Skip to content

fix(status): recompute fallback context window#51795

Merged
frankekn merged 12 commits intoopenclaw:mainfrom
RichardCao:fix/issue-51554-status-context-window
Mar 23, 2026
Merged

fix(status): recompute fallback context window#51795
frankekn merged 12 commits intoopenclaw:mainfrom
RichardCao:fix/issue-51554-status-context-window

Conversation

@RichardCao
Copy link
Copy Markdown
Contributor

@RichardCao RichardCao commented Mar 21, 2026

Summary

  • recompute /status context-window reporting only after the active runtime model is fully settled
  • ignore stale persisted contextTokens when the session is actually being served by a fallback model
  • add regression coverage for fallback-model reporting and refresh the generated Plugin SDK baseline required on this branch

Testing

  • NODE_OPTIONS='--max-old-space-size=6144' pnpm plugin-sdk:api:check
  • pnpm test -- src/commands/status-json.test.ts src/commands/status.command.test.ts src/commands/status.command-flow.test.ts src/commands/gateway-status.test.ts src/commands/health.snapshot.test.ts

Fixes #51554

@greptile-apps
Copy link
Copy Markdown
Contributor

greptile-apps bot commented Mar 21, 2026

Greptile Summary

This PR fixes /status reporting a stale context window when a session falls back to a different runtime model. The core issue was that resolveContextTokensForModel was called before activeProvider/activeModel were fully settled, and it would reuse the persisted sessionEntry.contextTokens (which belonged to the originally selected model) even when serving via a fallback model with a smaller window.

The fix:

  • Moves contextTokens resolution to after both the session-entry model resolution and the transcript-based model update have completed.
  • Sets contextTokensOverride to undefined when the active runtime model differs from the selected model, so the config-registered context window for the active model is used instead of any stale persisted override.
  • Removes a dead resolveContextTokensForModel call inside the includeTranscriptUsage block that was unreachable (the guarding if (!contextTokens) could never be true after the first call used fallbackContextTokens: DEFAULT_CONTEXT_TOKENS).
  • Adds a focused regression test that exercises exactly the reported scenario (xiaomi/mimo-v2-flashminimax-portal/MiniMax-M2.5 fallback) and asserts the correct 49k/200k display.

The change is well-scoped and correctly handles both the session-fallback path and the transcript-derived model path.

Confidence Score: 5/5

  • This PR is safe to merge — it is a focused, well-tested fix with no side-effects on the non-fallback path.
  • The change is minimal and targeted: it consolidates context-window resolution into a single post-settlement call, ignores stale persisted overrides only when the runtime model provably differs, and removes dead code. A regression test directly validates the reported scenario. The non-fallback path is unaffected (when active model equals selected model, contextTokensOverride is identical to the old behavior). No new public API surface or schema changes are introduced.
  • No files require special attention.

Last reviewed commit: "fix(status): recompu..."

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 544a8ca5b8

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 7ed8951ebe

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from 7ed8951 to 0e902ca Compare March 22, 2026 06:52
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 0e902ca12c

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9fccbc6172

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from 9fccbc6 to 097b68c Compare March 22, 2026 11:45
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 64bcad3712

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: da8f5ab1e3

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment on lines +555 to +559
typeof activeContextTokens === "number" &&
activeContextTokens !== selectedContextTokens;
if (persistedLooksSelectedWindow && activeWindowDiffersFromSelected) {
return activeContextTokens;
}
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Preserve persisted caps that happen to match selected windows

When a fallback session is running under an explicit contextTokens cap whose numeric value happens to equal the selected model's native window, this branch now treats the persisted snapshot as stale and replaces it with the fallback model's window. That regresses /status for larger-window fallbacks: agent-runner.ts:474-478 persists agentCfgContextTokens as the live runtime limit, but after the next run this code will still render the larger activeContextTokens instead. A concrete case is a 128k cap on a 128k selected model that falls back to a 200k model: the session really stays capped at 128k, yet /status now reports .../200k here.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adopted in the updated precedence logic. The fallback branch now distinguishes a stale persisted selected-model window from an explicit configured cap that happens to have the same numeric value, so an intentional cap is preserved instead of being blindly replaced by the larger fallback model window.

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from da8f5ab to e5ef174 Compare March 22, 2026 14:21
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: e5ef174770

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment on lines +511 to +514
const activeContextTokens = resolveContextTokensForModel({
cfg: contextConfig,
...(contextLookupProvider ? { provider: contextLookupProvider } : {}),
model: contextLookupModel,
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Avoid provider-qualified lookup for slash runtime model IDs

When the active runtime model comes from sessionEntry.model without sessionEntry.modelProvider, resolveSelectedAndActiveModel() will split a raw ID like google/gemini-2.5-pro into provider=google and model=gemini-2.5-pro (src/auto-reply/model-runtime.ts). This new activeContextTokens call then passes that explicit provider into resolveContextTokensForModel(), but src/agents/context.ts explicitly warns that provider-qualified lookup is wrong for OpenRouter-style slash IDs because it returns the configured Google window instead of the raw discovery-cache entry. We already have coverage that legacy sessions can store slash-prefixed runtime models with no modelProvider (src/gateway/session-utils.test.ts:475-487), so /status will now recompute those fallback sessions to the wrong context window.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adopted, with a narrower guard. The branch still keeps model-only lookup for OpenRouter-style slash ids, but it no longer forces that path for persisted runtime slash ids when the stored runtime model is actually the selected/active provider model. That preserves provider-aware resolution where it is safe, without reintroducing the cross-provider slash-id regression.

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from e5ef174 to 979fc81 Compare March 22, 2026 14:31
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

if (!entry?.model && logUsage.model) {
const slashIndex = logUsage.model.indexOf("/");
if (slashIndex > 0) {
const provider = logUsage.model.slice(0, slashIndex).trim();
const model = logUsage.model.slice(slashIndex + 1).trim();

P2 Badge Ignore transcript models after a user switches session models

On the session-status-tool path, buildStatusMessage() is called with includeTranscriptUsage: true (src/agents/tools/session-status-tool.ts:480-506). But applyModelOverrideToSessionEntry() deliberately clears entry.model, entry.modelProvider, and entry.contextTokens after a manual model switch so status reflects the new selection until the next run (src/sessions/model-overrides.ts:44-72). Rehydrating activeModel from the last transcript whenever entry.model is absent means /session-status can immediately jump back to the previous run's context window after a switch, even though there is no active fallback and the user has already selected a different model.

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment on lines 490 to +492
activeModel = logUsage.model;
contextLookupProvider = undefined;
contextLookupModel = logUsage.model;
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Preserve provider-aware lookup for bare transcript model ids

For legacy sessions with no stored runtime model, this branch clears contextLookupProvider even when activeProvider is still known. That breaks the provider-qualified path that resolveContextTokensForModel() relies on to avoid the bare cache key's cross-provider minimum (src/agents/context.ts:401-418), so /session-status can now underreport the context window for bare transcript ids such as shared Gemini model names. The new slash-ID test covers google/gemini-2.5-pro, but not the bare-ID case introduced here.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adopted in 77c81efb29.

I kept the model-only lookup guard for slash transcript ids, but stopped clearing contextLookupProvider for bare transcript model ids. That preserves the provider-qualified cache path for shared names while still avoiding the OpenRouter-style slash-id regression. I also added a regression test for the bare-id path, and I verified the new case locally with a minimal transcript-log repro because the broader transcript-usage vitest block is intermittently hanging in this environment.

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch 2 times, most recently from 8f44156 to 77c81ef Compare March 22, 2026 15:39
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 77c81efb29

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment on lines 480 to +487
if (provider && model) {
activeProvider = provider;
activeModel = model;
// Preserve model-only lookup for transcript-derived provider/model IDs
// like "google/gemini-2.5-pro" that may come from a different upstream
// provider (for example OpenRouter).
contextLookupProvider = undefined;
contextLookupModel = logUsage.model;
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Ignore stale transcript models after a session model switch

When /session-status is used with model=..., applyModelOverrideToSessionEntry() intentionally clears entry.model and entry.modelProvider so status reflects the newly selected model immediately (src/sessions/model-overrides.ts:44-46). This new block repopulates activeProvider/activeModel from the last transcript message whenever those fields are missing, and session-status-tool always enables includeTranscriptUsage (src/agents/tools/session-status-tool.ts:480-507). Right after a model switch, the transcript still points at the previous model, so the later runtimeDiffersFromSelected logic recomputes the context window from stale transcript data and can show the old/default window with no fallback notice until another run refreshes the session.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adopted on the current branch head. I now disable transcript-usage backfill on the immediate /session-status response after a model=... override, so the tool no longer treats stale transcript metadata as the active runtime identity before a fresh run repopulates entry.model / entry.modelProvider.

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from 77c81ef to 1a4971d Compare March 22, 2026 15:59
@RichardCao
Copy link
Copy Markdown
Contributor Author

Refreshed this PR onto the latest successful green main commit 4f0bb7594bc73847cc7e4ec772241ed793d3e103 and reran the focused status-path regression coverage:\n\n- pnpm test -- src/commands/status.command.ts src/commands/status-json.ts src/commands/status-json.test.ts src/commands/status.command.test.ts src/commands/gateway-status.test.ts src/commands/gateway-status.ts src/commands/gateway-status/helpers.ts src/commands/status.command-flow.test.ts src/commands/health.snapshot.test.ts src/commands/health.ts src/commands/models/list.status-command.ts src/commands/channels/status.ts\n\nThose status-related tests are green locally on the new green base.

@RichardCao
Copy link
Copy Markdown
Contributor Author

Refreshed this PR again onto the newer successful green main commit 828afd39ec90d2cf7393a04b643f98f344324a4e and reran the same focused status-path regression coverage:\n\n- pnpm test -- src/commands/status.command.ts src/commands/status-json.ts src/commands/status-json.test.ts src/commands/status.command.test.ts src/commands/gateway-status.test.ts src/commands/gateway-status.ts src/commands/gateway-status/helpers.ts src/commands/status.command-flow.test.ts src/commands/health.snapshot.test.ts src/commands/health.ts src/commands/models/list.status-command.ts src/commands/channels/status.ts\n\nThose status-related tests are still green locally after the newer green-base refresh.

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from 4235ba9 to d740b4f Compare March 23, 2026 03:09
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: d740b4fe5b

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

Comment on lines +514 to +518
const activeContextTokens = resolveContextTokensForModel({
cfg: contextConfig,
...(contextLookupProvider ? { provider: contextLookupProvider } : {}),
model: contextLookupModel,
fallbackContextTokens: DEFAULT_CONTEXT_TOKENS,
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Stop using the 32k default as an active-model window

If the fallback runtime model is not present in config or the discovery cache, resolveContextTokensForModel() returns the fallbackContextTokens passed here (src/agents/context.ts:361-446), so activeContextTokens becomes a synthetic 32k rather than “unknown”. The later stale-snapshot check in src/auto-reply/status.ts:553-561 then treats that 32k as authoritative and can overwrite a real persisted/runtime cap whenever entry.contextTokens happens to equal the selected model’s window. In practice, any cache-cold or custom fallback model can make /status underreport the context limit as 32k even though the session store still had the last known runtime cap.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adopted in the current precedence logic. On the fallback path I no longer pass a synthetic fallback default into active runtime lookup here, so an unresolvable active model stays unknown instead of being treated as an authoritative 32k window. That preserves persisted/runtime caps instead of overwriting them with a fake active limit.

@RichardCao
Copy link
Copy Markdown
Contributor Author

Current merge-CI red on this refreshed branch is tracking the same failures that are on current main, not the status/context-window change in this PR.

From the failing logs on this run:

  • check: formatting drift in extensions/voice-call/src/manager/outbound.test.ts
  • checks (node, extensions): broad matrix/line/msteams failures, including Matrix TypeError (class extends undefined), multiple LINE bot-handler assertions, and the MS Teams setup-surface regression
  • checks (node, contracts): src/plugins/contracts/auth.contract.test.ts times out in the GitHub Copilot provider-owned auth case

Those files do not overlap this PRs touched status command/status model paths. The branch itself is based on the latest successful green main commit 828afd3, and the focused status-path regression suite remains green locally.

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from d740b4f to 6277268 Compare March 23, 2026 03:40
@RichardCao
Copy link
Copy Markdown
Contributor Author

Refreshed onto the latest successful green main commit daa3b4ba895d301c60d18a772d5308b54e780b14 and rebuilt this branch as that base plus only the status/context-window commits.

Local validation

  • attempted: pnpm test -- src/commands/status-json.test.ts src/commands/status.command.test.ts src/commands/status.command-flow.test.ts src/commands/gateway-status.test.ts src/commands/health.snapshot.test.ts
  • current local blocker on this checkout: the run aborts while resolving unrelated openclaw/plugin-sdk/line-runtime from extensions/line/runtime-api.ts during health.snapshot.test.ts setup

I pushed the refreshed head so CI can re-evaluate this status fix on the correct green base SHA.

@frankekn frankekn self-assigned this Mar 23, 2026
@RichardCao
Copy link
Copy Markdown
Contributor Author

Refreshed this branch again onto the latest successful green main commit 65405edaab59e524a0120ded50afb4e38e62c298 and rebuilt it as that base plus only the status/context-window commits currently on the PR branch.

Testing

  • NODE_OPTIONS='--max-old-space-size=6144' pnpm plugin-sdk:api:check
  • pnpm test -- src/commands/status-json.test.ts src/commands/status.command.test.ts src/commands/status.command-flow.test.ts src/commands/gateway-status.test.ts src/commands/health.snapshot.test.ts

@frankekn
Copy link
Copy Markdown
Contributor

@codex review

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 56746f13dd

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".

Comment on lines +459 to +463
// Legacy sessions can persist raw runtime ids like "google/gemini-2.5-pro"
// without a separate provider field. Keep the raw id for context lookup so
// provider-qualified resolution does not jump to a different upstream window.
contextLookupProvider = undefined;
contextLookupModel = runtimeModelRaw;
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep provider-aware context lookup for legacy runtime model IDs

When sessionEntry.model is slash-qualified and modelProvider is missing, this block forces contextLookupProvider to undefined. That makes resolveContextTokensForModel skip provider config scanning, so entries like minimax-portal/MiniMax-M2.5 can no longer read models.providers.minimax-portal[*].contextWindow and may fall back to 32k (or keep stale selected-model tokens) if the context cache is empty. Before this change, the provider-aware lookup still resolved the configured active window, so this introduces incorrect /status context reporting for legacy sessions without modelProvider.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adopted on the updated branch head.

I agreed with this one for persisted legacy runtime ids on sessionEntry.model: when the session already stores an active fallback like minimax-portal/MiniMax-M2.5, we do want the provider-aware lookup path so config-backed provider windows still resolve even if the cache is cold.

What changed:

  • kept the transcript-only raw slash lookup behavior for logUsage.model follow-ups where cross-provider ids like google/gemini-2.5-pro can still be model-only
  • stopped forcing model-only lookup for persisted legacy runtime ids from sessionEntry.model
  • added a regression test covering the legacy slash runtime-id fallback case
  • refreshed the Plugin SDK API baseline afterward because the status.ts export source lines moved

Relevant commits on this branch:

  • 0b1521b58697 for the fallback-lookup fix + regression coverage
  • 46012ff7b486 for the required Plugin SDK baseline refresh

@RichardCao RichardCao force-pushed the fix/issue-51554-status-context-window branch from 56746f1 to f285923 Compare March 23, 2026 07:51
@RichardCao
Copy link
Copy Markdown
Contributor Author

Refreshed this branch onto the latest successful green main commit 9fbb840c79edb79039d8da53254a29b170cdc60d and rebuilt it as that base plus only the status/context-window commits on this PR.

Testing

  • NODE_OPTIONS='--max-old-space-size=6144' pnpm plugin-sdk:api:check
  • pnpm test -- src/commands/status-json.test.ts src/commands/status.command.test.ts src/commands/status.command-flow.test.ts src/commands/gateway-status.test.ts

I also tried one broader local sweep including src/commands/health.snapshot.test.ts; on this checkout that run still hit unrelated Telegram probe assertions outside this PR's touched status/context-window paths, so I kept the final validation scoped to the status/gateway files that this change actually affects.

@frankekn
Copy link
Copy Markdown
Contributor

@codex review

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 0b1521b586

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".

@frankekn
Copy link
Copy Markdown
Contributor

@codex review

@chatgpt-codex-connector
Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Another round soon, please!

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".

@frankekn frankekn merged commit a835c20 into openclaw:main Mar 23, 2026
23 of 40 checks passed
@frankekn
Copy link
Copy Markdown
Contributor

Thanks for your contribution, @RichardCao.

Landed in a835c20
Source head was 8e9a83a

mrosmarin added a commit to mrosmarin/openclaw that referenced this pull request Mar 23, 2026
* main: (704 commits)
  fix: repair runtime seams after rebase
  test: update codex test fixtures to gpt-5.4
  fix: keep message-tool buttons optional for Telegram and Mattermost (openclaw#52589) (thanks @tylerliu612)
  fix(telegram): make buttons schema optional in message tool
  fix(status): recompute fallback context window (openclaw#51795)
  fix(memory-core): register memory tools independently to prevent coupled failure (openclaw#52668)
  style: format image-generation runtime tests
  test: finish no-isolate suite hardening
  fix: align websocket stream fallback types
  test: harden ci isolated mocks
  docs: clarify unreleased breaking changes
  fix: alphabetize web search provider listings
  fix(changelog): note windows media path guardrails (openclaw#52738)
  docs: reorder unreleased changelog
  test: harden no-isolate mocked module resets
  fix: sync agent and autoreply e2e updates
  test: isolate base vitest thread blockers
  fix(android): gate canvas bridge to trusted pages (openclaw#52722)
  test: stop leaking image workspace temp dirs
  ACPX: align pinned runtime version (openclaw#52730)
  ...
furaul pushed a commit to furaul/openclaw that referenced this pull request Mar 24, 2026
* fix(status): recompute fallback context window

* fix(status): keep live context token caps on fallback

* fix(status): preserve fallback runtime context windows

* fix(status): preserve configured fallback context caps

* fix(status): keep provider-aware transcript context lookups

* fix(status): preserve explicit fallback context caps

* fix(status): clamp fallback configured context caps

* fix(status): keep raw runtime slash ids

* fix(status): refresh plugin-sdk api baseline

* fix(status): preserve fallback context lookup

* test(status): refresh plugin-sdk api baseline

* fix(status): keep runtime slash-id context lookup

---------

Co-authored-by: create <[email protected]>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: RichardCao <[email protected]>
npmisantosh pushed a commit to npmisantosh/openclaw that referenced this pull request Mar 25, 2026
* fix(status): recompute fallback context window

* fix(status): keep live context token caps on fallback

* fix(status): preserve fallback runtime context windows

* fix(status): preserve configured fallback context caps

* fix(status): keep provider-aware transcript context lookups

* fix(status): preserve explicit fallback context caps

* fix(status): clamp fallback configured context caps

* fix(status): keep raw runtime slash ids

* fix(status): refresh plugin-sdk api baseline

* fix(status): preserve fallback context lookup

* test(status): refresh plugin-sdk api baseline

* fix(status): keep runtime slash-id context lookup

---------

Co-authored-by: create <[email protected]>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: RichardCao <[email protected]>
PotatoParser added a commit to Lilac-Labs/openclaw that referenced this pull request Mar 26, 2026
* fix(delivery-queue): increment retryCount on deferred entries when time budget exceeded

When delivery recovery ran out of the 60s time budget, remaining pending
entries were silently deferred to the next restart with no retryCount
increment. This caused them to loop forever across restarts, never hitting
MAX_RETRIES and never moving to failed/.

Fix: call failDelivery() on each remaining entry before breaking out of
the recovery loop (both the deadline check and the backoff-exceeds-deadline
check). This increments retryCount so that entries eventually exhaust
MAX_RETRIES and are permanently skipped.

Fixes openclaw#24353

* fix(delivery-queue): break immediately on deadline instead of failing all remaining entries

P1-C: After now >= deadline, the old code would iterate all remaining queue
entries and call failDelivery() on each — O(n) work that nullified the
maxRecoveryMs wall-clock cap on large queues.

Fix: break out of the recovery loop immediately when the deadline is exceeded.
Remaining entries are picked up on next startup unchanged (retryCount not
incremented). The deadline means 'stop here', not 'fail everything remaining'.

* fix(delivery-queue): align test assertion and JSDoc with 'next startup' log message

* fix(browser): add ChildProcessWithoutNullStreams cast for @types/node compat

The stdio tuple overload resolves differently across @types/node versions
(v20 vs v24/v25). Cast the spawn() result to ChildProcessWithoutNullStreams
to ensure proc.stderr?.on/off type-checks regardless of installed @types/node.

* test(delivery-queue): align test assertion with 'next startup' log message

* fix(delivery-queue): increment retryCount on deadline-deferred entries

Codex P1: entries deferred by the recovery time budget kept retryCount=0
forever, so they could loop across restarts without ever reaching MAX_RETRIES.

After breaking on deadline, call failDelivery() for all remaining entries
so retryCount is incremented. Entries stay in queue until MAX_RETRIES is
reached and they are pruned normally.

Also updates the maxRecoveryMs test to assert retryCount=1 on deferred entries.

* fix(ci): restore delivery queue branch checks

* fix(plugins): make metadata generator formatter portable

* fix(image): deprecate legacy skill and clarify auth

* docs(image): remove duplicate typical values bullet

* fix: harden image auth env lookups (openclaw#52552) (thanks @vincentkoc)

* test(mattermost): cover directory discovery

* test(msteams): cover store and live directory helpers

* fix(mattermost): honor replyToMode off for threaded messages

* perf(reply): lazy-load runner execution and memory

* fix(plugins): remove metadata generator conflict markers

* test(nextcloud-talk): cover inbound behavior branches

* test(irc): cover inbound behavior branches

* test: slim outbound test import graphs

* perf: remove remaining unit thread pins

* perf(reply): lazy-load usage cost resolution

* test(googlechat): cover security normalization

* perf(reply): lazy-load context token lookup

* style(format): fix extension test drift

* test: centralize cli runtime capture helpers

* refactor: reuse shared cli runtime test mocks

* fix: restore bundled plugin metadata generator

* fix(telegram): add allow_sending_without_reply to prevent lost messages

When a Telegram message that OpenClaw is replying to gets deleted before
delivery, the Telegram API rejects the entire sendMessage call with
"message to be replied not found". This causes the bot's response to be
silently lost and stuck in the failed delivery queue permanently.

Setting allow_sending_without_reply: true tells Telegram to deliver the
message as a standalone message if the reply target no longer exists,
instead of failing the entire request.

Applied to all 6 locations across 4 source files where
reply_to_message_id is set:
- send.ts: buildTelegramReplyParams (both reply_parameters and plain reply)
- bot/delivery.send.ts: buildTelegramSendParams
- draft-stream.ts: draft stream reply params
- bot-handlers.runtime.ts: error reply messages (file too large, media download failed)

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix(telegram): update test expectations for allow_sending_without_reply

Update exact-match test assertions in send.test.ts to include the new
allow_sending_without_reply: true parameter. Tests using objectContaining
already pass, but several tests use exact object matching.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: finish telegram reply fallback landing (openclaw#52524) (thanks @moltbot886)

* refactor: extract single-provider plugin entry helper

* refactor: add provider onboarding preset appliers

* refactor: share parsed channel allowlist prompts

* refactor: share channel setup status helpers

* fix: export provider-entry plugin sdk subpath

* style: format plugin sdk helper updates

* fix(docs): code-verified fixes from deep reference audit

- sdk-runtime.md: add missing required params (runId, timeoutMs) to
  runEmbeddedPiAgent example
- sdk-provider-plugins.md: add missing onModelSelected hook (openclaw#22),
  clarify capabilities is data not callable, drop misleading '21' count

* test: fix googlechat security typing drift

* perf: remove stale unit isolated entry

* refactor(outbound): split delivery queue storage and recovery

* fix(docs): remaining code audit fixes

- sdk-entrypoints.md: fix mislabeled 'Channel entry options' heading
  (should be 'Options' — these are definePluginEntry options, not
  channel-specific)
- sdk-overview.md: add 4 missing API object fields (version, description,
  source, rootDir) from OpenClawPluginApi type

* perf(reply): split usage line helpers

* perf(reply): narrow queue imports

* test(msteams): cover graph helpers

* test(msteams): cover upload and webhook helpers

* refactor: harden generated-file guards and provider ids

* fix: restore main gate after type updates

* fix(plugins): accept media-understanding id hints

* test: default scoped vitest configs to no-isolate

* test(msteams): cover poll and file-card helpers

* test: fix provider config typing drift

* perf: default channel vitest lanes to threads

* perf(reply): lazy-load media path normalization

* style(format): fix msteams test drift

* refactor(plugins): move remaining channel and provider ownership out of src

* refactor(plugins): finish provider and whatsapp cleanup

* fix(gateway): pass process.env in status command probe auth to resolve SecretRef

Fixes openclaw#52360

resolveGatewayProbeAuthSafe was called from status-all.ts without an
env argument, causing the credential resolution chain to fall back to
an empty object instead of process.env. This made env-backed SecretRef
tokens (gateway.auth.token, Telegram botToken, etc.) appear unresolved
in the status command path even when the runtime was healthy.

