fix(gateway): reject unknown OpenAI agent selectors by zhangguiping-xydt · Pull Request #92510 · openclaw/openclaw

zhangguiping-xydt · 2026-06-12T18:34:25Z

Summary

Fixes explicit OpenAI-compatible agent selector handling for Gateway runs well-formed-but-unknown agent slug under agents.defaults instead of 4xx (no roster validation in resolveAgentIdForRequest; x-openclaw-agent-id header never roster-validated) #92504.
Explicit selector strings now fail closed when the requested agent is not in the configured roster, instead of creating phantom agent:<id>: request/session state.
Default routing stays compatible for clients that omit an explicit selector or use the default alias.
Review focus: shared selector validation in http-utils, plus the HTTP 400 mapping in chat completions, responses, and embeddings.

Linked context

Which issue does this close?

Closes #92504

Which issues, PRs, or discussions are related?

Related #92504

Was this requested by a maintainer or owner?

No direct maintainer request; this addresses the linked bug report.

Real behavior proof (required for external PRs)

Behavior or issue addressed: OpenAI-compatible gateway requests that explicitly target an unknown agent now receive a structured request error instead of continuing with phantom agent-scoped state.
Real environment tested: Local OpenClaw checkout on this PR branch with a separate openclaw gateway process, token auth, a configured agent roster (main, beta), and a local mock OpenAI-compatible provider. The matrix used real HTTP requests against POST /v1/chat/completions.

Exact steps or command run after this patch:

node --import tsx src/entry.ts gateway --port <loopback-port> --bind loopback --auth token --token <redacted>

POST /v1/chat/completions with:
- model=openclaw/missing-agent
- model=openclaw plus x-openclaw-agent-id=missing-agent
- model=openclaw:missing-agent
- model=agent:missing-agent
- model=openclaw/beta
- model=openclaw/default
- omitted model

node scripts/run-vitest.mjs src/gateway/http-utils.request-context.test.ts src/gateway/openai-http.test.ts src/gateway/openresponses-http.test.ts src/gateway/embeddings-http.test.ts && git diff --check

Evidence after fix (screenshot, recording, terminal capture, console output, redacted runtime log, linked artifact, or copied live output):

OpenClaw live selector matrix proof
Setup: separate `openclaw gateway` process, token auth, configured agents = main,beta, local mock OpenAI-compatible provider.
Gateway: http://127.0.0.1:<redacted-loopback-port>
unknown model selector model=openclaw/missing-agent => HTTP 400 type=invalid_request_error message="Unknown agent 'missing-agent'."
unknown header selector x-openclaw-agent-id=missing-agent => HTTP 400 type=invalid_request_error message="Unknown agent 'missing-agent'."
unknown colon selector model=openclaw:missing-agent => HTTP 400 type=invalid_request_error message="Unknown agent 'missing-agent'."
unknown agent alias selector model=agent:missing-agent => HTTP 400 type=invalid_request_error message="Unknown agent 'missing-agent'."
configured model selector model=openclaw/beta => HTTP 200 type=ok
default selector model=openclaw/default => HTTP 200 type=ok
omitted selector no model => HTTP 200 type=ok
Result: PASS

Focused regression validation also passed:

Test Files 13 passed (13)
Tests 227 passed (227)
[test] passed 1 Vitest shard in 95.00s

Observed result after fix: Unknown explicit agent selectors return 400 invalid_request_error; omitted/default selectors and configured agents remain valid.
What was not tested: No browser UI or mobile app flow was tested; this change is limited to OpenAI-compatible gateway HTTP routing.
Proof limitations or environment constraints: The live proof used loopback networking and a local mock OpenAI-compatible provider to keep the configured gateway deterministic; no external model provider was contacted.
Before evidence (optional but encouraged): The new regression test was written first and failed before the fix because resolveGatewayRequestContext accepted explicit unknown agent IDs instead of rejecting them.

Tests and validation

Which commands did you run?

node scripts/run-vitest.mjs src/gateway/http-utils.request-context.test.ts src/gateway/openai-http.test.ts src/gateway/openresponses-http.test.ts src/gateway/embeddings-http.test.ts && git diff --check

What regression coverage was added or updated?

Shared request-context resolver coverage for explicit unknown header/model agent selectors.
Chat completions HTTP coverage for unknown selector 400 responses and no agent dispatch.
Responses HTTP coverage for unknown selector 400 responses in both resolver paths.
Embeddings HTTP coverage for unknown selector 400 responses while preserving configured-agent behavior.

