fix(agents): preserve signed thinking payloads by joshavant · Pull Request #87493 · openclaw/openclaw

joshavant · 2026-05-28T03:40:56Z

Summary

Preserve provider-owned signed Anthropic thinking text byte-for-byte on transport ingest and replay.
Preserve signed Bedrock Anthropic reasoningText byte-for-byte on replay.
Keep surrogate sanitation for unsigned fallback text and synthetic reasoning_content blocks.

Verification

node scripts/run-vitest.mjs src/agents/anthropic-transport-stream.test.ts src/llm/providers/anthropic.test.ts extensions/amazon-bedrock/stream.runtime.test.ts - 4 files passed, 91 tests passed.
pnpm format:check -- src/agents/anthropic-transport-stream.ts src/agents/anthropic-transport-stream.test.ts src/llm/providers/anthropic.ts src/llm/providers/anthropic.test.ts extensions/amazon-bedrock/stream.runtime.ts extensions/amazon-bedrock/stream.runtime.test.ts
node scripts/run-oxlint.mjs src/agents/anthropic-transport-stream.ts src/agents/anthropic-transport-stream.test.ts src/llm/providers/anthropic.ts src/llm/providers/anthropic.test.ts extensions/amazon-bedrock/stream.runtime.ts extensions/amazon-bedrock/stream.runtime.test.ts
git diff --check HEAD~1..HEAD
.agents/skills/autoreview/scripts/autoreview --mode local --prompt "Review this OpenClaw fix for issue #87459 after the synthetic reasoning_content correction. Focus on provider-owned signed reasoning/thinking payload immutability, whether unsigned/synthetic sanitizer behavior is preserved, and whether sibling Anthropic/Bedrock surfaces are covered. Do not request broader refactors." - clean, no accepted/actionable findings.
AWS Crabbox run_ce07acf3942c, provider aws, lease cbx_d4ae60080f6a, PR head fc08985ad977f72c0fd525a1751f73e45259c85c - live Anthropic signed-thinking replay plus focused Linux regression tests passed.

Real behavior proof

Behavior addressed: OpenClaw no longer mutates provider-owned signed Anthropic/Bedrock thinking payload text while retaining the original provider signature.

Real environment tested: AWS Crabbox Linux, provider aws, lease cbx_d4ae60080f6a, run run_ce07acf3942c, PR head fc08985ad977f72c0fd525a1751f73e45259c85c, live Anthropic Claude Sonnet 4.6 API credentials loaded from a local /private/tmp env profile without printing secrets.

Exact steps or command run after this patch: node scripts/crabbox-wrapper.mjs run --provider aws --env-from-profile /private/tmp/openclaw-87459-anthropic.env --allow-env ANTHROPIC_API_KEY --allow-env ANTHROPIC_MODEL --idle-timeout 90m --ttl 240m --timing-json --script /private/tmp/openclaw-87459-live-proof.sh

Evidence after fix: The live portion requested a thinking-enabled Anthropic tool-use turn, received a signed thinking block plus tool_use, replayed the assistant content exactly with a tool_result, and received a successful second response. The same live script then intentionally corrupted the thinking signature and Anthropic rejected it, proving the replay path is signature-sensitive. The Linux regression portion then ran the focused tests covering Anthropic transport ingest, Anthropic transport replay, legacy Anthropic provider replay, Bedrock signed reasoning replay, and sanitizer retention for unsigned/synthetic paths.

Observed result after fix: Live first turn returned stopReason: tool_use with signed thinking (signatureLen: 424) and a tool call; exact live replay returned stopReason: end_turn; corrupted-signature replay was rejected; focused Linux regression tests passed with 4 files and 91 tests.

What was not tested: The original reporter's exact visible-thinking mutation was not reproduced live because current Anthropic behavior did not emit the reported sanitizer-sensitive payload in prior investigation. This proof validates the fixed signed-replay behavior live and validates the sanitizer-sensitive boundary synthetically in focused regression tests.

clawsweeper · 2026-05-28T03:42:35Z

Codex review: needs maintainer review before merge. Reviewed May 28, 2026, 12:45 AM ET / 04:45 UTC.

