fix(openrouter): skip reasoning.effort injection for x-ai/grok models#32054
Merged
steipete merged 2 commits intoopenclaw:mainfrom Mar 2, 2026
Merged
Conversation
Contributor
Greptile SummaryAdds targeted fix for x-ai/grok models on OpenRouter that reject the
Confidence Score: 5/5
Last reviewed commit: ed5e0ae |
x-ai/grok models on OpenRouter do not support the reasoning.effort parameter and reject payloads containing it with "Invalid arguments passed to the model." Skip reasoning injection for these models, the same way we already skip it for the dynamic "auto" routing model. Closes openclaw#32039 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
3 tasks
ed5e0ae to
a207fa9
Compare
Contributor
|
Landed via temp rebase onto main.
Thanks @scoootscooob! |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a207fa911a
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| // model." Skip reasoning injection for these models. | ||
| // See: openclaw/openclaw#32039 | ||
| const skipReasoningInjection = modelId === "auto" || isOpenRouterReasoningUnsupported(modelId); | ||
| const openRouterThinkingLevel = skipReasoningInjection ? undefined : thinkingLevel; |
There was a problem hiding this comment.
Keep legacy reasoning_effort sanitization for x-ai models
Setting openRouterThinkingLevel to undefined for x-ai/* disables the createOpenRouterWrapper payload-mutation block entirely, and that block is also where legacy reasoning_effort gets stripped before sending to OpenRouter. In the x-ai path, any upstream reasoning_effort (the wrapper comment already notes pi-ai may inject this field) now passes through unchanged, so affected requests can still fail with invalid-argument errors even though nested reasoning.effort injection was skipped.
Useful? React with 👍 / 👎.
steipete
added a commit
to liuxiaopai-ai/openclaw
that referenced
this pull request
Mar 2, 2026
steipete
added a commit
that referenced
this pull request
Mar 2, 2026
* fix(plugins): fallback install entrypoints for legacy manifests * Voice Call: enforce exact webhook path match * Tests: isolate webhook path suite and reset cron auth state * chore: keep #31930 scoped to voice webhook path fix * fix: add changelog for exact voice webhook path match (#31930) (thanks @afurm) * fix: handle HTTP 529 (Anthropic overloaded) in failover error classification Classify Anthropic's 529 status code as "rate_limit" so model fallback triggers reliably without depending on fragile message-based detection. Closes #28502 * fix: add changelog for HTTP 529 failover classification (#31854) (thanks @bugkill3r) * fix(slack): guard against undefined text in includes calls during mention handling * fix: add changelog for mentions/slack null-safe guards (#31865) (thanks @stone-jin) * fix(memory-lancedb): pass dimensions to embedding API call - Add dimensions parameter to Embeddings constructor - Pass dimensions to OpenAI embeddings.create() API call - Fixes dimension mismatch when using custom embedding models like DashScope text-embedding-v4 * fix: add regression for memory-lancedb dimensions pass-through (#32036) (thanks @scotthuang) * fix(telegram): guard malformed native menu specs * fix: harden plugin command registration + telegram menu guard (#31997) (thanks @liuxiaopai-ai) * fix(gateway): restart heartbeat on model config changes * fix: add changelog credit for heartbeat model reload (#32046) (thanks @stakeswky) * test(process): replace no-output timer subprocess with spawn mock * test(perf): trim repeated setup in cron memory and config suites * test(perf): reduce per-case setup in script and git-hook tests * fix(slack): scope debounce key by message timestamp to prevent cross-thread collisions Top-level channel messages from the same sender shared a bare channel debounce key, causing concurrent messages in different threads to merge into a single reply on the wrong thread. Now the debounce key includes the message timestamp for top-level messages, matching how the downstream session layer already scopes by canonicalThreadId. Extracted buildSlackDebounceKey() for testability. Closes #31935 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: harden slack debounce key routing and ordering (#31951) (thanks @scoootscooob) * fix(openrouter): skip reasoning.effort injection for x-ai/grok models x-ai/grok models on OpenRouter do not support the reasoning.effort parameter and reject payloads containing it with "Invalid arguments passed to the model." Skip reasoning injection for these models, the same way we already skip it for the dynamic "auto" routing model. Closes #32039 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for openrouter x-ai reasoning guard (#32054) (thanks @scoootscooob) * fix(agents): scope volcengine-plan/byteplus-plan auth lookup to profile resolution The configure flow stores auth credentials under `provider: "volcengine"`, but the coding model uses `volcengine-plan` as its provider. Add a scoped `normalizeProviderIdForAuth` function used only by `listProfilesForProvider` so coding-plan variants resolve to their base provider for auth credential lookup without affecting global provider routing. Closes #31731 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tools): honor fsPolicy.workspaceOnly in image/pdf tool localRoots PR #28822 fixed the Write/Edit tools to respect `tools.fs.workspaceOnly`, but the image and PDF tools still unconditionally