Fix smart-quoted tool call argument repair by ferminquant · Pull Request #86611 · openclaw/openclaw

ferminquant · 2026-05-25T19:08:31Z

Summary

Fixes Cron job result serialization fails on special characters in edit tool arguments #67488.
Repairs malformed smart-quoted tool-call argument objects inside the existing embedded-runner malformed argument repair wrapper.
Keeps the change local to src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts; no shared JSON helper, cron status, delivery, or dependency changes.
Adds focused stream-wrapper regressions in src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts.

AI assistance disclosure

This PR was implemented with Codex assistance. I reviewed the change and understand the affected embedded-runner tool-call argument repair path.

Real behavior proof

Behavior addressed: malformed smart-quoted edit/write/exec tool-call arguments are repaired before the embedded runner observes empty {} arguments.

Real environment tested: local Node.js v22.22.0 loading the TypeScript source with tsx, exercising the actual wrapStreamFnRepairMalformedToolCallArguments stream wrapper with synthetic streamed tool calls. No live credentials or delivery channels were used.

Exact steps or command run after this patch: node --import tsx --input-type=module script importing src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts, streaming .functions.<tool>:0 plus smart-quoted JSON-like args, draining the wrapped stream, and printing repaired tool-call args. Local proof log: .artifacts/67488-smart-quote-repair-proof.log.

Evidence after fix:

node_version: v22.22.0
json_parse_structural_smart_quotes: SyntaxError: Expected property name or '}' in JSON at position 1 (line 1 column 2)
repair_gate_openai_completions: true
edit_case_final_args: {"path":"notes/报告.md","oldText":"旧的 **草稿**","newText":"更新 **草稿** with “smart”, “sure” and code \"x\"\nJSON-ish “alpha”, “path”: “ignored” snippet\nSee [“quoted”](https://example.test)\nconst re = /\\d+/;\n内部内容"}
edit_case_all_surfaces_match: true
edit_case_content_preserved: true
jsonish_prose_guard_final_args: {"path":"safe.txt","content":"Use ”, “foo”: “bar” in prose"}
jsonish_prose_guard_no_synthetic_foo: true
exec_workdir_final_args: {"command":"pwd","workdir":"/tmp"}
exec_workdir_repaired: true
exact_no_preamble_final_args: {"path":"safe.txt"}
exact_no_preamble_repaired: true
escape_case_final_args: {"path":"safe.txt","content":"line\nnext \"quoted\" path C:\\tmp mark ✓ invalid \\d"}
escape_case_matches_json_semantics: true
escape_case_all_surfaces_match: true
escape_case_actual_newline: true
escape_case_invalid_escape_preserved: true
nested_edit_case_final_args: {"path":"notes/报告.md","edits":[{"oldText":"旧的 **草稿**","newText":"更新 \"草稿\"\nnext"},{"oldText":"tail","newText":"done"}]}
nested_edit_case_repaired: true
nested_edit_case_all_surfaces_match: true

Observed result after fix: Node still rejects structural smart quotes directly, but the existing repair wrapper recovers the streamed malformed tool arguments and writes identical repaired args into the partial, streamed, end-message, and final tool-call surfaces. Smart-quoted string values now decode JSON escapes for newline, quote, backslash, and Unicode sequences while preserving invalid prose-style escapes such as \d.

What was not tested: live cron scheduling, live Telegram delivery, and real provider credentials. The proof targets the smallest representative runtime boundary for the reported failure: the embedded-runner malformed tool-call argument repair wrapper.

Root Cause

The current repair path first tries JSON.parse(raw) and then uses extractBalancedJsonPrefix(raw) plus JSON.parse(extracted.json). Both are ASCII-quote JSON paths. Provider output that uses Unicode smart quotes as structural string delimiters is visually JSON-like but invalid JSON, so the wrapper could fail to recover edit/write args and downstream status reporting could preserve the parse error even after delivery.

Dependency contract

Node/ECMAScript JSON.parse requires JSON object keys and string values to use ASCII double quotes. The proof shows Node v22.22.0 rejecting {“path”:“notes/报告.md”} with SyntaxError.

The internal repair contract remains: valid JSON is preserved first, existing balanced-prefix/trailing-junk recovery is preserved next, and this patch only adds a local smart-quote fallback for the existing malformed tool-call repair gate.

Regression Test Plan

src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts covers smart-quoted edit args with CJK/Markdown/inner smart quotes, ASCII-delimited content with smart quotes, same-direction smart quote delimiters, command/workdir args, and member-looking prose that must not synthesize extra args.
src/agents/embedded-agent-runner/run/attempt.test.ts keeps the broader embedded-runner coverage green.

Security Impact

No credential, auth, sandbox, workflow, dependency, lockfile, or network behavior changes. The parser is bounded to the existing malformed tool-call argument repair gate and synthetic recovery of streamed arguments.