Summary
The PR changes Anthropic transport, legacy Anthropic provider, and Amazon Bedrock replay conversion so provider-signed thinking/reasoning text is preserved byte-for-byte while unsigned and synthetic reasoning paths remain sanitized.

PR surface: Source +5, Tests +209. Total +214 across 6 files.

Reproducibility: yes. as a source-level reproduction: current main mutates signed thinking/reasoning text before replay while retaining the original signature. The exact live reporter payload was not reproduced, but the PR adds focused tests for the sanitizer-sensitive boundary and live proof for signature-sensitive replay.

Review metrics: none identified.

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

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

Risk before merge

[P1] The live proof validates exact signed replay and corrupted-signature rejection, but the original reporter's exact sanitizer-sensitive payload was not reproduced live; focused source tests cover that remaining boundary.

Maintainer options:

Decide the mitigation before merge
Land this narrow provider-signed payload preservation fix after maintainer review and required checks, then close the linked bug as fixed by this PR.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge

[P2] No automated code repair is needed; the remaining action is maintainer review for a protected-label PR plus normal CI and mergeability gating.

Security
Cleared: The diff only changes provider message conversion logic and tests; it does not alter dependencies, workflows, secrets handling, build scripts, or package metadata.

Review details

Best possible solution:

Land this narrow provider-signed payload preservation fix after maintainer review and required checks, then close the linked bug as fixed by this PR.

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

Yes, as a source-level reproduction: current main mutates signed thinking/reasoning text before replay while retaining the original signature. The exact live reporter payload was not reproduced, but the PR adds focused tests for the sanitizer-sensitive boundary and live proof for signature-sensitive replay.

Is this the best way to solve the issue?

Yes. The patch is the narrow maintainable fix because it preserves provider-owned signed payloads on the Anthropic and Bedrock paths while keeping sanitation for unsigned fallback text and synthetic reasoning_content blocks.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 51d7f3c14382.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix AWS Crabbox live output showing Anthropic signed-thinking replay succeeds, corrupted-signature replay is rejected, and focused Linux regression tests pass.
add rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes after-fix AWS Crabbox live output showing Anthropic signed-thinking replay succeeds, corrupted-signature replay is rejected, and focused Linux regression tests pass.
remove rating: 🦪 silver shellfish: Current PR rating is rating: 🦞 diamond lobster, so this older rating label is no longer current.
remove status: 📣 needs proof: Current PR status label is status: 👀 ready for maintainer look.

Label justifications:

P1: The linked bug can break Anthropic/Bedrock multi-turn sessions when signed thinking is replayed after mutation.
rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The PR body includes after-fix AWS Crabbox live output showing Anthropic signed-thinking replay succeeds, corrupted-signature replay is rejected, and focused Linux regression tests pass.
proof: sufficient: Contributor real behavior proof is sufficient. The PR body includes after-fix AWS Crabbox live output showing Anthropic signed-thinking replay succeeds, corrupted-signature replay is rejected, and focused Linux regression tests pass.

Evidence reviewed

PR surface:

Source +5, Tests +209. Total +214 across 6 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	3	11	6	+5
Tests	3	223	14	+209
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	6	234	20	+214

Acceptance criteria:

[P1] node scripts/run-vitest.mjs src/agents/anthropic-transport-stream.test.ts src/llm/providers/anthropic.test.ts extensions/amazon-bedrock/stream.runtime.test.ts.
[P1] pnpm format:check -- src/agents/anthropic-transport-stream.ts src/agents/anthropic-transport-stream.test.ts src/llm/providers/anthropic.ts src/llm/providers/anthropic.test.ts extensions/amazon-bedrock/stream.runtime.ts extensions/amazon-bedrock/stream.runtime.test.ts.
[P1] node scripts/run-oxlint.mjs src/agents/anthropic-transport-stream.ts src/agents/anthropic-transport-stream.test.ts src/llm/providers/anthropic.ts src/llm/providers/anthropic.test.ts extensions/amazon-bedrock/stream.runtime.ts extensions/amazon-bedrock/stream.runtime.test.ts.