What failed before this fix, if known?

The shared request-context regression failed before the production change because resolveGatewayRequestContext accepted explicit unknown agent IDs instead of rejecting them.

If no test was added, why not?

Regression tests were added.

Risk checklist

Did user-visible behavior change? (Yes/No)

Yes. Explicit unknown agent selectors now receive HTTP 400 instead of continuing through gateway routing.

Did config, environment, or migration behavior change? (Yes/No)

No. Existing configured agent rosters and default selection semantics are unchanged.

Did security, auth, secrets, network, or tool execution behavior change? (Yes/No)

No. The change is request validation for already-parsed gateway selector inputs.

What is the highest-risk area?

Compatibility for integrations that accidentally send an unknown explicit agent ID and previously relied on the buggy fallback behavior.

How is that risk mitigated?

The rejection is limited to explicit selectors that do not exist in the configured roster. Omitted/default routing and configured agent IDs continue to work, and all three OpenAI-compatible endpoints now return the same structured request error for the invalid selector case.

Current review state

What is the next action?

Waiting for CI and ClawSweeper to re-check the updated live configured-gateway proof.

What is still waiting on author, maintainer, CI, or external proof?

CI/proof automation needs to rerun after this PR body update.

Which bot or reviewer comments were addressed?

Addressed ClawSweeper's request to add redacted terminal output from a separately started configured gateway showing unknown selectors fail and configured/default/omitted selectors succeed.

clawsweeper · 2026-06-12T18:36:28Z

Codex review: needs maintainer review before merge. Reviewed June 12, 2026, 3:23 PM ET / 19:23 UTC.

Summary
The PR validates explicit OpenAI-compatible agent selectors against the effective configured roster before state creation and returns structured HTTP 400 errors across chat completions, responses, and embeddings.

PR surface: Source +72, Tests +109. Total +181 across 8 files.

Reproducibility: yes. from source with high confidence. Current main accepts explicit sanitized IDs without roster membership validation, and the linked report supplies concrete model and header request forms; I did not independently run the gateway.

Review metrics: 1 noteworthy metric.

Fallback contract: 1 implicit fallback removed. Unknown explicit selectors stop producing successful default-agent execution across three public OpenAI-compatible endpoint families.

Stored data model
Persistent data-model change detected: unknown-data-model-change: src/gateway/embeddings-http.test.ts, vector/embedding metadata: src/gateway/embeddings-http.test.ts, vector/embedding metadata: src/gateway/embeddings-http.ts. Confirm migration or upgrade compatibility proof before merge.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
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:

[P1] Obtain maintainer acceptance of the fail-closed compatibility change.

Risk before merge

[P1] Existing integrations that send a well-formed but unconfigured explicit agent ID will change from successful default-agent execution to a client-visible HTTP 400; maintainers must explicitly accept that upgrade behavior.

Maintainer options:

Accept strict explicit selectors (recommended)
Merge after a maintainer explicitly accepts HTTP 400 as the corrected contract for unknown explicit agent IDs.
Preserve fallback by policy
Pause the PR if unknown-selector fallback is considered a shipped contract and first define an explicit strict-mode or upgrade policy.

Next step before merge

The patch and proof are technically ready for normal review, but only maintainers can accept the intentional upgrade-visible removal of unknown-selector fallback.

Security
Cleared: The diff only narrows local selector validation and adds tests; it does not change authentication, authorization, secrets, permissions, dependencies, artifact downloads, or supply-chain execution.

Review details

Best possible solution:

Land the centralized typed rejection with identical endpoint error mapping while preserving configured, default-alias, omitted-selector, and implicit-default-agent routing exactly as covered by the branch.

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

Yes, from source with high confidence. Current main accepts explicit sanitized IDs without roster membership validation, and the linked report supplies concrete model and header request forms; I did not independently run the gateway.

Is this the best way to solve the issue?

Yes for the implementation boundary. Shared typed validation before session or provider state is derived is narrower and less drift-prone than endpoint-specific checks, and the effective-roster helper preserves implicit-default behavior; only compatibility acceptance remains.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against e3a6da0f5181.