Human Verification

I reviewed the narrowed diff after removing the shared-helper change. The local mini-guide for the affected architecture and proof is .artifacts/issue-67488-smart-quote-repair-guide.html.

CODEOWNERS / owner review

Checked .github/CODEOWNERS; the touched files do not match a special owner-restricted pattern. Expect normal maintainer review for src/agents/embedded-agent-runner/run/*.

Changelog

No contributor CHANGELOG.md edit. Maintainers can add a release note during landing if needed.

Review conversations

Existing ClawSweeper review on the first draft called out shared-helper exposure through src/shared/balanced-json.ts. This revision removes that shared-helper change and keeps the repair local to the embedded-runner wrapper. A later ClawSweeper review found that exact smart-quoted argument objects without preamble or trailing junk were still rejected; this revision now repairs that case and adds a focused regression. A May 28 ClawSweeper review then found that accepted smart-quoted values preserved JSON escapes literally; this revision decodes JSON string escapes and adds a regression for newline, quote, backslash, Unicode, and invalid-escape preservation. A later May 28 ClawSweeper review found the current nested edit-array schema was not repaired; this revision now repairs smart-quoted edits: [{ oldText, newText }] arrays and adds a focused regression.

Local codex review --base origin/main could not complete after the revision because the account hit the usage limit:

ERROR: You've hit your usage limit. Visit https://chatgpt.com/codex/settings/usage to purchase more credits or try again at 5:31 PM.
Review was interrupted. Please re-run /review and wait for it to complete.

Risks

Smart-quote repair is heuristic because malformed JSON has no complete formal grammar.
The fallback intentionally focuses on top-level tool-argument objects and common string-heavy tool args, so unusual malformed smart-quoted nested structures may still fail closed.

Behavior tradeoffs

Freeform text fields such as content, text, message, oldText, and newText keep JSON-looking prose inside the string instead of synthesizing extra top-level args.
For edit-style replacements, oldText may close before its expected newText successor.
Existing valid JSON and existing ASCII balanced-prefix/trailing-junk repair behavior continue to run before the smart-quote fallback.

Scope boundaries

Does not change cron state accounting, delivery status, or error persistence.
Does not change src/shared/balanced-json.ts or CLI-output JSON extraction.
Does not expand repair to direct openai-responses transports.
Does not add dependencies or change package metadata.

Validation

node scripts/run-vitest.mjs src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts src/agents/embedded-agent-runner/run/attempt.test.ts
3 files passed, 261 tests passed, Vitest reported 8.81s after rebasing onto upstream main c2c29588f4

node scripts/run-oxlint.mjs src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts
passed

git diff --check
passed

node --import tsx --input-type=module <synthetic stream repair proof>
passed; see Real behavior proof

pnpm check:changed was not rerun after the last narrow parser follow-up; the branch was rebased onto upstream main c2c29588f4 to avoid the unrelated stale-base check-prod-types failure in src/secrets/path-utils.ts.

clawsweeper · 2026-05-25T19:11:39Z

Codex review: needs maintainer review before merge. Reviewed May 28, 2026, 10:54 PM ET / 02:54 UTC.

Summary
The PR adds smart-quote-aware malformed tool-call argument repair inside the embedded runner stream wrapper and expands focused regression coverage.

PR surface: Source +483, Tests +274. Total +757 across 2 files.

Reproducibility: yes. at the parser boundary: current main only uses ASCII JSON parsing paths, and Node rejects structural smart quotes with SyntaxError. I did not run the full live cron or Telegram delivery flow.

Review metrics: none identified.

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

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

Rank-up moves:

Let exact-head CI or equivalent maintainer validation settle after the latest hardening commit.
[P2] Have maintainers explicitly accept the bounded smart-quote repair scope before merge.

Risk before merge

[P1] The smart-quote parser intentionally recovers malformed provider output, so unusual malformed nested or freeform shapes may still fail closed or be interpreted differently than the model intended.
[P1] The GitHub context reports the PR as mergeable but unstable after the latest force-push, so merge should wait for exact-head checks or maintainer validation.

Maintainer options:

Accept the bounded parser heuristic (recommended)
Maintainers can land this once exact-head checks pass if they accept that the fallback only targets known malformed smart-quote tool-argument shapes.
Request one more focused hardening pass
If maintainers want more confidence, ask for specific additional malformed-shape tests rather than broadening the parser into a shared JSON helper.
Pause for a broader parser design
If the desired direction is a general malformed-JSON recovery layer, pause this PR and replace it with an owner-approved design for that wider contract.

Next step before merge

[P2] Human review should decide whether to accept the bounded parser heuristic after current-head checks; there is no narrow automated repair indicated.

Security
Cleared: The diff changes local parser/test code only and does not touch credentials, auth, workflows, dependencies, lockfiles, package metadata, or network behavior.