What I checked:

Current-main Anthropic transport bug surface: Current main sanitizes a signed thinking block before replay, which can change the text while keeping the original signature. (src/agents/anthropic-transport-stream.ts:383, 51d7f3c14382)
Current-main legacy Anthropic provider bug surface: The legacy Anthropic provider also sanitizes signed thinking text before replaying it with the original signature. (src/llm/providers/anthropic.ts:1124, 51d7f3c14382)
Current-main Bedrock sibling bug surface: The Bedrock Converse replay path sanitizes signed reasoningText text while retaining the signature. (extensions/amazon-bedrock/stream.runtime.ts:665, 51d7f3c14382)
PR preserves Anthropic signed replay while keeping synthetic sanitation: The PR only skips sanitation for provider-owned signatures and still sanitizes the synthetic reasoning_content marker. (src/agents/anthropic-transport-stream.ts:383, fc08985ad977)
PR preserves Anthropic signed ingest: The PR stores provider-returned thinking block text without sanitizer mutation on stream ingest. (src/agents/anthropic-transport-stream.ts:1125, fc08985ad977)
PR covers Bedrock signed reasoning replay: The Bedrock path now sends the signed reasoningText text unchanged when the model supports thinking signatures. (extensions/amazon-bedrock/stream.runtime.ts:665, fc08985ad977)

Likely related people:

steipete: Blame and -S history tie the current sanitizer-on-signed-thinking behavior in all three central files to commit da27904. (role: recent area contributor; confidence: high; commits: da279041aba2; files: src/agents/anthropic-transport-stream.ts, src/llm/providers/anthropic.ts, extensions/amazon-bedrock/stream.runtime.ts)
vincentkoc: Recent history shows the Anthropic transport runtime and shared transport helpers were introduced or refactored in commits by Vincent Koc before the current sanitizer behavior was carried forward. (role: feature introducer and adjacent owner; confidence: medium; commits: ea4265a82063, d8458a1481e9, 067496b12934; files: src/agents/anthropic-transport-stream.ts, src/llm/providers/anthropic.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 · 2026-05-28T03:48:47Z

ClawSweeper PR egg: ✨ hatched 🥚 common Neon Test Hopper. Rarity: 🥚 common. Trait: hums during re-review.

Details

Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Neon Test Hopper in ClawSweeper.
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.

joshavant · 2026-05-28T04:38:38Z

@clawsweeper re-review

clawsweeper · 2026-05-28T04:38:40Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/26555029690
Updated: 2026-05-28T04:46:20.651Z

…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(agents): preserve signed thinking payloads

fc08985

openclaw-barnacle Bot added agents Agent runtime and tooling extensions: amazon-bedrock size: M maintainer Maintainer-authored PR labels May 28, 2026

joshavant merged commit 4a45a25 into main May 28, 2026
204 of 222 checks passed

joshavant deleted the fix/87459-preserve-signed-thinking branch May 28, 2026 04:57

This was referenced May 28, 2026

Anthropic thinking blocks rejected after sanitizeTransportPayloadText() mutates signed content #87459

Closed

fix(transport): preserve Anthropic-signed thinking block content #87460

Closed

github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request May 28, 2026

fix(agents): preserve signed thinking payloads (openclaw#87493)

7053b73

github-actions Bot mentioned this pull request May 28, 2026

📡 Upstream Digest — 2026-05-28 07:50 UTC curtismercier/openclaw-mods#962

Open

clawsweeper Bot mentioned this pull request May 28, 2026

Bug: anthropic-transport-stream overwrites signature_delta instead of appending, causing permanent session corruption #87574

Closed

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

fix(agents): preserve signed thinking payloads (openclaw#87493)

b42a730

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

fix(agents): preserve signed thinking payloads (openclaw#87493)

576283a

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(agents): preserve signed thinking payloads#87493

fix(agents): preserve signed thinking payloads#87493
joshavant merged 1 commit into
mainfrom
fix/87459-preserve-signed-thinking

joshavant commented May 28, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

joshavant commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

joshavant commented May 28, 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 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

joshavant commented May 28, 2026

Uh oh!

clawsweeper Bot commented May 28, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

joshavant commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading

clawsweeper Bot commented May 28, 2026 •

edited

Loading