Label changes

Label changes:

add proof: sufficient: Contributor real behavior proof is sufficient. The updated PR body contains redacted after-fix HTTP output from a separately started configured gateway and directly demonstrates invalid selectors plus configured, default, and omitted controls.
add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
add status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The updated PR body contains redacted after-fix HTTP output from a separately started configured gateway and directly demonstrates invalid selectors plus configured, default, and omitted controls.
remove rating: 🦪 silver shellfish: Current PR rating is rating: 🐚 platinum hermit, 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 underlying bug can silently execute a request under the wrong agent persona and create misleading successful responses and agent-scoped state.
merge-risk: 🚨 compatibility: Merging intentionally changes previously successful unknown-selector requests into structured HTTP 400 failures.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🐚 platinum hermit and patch quality is 🐚 platinum hermit.
status: 👀 ready for maintainer look: ClawSweeper has no concrete contributor-facing blocker left for this PR. Sufficient (live_output): The updated PR body contains redacted after-fix HTTP output from a separately started configured gateway and directly demonstrates invalid selectors plus configured, default, and omitted controls.
proof: sufficient: Contributor real behavior proof is sufficient. The updated PR body contains redacted after-fix HTTP output from a separately started configured gateway and directly demonstrates invalid selectors plus configured, default, and omitted controls.

Evidence reviewed

PR surface:

Source +72, Tests +109. Total +181 across 8 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	4	92	20	+72
Tests	4	126	17	+109
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	8	218	37	+181

What I checked:

Current-main bug path: Current main returns sanitized header selectors directly and accepts parsed model selectors without checking configured-roster membership before agent-scoped session or provider state is derived. (src/gateway/http-utils.ts:135, e3a6da0f5181)
Shared validation boundary: The branch adds a typed unknown-agent error and checks explicit header and model selectors in the shared resolver before resolveGatewayRequestContext constructs session state. (src/gateway/http-utils.ts:159, 0bd251515ff2)
Effective roster compatibility: listAgentIds returns configured normalized IDs and falls back to the implicit default agent when no agent list exists, so the membership check preserves ordinary implicit-default installations. (src/agents/agent-scope-config.ts:73, e3a6da0f5181)
Endpoint coverage: The branch maps the typed error to the same 400 invalid_request_error shape in chat completions, Responses—including both resolver paths—and embeddings. (src/gateway/openresponses-http.ts:478, 0bd251515ff2)
Regression coverage: Focused tests cover unknown header and model selectors, prevent agent dispatch, and retain configured-agent behavior across the three endpoint families. (src/gateway/http-utils.request-context.test.ts:57, 0bd251515ff2)
Real behavior proof: The updated PR body supplies redacted HTTP results from a separately started configured gateway: four unknown selector forms return 400, while configured, default, and omitted controls return 200. (0bd251515ff2)

Likely related people:

Shakker: Git blame ties the current shared selector resolver and surrounding OpenAI-compatible gateway implementation to commit 0fc2faa. (role: introduced current surface; confidence: medium; commits: 0fc2faa0f48a; files: src/gateway/http-utils.ts, src/gateway/openai-http.ts, src/gateway/openresponses-http.ts)
steipete: File history shows the largest contribution count across the central OpenAI-compatible gateway files, making this a strong routing candidate for compatibility ownership. (role: recent area contributor; confidence: medium; files: src/gateway/http-utils.ts, src/gateway/openai-http.ts, src/gateway/openresponses-http.ts)
spence27: Authored the earlier closed attempt at the same unknown-agent rejection behavior, including tests for the shared resolver and two gateway endpoints. (role: prior fix contributor; confidence: medium; commits: 3eec49784dc7; files: src/gateway/http-utils.ts, src/gateway/openai-http.ts, src/gateway/openresponses-http.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.

zhangguiping-xydt · 2026-06-12T18:48:31Z

@clawsweeper re-review

clawsweeper · 2026-06-12T18:48:34Z

🦞🧹
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/27436143838
Updated: 2026-06-12T18:53:55.637Z

Validate explicit OpenAI-compatible agent selectors against the configured roster so malformed integrations fail closed instead of creating phantom agent sessions. Co-Authored-By: Claude Opus 4.7 <[email protected]>

vincentkoc

No blocking findings.

What changed: OpenAI-compatible gateway requests now reject explicit unknown or malformed agent selectors before creating agent-scoped request/session state. Default aliases remain compatible, while chat completions, Responses, and embeddings map the selector error to a structured 400 instead of dispatching agent work.

Best-fix verdict: best after maintainer fix. The shared resolver is the right boundary because all affected OpenAI-compatible routes already depend on it for agent/session context. Alternatives considered: endpoint-local validation would duplicate selector rules across chat/responses/embeddings; validating only after normalization was unsafe because malformed headers like !!! could collapse to main.

