Plugin SDK entrypoint and can affect third-party plugin API expectations if merged without approval and baseline alignment.

Label justifications:

P2: The PR addresses a bounded Codex prompt/context behavior but still has normal-priority runtime and SDK-surface blockers.
merge-risk: 🚨 compatibility: The diff changes a public Plugin SDK entrypoint and can affect third-party plugin API expectations if merged without approval and baseline alignment.
rating: 🦪 silver shellfish: Overall readiness is 🦪 silver shellfish; 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 real behavior proof before merge: The PR body reports focused tests and checks but explicitly says no live Codex app-server run against a real Codex model was tested, so contributor-supplied real behavior proof is still needed 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 +119, Tests +146, Docs +11. Total +276 across 7 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	3	128	9	+119
Tests	1	151	5	+146
Docs	3	25	14	+11
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	7	304	28	+276

What I checked:

Repository policy read: Read the full root AGENTS.md plus relevant docs, extensions, and Plugin SDK scoped guides; the Plugin SDK boundary and ClawSweeper PR proof rules affected this review. (AGENTS.md:1, 2f710f560450)
PR filters all basename MEMORY.md files: The PR-head implementation removes every bootstrap file whose basename is memory.md before building injected context when memory tools are available, not only the canonical root workspace MEMORY.md. (extensions/codex/src/app-server/attempt-context.ts:236, 362cfce88fe4)
Extra bootstrap MEMORY.md is a supported context path: The bundled bootstrap-extra-files hook appends extra bootstrap files and its hook docs say recognized bootstrap basenames include MEMORY.md, so those configured files are intended to be injected as Project Context. (src/hooks/bundled/bootstrap-extra-files/handler.ts:58, 2f710f560450)
memory_get-only configurations are valid: Memory-core has explicit get-only prompt guidance when memory_get is available without memory_search, but the PR's tool-detection helper only returns true for memory_search. (extensions/memory-core/src/prompt-section.ts:21, 2f710f560450)
SDK API baseline surface changed: agent-harness-runtime is a generated Plugin SDK API entrypoint, and the PR adds two exports there without changing the checked baseline hash file. (scripts/lib/plugin-sdk-entrypoints.json:111, 2f710f560450)
Real behavior proof is still absent: The PR body lists focused tests and checks, but explicitly says a live Codex app-server run against a real Codex model was not tested. (362cfce88fe4)

Likely related people:

steipete: Git history shows Peter Steinberger recently split and maintained the Codex app-server attempt context where the bootstrap routing lives, and also touched the agent harness runtime barrel in current-main history. (role: recent Codex app-server area contributor; confidence: high; commits: a4c2e7f5cf1b, bb46b79d3c14; files: extensions/codex/src/app-server/attempt-context.ts, extensions/codex/src/app-server/run-attempt.ts, src/plugin-sdk/agent-harness-runtime.ts)
vincentkoc: Blame on the current agent-harness-runtime export block points to Vincent Koc's recent SDK/barrel work, which is relevant to the public export and baseline question. (role: recent SDK barrel contributor; confidence: medium; commits: d2a1f62d238b; files: src/plugin-sdk/agent-harness-runtime.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.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: a89e96413e

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-27T18:38:02Z

+      params.memoryToolsAvailable
+        ? bootstrapFiles.filter((file) => !isCodexMemoryBootstrapFile(file))
+        : bootstrapFiles,


Keep hook-added MEMORY.md files injectable

When memory tools are available, this removes every bootstrap file whose basename is MEMORY.md, including files added by agent:bootstrap hooks such as the bundled bootstrap-extra-files hook for packages/*/MEMORY.md. The memory tools only cover the canonical workspace MEMORY.md and memory/**/*.md corpus (see src/plugin-sdk/memory-host-core.ts / extensions/memory-core/src/prompt-section.ts), so those extra bootstrap files are no longer pasted and are not retrievable by memory_search/memory_get, silently dropping configured workspace context.

Useful? React with 👍 / 👎.

chatgpt-codex-connector · 2026-05-27T18:38:02Z

+  buildBootstrapContextForFiles,
+  resolveBootstrapContextForRun,
+  resolveBootstrapFilesForRun,


Regenerate the SDK API baseline

This public agent-harness-runtime entrypoint is listed in scripts/lib/plugin-sdk-entrypoints.json, so adding these exports changes the generated Plugin SDK API surface. Because the commit does not update docs/.generated/plugin-sdk-api-baseline.sha256, the plugin SDK API baseline check will report drift for this SDK-surface change before the PR can land.