Review details

Best possible solution:

Land the local repair after maintainers accept the bounded heuristic and exact-head validation is green; track any future malformed shapes as focused follow-ups.

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

Yes, at the parser boundary: current main only uses ASCII JSON parsing paths, and Node rejects structural smart quotes with SyntaxError. I did not run the full live cron or Telegram delivery flow.

Is this the best way to solve the issue?

Yes, the proposed fix is the narrow maintainable path because it stays inside the existing malformed tool-call argument wrapper, preserves valid JSON first, and avoids shared helper or config surface changes. The remaining question is maintainer acceptance of the bounded heuristic scope.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against c8cc010e092c.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes terminal output from Node v22 loading the TypeScript source with tsx and exercising the actual stream wrapper on representative smart-quoted streamed tool calls.

Label justifications:

P2: The PR fixes a bounded agent-runtime malformed tool-call argument bug linked to cron/session status without evidence of data loss or an urgent outage.
merge-risk: 🚨 other: The diff adds heuristic recovery for malformed provider output, and unusual malformed shapes cannot be fully proven by ordinary CI.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🦞 diamond lobster and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (terminal): The PR body includes terminal output from Node v22 loading the TypeScript source with tsx and exercising the actual stream wrapper on representative smart-quoted streamed tool calls.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes terminal output from Node v22 loading the TypeScript source with tsx and exercising the actual stream wrapper on representative smart-quoted streamed tool calls.

Evidence reviewed

PR surface:

Source +483, Tests +274. Total +757 across 2 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	1	514	31	+483
Tests	1	274	0	+274
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	2	788	31	+757

Acceptance criteria:

[P1] node scripts/run-vitest.mjs src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts src/agents/embedded-agent-runner/run/attempt.test.ts.
[P1] node scripts/run-oxlint.mjs src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts.
[P1] git diff --check.

What I checked:

Repository policy read: Root and scoped agent policies were read and applied; the touched embedded-runner path favors focused helper tests for narrow runner behavior and exact source/proof review. (AGENTS.md:1, c8cc010e092c)
Scoped embedded-runner policy read: The scoped guide for this subtree recommends focused helper tests instead of full-runner coverage for isolated runner helper behavior, which matches the PR's test shape. (src/agents/embedded-agent-runner/run/AGENTS.md:1, c8cc010e092c)
Current-main limitation: Current main's repair path preserves valid JSON first, then only attempts balanced-prefix JSON parsing; structural smart quotes are not recoverable through those ASCII JSON paths. (src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts:58, c8cc010e092c)
PR implementation: The PR adds a smart-quote fallback that finds the object, validates the leading prefix/suffix, parses smart-quoted keys and values, and uses the streamed tool name as parsing context. (src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts:507, 75359f3bc4c8)
Runtime boundary: The existing embedded attempt runner applies this wrapper only for the malformed-argument repair gate selected by provider and model API, so the PR stays local to that stream boundary. (src/agents/embedded-agent-runner/run/attempt.ts:2573, c8cc010e092c)
Regression coverage: The PR covers smart-quoted edit args, current edits array payloads, command/workdir args, exact prefixless objects, JSON escape decoding, and guards against synthesizing member-looking prose. (src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts:272, 75359f3bc4c8)

Likely related people:

steipete: Peter Steinberger created the current extracted repair file on main, carried several recent embedded-runner repair/refactor commits, and authored the latest hardening commit on this PR head. (role: recent area contributor; confidence: high; commits: 10a3417bd36a, 8879ed153d27, 17bd5f1dd21e; files: src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts, src/agents/embedded-agent-runner/run/attempt.ts)
Vignesh Natarajan: The malformed tool-call JSON repair behavior appears to date to the March 2026 repair commit on the predecessor path. (role: introduced behavior; confidence: medium; commits: a2e4707cfe4c; files: src/agents/pi-embedded-runner/run/attempt.tool-call-argument-repair.ts)
yuanchao: A later current-main repair commit adjusted preservation of valid Anthropic-compatible toolCall arguments in the same malformed-args repair path. (role: adjacent contributor; confidence: medium; commits: ec7f19e2ef7a; files: src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.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 · 2026-05-25T19:20:01Z

ClawSweeper PR egg: 🔥 warming; proof passed, review follow-up or readiness checks remain. Hatch with @clawsweeper hatch when eligible.

Rules and details

Hatchability:

Merged PRs are hatchable.
Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

About:

Eggs appear after real-behavior proof passes. They are collectible flavor only.
Review momentum changes the shell state: follow-up work warms it, re-review makes it wobble, and a clean final review lets it hatch.
The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

steipete · 2026-05-29T03:15:15Z

Maintainer fixup pushed and verified on head bb3d4d7ef098b4b72ca2bef501c35dea448bd210.