Verification:

git diff --check origin/main...HEAD
node_modules/.bin/oxfmt --check src/gateway/embeddings-http.test.ts src/gateway/embeddings-http.ts src/gateway/http-utils.request-context.test.ts src/gateway/http-utils.ts src/gateway/openai-http.test.ts src/gateway/openai-http.ts src/gateway/openresponses-http.test.ts src/gateway/openresponses-http.ts
node scripts/run-oxlint.mjs src/gateway/embeddings-http.test.ts src/gateway/embeddings-http.ts src/gateway/http-utils.request-context.test.ts src/gateway/http-utils.ts src/gateway/openai-http.test.ts src/gateway/openai-http.ts src/gateway/openresponses-http.test.ts src/gateway/openresponses-http.ts
.agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main — first run found malformed-header bypass; fixed in ffdf462631c; final run clean, no accepted/actionable findings
Azure Crabbox cbx_4f10076d5110 / run run_8c71dd23f2eb: node scripts/run-vitest.mjs src/gateway/http-utils.request-context.test.ts src/gateway/openai-http.test.ts src/gateway/openresponses-http.test.ts src/gateway/embeddings-http.test.ts — 242 tests passed; lease stopped
GitHub exact head ffdf462631c04fdd4ea5cecd6794efefedd40f06: 130 successful, 0 failing, 1 pending tail check when reviewed

…26.6.8) (#1144) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.6` → `2026.6.8` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.8`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202668) [Compare Source](openclaw/openclaw@v2026.6.6...v2026.6.8) ##### Highlights - Telegram and WhatsApp channel delivery are richer and less brittle: Telegram can send structured rich text with tables, lists, expandable blockquotes, prompt-preserving CLI backend delivery, retired native draft migration, and safer rich-media boundaries, while WhatsApp now honors configured ACP bindings. ([#92679](openclaw/openclaw#92679), [#84082](openclaw/openclaw#84082), [#89421](openclaw/openclaw#89421), [#92513](openclaw/openclaw#92513)) Thanks [@obviyus](https://github.com/obviyus), [@jzakirov](https://github.com/jzakirov), [@spacegeologist](https://github.com/spacegeologist), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agent and Gateway recovery is sharper across account-scoped DM sends, generated media completions, restart shutdown aborts, yielded subagent pauses, yielded cron media, heartbeat dedupe, session identity prompts, and unknown OpenAI agent selector rejection. ([#92788](openclaw/openclaw#92788), [#91246](openclaw/openclaw#91246), [#91357](openclaw/openclaw#91357), [#92631](openclaw/openclaw#92631), [#92146](openclaw/openclaw#92146), [#91287](openclaw/openclaw#91287), [#92468](openclaw/openclaw#92468), [#92510](openclaw/openclaw#92510)) Thanks [@yetval](https://github.com/yetval), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@ooiuuii](https://github.com/ooiuuii), [@openperf](https://github.com/openperf), [@IWhatsskill](https://github.com/IWhatsskill), [@ZengWen-DT](https://github.com/ZengWen-DT), and [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Provider/model handling expands and tightens with GLM-5.2, Claude Haiku 4.5 catalog rows, OpenRouter and Google Vertex provider-prefix normalization, managed SecretRef auth, bounded model browse discovery, storeless OpenAI Responses replay gating, and Claude 4.5 Copilot tool-streaming safety. ([#92796](openclaw/openclaw#92796), [#90116](openclaw/openclaw#90116), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218), [#90686](openclaw/openclaw#90686), [#92247](openclaw/openclaw#92247), [#90706](openclaw/openclaw#90706), [#75393](openclaw/openclaw#75393)) Thanks [@arkyu2077](https://github.com/arkyu2077), [@liuhao1024](https://github.com/liuhao1024), [@bymle](https://github.com/bymle), [@rohitjavvadi](https://github.com/rohitjavvadi), [@samson910022](https://github.com/samson910022), [@snowzlm](https://github.com/snowzlm), and [@Kailigithub](https://github.com/Kailigithub). - `/usage` and reply payload hooks now have a native full footer renderer, default template, fixed-decimal formatting, credential-aware limits, better partial-count handling, and warnings for broken templates instead of silent bad output. ([#92657](openclaw/openclaw#92657), [#89835](openclaw/openclaw#89835), [#89629](openclaw/openclaw#89629)) Thanks [@Marvinthebored](https://github.com/Marvinthebored). - UI and mobile flows are steadier: workspace files can collapse and start collapsed, WebChat backscroll survives streaming, the sidebar session picker remains interactive above the desktop workbench, reset soft args survive UI dispatch, stale dashboard session parent lineage is preserved, and iOS reconnects stale foreground gateways. ([#92779](openclaw/openclaw#92779), [#92622](openclaw/openclaw#92622), [#92705](openclaw/openclaw#92705), [#91353](openclaw/openclaw#91353), [#90658](openclaw/openclaw#90658), [#92552](openclaw/openclaw#92552)) Thanks [@shakkernerd](https://github.com/shakkernerd), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@NianJiuZst](https://github.com/NianJiuZst), [@zhouhe-xydt](https://github.com/zhouhe-xydt), [@luoyanglang](https://github.com/luoyanglang), and [@Solvely-Colin](https://github.com/Solvely-Colin). - Memory, state, and diagnostics recover cleaner: oversized OpenAI embedding batches split before 431s, QMD memory search stays available in transient mode, SQLite avoids WAL on NFS state volumes, stuck-session recovery scheduling no longer resets warning backoff, and Infinity chunk limits stay genuinely unbounded. ([#92650](openclaw/openclaw#92650), [#92618](openclaw/openclaw#92618), [#92639](openclaw/openclaw#92639), [#91247](openclaw/openclaw#91247), [#92752](openclaw/openclaw#92752), [#92735](openclaw/openclaw#92735)) Thanks [@mushuiyu886](https://github.com/mushuiyu886), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@849261680](https://github.com/849261680), [@gnanam1990](https://github.com/gnanam1990), and [@yhterrance](https://github.com/yhterrance). ##### Changes - Providers/models: add GLM-5.2 support and Claude Haiku 4.5 catalog entries while keeping provider-qualified model IDs normalized across OpenRouter and Google Vertex paths. ([#92796](openclaw/openclaw#92796), [#90116](openclaw/openclaw#90116), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218)) Thanks [@arkyu2077](https://github.com/arkyu2077), [@liuhao1024](https://github.com/liuhao1024), and [@bymle](https://github.com/bymle). - Channel plugins: ship Telegram rich-message delivery and WhatsApp ACP binding support, including rich prompt handoff to CLI backends and transport fixtures for richer drafts. ([#92679](openclaw/openclaw#92679), [#92513](openclaw/openclaw#92513)) Thanks [@obviyus](https://github.com/obviyus) and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agent commands: support `/btw` in CLI-backed sessions and keep CLI usage-error exits classified as usage failures instead of successful runs. ([#92669](openclaw/openclaw#92669), [#92162](openclaw/openclaw#92162)) Thanks [@joshavant](https://github.com/joshavant) and [@Pandah97](https://github.com/Pandah97). - Usage hooks: add built-in full footer rendering, default footer templates, per-turn usage state, credential-aware limits, and fixed-decimal formatting for usage-bar templates. ([#92657](openclaw/openclaw#92657), [#89835](openclaw/openclaw#89835), [#89629](openclaw/openclaw#89629)) Thanks [@Marvinthebored](https://github.com/Marvinthebored). - Docs and operator guidance: document node config examples, clarify before-install hook scope, correct agent default concurrency comments, refresh ZAI provider docs, and update channel/group docs for current Telegram and WhatsApp behavior. ([#92677](openclaw/openclaw#92677), [#92766](openclaw/openclaw#92766), [#92695](openclaw/openclaw#92695)) Thanks [@liuhao1024](https://github.com/liuhao1024), [@sallyom](https://github.com/sallyom), and [@ArielSmoliar](https://github.com/ArielSmoliar). ##### Fixes - Onboarding/skills: show the Homebrew install recommendation only on macOS and Linux, so FreeBSD and other unsupported platforms no longer get a misleading brew prompt. Fixes [#68893](openclaw/openclaw#68893); carries forward [#68894](openclaw/openclaw#68894), [#68910](openclaw/openclaw#68910), [#68941](openclaw/openclaw#68941), [#68943](openclaw/openclaw#68943), [#69002](openclaw/openclaw#69002), and [#69545](openclaw/openclaw#69545). Thanks [@yurivict](https://github.com/yurivict), [@Sanjays2402](https://github.com/Sanjays2402), [@Eruditi](https://github.com/Eruditi), [@JustInCache](https://github.com/JustInCache), [@nnish16](https://github.com/nnish16), and [@Mlightsnow](https://github.com/Mlightsnow). - Channels and delivery: preserve account-scoped DM channel send policy, rich Telegram final replies, rich Telegram tables and lists, Telegram thread-create CLI remapping, Slack outbound `message_sent` hooks, contributed message-tool schema optionality, same-channel generated media completions, and channel chunking around surrogate pairs and Infinity limits. ([#92788](openclaw/openclaw#92788), [#92679](openclaw/openclaw#92679), [#89421](openclaw/openclaw#89421), [#89943](openclaw/openclaw#89943), [#91137](openclaw/openclaw#91137), [#91246](openclaw/openclaw#91246), [#92735](openclaw/openclaw#92735)) Thanks [@yetval](https://github.com/yetval), [@obviyus](https://github.com/obviyus), [@spacegeologist](https://github.com/spacegeologist), [@rishitamrakar](https://github.com/rishitamrakar), [@lundog](https://github.com/lundog), [@TurboTheTurtle](https://github.com/TurboTheTurtle), and [@yhterrance](https://github.com/yhterrance). - Auto-reply/groups: keep ordinary group text replies on automatic final-reply delivery while allowing `message(action=send)` for files, images, and other attachments to the same group or topic. Carries forward [#43276](openclaw/openclaw#43276); refs [#48004](openclaw/openclaw#48004). Thanks [@NayukiChiba](https://github.com/NayukiChiba) and [@ShakaRover](https://github.com/ShakaRover). - Auto-reply/skills: preserve multiline payloads for `/skill` and direct skill slash commands while keeping command-head normalization for aliases, colon syntax, and bot mentions. Fixes [#79155](openclaw/openclaw#79155); carries forward [#81305](openclaw/openclaw#81305). Thanks [@web3blind](https://github.com/web3blind). - iMessage: normalize leading NUL sent-message echo prefixes while preserving interior NUL bytes and the leading attributedBody marker handling from [#73942](openclaw/openclaw#73942). Carries forward [#63581](openclaw/openclaw#63581). Thanks [@drvoss](https://github.com/drvoss). - Discord: give generated auto-thread titles a 60-second timeout and 4,096-token reasoning-model output budget, clamped to the selected model output cap. ([#64734](openclaw/openclaw#64734)) Thanks [@hanamizuki](https://github.com/hanamizuki). - Agent, cron, and Gateway runtime: mark active main sessions before restart shutdown aborts, pause yielded subagent runs whose terminal also signals abort, preserve yielded media completions, de-duplicate main-session heartbeat events, expose session identity in runtime prompts, reject unknown OpenAI agent selectors, keep generated media completions and slash-command block replies in WebChat, preserve fresh post-compaction usage while clearing stale usage snapshots, and require admin privileges for HTTP session/model override surfaces. ([#91357](openclaw/openclaw#91357), [#92631](openclaw/openclaw#92631), [#92146](openclaw/openclaw#92146), [#91287](openclaw/openclaw#91287), [#92468](openclaw/openclaw#92468), [#92510](openclaw/openclaw#92510), [#91246](openclaw/openclaw#91246), [#50795](openclaw/openclaw#50795), [#50845](openclaw/openclaw#50845), [#82874](openclaw/openclaw#82874), [#92651](openclaw/openclaw#92651), [#92646](openclaw/openclaw#92646)) Thanks [@ooiuuii](https://github.com/ooiuuii), [@openperf](https://github.com/openperf), [@IWhatsskill](https://github.com/IWhatsskill), [@ZengWen-DT](https://github.com/ZengWen-DT), [@zhangguiping-xydt](https://github.com/zhangguiping-xydt), [@Hollychou924](https://github.com/Hollychou924), [@leno23](https://github.com/leno23), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Agents/exec: default empty-success background completion notices on only for real chat channels, preserving explicit opt-outs and keeping generic providers silent while carrying forward the narrow UX intent from [#39726](openclaw/openclaw#39726) and [#46926](openclaw/openclaw#46926). Thanks [@Sapientropic](https://github.com/Sapientropic) and [@wenkang-xie](https://github.com/wenkang-xie). - Providers and model replay: preserve storeless OpenAI Responses replay compatibility, avoid eager tool streaming for Claude 4.5 in Copilot, honor profile auth for SecretRef model entries, bound model browsing, strip provider prefixes where runtimes need bare IDs, and surface nested embedding fetch failures. ([#90706](openclaw/openclaw#90706), [#75393](openclaw/openclaw#75393), [#90686](openclaw/openclaw#90686), [#92247](openclaw/openclaw#92247), [#92627](openclaw/openclaw#92627), [#91218](openclaw/openclaw#91218), [#92628](openclaw/openclaw#92628)) Thanks [@snowzlm](https://github.com/snowzlm), [@Kailigithub](https://github.com/Kailigithub), [@rohitjavvadi](https://github.com/rohitjavvadi), [@samson910022](https://github.com/samson910022), [@liuhao1024](https://github.com/liuhao1024), [@bymle](https://github.com/bymle), and [@mushuiyu886](https://github.com/mushuiyu886). - Memory, state, diagnostics, and config: split header-too-large embedding batches, keep QMD memory search enabled in transient mode, avoid SQLite WAL on NFS volumes, preserve recovery scheduling outside stuck-session warning backoff, and keep shell environment fallbacks contained in config write tests. ([#92650](openclaw/openclaw#92650), [#92618](openclaw/openclaw#92618), [#92639](openclaw/openclaw#92639), [#91247](openclaw/openclaw#91247), [#92752](openclaw/openclaw#92752)) Thanks [@mushuiyu886](https://github.com/mushuiyu886), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@849261680](https://github.com/849261680), and [@gnanam1990](https://github.com/gnanam1990). - Workspace setup state: store setup completion outside the workspace dot directory using an OpenClaw-named root file, migrate valid legacy state forward, and avoid clobbering generic root `workspace-state.json` files for TigerFS-style dot-path compatibility. This Clownfish replacement carries forward the focused [#53326](openclaw/openclaw#53326) fix idea because the original branch was closed and uneditable. ([#53326](openclaw/openclaw#53326), [#44783](openclaw/openclaw#44783), [#39446](openclaw/openclaw#39446)) Thanks [@1qh](https://github.com/1qh). - UI/mobile/TUI: preserve dashboard session parent lineage, WebChat backscroll, reset soft command args, sidebar session picker interactivity, collapsed workspace files, resolved `/model` confirmation refs, and stale foreground iOS Gateway reconnects. ([#90658](openclaw/openclaw#90658), [#92622](openclaw/openclaw#92622), [#91353](openclaw/openclaw#91353), [#92705](openclaw/openclaw#92705), [#92779](openclaw/openclaw#92779), [#92773](openclaw/openclaw#92773), [#92552](openclaw/openclaw#92552)) Thanks [@luoyanglang](https://github.com/luoyanglang), [@TurboTheTurtle](https://github.com/TurboTheTurtle), [@zhouhe-xydt](https://github.com/zhouhe-xydt), [@NianJiuZst](https://github.com/NianJiuZst), [@shakkernerd](https://github.com/shakkernerd), [@NarahariRaghava](https://github.com/NarahariRaghava), and [@Solvely-Colin](https://github.com/Solvely-Colin). - TUI: reload the active session after external `/new` or `/reset` session-change events so stale transcript and stream state clear promptly. Fixes [#38966](openclaw/openclaw#38966); carries forward [#40472](openclaw/openclaw#40472). Thanks [@yizhanzjz](https://github.com/yizhanzjz) and [@wsyjh8](https://github.com/wsyjh8). - Control UI: preserve Gateway Access tokens during same-normalized WebSocket URL edits and reload gateway-scoped tokens when switching endpoints. Fixes [#41545](openclaw/openclaw#41545); repairs [#42001](openclaw/openclaw#42001) with additional source PRs [#41546](openclaw/openclaw#41546), [#41552](openclaw/openclaw#41552), and [#41718](openclaw/openclaw#41718). Thanks [@wsyjh8](https://github.com/wsyjh8), [@llagy0020](https://github.com/llagy0020), [@llagy007](https://github.com/llagy007), [@pingfanfan](https://github.com/pingfanfan), and [@zheliu2](https://github.com/zheliu2). - Gateway CLI: tolerate a single transient clean WebSocket close before `hello-ok` so one-shot RPC calls reconnect instead of failing noisily, while repeated clean pre-hello closes still surface. Carries forward source PRs [#54475](openclaw/openclaw#54475) and [#54774](openclaw/openclaw#54774); [#85253](openclaw/openclaw#85253) covered adjacent connect assembly diagnostics. Thanks [@ruanrrn](https://github.com/ruanrrn). - Gateway/Linux: keep root-owned systemd user service lifecycle commands on root's user manager when a stale `SUDO_USER` remains in a root shell with root's user bus environment. Fixes [#81410](openclaw/openclaw#81410). Thanks [@Ericksza](https://github.com/Ericksza) and [@ChuckClose-tech](https://github.com/ChuckClose-tech). - Release and test reliability: extend slow Gateway/full-suite watchdogs, split local full-suite shards when throttled, stabilize plugin auth marker fixtures, avoid brittle provider-ref error text, and keep QA Lab bootstrap selection assertions aligned with flow-only scenarios. ([#92652](openclaw/openclaw#92652)) - macOS Peekaboo bridge: update the embedded Peekaboo package to 3.5.2 and route bundled-skill CLI commands through the OpenClaw app bridge so they inherit its Screen Recording and Accessibility grants. - Agent routing: route subagent RPC callbacks addressed to an agent-shaped `--to` target to the correct session key instead of falling back to the main session, so WeChat (and other channel) session-key callbacks reach the intended subagent session. ([#90231](openclaw/openclaw#90231)) Thanks [@zhangguiping-xydt](https://github.com/zhangguiping-xydt). - Cron: preserve model, fallback, thinking, timeout, light-context, unsafe-content, and tool allow-list overrides on implicit text payloads by promoting them to agent turns, while explicit system events still prune those fields. Fixes [#28905](openclaw/openclaw#28905); carries forward [#64060](openclaw/openclaw#64060) and [#73946](openclaw/openclaw#73946). Thanks [@liaoandi](https://github.com/liaoandi). - QQBot delivery: keep markdown table chunks self-contained across message boundaries by preserving table state across block deliveries, flushing unfinished table-row fragments as plain text, and detecting short pipe-terminated rows by column count so split rows are not sent as malformed markdown. ([#92428](openclaw/openclaw#92428)) Thanks [@sliverp](https://github.com/sliverp). </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/1144

openclaw-barnacle Bot added gateway Gateway runtime size: M triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 12, 2026

openclaw-barnacle Bot added proof: supplied External PR includes structured after-fix real behavior proof. and removed triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels Jun 12, 2026

clawsweeper Bot mentioned this pull request Jun 13, 2026

fix(gateway): reject unknown explicit compat agents #92621

Closed

zhangguiping-xydt and others added 2 commits June 13, 2026 20:04

fix(gateway): reject unknown explicit agent selectors

8972767

Validate explicit OpenAI-compatible agent selectors against the configured roster so malformed integrations fail closed instead of creating phantom agent sessions. Co-Authored-By: Claude Opus 4.7 <[email protected]>

fix(gateway): reject malformed agent selector headers

ffdf462

vincentkoc force-pushed the feat/issue-92504 branch from 0bd2515 to ffdf462 Compare June 13, 2026 12:11

openclaw-barnacle Bot removed the proof: sufficient ClawSweeper judged the real behavior proof convincing. label Jun 13, 2026

vincentkoc approved these changes Jun 13, 2026

View reviewed changes

vincentkoc merged commit 8eb1fa0 into openclaw:main Jun 13, 2026
163 checks passed

clawsweeper Bot mentioned this pull request Jun 15, 2026

fix(gateway): reject unknown agent slugs on OpenAI-compatible endpoints #93103

Closed

SunnyShu0925 mentioned this pull request Jun 17, 2026

feat(memory-core): allow private network endpoints for memory embeddi… #94180

Closed

29 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(gateway): reject unknown OpenAI agent selectors#92510

fix(gateway): reject unknown OpenAI agent selectors#92510
vincentkoc merged 2 commits into
openclaw:mainfrom
zhangguiping-xydt:feat/issue-92504

zhangguiping-xydt commented Jun 12, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 12, 2026 •

edited

Loading

Uh oh!

zhangguiping-xydt commented Jun 12, 2026

Uh oh!

clawsweeper Bot commented Jun 12, 2026 •

edited

Loading

Uh oh!

vincentkoc left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Uh oh!

Conversation

zhangguiping-xydt commented Jun 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Linked context

Real behavior proof (required for external PRs)

Tests and validation

Risk checklist

Current review state

Uh oh!

clawsweeper Bot commented Jun 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

zhangguiping-xydt commented Jun 12, 2026

Uh oh!

clawsweeper Bot commented Jun 12, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

vincentkoc left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

zhangguiping-xydt commented Jun 12, 2026 •

edited

Loading

clawsweeper Bot commented Jun 12, 2026 •

edited

Loading

clawsweeper Bot commented Jun 12, 2026 •

edited

Loading