Useful? React with 👍 / 👎.

clawsweeper · 2026-05-27T18:42:17Z

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.

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 362cfce88f

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-27T19:00:31Z

+export function hasCodexWorkspaceMemoryTools(tools: readonly { name: string }[]): boolean {
+  return tools.some((tool) => normalizeCodexDynamicToolName(tool.name) === "memory_search");
+}


Route memory_get-only runs through memory tools

When a Codex run narrows toolsAllow to memory_get (or policy denies only memory_search), the model still has an exact reader for MEMORY.md—the memory plugin has get-only prompt guidance and Codex tool filtering honors exact tool names—but this check returns false unless memory_search is present. In that valid memory-tool configuration, raw MEMORY.md is still injected into turn context and budget instead of using on-demand retrieval, so the new routing only works for one of the two supported memory tools; consider recognizing either available memory tool and only naming tools that are actually present.

Useful? React with 👍 / 👎.

* fix(codex): route workspace memory through tools * fix(codex): preserve extra memory bootstrap files * fix(codex): support memory_get-only context routing * fix(codex): only tool-route canonical workspace memory * fix(codex): keep memory fallback for sandbox workspaces (cherry picked from commit d93524d)

* fix(codex): route workspace memory through tools * fix(codex): preserve extra memory bootstrap files * fix(codex): support memory_get-only context routing * fix(codex): only tool-route canonical workspace memory * fix(codex): keep memory fallback for sandbox workspaces

…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

* fix(codex): route workspace memory through tools * fix(codex): preserve extra memory bootstrap files * fix(codex): support memory_get-only context routing * fix(codex): only tool-route canonical workspace memory * fix(codex): keep memory fallback for sandbox workspaces

openclaw-barnacle Bot added docs Improvements or additions to documentation extensions: codex size: M maintainer Maintainer-authored PR labels May 27, 2026

chatgpt-codex-connector Bot reviewed May 27, 2026

View reviewed changes

clawsweeper Bot added rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. labels May 27, 2026

fix(codex): route workspace memory through tools

362cfce

steipete force-pushed the fix/codex-memory-context-routing branch from a89e964 to 362cfce Compare May 27, 2026 18:58

chatgpt-codex-connector Bot reviewed May 27, 2026

View reviewed changes

clawsweeper Bot added P2 Normal backlog priority with limited blast radius. merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. labels May 27, 2026

steipete added 4 commits May 27, 2026 20:17

fix(codex): preserve extra memory bootstrap files

9d556da

fix(codex): support memory_get-only context routing

3478e93

fix(codex): only tool-route canonical workspace memory

bbc1611

fix(codex): keep memory fallback for sandbox workspaces

3cae0b8

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

steipete merged commit d93524d into main May 27, 2026
101 of 109 checks passed

steipete deleted the fix/codex-memory-context-routing branch May 27, 2026 19:55

steipete mentioned this pull request May 27, 2026

fix(codex): route workspace memory through tools #87403

Merged

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

📡 Upstream Digest — 2026-05-27 21:46 UTC curtismercier/openclaw-mods#959

Open

This was referenced Jun 9, 2026

fix(codex): restore memory recall guidance #91594

Open

fix(codex): restore memory recall from plugin tools #91813

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(codex): route workspace memory through tools#87383

fix(codex): route workspace memory through tools#87383
steipete merged 5 commits into
mainfrom
fix/codex-memory-context-routing

steipete commented May 27, 2026

Uh oh!

clawsweeper Bot commented May 27, 2026 •

edited

Loading

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 27, 2026

Uh oh!

chatgpt-codex-connector Bot May 27, 2026

Uh oh!

clawsweeper Bot commented May 27, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

steipete commented May 27, 2026

Summary

Verification

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!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 27, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot May 27, 2026

Choose a reason for hiding this comment

Uh oh!

clawsweeper Bot commented May 27, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 27, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

clawsweeper Bot commented May 27, 2026 •

edited

Loading