Added process.env as default fallback in buildGatewayProbeCredentialPolicy
and passed env explicitly from status-all.ts callers.

Related: openclaw#33070, openclaw#38973, openclaw#39415, openclaw#46014, openclaw#49730

* fix(status): resolve only selected probe-auth branch and fix plain status path

Address two Codex P1/P2 issues:

1. (P1) Plain 'openclaw status' and 'openclaw status --json' still went
   through the sync resolveGatewayProbeAuthSafe path in
   status.gateway-probe.ts, which cannot expand SecretRef objects.
   Switched to async resolveGatewayProbeAuthSafeWithSecretInputs.

2. (P2) status-all.ts was eagerly resolving both local and remote probe
   auth before deciding which to use. A stale SecretRef in the unused
   branch could abort the command. Collapsed to a single resolution
   call using the correct mode upfront.

Updated status.scan.test.ts to use mockResolvedValue since
resolveGatewayProbeAuthResolution is now async.

* fix(status): await resolveGatewayProbeAuthResolution in scan.shared

Function is now async after switching to resolveGatewayProbeAuthSafeWithSecretInputs.
Missing await caused TS error: Property 'auth' does not exist on type 'Promise<...>'.

* fix: finish gateway probe auth landing (openclaw#52513) (thanks @CodeForgeNet)

* fix: finish gateway probe auth landing (openclaw#52513) (thanks @CodeForgeNet)

* test: clear msteams gate drift for gateway probe auth landing (openclaw#52513) (thanks @CodeForgeNet)

* fix(exec): return plain-text tool result on failure instead of raw JSON

When an exec command fails (e.g. timeout), the tool previously rejected
with an Error, which the tool adapter caught and wrapped in a JSON object
({ status, tool, error }). The model then received this raw JSON as the
tool result and could parrot it verbatim to the user.

Now exec failures resolve with a proper tool result containing the error
as human-readable text in content[], matching the success path structure.
The model sees plain text it can naturally incorporate into its reply.

Also fixes a pre-existing format issue in update-cli.test.ts.

Fixes openclaw#52484

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: finish exec tool failure landing (openclaw#52508) (thanks @martingarramon)

* fix(openshell): bundle upstream cli fallback

* perf(reply): lazy-load session store writes

* fix(build): restore plugin-sdk and line compat after refactor

* refactor(kilocode): route shared model constants through core seam

* refactor(plugin-sdk): route core provider and telegram seams through sdk barrels

* fix(acp): preserve hidden thought chunks from gateway chat

* fix(docs): rename 'Channel Options' to 'Options' in sdk-entrypoints

This heading labels definePluginEntry options (generic, not channel-specific).
Another agent reverted the previous fix during a merge.

* fix(line): narrow plugin-sdk seams after refactor

* test(voice-call): cover helper utilities

* test(voice-call): cover manager and api helpers

* fix(acp): preserve hidden thought replay on session load

* test(voice-call): cover twilio and reaper helpers

* docs(changelog): note ACP hidden thought replay fix

* test(voice-call): cover utility and tailscale helpers

* fix(ci): resync generated baselines and line runtime seam

* fix(docs): remove duplicate '### Options' headings (MD024)

* fix(ci): restore plugin manifests and boundary tests

* style(docs): format sdk entrypoints doc

* docs(config): refresh generated baseline

* test(voice-call): cover outbound call flow helpers

* fix(ci): repair tts and matrix refactor fallout

* fix(ci): repair voice-call typing and provider contracts

* fix(ci): satisfy voice-call typing and extension boundaries

* Remove personal references from docs (openclaw#25260)

* docs: remove personal references from AGENTS.md

* docs: remove personal reference from sag skill

* docs: note generic agent guidance cleanup

* Update CHANGELOG.md

---------

Co-authored-by: Josh Lehman <[email protected]>
Co-authored-by: Vincent Koc <[email protected]>

* fix(plugins): route keyed queue imports through core (openclaw#52608)

* fix(matrix): preserve send aliases and voice intent

* fix(build): repair stale plugin sdk surfaces

* fix(plugin-sdk): export line runtime subpath

* fix(auth): route copilot login through sdk seam

* feat(web-search): add bundled Exa plugin (openclaw#52617)

* test(msteams): await async setup status lines

* fix(whatsapp): remove outbound runtime cycle

* fix(plugin-sdk): fast-path root diagnostic subscriptions

* fix(exa): align freshness typing and config docs

* fix(matrix): avoid touching dropped room bindings

* fix(web-search): align Exa plugin with current API

* docs(tools): add DuckDuckGo Search provider page

New page: tools/duckduckgo-search.md
- Key-free fallback provider, no API key needed
- Clear Warning about unofficial HTML-based integration
- Limitations section covering bot-challenge risk and reliability
- CardGroup showing good-for vs not-recommended-for use cases

Updated: tools/web.md with DuckDuckGo in CardGroup and comparison table
Updated: docs.json nav and redirect

* test(telegram): align webhook grammy mock

* docs(tools): add Exa Search page, align all search provider docs

New page: tools/exa-search.md
- Neural/keyword/hybrid search modes with content extraction
- Tool parameters including contents (highlights, text, summary)
- Search mode reference table

Rewritten: tools/duckduckgo-search.md
- Aligned to consistent template (Setup, Config, Tool parameters, Notes, Related)
- Simplified from previous version

Aligned across all providers:
- Every search page now ends with a consistent ## Related section
- Replaced 'See [Web tools]' with proper Related links
- Added Exa + DuckDuckGo to web.md overview CardGroup and comparison table
- Added Exa to docs.json nav and redirects

* fix(telegram): inject media loader through bot deps

* fix(ci): harden telegram seams and cap job timeouts

* docs(tools): update Exa Search notes for current API behavior

Add notes about default highlights contents, highlightScores/summary
preservation from responses, description resolution order, and
100-result cap.

* perf: add vitest test perf workflows

* fix(ci): harden changed extension diff fallback

* fix(telegram): harden grammy seams across tests

* refactor: extract exec outcome and tool result helpers

* test: isolate exec foreground failure coverage

* fix(test): allow empty extension lane

* perf: enable vitest fs module cache by default

* fix(cli): route plugin logs to stderr during --json output

* fix(cli): route deferred plugin logs to stderr in status --json

* fix: keep status --json stdout clean (openclaw#52449) (thanks @cgdusek)

* refactor(ci): collapse fast setup jobs into preflight

* fix(exec): accept runtime failure kind in formatter

* fix: include .env file vars in gateway service environment on install

When building the gateway install plan, read and parse
~/.openclaw/.env (or $OPENCLAW_STATE_DIR/.env) and merge those
key-value pairs into the service environment at the lowest
priority — below config env vars, auth-profile refs, and the
core service environment (HOME, PATH, OPENCLAW_*).

This ensures that user-defined secrets stored in .env (e.g.
BRAVE_API_KEY, OPENROUTER_API_KEY, DISCORD_BOT_TOKEN) are
embedded in the LaunchAgent plist (macOS), systemd unit (Linux),
and Scheduled Task (Windows) at install time, rather than
relying solely on the gateway process loading them via
dotenv.config() at startup.

Previously, on macOS the LaunchAgent plist never included .env
vars, which meant:
- launchctl print did not show user secrets (hard to debug)
- Child processes spawned before dotenv loaded had no access
- If the same key existed in both .env and the plist, the stale
  plist value won via dotenv override:false semantics

Dangerous host env vars (NODE_OPTIONS, LD_PRELOAD, etc.) are
filtered using the same security policy applied to config env
vars.

Fixes openclaw#37101
Relates to openclaw#22663

* fix: normalize env var keys and isolate tests from real .env

- Apply normalizeEnvVarKey({ portable: true }) before security
  filtering, matching the established pattern in env-vars.ts.
  Rejects non-portable key names (spaces, special chars) that
  would produce invalid plist/systemd syntax.

- Isolate existing tests from the developer's real ~/.openclaw/.env
  by providing a temp HOME directory, preventing flaky failures
  when the test machine has a populated .env file.

* fix: narrow exec exit failure kind typing

* fix(test): isolate flaky extension lanes

* feat(web-search): add DuckDuckGo bundled plugin (openclaw#52629)

* feat(web-search): add DuckDuckGo bundled plugin

* chore(changelog): restore main changelog

* fix(web-search): harden DuckDuckGo challenge detection

* refactor: split durable service env helpers

* refactor: extract gateway install token helpers

* fix(web-search): mark DuckDuckGo experimental

* docs(tools): update DuckDuckGo Search for landed plugin code

- Mark as experimental (not just unofficial)
- Add region and safeSearch tool parameters (from DDG schema)
- Add plugin config example for region/safeSearch defaults
- Document auto-detection order (100 = last)
- Note SafeSearch defaults to moderate
- Verified against extensions/duckduckgo/src/

* fix(agents): deny local MEDIA paths for MCP results

* Usage: include reset and deleted session archives (openclaw#43215)

Merged via squash.

Prepared head SHA: 49ed6c2
Co-authored-by: rcrick <[email protected]>
Co-authored-by: frankekn <[email protected]>
Reviewed-by: @frankekn

* docs(tools): soften DDG wording (scrapes -> pulls/gathers)

* fix(build): add stable memory-cli dist entry (openclaw#51759)

Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: Frank <[email protected]>

* refactor!: drop legacy CLAWDBOT env compatibility

* refactor!: remove moltbot state-dir migration fallback

* fix(gateway): preserve async hook ingress provenance

* fix(ci): write dist build stamp after builds

* perf: trim vitest hot imports and refresh manifests

* fix(security): unwrap time dispatch wrappers

* fix(plugin-sdk): fall back to src root alias files

* fix(ci): skip docs-only preflight pnpm audit

* docs(changelog): note time exec approval fix

* docs: refresh plugin-sdk api baseline

* fix(runtime): make dist-runtime staging idempotent

* fix(media): bound remote error-body snippet reads

* fix(gateway): gate internal command persistence mutations

* fix: restrict remote marketplace plugin sources

* fix(runtime): skip peer resolution for bundled plugin deps

* docs(agents): prefer current test model examples

* fix(exec): escape invisible approval filler chars

* test(models): refresh example model fixtures

* fix(security): unify dispatch wrapper approval hardening

* fix(security): harden explicit-proxy SSRF pinning

* fix: gate synology chat reply name matching

* docs: clarify sessions_spawn ACP vs subagent policies

* refactor(exec): split wrapper resolution modules

* refactor(exec): make dispatch wrapper semantics spec-driven

* refactor(exec): share wrapper trust planning

* refactor(exec): rename wrapper plans for trust semantics

* fix: include .npmrc in onboard docker build

* test: trim docker live auth mounts

* Docs: refresh config baseline for Synology Chat

* refactor: clarify synology delivery identity names

* refactor: centralize synology dangerous name matching

* refactor: narrow synology legacy name lookup

* refactor: audit synology dangerous name matching

* refactor: dedupe synology config schema

* fix: normalize scoped vitest filter paths

* fix(voice-call): harden webhook pre-auth guards

* fix(synology-chat): fail closed shared webhook paths

* docs: credit nexrin in synology changelog

* test: fix base vitest thread regressions

* test: finish base vitest thread fixture fixes

* test(voice-call): accept oversize webhook socket resets

* test: honor env auth in gateway live probes

* fix: harden plugin docker e2e

* Docs: align MiniMax examples with M2.7

* fix(ci): restore stale guardrails and baselines

* Test: isolate qr dashboard integration suite

* Gateway: resolve fallback plugin context lazily

* fix: bind bootstrap setup codes to node profile

* fix(tlon): unify settings reconciliation semantics

* refactor(synology-chat): type startup webhook path policy

* docs(synology-chat): clarify multi-account webhook paths

* refactor: unify minimax model and failover live policies

* docs: sync minimax m2.7 references

* fix: harden Windows Parallels smoke installs

* docs: reorder unreleased changelog by user impact

* refactor: remove embedded runner cwd mutation

* Infra: support shell carrier allow-always approvals

* refactor: centralize bootstrap profile handling

* refactor: reuse canonical setup bootstrap profile

* fix(plugin-sdk): resolve hashed diagnostic events chunks

* fix(plugin-sdk): normalize hashed diagnostic event exports

* test: fix ci env-sensitive assertions

* fix(gateway): fail closed on unresolved discovery endpoints

* feat: add slash plugin installs

* fix(media): block remote-host file URLs in loaders

* fix(media): harden secondary local path seams

* test: harden no-isolate reply teardown

* docs(changelog): add Windows media security fix

* refactor(gateway): centralize discovery target handling

* test: narrow live transcript scaffolding strip

* test: fix ci docs drift and bun qr exit handling

* fix(browser): enforce node browser proxy allowProfiles

* refactor(media): share local file access guards

* test: stabilize ci test harnesses

* test: harden no-isolate test module resets

* fix(plugins): preserve live hook registry during gateway runs

* test: fix channel summary registry setup

* test: harden isolated test mocks

* chore(plugins): remove opik investigation checkpoints

* ACPX: align pinned runtime version (openclaw#52730)

* ACPX: align pinned runtime version

* ACPX: drop version example from help text

* test: stop leaking image workspace temp dirs

* fix(android): gate canvas bridge to trusted pages (openclaw#52722)

* fix(android): gate canvas bridge to trusted pages

* fix(changelog): note android canvas bridge gating

* Update apps/android/app/src/main/java/ai/openclaw/app/node/CanvasActionTrust.kt

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(android): snapshot canvas URL on UI thread

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test: isolate base vitest thread blockers

* fix: sync agent and autoreply e2e updates

* test: harden no-isolate mocked module resets

* docs: reorder unreleased changelog

* fix(changelog): note windows media path guardrails (openclaw#52738)

* fix: alphabetize web search provider listings

* docs: clarify unreleased breaking changes

* test: harden ci isolated mocks

* fix: align websocket stream fallback types

* test: finish no-isolate suite hardening

* style: format image-generation runtime tests

* fix(memory-core): register memory tools independently to prevent coupled failure (openclaw#52668)

Merged via admin squash because current required CI failures are inherited from base and match latest `main` failures outside this PR's `memory-core` surface.

Prepared head SHA: df7f968
Co-authored-by: artwalker <[email protected]>
Reviewed-by: @frankekn

* fix(status): recompute fallback context window (openclaw#51795)

* fix(status): recompute fallback context window

* fix(status): keep live context token caps on fallback

* fix(status): preserve fallback runtime context windows

* fix(status): preserve configured fallback context caps

* fix(status): keep provider-aware transcript context lookups

* fix(status): preserve explicit fallback context caps

* fix(status): clamp fallback configured context caps

* fix(status): keep raw runtime slash ids

* fix(status): refresh plugin-sdk api baseline

* fix(status): preserve fallback context lookup

* test(status): refresh plugin-sdk api baseline

* fix(status): keep runtime slash-id context lookup

---------

Co-authored-by: create <[email protected]>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: RichardCao <[email protected]>

* fix(telegram): make buttons schema optional in message tool

The Telegram plugin injects a `buttons` property into the message tool
schema via `createMessageToolButtonsSchema()`, but without wrapping it
in `Type.Optional()`. This causes TypeBox to include `buttons` in the
JSON Schema `required` array.

In isolated sessions (e.g. cron jobs) where no `currentChannel` is set,
all plugin schemas are merged into the message tool. When the LLM calls
the message tool without a `buttons` parameter, AJV validation fails
with: `buttons: must have required property 'buttons'`.

Wrap the buttons schema in `Type.Optional()` so it is not required.

* fix: keep message-tool buttons optional for Telegram and Mattermost (openclaw#52589) (thanks @tylerliu612)

* test: update codex test fixtures to gpt-5.4

* fix: repair runtime seams after rebase

* fix: restore Telegram topic announce delivery (openclaw#51688) (thanks @mvanhorn)

When `replyLike.text` or `replyLike.caption` is an unexpected
non-string value (edge case from some Telegram API responses),
the reply body was coerced to "[object Object]" via string
concatenation. Add a `typeof === "string"` guard to gracefully
fall back to empty string, matching the existing pattern used
for `quoteText` in the same function.

Co-authored-by: Penchan <[email protected]>

* docs: sync generated release baselines

* test: isolate pi embedded model thread fixtures

* fix: restore provider runtime lazy boundary

* fix: preserve Telegram reply context text (openclaw#50500) (thanks @p3nchan)

* fix: guard Telegram reply context text (openclaw#50500) (thanks @p3nchan)

* fix: preserve Telegram reply caption fallback (openclaw#50500) (thanks @p3nchan)

---------

Co-authored-by: Ayaan Zaidi <[email protected]>

* fix: harden gateway SIGTERM shutdown (openclaw#51242) (thanks @juliabush)

* fix: increase shutdown timeout to avoid SIGTERM hang

* fix(telegram): abort polling fetch on shutdown to prevent SIGTERM hang

* fix(gateway): enforce hard exit on shutdown timeout for SIGTERM

* fix: tighten gateway shutdown watchdog

* fix: harden gateway SIGTERM shutdown (openclaw#51242) (thanks @juliabush)

---------

Co-authored-by: Ayaan Zaidi <[email protected]>

* build: prepare 2026.3.22-beta.1

* fix: restore provider runtime lazy boundary

* test: add parallels npm update smoke

* test: split pi embedded model thread fixtures

* fix: stop browser server tests from launching real chrome

* test: stabilize live provider docker probes

* fix: restart windows gateway after npm update

* test: isolate server-context browser harness imports

* test: inject model runtime hooks for thread-safe tests

* test: snapshot ci timeout investigation

* test: target gemini 3.1 flash alias

* test: stabilize trigger handling and hook e2e tests

* build: prepare 2026.3.22

---------

Co-authored-by: Stephen Schoettler <[email protected]>
Co-authored-by: Peter Steinberger <[email protected]>
Co-authored-by: Vincent Koc <[email protected]>
Co-authored-by: create <[email protected]>
Co-authored-by: moltbot886 <[email protected]>
Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
Co-authored-by: CodeForgeNet <[email protected]>
Co-authored-by: Martin Garramon <[email protected]>
Co-authored-by: François Martin <[email protected]>
Co-authored-by: Josh Lehman <[email protected]>
Co-authored-by: Charles Dusek <[email protected]>
Co-authored-by: Kevin ONeill <[email protected]>
Co-authored-by: Rick_Xu <[email protected]>
Co-authored-by: rcrick <[email protected]>
Co-authored-by: frankekn <[email protected]>
Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: Frank <[email protected]>
Co-authored-by: scoootscooob <[email protected]>
Co-authored-by: ruochen <[email protected]>
Co-authored-by: Onur Solmaz <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: artwalker <[email protected]>
Co-authored-by: RichardCao <[email protected]>
Co-authored-by: RichardCao <[email protected]>
Co-authored-by: liuyang <[email protected]>
Co-authored-by: Ayaan Zaidi <[email protected]>
Co-authored-by: Matt Van Horn <[email protected]>
Co-authored-by: Penchan <[email protected]>
Co-authored-by: Penchan <[email protected]>
Co-authored-by: Julia Bush <[email protected]>
joe2643 added a commit to joe2643/openclaw that referenced this pull request Mar 26, 2026
…d off (#2)

* refactor(plugins): move remaining channel and provider ownership out of src

* refactor(plugins): finish provider and whatsapp cleanup

* fix(gateway): pass process.env in status command probe auth to resolve SecretRef

Fixes openclaw#52360

resolveGatewayProbeAuthSafe was called from status-all.ts without an
env argument, causing the credential resolution chain to fall back to
an empty object instead of process.env. This made env-backed SecretRef
tokens (gateway.auth.token, Telegram botToken, etc.) appear unresolved
in the status command path even when the runtime was healthy.

Added process.env as default fallback in buildGatewayProbeCredentialPolicy
and passed env explicitly from status-all.ts callers.

Related: openclaw#33070, openclaw#38973, openclaw#39415, openclaw#46014, openclaw#49730

* fix(status): resolve only selected probe-auth branch and fix plain status path

Address two Codex P1/P2 issues:

1. (P1) Plain 'openclaw status' and 'openclaw status --json' still went
   through the sync resolveGatewayProbeAuthSafe path in
   status.gateway-probe.ts, which cannot expand SecretRef objects.
   Switched to async resolveGatewayProbeAuthSafeWithSecretInputs.

2. (P2) status-all.ts was eagerly resolving both local and remote probe
   auth before deciding which to use. A stale SecretRef in the unused
   branch could abort the command. Collapsed to a single resolution
   call using the correct mode upfront.

Updated status.scan.test.ts to use mockResolvedValue since
resolveGatewayProbeAuthResolution is now async.

* fix(status): await resolveGatewayProbeAuthResolution in scan.shared

Function is now async after switching to resolveGatewayProbeAuthSafeWithSecretInputs.
Missing await caused TS error: Property 'auth' does not exist on type 'Promise<...>'.

* fix: finish gateway probe auth landing (openclaw#52513) (thanks @CodeForgeNet)

* fix: finish gateway probe auth landing (openclaw#52513) (thanks @CodeForgeNet)

* test: clear msteams gate drift for gateway probe auth landing (openclaw#52513) (thanks @CodeForgeNet)

* fix(exec): return plain-text tool result on failure instead of raw JSON

When an exec command fails (e.g. timeout), the tool previously rejected
with an Error, which the tool adapter caught and wrapped in a JSON object
({ status, tool, error }). The model then received this raw JSON as the
tool result and could parrot it verbatim to the user.

Now exec failures resolve with a proper tool result containing the error
as human-readable text in content[], matching the success path structure.
The model sees plain text it can naturally incorporate into its reply.

Also fixes a pre-existing format issue in update-cli.test.ts.

Fixes openclaw#52484

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

* fix: finish exec tool failure landing (openclaw#52508) (thanks @martingarramon)

* fix(openshell): bundle upstream cli fallback

* perf(reply): lazy-load session store writes

* fix(build): restore plugin-sdk and line compat after refactor

* refactor(kilocode): route shared model constants through core seam

* refactor(plugin-sdk): route core provider and telegram seams through sdk barrels

* fix(acp): preserve hidden thought chunks from gateway chat

* fix(docs): rename 'Channel Options' to 'Options' in sdk-entrypoints

This heading labels definePluginEntry options (generic, not channel-specific).
Another agent reverted the previous fix during a merge.

* fix(line): narrow plugin-sdk seams after refactor

* test(voice-call): cover helper utilities

* test(voice-call): cover manager and api helpers

* fix(acp): preserve hidden thought replay on session load

* test(voice-call): cover twilio and reaper helpers

* docs(changelog): note ACP hidden thought replay fix

* test(voice-call): cover utility and tailscale helpers

* fix(ci): resync generated baselines and line runtime seam

* fix(docs): remove duplicate '### Options' headings (MD024)

* fix(ci): restore plugin manifests and boundary tests

* style(docs): format sdk entrypoints doc

* docs(config): refresh generated baseline

* test(voice-call): cover outbound call flow helpers

* fix(ci): repair tts and matrix refactor fallout

* fix(ci): repair voice-call typing and provider contracts

* fix(ci): satisfy voice-call typing and extension boundaries

* Remove personal references from docs (openclaw#25260)

* docs: remove personal references from AGENTS.md

* docs: remove personal reference from sag skill

* docs: note generic agent guidance cleanup

* Update CHANGELOG.md

---------

Co-authored-by: Josh Lehman <[email protected]>
Co-authored-by: Vincent Koc <[email protected]>

* fix(plugins): route keyed queue imports through core (openclaw#52608)

* fix(matrix): preserve send aliases and voice intent

* fix(build): repair stale plugin sdk surfaces

* fix(plugin-sdk): export line runtime subpath

* fix(auth): route copilot login through sdk seam

* feat(web-search): add bundled Exa plugin (openclaw#52617)

* test(msteams): await async setup status lines

* fix(whatsapp): remove outbound runtime cycle

* fix(plugin-sdk): fast-path root diagnostic subscriptions

* fix(exa): align freshness typing and config docs

* fix(matrix): avoid touching dropped room bindings

* fix(web-search): align Exa plugin with current API

* docs(tools): add DuckDuckGo Search provider page

New page: tools/duckduckgo-search.md
- Key-free fallback provider, no API key needed
- Clear Warning about unofficial HTML-based integration
- Limitations section covering bot-challenge risk and reliability
- CardGroup showing good-for vs not-recommended-for use cases

Updated: tools/web.md with DuckDuckGo in CardGroup and comparison table
Updated: docs.json nav and redirect

* test(telegram): align webhook grammy mock

* docs(tools): add Exa Search page, align all search provider docs

New page: tools/exa-search.md
- Neural/keyword/hybrid search modes with content extraction
- Tool parameters including contents (highlights, text, summary)
- Search mode reference table

Rewritten: tools/duckduckgo-search.md
- Aligned to consistent template (Setup, Config, Tool parameters, Notes, Related)
- Simplified from previous version

Aligned across all providers:
- Every search page now ends with a consistent ## Related section
- Replaced 'See [Web tools]' with proper Related links
- Added Exa + DuckDuckGo to web.md overview CardGroup and comparison table
- Added Exa to docs.json nav and redirects

* fix(telegram): inject media loader through bot deps

* fix(ci): harden telegram seams and cap job timeouts

* docs(tools): update Exa Search notes for current API behavior

Add notes about default highlights contents, highlightScores/summary
preservation from responses, description resolution order, and
100-result cap.

* perf: add vitest test perf workflows

* fix(ci): harden changed extension diff fallback

* fix(telegram): harden grammy seams across tests

* refactor: extract exec outcome and tool result helpers

* test: isolate exec foreground failure coverage

* fix(test): allow empty extension lane

* perf: enable vitest fs module cache by default

* fix(cli): route plugin logs to stderr during --json output

* fix(cli): route deferred plugin logs to stderr in status --json

* fix: keep status --json stdout clean (openclaw#52449) (thanks @cgdusek)

* refactor(ci): collapse fast setup jobs into preflight

* fix(exec): accept runtime failure kind in formatter

* fix: include .env file vars in gateway service environment on install

When building the gateway install plan, read and parse
~/.openclaw/.env (or $OPENCLAW_STATE_DIR/.env) and merge those
key-value pairs into the service environment at the lowest
priority — below config env vars, auth-profile refs, and the
core service environment (HOME, PATH, OPENCLAW_*).

This ensures that user-defined secrets stored in .env (e.g.
BRAVE_API_KEY, OPENROUTER_API_KEY, DISCORD_BOT_TOKEN) are
embedded in the LaunchAgent plist (macOS), systemd unit (Linux),
and Scheduled Task (Windows) at install time, rather than
relying solely on the gateway process loading them via
dotenv.config() at startup.

Previously, on macOS the LaunchAgent plist never included .env
vars, which meant:
- launchctl print did not show user secrets (hard to debug)
- Child processes spawned before dotenv loaded had no access
- If the same key existed in both .env and the plist, the stale
  plist value won via dotenv override:false semantics

Dangerous host env vars (NODE_OPTIONS, LD_PRELOAD, etc.) are
filtered using the same security policy applied to config env
vars.

Fixes openclaw#37101
Relates to openclaw#22663

* fix: normalize env var keys and isolate tests from real .env

- Apply normalizeEnvVarKey({ portable: true }) before security
  filtering, matching the established pattern in env-vars.ts.
  Rejects non-portable key names (spaces, special chars) that
  would produce invalid plist/systemd syntax.

- Isolate existing tests from the developer's real ~/.openclaw/.env
  by providing a temp HOME directory, preventing flaky failures
  when the test machine has a populated .env file.

* fix: narrow exec exit failure kind typing

* fix(test): isolate flaky extension lanes

* feat(web-search): add DuckDuckGo bundled plugin (openclaw#52629)

* feat(web-search): add DuckDuckGo bundled plugin

* chore(changelog): restore main changelog

* fix(web-search): harden DuckDuckGo challenge detection

* refactor: split durable service env helpers

* refactor: extract gateway install token helpers

* fix(web-search): mark DuckDuckGo experimental

* docs(tools): update DuckDuckGo Search for landed plugin code

- Mark as experimental (not just unofficial)
- Add region and safeSearch tool parameters (from DDG schema)
- Add plugin config example for region/safeSearch defaults
- Document auto-detection order (100 = last)
- Note SafeSearch defaults to moderate
- Verified against extensions/duckduckgo/src/

* fix(agents): deny local MEDIA paths for MCP results

* Usage: include reset and deleted session archives (openclaw#43215)

Merged via squash.

Prepared head SHA: 49ed6c2
Co-authored-by: rcrick <[email protected]>
Co-authored-by: frankekn <[email protected]>
Reviewed-by: @frankekn

* docs(tools): soften DDG wording (scrapes -> pulls/gathers)

* fix(build): add stable memory-cli dist entry (openclaw#51759)

Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: Frank <[email protected]>

* refactor!: drop legacy CLAWDBOT env compatibility

* refactor!: remove moltbot state-dir migration fallback

* fix(gateway): preserve async hook ingress provenance

* fix(ci): write dist build stamp after builds

* perf: trim vitest hot imports and refresh manifests

* fix(security): unwrap time dispatch wrappers

* fix(plugin-sdk): fall back to src root alias files

* fix(ci): skip docs-only preflight pnpm audit

* docs(changelog): note time exec approval fix

* docs: refresh plugin-sdk api baseline

* fix(runtime): make dist-runtime staging idempotent

* fix(media): bound remote error-body snippet reads

* fix(gateway): gate internal command persistence mutations

* fix: restrict remote marketplace plugin sources

* fix(runtime): skip peer resolution for bundled plugin deps

* docs(agents): prefer current test model examples

* fix(exec): escape invisible approval filler chars

* test(models): refresh example model fixtures

* fix(security): unify dispatch wrapper approval hardening

* fix(security): harden explicit-proxy SSRF pinning

* fix: gate synology chat reply name matching

* docs: clarify sessions_spawn ACP vs subagent policies

* refactor(exec): split wrapper resolution modules

* refactor(exec): make dispatch wrapper semantics spec-driven

* refactor(exec): share wrapper trust planning

* refactor(exec): rename wrapper plans for trust semantics

* fix: include .npmrc in onboard docker build

* test: trim docker live auth mounts

* Docs: refresh config baseline for Synology Chat

* refactor: clarify synology delivery identity names

* refactor: centralize synology dangerous name matching

* refactor: narrow synology legacy name lookup

* refactor: audit synology dangerous name matching

* refactor: dedupe synology config schema

* fix: normalize scoped vitest filter paths

* fix(voice-call): harden webhook pre-auth guards

* fix(synology-chat): fail closed shared webhook paths

* docs: credit nexrin in synology changelog

* test: fix base vitest thread regressions

* test: finish base vitest thread fixture fixes

* test(voice-call): accept oversize webhook socket resets

* test: honor env auth in gateway live probes

* fix: harden plugin docker e2e

* Docs: align MiniMax examples with M2.7

* fix(ci): restore stale guardrails and baselines

* Test: isolate qr dashboard integration suite

* Gateway: resolve fallback plugin context lazily

* fix: bind bootstrap setup codes to node profile

* fix(tlon): unify settings reconciliation semantics

* refactor(synology-chat): type startup webhook path policy

* docs(synology-chat): clarify multi-account webhook paths

* refactor: unify minimax model and failover live policies

* docs: sync minimax m2.7 references

* fix: harden Windows Parallels smoke installs

* docs: reorder unreleased changelog by user impact

* refactor: remove embedded runner cwd mutation

* Infra: support shell carrier allow-always approvals

* refactor: centralize bootstrap profile handling

* refactor: reuse canonical setup bootstrap profile

* fix(plugin-sdk): resolve hashed diagnostic events chunks

* fix(plugin-sdk): normalize hashed diagnostic event exports

* test: fix ci env-sensitive assertions

* fix(gateway): fail closed on unresolved discovery endpoints

* feat: add slash plugin installs

* fix(media): block remote-host file URLs in loaders

* fix(media): harden secondary local path seams

* test: harden no-isolate reply teardown

* docs(changelog): add Windows media security fix

* refactor(gateway): centralize discovery target handling

* test: narrow live transcript scaffolding strip

* test: fix ci docs drift and bun qr exit handling

* fix(browser): enforce node browser proxy allowProfiles

* refactor(media): share local file access guards

* test: stabilize ci test harnesses

* test: harden no-isolate test module resets

* fix(plugins): preserve live hook registry during gateway runs

* test: fix channel summary registry setup

* test: harden isolated test mocks

* chore(plugins): remove opik investigation checkpoints

* ACPX: align pinned runtime version (openclaw#52730)

* ACPX: align pinned runtime version

* ACPX: drop version example from help text

* test: stop leaking image workspace temp dirs

* fix(android): gate canvas bridge to trusted pages (openclaw#52722)

* fix(android): gate canvas bridge to trusted pages

* fix(changelog): note android canvas bridge gating

* Update apps/android/app/src/main/java/ai/openclaw/app/node/CanvasActionTrust.kt

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(android): snapshot canvas URL on UI thread

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test: isolate base vitest thread blockers

* fix: sync agent and autoreply e2e updates

* test: harden no-isolate mocked module resets

* docs: reorder unreleased changelog

* fix(changelog): note windows media path guardrails (openclaw#52738)

* fix: alphabetize web search provider listings

* docs: clarify unreleased breaking changes

* test: harden ci isolated mocks

* fix: align websocket stream fallback types

* test: finish no-isolate suite hardening

* style: format image-generation runtime tests

* fix(memory-core): register memory tools independently to prevent coupled failure (openclaw#52668)

Merged via admin squash because current required CI failures are inherited from base and match latest `main` failures outside this PR's `memory-core` surface.

Prepared head SHA: df7f968
Co-authored-by: artwalker <[email protected]>
Reviewed-by: @frankekn

* fix(status): recompute fallback context window (openclaw#51795)

* fix(status): recompute fallback context window

* fix(status): keep live context token caps on fallback

* fix(status): preserve fallback runtime context windows

* fix(status): preserve configured fallback context caps

* fix(status): keep provider-aware transcript context lookups

* fix(status): preserve explicit fallback context caps

* fix(status): clamp fallback configured context caps

* fix(status): keep raw runtime slash ids

* fix(status): refresh plugin-sdk api baseline

* fix(status): preserve fallback context lookup

* test(status): refresh plugin-sdk api baseline

* fix(status): keep runtime slash-id context lookup

---------

Co-authored-by: create <[email protected]>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: RichardCao <[email protected]>

* fix(telegram): make buttons schema optional in message tool

The Telegram plugin injects a `buttons` property into the message tool
schema via `createMessageToolButtonsSchema()`, but without wrapping it
in `Type.Optional()`. This causes TypeBox to include `buttons` in the
JSON Schema `required` array.

In isolated sessions (e.g. cron jobs) where no `currentChannel` is set,
all plugin schemas are merged into the message tool. When the LLM calls
the message tool without a `buttons` parameter, AJV validation fails
with: `buttons: must have required property 'buttons'`.

Wrap the buttons schema in `Type.Optional()` so it is not required.

* fix: keep message-tool buttons optional for Telegram and Mattermost (openclaw#52589) (thanks @tylerliu612)

* test: update codex test fixtures to gpt-5.4

* fix: repair runtime seams after rebase

* fix: restore Telegram topic announce delivery (openclaw#51688) (thanks @mvanhorn)

When `replyLike.text` or `replyLike.caption` is an unexpected
non-string value (edge case from some Telegram API responses),
the reply body was coerced to "[object Object]" via string
concatenation. Add a `typeof === "string"` guard to gracefully
fall back to empty string, matching the existing pattern used
for `quoteText` in the same function.

Co-authored-by: Penchan <[email protected]>

* docs: sync generated release baselines

* test: isolate pi embedded model thread fixtures

* fix: restore provider runtime lazy boundary

* fix: preserve Telegram reply context text (openclaw#50500) (thanks @p3nchan)

* fix: guard Telegram reply context text (openclaw#50500) (thanks @p3nchan)

* fix: preserve Telegram reply caption fallback (openclaw#50500) (thanks @p3nchan)

---------

Co-authored-by: Ayaan Zaidi <[email protected]>

* fix: harden gateway SIGTERM shutdown (openclaw#51242) (thanks @juliabush)

* fix: increase shutdown timeout to avoid SIGTERM hang

* fix(telegram): abort polling fetch on shutdown to prevent SIGTERM hang

* fix(gateway): enforce hard exit on shutdown timeout for SIGTERM

* fix: tighten gateway shutdown watchdog

* fix: harden gateway SIGTERM shutdown (openclaw#51242) (thanks @juliabush)

---------

Co-authored-by: Ayaan Zaidi <[email protected]>

* build: prepare 2026.3.22-beta.1

* fix: restore provider runtime lazy boundary

* test: add parallels npm update smoke

* test: split pi embedded model thread fixtures

* fix: stop browser server tests from launching real chrome

* test: stabilize live provider docker probes

* fix: restart windows gateway after npm update

* test: isolate server-context browser harness imports

* test: inject model runtime hooks for thread-safe tests

* test: snapshot ci timeout investigation

* test: target gemini 3.1 flash alias

* test: stabilize trigger handling and hook e2e tests

* build: prepare 2026.3.22

* test: harden channel suite isolation

* test: inject thread-safe deps for agent tools

* test: raise timeout for slow provider auth normalization

* ci: stabilize windows and bun unit lanes

* test: inject thread-safe gateway and ACP seams

* test: isolate pi model and reset-model thread fixtures

* build: prepare 2026.3.23

* test: inject image-tool provider deps for raw threads

* test: stabilize e2e module isolation

* test: decouple vitest config checks from ambient env

* fix: harden parallels smoke agent invocation

* test: avoid repo-root perf profile artifacts

* test: inject thread-safe base seams

* fix: document Telegram asDocument alias (openclaw#52461) (thanks @bakhtiersizhaev)

* feat(telegram): add asDocument param to message tool

Adds `asDocument` as a user-facing alias for the existing `forceDocument`
parameter in the message tool. When set to `true`, media files (images,
videos, GIFs) are sent via `sendDocument` instead of `sendPhoto`/
`sendVideo`/`sendAnimation`, preserving the original file quality
without Telegram compression.

This is useful when agents need to deliver high-resolution images or
uncompressed files to users via Telegram.

`asDocument` is intentionally an alias rather than a replacement — the
existing `forceDocument` continues to work unchanged.

Changes:
- src/agents/tools/message-tool.ts: add asDocument to send schema
- src/agents/tools/telegram-actions.ts: OR asDocument into forceDocument
- src/infra/outbound/message-action-runner.ts: same OR logic for outbound path
- extensions/telegram/src/channel-actions.ts: read and forward asDocument
- src/channels/plugins/actions/actions.test.ts: add test case

* fix: restore channel-actions.ts to main version (rebase conflict fix)

* fix(test): match asDocument test payload to actual params structure

* fix(telegram): preserve forceDocument alias semantics

* fix: document Telegram asDocument alias (openclaw#52461) (thanks @bakhtiersizhaev)

---------

Co-authored-by: Бахтиер Сижаев <[email protected]>
Co-authored-by: Ayaan Zaidi <[email protected]>

* fix: refactor deepseek bundled plugin (openclaw#48762) (thanks @07akioni)

* fix: declare typebox runtime dep for mattermost plugin

* test: reset line webhook mocks between cases

* test: split attempt spawn-workspace thread fixtures

* test: remove replaced spawn-workspace monolith

* refactor: isolate attempt context engine thread helpers

* CI: remove npm release preview workflow (openclaw#52825)

* CI: remove npm release preview workflow

* Docs: align release maintainer skill with manual publish

* Docs: expand release maintainer skill flow

* test: stabilize gateway thread harness

* test: fix status plugin pagination expectation

* test: harden channel suite isolation

* build: sync lockfile for mattermost plugin

* fix: ensure env proxy dispatcher before MiniMax and OpenAI Codex OAuth flows (openclaw#52228)

Verified:
- pnpm install --frozen-lockfile
- NPM_CONFIG_CACHE=/tmp/openclaw-npm-cache-52228 pnpm build
- pnpm check
- pnpm test:macmini (failed on inherited pre-existing plugin contract test: src/plugins/contracts/registry.contract.test.ts missing deepseek in bundled provider contract registry outside this PR surface)

Co-authored-by: openperf <[email protected]>
Co-authored-by: Tak Hoffman <[email protected]>

* fix: restore ci gates

* test: stabilize channel ci gate

* docs: refresh generated config baseline

* release: verify control-ui assets are included in npm tarball

* release-check: include stderr/stdout when npm pack fails

* release: add changelog for control UI tarball check

* fix: keep session transcript pointers fresh after compaction (openclaw#50688)

Co-authored-by: Frank Yang <[email protected]>

* fix(msteams): isolate probe test env credentials

* release: automate macOS publishing (openclaw#52853)

* release: automate macOS publishing

* release: keep mac appcast in openclaw repo

* release: add preflight-only release workflow runs

* release: keep appcast updates manual

* release: generate signed appcast as workflow artifact

* release: require preflight before publish

* release: require mac app for every release

* docs: clarify every release ships mac app

* release: document Sparkle feed and SHA rules

* release: keep publish flow tag-based

* release: stabilize mac appcast flow

* release: document local mac fallback

* Update CHANGELOG.md

* Improve PR template regression prompts

* fix(agents): preserve anthropic thinking block order (openclaw#52961)

* fix(release): ship bundled plugins in pack artifacts

* fix(config): keep built-in channels out of plugin allowlists (openclaw#52964)

* fix(config): keep built-in channels out of plugin allowlists

* docs(changelog): note doctor whatsapp allowlist fix

* docs(changelog): move doctor whatsapp fix to top

* Update CHANGELOG.md

* fix(config): keep built-in auto-enable idempotent

* fix(release): preserve shipped channel surfaces in npm tar (openclaw#52913)

* fix(channels): ship official channel catalog (openclaw#52838)

* fix(release): keep shipped bundles in npm tar (openclaw#52838)

* build(release): fix rebased release-check helpers (openclaw#52838)

* fix(gateway): harden supervised lock and browser attach readiness

* fix(matrix): avoid duplicate runtime api exports

* fix(gateway): avoid probe false negatives after connect

* docs(changelog): note release and matrix fixes

* fix(plugins): unblock Discord/Slack message tool sends and Feishu media (openclaw#52991)

* fix(plugins): unblock Discord and Slack message tool payloads

* docs(changelog): note Discord Slack and Feishu message fixes

* fix(channels): preserve external catalog overrides (openclaw#52988)

* fix(channels): preserve external catalog overrides

* fix(channels): clarify catalog precedence

* fix(channels): respect overridden install specs

* fix(gateway): require admin for agent session reset

* fix(voice-call): stabilize plivo v2 replay keys

* fix(gateway): require auth for canvas routes

* feat(context-pruning): cache media to disk during pruning instead of stripping

When cacheMedia is enabled, pruned image blocks are saved to
~/.openclaw/media/cache/ and replaced with a file path reference
so the agent can re-read them on demand. Includes TTL cleanup
and session-scoped cache management.

* feat(media): add media cache module for context pruning

* feat(whatsapp): make block streaming configurable instead of hardcoded off

---------

Co-authored-by: Vincent Koc <[email protected]>
Co-authored-by: CodeForgeNet <[email protected]>
Co-authored-by: Peter Steinberger <[email protected]>
Co-authored-by: Martin Garramon <[email protected]>
Co-authored-by: Claude Opus 4.6 (1M context) <[email protected]>
Co-authored-by: François Martin <[email protected]>
Co-authored-by: Josh Lehman <[email protected]>
Co-authored-by: Charles Dusek <[email protected]>
Co-authored-by: Kevin ONeill <[email protected]>
Co-authored-by: Rick_Xu <[email protected]>
Co-authored-by: rcrick <[email protected]>
Co-authored-by: frankekn <[email protected]>
Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: Frank <[email protected]>
Co-authored-by: scoootscooob <[email protected]>
Co-authored-by: ruochen <[email protected]>
Co-authored-by: Onur Solmaz <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: artwalker <[email protected]>
Co-authored-by: RichardCao <[email protected]>
Co-authored-by: create <[email protected]>
Co-authored-by: RichardCao <[email protected]>
Co-authored-by: liuyang <[email protected]>
Co-authored-by: Ayaan Zaidi <[email protected]>
Co-authored-by: Matt Van Horn <[email protected]>
Co-authored-by: Penchan <[email protected]>
Co-authored-by: Penchan <[email protected]>
Co-authored-by: Julia Bush <[email protected]>
Co-authored-by: Bakhtier Sizhaev <[email protected]>
Co-authored-by: Бахтиер Сижаев <[email protected]>
Co-authored-by: wangchunyue <[email protected]>
Co-authored-by: Tak Hoffman <[email protected]>
Co-authored-by: evann <[email protected]>
Co-authored-by: Robin Waslander <[email protected]>
Co-authored-by: Sathvik Veerapaneni <[email protected]>
Co-authored-by: Nimrod Gutman <[email protected]>
0x666c6f added a commit to 0x666c6f/openclaw that referenced this pull request Mar 26, 2026
…claw#105)

* fix(web-search): mark DuckDuckGo experimental

* docs(tools): update DuckDuckGo Search for landed plugin code

- Mark as experimental (not just unofficial)
- Add region and safeSearch tool parameters (from DDG schema)
- Add plugin config example for region/safeSearch defaults
- Document auto-detection order (100 = last)
- Note SafeSearch defaults to moderate
- Verified against extensions/duckduckgo/src/

* fix(agents): deny local MEDIA paths for MCP results

* Usage: include reset and deleted session archives (openclaw#43215)

Merged via squash.

Prepared head SHA: 49ed6c2
Co-authored-by: rcrick <[email protected]>
Co-authored-by: frankekn <[email protected]>
Reviewed-by: @frankekn

* docs(tools): soften DDG wording (scrapes -> pulls/gathers)

* fix(build): add stable memory-cli dist entry (openclaw#51759)

Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: Frank <[email protected]>

* refactor!: drop legacy CLAWDBOT env compatibility

* refactor!: remove moltbot state-dir migration fallback

* fix(gateway): preserve async hook ingress provenance

* fix(ci): write dist build stamp after builds

* perf: trim vitest hot imports and refresh manifests

* fix(security): unwrap time dispatch wrappers

* fix(plugin-sdk): fall back to src root alias files

* fix(ci): skip docs-only preflight pnpm audit

* docs(changelog): note time exec approval fix

* docs: refresh plugin-sdk api baseline

* fix(runtime): make dist-runtime staging idempotent

* fix(media): bound remote error-body snippet reads

* fix(gateway): gate internal command persistence mutations

* fix: restrict remote marketplace plugin sources

* fix(runtime): skip peer resolution for bundled plugin deps

* docs(agents): prefer current test model examples

* fix(exec): escape invisible approval filler chars

* test(models): refresh example model fixtures

* fix(security): unify dispatch wrapper approval hardening

* fix(security): harden explicit-proxy SSRF pinning

* fix: gate synology chat reply name matching

* docs: clarify sessions_spawn ACP vs subagent policies

* refactor(exec): split wrapper resolution modules

* refactor(exec): make dispatch wrapper semantics spec-driven

* refactor(exec): share wrapper trust planning

* refactor(exec): rename wrapper plans for trust semantics

* fix: include .npmrc in onboard docker build

* test: trim docker live auth mounts

* Docs: refresh config baseline for Synology Chat

* refactor: clarify synology delivery identity names

* refactor: centralize synology dangerous name matching

* refactor: narrow synology legacy name lookup

* refactor: audit synology dangerous name matching

* refactor: dedupe synology config schema

* fix: normalize scoped vitest filter paths

* fix(voice-call): harden webhook pre-auth guards

* fix(synology-chat): fail closed shared webhook paths

* docs: credit nexrin in synology changelog

* test: fix base vitest thread regressions

* test: finish base vitest thread fixture fixes

* test(voice-call): accept oversize webhook socket resets

* test: honor env auth in gateway live probes

* fix: harden plugin docker e2e

* Docs: align MiniMax examples with M2.7

* fix(ci): restore stale guardrails and baselines

* Test: isolate qr dashboard integration suite

* Gateway: resolve fallback plugin context lazily

* fix: bind bootstrap setup codes to node profile

* fix(tlon): unify settings reconciliation semantics

* refactor(synology-chat): type startup webhook path policy

* docs(synology-chat): clarify multi-account webhook paths

* refactor: unify minimax model and failover live policies

* docs: sync minimax m2.7 references

* fix: harden Windows Parallels smoke installs

* docs: reorder unreleased changelog by user impact

* refactor: remove embedded runner cwd mutation

* Infra: support shell carrier allow-always approvals

* refactor: centralize bootstrap profile handling

* refactor: reuse canonical setup bootstrap profile

* fix(plugin-sdk): resolve hashed diagnostic events chunks

* fix(plugin-sdk): normalize hashed diagnostic event exports

* test: fix ci env-sensitive assertions

* fix(gateway): fail closed on unresolved discovery endpoints

* feat: add slash plugin installs

* fix(media): block remote-host file URLs in loaders

* fix(media): harden secondary local path seams

* test: harden no-isolate reply teardown

* docs(changelog): add Windows media security fix

* refactor(gateway): centralize discovery target handling

* test: narrow live transcript scaffolding strip

* test: fix ci docs drift and bun qr exit handling

* fix(browser): enforce node browser proxy allowProfiles

* refactor(media): share local file access guards

* test: stabilize ci test harnesses

* test: harden no-isolate test module resets

* fix(plugins): preserve live hook registry during gateway runs

* test: fix channel summary registry setup

* test: harden isolated test mocks

* chore(plugins): remove opik investigation checkpoints

* ACPX: align pinned runtime version (openclaw#52730)

* ACPX: align pinned runtime version

* ACPX: drop version example from help text

* test: stop leaking image workspace temp dirs

* fix(android): gate canvas bridge to trusted pages (openclaw#52722)

* fix(android): gate canvas bridge to trusted pages

* fix(changelog): note android canvas bridge gating

* Update apps/android/app/src/main/java/ai/openclaw/app/node/CanvasActionTrust.kt

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* fix(android): snapshot canvas URL on UI thread

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* test: isolate base vitest thread blockers

* fix: sync agent and autoreply e2e updates

* test: harden no-isolate mocked module resets

* docs: reorder unreleased changelog

* fix(changelog): note windows media path guardrails (openclaw#52738)

* fix: alphabetize web search provider listings

* docs: clarify unreleased breaking changes

* test: harden ci isolated mocks

* fix: align websocket stream fallback types

* test: finish no-isolate suite hardening

* style: format image-generation runtime tests

* fix(memory-core): register memory tools independently to prevent coupled failure (openclaw#52668)

Merged via admin squash because current required CI failures are inherited from base and match latest `main` failures outside this PR's `memory-core` surface.

Prepared head SHA: df7f968
Co-authored-by: artwalker <[email protected]>
Reviewed-by: @frankekn

* fix(status): recompute fallback context window (openclaw#51795)

* fix(status): recompute fallback context window

* fix(status): keep live context token caps on fallback

* fix(status): preserve fallback runtime context windows

* fix(status): preserve configured fallback context caps

* fix(status): keep provider-aware transcript context lookups

* fix(status): preserve explicit fallback context caps

* fix(status): clamp fallback configured context caps

* fix(status): keep raw runtime slash ids

* fix(status): refresh plugin-sdk api baseline

* fix(status): preserve fallback context lookup

* test(status): refresh plugin-sdk api baseline

* fix(status): keep runtime slash-id context lookup

---------

Co-authored-by: create <[email protected]>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: RichardCao <[email protected]>

* fix(telegram): make buttons schema optional in message tool

The Telegram plugin injects a `buttons` property into the message tool
schema via `createMessageToolButtonsSchema()`, but without wrapping it
in `Type.Optional()`. This causes TypeBox to include `buttons` in the
JSON Schema `required` array.

In isolated sessions (e.g. cron jobs) where no `currentChannel` is set,
all plugin schemas are merged into the message tool. When the LLM calls
the message tool without a `buttons` parameter, AJV validation fails
with: `buttons: must have required property 'buttons'`.

Wrap the buttons schema in `Type.Optional()` so it is not required.

* fix: keep message-tool buttons optional for Telegram and Mattermost (openclaw#52589) (thanks @tylerliu612)

* test: update codex test fixtures to gpt-5.4

* fix: repair runtime seams after rebase

* fix: restore Telegram topic announce delivery (openclaw#51688) (thanks @mvanhorn)

When `replyLike.text` or `replyLike.caption` is an unexpected
non-string value (edge case from some Telegram API responses),
the reply body was coerced to "[object Object]" via string
concatenation. Add a `typeof === "string"` guard to gracefully
fall back to empty string, matching the existing pattern used
for `quoteText` in the same function.

Co-authored-by: Penchan <[email protected]>

* docs: sync generated release baselines

* test: isolate pi embedded model thread fixtures

* fix: restore provider runtime lazy boundary

* fix: preserve Telegram reply context text (openclaw#50500) (thanks @p3nchan)

* fix: guard Telegram reply context text (openclaw#50500) (thanks @p3nchan)

* fix: preserve Telegram reply caption fallback (openclaw#50500) (thanks @p3nchan)

---------

Co-authored-by: Ayaan Zaidi <[email protected]>

* fix: harden gateway SIGTERM shutdown (openclaw#51242) (thanks @juliabush)

* fix: increase shutdown timeout to avoid SIGTERM hang

* fix(telegram): abort polling fetch on shutdown to prevent SIGTERM hang

* fix(gateway): enforce hard exit on shutdown timeout for SIGTERM

* fix: tighten gateway shutdown watchdog

* fix: harden gateway SIGTERM shutdown (openclaw#51242) (thanks @juliabush)

---------

Co-authored-by: Ayaan Zaidi <[email protected]>

* build: prepare 2026.3.22-beta.1

* fix: restore provider runtime lazy boundary

* test: add parallels npm update smoke

* test: split pi embedded model thread fixtures

* fix: stop browser server tests from launching real chrome

* test: stabilize live provider docker probes

* fix: restart windows gateway after npm update

* test: isolate server-context browser harness imports

* test: inject model runtime hooks for thread-safe tests

* test: snapshot ci timeout investigation

* test: target gemini 3.1 flash alias

* test: stabilize trigger handling and hook e2e tests

* build: prepare 2026.3.22

* test: harden channel suite isolation

* test: inject thread-safe deps for agent tools

* test: raise timeout for slow provider auth normalization

* ci: stabilize windows and bun unit lanes

* test: inject thread-safe gateway and ACP seams

* test: isolate pi model and reset-model thread fixtures

* build: prepare 2026.3.23

* test: inject image-tool provider deps for raw threads

* test: stabilize e2e module isolation

* test: decouple vitest config checks from ambient env

* fix: harden parallels smoke agent invocation

* test: avoid repo-root perf profile artifacts

* test: inject thread-safe base seams

* fix: document Telegram asDocument alias (openclaw#52461) (thanks @bakhtiersizhaev)

* feat(telegram): add asDocument param to message tool

Adds `asDocument` as a user-facing alias for the existing `forceDocument`
parameter in the message tool. When set to `true`, media files (images,
videos, GIFs) are sent via `sendDocument` instead of `sendPhoto`/
`sendVideo`/`sendAnimation`, preserving the original file quality
without Telegram compression.

This is useful when agents need to deliver high-resolution images or
uncompressed files to users via Telegram.

`asDocument` is intentionally an alias rather than a replacement — the
existing `forceDocument` continues to work unchanged.

Changes:
- src/agents/tools/message-tool.ts: add asDocument to send schema
- src/agents/tools/telegram-actions.ts: OR asDocument into forceDocument
- src/infra/outbound/message-action-runner.ts: same OR logic for outbound path
- extensions/telegram/src/channel-actions.ts: read and forward asDocument
- src/channels/plugins/actions/actions.test.ts: add test case

* fix: restore channel-actions.ts to main version (rebase conflict fix)

* fix(test): match asDocument test payload to actual params structure

* fix(telegram): preserve forceDocument alias semantics

* fix: document Telegram asDocument alias (openclaw#52461) (thanks @bakhtiersizhaev)

---------

Co-authored-by: Бахтиер Сижаев <[email protected]>
Co-authored-by: Ayaan Zaidi <[email protected]>

* fix: refactor deepseek bundled plugin (openclaw#48762) (thanks @07akioni)

* fix: declare typebox runtime dep for mattermost plugin

* test: reset line webhook mocks between cases

* test: split attempt spawn-workspace thread fixtures

* test: remove replaced spawn-workspace monolith

* refactor: isolate attempt context engine thread helpers

* CI: remove npm release preview workflow (openclaw#52825)

* CI: remove npm release preview workflow

* Docs: align release maintainer skill with manual publish

* Docs: expand release maintainer skill flow

* test: stabilize gateway thread harness

* test: fix status plugin pagination expectation

* test: harden channel suite isolation

* build: sync lockfile for mattermost plugin

* fix: ensure env proxy dispatcher before MiniMax and OpenAI Codex OAuth flows (openclaw#52228)

Verified:
- pnpm install --frozen-lockfile
- NPM_CONFIG_CACHE=/tmp/openclaw-npm-cache-52228 pnpm build
- pnpm check
- pnpm test:macmini (failed on inherited pre-existing plugin contract test: src/plugins/contracts/registry.contract.test.ts missing deepseek in bundled provider contract registry outside this PR surface)

Co-authored-by: openperf <[email protected]>
Co-authored-by: Tak Hoffman <[email protected]>

* fix: restore ci gates

* test: stabilize channel ci gate

* docs: refresh generated config baseline

* release: verify control-ui assets are included in npm tarball

* release-check: include stderr/stdout when npm pack fails

* release: add changelog for control UI tarball check

* fix: keep session transcript pointers fresh after compaction (openclaw#50688)

Co-authored-by: Frank Yang <[email protected]>

* fix(msteams): isolate probe test env credentials

* release: automate macOS publishing (openclaw#52853)

* release: automate macOS publishing

* release: keep mac appcast in openclaw repo

* release: add preflight-only release workflow runs

* release: keep appcast updates manual

* release: generate signed appcast as workflow artifact

* release: require preflight before publish

* release: require mac app for every release

* docs: clarify every release ships mac app

* release: document Sparkle feed and SHA rules

* release: keep publish flow tag-based

* release: stabilize mac appcast flow

* release: document local mac fallback

* Update CHANGELOG.md

* Improve PR template regression prompts

* fix(agents): preserve anthropic thinking block order (openclaw#52961)

* fix(release): ship bundled plugins in pack artifacts

* fix(config): keep built-in channels out of plugin allowlists (openclaw#52964)

* fix(config): keep built-in channels out of plugin allowlists

* docs(changelog): note doctor whatsapp allowlist fix

* docs(changelog): move doctor whatsapp fix to top

* Update CHANGELOG.md

* fix(config): keep built-in auto-enable idempotent

* fix(release): preserve shipped channel surfaces in npm tar (openclaw#52913)

* fix(channels): ship official channel catalog (openclaw#52838)

* fix(release): keep shipped bundles in npm tar (openclaw#52838)

* build(release): fix rebased release-check helpers (openclaw#52838)

* fix(gateway): harden supervised lock and browser attach readiness

* fix(matrix): avoid duplicate runtime api exports

* fix(gateway): avoid probe false negatives after connect

* docs(changelog): note release and matrix fixes

* fix(plugins): unblock Discord/Slack message tool sends and Feishu media (openclaw#52991)

* fix(plugins): unblock Discord and Slack message tool payloads

* docs(changelog): note Discord Slack and Feishu message fixes

* fix(channels): preserve external catalog overrides (openclaw#52988)

* fix(channels): preserve external catalog overrides

* fix(channels): clarify catalog precedence

* fix(channels): respect overridden install specs

* fix(gateway): require admin for agent session reset

* fix(voice-call): stabilize plivo v2 replay keys

* fix(gateway): require auth for canvas routes

* fix(clawhub): resolve auth token for skill browsing (openclaw#53017)

* fix(clawhub): resolve auth token for skill browsing

* docs(changelog): note clawhub skill auth fix

* fix(release): raise npm pack size budget

* Tests: fix fresh-main regressions (openclaw#53011)

* Tests: fix fresh-main regressions

* Tests: avoid chat notice cache priming

---------

Co-authored-by: Vincent Koc <[email protected]>

* fix(config): ignore stale plugin allow entries

* fix(browser): reuse running loopback browser after probe miss

* fix(clawhub): honor macOS auth config path (openclaw#53034)

* docs: fix nav ordering, missing pages, and stale model references

- Sort providers alphabetically in docs.json nav
- Sort channels alphabetically in docs.json nav (slack before synology-chat)
- Add install/migrating-matrix to Maintenance nav section (was orphaned)
- Remove zh-CN/plugins/architecture from nav (file does not exist)
- Add Voice Call to channels index page
- Add missing providers to providers index (DeepSeek, GitHub Copilot, OpenCode Go, Synthetic)
- Sort providers index alphabetically
- Update stale claude-3-5-sonnet model reference to claude-sonnet-4-6 in webhook docs

* fix(clawhub): preserve XDG auth path on macOS

* Agents: fix runtime web_search provider selection (openclaw#53020)

Co-authored-by: Vincent Koc <[email protected]>

* docs: fix CLI command tree, SDK import path, and tool group listing

- Remove non-existent 'secrets migrate' from CLI command tree
- Add actual secrets subcommands: audit, configure, apply
- Add missing plugin subcommands: inspect, uninstall, update, marketplace list
- Fix plugins info -> inspect (actual command name)
- Add message send and broadcast subcommands to command tree
- Remove misleading deprecated import from sdk-overview
- Add sessions_yield and subagents to group:sessions tool group docs
- Fix formatting

* fix(gateway): guard openrouter auto pricing recursion (openclaw#53055)

* test: refresh thread-safe agent fixtures

* Release: fix npm release preflight under pnpm (openclaw#52985)

Co-authored-by: Vincent Koc <[email protected]>

* docs(changelog): add channel catalog override note (openclaw#52988) (openclaw#53059)

* fix: harden update dev switch and refresh changelog

* fix(mistral): repair max-token defaults and doctor migration (openclaw#53054)

* fix(mistral): repair max-token defaults and doctor migration

* fix(mistral): add missing small-model repair cap

* fix(plugins): enable bundled Brave web search plugin by default (openclaw#52072)

Brave is a bundled web search plugin but was missing from
BUNDLED_ENABLED_BY_DEFAULT, causing it to be filtered out during
provider resolution. This made web_search unavailable even when
plugins.entries.brave.enabled was configured.

Fixes openclaw#51937

Co-authored-by: Ubuntu <[email protected]>
Co-authored-by: Vincent Koc <[email protected]>

* fix(release): fail empty control ui tarballs

* Revert "fix(plugins): enable bundled Brave web search plugin by default (openclaw#52072)"

This reverts commit 0ea3c4d.

* Telegram: preserve inbound debounce order

* Telegram: fix fire-and-forget debounce order

* fix(reply): refresh followup drain callbacks

* Update CHANGELOG.md

* fix(reply): preserve no-debounce inbound concurrency

* fix(reply): clear idle followup callbacks

* fix(inbound): bound tracked debounce keys

* fix: preserve debounce and followup ordering (openclaw#52998) (thanks @osolmaz)

* fix(discord): reply on native command auth failures (openclaw#53072)

* docs(changelog): add missing recent fixes

* fix: bound tracked debounce key accounting

* fix packaged control ui asset lookup (openclaw#53081)

* fix(cli): preserve posix default git dir

* build: prepare 2026.3.23-beta.1

* test: harden canvas host undici isolation

* docs(changelog): credit web search runtime fix

* fix(openai-codex): bootstrap proxy on oauth refresh (openclaw#53078)

Verified:
- pnpm install --frozen-lockfile
- pnpm exec vitest run extensions/openai/openai-codex-provider.runtime.test.ts extensions/openai/openai-provider.test.ts

* release: harden preflight workflows (openclaw#53087)

* release: harden preflight-only workflows

* release: require main for publish runs

* release: select xcode for macos workflow

* release: retry flaky macos preflight steps

* ci: shard bun test lane

* Fix Control UI operator.read scope handling (openclaw#53110)

Preserve Control UI scopes through the device-auth bypass path, normalize implied operator device-auth scopes, ignore cached under-scoped operator tokens, and degrade read-backed main pages gracefully when a connection truly lacks operator.read.

Co-authored-by: Val Alexander <[email protected]>

* build: prepare 2026.3.23

* fix(agents): prefer runtime snapshot for skill secrets

* docs(changelog): note skill secretref runtime fix

* fix(memory): bootstrap lancedb runtime on demand (openclaw#53111)

Bootstrap LanceDB into plugin runtime state on first use for packaged/global installs, keep @lancedb/lancedb plugin-local, and add regression coverage for bundled, cached, retry, and Nix fail-fast runtime paths.

Co-authored-by: Val Alexander <[email protected]>

* build: finalize 2026.3.23 release

* release: upload macos preflight artifacts (openclaw#53105)

* release: upload macos preflight artifacts

* release: speed up macos preflight

* release: use xlarge macos runner

* release: skip dmg path in macos preflight

* fix(subagents): recheck timed-out announce waits (openclaw#53127)

Recheck timed-out subagent announce waits against the latest runtime snapshot before announcing timeout, and keep that recheck best-effort so transient gateway failures do not suppress the announcement.

Co-authored-by: Val Alexander <[email protected]>

* docs(feishu): replace botName with name in config examples (openclaw#52753)

Merged via squash.

Prepared head SHA: 5237726
Co-authored-by: haroldfabla2-hue <[email protected]>
Co-authored-by: altaywtf <[email protected]>
Reviewed-by: @altaywtf

* fix(plugins): accept clawhub uninstall specs

* test(auth): align device scope expectations (openclaw#53151)

* fix: prevent delivery-mirror re-delivery and raise Slack chunk limit (openclaw#45489)

Merged via squash.

Prepared head SHA: c7664c7
Co-authored-by: theo674 <[email protected]>
Co-authored-by: altaywtf <[email protected]>
Reviewed-by: @altaywtf

* Infra: tighten shell-wrapper positional-argv allowlist matching (openclaw#53133)

* Infra: tighten shell carrier allowlist matching

* fix(security): tighten shell carrier allowlist matcher

* fix: generalize api_error detection for fallback model triggering (openclaw#49611)

Co-authored-by: Ayush Ojha <[email protected]>
Co-authored-by: altaywtf <[email protected]>

* feat(modelstudio): add standard (pay-as-you-go) DashScope endpoints for Qwen (openclaw#43878)

Add Standard API Key auth methods for China (dashscope.aliyuncs.com)
and Global/Intl (dashscope-intl.aliyuncs.com) pay-as-you-go endpoints
alongside the existing Coding Plan (subscription) endpoints.

Also updates group label to 'Qwen (Alibaba Cloud Model Studio)' and
fixes glm-4.7 -> glm-5 in Coding Plan note messages.

Co-authored-by: wenmeng zhou <[email protected]>

* Release: privatize macOS publish flow (openclaw#53166)

* fix(diagnostics): redact credentials from cache-trace diagnostic output

Refs openclaw#53103

* Release: document manual macOS asset upload (openclaw#53178)

* Release: document manual macOS asset upload

* Release: document macOS smoke-test mode

* docs(changelog): reorder release highlights

* test(whatsapp): stabilize login coverage in shared workers

* test(whatsapp): preserve session exports in login coverage

* test(whatsapp): preserve media test module exports

* test(whatsapp): preserve harness session exports

* fix(ci): stabilize whatsapp extension checks

* test: make update-cli checkout path assertion platform-safe

* fix(auth): prevent stale auth store reverts (openclaw#53211)

* Doctor: prune stale plugin allowlist and entry refs (openclaw#53187)

Signed-off-by: sallyom <[email protected]>

* test: stabilize test isolation

* test: update command coverage

* test: expand gemini live transcript stripping

* test: fix update-cli default path assertion

* chore(sre:PLA-920): adopt upstream sync changes

* fix(sre:PLA-920): align branch with adopted upstream tree

* build(sre:PLA-920): refresh dist artifacts

* test(sre:PLA-920): align incident-format expectations

---------

Signed-off-by: sallyom <[email protected]>
Co-authored-by: Vincent Koc <[email protected]>
Co-authored-by: Peter Steinberger <[email protected]>
Co-authored-by: Rick_Xu <[email protected]>
Co-authored-by: rcrick <[email protected]>
Co-authored-by: frankekn <[email protected]>
Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: oliviareid-svg <[email protected]>
Co-authored-by: Frank <[email protected]>
Co-authored-by: scoootscooob <[email protected]>
Co-authored-by: ruochen <[email protected]>
Co-authored-by: Onur Solmaz <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
Co-authored-by: Frank Yang <[email protected]>
Co-authored-by: artwalker <[email protected]>
Co-authored-by: RichardCao <[email protected]>
Co-authored-by: create <[email protected]>
Co-authored-by: RichardCao <[email protected]>
Co-authored-by: liuyang <[email protected]>
Co-authored-by: Ayaan Zaidi <[email protected]>
Co-authored-by: Matt Van Horn <[email protected]>
Co-authored-by: Penchan <[email protected]>
Co-authored-by: Penchan <[email protected]>
Co-authored-by: Julia Bush <[email protected]>
Co-authored-by: Bakhtier Sizhaev <[email protected]>
Co-authored-by: Бахтиер Сижаев <[email protected]>
Co-authored-by: wangchunyue <[email protected]>
Co-authored-by: Tak Hoffman <[email protected]>
Co-authored-by: evann <[email protected]>
Co-authored-by: Robin Waslander <[email protected]>
Co-authored-by: Sathvik Veerapaneni <[email protected]>
Co-authored-by: Nimrod Gutman <[email protected]>
Co-authored-by: Luke <[email protected]>
Co-authored-by: scoootscooob <[email protected]>
Co-authored-by: Jamil Zakirov <[email protected]>
Co-authored-by: TheRipper <[email protected]>
Co-authored-by: Quinn H. <[email protected]>
Co-authored-by: Ubuntu <[email protected]>
Co-authored-by: Val Alexander <[email protected]>
Co-authored-by: betoblair <[email protected]>
Co-authored-by: haroldfabla2-hue <[email protected]>
Co-authored-by: altaywtf <[email protected]>
Co-authored-by: Altay <[email protected]>
Co-authored-by: theo674 <[email protected]>
Co-authored-by: theo674 <[email protected]>
Co-authored-by: Ayush Ojha <[email protected]>
Co-authored-by: Ayush Ojha <[email protected]>
Co-authored-by: George Zhang <[email protected]>
Co-authored-by: wenmeng zhou <[email protected]>
Co-authored-by: Onur <[email protected]>
Co-authored-by: Sally O'Malley <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

agents Agent runtime and tooling docs Improvements or additions to documentation size: L

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Bug]: Status shows wrong context window (1.0m instead of 200k)

2 participants