include default local roots (`~/.openclaw/media`, `~/.openclaw/agents`, etc.) when computing the `localRoots` allowlist for non-sandbox mode. When `fsPolicy.workspaceOnly` is true, restrict `localRoots` to only the workspace directory so that files outside the workspace are rejected by `assertLocalMediaAllowed()`. Relates to #31716 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for fsPolicy image/pdf propagation (#31882) (thanks @justinhuangcode) * fix: skip Telegram command sync when menu is unchanged (#32017) Hash the command list and cache it to disk per account. On restart, compare the current hash against the cached one and skip the deleteMyCommands + setMyCommands round-trip when nothing changed. This prevents 429 rate-limit errors when the gateway restarts several times in quick succession. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(telegram): scope command-sync hash cache by bot identity (#32059) * fix: normalize coding-plan providers in auth order validation * feat(security): Harden Docker browser container chromium flags (#23889) (#31504) * Gateway: honor OPENCLAW_GATEWAY_URL override for remote/local calls * Agents: fix sandbox sessionKey usage for PI embedded subagent calls * Sandbox: tighten browser container Chromium runtime flags * fix: add sandbox browser defaults for container hardening * docs: expand sandbox browser default flags list * fix: make sandbox browser flags optional and preserve gateway env auth overrides * docs: scope PR 31504 changelog entry * style: format gateway call override handling * fix: dedupe sandbox browser chrome args * fix: preserve remote tls fingerprint for env gateway override * fix: enforce auth for env gateway URL override * chore: document gateway override auth security expectations * fix(delivery): strip HTML tags for plain-text messaging surfaces Models occasionally produce HTML tags in their output. While these render fine on web surfaces, they appear as literal text on WhatsApp, Signal, SMS, IRC, and Telegram. Add sanitizeForPlainText() utility that converts common inline HTML to lightweight-markup equivalents and strips remaining tags. Applied in the outbound delivery pipeline for non-HTML surfaces only. Closes #31884 See also: #18558 * fix(outbound): harden plain-text HTML sanitization paths (#32034) * fix(security): harden file installs and race-path tests * matrix: bootstrap crypto runtime when npm scripts are skipped * fix(matrix): keep plugin register sync while bootstrapping crypto runtime (#31989) * perf(runtime): reduce cron persistence and logger overhead * test(perf): use prebuilt plugin install archive fixtures * test(perf): increase guardrail scan read concurrency * fix(queue): restart drain when message enqueued after idle window After a drain loop empties the queue it deletes the key from FOLLOWUP_QUEUES. If a new message arrives at that moment enqueueFollowupRun creates a fresh queue object with draining:false but never starts a drain, leaving the message stranded until the next run completes and calls finalizeWithFollowup. Fix: persist the most recent runFollowup callback per queue key in FOLLOWUP_RUN_CALLBACKS (drain.ts). enqueueFollowupRun now calls kickFollowupDrainIfIdle after a successful push; if a cached callback exists and no drain is running it calls scheduleFollowupDrain to restart immediately. clearSessionQueues cleans up the callback cache alongside the queue state. * fix: avoid stale followup drain callbacks (#31902) (thanks @Lanfei) * fix(synology-chat): read cfg from outbound context so incomingUrl resolves * fix: require openclaw.extensions for plugin installs (#32055) (thanks @liuxiaopai-ai) --------- Co-authored-by: Andrii Furmanets <furmanets.andriy@gmail.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: Saurabh <skmishra1991@gmail.com> Co-authored-by: stone-jin <1520006273@qq.com> Co-authored-by: scotthuang <scotthuang@tencent.com> Co-authored-by: User <user@example.com> Co-authored-by: scoootscooob <zhentongfan@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: justinhuangcode <justinhuangcode@users.noreply.github.com> Co-authored-by: Vincent Koc <vincentkoc@ieee.org> Co-authored-by: AytuncYildizli <cryptosquanch@gmail.com> Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com> Co-authored-by: Jealous <CooLanfei@163.com> Co-authored-by: white-rm <zhang.xujin@xydigit.com>
|
FYI — tested this in production with xAI models via OpenRouter and the 502s persist after this fix. The actual cause is JSON Schema validation-constraint keywords ( This fix does not resolve #32039 — the — Diagnosed by Claude Code (claude-sonnet-4-6), tested by @asyncjason |
Contributor
Author
|
@asyncjason — thanks for the production report! Makes sense that these are two separate failure modes:
Good to know both are now addressed across the two PRs. Appreciate the testing! |
execute008
pushed a commit
to execute008/openclaw
that referenced
this pull request
Mar 2, 2026
execute008
pushed a commit
to execute008/openclaw
that referenced
this pull request
Mar 2, 2026
* fix(plugins): fallback install entrypoints for legacy manifests * Voice Call: enforce exact webhook path match * Tests: isolate webhook path suite and reset cron auth state * chore: keep openclaw#31930 scoped to voice webhook path fix * fix: add changelog for exact voice webhook path match (openclaw#31930) (thanks @afurm) * fix: handle HTTP 529 (Anthropic overloaded) in failover error classification Classify Anthropic's 529 status code as "rate_limit" so model fallback triggers reliably without depending on fragile message-based detection. Closes openclaw#28502 * fix: add changelog for HTTP 529 failover classification (openclaw#31854) (thanks @bugkill3r) * fix(slack): guard against undefined text in includes calls during mention handling * fix: add changelog for mentions/slack null-safe guards (openclaw#31865) (thanks @stone-jin) * fix(memory-lancedb): pass dimensions to embedding API call - Add dimensions parameter to Embeddings constructor - Pass dimensions to OpenAI embeddings.create() API call - Fixes dimension mismatch when using custom embedding models like DashScope text-embedding-v4 * fix: add regression for memory-lancedb dimensions pass-through (openclaw#32036) (thanks @scotthuang) * fix(telegram): guard malformed native menu specs * fix: harden plugin command registration + telegram menu guard (openclaw#31997) (thanks @liuxiaopai-ai) * fix(gateway): restart heartbeat on model config changes * fix: add changelog credit for heartbeat model reload (openclaw#32046) (thanks @stakeswky) * test(process): replace no-output timer subprocess with spawn mock * test(perf): trim repeated setup in cron memory and config suites * test(perf): reduce per-case setup in script and git-hook tests * fix(slack): scope debounce key by message timestamp to prevent cross-thread collisions Top-level channel messages from the same sender shared a bare channel debounce key, causing concurrent messages in different threads to merge into a single reply on the wrong thread. Now the debounce key includes the message timestamp for top-level messages, matching how the downstream session layer already scopes by canonicalThreadId. Extracted buildSlackDebounceKey() for testability. Closes openclaw#31935 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: harden slack debounce key routing and ordering (openclaw#31951) (thanks @scoootscooob) * fix(openrouter): skip reasoning.effort injection for x-ai/grok models x-ai/grok models on OpenRouter do not support the reasoning.effort parameter and reject payloads containing it with "Invalid arguments passed to the model." Skip reasoning injection for these models, the same way we already skip it for the dynamic "auto" routing model. Closes openclaw#32039 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for openrouter x-ai reasoning guard (openclaw#32054) (thanks @scoootscooob) * fix(agents): scope volcengine-plan/byteplus-plan auth lookup to profile resolution The configure flow stores auth credentials under `provider: "volcengine"`, but the coding model uses `volcengine-plan` as its provider. Add a scoped `normalizeProviderIdForAuth` function used only by `listProfilesForProvider` so coding-plan variants resolve to their base provider for auth credential lookup without affecting global provider routing. Closes openclaw#31731 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tools): honor fsPolicy.workspaceOnly in image/pdf tool localRoots PR openclaw#28822 fixed the Write/Edit tools to respect `tools.fs.workspaceOnly`, but the image and PDF tools still unconditionally include default local roots (`~/.openclaw/media`, `~/.openclaw/agents`, etc.) when computing the `localRoots` allowlist for non-sandbox mode. When `fsPolicy.workspaceOnly` is true, restrict `localRoots` to only the workspace directory so that files outside the workspace are rejected by `assertLocalMediaAllowed()`. Relates to openclaw#31716 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for fsPolicy image/pdf propagation (openclaw#31882) (thanks @justinhuangcode) * fix: skip Telegram command sync when menu is unchanged (openclaw#32017) Hash the command list and cache it to disk per account. On restart, compare the current hash against the cached one and skip the deleteMyCommands + setMyCommands round-trip when nothing changed. This prevents 429 rate-limit errors when the gateway restarts several times in quick succession. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(telegram): scope command-sync hash cache by bot identity (openclaw#32059) * fix: normalize coding-plan providers in auth order validation * feat(security): Harden Docker browser container chromium flags (openclaw#23889) (openclaw#31504) * Gateway: honor OPENCLAW_GATEWAY_URL override for remote/local calls * Agents: fix sandbox sessionKey usage for PI embedded subagent calls * Sandbox: tighten browser container Chromium runtime flags * fix: add sandbox browser defaults for container hardening * docs: expand sandbox browser default flags list * fix: make sandbox browser flags optional and preserve gateway env auth overrides * docs: scope PR 31504 changelog entry * style: format gateway call override handling * fix: dedupe sandbox browser chrome args * fix: preserve remote tls fingerprint for env gateway override * fix: enforce auth for env gateway URL override * chore: document gateway override auth security expectations * fix(delivery): strip HTML tags for plain-text messaging surfaces Models occasionally produce HTML tags in their output. While these render fine on web surfaces, they appear as literal text on WhatsApp, Signal, SMS, IRC, and Telegram. Add sanitizeForPlainText() utility that converts common inline HTML to lightweight-markup equivalents and strips remaining tags. Applied in the outbound delivery pipeline for non-HTML surfaces only. Closes openclaw#31884 See also: openclaw#18558 * fix(outbound): harden plain-text HTML sanitization paths (openclaw#32034) * fix(security): harden file installs and race-path tests * matrix: bootstrap crypto runtime when npm scripts are skipped * fix(matrix): keep plugin register sync while bootstrapping crypto runtime (openclaw#31989) * perf(runtime): reduce cron persistence and logger overhead * test(perf): use prebuilt plugin install archive fixtures * test(perf): increase guardrail scan read concurrency * fix(queue): restart drain when message enqueued after idle window After a drain loop empties the queue it deletes the key from FOLLOWUP_QUEUES. If a new message arrives at that moment enqueueFollowupRun creates a fresh queue object with draining:false but never starts a drain, leaving the message stranded until the next run completes and calls finalizeWithFollowup. Fix: persist the most recent runFollowup callback per queue key in FOLLOWUP_RUN_CALLBACKS (drain.ts). enqueueFollowupRun now calls kickFollowupDrainIfIdle after a successful push; if a cached callback exists and no drain is running it calls scheduleFollowupDrain to restart immediately. clearSessionQueues cleans up the callback cache alongside the queue state. * fix: avoid stale followup drain callbacks (openclaw#31902) (thanks @Lanfei) * fix(synology-chat): read cfg from outbound context so incomingUrl resolves * fix: require openclaw.extensions for plugin installs (openclaw#32055) (thanks @liuxiaopai-ai) --------- Co-authored-by: Andrii Furmanets <furmanets.andriy@gmail.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: Saurabh <skmishra1991@gmail.com> Co-authored-by: stone-jin <1520006273@qq.com> Co-authored-by: scotthuang <scotthuang@tencent.com> Co-authored-by: User <user@example.com> Co-authored-by: scoootscooob <zhentongfan@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: justinhuangcode <justinhuangcode@users.noreply.github.com> Co-authored-by: Vincent Koc <vincentkoc@ieee.org> Co-authored-by: AytuncYildizli <cryptosquanch@gmail.com> Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com> Co-authored-by: Jealous <CooLanfei@163.com> Co-authored-by: white-rm <zhang.xujin@xydigit.com>
dawi369
pushed a commit
to dawi369/davis
that referenced
this pull request
Mar 3, 2026
dawi369
pushed a commit
to dawi369/davis
that referenced
this pull request
Mar 3, 2026
* fix(plugins): fallback install entrypoints for legacy manifests * Voice Call: enforce exact webhook path match * Tests: isolate webhook path suite and reset cron auth state * chore: keep openclaw#31930 scoped to voice webhook path fix * fix: add changelog for exact voice webhook path match (openclaw#31930) (thanks @afurm) * fix: handle HTTP 529 (Anthropic overloaded) in failover error classification Classify Anthropic's 529 status code as "rate_limit" so model fallback triggers reliably without depending on fragile message-based detection. Closes openclaw#28502 * fix: add changelog for HTTP 529 failover classification (openclaw#31854) (thanks @bugkill3r) * fix(slack): guard against undefined text in includes calls during mention handling * fix: add changelog for mentions/slack null-safe guards (openclaw#31865) (thanks @stone-jin) * fix(memory-lancedb): pass dimensions to embedding API call - Add dimensions parameter to Embeddings constructor - Pass dimensions to OpenAI embeddings.create() API call - Fixes dimension mismatch when using custom embedding models like DashScope text-embedding-v4 * fix: add regression for memory-lancedb dimensions pass-through (openclaw#32036) (thanks @scotthuang) * fix(telegram): guard malformed native menu specs * fix: harden plugin command registration + telegram menu guard (openclaw#31997) (thanks @liuxiaopai-ai) * fix(gateway): restart heartbeat on model config changes * fix: add changelog credit for heartbeat model reload (openclaw#32046) (thanks @stakeswky) * test(process): replace no-output timer subprocess with spawn mock * test(perf): trim repeated setup in cron memory and config suites * test(perf): reduce per-case setup in script and git-hook tests * fix(slack): scope debounce key by message timestamp to prevent cross-thread collisions Top-level channel messages from the same sender shared a bare channel debounce key, causing concurrent messages in different threads to merge into a single reply on the wrong thread. Now the debounce key includes the message timestamp for top-level messages, matching how the downstream session layer already scopes by canonicalThreadId. Extracted buildSlackDebounceKey() for testability. Closes openclaw#31935 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: harden slack debounce key routing and ordering (openclaw#31951) (thanks @scoootscooob) * fix(openrouter): skip reasoning.effort injection for x-ai/grok models x-ai/grok models on OpenRouter do not support the reasoning.effort parameter and reject payloads containing it with "Invalid arguments passed to the model." Skip reasoning injection for these models, the same way we already skip it for the dynamic "auto" routing model. Closes openclaw#32039 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for openrouter x-ai reasoning guard (openclaw#32054) (thanks @scoootscooob) * fix(agents): scope volcengine-plan/byteplus-plan auth lookup to profile resolution The configure flow stores auth credentials under `provider: "volcengine"`, but the coding model uses `volcengine-plan` as its provider. Add a scoped `normalizeProviderIdForAuth` function used only by `listProfilesForProvider` so coding-plan variants resolve to their base provider for auth credential lookup without affecting global provider routing. Closes openclaw#31731 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tools): honor fsPolicy.workspaceOnly in image/pdf tool localRoots PR openclaw#28822 fixed the Write/Edit tools to respect `tools.fs.workspaceOnly`, but the image and PDF tools still unconditionally include default local roots (`~/.openclaw/media`, `~/.openclaw/agents`, etc.) when computing the `localRoots` allowlist for non-sandbox mode. When `fsPolicy.workspaceOnly` is true, restrict `localRoots` to only the workspace directory so that files outside the workspace are rejected by `assertLocalMediaAllowed()`. Relates to openclaw#31716 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for fsPolicy image/pdf propagation (openclaw#31882) (thanks @justinhuangcode) * fix: skip Telegram command sync when menu is unchanged (openclaw#32017) Hash the command list and cache it to disk per account. On restart, compare the current hash against the cached one and skip the deleteMyCommands + setMyCommands round-trip when nothing changed. This prevents 429 rate-limit errors when the gateway restarts several times in quick succession. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(telegram): scope command-sync hash cache by bot identity (openclaw#32059) * fix: normalize coding-plan providers in auth order validation * feat(security): Harden Docker browser container chromium flags (openclaw#23889) (openclaw#31504) * Gateway: honor OPENCLAW_GATEWAY_URL override for remote/local calls * Agents: fix sandbox sessionKey usage for PI embedded subagent calls * Sandbox: tighten browser container Chromium runtime flags * fix: add sandbox browser defaults for container hardening * docs: expand sandbox browser default flags list * fix: make sandbox browser flags optional and preserve gateway env auth overrides * docs: scope PR 31504 changelog entry * style: format gateway call override handling * fix: dedupe sandbox browser chrome args * fix: preserve remote tls fingerprint for env gateway override * fix: enforce auth for env gateway URL override * chore: document gateway override auth security expectations * fix(delivery): strip HTML tags for plain-text messaging surfaces Models occasionally produce HTML tags in their output. While these render fine on web surfaces, they appear as literal text on WhatsApp, Signal, SMS, IRC, and Telegram. Add sanitizeForPlainText() utility that converts common inline HTML to lightweight-markup equivalents and strips remaining tags. Applied in the outbound delivery pipeline for non-HTML surfaces only. Closes openclaw#31884 See also: openclaw#18558 * fix(outbound): harden plain-text HTML sanitization paths (openclaw#32034) * fix(security): harden file installs and race-path tests * matrix: bootstrap crypto runtime when npm scripts are skipped * fix(matrix): keep plugin register sync while bootstrapping crypto runtime (openclaw#31989) * perf(runtime): reduce cron persistence and logger overhead * test(perf): use prebuilt plugin install archive fixtures * test(perf): increase guardrail scan read concurrency * fix(queue): restart drain when message enqueued after idle window After a drain loop empties the queue it deletes the key from FOLLOWUP_QUEUES. If a new message arrives at that moment enqueueFollowupRun creates a fresh queue object with draining:false but never starts a drain, leaving the message stranded until the next run completes and calls finalizeWithFollowup. Fix: persist the most recent runFollowup callback per queue key in FOLLOWUP_RUN_CALLBACKS (drain.ts). enqueueFollowupRun now calls kickFollowupDrainIfIdle after a successful push; if a cached callback exists and no drain is running it calls scheduleFollowupDrain to restart immediately. clearSessionQueues cleans up the callback cache alongside the queue state. * fix: avoid stale followup drain callbacks (openclaw#31902) (thanks @Lanfei) * fix(synology-chat): read cfg from outbound context so incomingUrl resolves * fix: require openclaw.extensions for plugin installs (openclaw#32055) (thanks @liuxiaopai-ai) --------- Co-authored-by: Andrii Furmanets <furmanets.andriy@gmail.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: Saurabh <skmishra1991@gmail.com> Co-authored-by: stone-jin <1520006273@qq.com> Co-authored-by: scotthuang <scotthuang@tencent.com> Co-authored-by: User <user@example.com> Co-authored-by: scoootscooob <zhentongfan@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: justinhuangcode <justinhuangcode@users.noreply.github.com> Co-authored-by: Vincent Koc <vincentkoc@ieee.org> Co-authored-by: AytuncYildizli <cryptosquanch@gmail.com> Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com> Co-authored-by: Jealous <CooLanfei@163.com> Co-authored-by: white-rm <zhang.xujin@xydigit.com>
OWALabuy
pushed a commit
to kcinzgg/openclaw
that referenced
this pull request
Mar 4, 2026
OWALabuy
pushed a commit
to kcinzgg/openclaw
that referenced
this pull request
Mar 4, 2026
* fix(plugins): fallback install entrypoints for legacy manifests * Voice Call: enforce exact webhook path match * Tests: isolate webhook path suite and reset cron auth state * chore: keep openclaw#31930 scoped to voice webhook path fix * fix: add changelog for exact voice webhook path match (openclaw#31930) (thanks @afurm) * fix: handle HTTP 529 (Anthropic overloaded) in failover error classification Classify Anthropic's 529 status code as "rate_limit" so model fallback triggers reliably without depending on fragile message-based detection. Closes openclaw#28502 * fix: add changelog for HTTP 529 failover classification (openclaw#31854) (thanks @bugkill3r) * fix(slack): guard against undefined text in includes calls during mention handling * fix: add changelog for mentions/slack null-safe guards (openclaw#31865) (thanks @stone-jin) * fix(memory-lancedb): pass dimensions to embedding API call - Add dimensions parameter to Embeddings constructor - Pass dimensions to OpenAI embeddings.create() API call - Fixes dimension mismatch when using custom embedding models like DashScope text-embedding-v4 * fix: add regression for memory-lancedb dimensions pass-through (openclaw#32036) (thanks @scotthuang) * fix(telegram): guard malformed native menu specs * fix: harden plugin command registration + telegram menu guard (openclaw#31997) (thanks @liuxiaopai-ai) * fix(gateway): restart heartbeat on model config changes * fix: add changelog credit for heartbeat model reload (openclaw#32046) (thanks @stakeswky) * test(process): replace no-output timer subprocess with spawn mock * test(perf): trim repeated setup in cron memory and config suites * test(perf): reduce per-case setup in script and git-hook tests * fix(slack): scope debounce key by message timestamp to prevent cross-thread collisions Top-level channel messages from the same sender shared a bare channel debounce key, causing concurrent messages in different threads to merge into a single reply on the wrong thread. Now the debounce key includes the message timestamp for top-level messages, matching how the downstream session layer already scopes by canonicalThreadId. Extracted buildSlackDebounceKey() for testability. Closes openclaw#31935 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: harden slack debounce key routing and ordering (openclaw#31951) (thanks @scoootscooob) * fix(openrouter): skip reasoning.effort injection for x-ai/grok models x-ai/grok models on OpenRouter do not support the reasoning.effort parameter and reject payloads containing it with "Invalid arguments passed to the model." Skip reasoning injection for these models, the same way we already skip it for the dynamic "auto" routing model. Closes openclaw#32039 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for openrouter x-ai reasoning guard (openclaw#32054) (thanks @scoootscooob) * fix(agents): scope volcengine-plan/byteplus-plan auth lookup to profile resolution The configure flow stores auth credentials under `provider: "volcengine"`, but the coding model uses `volcengine-plan` as its provider. Add a scoped `normalizeProviderIdForAuth` function used only by `listProfilesForProvider` so coding-plan variants resolve to their base provider for auth credential lookup without affecting global provider routing. Closes openclaw#31731 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(tools): honor fsPolicy.workspaceOnly in image/pdf tool localRoots PR openclaw#28822 fixed the Write/Edit tools to respect `tools.fs.workspaceOnly`, but the image and PDF tools still unconditionally include default local roots (`~/.openclaw/media`, `~/.openclaw/agents`, etc.) when computing the `localRoots` allowlist for non-sandbox mode. When `fsPolicy.workspaceOnly` is true, restrict `localRoots` to only the workspace directory so that files outside the workspace are rejected by `assertLocalMediaAllowed()`. Relates to openclaw#31716 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: add changelog credit for fsPolicy image/pdf propagation (openclaw#31882) (thanks @justinhuangcode) * fix: skip Telegram command sync when menu is unchanged (openclaw#32017) Hash the command list and cache it to disk per account. On restart, compare the current hash against the cached one and skip the deleteMyCommands + setMyCommands round-trip when nothing changed. This prevents 429 rate-limit errors when the gateway restarts several times in quick succession. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(telegram): scope command-sync hash cache by bot identity (openclaw#32059) * fix: normalize coding-plan providers in auth order validation * feat(security): Harden Docker browser container chromium flags (openclaw#23889) (openclaw#31504) * Gateway: honor OPENCLAW_GATEWAY_URL override for remote/local calls * Agents: fix sandbox sessionKey usage for PI embedded subagent calls * Sandbox: tighten browser container Chromium runtime flags * fix: add sandbox browser defaults for container hardening * docs: expand sandbox browser default flags list * fix: make sandbox browser flags optional and preserve gateway env auth overrides * docs: scope PR 31504 changelog entry * style: format gateway call override handling * fix: dedupe sandbox browser chrome args * fix: preserve remote tls fingerprint for env gateway override * fix: enforce auth for env gateway URL override * chore: document gateway override auth security expectations * fix(delivery): strip HTML tags for plain-text messaging surfaces Models occasionally produce HTML tags in their output. While these render fine on web surfaces, they appear as literal text on WhatsApp, Signal, SMS, IRC, and Telegram. Add sanitizeForPlainText() utility that converts common inline HTML to lightweight-markup equivalents and strips remaining tags. Applied in the outbound delivery pipeline for non-HTML surfaces only. Closes openclaw#31884 See also: openclaw#18558 * fix(outbound): harden plain-text HTML sanitization paths (openclaw#32034) * fix(security): harden file installs and race-path tests * matrix: bootstrap crypto runtime when npm scripts are skipped * fix(matrix): keep plugin register sync while bootstrapping crypto runtime (openclaw#31989) * perf(runtime): reduce cron persistence and logger overhead * test(perf): use prebuilt plugin install archive fixtures * test(perf): increase guardrail scan read concurrency * fix(queue): restart drain when message enqueued after idle window After a drain loop empties the queue it deletes the key from FOLLOWUP_QUEUES. If a new message arrives at that moment enqueueFollowupRun creates a fresh queue object with draining:false but never starts a drain, leaving the message stranded until the next run completes and calls finalizeWithFollowup. Fix: persist the most recent runFollowup callback per queue key in FOLLOWUP_RUN_CALLBACKS (drain.ts). enqueueFollowupRun now calls kickFollowupDrainIfIdle after a successful push; if a cached callback exists and no drain is running it calls scheduleFollowupDrain to restart immediately. clearSessionQueues cleans up the callback cache alongside the queue state. * fix: avoid stale followup drain callbacks (openclaw#31902) (thanks @Lanfei) * fix(synology-chat): read cfg from outbound context so incomingUrl resolves * fix: require openclaw.extensions for plugin installs (openclaw#32055) (thanks @liuxiaopai-ai) --------- Co-authored-by: Andrii Furmanets <furmanets.andriy@gmail.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: Saurabh <skmishra1991@gmail.com> Co-authored-by: stone-jin <1520006273@qq.com> Co-authored-by: scotthuang <scotthuang@tencent.com> Co-authored-by: User <user@example.com> Co-authored-by: scoootscooob <zhentongfan@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: justinhuangcode <justinhuangcode@users.noreply.github.com> Co-authored-by: Vincent Koc <vincentkoc@ieee.org> Co-authored-by: AytuncYildizli <cryptosquanch@gmail.com> Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com> Co-authored-by: Jealous <CooLanfei@163.com> Co-authored-by: white-rm <zhang.xujin@xydigit.com>
zooqueen
pushed a commit
to hanzoai/bot
that referenced
this pull request
Mar 6, 2026
zooqueen
pushed a commit
to hanzoai/bot
that referenced
this pull request
Mar 6, 2026
* fix(plugins): fallback install entrypoints for legacy manifests * Voice Call: enforce exact webhook path match * Tests: isolate webhook path suite and reset cron auth state * chore: keep openclaw#31930 scoped to voice webhook path fix * fix: add changelog for exact voice webhook path match (openclaw#31930) (thanks @afurm) * fix: handle HTTP 529 (Anthropic overloaded) in failover error classification Classify Anthropic's 529 status code as "rate_limit" so model fallback triggers reliably without depending on fragile message-based detection. Closes openclaw#28502 * fix: add changelog for HTTP 529 failover classification (openclaw#31854) (thanks @bugkill3r) * fix(slack): guard against undefined text in includes calls during mention handling * fix: add changelog for mentions/slack null-safe guards (openclaw#31865) (thanks @stone-jin) * fix(memory-lancedb): pass dimensions to embedding API call - Add dimensions parameter to Embeddings constructor - Pass dimensions to OpenAI embeddings.create() API call - Fixes dimension mismatch when using custom embedding models like DashScope text-embedding-v4 * fix: add regression for memory-lancedb dimensions pass-through (openclaw#32036) (thanks @scotthuang) * fix(telegram): guard malformed native menu specs * fix: harden plugin command registration + telegram menu guard (openclaw#31997) (thanks @liuxiaopai-ai) * fix(gateway): restart heartbeat on model config changes * fix: add changelog credit for heartbeat model reload (openclaw#32046) (thanks @stakeswky) * test(process): replace no-output timer subprocess with spawn mock * test(perf): trim repeated setup in cron memory and config suites * test(perf): reduce per-case setup in script and git-hook tests * fix(slack): scope debounce key by message timestamp to prevent cross-thread collisions Top-level channel messages from the same sender shared a bare channel debounce key, causing concurrent messages in different threads to merge into a single reply on the wrong thread. Now the debounce key includes the message timestamp for top-level messages, matching how the downstream session layer already scopes by canonicalThreadId. Extracted buildSlackDebounceKey() for testability. Closes openclaw#31935 * fix: harden slack debounce key routing and ordering (openclaw#31951) (thanks @scoootscooob) * fix(openrouter): skip reasoning.effort injection for x-ai/grok models x-ai/grok models on OpenRouter do not support the reasoning.effort parameter and reject payloads containing it with "Invalid arguments passed to the model." Skip reasoning injection for these models, the same way we already skip it for the dynamic "auto" routing model. Closes openclaw#32039 * fix: add changelog credit for openrouter x-ai reasoning guard (openclaw#32054) (thanks @scoootscooob) * fix(agents): scope volcengine-plan/byteplus-plan auth lookup to profile resolution The configure flow stores auth credentials under `provider: "volcengine"`, but the coding model uses `volcengine-plan` as its provider. Add a scoped `normalizeProviderIdForAuth` function used only by `listProfilesForProvider` so coding-plan variants resolve to their base provider for auth credential lookup without affecting global provider routing. Closes openclaw#31731 * fix(tools): honor fsPolicy.workspaceOnly in image/pdf tool localRoots PR openclaw#28822 fixed the Write/Edit tools to respect `tools.fs.workspaceOnly`, but the image and PDF tools still unconditionally include default local roots (`~/.openclaw/media`, `~/.openclaw/agents`, etc.) when computing the `localRoots` allowlist for non-sandbox mode. When `fsPolicy.workspaceOnly` is true, restrict `localRoots` to only the workspace directory so that files outside the workspace are rejected by `assertLocalMediaAllowed()`. Relates to openclaw#31716 * fix: add changelog credit for fsPolicy image/pdf propagation (openclaw#31882) (thanks @justinhuangcode) * fix: skip Telegram command sync when menu is unchanged (openclaw#32017) Hash the command list and cache it to disk per account. On restart, compare the current hash against the cached one and skip the deleteMyCommands + setMyCommands round-trip when nothing changed. This prevents 429 rate-limit errors when the gateway restarts several times in quick succession. * fix(telegram): scope command-sync hash cache by bot identity (openclaw#32059) * fix: normalize coding-plan providers in auth order validation * feat(security): Harden Docker browser container chromium flags (openclaw#23889) (openclaw#31504) * Gateway: honor OPENCLAW_GATEWAY_URL override for remote/local calls * Agents: fix sandbox sessionKey usage for PI embedded subagent calls * Sandbox: tighten browser container Chromium runtime flags * fix: add sandbox browser defaults for container hardening * docs: expand sandbox browser default flags list * fix: make sandbox browser flags optional and preserve gateway env auth overrides * docs: scope PR 31504 changelog entry * style: format gateway call override handling * fix: dedupe sandbox browser chrome args * fix: preserve remote tls fingerprint for env gateway override * fix: enforce auth for env gateway URL override * chore: document gateway override auth security expectations * fix(delivery): strip HTML tags for plain-text messaging surfaces Models occasionally produce HTML tags in their output. While these render fine on web surfaces, they appear as literal text on WhatsApp, Signal, SMS, IRC, and Telegram. Add sanitizeForPlainText() utility that converts common inline HTML to lightweight-markup equivalents and strips remaining tags. Applied in the outbound delivery pipeline for non-HTML surfaces only. Closes openclaw#31884 See also: openclaw#18558 * fix(outbound): harden plain-text HTML sanitization paths (openclaw#32034) * fix(security): harden file installs and race-path tests * matrix: bootstrap crypto runtime when npm scripts are skipped * fix(matrix): keep plugin register sync while bootstrapping crypto runtime (openclaw#31989) * perf(runtime): reduce cron persistence and logger overhead * test(perf): use prebuilt plugin install archive fixtures * test(perf): increase guardrail scan read concurrency * fix(queue): restart drain when message enqueued after idle window After a drain loop empties the queue it deletes the key from FOLLOWUP_QUEUES. If a new message arrives at that moment enqueueFollowupRun creates a fresh queue object with draining:false but never starts a drain, leaving the message stranded until the next run completes and calls finalizeWithFollowup. Fix: persist the most recent runFollowup callback per queue key in FOLLOWUP_RUN_CALLBACKS (drain.ts). enqueueFollowupRun now calls kickFollowupDrainIfIdle after a successful push; if a cached callback exists and no drain is running it calls scheduleFollowupDrain to restart immediately. clearSessionQueues cleans up the callback cache alongside the queue state. * fix: avoid stale followup drain callbacks (openclaw#31902) (thanks @Lanfei) * fix(synology-chat): read cfg from outbound context so incomingUrl resolves * fix: require openclaw.extensions for plugin installs (openclaw#32055) (thanks @liuxiaopai-ai) --------- Co-authored-by: Andrii Furmanets <furmanets.andriy@gmail.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: Saurabh <skmishra1991@gmail.com> Co-authored-by: stone-jin <1520006273@qq.com> Co-authored-by: scotthuang <scotthuang@tencent.com> Co-authored-by: User <user@example.com> Co-authored-by: scoootscooob <zhentongfan@gmail.com> Co-authored-by: justinhuangcode <justinhuangcode@users.noreply.github.com> Co-authored-by: Vincent Koc <vincentkoc@ieee.org> Co-authored-by: AytuncYildizli <cryptosquanch@gmail.com> Co-authored-by: bmendonca3 <bmendonca3@users.noreply.github.com> Co-authored-by: Jealous <CooLanfei@163.com> Co-authored-by: white-rm <zhang.xujin@xydigit.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
x-ai/grok-4.1-fast(and other x-ai models) on OpenRouter rejectreasoning.effortparameter with "Invalid arguments passed to the model"isOpenRouterReasoningUnsupported()check forx-ai/model prefixautomodel exclusion patternTest plan
reasoning.effortinjectedtsgo)Closes #32039
🤖 Generated with Claude Code