Verification:

node scripts/run-vitest.mjs src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts src/agents/embedded-agent-runner/run/attempt.test.ts - 3 files, 268 tests passed
node scripts/run-oxlint.mjs src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts
node scripts/run-oxlint.mjs src/agents/models-config.uses-first-github-copilot-profile-env-tokens.test.ts src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.ts src/agents/embedded-agent-runner/run/attempt.tool-call-argument-repair.test.ts
pnpm check:test-types
$autoreview clean after the final parser fixup
GitHub CI for bb3d4d7ef098b4b72ca2bef501c35dea448bd210 is green

Fixup notes:

Scoped read-only smart-quote successor parsing to the structured tool name, with prefixless, case-varied, mismatched-prefix, and inherited-name regressions.
Removed a duplicate pluginCatalogWrites expectation that was blocking current-main test-types/lint after rebasing.

Thanks @ferminquant.

…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

openclaw-barnacle Bot added agents Agent runtime and tooling size: L proof: supplied External PR includes structured after-fix real behavior proof. labels May 25, 2026

ferminquant force-pushed the codex/67488-smart-quote-tool-args branch from 46fb2ee to 20091cd Compare May 25, 2026 20:50

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 25, 2026

ferminquant marked this pull request as ready for review May 26, 2026 01:24

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 26, 2026

ferminquant force-pushed the codex/67488-smart-quote-tool-args branch from 1bd79e6 to 0d9d4ee Compare May 28, 2026 11:18

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 28, 2026

ferminquant force-pushed the codex/67488-smart-quote-tool-args branch from 0d9d4ee to cde46bd Compare May 28, 2026 11:21

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 28, 2026

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 28, 2026

ferminquant force-pushed the codex/67488-smart-quote-tool-args branch from 4301233 to 19d855b Compare May 28, 2026 17:13

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 28, 2026

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 28, 2026

steipete force-pushed the codex/67488-smart-quote-tool-args branch from 19d855b to 75359f3 Compare May 29, 2026 02:47

steipete added a commit to ferminquant/openclaw that referenced this pull request May 29, 2026

fix: harden smart-quoted argument repair (openclaw#86611)

75359f3

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 29, 2026

clawsweeper Bot added the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 29, 2026

steipete added a commit to ferminquant/openclaw that referenced this pull request May 29, 2026

fix: harden smart-quoted argument repair (openclaw#86611)

cc3f145

steipete force-pushed the codex/67488-smart-quote-tool-args branch from 75359f3 to cc3f145 Compare May 29, 2026 03:00

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label May 29, 2026

ferminquant and others added 6 commits May 29, 2026 04:03

fix(agents): repair smart-quoted tool args

f743886

fix(agents): handle exact smart-quoted args

45dd2d7

fix(agents): decode smart-quoted arg escapes

87b09ea

fix(agents): satisfy smart quote lint

d19490b

fix(agents): repair smart-quoted edit arrays

c657506

fix: harden smart-quoted argument repair (openclaw#86611)

ccb8a91

steipete force-pushed the codex/67488-smart-quote-tool-args branch from cc3f145 to ccb8a91 Compare May 29, 2026 03:06

test: remove duplicate catalog write expectation

bb3d4d7

steipete merged commit 5a84869 into openclaw:main May 29, 2026
99 checks passed

steipete added a commit that referenced this pull request May 29, 2026

fix: harden smart-quoted argument repair (#86611)

bca6a91

RomneyDa added dependency-guard-backfill and removed dependency-guard-backfill labels May 29, 2026

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 29, 2026

fix: harden smart-quoted argument repair (openclaw#86611)

42e949c

ferminquant deleted the codex/67488-smart-quote-tool-args branch May 29, 2026 14:05

SYU8384 pushed a commit to SYU8384/openclaw that referenced this pull request Jun 3, 2026

fix: harden smart-quoted argument repair (openclaw#86611)

96741d5

sablehead pushed a commit to sablehead/openclaw that referenced this pull request Jun 10, 2026

fix: harden smart-quoted argument repair (openclaw#86611)

41da59c

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Fix smart-quoted tool call argument repair#86611

Fix smart-quoted tool call argument repair#86611
steipete merged 7 commits into
openclaw:mainfrom
ferminquant:codex/67488-smart-quote-tool-args

ferminquant commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

steipete commented May 29, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

Conversation

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

Uh oh!

Summary

AI assistance disclosure

Real behavior proof

Root Cause

Dependency contract

Regression Test Plan

Security Impact

Human Verification

CODEOWNERS / owner review

Changelog

Review conversations

Risks

Behavior tradeoffs

Scope boundaries

Validation

Uh oh!

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

Uh oh!

Uh oh!

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

Uh oh!

Uh oh!

steipete commented May 29, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

ferminquant commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading