* test(ci): route plugin prerelease coverage to plugin shard
* test(ci): add plugin prerelease suite to CI
* fix(ci): preserve pnpm path in plugin prerelease shard
* fix(ci): avoid inheriting secrets for plugin prerelease suite
For 771846c5fa: docs/providers/bedrock.md "Advanced configuration" now
includes a "Claude Opus 4.7 temperature" accordion describing that
OpenClaw automatically omits `temperature` for Opus 4.7 Bedrock refs
(foundation model ids, named profiles, application inference profiles
whose underlying model resolves to Opus 4.7, and dotted `opus-4.7`
variants with regional prefixes), since Bedrock rejects the parameter on
that model. The fix has no user-facing knob, but Opus 4.7 Bedrock users
need to know the request shape changes silently.
Three findings from the second pass:
1. **MEDIUM — Cross-chat short message ID guard bypassed on empty chat
context (CWE-285).** When `requireKnownShortId=true` and `chatContext`
was missing or `{}`, `resolveBlueBubblesMessageId` would still resolve
the short id. Short ids are allocated from a single global counter
across every account and chat, so an action call without a chat
scope could silently apply to the wrong conversation. Throw "requires
a chat scope" instead. The previous behavior was an explicit
"fail-open" choice with a comment acknowledging the risk; the
underlying assumption (downstream call carries chatGuid) does not
hold for every action handler. Test rewritten to expect fail-closed.
2. **LOW — Unsanitized messageId reflected in cross-chat guard error
(CWE-117 / CWE-200).** The thrown error embedded the raw inputId
(and the raw chatGuid / chatIdentifier from the cached entry until
the previous pass). Replace the inputId with a shape descriptor
(`<short:N-digit>` or `<uuid:prefix…>`) so cross-chat errors no
longer leak any concrete identifier. Combined with the chat
identifier redaction in describeChatForError (already in place),
the error is fully redacted.
3. **LOW — PII exposure via verbose logs (CWE-532).** Untrusted webhook
identifiers (senderId / messageId / action) were already passed
through `sanitizeForLog`, but the helper only stripped control
characters — it did not redact secrets such as `?password=` query
strings or `Authorization: Bearer …` headers that occasionally
bleed into error chains. Extend `sanitizeForLog` to redact those
patterns. All call sites benefit immediately.
Four findings on this PR, all addressed in this commit:
1. **Cross-chat guard bypass when ctx.chatGuid present but cached lacks chatGuid**
(CWE-697). Earlier `isCrossChatMismatch` gated chatIdentifier and chatId
fallback comparisons on `!ctxChatGuid`, which let any non-empty
ctx.chatGuid suppress the fallback checks when the cached entry happened
to lack chatGuid — letting a short id from chat A be reused while acting
in chat B. Rewrite the function so chatIdentifier/chatId comparisons
run independently based on availability on each side, not on whether
ctx.chatGuid happens to be present.
2. **Sensitive chat identifiers exposed via thrown cross-chat error**
(CWE-200). `describeChatForError` interpolated raw chatGuid /
chatIdentifier / chatId into the error message — these can leak phone
numbers / email addresses / chat GUIDs into agent transcripts, tool
results, remote channel deliveries, or third-party log aggregators.
Surface only the *shape* of the chat target with `=<redacted>` values.
3. **Group reaction drop-guard bypass via whitespace chatIdentifier**.
Earlier guard treated "" as missing but accepted " " / "\t". Trim
chatGuid/chatIdentifier before the missing-check so a webhook sender
supplying whitespace cannot satisfy the guard and have peerId degrade
to the literal "group".
4. **Log injection via webhook senderId/messageId in verbose log lines**
(CWE-117). Untrusted webhook fields were interpolated directly into
`logVerbose` calls without sanitization, allowing log forging if a
sender carried CR/LF/control bytes. Wrap with the existing
`sanitizeForLog()` helper at all such sites.
Test updates: monitor-reply-cache.test.ts cross-chat error assertions
now expect `chatGuid=<redacted>` instead of raw values.
resolveBlueBubblesOutboundSessionRoute classified all `chat_guid:`
prefixed targets as groups:
const isGroup =
parsed.kind === "chat_id" ||
parsed.kind === "chat_guid" ||
parsed.kind === "chat_identifier";
But BlueBubbles also encodes DM chatGuids in the same `chat_guid:`
form — they look like `iMessage;-;+15551234567` (the `;-;` separator
is the DM marker; groups use `;+;`). Treating those as groups gave
the same DM two different sessionKeys depending on how the caller
addressed it:
- handle form (`bluebubbles:imessage:+15551234567`)
→ peer.kind = "direct", from = `bluebubbles:+15551234567`
- chat_guid form (`bluebubbles:chat_guid:iMessage;-;+15551234567`)
→ peer.kind = "group", from = `group:iMessage;-;+15551234567`
When a bound DM session was looked up against the second form, no
binding matched and the outbound landed in a freshly-synthesized
"group" sessionKey — a degenerate session that the next inbound
message also failed to find, surfacing the conversation in the
wrong place.
Use resolveGroupFlagFromChatGuid (already used by monitor-normalize
to read the same marker for inbound webhooks) so both directions
agree on what counts as a group. Unknown chatGuid shapes still
fall back to "group" to preserve prior behavior — we never
silently downgrade a real group to direct.
Tests: extensions/bluebubbles/src/session-route.test.ts (new)
- chat_guid `;-;` → direct
- chat_guid `;+;` → group
- chat_guid with no recognizable marker → group (back-compat)
- handle target → direct
- chat_id / chat_identifier → group (unchanged)
- DM addressed two ways converges on the same peer kind
Local patch for upstream consideration. Latent bug introduced by
0f7cd59824 (BlueBubbles: move outbound session routing behind plugin
boundary), not commonly hit because most outbound DM call sites use
the handle form, but a real foot-gun for callers that pass the
chat_guid form.
processReaction's peerId calculation:
const peerId = reaction.isGroup
? (chatGuid ?? chatIdentifier ?? (chatId ? String(chatId) : "group"))
: reaction.senderId;
reads as "if it's a group with at least one chat hint, use that hint;
otherwise fall through to either the literal string 'group' (group case)
or the sender id (DM case)". Two failure modes hide here:
1. BlueBubbles fires a `message-reaction` event with `isGroup: true` but
omits chatGuid AND chatId AND chatIdentifier — peerId becomes the
literal "group" and resolveBlueBubblesConversationRoute synthesizes
a session key unrelated to any real binding. The reaction surfaces in
whatever session the binding fallback picks, never the right one.
2. The same payload arrives with isGroup misclassified as false (BB's
group-flag inference relies on chatGuid, explicit isGroup, or
participants > 2 — none of which are guaranteed for reaction events;
monitor.webhook.test-helpers.ts even ships a default reaction fixture
with no chatGuid and isGroup defaulted to false). peerId then becomes
reaction.senderId and the event is enqueued into the sender's DM
session — the group tapback shows up inside an unrelated 1:1
transcript Chris was looking at.
Neither outcome is recoverable without a chat hint — without chatGuid,
chatId, or chatIdentifier we cannot identify which group the reaction
belongs to. Drop the event with a verbose-log and let the agent miss
that reaction rather than route it incorrectly. DM reactions (which
legitimately may arrive with no chat hint and only a sender) keep
working because the guard is gated on `reaction.isGroup === true`.
A latent risk remains: if BB ever sends an isGroup-misclassified-as-false
payload, this guard does not catch it. That would require teaching
normalize to surface group-flag confidence, which is a larger change
left for follow-up.
Tests (extensions/bluebubbles/src/monitor.test.ts):
- Group reaction with no chat identifiers → not enqueued
- Group reaction with at least one chat identifier → still enqueued
(regression sentinel for the new guard)
Local patch for upstream consideration.
The cross-chat guard added in the prior commit (resolveBlueBubblesMessageId
with chatContext) only ran on numeric short ids — `if (/^\d+$/.test(trimmed))`.
Full GUID input fell through to `return trimmed` with no chat check.
Once the short-id guard started rejecting cross-chat reuses, agents would
retry the same call with the full GUID copied from history or a previous
tool result. That second attempt bypassed the guard entirely and the
group reaction landed in the DM anyway — exactly the symptom the prior
commit was meant to close.
Apply the same `isCrossChatMismatch` check to full GUID input. Cache miss
still falls through (callers may legitimately supply a fresh-from-the-wire
GUID the cache hasn't observed yet), but cache hits with a chat mismatch
throw with a remediation hint pointed at the chat target rather than at
the id format — telling an agent to "retry with the full GUID" makes no
sense when it already supplied one.
Tests (extensions/bluebubbles/src/monitor-reply-cache.test.ts):
- UUID + same chat → resolves
- UUID + different chat → throws (this is the regression)
- UUID + cache miss → passes through (preserves behavior for fresh GUIDs)
- UUID + empty chatContext → passes through (preserves prior behavior)
- UUID error message hints at the chat target, not the id format
- chatIdentifier fallback applies to UUID input too
Local patch for upstream consideration — completes the cross-chat guard
started in the prior commit so both id forms are protected symmetrically.
When a BlueBubbles inbound webhook arrives without `chatGuid`, processMessage
falls back to `resolveChatGuidForTarget` to look it up. The previous fallback
target was:
isGroup && (chatId || chatIdentifier)
? <chat_id or chat_identifier>
: { kind: "handle", address: message.senderId }
That `else` branch quietly covered two very different cases:
1. DM with no chatGuid — resolving via sender handle is correct, the chat
IS the conversation with that handle.
2. **Group with no chatGuid AND no chatId AND no chatIdentifier** — resolving
via sender handle yields *that sender's DM chatGuid*, then the rest of
processMessage uses it for ack reactions, mark-read, outbound reply cache,
typing indicators, and outboundTarget.
Case 2 is reachable: `monitor.webhook.test-helpers.ts` ships a default
`createMessageReactionPayloadForTest` payload with no chatGuid/chatId/
chatIdentifier and `isGroup` defaulted to `false`, mirroring real BlueBubbles
reaction/tapback webhooks. When a group reaction or tapback arrives in that
shape and isGroup is later corrected to true (or the message takes the same
poisoned path), `chatGuidForActions` becomes the sender's DM chatGuid. The
poisoned chatGuid then writes the outbound reply cache (line ~1395) with the
wrong chat, defeating the cross-chat short-id guard added in
9912472289 — a later short id resolved against that cache cannot detect the
mismatch and the agent's reaction/reply silently lands in the DM.
Symptom Chris observed (recurring after 9912472289 baked): group messages
getting reacted to from the agent's side show up in a DM transcript with
that sender, attached to a message GUID the user can no longer locate in
the DM.
Extract the fallback target construction into
`buildBlueBubblesInboundChatResolveTarget` so the rule is testable in
isolation and the wrong fallback can never be reached again:
- Group inbound + chatId present → `chat_id`
- Group inbound + chatIdentifier present → `chat_identifier`
- **Group inbound + neither → return null (caller skips chatGuid-dependent actions)**
- DM inbound → `handle` (unchanged: the conversation IS that sender)
processMessage now logs at verbose when the group case returns null instead
of silently degrading to the sender's DM.
Tests: extensions/bluebubbles/src/monitor-processing-chat-resolve.test.ts
covers the eight branches (group with id, group with identifier, group
preferring id, group with neither, blank/non-finite/null variants, DM, DM
with chat_id present, DM with empty sender).
Local patch for upstream consideration — pairs with the short-id chat guard
landed in the previous commit.
BlueBubbles short message ids (numeric aliases like "1", "5" that agents
use instead of full GUIDs to save tokens) are allocated from a single
global counter across every account and every chat. Nothing in
resolveBlueBubblesMessageId verified that the resolved GUID was actually
in the chat the caller was acting on, so any time an agent reused or
mis-remembered a short id — especially common after a long group
conversation — the id could silently point at a different chat entirely.
Symptom Chris observed: reactions/tapbacks and quoted replies authored
inside a group would intermittently land in a DM, targeting an old
message the user could no longer see. Tool call looks successful, chat
archive shows a group reaction appearing in the DM transcript.
Add an optional chatContext parameter to resolveBlueBubblesMessageId
(chatGuid / chatIdentifier / chatId). When provided, look up the
cached reply entry for the resolved GUID and compare. A clear mismatch
(same identifier present on both sides, different values) throws with a
message that lists both chats and points at "use the full GUID", so the
agent fails fast and retries with a disambiguated id. Ambiguous cases
(either side missing all identifiers) pass through to preserve existing
behavior for callers that cannot supply chat hints. The comparison
mirrors resolveReplyContextFromCache so outbound and inbound paths agree
on scope.
Update every call site that resolves a short id for outbound BB traffic
to pass chatContext:
- extensions/bluebubbles/src/actions.ts: react, edit, unsend, reply
(build context from chat* params, then to/target, then the tool's
currentChannelId)
- extensions/bluebubbles/src/channel.ts sendText: derive context from
the `to` target
- extensions/bluebubbles/src/media-send.ts: same
- extensions/bluebubbles/src/monitor-processing.ts deliver path: pass
the chat already resolved for routing
Add buildBlueBubblesChatContextFromTarget to targets.ts so callers can
project a raw target string (`chat_guid:...`, `chat_id:42`,
`imessage:+1...`, bare handle) into the context shape.
Tests:
- extensions/bluebubbles/src/monitor-reply-cache.test.ts (new, 8 cases):
same-chat resolves, cross-chatGuid throws, ambiguous passes,
chatIdentifier fallback, chatId fallback, full GUID input bypasses,
error message identifies both chats, unknown short id still errors.
- extensions/bluebubbles/src/actions.test.ts: update the react short-id
assertion to verify chatContext now flows through.
Local patch for upstream consideration — same root cause affects every
BB user; plan is to open a separate upstream PR once this bakes locally.
For c2d31a5e59: docs/gateway/security/index.md "External content
special-token sanitization" section already mentions the outbound
sanitizer with `<tool_call>` and `<function_calls>` examples, but it
predates the new internal-runtime-scaffolding stripping that targets
`<system-reminder>` and `<previous_response>` tags. Adds those two tags
as explicit examples and notes the final channel delivery boundary so
operators reading the security page see the same coverage exposed by
the c2d31a5e59 sanitizer.
Persist the NVIDIA_API_KEY marker in generated catalog output and mark bundled NVIDIA Chat Completions models as string-content compatible.\n\nFixes #73013.\nFixes #50107.\nRefs #73014.
For 195f704c74: docs/channels/groups.md "Visible replies" section now
records that native slash commands (Discord, Telegram, and other surfaces
with native command support) reply visibly even when
`messages.groupChat.visibleReplies` is `"message_tool"`, so the channel-
native command UI gets the response it expects. Text-typed `/...` commands
and ordinary chat turns still follow the configured group default.
For 891c7d9f1c: docs/plugins/hooks.md "Quick start" now lists the `priority`
and new `timeoutMs` opts that `api.on(...)` accepts, explaining that the
per-hook budget aborts a slow handler instead of letting plugin setup or
recall work consume the caller's configured model timeout. The change is
traceable to the new `OpenClawPluginApi.on` `{ priority?; timeoutMs? }`
signature and `PluginHookRegistration.timeoutMs` field added in the same
SHA.
Fixes#73502.
Active Memory now allows its hidden recall sub-agent to use both bundled memory tool contracts: memory_recall for memory-lancedb and memory_search/memory_get for memory-core. The prompt prefers memory_recall when available and falls back to the legacy tool pair when that is the active backend surface.
Also updates Active Memory docs, QA mock fixtures, and debug parsing compatibility for the two recall paths.
Verified:
- pnpm install --frozen-lockfile
- pnpm build
- pnpm check
- pnpm test (local full suite failed in unrelated plugin/logging shards; PR-specific docs/changelog checks and GitHub checks passed)
- GitHub status checks for c2c5a94df8 completed without failure
Co-authored-by: WuKongAI-CMU <210765158+WuKongAI-CMU@users.noreply.github.com>
Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
* fix: Discord read/search timeout, session-key fallback, and gateway execution mode
- Add 15s timeout to readMessagesDiscord and searchMessagesDiscord so they
fail fast instead of hanging indefinitely (#73431)
- Fall back to CommandTargetSessionKey in dispatchReplyFromConfig when
SessionKey is empty, so Discord inbound message:received hooks fire
reliably (#73431, refs #33038)
- Add resolveExecutionMode to Discord channel actions routing read/search
through gateway timeout path, matching Telegram's pattern (#73431)
* fix: move timeout to fetch layer, drop send.messages wrapper
Inject AbortSignal.timeout into the Discord proxy-request-client fetch
wrapper so every Discord REST call gets a 15s timeout at the HTTP level.
This replaces the Promise.race wrapper in send.messages.ts — cleaner,
covers all calls, and actually aborts the TCP connection.
* fix: remove unused callerController variable in proxy-request-client test
* fix: remove unnecessary mergeAbortSignal helper
- docs/plugins/hooks.md: add `cron_changed` to the Lifecycle hook catalog and
a Gateway lifecycle paragraph describing its typed event payload, run
status, delivery status, and removed-event job snapshot, so plugin authors
picking up f155a5f955 (#72773) have a canonical reference beyond the
sdk-overview bullet that already shipped in the same SHA.
- docs/help/environment.md: add a "Legacy environment variables" section for
aa1834a3ff so users see that `CLAWDBOT_*` and `MOLTBOT_*` prefixes are now
ignored and trigger an `OPENCLAW_LEGACY_ENV_VARS` deprecation warning,
with a rename example to `OPENCLAW_*`.
For 058b57867e: docs/providers/qwen.md "Qwen 3.6 Plus availability"
accordion now records that the bundled catalog still does not advertise
`qwen3.6-plus` on Coding Plan endpoints, but explicitly configured
`models.providers.qwen.models` entries for that model are honored on
Coding Plan baseUrls so subscribers whose plan enables it can opt in. The
upstream API still decides whether the call succeeds.
Aligns Gateway history and session list thinking-default resolution so backend session state matches the Control UI default label:
- `chat.history` now falls back through the shared Gateway session thinking-default resolver.
- Explicit session overrides still win, then owning `agents.list[].thinkingDefault`, then global/model/catalog defaults.
- `sessions.list` catalog-aware thinking defaults are covered by focused regressions.
PR by @jpreagan.
Validated in Blacksmith Testbox `tbx_01kq9t1aeqrz1mj598vvqv9dpg`:
- `pnpm test:serial src/gateway/session-utils.test.ts src/gateway/server.sessions.gateway-server-sessions-a.test.ts src/gateway/server.chat.gateway-server-chat.test.ts` (141 passed)
- `OPENCLAW_TESTBOX=1 pnpm check:changed`
Add opt-in `sandbox.docker.gpus` config plumbing for Docker sandbox containers.
- thread the optional GPU passthrough field through config types, schema, resolution, and Docker create args
- reject empty config values and emit `--gpus` as a separate Docker argv pair
- document the Docker-only behavior and credit the original contributor in the changelog
Fixes#57976.
Carries forward #58124 from @cyan-ember.
Co-authored-by: cyan-ember <5855097+cyan-ember@users.noreply.github.com>
Route Memory Wiki bridge-mode status, doctor, and bridge import CLI paths through Gateway RPC when bridge artifact reads are active, while preserving local/offline fallbacks.
Harden Gateway CLI rendering and imported-source writes: validate RPC response shapes, bound response strings before rendering/JSON serialization, sanitize/escape terminal-controlled output, avoid redundant JSON forwarding, and replace imported source pages through a temp-file rename path with symlink and hardlink regressions.
Fixes#65722Fixes#65976Fixes#66082Fixes#67979Fixes#68371Fixes#68828Fixes#69019Fixes#70181Fixes#70242Fixes#70842
Thanks @moorsecopers99, @vincentkoc, and @prasad-yashdeep.
For 47dc9f7fc0: docs/gateway/sandboxing.md now warns under "Build the default
image" that OpenClaw no longer silently retags plain debian:bookworm-slim as
openclaw-sandbox:bookworm-slim when the default image is missing. Sandbox runs
fail with a build instruction so the python3 tooling required by sandbox
write/edit helpers is preserved instead of being silently dropped.
- docs/concepts/model-providers.md: add proxy-route shaping rule for the
09ec5d2c4d fix that suppresses implicit Anthropic beta headers
(`claude-code-20250219`, `interleaved-thinking-2025-05-14`, OAuth markers)
on non-direct endpoints, parallel to the existing OpenAI
`compat.supportsDeveloperRole` rule.
- docs/gateway/cli-backends.md: add a "Fallback prelude from claude-cli
sessions" section for a96f1fa5ef so users know that non-CLI fallback
candidates after a claude-cli failure are now seeded with a context prelude
harvested from Claude Code's `~/.claude/projects/` JSONL (preferring the
latest `/compact` summary, coalescing tool blocks, skipping same-provider
`--resume` fallbacks).
The required-typed param introduced in 9987e7797f broke
attempt-execution.cli.test.ts and auth-profile-runtime-contract.test.ts
which construct runAgentAttempt params without an originalProvider field.
Make it optional and explicitly require the typeof check before passing
to isClaudeCliProvider so a missing field correctly skips the seed
(defensive default for fallback paths that didn't plumb the original
provider through, no-op for non-fallback paths).
Addresses review on #72069:
- Codex P1 ("Gate Claude prelude seeding by source provider"): the
guard checked the *current* fallback candidate but not the failed
attempt. A session that still carried a stale
cliSessionBindings["claude-cli"] from an unrelated past run would
inject Claude transcript context into a fallback chain that started
on a different provider (e.g. openai -> openai-codex), leaking
irrelevant prior conversation. Plumb `originalProvider` (the
user-requested provider for the chain) through to runAgentAttempt
and require `isClaudeCliProvider(originalProvider)` before reading
Claude history.
- Codex P2 ("Prefer latest compact boundary when summary is missing"):
the resolver always preferred the most recent explicit summary, so
a later compaction without its own summary entry (rare crash case)
paired stale summary text with post-latest-boundary turns. Restructure
readClaudeCliFallbackSeed to queue summaries into pendingSummary and
flush each boundary's pair atomically. A boundary with no preceding
summary now correctly falls back to the boundary's own content
rather than serving an older summary alongside fresh turns.
- Greptile P2 (newest-first break vs sparse coverage): the
formatFallbackTurns walk intentionally stops on the first oversized
turn so the prelude stays a contiguous "what was happening just
before the failure" window. Document the design choice inline so a
future maintainer doesn't reflexively change it to skip-and-continue.
Tests:
- New gateway cases for the boundary-without-summary edge case and
for trailing summaries written without a paired boundary.
- existing 33 attempt-execution + 14 cli-session-history tests still
pass; broader src/agents/command suite stays green (63/63).
Local default oxlint did not run --type-aware so the warning was missed
on the initial commit; CI surfaced it via check-lint. Hoist the heading
into a named const so its length is read directly without the assertion.
When a claude-cli attempt failed with a fallbackable error (e.g. a 402
billing limit), the next candidate -- typically a non-CLI provider --
ran with no prior conversation context. Claude Code keeps its own
JSONL session under ~/.claude/projects/, but the fallback runner only
sees what OpenClaw assembles from its own transcript, which is empty
for claude-cli sessions. The fallback model therefore behaved as if
the conversation just started, even though Claude later resumed fine.
Resolution mirrors what Claude Code itself does on resume after
compaction: prefer the explicit `/compact` summary, then append the
most recent post-boundary turns up to a char budget. Concretely:
- `readClaudeCliFallbackSeed` (gateway): walks the Claude JSONL with
awareness of `type: "summary"` and `type: "system",
subtype: "compact_boundary"` entries. Pre-boundary turns are dropped
(they are represented by the summary); post-boundary turns become
the recent-window. Multiple compactions are handled by preferring
the latest summary. Path safety reuses the existing
`resolveClaudeCliSessionFilePath` validation.
- `formatClaudeCliFallbackPrelude` / `buildClaudeCliFallbackContext\
Prelude` (agents helpers): format the harvested seed into a labeled
prelude. Tool blocks are coalesced to compact "(tool call: name)" /
"(tool result: …)" hints to keep the prompt budget honest. Newest
turns are kept first when truncating; the summary is clearly
labeled "(truncated)" if it overflows.
- `resolveFallbackRetryPrompt`: gains an optional
`priorContextPrelude` that prepends before the existing retry
marker. Empty/whitespace preludes are ignored; first-attempt prompts
are unchanged.
- `runAgentAttempt`: builds the prelude when `isFallbackRetry === true`
AND the new candidate is non-claude-cli AND a Claude-cli session
binding is present. Same-provider fallbacks (claude-cli to
claude-cli) are unaffected because Claude's own --resume still works.
Verified the new tests (12 in cli-session-history, 12 added to
attempt-execution) catch the regression: removing the prelude prepend
in resolveFallbackRetryPrompt makes both new prelude cases fail,
restoring the original cold-start behavior.
References:
- https://code.claude.com/docs/en/how-claude-code-works
- "Inside Claude Code: The Session File Format"
https://databunny.medium.com/inside-claude-code-the-session-file-format-and-how-to-inspect-it-b9998e66d56b
* fix: add CJK error patterns to failover classification
Chinese LLM providers (ZhipuAI/GLM, Bailian, Kimi/Moonshot, DeepSeek,
etc.) return error messages in Chinese. The existing failover
classification only matches English patterns, causing these errors to
fall through as unclassified — surfacing raw provider errors to users
instead of triggering model fallback.
Real production example: ZhipuAI error code 1234 returns
'网络错误，错误id：xxx，请联系客服。' (network error). This was not
matched by the existing 'network error' English pattern, so no failover
was triggered despite having a configured fallback model.
Changes:
- Add Chinese patterns to all error categories in failover-matches.ts:
timeout, serverError, rateLimit, billing, auth, overloaded
- Add Chinese network error detection in formatTransportErrorCopy()
for user-friendly error messages
- Add comprehensive test coverage for all CJK error categories
Follows the existing precedent set by Chinese context overflow patterns
in isContextOverflowError().
* fix: narrow billing pattern and fix placeholder issue URL
- Change '账户余额' to '账户余额不足' to avoid false positives on
messages that merely mention account balance (per greptile review)
- Replace XXXXX placeholder with actual issue #56242
* fix: wire CJK auth failover patterns
* fix: classify CJK provider failover errors
* fix: place failover changelog entry in unreleased
---------
Co-authored-by: Altay <altay@uinaf.dev>
When a bundled plugin (e.g. plugin-sdk loaded transitively) is resolved via a
pluginRoot already inside the existing plugin-runtime-deps cache, its path
does not match the `dist/extensions/<plugin>` shape, so
resolveBundledPluginPackageRoot() returns null and the caller falls back to
the raw pluginRoot. resolveExistingExternalBundledRuntimeDepsRoots() then
rejected the path because the relative segment crossed a directory separator,
causing the resolver to mint a fresh `openclaw-unknown-<pathhash>` cache
beside the real versioned one. The two caches raced replaceNodeModulesDir()
and triggered ENOTEMPTY crash loops.
Treat any descendant of `<base>/openclaw-*` as belonging to that cache key
so nested resolutions return the existing versioned root instead of creating
a self-referential zombie cache.
Fixes#72956
createSubsystemLogger writes through writeConsoleLine, which intentionally
bypasses the patched console.* capture handler in src/logging/console.ts to
avoid recursion. That bypass also skipped the sink-boundary
redactSensitiveText() gate, so secrets reaching subsystem loggers as
message strings or formatted meta could appear verbatim on the terminal —
a follow-up to the file-transport redaction landed in #67953, tracked
under #64046.
Apply redactSensitiveText() at the writeConsoleLine() exit, immediately
after the existing Windows surrogate sanitization and before dispatching
to the rawConsole sink. This covers all subsystem console paths
(trace/debug/info/warn/error/fatal and .raw) because they share the same
writeConsoleLine() exit, matching the redact-at-sink-boundary pattern
already used in console.ts and the file transport.
Closes#73284
Rewrites the always-on reply handling so group/channel rooms default to message-tool-visible output, while `messages.groupChat.visibleReplies: \"automatic\"` preserves legacy auto-posting.\n\nThanks @scoootscooob.
Persist refreshed `zca-js` session cookies after QR login, session restore, and successful API calls so gateway restarts restore the freshest local Zalo Personal session.
- Adds stable credential cookie signatures so equivalent cookie-jar reorderings do not rewrite credentials.
- Adds regression coverage for reordered live cookie jars preserving credential file content and mtime.
- Updates CHANGELOG.md: (#73277) Thanks @darkamenosa.
Co-authored-by: Tuyen <hxtxmu@gmail.com>
Co-authored-by: Frank Yang <frank.ekn@gmail.com>
Clean up local Claude stdio one-shot runs before returning from embedded `openclaw agent --local`, including bundle MCP loopback teardown for local process resources.
Keeps gateway-owned MCP loopback cleanup internal to the Gateway, documents the local-vs-gateway behavior, and aligns the stale OpenAI provider-runtime fixture with the current unsupported Codex mini route.
Cap detached Dream Diary narrative subagent runs across cron dreaming sweeps so multi-workspace runs cannot fan out unbounded subagent sessions.
Adds regression coverage that queued detached narratives resume and clean up, plus a unit-fast lane correction for the security symlink audit test.
* fix(tui): clear stale streaming after orphaned finals
* fix(tui): clear stale streaming after orphaned finals
* fix(tui): clear stale streaming after orphaned finals
Fix config writes so in-process reload notifications use the canonical post-write source snapshot, matching the file watcher path.
Adds regression coverage for the runtime source snapshot and changelog credit.
* fix(export): fix broken template placeholders in session export HTML
The {{MARKED_JS}}, {{HIGHLIGHT_JS}}, and {{JS}} placeholders in the
export HTML template were split across multiple lines by a code
formatter, turning them into JS block statements instead of template
tokens. The generateHtml() function uses .replace('{{MARKED_JS}}', ...)
which requires contiguous strings, so the vendor JS and app code were
never injected — producing a 2MB HTML file that opens with styles and
session data but renders blank (no JS to parse/display the data).
Fix: collapse placeholders to single-line {{TOKEN}} format and add
prettier-ignore comments to prevent re-formatting.
Introduced in 9d403fd.
* fix(export): use function replacers for vendor JS injection
String.replace() interprets $ sequences ($&, $$, $', etc.) in
replacement strings. The minified vendor libraries (highlight.min.js,
marked.min.js) and the template JS contain literal $ characters that
get mutated during injection — e.g. $& becomes the matched placeholder
text, $$ becomes a single $.
Fix: use arrow function replacers for JS content so replacement text
is injected verbatim without $ interpretation. CSS and session data
use string replacers since they don't contain problematic $ patterns.
Flagged by Codex review (P2).
* ci: retrigger checks
* fix(export-session): restore inline export scripts
---------
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Closes the gap left by #72496 on the parallel `messages.tts.providers.<id>` site. After #72496 landed, `talk.config` still threw `unresolved SecretRef` whenever an operator pinned a TTS apiKey or token as a SecretRef on the messages.tts side — same user-facing symptom (iOS / macOS / Control UI Talk overlays falling back to local AVSpeechSynthesizer).
Adds `stripUnresolvedSecretInputsFromBaseTtsProviders` in `src/gateway/server-methods/talk.ts` that walks each entry in `messages.tts.providers` and strips any unresolved SecretRef wrappers from the configured secret-input keys (`apiKey`, `token`) before handing the base TTS config down to `speechProvider.resolveTalkConfig`. Mirrors the `talk.providers` strip pattern from #72496.
Hardening: rebuilds the providers map with `Object.create(null)` instead of `{}` so an operator-config payload carrying `messages.tts.providers.__proto__` (or `constructor`/`prototype`) cannot mutate Object.prototype via the dynamic `cleaned[providerId] = ...` assignment. Caught by Aisle security review.
Adds three regression tests covering: SecretRef apiKey on messages.tts (the original bug), SecretRef token on messages.tts (Peter's generalization), and `__proto__`-keyed providers (Aisle hardening). All pass; full CI green (57/57) on the rebased branch.
Fixes#73109. Refs #72496.
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Raise the Bonjour stuck-announcing watchdog threshold from 8s to 20s and align watchdog timer coverage so healthy 12-13s LAN announcements do not trigger false-positive advertiser teardown.
Replaces JavaScriptCore catalog evaluation with a bounded fail-closed object-literal parser for the generated macOS model catalog.\n\nValidation: macos-node, macos-swift, security-fast, security-scm-fast, security-dependency-audit, workflow sanity checks passed on PR #73112.
Several `openclaw <parent>` commands (channels, plugins, approvals, devices,
cron, mcp) were exiting with code 1 when invoked bare, while printing the
same help-style content that `<parent> --help` produces (which exits 0).
This broke `&&` chains and surfaced a misleading
`ELIFECYCLE Command failed with exit code 1.` line under pnpm.
Add a small `applyParentDefaultHelpAction(cmd)` helper in
`src/cli/program/parent-default-help.ts` that attaches a default action
which prints the parent's own help and sets `process.exitCode = 0`. The
helper is a no-op when the parent already has its own action (e.g.
`agents` defaulting to `agents list`), so existing intentional defaults
are preserved.
Apply it to the six core parents listed in #73077.
On ARM64 devices (e.g. Raspberry Pi 4), resolvePluginProviders takes ~20s
on first call. Three bugs cause this cost to be paid repeatedly:
1. ensureOpenClawModelsJson readyCache fingerprint includes models.json
mtime. After a write, the stored fingerprint (pre-write mtime) never
matches again, forcing every caller to re-run planOpenClawModelsJson.
2. readyCache has one entry per file path. Agents with different configs
(e.g. main agent vs active-memory subagent) overwrite each other's
entry, so neither benefits from caching.
3. resolveExplicitModelWithRegistry calls shouldSuppressBuiltInModel →
resolveProviderPluginsForCatalogHooks on every agent run. The internal
cache key includes the full config, so callers with slightly different
configs each pay the full provider-load cost.
Fixes:
- Remove modelsFileMtimeMs from fingerprint (bug 1)
- Add noopCache to MODELS_JSON_STATE keyed by (path, mtime) — a noop
result is config-agnostic, so any caller can reuse it (bug 2)
- Cache resolveExplicitModelWithRegistry by (provider, modelId, agentDir),
stable for the lifetime of a gateway session (bug 3)
Measured on Raspberry Pi 4 (ARM64):
active-memory subagent preprocessing: 66-75s → ~3s (warm)
active-memory total elapsed: ~96s → ~14s (warm)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- stream fallback Memory Core vector scoring with SQLite iterate() and a bounded top-K result set
- add regression coverage and live-main lint/boundary helper repairs
- supersedes #73069
Thanks @parkertoddbrooks.
A local containment profile uses plugins.enabled=false to stop plugin and channel runtime churn. The previous startup path still built plugin lookup tables and doctor stale scans despite the global disable, which made the switch noisy and slow.
Constraint: plugins.enabled=false must leave channel blocker warnings intact while treating stale plugin config as inert.
Rejected: Clear user plugin config automatically | would mutate a reversible containment setting.
Confidence: high
Scope-risk: narrow
Directive: Do not reintroduce plugin registry discovery before checking plugins.enabled.
Tested: pnpm test src/gateway/server-startup-plugins.test.ts src/config/plugin-auto-enable.core.test.ts src/commands/doctor/shared/stale-plugin-config.test.ts src/commands/doctor/shared/preview-warnings.test.ts
Tested: pnpm check:changed
Tested: pnpm build
* fix(agents): resolve model aliases in sessions_spawn
normalizeModelSelection() only trims the input — it never resolves
aliases through the model alias index. When a user passes an alias
like 'opus' to sessions_spawn, the child session gets patched with
the raw string, which the gateway cannot match to any provider.
Add resolveModelThroughAliases() to check bare strings against the
configured alias map before returning from
resolveSubagentSpawnModelSelection().
Fixes#57532
Refs #50736
* refactor: address review feedback on alias resolution
- Accept pre-built ModelAliasIndex instead of rebuilding per call
- Narrow helper signature to (string, ModelAliasIndex) → string
- Remove unreachable ?? raw fallback
Co-Authored-By: greptile-apps[bot]
* fix(agents): resolve sessions_spawn model aliases
---------
Co-authored-by: HowdyDooToYou <HowdyDooToYou@users.noreply.github.com>
Co-authored-by: vincentkoc <25068+vincentkoc@users.noreply.github.com>
Conservatively filter macOS CodeQL SARIF by dropping only findings where every location is SwiftPM build output. Verified with workflow sanity, local jq filtering, PR CI, and a failed-job rerun for an unrelated stalled Vitest shard.
Document the redaction surface added in f3e8c50df3: custom logging.redactPatterns now apply to Control UI tool start args, partial/final result payloads, derived exec output, and patch summaries on top of the built-in defaults.
Allow the memory index suite to exceed the global 120s test timeout when it runs inside a packed extension shard. The scoped Vitest config is reset after the file.
Harden the macOS CodeQL SARIF filter to drop only findings whose primary location is SwiftPM build output. Verified with workflow sanity, local jq filtering, full PR CI, and profile=macos-security branch proof in 18m44s.
Filter SwiftPM dependency build results from the manual macOS CodeQL shard before upload. Verified with workflow sanity, local jq filtering, and profile=macos-security branch proof in 15m54s. PR CI has the same unrelated extensions/memory-core timeout failure currently present on main.
End-to-end testing on macOS + BlueBubbles + ElevenLabs walked through three CAF flavors before landing on the format Apple's Messages.app actually emits when a user records a native iMessage voice memo:
- PCM int16 @ 44.1 kHz CAF: BlueBubbles' internal `afconvert -f m4af -d aac` conversion fails; the original CAF reaches iMessage but renders with 0 s duration.
- AAC @ 22.05 kHz mono CAF: BlueBubbles' conversion succeeds and the server silently downgrades the delivery, sending the converted MP3 as a generic audio attachment.
- **Opus @ 24 kHz mono CAF**: byte-identical to the descriptor block Apple's Messages.app produces; BlueBubbles passes it through unchanged and iMessage renders a native voice-memo bubble with proper duration and waveform UI.
Adds an opt-in `tts.voice.preferAudioFileFormat` channel capability and a macOS `afconvert`-backed pre-transcode in the speech-core pipeline. BlueBubbles declares `preferAudioFileFormat: "caf"`. Other channels are unaffected. Falls back to the original buffer when the host platform, the source/target pair, or the transcoder process can't produce the preferred container — so non-Darwin hosts and unsupported provider combinations are unchanged.
Also adds a `caff` magic-byte sniff in `src/media/mime.ts` so the auto-reply host-local-media validator (which uses `file-type` and didn't recognize CAF natively) accepts the buffer instead of dropping it as "⚠️ Media failed."
Fixes#72506.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Remediate current-profile CodeQL findings for file SecretRef id validation and release workflow job permissions. Includes changelog credit. Thanks @vincentkoc.
Feishu config defaults groupPolicy to 'allowlist'. Inbound group handling read groupAllowFrom and called isFeishuGroupAllowed before resolveFeishuReplyPolicy was reached, so a config that only set channels.feishu.groups.<chat_id>.requireMention=false (with no groupAllowFrom) was rejected with 'group not in groupAllowFrom' before per-group requireMention could take effect. Treat the explicit presence of a group entry under channels.feishu.groups as the operator's allowlist signal: if groupConfig is defined, skip the empty-allowlist rejection. resolveFeishuReplyPolicy still owns mention gating, and existing groupConfig.enabled=false / groupAllowFrom-driven rejections are preserved. Adds a regression test that exercises the reporter's exact config shape and confirms inbound text reaches finalize/dispatch.
The ACP dispatch path calls applyMediaUnderstanding without the agentDir
parameter. This prevents the media understanding pipeline from locating
agent-specific models.json and auth profiles, causing image understanding
to fail silently for non-visual models configured with a separate image
understanding model.
The non-ACP reply path (get-reply.ts) already passes agentDir correctly.
This aligns the ACP path with the same behavior.
Closes#55046
AI-assisted (built with Hermes orchestration).
Address review feedback on PR #72888. triggerInternalHook passes the
same event reference to all handlers sequentially. Mutating evt.context
leaks pluginConfig to subsequent handlers and causes cross-plugin
overwrites. Shallow-copy event and context instead.
When plugins register hooks via api.registerHook(), pluginConfig from
openclaw.json was not available in the hook event context. Plugins that
accessed ctx.pluginConfig or event.context.pluginConfig received
undefined, causing silent failures or fallback to defaults.
Changes:
- Add pluginConfig parameter to registerHook() function
- Wrap handler to inject pluginConfig into event.context before invocation
- Pass params.pluginConfig through createApi() call site
Fixes#72880
Closes#72837. The 15s narrative-subagent timeout was empirically too
tight for warm-gateway runs across light, REM, and deep phases —
gpt-5.4-mini latency through OpenAI alone routinely brushes 12s+, so the
first sweep after a restart deterministically times out across all three
phases. 60s gives realistic LLM-call headroom while still capping the
worst case at one minute, preserving the original comment's "don't leave
parent cron running for minutes" constraint.
Test: updates the matching toMatchObject assertion in
dreaming-narrative.test.ts from 15_000 to 60_000.
When the system hostname exceeds 63 bytes (common with Kubernetes pod
names), the @homebridge/ciao DNS label encoder throws an AssertionError
that crashes the gateway on startup.
Add truncateToDnsLabel() that safely truncates UTF-8 strings at byte
boundaries, applied to both the service instance name and hostname
before passing them to ciao.
Closes#37705
AI-assisted (built with Hermes orchestration).
Commit 2cd23957c0 ("build: use slim docker runtime") switched the
runtime image from `node:24-bookworm` (full) to `node:24-bookworm-slim`.
The slim base does not ship `ca-certificates`, and the runtime stage's
`apt-get install` line was not updated to add it.
Result on the resulting image:
- `/etc/ssl/certs/` is empty (`ls /etc/ssl/certs/ | wc -l` == 0)
- `dpkg -l ca-certificates` reports `un` (not installed)
- `update-ca-certificates` is missing in `$PATH` (exit 127)
- every HTTPS outbound from the gateway dies at TLS handshake with
`error setting certificate file: /etc/ssl/certs/ca-certificates.crt`
- channel plugins that use `node fetch` (telegram/discord/slack)
crash-loop with `Network request for 'deleteWebhook' failed!`
and pin the gateway main thread at ~100% CPU on retry.
Verified by rebuilding the runtime image with this patch and
confirming inside the container:
- `ls /etc/ssl/certs/ | wc -l` -> 285
- `curl -4 https://api.telegram.org/` -> 302
- `curl -4 https://www.google.com/` -> 200
- channel plugins (telegram/discord/slack) register cleanly,
gateway main-thread CPU returns to idle.
Add `ca-certificates` to the apt-install list and call
`update-ca-certificates` to populate the CA bundle.
Signed-off-by: ryuhaneul <luj.moonlight@gmail.com>
When the post-update completion cache refresh times out (slow disk,
large bundled plugin tree, Docker overlayfs), the user previously saw
the opaque 'Completion cache update failed: Error: spawnSync
/usr/bin/node ETIMEDOUT'. Detect ETIMEDOUT specifically, surface
'timed out after 30s', and append a manual refresh hint pointing at
'openclaw completion --write-state' so users know it's non-fatal and
how to recover.
Fixes#72842
Add an end anchor to the type/subtype match and explicitly accept the
RFC 9110 ;parameter tail. Inputs like "image/png<script>" or
"application/json garbage" now return undefined instead of silently
matching the leading prefix.
Closes#9795
Remove the two Unreleased Coven ACP/runtime changelog bullets that were reintroduced after the Coven extension removal.\n\nVerification:\n- rg -n -i "coven" CHANGELOG.md Swabble/CHANGELOG.md extensions/matrix/CHANGELOG.md apps/ios/CHANGELOG.md\n- git diff --check origin/main..HEAD\n- PR checks passed on head 767c274b0f
* fix(ui): discard stale config state on explicit reload
* fix(clownfish): address review for ghcrawl-156594-autonomous-smoke (1)
* fix(clownfish): address review for ghcrawl-156594-autonomous-smoke (1)
* test(ui): align channel config host state
* fix(gateway): preserve runtime-backed health state
* fix(clownfish): address review for ghcrawl-207035-agentic-merge (1)
* fix(gateway): harden health snapshot exposure
Both lanes had only one paragraph each in qa-e2e-automation.md. Adds a
"Telegram and Discord QA reference" section verified against
extensions/qa-lab/src/live-transports/{telegram,discord}/* with:
- shared CLI flags table (--scenario, --output-dir, --repo-root, --sut-account,
--provider-mode, --model, --alt-model, --fast, --credential-source,
--credential-role) — none of these were enumerated for either lane.
- Telegram QA: 8 scenario ids
(telegram-canary/-mention-gating/-mentioned-message-reply/-help-command/
-commands-command/-tools-compact-command/-whoami-command/-context-command),
output artifact paths (telegram-qa-report.md, -summary.json,
-observed-messages.json), and the redaction toggle.
- Discord QA: 3 scenario ids
(discord-canary/-mention-gating/-native-help-command-registration), output
artifact paths, and the SUT-application-id-must-match-bot-user-id check.
- Convex credential pool: documents Discord support (only Telegram was
mentioned before) and the per-kind payload shapes for the
admin/add validator. Cross-links to testing.md for the broker endpoint
contract.
Slims the duplicate Operator-flow paragraphs for Telegram and Discord into a
single one-block pointer that links to the new reference section.
Reorg
- Rename the architecture page title to "QA overview" (slug stays
/concepts/qa-e2e-automation so inbound links keep working).
- Move "Adding a channel to QA" + scenario-helper-name reference from
testing.md into qa-e2e-automation.md under "Transport adapters". Architecture
belongs with the architecture page.
- Drop the duplicate live-transport coverage table from testing.md; canonical
copy stays in qa-e2e-automation.md under a new "Live transport coverage"
heading so qa-matrix.md can deep-link to it.
- Slim testing.md QA-specific runners section to ops only, with cross-links.
Audit (against extensions/qa-lab/src/cli.ts, qa-channel/src/config-schema.ts,
and live-transport runtimes)
- qa-e2e-automation.md gains a "Command surface" table covering all 14
openclaw qa <subcommand> forms; previously only ~7 of 14 were named.
- Document missing OPENCLAW_QA_TELEGRAM_CAPTURE_CONTENT and
OPENCLAW_QA_DISCORD_CAPTURE_CONTENT env vars (Matrix already had it).
- Cross-link qa coverage from the Reporting section.
- qa-channel.md completes the config-key list (enabled, name, accounts,
defaultAccount were missing from the schema doc) and pollTimeoutMs range.
- Drop stale "Follow-up work" framing in qa-channel.md (provider/model matrix,
scenario discovery, orchestration) — all three already shipped.
- Replace "vertical slice" language with current behavior; fix misplaced
debugger-UI paragraph.
Discoverability
- Add a Note callout to testing.md pointing at the three QA pages
(QA overview, Matrix QA, QA channel) so maintainers landing on testing.md
see the QA stack in the prologue.
Glossary entries for the renamed/new doc titles.
Adds a focused reference for the Docker-backed Matrix QA lane (CLI flags,
seven scenario profiles, eight env vars including the redaction toggle and
Tuwunel image override, scenario taxonomy, output artifact layout, and triage
tips). Source-of-truth checked against extensions/qa-matrix/src/cli.ts,
shared/live-transport-cli.ts, runners/contract/{runtime,scenario-catalog}.ts,
and substrate/harness.runtime.ts.
Registered in docs/docs.json alongside QA E2E automation.
Add the opt-in Coven ACP runtime bridge as a bundled extension while keeping ACPX as the default path.
Security hardening included before merge:
- fail closed by default instead of silently falling back;
- bounded health/socket requests and daemon response sizes;
- fixed Coven socket trust anchor and symlink/path validation;
- reject untrusted harness/session/event ids before exposing them;
- sanitize daemon-controlled terminal/status/error strings;
- use incremental event polling with bounded dedupe state;
- clean up launched Coven sessions before fallback when daemon ids are invalid.
Validation:
- pnpm test extensions/coven/src/config.test.ts extensions/coven/src/client.test.ts extensions/coven/src/runtime.test.ts
- pnpm check:changed
- GitHub CI green on a64eac20b9
- Greptile Review green
Preserve contributor credit and land the narrowed sessions_spawn ACP-field handling with follow-up transcript redaction and ACP resume ownership hardening. Targeted Blacksmith validation passed for the touched sessions/ACP tests.
The talk.config discovery RPC was handing the source-snapshot's
talkProviderConfig (with the unresolved SecretRef wrapper still on
apiKey) to speechProvider.resolveTalkConfig. ElevenLabs/OpenAI's
strict normalizeResolvedSecretInputString helper threw 'unresolved
SecretRef' there, so iOS / macOS / Control UI Talk overlays never
learned the configured provider and silently fell back to local
AVSpeechSynthesizer ('robot voice') even though talk.realtime.session
and talk.speak both worked end-to-end with the same SecretRef.
Prefer the runtime-resolved provider config when calling
resolveTalkConfig, strip the apiKey field if it's still a SecretRef
wrapper at the call site, and restore the source-shaped apiKey onto
the response so the UI keeps the SecretRef context. Redaction strips
the value when includeSecrets=false.
Adds a regression test using a strict resolver speech provider that
mirrors ElevenLabs/OpenAI behavior so the path stays covered for
SecretRef apiKeys.
Fixes#72496
Thanks @omarshahine
Keep Google Live Talk browser sessions on the supported WebSocket/gateway-relay paths instead of falling back to browser WebRTC, remove stale browser-native voice controls that bypass Talk/TTS provider settings, and harden the Google Live URL plus realtime relay resource controls.
Verification:
- pnpm test ui/src/ui/realtime-talk.test.ts ui/src/ui/realtime-talk-google-live.test.ts src/gateway/talk-realtime-relay.test.ts src/gateway/server-methods/talk.test.ts
- pnpm check:changed
* feat(qqbot): implement unified media upload handling and introduce chunked upload support
This commit enhances the media upload functionality by introducing a unified `sendMedia` method that consolidates the previous separate methods for sending images, voice messages, videos, and files. Key changes include:
- Added `uploadChunked` function for future chunked media uploads, currently marked as not implemented.
- Introduced `MediaSource` abstraction to handle various media types (URLs, base64, local files, buffers) uniformly.
- Updated existing media handling logic to utilize the new `sendMedia` method, ensuring consistent media processing across different types.
- Enhanced error handling and validation for media uploads, including MIME type checks and file size limits.
These changes aim to streamline the media upload process and prepare for future enhancements in handling larger files through chunked uploads.
* feat(qqbot): enhance media upload capabilities with chunked upload support
This commit updates the media upload functionality by implementing chunked upload support for larger files. Key changes include:
- Revised the `SKILL.md` documentation to clarify media file size limits and local file path requirements.
- Introduced a new test suite for the chunked media upload functionality, ensuring robust error handling and upload processes.
- Updated the media handling logic to enforce per-file-type upload ceilings, allowing for seamless integration of chunked uploads.
- Enhanced error handling for daily upload limits, providing user-friendly messages when limits are exceeded.
These improvements aim to streamline the media upload process and accommodate larger files effectively.
* feat(qqbot): add C2C streaming API support for message delivery
This commit introduces support for the QQ C2C official `stream_messages` API, enabling single-message typing-style updates. Key changes include:
- Updated the configuration schema to include a new `c2cStreamApi` boolean option for enabling the C2C streaming API.
- Enhanced the `QQBotAccountConfig` interface to accommodate the new streaming option.
- Implemented a `StreamingController` to manage the lifecycle of C2C stream messages, ensuring proper handling of media tags and message boundaries.
- Updated the outbound dispatch logic to utilize the new streaming capabilities, allowing for more dynamic message delivery in one-to-one chats.
These enhancements aim to improve the responsiveness and interactivity of message delivery within the QQBot framework.
* feat(qqbot): implement group chat support and unify adapter/DI architecture
- Implement group message history tracking with pending history buffer
(record on skip, render on @-mention reply)
- Add mention detection and gating: explicit @bot, implicit quote-reply,
ignoreOtherMentions, configurable activation mode (mention/always)
- Add group activation resolution with session store persistence
- Add message queue with per-peer FIFO and group message merging
(batch multiple rapid messages into one merged payload)
- Add deliver debounce to merge rapid outbound text bursts into
single messages, with media flush and maxWait cap
- Add group config resolution: per-group prompt, history limit,
wildcard and specific group overrides
- Enrich history attachments with local paths from processAttachments
so that history context renders downloaded paths instead of ephemeral
QQ CDN URLs
- Merge ports/ directory into adapter/ as single entry point
- Expand EngineAdapters to 5 required ports: history, mentionGate,
audioConvert, outboundAudio, commands
- Remove global register/get singletons in favor of constructor
injection and one-time init
- Add createEngineAdapters() in bridge/gateway.ts as single assembly point
- Extract monolithic buildInboundContext into 11 discrete stages:
access, content, quote, refidx, group-gate, envelope, assembly
- Extract group chat modules: history, mention, activation,
message-gating, deliver-debounce
- Extract config/group.ts, utils/attachment-tags.ts
* feat(qqbot): add /bot-streaming command for C2C message streaming control
This commit introduces the `/bot-streaming` command, allowing users to enable or disable streaming for message delivery in C2C chats. Key changes include:
- Implementation of the `isStreamingConfigEnabled` function to check the current streaming configuration.
- Command handler for `/bot-streaming` that provides usage instructions and manages the streaming state.
- Updates to the command's response messages to inform users of the current streaming status and how to toggle it.
These enhancements aim to improve user experience by providing a straightforward way to manage streaming message delivery in private chats.
* feat(qqbot): extract interaction handler and add remote config query/update support
- Extract INTERACTION_CREATE handler from gateway.ts into a dedicated
interaction-handler.ts module for better separation of concerns
- Add config query (type=2001) and config update (type=2002) interaction
branches that read/write claw_cfg via runtime.config API
- Register INTERACTION intent (1<<26) in FULL_INTENTS to receive
INTERACTION_CREATE events from the gateway
- Add InteractionType constants (CONFIG_QUERY, CONFIG_UPDATE)
- Extend GatewayPluginRuntime with optional config API (loadConfig,
writeConfigFile) for interaction handler access
- Add QQBotAccountConfigView interface for typed config field access
- Extend acknowledgeInteraction to accept optional data payload for
rich ACK responses (e.g. claw_cfg snapshot)
- Export getFrameworkVersion from slash-commands-impl for version
reporting in config snapshots
- Remove unused eslint-disable directive in streaming-media-send.ts
* feat(qqbot): enhance account management and logging capabilities
- Introduced `toGatewayAccount` function to map resolved QQBot accounts to the engine's gateway account structure.
- Added `persistAccountCredentialSnapshot` function to streamline credential backup during gateway events.
- Updated the `qqbotPlugin` to utilize the new account mapping and credential persistence functions, improving the handling of account data.
- Enhanced logging functionality by modifying the `EngineLogger` interface to support metadata in log messages.
- Implemented new commands for managing logs and clearing storage, providing users with better control over their data and system resources.
- Registered multiple built-in commands for improved user interaction, including `/bot-logs` for exporting logs and `/bot-clear-storage` for managing downloaded files.
- Updated configuration schemas to reflect new options and improve clarity for users.
* fix(qqbot): resolve oxlint errors and update raw-fetch allowlist
- Replace unnecessary `else` after `return` in outbound-media-send.ts (6 occurrences)
- Use `Number.parseInt` instead of global `parseInt` in outbound.ts and streaming-media-send.ts
- Use `Number.isNaN` instead of global `isNaN` in register-basic.ts
- Prefer `**` over `Math.pow` in media-chunked.ts
- Convert interface with call signature to function type in commands.port.ts
- Update api-client.ts allowlist line number (108→124) and add media-chunked.ts:552 to raw-fetch allowlist
* docs(qqbot): translate streaming-c2c.ts header comments to English
* feat(qqbot): add voiceMediaTypes
* feat: restore dispatch changes
* fix(qqbot): align test files with updated engine interfaces after rebase
- inbound-attachments.test: replace removed registerAudioConvertAdapter
with AudioConvertPort, pass audioConvert in ProcessContext
- inbound-pipeline.self-echo.test: add required adapters field to
InboundPipelineDeps mock (history, mentionGate, audioConvert,
outboundAudio, commands)
- outbound-dispatch.test: add required skipped field to InboundContext
* fix(qqbot): update test assertions to match refactored engine interfaces
- inbound-pipeline.self-echo.test: self-echo blocking was moved upstream;
update test to expect non-blocked pipeline behavior
- outbound-dispatch.test: TTS voice path now uses unified sendMedia
instead of sendVoiceMessage; add sendMedia mock and update assertion
- format-ref-entry.test: attachment format changed from [image: ...]
to MEDIA: tag syntax via renderAttachmentTags; update expected output
* refactor(qqbot): migrate from deprecated config API to current/replaceConfigFile
Replace all usages of deprecated runtime config methods:
- loadConfig() → current()
- writeConfigFile(cfg) → replaceConfigFile({ nextConfig, afterWrite })
Updated files:
- bridge/narrowing.ts: writeOpenClawConfigThroughRuntime
- adapter/commands.port.ts: ApproveRuntimeGetter type signature
- commands/builtin/register-approve.ts: loadExecConfig, writeExecConfig, reset
- commands/builtin/register-streaming.ts: config read/write
- gateway/interaction-handler.ts: config query/update handlers
- gateway/types.ts: GatewayPluginRuntime.config interface
* feat(qqbot): update package.json
* fix(qqbot): replace deprecated config-runtime import with config-types subpath
Bundled plugin lint requires focused plugin-sdk subpaths.
- gateway.ts: openclaw/plugin-sdk/config-runtime → config-types
- narrowing.ts: openclaw/plugin-sdk/config-runtime → config-types
* feat(qqbot): group chat support, C2C streaming, chunked media upload, and architecture refactor (#70624) (thanks @cxyhhhhh)
---------
Co-authored-by: Bobby <zkd8907@live.com>
Co-authored-by: sliverp <870080352@qq.com>
## Summary
- render cron job prompts and run summaries through the sanitized markdown pipeline in the Control UI
- keep system-event cron payloads plain and prevent markdown link clicks from triggering row selection
- handle failed runs with missing or empty summaries without duplicating or hiding the error text
## Verification
- pnpm test ui/src/ui/views/cron.test.ts
- pnpm test src/plugins/doctor-contract-registry.test.ts src/plugins/setup-registry.test.ts
- pnpm check:changed
- GitHub CI green on 251f01a3b0
Trace to edb3e84898 (fix: clean stale plugin channel config). When
openclaw doctor --fix removes a missing channel plugin, it also cascades
the cleanup to dangling channel config, heartbeat targets, and channel
model overrides, preventing gateway boot loops after failed plugin
reinstalls. Added an Accordion 11d to docs/gateway/doctor.md listing the
exact config keys that get pruned alongside the plugin entry.
Fixes#68160.
Drops stale optionality from the hello-ok auth schema and keeps generated Swift models, macOS fixtures, browser client types, protocol docs, and merged-base test boundaries aligned.
Harden WebChat input history handling so draft, navigation, and render-state behavior stay consistent across the chat UI.
Validated locally on the rebased PR head 742a5f22f1:
- CI=true OPENCLAW_LOCAL_CHECK=0 pnpm check:changed
- CI=true OPENCLAW_LOCAL_CHECK=0 pnpm test:changed
Closes#38702.
Trace to fee16865b2 (fix(agents): accept LAN local auth markers) and the
companion 0dd2844991 (fix: preserve Ollama local marker auth). The fix
extends ollama-local marker handling to any custom OpenAI-compatible
provider whose baseUrl resolves to loopback, a private LAN, .local, or a
bare hostname, so persisted local markers no longer fail with missing-auth
errors for non-Ollama-typed local providers (LM Studio, vLLM, LiteLLM).
The Ollama provider page already covers ollama-local for Ollama-typed
providers; this note lives in docs/gateway/local-models.md where custom
OpenAI-compatible local stacks are documented.
The publish workflow rsyncs source docs/ into the publish repo with --delete,
but explicitly protects locale directories so translation files survive
non-translation-pipeline syncs. When an English source file is renamed (for
example install/migrating-matrix.md -> channels/matrix-migration.md), the
locale copies at <locale>/install/migrating-matrix.md become orphans:
deleted from the English nav but still present on disk.
Mintlify's hosted build appears to silently fall back to the previous
deployment when nav references a path with mixed locale availability, so
recent docs changes (the migration hub rework, matrix-migration move) are
not propagating to docs.openclaw.ai even though every CI run reports
success and the publish repo has the right English content.
Add a pruneOrphanLocaleDocs() pass that walks every generated-locale
directory in the publish target and removes any .md/.mdx file whose
matching English path no longer exists in source docs. Runs after rsync
and before composing docs.json so the regenerated nav and the on-disk
files stay consistent. Verified the logic against the live publish repo:
identifies all ja-JP/es/pt-BR/ko/de/fr/ar/it/tr/uk/id/pl/zh-CN orphans of
install/migrating-matrix.md (12 entries) and would also catch any future
renames the same way.
The Matrix migration guide is plugin-upgrade content (encrypted-state recovery,
device verification, room-key restore) rather than a cross-system import or
machine move, so it belongs alongside the Matrix channel docs rather than under
Install > Maintenance > Migrating.
- Move docs/install/migrating-matrix.md to docs/channels/matrix-migration.md
- Update inbound link in docs/channels/matrix.md
- Update the migrating.md hub: replace the Matrix Card with a one-line link in 'Upgrade a plugin in place'
- Refresh Related list on the moved page (link Matrix push rules and Migration guide hub)
- docs.json: remove install/migrating-matrix from Maintenance > Migrating, slot channels/matrix-migration between channels/matrix and channels/matrix-push-rules in the Mainstream channels group, and add a /install/migrating-matrix -> /channels/matrix-migration redirect
- install/migrating: convert to a hub page with three clear paths (CardGroup for cross-system imports linking Claude+Hermes, machine-to-machine move with Steps and AccordionGroup, plugin upgrade Card linking Matrix)
- install/migrating-claude: align with Hermes page structure (add Restart-and-verify Step, JSON output for automation, Troubleshooting AccordionGroup with 4 entries, cross-link to Hermes guide)
- cli/migrate: tighten intro to mention both bundled providers and link the migration hub
- docs.json: move Maintenance group to immediately after Install overview, nest the four migrating pages (migrating, migrating-claude, migrating-hermes, migrating-matrix) under a 'Migrating' subgroup so they collapse into a dropdown
Adds a raw config pending-changes diff panel in Control UI raw mode, with JSON5 parsing, sensitive-value redaction until explicit reveal, bounded diff work, and tests for redaction/reveal and stale reveal-state reset.
Also aligns provider manifest contract coverage for google-vertex and Qwen aliases to unblock the rebased CI matrix.
Supersedes stale PRs #48621 and #46654. PR #48621 had gone stale without maintainer follow-up, so this maintainer-authored PR carries the implementation forward transparently while preserving changelog credit for the original contributor and @BunsDev.
* fix(cli): keep nodes list aligned with nodes status
* fix(clownfish): address review for ghcrawl-156588-autonomous-smoke (1)
* fix(cli): keep nodes list aligned with nodes status
Trace to b642ebece9 (fix(feishu): do not treat @all as a bot mention).
Document the new behavior in the mention requirement section: broadcast-only
@all/@_all messages no longer wake the bot, while messages that combine @all
with a direct bot mention still count as a bot mention.
Add a bundled Claude migration provider for Claude Code and Claude Desktop imports.\n\nIncludes source discovery, preview/apply behavior for instructions, MCP servers, skills and command prompts, archive/manual handling for unsafe Claude state, docs, labeler, and tests.
Display friendly agent identity labels in the Control UI Sessions key column when identity data is available, keep raw-key fallback behavior, and allow filtering by agent identity name.
This is the maintainer-owned replacement for #54212 by @dingtao416. Thanks @dingtao416 for the original feature idea and implementation direction.
Includes follow-up fixes from maintainer review automation: normalized key-cell classes, own-property identity lookup, and friendly-label tooltips.
Validation:
- pnpm test ui/src/ui/format.test.ts ui/src/ui/views/sessions.test.ts
- pnpm check:changed
Closes#54163.
Supersedes #54212.
Require Control UI updates to observe a real gateway process replacement, surface skipped/error update outcomes, and verify the running gateway version after restart.\n\nAdds update.status restart-sentinel plumbing, docs, generated protocol model updates, and changelog attribution.\n\nLocal verification:\n- pnpm test src/gateway/server-methods/update.test.ts src/cli/gateway-cli/run-loop.test.ts src/infra/restart-sentinel.test.ts src/infra/process-respawn.test.ts src/infra/update-runner.test.ts ui/src/ui/app-gateway.node.test.ts ui/src/ui/controllers/config.test.ts\n- git diff --check\n- pnpm exec oxfmt --check --threads=1 CHANGELOG.md docs/gateway/protocol.md docs/gateway/configuration.md docs/web/control-ui.md\n- pnpm docs:check-mdx
Trace to 8bdfa58cbb (fix(migrations): avoid partial Hermes config apply after
conflict). Hermes apply now marks remaining dependent config items as
"blocked by earlier apply conflict" when a conflict surfaces mid-apply,
instead of writing them partially. Document the user-visible reason string
and where to find blocked items in the migration report.
Routes stateful Google Meet tool actions through the gateway-owned runtime so create/join/status/speak/leave share the same session owner instead of losing tool-created realtime sessions after the agent turn.
Also preserves structured gateway error details for missing session ids and tightens node-host child cleanup for already-closed sessions.
Fixes#72440.
Co-authored-by: BSnizND <199837910+BsnizND@users.noreply.github.com>
Require explicit confirmation before applying restart-impacting Dreaming mode changes in the Control UI.
- Add pending/confirm/loading state for the Dreaming toggle path
- Render a restart confirmation dialog before sending the config patch
- Sync Control UI locale metadata and cover the confirmation flow in browser tests
Fixes#63804
- cli/migrate: convert flat reference into structured Mintlify page (Tip pointer, ParamField for flags, AccordionGroup for safety model, sub-sections for Hermes provider with what's imported, .env keys, archive-only state, and plugin contract)
- install/migrating-hermes: new dedicated user guide modeled after migrating-matrix.md (Tabs for onboarding vs CLI, AccordionGroup for what gets imported, Steps for recommended flow, Warning for --overwrite, Troubleshooting accordions)
- docs.json: add install/migrating-hermes to Maintenance group alongside migrating and migrating-matrix
Remote proof:
- CI run 24982271745 passed on 6122e13c9f.
- Blacksmith Testbox tbx_01kq6vwehcszjfpp52f0pb3v1q passed focused Google Meet formatting, docs/link checks, realtime consult runtime tests, Google Meet tests, extension test typecheck, the core-unit-fast-support shard, and the core support boundary shard.
Thanks @BsnizND.
Co-authored-by: BSnizND <199837910+BsnizND@users.noreply.github.com>
Fixes#72523.
Remote proof:
- CI run 24980529154 passed on 29f825bea5.
- Blacksmith Testbox tbx_01kq6tsgbaxgstxmtearwy9n4w passed focused formatting, Google Meet tests, Google realtime provider tests, and extension test typecheck.
Thanks @BsnizND.
Co-authored-by: BSnizND <199837910+BsnizND@users.noreply.github.com>
Trace to db09f68ce5 (Support SecretRef for voice-call credentials and bundled
plugin SecretInputs #72607). The reference page docs/reference/secretref-credential-surface.md
listed the new entries in the same SHA, but docs/plugins/voice-call.md showed
only plain-string credentials without pointing to the SecretRef surface.
- platforms/android: blockquote Note for Android app status, Note for canvas host port
- platforms/macos: Tip component for app vs CLI discovery comparison
- plugins/zalouser, channels/zalouser: blockquote Warning components for unofficial automation risk
- channels/pairing: convert two Important paragraphs to Note components for DM-vs-group scope and silent-upgrade behavior
- start/openclaw: workspace-as-memory Tip component
- automation/tasks: drop 'this page covers' filler in Note
- automation/auth-monitoring, clawflow, cron-vs-heartbeat: collapse 'this page moved... See X' redirects to single direct sentences
- testing-live: Tip components for model-discovery and authoritative-list guidance
- debugging: --dev flag Note and non-dev gateway stop Tip
- testing: narrowing live tests Tip
- tools/lobster: optional-plugin allowlist Note
- tools/acp-agents-setup: blockquote Important to Warning component
- memory: replace en-dash list separators with em-dashes, sentence-case Further reading link titles
- messages: rewrite filler 'this page ties together' opener to a direct one
- delegate-architecture: convert 4 blockquote security warnings to Warning and Note components
- system-prompt: convert blockquote daily-memory note to Note component
- channels: convert Tip prose to component, fix /channels/index link, sentence-case heading
- configure: convert Note and Tip prose to components
- devices: convert Note and Warning prose to components
- models: sentence-case scan/status subheadings
- agents: clean up related links and Title Case body link
Add the legacy `models.providers.*.api: "openai"` → `"openai-completions"`
migration to doctor's Current migrations list, and note the gateway startup
behavior that skips providers with future or unknown api enum values instead
of failing closed.
Traces to:
- 6a7980e984 fix(doctor): migrate legacy OpenAI provider api
- 147f4f50f5 fix(gateway): skip stale model provider api entries
Polish the Control UI quick settings dashboard layout.
- Rework quick settings into a 12-column desktop grid with matched top-row card heights.
- Pair Personal with a right-side Appearance/Automations stack on large screens while preserving tablet/mobile ordering.
- Add render/style guards plus an Unreleased changelog entry crediting @BunsDev.
Validated with focused UI tests, formatting, git diff checks, local changed gate, and full PR CI.
Add manifest-owned GitHub Copilot token support for non-interactive onboarding, including documented env fallback, ref-mode tokenRef storage, saved-profile reuse, and default model wiring that preserves existing primary model configuration.
Validation:
- pnpm test extensions/github-copilot/index.test.ts src/plugins/contracts/registry.contract.test.ts src/commands/onboard-non-interactive/local/auth-choice-inference.test.ts
- pnpm check:changed
- CI green on aadac2c8d4
Resolve Feishu group chat labels through getChatInfo so session labels prefer human-readable group names over raw chat IDs.\n\nPreserve topic/thread label priority and defer the lookup until after broadcast dedup claims to avoid duplicate account API calls.\n\nValidation:\n- pnpm test extensions/feishu/src/bot-group-name.test.ts extensions/feishu/src/bot.broadcast.test.ts\n- pnpm check:changed\n- GitHub CI green on c154dc0a41fd715dce95ef1fb5d0c269533b8c22\n\nCloses #35675
Address Clownfish follow-up on Telegram native draft finalization. Requires real streamed assistant partials before materializing drafts, clears stale native draft previews, and keeps media/buttons on normal send path.
Fixes the post-merge review follow-ups from #72471 by deduping stale pre-compaction state entries and preserving parent-before-child ordering for successor transcripts.
Add command-level sentinel coverage proving channel setup metadata, onboarding auth choices, and models-list provider ownership stay on manifest/registry paths without importing plugin runtime.\n\nLocal verification:\n- pnpm exec oxfmt --check --threads=1 src/commands/plugin-control-plane-cold-imports.test.ts\n- OPENCLAW_LOCAL_CHECK_MODE=throttled pnpm test:serial src/commands/plugin-control-plane-cold-imports.test.ts\n- OPENCLAW_LOCAL_CHECK_MODE=throttled pnpm check:changed\n- clean rebase sanity: git diff --check origin/main...HEAD\n\nPR CI had known unrelated main-red failures matching latest main run 24970053892; the new sentinel test passed in CI.
* fix(telegram): send fresh finals for stale previews
* test(telegram): cover stale preview send fallback
* fix(telegram): keep stale archived preview fallback
* fix(telegram): clear stale active previews
* fix(telegram): reset preview state after fresh finals
Fixes #70678.\n\nKeeps quiet but healthy WhatsApp linked-device sessions connected by tracking WhatsApp Web transport activity, while retaining a longer app-silence cap so frame activity cannot mask a stuck session forever. Also cleans up transport activity listeners on failed connection-open paths.\n\nCarries forward the focused #71466 approach and keeps #63939 as related configurable-timeout follow-up. Thanks @vincentkoc and @oromeis.\n\nValidation:\n- pnpm test:serial extensions/whatsapp/src/auto-reply.web-auto-reply.connection-and-logging.e2e.test.ts extensions/whatsapp/src/connection-controller.test.ts\n- pnpm check:changed\n- codex review --base origin/main
* 'main' of https://github.com/openclaw/openclaw:
fix(plugins): satisfy doctor compat lint
chore(plugins): inventory doctor deprecation compat
fix(plugins): record crabpot compat deprecations
docs(dreaming): rewrite with AccordionGroup for phases and backfill, Tabs for quick start and CLI workflow, ParamField for dreaming defaults
Review feedback from @chatgpt-codex-connector (P1): callers that pass
`tryNative: false` rely on jiti's alias rewriting (e.g.
`bundled-capability-runtime` in Vitest+dist mode narrows the SDK
slice through shim aliases). Route everything through the jiti
loader when `tryNative` is false so those rewrites still apply.
Review feedback from @greptile-apps (P2): forward the full argument
tuple through to the jiti fallback with `...rest` so any future
loader option argument is not silently dropped by the wrapper.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Every CLI invocation reads the config snapshot, which pulls bundled
channel doctor contracts and setup surfaces through
`getCachedPluginJitiLoader`. jiti's TS→JS transform pipeline adds
several seconds of per-load overhead on slower hosts (NAS profiling
shows ~78% of `openclaw config get` wall time spent inside the jiti
library), and that overhead is pure waste for the already-compiled
`.js` artifacts shipped in dist/.
Wrap the loader returned by `getCachedPluginJitiLoader` so that
compiled JS targets go through `tryNativeRequireJavaScriptModule`
first. Jiti stays on the hot path for:
- TS/TSX/MTS/CTS sources
- paths the native-require helper declines (Windows by default, or
module-resolution fallbacks)
This centralises the fast path that already existed — inside
`doctor-contract-registry` and `channel-entry-contract` — and extends
it to every caller that goes through the jiti loader cache.
Benchmark on a modest NAS (Node 22.22, ZFS, telegram + discord
configured):
| command | before | after |
|------------------|-------:|------:|
| config get X | 24s | 6s |
| status | 45s | 18s |
| devices list | 55s | 26s |
| nodes status | 55s | 26s |
Fixes the slow config/status/devices/nodes read paths reported in
openclaw#62842. Remaining time is dominated by non-jiti code paths
(config schema validation, eager provider-plugin module eval) that
are out of scope for this patch.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Keep web-search configure and channel command defaults on cold plugin metadata, harden persisted registry reads, and require active config for manifest command defaults.\n\nThanks @vincentkoc
Refresh loaded gateway service installs when the current service embeds stale gateway auth instead of returning already-installed, avoiding LaunchAgent token-mismatch loops after token rotation.
Fixes#70752.
Thanks @hyspacex.
Co-authored-by: Harry Xie <harryhsieh963@yahoo.com>
The clawhub doc was 358 lines mixing two install-command bullet
blocks, a 'beginner-friendly' prose walkthrough, six sequential
flat CLI command sections (Auth, Search, Install, Update, List,
Publish skills, Publish plugins, Delete, Sync), and a workflow
section that repeated the same commands a third time.
Restructure for scan-first reading without losing reference detail:
- Wrap Quick start in a 4-step Steps component (search -> install
-> use -> publish optional CLI install).
- Convert the duplicate native-OpenClaw skills/plugins blocks into
a single Tabs component with one tab per surface, keeping the
validation/safety notes inline.
- Convert the service-features bullet list to a 7-row table.
- Move reporting and moderation rules into a 2-panel
AccordionGroup.
- Convert the eight CLI command sections into one AccordionGroup
(Auth / Search / Install update list / Publish skills / Publish
plugins / Delete undelete / Sync) so the flat command catalog
collapses.
- Convert the global-options bullet list into ParamField
definitions.
- Consolidate the duplicate workflows section into a single Tabs
component (Search / Install / Update all / Publish single /
Sync many / Publish plugin from GitHub).
- Move versioning, lockfile, sync fallback, storage, and telemetry
notes into a dedicated AccordionGroup.
- Convert the env vars bullet list into a 5-row table.
- Drop the duplicate 'How it works / What you can do / Quick start
(non-technical)' prose; the same content lives in the new Quick
start Steps and 'What ClawHub is' summary.
- Sentence-case the Related list and add a missing 'Plugins' link.
- Add sidebarTitle for explicit nav.
CLI flags, command parameters, registry semantics, lockfile path,
moderation thresholds (1-week account age, 20-report cap, 3-report
auto-hide), telemetry env var, and required plugin package.json
metadata are unchanged. Pure restructure plus Mintlify upgrades.
The exec-approvals doc was 379 lines mixing inspection commands as
free bullets, bullet-list policy knobs (security/ask/askFallback/
strictInlineEval), a long YOLO-mode walkthrough split between two
shell blocks, and a stray dangling HTML comment from a prior split
to the advanced page.
Restructure for scan-first reading without losing operational detail:
- Convert 'Inspecting the effective policy' command bullets into a
command/result table.
- Convert each policy knob (security, ask, askFallback,
strictInlineEval) into a ParamField definition so type/values are
visually distinct.
- Wrap the persistent gateway-host YOLO setup in a Steps component
(config -> approvals file).
- Move the YOLO 'pick which layer' note and 'auto vs YOLO'
distinctions into a Warning callout instead of buried inline
bullets.
- Convert the YOLO layer summary into a 3-row layer/setting table.
- Move the local-only exec-policy limitations into a Note callout.
- Convert allowlist entry fields (id, lastUsedAt, lastUsedCommand,
lastResolvedPath) into a 4-row table.
- Surface Auto-allow trust caveats as a Warning callout.
- Drop the dangling HTML comment '<!-- moved to /tools/exec-approvals-advanced -->'.
- Sentence-case 'YOLO mode (no-approval)' replacing the inverted
quote variant ('No-approval YOLO mode').
- Add sidebarTitle for explicit nav.
Trust model, schema example, host approvals JSON shape, allowlist
glob rules, ask-fallback semantics, system-event names, deny-rerun
guard, and the trailing CardGroup of related entries are unchanged.
Pure restructure plus Mintlify component upgrades.
The sub-agents doc was 412 lines of dense bullet lists describing
spawn behavior, tool params, thread binding flow, allowlist rules,
auto-archive behavior, announce semantics, and the sessions_history
sanitization pipeline.
Restructure for scan-first reading without losing reference detail:
- Move spawn-behavior bullets into an AccordionGroup with four
panels (Non-blocking + push-based; Manual-spawn delivery
resilience; Completion handoff metadata; Modes and ACP runtime).
- Convert sessions_spawn tool params into ParamField definitions so
type/default/required render visually.
- Wrap the thread-binding flow in a Steps component (spawn -> bind
-> route -> inspect timeouts -> detach).
- Convert manual thread controls into a 5-row table.
- Convert allowlist fields (allowAgents, requireAgentId) into
ParamField definitions.
- Convert announce-context fields into a 6-row source/field table.
- Surface the cost-budget guidance, sessions_spawn delivery-param
exclusion, operational guidance, and the PAIRING_REQUIRED caller
caveat as Note/Warning callouts where they were buried inline.
- Sentence-case 'Tool Policy' to 'Tool policy' (heading-case fix).
- Sentence-case 'Configuration Reference' link.
- Alphabetize the Related list and add 'Background tasks' which was
referenced inline but missing from Related.
- Add sidebarTitle for explicit nav.
Tool surface, depth tables, slash commands, defaults, allowlist
semantics, sandbox-inheritance guard, per-depth tool policy,
auto-archive timing, announce status sourcing, sessions_history
normalization steps, concurrency lane, recovery rules, and
limitations are unchanged. Pure restructure plus Mintlify upgrades.
The skills doc was 409 lines of nested bullet lists describing
precedence, allowlist rules, gating fields, installer specs, and
config overrides. Heavy reference content but no Mintlify structure.
Restructure for scan-first reading without losing reference detail:
- Convert 'Locations and precedence' from a numbered list + arrow
string into a 6-row precedence table.
- Convert 'Per-agent vs shared skills' bullet/paragraph mix into a
scope/path/visibility table.
- Move agent-allowlist rules into an AccordionGroup so the example
config is the headline and the rules collapse on demand.
- Convert ClawHub install/update/sync bullets into a 3-row command
table.
- Convert SKILL.md frontmatter optional keys (homepage, user-invocable,
disable-model-invocation, command-dispatch, command-tool,
command-arg-mode) into ParamField definitions.
- Convert metadata.openclaw fields (always, emoji, homepage, os,
requires.bins, requires.anyBins, requires.env, requires.config,
primaryEnv, install) into ParamField definitions.
- Move installer-selection rules and per-installer details (Go, download)
into an AccordionGroup so the gating section reads as the canonical
schema plus collapsible operational notes.
- Convert skills.entries config-override rules (enabled, apiKey, env,
config, allowBundled) into ParamField definitions.
- Surface security caveats as a Warning callout up top instead of a
bullet list.
- Move 'Looking for more skills?' into the trailing Related list and
drop the dangling --- separator.
- Sentence-case headings (Format, Gating, Config overrides, Token
impact) and the Related entries (Creating skills, Skills config,
Slash commands).
- Drop the redundant 'Skill Workshop' Title-Case heading variant.
- Add sidebarTitle 'Skills' for explicit nav.
Skill source paths, frontmatter parser rules, gating semantics,
installer selection logic, sandboxing notes, env-injection scope,
snapshot/refresh behaviour, remote-node behaviour, and token-impact
formula are unchanged. Pure restructure plus Mintlify components.
The voice-call plugin doc was 664 lines with a flat install/setup
walkthrough, three flat 'Realtime' / 'Streaming' / 'TTS' provider
config blocks each shown twice, an italicised webhook-security
section in Title Case, and a duplicate-Voice Call body H1.
Restructure for scan-first reading without losing operational detail:
- Wrap Quick start in a Steps component (install -> configure ->
verify -> smoke), with the 'install from npm' vs 'install from
local folder' choice as a nested Tabs.
- Surface the public-webhook-URL constraint as a Warning at the top
of Quick start so readers see it before they hit setup.
- Move provider exposure caveats, streaming connection caps, and
legacy config migration notes into a single AccordionGroup so
the Configuration section reads as the canonical config plus
collapsible operational details.
- Convert the Realtime, Streaming, and TTS provider examples to
Tabs with one tab per provider (Google/OpenAI for realtime;
OpenAI/xAI for streaming; Core/ElevenLabs/OpenAI override for TTS),
removing the previous duplicate-block-per-provider pattern.
- Convert the realtime tool-policy bullet list to a 3-row table.
- Convert the agent tool action list and gateway RPC list into
small tables (action -> args).
- Surface inboundPolicy caller-ID weakness, microsoft-not-supported
for telephony, and realtime+streaming exclusivity as Warning
callouts where they were previously buried inline.
- Sentence-case 'Webhook security' (was Title Case), drop the
duplicate body H1, and refresh the Related list to alphabetical
sentence-case.
Provider names, env vars, defaults, models, voice ids, command
flags, and field semantics are unchanged. Pure restructure plus
Mintlify component upgrades.
The video-generation page was 454 lines with a 3-step Quick start
written as flat numbered prose, four separate parameter tables (Required,
Content inputs, Style controls, Advanced), the task lifecycle as a
numbered list, and a Related list mixing alphabetic and recency order.
Restructure for scan-first reading without losing technical content:
- Wrap Quick start in a Steps component (auth -> default model ->
ask the agent).
- Convert all four parameter tables into ParamField definitions grouped
under their existing sub-section headings (Required / Content inputs /
Style controls / Advanced), so types, defaults, and required flags
show as visual chips and long descriptions wrap cleanly.
- Convert the task lifecycle from a numbered list to a 4-row table for
at-a-glance scanning.
- Convert Yes/No checkmarks in both the Supported providers and
Capability matrix tables to ✓ and em-dash, matching the rest of the
media docs.
- Convert the bullet list under Actions into a 3-row table.
- Sentence-case Related entries and alphabetize the Related list.
- Add sidebarTitle so the nav reads 'Video generation' explicitly.
Schema fields, defaults, model refs, env vars, capability declarations,
fallback rules, and provider notes are unchanged. AccordionGroup of 14
provider notes was already alphabetized and is preserved verbatim.
The music-generation page was 291 lines with two side-by-side
'Quick start' subsections (shared provider-backed vs. ComfyUI
workflow), a flat parameter table, two prose paragraphs explaining
async behaviour and task lifecycle, and a 'Provider notes' bullet
list mixed with a separate 'Choosing the right path' section.
Restructure for scan-first reading without losing technical content:
- Wrap Quick start in a top-level Tabs with two child Steps blocks
(Shared provider-backed | ComfyUI workflow), so readers pick a path
first and only see the matching steps.
- Convert the tool parameter list to ParamField definitions with
type signatures and required flags surfaced visually.
- Convert the four async-behaviour bullets to a labelled bullet list
and the four-state task lifecycle to a table for at-a-glance
scanning.
- Change Capability matrix Yes/No values to checkmarks/em-dashes for
alignment with the rest of the media docs.
- Convert the 'Provider notes' free-form paragraphs into an
AccordionGroup keyed by provider (ComfyUI / Google Lyria 3 /
MiniMax), keeping wording faithful.
- Sentence-case Related entries and add sidebarTitle so the nav reads
'Music generation' explicitly.
Provider rows already alphabetized in the supported providers table
(ComfyUI / Google / MiniMax), kept that order. Wording, model refs,
defaults, env vars, and capability declarations are unchanged.
The image-generation page was 395 lines with a 3-step quick-start
written as plain numbered prose, a sprawling 'OpenAI gpt-image-2'
section that mixed routing/legacy/OpenAI options with five inline
slash-command examples, and provider tables that mixed alphabetic
and recency order.
Restructure for scan-first reading without losing technical content:
- Wrap Quick start in a Steps component (auth -> default model ->
ask the agent), pulling the Codex OAuth note inline with the model
step where it belongs and surfacing the LAN/SSRF caveat as a
Warning callout.
- Alphabetize the Supported providers table (ComfyUI, fal, Google,
LiteLLM, MiniMax, OpenAI, OpenRouter, Vydra, xAI) and the Provider
capabilities table (same order across both). Convert the Yes/No
capability table to checkmarks plus exact counts for readability.
- Replace the long inline OpenAI / OpenRouter / MiniMax / xAI prose
with a 'Provider deep dives' AccordionGroup so each backend's
routing, legacy URL handling, and provider-specific knobs collapse
by default.
- Move the four provider-selection-order notes into a small
AccordionGroup ('Per-call overrides are exact', 'Auto-detection is
auth-aware', 'Timeouts', 'Inspect at runtime').
- Collapse the five flat slash-command examples into a single Tabs
component (4K landscape / transparent PNG / two-square /
edit-one-ref / edit-multi-ref) with the matching CLI variant inline
on the transparent-PNG tab.
- Sentence-case the Related list (Tools overview, Configuration
reference) and drop the redundant generic introductory wording.
- Add sidebarTitle so the nav reads 'Image generation' explicitly.
Wording, schema fields, defaults, model refs, env vars, and the
detailed OpenAI/OpenRouter/Codex routing rules are unchanged.
The media overview was a 91-line page that opened with a redundant
Title-Case body H1 ('# Media Generation and Understanding'), then
mixed a capability table, a Yes/Yes/Yes provider matrix, dense prose
about async behaviour and STT/Voice Call surfaces, plus duplicate
'Quick links' and 'Related' sections at the end.
Restructure for scan-first reading without losing any content:
- Drop the redundant body H1; lead with a one-paragraph summary.
- Replace the 'Capabilities at a glance' table with a CardGroup of six
entry cards (Image / Video / Music / TTS / Media understanding / STT)
each linking directly to its dedicated page. Mode (sync/async) is
noted on the card so readers see latency expectations up front.
- Convert the provider matrix to checkmarks for readability and align
the column header names. Provider rows already alphabetized.
- Pull async vs synchronous behaviour into a 5-row table that names
why each capability is sync or async, then keep the operator-facing
paragraph that explains task-id handoff.
- Move the long 'Google maps to ... OpenAI maps to ... xAI maps to ...'
paragraph into a per-vendor AccordionGroup so each mapping is a
collapsible panel instead of one large prose block.
- Drop duplicate 'Quick links' section in favour of a single Related
list, sentence-cased to match the rest of the docs.
Default sidebar label fell back to title 'Text-to-speech', which is fine
on the page header but readers scanning the Tools sidebar look for the
acronym 'TTS'. Add a sidebarTitle so Mintlify renders 'Text to speech
(TTS)' in the sidebar while keeping the canonical page title intact.
Sentence case matches the rest of the Tools sidebar group (e.g.
'Image generation', 'Music generation', 'Video generation').
Preserve exact Telegram selected quote text for native quote replies, share Telegram reply parameter construction between bot delivery and direct outbound sends, and retry with legacy replies when Telegram rejects native quote parameters.\n\nThanks @rubencu.
- docs/tools/tts.md: alphabetize providers in three places that listed
them: the supported-providers table (Azure Speech ... Xiaomi MiMo),
the configuration Tabs (12 provider presets in A-Z), and the field
reference AccordionGroup. Top-level fields stay first; provider
tabs/accordions follow strict alphabetical order. Wording, schema,
and defaults unchanged.
- docs/docs.json: add tools/tts to the main Tools sidebar group
(slotted between trajectory and video-generation, matching the
alphabetical neighborhood with image-generation, music-generation,
video-generation). Previously tts only appeared under
Nodes > Media capabilities, which was a discoverability gap for
readers looking for TTS alongside the other generation tools.
The TTS doc had grown to 1008 lines with 11 separate flat 'X primary'
config blocks, a 100-line dense 'Notes on fields' bullet list, and
the new provider-personas feature (#70748) buried near the bottom.
Restructure for readability and feature visibility:
- Lead with a Steps-based 'Quick start' so first-time readers can
enable TTS in 4 explicit steps.
- Replace the 13-bullet provider list with a single 'Supported
providers' table that names auth env vars and per-provider notes
inline. Add a Warning callout for the Microsoft/edge legacy alias.
- Collapse the 11 'X primary' config blocks into one Tabs component
('OpenAI + ElevenLabs', 'Google Gemini', 'Azure Speech',
'Microsoft (no key)', 'MiniMax', 'Inworld', 'xAI', 'Volcengine',
'Xiaomi MiMo', 'OpenRouter', 'Gradium', 'Local CLI') so users see
one preset at a time and the page is scannable.
- Promote 'Personas' to its own top-level section with two examples
(minimal and the Alfred provider-neutral persona), and add a new
'How providers use persona prompts' AccordionGroup covering Google
(promptTemplate audio-profile-v1, personaPrompt), OpenAI
(instructions auto-mapping), and Other providers, plus a fallback
policy table.
- Note that agents.list[].tts.persona overrides global persona
per-agent (covers the recent feat(tts) per-agent voice-override
work).
- Convert the 100-line 'Notes on fields' wall into a per-provider
AccordionGroup using ParamField, so the field reference is
scannable and field types/defaults are visually distinct.
- Sentence-case headings, drop redundant body H1, fold the flow
diagram inline with Auto-TTS behavior, and refresh the Output
formats section to a table-first layout.
- Schema fields (label/description/provider/fallbackPolicy/prompt
with profile/scene/sampleContext/style/accent/pacing/constraints
and providers map) verified against src/config/types.tts.ts; all
defaults and env-var fallbacks preserved verbatim.
Net diff: 585 insertions, 684 deletions across the same surface
area.
Two recent commits added user-facing surface that left signature-style
references in docs stale:
- 4428661779 Alvin Tang (#20721, thanks @alvinttang) extends the
configured model 'input' modality set to also accept 'audio' and
'video', matching what providers like LM Studio already report.
docs/plugins/manifest.md model-fields table listed only
'text | image | document', so add 'audio' and 'video'.
- 44da034516 Vincent (thanks @oc-factus) adds a bounded openclaw.agent
attribute on the openclaw.tokens counter so per-agent dashboards can
group usage. docs/gateway/opentelemetry.md metric reference omitted
it; add it to the attrs list.
Honor the parent `models auth --agent <id>` flag across auth write commands: `add`, `login`, `setup-token`, `paste-token`, and `login-github-copilot`.
The auth helpers now resolve the requested configured agent before choosing the auth-profile store and provider workspace, while preserving default-agent behavior when `--agent` is omitted.
Validation:
- `pnpm test src/cli/models-cli.test.ts src/commands/models/auth.test.ts`
- `pnpm test src/commands/models/auth.test.ts`
- `pnpm docs:check-mdx`
- `pnpm check:changed`
- `pnpm check`
- `pnpm build`
- `pnpm test src/cli/run-main.test.ts`
Full `pnpm test` was also run; it failed in unrelated `src/cli/run-main.test.ts` assertions during the full-suite order, while the exact file passes on both latest main and this branch. The PR diff only touches models auth CLI/auth files, docs, and changelog.
Fixes#71864.
Thanks @neeravmakwana.
* fix: add placeholder transcript for silent voice notes
* fix: handle placeholder transcripts per skipped attachment
* fix: preserve synthetic transcript attachment order
* fix: scope synthetic audio merge to audio slice only, preserve cross-capability and prefer ordering
Replace the global outputs.sort() with a targeted merge that:
1. Only sorts within the audio output slice (real + synthetic),
preserving CAPABILITY_ORDER and per-capability attachments.prefer
ordering for non-audio outputs.
2. Excludes synthetic placeholder indexes from audioAttachmentIndexes
used by extractFileBlocks, so tiny audio-MIME files with text
extensions can still be recovered via forcedTextMime.
Adds mergeAudioOutputsPreservingAttachmentOrder helper.
* fix: remove unused function and use toSorted() for oxlint compliance
* fix(media-understanding): preserve selected audio order for synthetic placeholders
- merge synthetic skipped-audio placeholders using audio decision order
instead of raw attachmentIndex sorting, preserving attachments.prefer
- insert synthetic-only audio outputs at the audio capability slot
(before video) when no real audio outputs were produced
* fix(media-understanding): use neutral too-small placeholder text
Clarify that this synthetic transcript path is triggered by attachment size,
not by a silence/no-speech detection result.
* test(media-understanding): update too-small audio placeholder expectations
* test(media-understanding): cover mixed too-small audio placeholder
* test(media-understanding): cover too-small audio context
* fix(tasks): preserve visible task title before internal context
* Revert "fix(tasks): preserve visible task title before internal context"
This reverts commit dc536fb4d3c8a01168de5d05e8562193dd68a88e.
---------
Co-authored-by: Eulices Lopez <eulices@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Terminalize Gateway-backed async task records from the run result while preserving aborted, failed, cancelled, and lost outcomes.\n\nThanks @likewen-tech.
Verify bundled runtime dependency installs before reporting success, so a clean npm exit cannot hide packages missing from the managed runtime-deps root.
Also updates the bundle command test mock for the current plugin enable-state API.
Local proof:
- `pnpm test src/plugins/bundle-commands.test.ts`
- `pnpm test src/plugins/bundled-runtime-deps.test.ts src/commands/doctor-bundled-plugin-runtime-deps.test.ts src/plugins/loader.test.ts`
- `pnpm check:changed`
Co-authored-by: Colin <colin@solvely.net>
Ayaan's 28e4cd81a9 (#70863, thanks @bidadh, source from Arthur Kazemi
8abbae0101) extended params.context1m:true so the configured 1M
context window override now applies to eligible Claude CLI Opus and
Sonnet models, not only direct API calls. CHANGELOG entry covered
the change but docs/providers/anthropic.md '1M context window (beta)'
Accordion only described direct-API behavior, so Claude CLI users had
no signal the same param works for their backend. Add a sentence
inside the same Accordion.
Normalize task lifecycle timestamps on create, update, and restore so startedAt/lastEventAt/endedAt cannot precede createdAt in audit-visible records.
Downgrade retained lost tasks with future cleanupAfter from audit errors to warnings while keeping expired or unstamped lost tasks as errors.
Verification: pnpm exec oxfmt --write --threads=1 src/tasks/task-registry.ts src/tasks/task-registry.test.ts src/tasks/task-registry.audit.ts src/tasks/task-registry.audit.test.ts
Verification: node scripts/test-projects.mjs src/tasks/task-registry.test.ts src/tasks/task-registry.audit.test.ts (task-registry.audit.test.ts 4 passed; task-registry.test.ts 45 passed)
Add an explicit rule under Docs / Changelog that bullets must stay on
one line — no wrapping or continuation across multiple lines.
Justification: dedupe, PR-ref, and credit-audit tooling assumes
single-line entries, and the rest of the file is already uniform
single-line. The recent flatten pass collapsed 80 multi-line bullets
in last two releases plus Unreleased; this rule prevents that drift
from coming back through new entries.
Many bullets in Unreleased, 2026.4.25 (Unreleased), 2026.4.24, and
2026.4.23 wrapped across two to five lines, mixing single-line and
multi-line entries within the same section. The repo convention is
single-line bullets — that is what every author/PR reformatter aims
at, what the dedupe and PR-ref scanners assume, and what readers
scrolling the file see in the rest of the changelog.
Reflow each multi-line bullet to a single line by joining
continuation lines on a single space and collapsing redundant
whitespace. Wording, casing, links, PR refs, and Thanks credits are
unchanged — the only edit is layout.
Skipped 2026.4.22 and earlier on purpose; this pass is scoped to
'last two releases plus unreleased' as requested.
Scott Glover's commit 371b69b3e2 ('Expose cron jobId in plugin hook
context') added an optional jobId field on PluginHookAgentContext,
populated for cron-driven runs. The commit shipped without a docs
update or CHANGELOG entry, so plugin authors had no visible signal
that the new ctx.jobId field exists.
Surface ctx.jobId in two existing hook context references in
docs/plugins/hooks.md: the before_tool_call ctx-fields list, and the
runId/agent-lifecycle paragraph that already names ctx.runId — extend
it to note ctx.jobId on cron-driven runs and what plugins can do with
it (scope metrics, side effects, or state to a scheduled job).
Codex app-server sends retryable stream error notifications while a turn is still recovering. OpenClaw now ignores retryable app-server errors and preserves nested terminal error messages instead of replacing them with a generic fallback.
Isolate Codex ACP launches with an OpenClaw-managed CODEX_HOME/config wrapper so global Codex desktop notify hooks do not leak into acpx sessions.\n\nValidation:\n- OPENCLAW_LOCAL_CHECK=0 OPENCLAW_VITEST_MAX_WORKERS=1 pnpm check:changed\n- pnpm test extensions/acpx/src/codex-auth-bridge.test.ts\n\nThanks @91wan.
Generated media can be produced in intermediate tool results before the assistant chooses which assets to share in its final reply. This change keeps those intermediate files from being appended a second time when the final reply already names the assets to deliver, and tightens the media directive parsing around unsafe or ambiguous URLs.
stripModelProfileSuffix() in providers.ts naively truncated model names at
the first '@', discarding quant variants like @iq3_xxs, @iq4_xs, @q4_k_xl
that LM Studio uses to distinguish quantization levels.
This caused two user-facing bugs (fixes#71474):
1. /model lmstudio/qwen3.6-27b@iq3_xxs → 'model not allowed: lmstudio/qwen3.6-27b'
2. API requests sent truncated model name → LM Studio picked a random quant
Changes:
- Replace the naive indexOf('@') strip in providers.ts with
splitTrailingAuthProfile() which already handles quant suffixes
- Extend the quant-suffix regex (q\d+...) to also match importance-
quantization tags (iq3_xxs, iq4_xs, ...) via i?q\d+ pattern
- Add tests for @iq* quant suffixes and auth-profile-after-iq combos
* Manage Codex app-server binary
* Use plugin deps for Codex app-server binary
* Stabilize media model registry test
* Exclude checkpoint transcripts from memory ingestion
Logging.md had grown to 487 lines with ~300 lines dedicated to
OpenTelemetry export — wire protocol, full metric/span catalog, env
vars, captureContent shape, sampling, the diagnostic event catalog,
and protocol notes — leaving the genuine logging overview buried
behind exporter reference material.
Move the OTEL surface to a dedicated page and slim logging.md to a
focused logs overview:
- Add docs/gateway/opentelemetry.md (OpenTelemetry export). Same
content reorganized: how it fits together, quick start, signals,
configuration reference + env vars table, privacy/captureContent,
sampling/flushing, full metric and span catalog, diagnostic event
catalog, no-exporter mode, diagnostics flags pointer, disable.
- docs/logging.md: drop the OTEL section in favor of a short
'Diagnostics and OpenTelemetry' summary that cross-links the new
page and the diagnostics-flags page. Drops 273 lines net. Also
drops the redundant body H1, retitles to 'Logging' (was 'Logging
overview' which mismatched sidebar usage), and refreshes the
Related list.
- docs/docs.json: insert gateway/opentelemetry into the
'Health and diagnostics' sidebar group, reorder pages so the user-
facing health/run pages come before exporter/internals pages, and
put logging next to opentelemetry where readers naturally
associate them.
- docs/gateway/diagnostics.md, docs/gateway/logging.md,
docs/gateway/configuration-reference.md: cross-link the new page
and sentence-case stale Title-Cased Related entries on
diagnostics.md.
Add Volcengine/BytePlus Seed Speech as a bundled TTS provider with current API-key auth, legacy AppID/token fallback, native Ogg/Opus voice-note output, and MP3 audio-file output.
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* docs(msteams): add Teams CLI setup instructions
Replace manual Azure Bot setup as primary path with
@microsoft/teams.cli workflow. Manual steps collapsed
into <details> blocks for users who can't use the CLI.
* docs(msteams): fix devtunnel instructions to use persistent tunnels
Use devtunnel create + host for stable URLs across sessions
instead of throwaway tunnels that change each time.
* docs(msteams): address PR feedback
- Remove "Abandon all hope" quote (showed as net-addition in diff)
- Add preview disclaimer for @microsoft/teams.cli
- Add security note for --allow-anonymous devtunnel flag
- Clarify where to find teamsAppId from create output
- Link to official devtunnel getting started guide
* docs(msteams): fix oxfmt formatting
* docs(msteams): clarify install step references create prompt
* docs(msteams): drop --env flag, use terminal output instead
Avoids writing secrets to a file that could be accidentally committed.
* docs(msteams): remove redundant H1, match other channel docs
Wrap runRecallSubagent() with Promise.race so maybeResolveActiveRecall
returns a timeout result at the configured timeoutMs even when the
embedded run has not cooperatively checked the abort signal. Late
subagent rejections are caught silently to prevent unhandled promise
errors.
Fixes#71629
When memory-core plugin is not registered (e.g. CLI context),
listActiveMemoryPublicArtifacts returns an empty array. The previous code
would then call pruneImportedSourceEntries with an empty activeKeys Set,
which removes ALL bridge-imported entries.
Now checks getMemoryCapabilityRegistration() instead of relying on artifact
count as a proxy, correctly distinguishing between 'plugin not loaded' and
'plugin loaded with no artifacts'.
Fixes#68373
* fix(process): skip kill-tree group kill when child wasn't detached (#71662)
When the supervisor spawns a child with detached:false (service-managed
runtime under launchd/systemd), the child shares the gateway's process
group. On session abort or SIGKILL, killProcessTree was unconditionally
issuing process.kill(-pid, 'SIGTERM') — which targets the entire process
GROUP (negative pid is POSIX group-kill semantics) and therefore
SIGTERMs the gateway parent along with the child.
Reporter saw this on macOS (LaunchAgent + KeepAlive=true): aborting a
claude-cli/claude-opus-4-7 session caused the gateway to receive
SIGTERM, then auto-restart, dropping all in-flight sessions. Switching
the primary model to a non-cli provider eliminated it because the
non-cli paths don't go through this kill-tree call. Did not occur on
Linux VPS where the gateway runs detached, because there
useDetached === true and the child got its own process group.
Fix:
- killProcessTree now accepts opts.detached?: boolean. When detached:false,
killProcessTreeUnix skips the `-pid` group-kill and goes straight to
direct-pid SIGTERM/SIGKILL. Group-kill default (detached:true) is
preserved so all existing callers behave exactly as before.
- supervisor/adapters/child.ts:286 now threads the spawn-time `useDetached`
flag into killProcessTree, so the kill-tree path matches the spawn-time
detachment decision (line 45 of the same file already computes
useDetached = process.platform !== 'win32' && !isServiceManagedRuntime()).
Tests:
- new: detached:false skips group kill and uses direct pid SIGTERM only.
- new: default behaviour (detached:true) still uses group kill (regression
guard so the existing test case isn't accidentally weakened).
Existing tests still pass (6/6 in kill-tree.test.ts). Lint clean.
Out of scope: other killProcessTree callers (mcp-stdio-transport,
bash-tools.process, etc.) keep the default group-kill behaviour because
those processes are typically detached from the gateway. Only the
supervisor/adapters/child.ts path threads `detached` through, since it's
the path that knows whether the child was actually spawned detached.
* fixup(process): also gate kill-tree group-kill on the no-detach spawn fallback (#71662)
Greptile review on the original PR caught a P1 gap: when
spawnWithFallback's initial detached spawn fails and it retries with the
no-detach fallback (label: "no-detach", options.detached: false), the
child runs detached:false but my variable useDetached was still true.
The kill closure then passed `detached: useDetached` = true to
killProcessTree, which still group-killed the gateway — same bug, just
on the fallback path.
Compute the actual detachment as
`useDetached && !spawned.usedFallback` after spawn returns, and pass
that through. This closes the gap: the kill path now correctly skips
group-kill in BOTH:
1. Service-managed runtime (useDetached=false from the start, original case)
2. Detached-spawn fallback to no-detach (useDetached=true at intent
time but spawned.usedFallback=true)
Tests:
- existing 'uses process-tree kill for default SIGKILL' updated to
assert the new {detached} option is forwarded.
- new: passes detached:false to killProcessTree when spawn fell back.
- new: passes detached:false in service-managed mode (regression guard
for the original fix).
11/11 tests pass in child.test.ts. 6/6 in kill-tree.test.ts.
When a subagent finishes while its parent main session is still running
(executing tools or awaiting model output), the announce queue would
follow the configured debounce and immediately attempt to deliver the
completion event back into the parent session via callGateway. The
gateway treats the parent as busy and the announce can either get
buffered until the next external user message or surface only as a
delayed echo, breaking the natural sessions_spawn -> sessions_yield
workflow where the parent expects the result to arrive as the next
turn.
This change adds an optional shouldDefer hook on the announce queue
state. The delivery layer wires it to the existing requester session
activity probe (resolveRequesterSessionActivity), so while the parent
session is still active the drain loop sleeps for max(250ms,
debounceMs) and re-checks instead of pushing the announce. As soon as
the parent goes idle, the queue drains normally.
- Plumbs shouldDefer through getAnnounceQueue / enqueueAnnounce.
- Skips drain step in scheduleAnnounceDrain when shouldDefer says the
target is still busy, with a bounded re-check sleep.
- Updates maybeQueueSubagentAnnounce to pass the activity probe.
- Adds a unit test that holds drain while parent is busy and resumes
when it goes idle.
No behavior change for callers that do not pass shouldDefer.
* fix(memory-core): add runtime cron service fallback for dreaming reconciliation
When the cron service is unavailable during gateway_start (e.g., due to
a startup timing race or deferred initialization), the startupCronSource
is captured as null and never refreshed. All subsequent runtime
reconciliation attempts fail with 'cron service unavailable', even when
the cron service is fully operational.
This adds a fallback path in the runtime reconciliation that attempts to
obtain the cron service from the plugin API runtime when the startup
capture was null. This handles the case where the cron service becomes
available after the initial startup event.
Fixes#67362
* fix(memory-core): hold gateway context for runtime cron resolution
The previous attempt tried to access api.runtime.cron which doesn't exist
on the PluginRuntime type. The cron service is only accessible through
PluginHookGatewayContext.getCron().
This fix stores the gateway context from the gateway_start event and uses
it to retry cron resolution at runtime when the initial capture was null.
This handles the race condition where the cron service isn't available
during gateway_start (250ms deferred init) but is ready later.
Also refreshes the startupCron capture when the runtime retry succeeds,
so subsequent reconciliation calls resolve immediately.
Addresses review feedback on #71694
Reporter measured `agents list --json` at ~7-9s on a fast host (~11s in
container) on 2026.4.23, while peer `--json` commands like
`channels list`, `cron list --all`, and `sessions ... --all-agents`
stay sub-second. Their cold-call dashboard endpoint dropped from 27s to
~2s after a local dist patch — they could even retire the 5-min cache
TTL workaround they had shipped to dodge it.
Root cause: `agents list` inherits `loadPlugins: 'always'` from the
parent `agents` policy in command-catalog, then `agentsListCommand`
calls `buildProviderStatusIndex(cfg)` unconditionally — both paths
trigger the bundled-extension import waterfall (~60+ extension index.js
modules).
`channels list` already uses `loadPlugins: 'never'` and proves the
shape is right; this PR matches that shape with the safer `text-only`
variant so human invocations are unchanged.
Two-line fix per reporter:
1. `src/cli/command-catalog.ts` — opt agents list into `text-only`,
the same plugin-preload policy bucket that already exists. Plugin
preload runs for human text output, skips for `--json`.
2. `src/commands/agents.commands.list.ts` — skip
`buildProviderStatusIndex` (and the per-summary provider
enrichment loop) when `opts.json`. Provider info is only rendered
in human text output via `formatSummary`, so dropping it from JSON
has no observable effect on existing callers that consume `id`,
`name`, `model`, `bindings`, `isDefault`, `identity*`, `workspace`,
or `agentDir`. `routes` is config-derived and continues to be set
in both modes.
Tests:
- new assertion in command-startup-policy.test.ts: `agents list` with
jsonOutputMode:true now resolves to `loadPlugins: false` (was
effectively `true` via the parent `agents` 'always' policy).
- existing assertion that human (jsonOutputMode:false) still triggers
plugin load is preserved verbatim.
6/6 tests pass. Lint clean.
Out of scope:
- `--bindings` flag opt-in for restoring providers in JSON output:
worth adding later if any consumer needs it; reporter said dashboard
consumers don't.
- Broader plugin-discovery cache work (#67040, #71690) which addresses
the same family of cold-start cost.
* feat(talk): add distinct system sounds for each Talk Mode phase
Play a short system sound on phase transitions to give the user
audible feedback:
- thinking: Tink
- speaking: Pop
- listening (after speech interrupted): Bottle
- listening (after thinking): Submarine
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(talk): add right Shift key to interrupt Talk Mode speech
Add TalkSpeechInterruptMonitor — a dedicated global key monitor that
listens for right Shift (keyCode 60) to interrupt Talk Mode speech.
Independent of Push-to-Talk, so it works even when PTT is disabled.
Stops only the current response; the next conversation cycle
continues normally via sendAndSpeak's resumeListeningIfNeeded flow.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(talk): increase silence detection timeout for CJK locales
Korean, Japanese, and Chinese speakers need longer pauses between
phrases. When the app locale is CJK, enforce a minimum 2000ms
silence window (vs the default 1500ms) to avoid premature
transcript submission.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(talk): remove force-unwraps and log CJK silence clamp in reloadConfig
Replace non-idiomatic force-unwraps (cfg.voiceId!, cfg.modelId!) with
safe flatMap unwrapping, and add an info log when CJK locale clamps the
silence timeout so the override is observable in diagnostics.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(talk): add settings toggle to mute phase-transition sounds
Add a "Play phase-transition sounds" checkbox to Voice Wake settings.
When disabled, Talk Mode phase transitions (Tink/Pop/Bottle/Submarine)
are silent. Defaults to enabled to preserve existing behavior.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(talk): add toggle for Right Option speech interrupt
Add a "Press Right Option to stop speech" checkbox to Voice Wake
settings. Also change the interrupt key from right Shift to right
Option (keyCode 61) to avoid conflicts with typing.
Defaults to enabled to preserve existing behavior.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(talk): disable Push-to-Talk while Talk Mode is active
Talk Mode and Push-to-Talk both use the right Option key (keyCode 61).
Disable PTT when Talk Mode is enabled to prevent conflicting handlers,
and restore PTT when Talk Mode is disabled.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(talk): show info when PTT is paused during Talk Mode
Display a footnote under the Push-to-Talk toggle when both PTT and
Talk Mode are enabled, explaining that PTT is paused while Talk Mode
is active and resumes when Talk Mode is turned off.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fixup: SwiftFormat lint on TalkModeController phase sound switch
Resolves macos-swift CI lint failures introduced by Korean
comment formatting in 'feat(talk): add distinct system sounds for each Talk Mode phase'.
- Collapse consecutive spaces between sound name and comment
- Move floating comments above the listening case expression so
they're at the correct indent level
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: hongsw <hongsw@hongswui-Macmini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Fabian Williams <fabian@adotob.com>
Pre-existing lint errors blocking the macos-swift CI check on every
PR that touches Swift code. Apply the wrapMultilineStatementBraces
rule by moving the opening brace of the multi-line if/else if to its
own line.
- apps/macos/Sources/OpenClaw/ExecAllowlistMatcher.swift:17
- apps/macos/Sources/OpenClaw/ExecApprovals.swift:621
Pure formatting change; no behavioral effect.
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Translate OpenClaw `mcp.servers.*.transport` entries into the downstream Claude/Gemini CLI `type` field before writing bundle MCP config.
Also keeps the plugin-sdk bundled-entry fast-path fixture unambiguously CommonJS on Node 24 after runtime-deps mirroring adds a `type: "module"` boundary.
Co-authored-by: Blockchain-Oracle <ajweb3dev@gmail.com>
Image generation and media understanding both thread the
sanitized models.providers.google.request config (including
allowPrivateNetwork) into resolveGoogleGenerativeAiHttpRequestConfig.
Speech synthesis omitted that arg, so TTS always saw
allowPrivateNetwork: false regardless of config — silently falling
back to a different speech provider when the configured Google TTS
endpoint resolved to a private/internal IP (proxies, custom backends,
test mocks).
Mirror the image-generation-provider pattern: thread request through
synthesizeGoogleTtsPcm at both call sites (synthesize and
synthesizeTelephony).
Follow-up to #67216.
* fix(github-copilot): preserve all reasoning IDs and add gpt-5.3-codex support
The existing guard (8fd15ed0e5) only skipped rewriting reasoning item IDs
when encrypted_content was a non-null string. When gpt-5.3-codex is used
via GitHub Copilot, the model falls through to the forward-compat catch-all
with reasoning:false, so encrypted_content is never requested and arrives
as null — bypassing the guard and causing a rewrite. Copilot validates
reasoning item IDs server-side regardless of whether the client includes
encrypted_content, so the rewritten id triggers the 400 error.
Two changes:
1. connection-bound-ids.ts: skip ALL reasoning items unconditionally.
Reasoning items always reference server-side state bound to their
original ID; rewriting any of them breaks Copilot's lookup.
2. models.ts + index.ts: extend the forward-compat cloning logic to
cover gpt-5.3-codex (adds it to the template-target set and to
CODEX_TEMPLATE_MODEL_IDS so it can also serve as a template source
for gpt-5.4). Adds gpt-5.3-codex to COPILOT_XHIGH_MODEL_IDS for
the thinking profile.
Thanks @InvalidPandaa.
* docs(github-copilot): clarify gpt-5.3-codex is a no-op template for itself
https://claude.ai/code/session_01EAFmq4WyKkiUkVAqRXp4Bm
* fix(github-copilot): remove dead reasoning prefix branch in deriveReplacementId
https://claude.ai/code/session_01EAFmq4WyKkiUkVAqRXp4Bm
* fix(github-copilot): align reasoning id replay tests
* test(plugin-sdk): use cjs sidecar for require fast path
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
mushuiyu_xydt's commit 0e1ef93e84 (#61155) routes MiniMax image
generation requests to the dedicated image endpoint
(api.minimax.io/v1/image_generation), ignoring models.providers.minimax.baseUrl
(which targets the chat/Anthropic-compatible API), and adds
MINIMAX_API_HOST support for the CN api.minimaxi.com endpoint. The
CHANGELOG entry covered it but docs/providers/minimax.md image-generation
section did not. Add a paragraph naming both endpoints and the
MINIMAX_API_HOST override.
* fix(minimax): use dedicated image generation endpoint
MiniMax image generation uses a dedicated API endpoint
(api.minimax.io/v1/image_generation) that is separate from the
text/chat API endpoint (api.minimax.io/anthropic).
Previously, the resolveMinimaxImageBaseUrl function would extract
the origin from the provider's configured baseUrl. If a user had
configured their baseUrl to the chat endpoint (e.g.,
api.minimax.chat/anthropic), the image generation would incorrectly
use that endpoint, resulting in "invalid api key" errors.
This fix always uses the dedicated image generation endpoint,
ignoring the provider's baseUrl configuration for image generation.
Fixes#61149
* fix(minimax): support CN endpoint for image generation
Respect MINIMAX_API_HOST environment variable to determine whether
to use the global (api.minimax.io) or CN (api.minimaxi.com) endpoint
for image generation.
This ensures that CN users who configure MINIMAX_API_HOST to use
api.minimaxi.com will continue to use the CN endpoint for image
generation, while global users continue to use api.minimax.io.
The original bug was caused by the code extracting the origin from
the provider's configured baseUrl, which could be set to incorrect
endpoints like api.minimax.chat. This fix uses the dedicated image
generation endpoints instead.
Fixes#61149
* fix(minimax): infer CN endpoint from provider config when env is unset
When MINIMAX_API_HOST is not set, fall back to checking the provider's
configured baseUrl to determine whether to use the CN or global image
endpoint. This ensures CN users who went through onboarding (which sets
models.providers.minimax.baseUrl to https://api.minimaxi.com/anthropic)
are correctly routed to the CN image endpoint.
The isMinimaxCnHost check ensures we only use the baseUrl origin for
CN detection - invalid endpoints like api.minimax.chat would not match
minimaxi.com and would correctly fall through to the global default.
Fixes#61149
* test(minimax): cover dedicated image endpoints
* fix(logging): handle context assembly diagnostics
* Revert "fix(logging): handle context assembly diagnostics"
This reverts commit f51d2f7d67f8193268dd37553ac77e80a0423390.
* test(minimax): isolate image endpoint env
* docs(changelog): credit minimax image fix
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* docs(browser): note tilde expansion also covers per-profile paths
The 95a2c9b fix expanded "~" for both `browser.executablePath` and
per-profile `profiles.<name>.executablePath` (config.ts:382 calls
`normalizeExecutablePath` for profile overrides). Per-profile
`userDataDir` on existing-session profiles is also tilde-expanded
(config.ts:391 via `resolveUserPath`). The configuration reference
only mentioned the top-level `browser.executablePath` case.
* docs(browser): align tilde path config help
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
* docs(browser): document local startup timeout bounds
The new browser.localLaunchTimeoutMs and browser.localCdpReadyTimeoutMs
options are clamped to MAX_BROWSER_STARTUP_TIMEOUT_MS (120000 ms) by
normalizeStartupTimeoutMs in extensions/browser/src/browser/config.ts,
and zero/negative/non-finite values fall back to the defaults. Without
this in the configuration reference, users setting a higher value see
no error and silently get the 120 s ceiling, or set 0 expecting 'no
timeout' and silently get the default.
* docs(browser): clarify startup timeout validation
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Fix the bundled Bonjour gateway discovery crash-loop caused by ciao probe cancellation rejections after the Bonjour plugin migration.
The plugin entry now wires the existing rejection handler into the advertiser, and the unhandled-rejection handler registry is anchored on globalThis so staged plugin SDK module copies register into the same process-level handler set used by the host.
Verification:
- pnpm test:serial extensions/bonjour/src/advertiser.test.ts src/infra/unhandled-rejections.fatal-detection.test.ts
- OPENCLAW_LOCAL_CHECK_MODE=throttled pnpm check:changed partially completed: conflict markers plus core/core-test/extensions/extension-test typecheck passed; local lint lane hit a self-lock and was stopped.
Five recent diagnostics-otel feat commits added user-facing OpenTelemetry
surfaces but did not update docs/logging.md, so the listed metrics and
spans drifted out of sync with what the plugin actually exports:
- 7bbd47349e adds gen_ai.client.token.usage histogram (GenAI semconv)
- b8a41739d5 adds memory heap/rss histograms, pressure counter and span
- d6ef1fcf24 adds openclaw.tool.loop counters and span
- ff172f46a5 adds openclaw.context.assembled span
- 44114328b4 adds openclaw.provider.request_id_hash attr on
openclaw.model.call spans
Append the new metrics under existing model-usage and exec sections,
add a 'Diagnostics internals' subsection for memory + tool-loop
metrics, and add the three new spans (context.assembled, tool.loop,
memory.pressure) plus the request-id-hash attribute to the spans
listing.
Fixes context usage display regressions and prevents active runs from being interrupted by channel reloads. Adds persisted tool-result detail bounds so large tool metadata stays out of model/session payloads.
* feat(litellm): add image generation provider
Registers litellm as an image-generation provider so model refs like
litellm/gpt-image-2 route through the LiteLLM proxy, and
agents.defaults.imageGenerationModel.fallbacks entries of the form
litellm/... resolve without "No image-generation provider registered
for litellm" errors.
Implementation uses the OpenAI-compatible /images/generations and
/images/edits endpoints that LiteLLM proxies for. BaseUrl resolves from
models.providers.litellm.baseUrl (default http://localhost:4000). Private
network is auto-allowed when baseUrl is a loopback/RFC1918 address, which
covers the common self-hosted LiteLLM proxy case without needing
OPENCLAW_PROVIDER_ALLOW_PRIVATE_NETWORK. Public baseUrls keep normal SSRF
defaults.
Default model is gpt-image-2 (matching upstream 4.21+ OpenAI default).
Advertises the same 2K/4K sizes OpenAI now exposes, plus legacy
256/512/1024 for dall-e-3. Supports both generate and edit.
Local patch. LiteLLM has no upstream image-generation support yet; revisit
if upstream adds one.
* ci: rerun after upstream main hot-fix
* fix(litellm): harden image generation provider
---------
Co-authored-by: Chris Zhang <chris@ChrisdeMac-mini.local>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Val Alexander's c65aa1d2a6 (#71639) changed assistant avatar uploads
from gateway config persistence to localStorage, mirroring the existing
user-avatar pattern. CHANGELOG covered it but docs/web/control-ui.md
'Personal identity (browser-local)' section only documented the user
identity. Add a paragraph noting the assistant avatar override follows
the same browser-local pattern, while keeping the ui.assistant.avatar
config field reachable for non-UI clients writing the field directly.
* fix(control-ui): rebalance quick settings into stable 3-col bento
Pair Appearance with Automations and let Channels stand alone in the
middle column so all three top-row columns reach similar heights.
Promote Personal to a full-width row with a horizontal body
(identity tiles | emoji + actions) so the avatar block stops fighting
for half-width space. Drops the unused .qs-stack--wide hook.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
* refactor(control-ui): rebalance Personal card with symmetric User↔Assistant identity pair
Restructure Personal card layout to present User and Assistant as 2 balanced identity cards instead of separate User tile + form controls. Mirrors the visual hierarchy and UI pattern across both identities.
Changes:
- Move User avatar text input into User identity card's .__repair section (mirroring Assistant's structure)
- Inline "Choose image" and "Clear avatar" buttons as flex-wrapped action group
- Remove .qs-personal-body and .qs-personal-form wrapper divs
- Update Personal card's .qs-identity-grid to 2-column layout with balanced spacing
- Responsive collapse to 1-column at ≤760px
Tests:
- config-quick.test.ts updated to expect 2 stacks (no longer wrapping Personal in form)
- config-quick.test.ts validates identity card layout now has symmetric User↔Assistant structure
- All 10 quick settings view tests passing
- All 20 schema regression tests passing
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
* chore: ignore .vmux worktree paths
* fix(control-ui): persist assistant avatar override locally instead of via gateway config
Mirrors the user-avatar pattern: assistant avatar uploads now go to
localStorage and overlay the gateway-resolved identity at bootstrap and on
agent.identity.get refreshes. Sidesteps the ui.assistant.avatar zod cap
that rejected uploaded data URLs as 'Too big: expected string to have
<=200 characters', removes one config.patch RPC from the avatar path, and
collapses the upload handler from a 44-line async/loadConfig dance into a
plain synchronous setter.
Also lifts the gateway-side ui.assistant.avatar schema cap from 200 to
2,000,000 to match the user-avatar size budget for non-UI clients writing
the field directly, and adds a content-aware text/image normalizer in
ui/src/ui/assistant-identity.ts so short-text avatars stay short while
data URLs survive round-tripping.
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Fix duplicate section title and description rendering in single-section Control UI config pages.\n\nKeeps root multi-section card headers intact, keeps single-section hero copy as the only visible section title, and adds browser coverage for both single-section and root views.\n\nFixes #68003.\n\nThanks @d1rshan.
Vincent's commit ab1d1a5c9e (#71560) added user-facing config keys to
existing-session profiles for the Chrome DevTools MCP launch path:
- browser.profiles.<name>.mcpCommand
- browser.profiles.<name>.mcpArgs
Plus runtime behavior changes:
- cdpUrl http(s) -> --browserUrl, cdpUrl ws(s) -> --wsEndpoint
- endpoint flags and userDataDir are mutually exclusive
The CHANGELOG entry covered the change, but docs/tools/browser.md
existing-session reference did not. Add a 'Custom Chrome MCP launch'
subsection describing the new fields and the cdpUrl endpoint mapping
rules.
Fixes openclaw#70973. Adds a \`google-gemini-cli\` branch to \`getLocalCliCredentialFingerprint\` that lifts OpenID \`id_token\` \`sub\`/\`email\` claims from \`~/.gemini/oauth_creds.json\` onto \`GeminiCliCredential\` so the shared \`encodeOAuthIdentity\` produces an identity-keyed auth-epoch matching the Claude/Codex contract, plus bumps \`CLI_AUTH_EPOCH_VERSION\` from 3 to 4 so existing v3 Gemini bindings without an \`authEpoch\` ride the existing \`cli-session.ts\` version-gate instead of forcing a one-time invalidation.
Fix Telegram partial-stream preview finalization so ambiguous final edit failures fall back to a final send when the visible preview is a strict prefix of the answer.
Includes archived-preview regression coverage and generated config metadata refresh.
Thanks @sahilsatralkar.
Co-authored-by: Sahil Satralkar <62758655+sahilsatralkar@users.noreply.github.com>
Polishes the basic config identity layout, aligns assistant avatar rendering with chat, and adds a Control UI assistant avatar override with IDENTITY.md fallback.
* fix(memory-host-sdk): use TRUSTED_ENV_PROXY mode in withRemoteHttpResponse
When a HTTP/HTTPS proxy is configured via environment variables
(HTTPS_PROXY, HTTP_PROXY, ALL_PROXY), the withRemoteHttpResponse
function now passes mode=TRUSTED_ENV_PROXY to fetchWithSsrFGuard.
This causes DNS resolution to skip the local resolver and route
through the configured proxy, fixing 'fetch failed' errors for
remote memory embeddings (including GitHub Copilot embeddings) in
proxy environments (e.g. Clash TUN, corporate proxies).
Previously, without an explicit mode, fetchWithSsrFGuard defaulted
to STRICT mode which performs local DNS pre-resolution via
resolvePinnedHostnameWithPolicy(), failing in proxy environments
where DNS must go through the proxy.
Fixes: openclaw/openclaw#52162
* fix: harden memory env proxy guard (#71506) (thanks @DhtIsCoding)
---------
Co-authored-by: Dht <dht@openclaw.ai>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Fixes#71494.
- Render Control UI links with https:// when gateway TLS is enabled.
- Render websocket links with wss:// through the shared link resolver.
- Add daemon status handoff coverage and TLS scheme docs.
Co-authored-by: deepkilord <wang_hgang@msn.com>
The empty-body guard only checked baseBodyFinal (current message body)
and softResetTail, ignoring inboundUserContext which includes
InboundHistory from group chat context. This caused the bot to reject
bare @mentions in Feishu group chats where prior messages provided the
conversation context via InboundHistory.
Now hasUserBody also checks whether inboundUserContext has content,
matching the behavior before the 2026.4.12 refactor.
Eduardo Cruz's PWA web push feat (21b7ad5805, #44590) added a substantial
user-facing surface — manifest.webmanifest, sw.js, gateway push.web.*
methods, persisted vapid-keys.json/web-push-subscriptions.json, and
OPENCLAW_VAPID_* env overrides — but did not touch any docs/.
Add a 'PWA install and web push' section to docs/web/control-ui.md
covering the new persisted state files, env vars, and the four scope-gated
gateway methods (push.web.vapidPublicKey, push.web.subscribe,
push.web.unsubscribe, push.web.test). Distinguish from the existing
APNS relay-backed iOS push path.
Adds browser PWA manifest and service worker support for the Control UI, plus gateway RPC methods and persisted Web Push subscription handling.
Maintainer verification:
- OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test src/infra/push-web.test.ts src/gateway/server-methods/push.test.ts src/gateway/control-ui.test.ts src/gateway/protocol/push.test.ts
- pnpm check:changed passed before final GitHub update-branch merge commit
- pnpm build
Source head: 0720024368
Strip configured trailing /v1beta from Google music/video generation base URLs before calling the Google GenAI SDK.\n\nFixes #63240.\n\nThanks @Hybirdss.
Preserve Google Chat reply text when typing indicator cleanup or update fails.
- Extract Google Chat reply delivery into a focused module
- Retry the failed first text chunk as a new message after placeholder update failure
- Cover media caption and chunk fallback regressions
Thanks @colin-lgtm.
Summary:
- Show full date and time in Control UI chat message footers.
- Collapse assistant model/token/context metadata behind an explicit Context disclosure.
- Update changelog attribution guidance to allow multi-author credited entries.
Validation:
- OPENCLAW_LOCAL_CHECK=0 pnpm test ui/src/ui/chat/grouped-render.test.ts
- OPENCLAW_LOCAL_CHECK=0 pnpm test src/commands/gateway-status/helpers.test.ts
- OPENCLAW_LOCAL_CHECK=0 pnpm check:changed
- GitHub CI passed on f071a38177
eleven_v3 already works end-to-end (model_id passes through to the API
without validation), but was missing from ELEVENLABS_TTS_MODELS so it
never appeared in the in-product model picker or catalog metadata.
* fix(heartbeat): clamp scheduler delay to Node setTimeout cap (#71414)
When `agents.defaults.heartbeat.every` resolves to >2_147_483_647 ms
(~24.85d), the previous scheduleNext() called setTimeout with the raw
delay. Node clamps any delay > 2^31-1 to 1 ms, fires the callback, and
the heartbeat re-arms with the same oversized value - a tight loop that
floods the log with TimeoutOverflowWarning and crashes the gateway with
exit code 1.
Clamp the computed delay to HEARTBEAT_MAX_TIMEOUT_MS (2_147_483_647)
before calling setTimeout. The worst case is now one heartbeat every
~24.85d instead of crash-loop. Warn once per process when clamping
fires, so a misconfigured "365d" remains visible without flooding.
This is a defense-in-depth fix at the scheduler layer; loadConfig-level
rejection is a broader change with more blast radius and a separate
question (some users may legitimately want "every: 365d" to mean
"effectively never"). The clamped behaviour is closer to that intent
than the crash is.
Test: new scheduler test sets heartbeat.every="365d" with fake timers,
advances 60s, and asserts runSpy was never called (with the bug, it
would be called ~60_000 times).
* style: format heartbeat scheduler clamp
* fix: share safe timeout delay clamp (#71478) (thanks @hclsys)
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Remove the misleading API Keys card from the quick settings page.
The card was hardcoded to a fixed env-var provider list and routed all actions to the broad Environment config section, which made the Add/Change affordances look more precise than they were. This removes the dead surface and keeps the quick settings grid focused on meaningful controls.
Verified:
- pnpm test ui/src/ui/views/config-quick.test.ts
- CI passed on PR #71496
Remove the startup persisted-offset getUpdates preflight so polling restarts do not self-conflict before the grammY runner starts.\n\nFixes #69304.\n\nThanks @chinar-amrutkar.
Add bounded outbound message delivery lifecycle diagnostics and OTEL export without message body, recipient, room, media path, or raw channel result data.
Polish the Control UI markdown preview chrome and sidebar raw-text behavior.
- Add the upgraded preview dialog/sidebar chrome and tighten related CSS coverage.
- Show workspace-relative paths in the markdown preview dialog instead of absolute filesystem paths.
- Preserve raw markdown source for idempotent raw-text toggles.
- Align browser plugin-sdk facade export parity for DEFAULT_BROWSER_ACTION_TIMEOUT_MS.
- Stabilize the gateway update channel test by waiting for the async update runner call.
Validation:
- OPENCLAW_LOCAL_CHECK=0 pnpm test ui/src/ui/views/agents.test.ts ui/src/ui/views/chat.test.ts src/plugins/contracts/plugin-sdk-subpaths.test.ts src/gateway/server.roles-allowlist-update.test.ts
- OPENCLAW_LOCAL_CHECK=0 pnpm check:changed
- GitHub checks green on ebbe96fc88
Three entries were missing co-credits I should have preserved:
- Diagnostics/OTEL exec-process spans (#71451): @vincentkoc implemented,
but @jlapenna's #70424 proposed the broader tracing work this entry
builds on. Now credits both.
- Diagnostics/OTEL preloaded SDK (#71450): same pattern — credits
@vincentkoc and @jlapenna.
- Agents/tool-result pruning (#51267): @cgdusek's PR explicitly built
on prior work in #39331 by @alvinttang and #34980 by @coffeexcoin.
Now credits all three.
- Two Diagnostics/OTEL Changes entries credited issue #70424 (jlapenna's
open meta-tracing proposal) as the PR ref. The actual implementing
PRs landed as #71451 (exec-process telemetry) and #71450 (preloaded
SDK mode), both authored by @vincentkoc — corrected.
- Telegram/webhook fix had no Thanks credit. Issue #71392 reporter
@joelforsberg46-source identified the delivery-retry behaviour, so
credit them on the entry.
* test(browser): cover tilde edge cases for executablePath
Adds coverage for cases the original tilde-expansion fix in 95a2c9b
intentionally supports but does not assert:
- bare "~" expands to the home directory
- Windows-style "~\AppData\..." expands to $HOME on Windows
- a stray "~" mid-path (e.g. /opt/~chromium/chrome) is preserved verbatim,
guarding the regex anchor against future regressions
No production code changes; tests only.
* test(browser): skip Windows-style ~\ tilde test on POSIX
path.resolve treats backslashes as literal characters on POSIX, so
"~\AppData\..." cannot resolve to "$HOME/AppData/..." on Linux/macOS.
Gate that case to win32 to keep the assertion meaningful.
- Remove duplicate #66884 alexlomt entry from top Unreleased > Fixes;
the canonical entry already lives under 2026.4.24 (Unreleased) per
Mason Huang's earlier 'move #66884 entry to 2026.4.24' commit.
- Reflow the wrapped 3-line Tool Access bullet (#71405) onto a single
line so it matches every other bullet in the section.
Three external-contributor commits from the last day landed without
CHANGELOG entries:
- Alex Fries (#68286, @ajfonthemove): hybrid memory search component
scores. Added under Unreleased > Changes (feat).
- Charles Dusek (#51267, @cgdusek): malformed tool-result text-block
guard. Added under Unreleased > Fixes.
- Jerome Benoit (#59935, @jerome-benoit): Nix Home Manager daemon PATH
support. Added under Unreleased > Fixes.
Also drop a duplicate raw-subject changelog line for #66884 that
restated alexlomt's already-formatted entry one line above.
Expose raw `vectorScore` and `textScore` alongside the combined hybrid memory search `score`.
- Preserve vector/text component scores from `mergeHybridResults` output.
- Add optional component-score fields to both memory host SDK type surfaces.
- Extend hybrid merge tests for vector-only, text-only, and overlapping result cases.
- Document that component scores remain raw retrieval diagnostics while temporal decay/MMR only adjust or reorder the combined ranking `score`.
Closes#68166.
Maintainer verification:
- `pnpm test extensions/memory-core/src/memory/hybrid.test.ts`
- `pnpm check:changed`
- Fresh GitHub checks passed.
Co-authored-by: Alex Fries <alex@engramlabs.io>
Harden context pruning and tool-result character estimation against malformed `{ type: "text" }` blocks created by void/undefined tool handler results.
- Require text blocks to carry a string before using `.length` in the tool-result estimator.
- Guard context-pruning text/image loops against malformed and null content entries.
- Serialize malformed non-string text blocks for pruning size accounting so they cannot bypass trimming as zero-sized.
- Add regression coverage for malformed text blocks, null entries, and non-string text payloads.
Closes#34979.
Maintainer verification:
- `pnpm test src/agents/pi-embedded-runner/tool-result-char-estimator.test.ts src/agents/pi-hooks/context-pruning/pruner.test.ts`
- `pnpm check:changed`
- GitHub checks passed, including the OpenAI / Opus 4.6 parity gate.
Based on prior work by #39331 and #34980.
Co-authored-by: Charles Dusek <cgdusek@gmail.com>
Co-authored-by: alvinttang <alvinttang@users.noreply.github.com>
Co-authored-by: coffeexcoin <coffeexcoin@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Two recent code changes lacked or had only partial doc coverage:
- contextInjection 'never' (#65006, xDarkicex): the new mode is now
documented under agents.defaults.contextInjection, alongside the
existing 'continuation-skip' mode, with guidance on when to use it
(custom context engines, native runtimes that own their prompt).
- Nix Home Manager daemon PATH (#44402, jerome.benoit): document the
service PATH auto-discovery (NIX_PROFILES right-to-left precedence
and ~/.nix-profile/bin fallback) under the Nix install page.
Also sentence-case three Title-Cased headings on the Nix page ('What
You Get', 'Quick Start', 'Nix Mode Runtime Behavior') and drop a
duplicate body H1 that restated the frontmatter title.
* fix(feishu): prevent duplicate message after streaming card close (#67791)
When onIdle closed the streaming card before the final delivery arrived, the streamed text was not tracked in deliveredFinalTexts. The subsequent final payload bypassed the streaming?.isActive() guard (already closed) and fell through to the non-streaming path, sending the same content as a redundant text/card message. Track raw streamText in deliveredFinalTexts when closeStreaming finalizes the card so the duplicate-final check catches it.
* test(feishu): cover idle streaming final dedupe
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Add Nix Home Manager profile bin directories to generated gateway service PATHs on macOS and Linux.
Includes ~/.nix-profile/bin fallback when NIX_PROFILES is absent, honors NIX_PROFILES right-to-left precedence when present, and covers the service PATH resolver with focused unit tests.
Closes#44402.
Defers the Node fs.constants lookup until tmp-dir resolution actually runs, adds browser-shim import regression coverage, and records the fix in the changelog.\n\nLocal verification:\n- pnpm test src/infra/tmp-openclaw-dir.browser-import.test.ts src/infra/tmp-openclaw-dir.test.ts src/logging/logger.browser-import.test.ts\n- pnpm test src/infra/run-node.test.ts -t "serializes runtime postbuild restaging|forwards wrapper SIGTERM"\n- pnpm build\n\nCo-authored-by: Valentinws <Valentinws@users.noreply.github.com>
Adds regression coverage for provider-qualified nested model ids such as nvidia/deepseek-ai/deepseek-v3.2.
Validated:
- pnpm test ui/src/ui/chat-model-ref.test.ts ui/src/ui/chat-model-select-state.test.ts
Thanks @monsonego.
Three table headers introduced in recent agent-runtime / Codex-harness
doc commits used Title Case despite the surrounding house style:
- agent-runtimes.md L17: 'What It Means' -> 'What it means'
- agent-runtimes.md L100: 'Why It Matters' -> 'Why it matters'
- codex-harness.md L615: 'V1 Boundary' / 'Future Path' ->
'V1 boundary' / 'Future path' (V1 stays as the recognized acronym)
Four pages started with weak meta-descriptions ('This page covers...')
that restate the frontmatter summary. Replace with direct content-first
openings, and sentence-case a stray 'Slash Commands' link in
configuration-reference.
- concepts/streaming.md: remove '# Streaming + chunking'.
- reference/session-management-compaction.md: remove Title Case H1
'# Session Management & Compaction (Deep Dive)'.
- plugins/voice-call.md: remove '# Voice Call (plugin)'.
CLI pages keep their command-formatted body H1s since that is the repo
convention and the formatting is not expressible in frontmatter.
Sweep recent (last ~5h) doc edits for two readability/uniformity issues:
- Replace 42 path-as-text links of the form '[/foo/bar](/foo/bar)' with
descriptive labels derived from each target page's frontmatter title
(e.g. '[Anthropic]', '[Token use and costs]', '[OpenAI-compatible
endpoints]'). Affected files include gateway/troubleshooting,
concepts/oauth, reference/session-management-compaction, and
reference/transcript-hygiene.
- Sentence-case Title-Cased headings and link text in Related sections
across codex-harness, model-providers, tools/plugin, sdk-runtime,
sdk-setup, prompt-caching, ci, cli/config, google-meet, browser,
rich-output-protocol, subagents, web/control-ui, while preserving
brand and proper-noun capitalization (OpenAI, Codex, Chrome, Parallels,
Z.AI, etc.).
* [EV-001] memory-core: filter memory_search session hits by visibility
- Move session visibility + listSpawnedSessionKeys to plugin-sdk; sync test
hook with sessions-resolution __testing.setDepsForTest
- Extract loadCombinedSessionStoreForGateway to config/sessions; re-export
from gateway session-utils
- Add session-transcript-hit stem resolver for builtin + QMD paths
- Post-filter memory_search results before citations/recall; fail closed when
requester session key missing; optional corpus=sessions
- Tests: stem extraction, visibility filter smoke, existing suites green
* chore: sync plugin-sdk exports for session-transcript-hit and session-visibility
Run pnpm plugin-sdk:sync-exports so package.json exports match
scripts/lib/plugin-sdk-entrypoints.json. Fixes contract tests and
lint:plugins:plugin-sdk-subpaths-exported for memory-core imports.
* fix(EV-001): cross-agent session memory hits + hoist combined store load
- resolveTranscriptStemToSessionKeys: stop filtering by requester agentId so
keys from other agents reach createSessionVisibilityGuard (a2a + visibility=all).
- Re-export loadCombinedSessionStoreForGateway from session-transcript-hit;
filterMemorySearchHitsBySessionVisibility loads the combined store once per pass.
- Drop unused agentId from filter params; extend tests (Greptile/Codex review).
* fix(memory_search): honor corpus=sessions before maxResults cap
Pass sources into MemoryIndexManager.search so FTS/vector queries add
source IN (...) before ranking and top-N slice (Codex: non-session hits
could fill the window).
QMD path: oversample fetch limit for single-source recall, filter by
source, then diversify/clamp to the requested maxResults.
Wire corpus=sessions from tools; extend MemorySearchManager opts and
wrappers.
* fix(memory_search): apply corpus=memory source filter like sessions
Pass sources: ["memory"] into manager.search so maxResults applies only
within the memory index; post-filter for defense in depth. Document
corpus=memory in the tool description.
* fix: scope qmd session memory search
* fix: enforce memory search session visibility (#70761) (thanks @nefainl)
---------
Co-authored-by: NefAI <info@nefai.nl>
Co-authored-by: Ayaan Zaidi <hi@obviy.us>
Preserve the requester-agent announce path for thread-bound subagent completions, while falling back to direct thread delivery only when the announce fails or produces no visible output.\n\nThanks @DolencLuka.
When navigating the /models picker via provider button click, the model
list showed raw model IDs (e.g. gemini-3.1-pro-preview) instead of
configured display names (e.g. Gemini 3.1 Pro (Bridge)).
Root cause: the button-click callback handler destructured modelData as
{ byProvider, providers } omitting modelNames, then called
buildModelsKeyboard() without it. buildModelsKeyboard falls back to the
raw model ID via modelNames?.get(...) ?? model when modelNames is absent.
The text-command path (/models <provider>) already passes modelNames
correctly through buildTelegramModelsListChannelData, confirming the fix.
Fix: destructure modelNames from modelData and forward it to
buildModelsKeyboard in the button-click callback handler.
Closes#70560
Fixes#70889 and #70890.
Retains overlapping/shared agent workspaces during `openclaw agents delete`, keeps `--json` output machine-readable, and repairs the stale hook-runner test harness mock that blocked CI.
Thanks @kaseonedge.
- Expand author->handle map with maintainers from docs/CONTRIBUTING.md
(Robin Waslander/@hydro13, Josh Lehman/@jalehman, Radek/@velvet-shark,
Muhammed/@mukhtharcm, Tengji/@odysseus0, Sliverp, Mason Huang/@hxy91819)
and PR-author lookups via gh for two dozen one-off contributors.
- Strip duplicate trailing 'Thanks @x' lines that prior backfill chunks
had introduced when an existing lowercase 'thanks @y' credit was already
present (case-sensitive skip check missed them); preserve the original
contributor credit.
- Dedupe doubled '(#NNNN)' tokens introduced by the same bug.
* fix(cron): default missing sessionTarget on load and guard assertSupportedJobSpec
* fix(cron): use Object.hasOwn for payload.kind check and log the backfill
Address review feedback on #70367:
- Switch the new payload.kind lookup from `in` to `Object.hasOwn` so
prototype pollution cannot drive the defaulter (Aisle Low finding).
- Log a warning when a job is auto-defaulted at load time, matching the
adjacent legacyJobIdIssue pattern so operators can run `openclaw
doctor --fix` to persist the canonical shape (Greptile P2).
* fix(cron): dedupe sessionTarget backfill warn per jobId and sharpen crash site reference
Address deep-review feedback on #70367:
- The code comment referenced assertSupportedJobSpec as the tick-time
crash site, but that function is only called from create/patch
(jobs.ts:607, 686) and manual-run preflight (ops.ts:516). The actual
on-tick TypeError surfaces in runIsolatedAgentJob (server-cron.ts).
Update the comment to say so.
- ensureLoaded runs with forceReload:true on every onTimer tick (~60s).
Before this change, a persistent legacy job missing sessionTarget
produced one warn line per tick, forever. Add a per-jobId dedupe set
on CronServiceState (mirroring the existing warnedDisabled flag) so
the warn fires once per job per process.
- Drop the 'run openclaw doctor --fix' remediation from the warn
message. Doctor's cron-store migration has no trackIssue entry for
missing sessionTarget (doctor-cron-store-migration.ts CronStoreIssueKey),
so doctor --fix on a store whose only defect is missing sessionTarget
silently returns without writing anything. Point operators at
jobs.json directly until that gap is closed.
* docs(changelog): note cron session target repair
---------
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
prepareCliBundleMcpConfig was not including cfg.mcp.servers when building
the temporary mcp.json that gets passed to claude-cli via --mcp-config.
This meant user-defined MCP servers (e.g. mcp.servers.omi in openclaw.json)
were silently dropped, even though --strict-mcp-config prevents any other
path for those servers to reach the CLI session.
The Pi runtime path (loadEmbeddedPiMcpConfig) already merges cfg.mcp.servers
after the bundle layer. This commit applies the same merge to the CLI runtime
path, with identical precedence: bundle defaults < user mcp.servers <
additionalConfig (loopback). The loopback entry remains last so it cannot be
overridden by user config.
Fixes: user-configured MCP servers not appearing as mcp__<name>__* tools in
claude-cli sessions started by OpenClaw.
* fix(auth): bootstrap codex cli credential without clobbering local
readCodexCliCredentialsCached was imported but never registered in
EXTERNAL_CLI_SYNC_PROVIDERS, so overlayExternalAuthProfiles could not
seed openai-codex:default on fresh agents and runtime surfaced
"No API key found for provider openai-codex" even after a successful
codex login.
Register the provider with a new bootstrapOnly flag. Providers flagged
bootstrapOnly are adopted only to fill an empty slot: the overlay skips
them when a local OAuth credential already exists for the profile, and
readExternalCliBootstrapCredential returns null so the refresh path
never replaces the locally stored canonical refresh token with stale
CLI state. Minimax keeps its existing replace-on-expiry behavior.
* test(auth): cover codex cli bootstrap
---------
Co-authored-by: sudol <sudol@A8Max.localdomain>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Patch live session usage metadata into the Control UI session list, coalesce overlapping refreshes, and add a compact action when fresh context usage is high.
Keep session refresh loading separate from session mutation ownership so background refreshes cannot re-enable mutation UI or overwrite delete/restore state mid-flight.
Co-authored-by: Val Alexander <68980965+BunsDev@users.noreply.github.com>
Preserve tokenjuice runtime rule JSON under dist/rules/tests during bundled plugin runtime dependency staging while continuing to prune unrelated tests directories.
Fix live webchat finalization for Codex app-server runs by emitting standard assistant and lifecycle completion events on the global agent event bus, instead of relying on a message-less chat.final fallback.
Replaces #70815. Closes#71183.
Co-authored-by: Lēsa <260982214+lesaai@users.noreply.github.com>
Browser control now authorizes only the resolved active gateway credential and fails closed when password mode lacks a resolved password.
Also removes the duplicate Slack test-helper middleware stub that kept current CI red after the base rebase.
Fixes#65626.
Co-authored-by: Coy Geek <65363919+coygeek@users.noreply.github.com>
* fix(gateway): restart channels after secret reload
* fix(gateway): serialize secrets.reload and isolate channel restart errors
Address review feedback from Greptile (P1), Codex (P2), and Aisle (Medium,
CWE-362) on #70720:
- Serialize the entire secrets.reload path through a promise tail lock so
concurrent callers cannot overlap the stop/start loop or diff against a
stale pre-activation snapshot.
- Wrap each channel's stop/start pair in a try/catch so one channel failing
to restart does not leave other changed channels unrestarted.
- Register slack/zalo/discord channel plugins with reload.configPrefixes in
the test setup so channels.<id>.* diff paths actually match a restart rule
(without this, the diff falls through to restart-gateway and the handler
never enters the per-channel restart branch).
- Add tests covering concurrent-reload serialization and per-channel
restart-failure isolation.
* fix(gateway): surface channel restart failures from secrets.reload
Address review feedback on the previous commit:
- Codex P1: `secrets.reload` swallowed per-channel restart failures and
still returned `{ ok: true }`, so a rotation that left a channel on the
old secret looked successful to the caller. The handler now collects
restart failures during the loop and throws an aggregate error after
attempting every channel, so the client-side RPC response surfaces the
partial failure while unaffected channels still restart (preserving the
original Greptile P1 non-cascading semantic).
- Greptile P2: test mock-call assertions sorted the captured channel
arguments so they no longer depend on `Set`/object-key iteration order,
which is not a stable contract of the handler.
* fix(gateway): harden secrets reload followups
* docs(changelog): note secret-backed channel restart on secrets.reload
* test(gateway): align secrets reload snapshot activation
* test(gateway): reset plugin runtime state in aux handlers
* fix(gateway): refresh reload rules and roll back channels
* fix(gateway): harden secrets.reload rollback tests
* test(gateway): inject aux handler reload plan
* test(gateway): avoid resettable reload-plan mocks
* test(gateway): isolate aux handler tests from skip env-var leakage
test-helpers.mocks.ts and test-helpers.server.ts set
OPENCLAW_SKIP_CHANNELS=1 / OPENCLAW_SKIP_PROVIDERS=1 at module load. When
a shared vitest worker imports those helpers before this file's tests
run, the leaked env vars route the secrets.reload skip-mode branch and
the channel restart loop never fires. Add a beforeEach that clears both
env vars so the suite is independent of worker import order.
* fix(gateway): restore required generation on secrets.reload rollback
setCurrentSharedGatewaySessionGeneration can clear `required` as a side
effect of activating a new generation. The previous rollback path
restored only `current`, leaving `required` cleared and weakening
shared-gateway auth-generation enforcement after a failed reload (Aisle
CWE-287). Capture both fields before activation and restore both in the
catch block. Add a focused regression test that locks in the contract.
* fix(gateway): track restart channels for rollback before stopChannel awaits
Pushing to stoppedChannels only after `await stopChannel` succeeded meant
that if stopChannel rejected mid-call (for example, a plugin stopAccount
hook throws after the runtime already closed the socket), the rollback
loop skipped that channel entirely. A failed secrets.reload could then
leave the channel down. Track the channel before awaiting so rollback
always attempts to bring it back, and add a regression test.
Export diagnostics OTEL logs through bounded diagnostic log events while keeping core log records off the public plugin diagnostic stream.\n\nIncludes security hardening for log payload redaction, bounded attributes, prototype-pollution keys, OTEL export failure reporting, and extension SDK seam usage.
* fix(slack): route stream-fallback delivery through chunked sender
deliverPendingStreamFallback was calling chat.postMessage directly for
err.pendingText, which bypasses the chunked reply path used everywhere
else. For Slack Connect cases where appendSlackStream throws
SlackStreamNotDeliveredError with a large pending buffer, the single
raw post could fail (msg_too_long) and drop the unsent tail.
Two changes:
1. deliverPendingStreamFallback now routes through deliverReplies so
long pendingText is chunked by the normal sender and the fallback
honors the configured replyToMode / identity.
2. The non-benign streaming-error branch in deliverWithStreaming now
clears the session via markSlackStreamFallbackDelivered before
falling back to deliverNormally. Without this, pendingText stays
populated and the post-loop finalize (stopSlackStream →
SlackStreamNotDeliveredError → fallback) re-posts the same chunk
that deliverNormally already sent.
Addresses the three Codex P1 findings on #70370 about bypassing the
chunked sender, and the related "avoid reposting buffered text after
append fallback" P1 about duplicate delivery. Tests updated to assert
deliverReplies routing (instead of raw postMessage) and a new case
covers the non-benign-error dedup.
Follow-up to #70370.
* fix(slack): preserve pending buffered text on non-benign stream errors
Address Codex P1 on #71124: `markSlackStreamFallbackDelivered` was
clearing `pendingText` before `deliverNormally` ran, so any earlier
buffered chunk was lost. E.g. chunk A buffered in the SDK, then
appending chunk B throws a generic network error → previous fix
dropped A+B and only sent B via `deliverNormally`, silently truncating
the final reply.
Route the full buffered `pendingText` through
`deliverPendingStreamFallback` with a synthetic
`SlackStreamNotDeliveredError`, then skip `deliverNormally` entirely
(pendingText already contains this payload's text, per
`appendSlackStream` accumulating before throw). If the chunked
fallback fails, fall back to `deliverNormally` so at least the current
payload lands.
Test updated to assert the full pendingText ("first buffered\nsecond
payload") gets routed through the chunked sender, not the
chunk-B-only partial send.
* fix(slack): harden stream fallback docs and chunking test (#71124)
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Verified against Carbon 0.16.0 source:
- Client constructor calls plugin.registerClient(this) without awaiting it.
- GatewayPlugin.registerClient publishes client before its awaited metadata fetch.
- identify() silently returns when client is missing.
This patch matches Carbon's ordering in OpenClaw's subclass, avoids a second super.registerClient call if lifecycle connect already opened the socket during metadata loading, and keeps regression coverage for both ws and isConnecting cases.
Local proof:
- pnpm test extensions/discord/src/monitor/provider.proxy.test.ts extensions/discord/src/monitor/gateway-plugin.test.ts
- pnpm lint:tmp:no-raw-channel-fetch
- pnpm check:changed
- pnpm check
- pnpm test
GitHub checks green for 72547825e1.
Fixes outbound Twilio realtime conversations so the TwiML fetch returns the realtime <Connect><Stream> path for outbound directions and the answered-call path does not overwrite it with legacy <Say> TwiML.
Local proof:
- pnpm test extensions/voice-call/src/manager.notify.test.ts extensions/voice-call/src/webhook.test.ts
- pnpm check:changed
- pnpm check
- pnpm build
- local VoiceCallWebhookServer + CallManager smoke for Direction=outbound-api
Closes#68713.
Keep WebChat runtime context available to the model while persisting only the transcript-facing user prompt across gateway, CLI, queued follow-up, and embedded Pi paths.
Adds regression coverage for history sanitization, CLI transcript persistence, media-only auto-reply prompts, and embedded Pi prompt rewrite against a real SessionManager file.
Co-authored-by: 91wan <91wan@users.noreply.github.com>
Render assistant text avatars from IDENTITY.md consistently in the Control UI chat welcome state and transcript groups.
Also supports authenticated blob avatar URLs in grouped messages and rejects bidi/invisible controls in assistant text avatars.
Verification:
- pnpm test ui/src/ui/chat/grouped-render.test.ts ui/src/ui/views/chat.test.ts ui/src/styles/chat/layout.test.ts
- pnpm check:changed
- GitHub CI green
- Review threads resolved
Keep WhatsApp QR login state synced across gateway, macOS, and UI wait flows.
- Preserve the latest QR data URL/version while login polling rotates codes.
- Keep the wait-result protocol bounded to current QR metadata.
- Stabilize QR rendering and media fixture coverage after rebasing on main.
Validation:
- pnpm test extensions/whatsapp/src/login-qr.test.ts extensions/whatsapp/src/media.test.ts extensions/whatsapp/src/agent-tools-login.test.ts src/gateway/protocol/channels.schema.test.ts src/gateway/server-methods/web.start.test.ts ui/src/ui/controllers/channels.test.ts
- pnpm test:extension whatsapp
- cd apps/macos && swift test --filter ChannelsSettingsSmokeTests
- GitHub PR checks: 62 success, 5 skipped
Adds the VoiceClaw-compatible realtime brain WebSocket endpoint backed by Gemini Live, with owner-auth gating, async OpenClaw tool handoff, docs, and lifecycle tests.
Maintainer fixup: terminal upstream errors now send the error, emit session.ended while the client socket is still open, then close the client-facing socket.
Co-authored-by: Michael Yagudaev <1386966+yagudaev@users.noreply.github.com>
Register agent RPC runs in the shared abort controller map so chat.abort and sessions.abort can interrupt them like chat.send runs.
Also centralize abort-controller registration/owned cleanup, preserve agent timeout semantics for maintenance expiry, and cover pre-dispatch failure cleanup with regression tests.
Fixes#71128.
* fix(googlechat): log webhook auth reject reasons and warn on appPrincipal misconfig
Closes#71078
Webhook auth failures previously returned 401 with no log line, leaving
operators no signal to diagnose. Additionally, app-url audience requires
a numeric OAuth 2.0 client ID as appPrincipal, but a misconfigured email
or empty value silently caused all requests to be rejected.
Changes:
- Log a WARN with accountId and reject reason when verifyGoogleChatRequest fails.
- Add warnAppPrincipalMisconfiguration() called at provider init: warns when
audienceType=app-url and appPrincipal is missing or contains '@'.
Tests: +9 cases in monitor-webhook.test.ts (3 reject-reason scenarios + 4 warner cases).
* fix(googlechat): defer auth rejection logs
* docs: note googlechat webhook auth fix
---------
Co-authored-by: luyao618 <luyao618@users.noreply.github.com>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
two bugs. both squash user model choice silently.
bug 1: applyDefaultModel() unconditional primary: model overwrite.
wizard calls with setDefaultModel=true, provider returns its default
(e.g. openrouter/auto), bam user primary gone. fix: existingPrimary ?? model.
bug 2: applyModelFallbacksFromSelection() phantom primary injection.
when no primary configured, resolvedKey (hardcoded default) written as
primary via nullish coalescing fallback. fix: conditional spread — only
include primary key when one actually existed.
tests for both. closes#70696
Expose first-class hook correlation fields for plugin message and run lifecycle hooks, including frozen diagnostic trace copies for plugin-facing events.
Adds the Gradium bundled plugin with TTS and speech-provider registration, docs, label routing, and focused/live coverage.
Also carries the current main lint cleanup needed for the rebased CI lane.
Co-authored-by: laurent <laurent.mazare@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(whatsapp): setting systemPrompt to "" suppresses the wildcard instead of falling through to it
* test(whatsapp): reset mocks instead of only clearing call history
* docs(changelog): note WhatsApp empty systemPrompt suppresses wildcard
* test(whatsapp): preserve real module exports in process-message mocks
* test(whatsapp): whitespace-only systemPrompt also suppresses wildcard
---------
Co-authored-by: Omar Shahine <10343873+omarshahine@users.noreply.github.com>
Export diagnostics OTEL lifecycle spans for runs, model calls, and tool executions while avoiding retained live span state and high-cardinality/sensitive exported attributes.
* fix(qqbot): enable qqbot plugin by default so runtime deps install before QR-code setup
The qqbot plugin manifest was missing the enabledByDefault: true flag.
Without it, ensureBundledPluginRuntimeDeps treats qqbot as bundled-but-
disabled-by-default (isBundledPluginConfiguredForRuntimeDeps returns
false when no qqbot channel/account is configured yet), so
@tencent-connect/qqbot-connector is never installed into
dist/extensions/qqbot/node_modules on first launch.
This creates a chicken-and-egg failure for the QR-code binding flow:
finalize.ts dynamically imports @tencent-connect/qqbot-connector to run
qrConnect(), but the package isn't present yet because no account is
configured — binding is exactly the step that configures the first
account. Users hit:
QQ Bot 绑定失败: Error [ERR_MODULE_NOT_FOUND]: Cannot find package
'@tencent-connect/qqbot-connector' imported from
.../dist/extensions/qqbot/channel-*.js
Adding enabledByDefault: true makes the host install qqbot's runtime
deps eagerly on first launch, mirroring the pattern already used by
mistral / groq / deepgram / amazon-bedrock-mantle and other bundled
plugins whose providers must be available before any channel config
exists. No code changes required; the existing runtime-deps install
pipeline handles everything once the gate is opened.
* fix(qqbot): changelog for enable-by-default fix (#71051) (thanks @cxyhhhhh)
---------
Co-authored-by: sliverp <870080352@qq.com>
Make diagnostics-otel startup restart-safe by tearing down stale SDK, log transport, and diagnostic-event listener handles before reinitializing or disabling the service. Adds regression coverage for repeated start and disabled restart paths.\n\nThanks @vincentkoc.
Record onboarding plugin install source metadata for npm and local paths, while keeping local path install records portable and preserving uninstall cleanup for relative source paths.
Pass immutable diagnostic trace contexts through agent and tool hook surfaces, emit model usage with the run trace, and parent OTEL spans/logs from validated trace context without retained global state.\n\nThanks @vincentkoc.
* test(cli-runner): RED — assert before_agent_reply fires on cron triggers
Mirrors src/agents/pi-embedded-runner/run.before-agent-reply-cron.test.ts
for the CLI runner. Asserts:
1. When trigger=cron and a before_agent_reply hook claims the turn
(handled: true), runCliAgent must NOT invoke the codex subprocess and
must return the hook's reply text in payloads[0].
2. When the hook claims without a reply body, the synthesized payload
uses SILENT_REPLY_TOKEN.
3. Non-cron triggers do not invoke the hook (no behavior change for
normal user/heartbeat traffic).
4. Without a registered hook, falls through to the CLI subprocess.
Currently fails (RED): tests 1 and 2 fail because runCliAgent never
fires before_agent_reply — the hook gate exists only in the embedded PI
runner (src/agents/pi-embedded-runner/run.ts:326). This is the
CLI-backed-agent dreaming gap reported in #70940 and identified in
PR #70737 review.
Next commit: implement the hook gate in runPreparedCliAgent (GREEN).
* fix(cli-runner): GREEN — fire before_agent_reply for cron-triggered turns
Mirrors the embedded PI runner gate from
src/agents/pi-embedded-runner/run.ts:326 so plugin-managed cron jobs
(notably memory-core dreaming) can short-circuit a CLI-backed agent
turn before the codex/claude/gemini subprocess is spawned.
Without this, configuring a default agent's model to a CLI backend
(codex-cli, claude-cli, gemini-cli, or any third-party
`registerCliBackend` provider) silently broke dreaming: the cron
sentinel was sent to the underlying LLM as a literal user prompt and
the dreaming hook never executed. See openclaw/openclaw#70940 for the
empirical repro (codex-cli observed sending the dream-token to GPT-5.5
with no `memory-core: dreaming promotion complete` line).
Also extracts `buildHandledReplyPayloads` locally; eventually that
should be unified with the embedded PI runner's helper, but that's a
mechanical refactor for a follow-up.
Closes#70940 once both this PR and #70737 land — this fix is only
useful if cron-driven dreaming exists, which is what #70737 introduces.
TDD trail:
- prior commit: RED test asserting the hook gate (4 cases)
- this commit: implementation that turns those tests green (4/4 pass).
Verified: pnpm test src/agents/cli-runner.before-agent-reply-cron.test.ts
4/4 passed; pnpm test src/agents/cli-runner 21/21 passed; lint clean
on touched files; pre-existing tsgo failure in
src/plugin-sdk/provider-tools.ts is unrelated to these changes.
* Revert "fix(memory/dreaming): surface blocked status when heartbeat is disabled for main (#69875)"
This reverts commit 529577e045.
Making way for the dreaming-vs-heartbeat decoupling from Josh's
josh/dreaming-isolated-cron-fix branch, which moves the managed dreaming
cron to isolated agent turns (sessionTarget: "isolated") so dreaming no
longer requires heartbeat to fire. Once the cron no longer rides the
heartbeat path, the blocked-reason observability has nothing left to
report — removing it cleanly here before the cherry-picks land.
* openclaw-3ba.1: move managed dreaming cron to isolated agent turns
* openclaw-46d: claim cron runs before embedded attempts
* openclaw-575: disable managed dreaming cron delivery
* openclaw-575: accept wrapped dreaming cron tokens
* openclaw-ccd: filter cron and wrapper transcript noise from dreaming corpus
* openclaw-cd9: filter archived, cron, and heartbeat transcript noise from dreaming corpus
* openclaw-cd9: suppress role-label reflection tags in rem dreaming
* openclaw-b49: stop narrative timeouts from blocking dreaming cron
* openclaw-b49: keep managed dreaming cron out of diary subagents
* openclaw-ff9: restore cron dream diary generation without serial waits
* openclaw-ff9: run dreaming narratives with lightweight isolated subagent lanes
* openclaw-ff9: detach cron dream diary generation from run completion
* openclaw-ff9: defer cron diary task startup until after cron completion
* doctor/cron: migrate stale managed dreaming jobs to isolated agent turns
After the dreaming cron moved off the heartbeat path to sessionTarget:
"isolated" + payload.kind: "agentTurn" (see the preceding memory-core
changes), users with existing ~/.openclaw/cron/jobs.json entries in the
old sessionTarget: "main" + payload.kind: "systemEvent" shape still
carry stale jobs until the gateway restart reconcile rewrites them.
Add a dreaming-specific cron migration to the existing
maybeRepairLegacyCronStore doctor path so "openclaw doctor" (and
"openclaw doctor --fix") rewrites those jobs without needing a gateway
restart. Match lives in a new doctor-cron-dreaming-payload-migration
helper alongside the existing legacy-delivery and store-migration files.
The matching uses the memory-core managed-job name and description tag
plus the short-term-promotion payload token. Constants are mirrored
from extensions/memory-core/src/dreaming.ts and commented so a future
rename in memory-core is a visible drift point here too.
* memory/dreaming: tighten cron-token match to known wrapper, not substring
The previous match relaxed the line check from 'trimmed line equals token'
to 'line contains token anywhere as a substring' to accept the
`[cron:<id>] <token>` wrapper that isolated-cron turns add. Substring
matching also let any user message embedding the token mid-sentence
trigger the dream-promotion hook, and was flagged by both Greptile and
Aisle on PR #70737.
Replace it with strip-the-known-prefix-then-exact-match: keep the
`[cron:<id>]` wrapper case working, reject every other variant. Add
focused unit coverage that the bare token, the wrapped token, and bare
multiline cases match while embedded / code-fenced / arbitrarily-wrapped
variants do not.
* memory/dreaming: drop assistant followup only on assistant-side signals
Per PR #70737 review (aisle-research-bot, Medium): the previous logic
suppressed the next assistant message whenever the prior user message
matched a 'generated prompt' pattern (`[cron:...]`,
`System (untrusted): ...`, heartbeat prompts, exec-completion events).
Real users can type those same patterns, which let a user exfiltrate
real assistant replies from the dreaming corpus by prefixing their own
prompt — the assistant's reply would be silently dropped.
Remove the cross-message coupling. Assistant-side machinery (silent
replies, system wrappers) is already dropped by sanitizeSessionText,
which is the right layer for that filter. Add an explicit assistant-side
HEARTBEAT_TOKEN check to keep the legitimate `HEARTBEAT_OK` ack drop
working without depending on the prior user message. Add a regression
test exercising the spoofing scenario.
* doctor/cron: assert mirrored dreaming constants stay in sync
Per PR #70737 review (greptile-apps): the doctor migration mirrors three
constants (MANAGED_DREAMING_CRON_NAME, MANAGED_DREAMING_CRON_TAG,
DREAMING_SYSTEM_EVENT_TEXT) from extensions/memory-core/src/dreaming.ts.
A future rename in either file would silently break the migration.
Add a vitest unit that reads both files and asserts the literals match.
Manually verified the assertion fires with a clear error when one side
diverges. Adds no runtime cost; sits in the regular test pipeline.
* fix(memory): stabilize dreaming CI checks
* memory/dreaming: skip eager narrative session cleanup when detached
Per PR #70737 review (chatgpt-codex-connector, P2): runDreamingSweepPhases
called deleteNarrativeSessionBestEffort synchronously right after each
phase. Once narrative generation moved to detached mode (queued via
queueMicrotask), the eager cleanup races the writer: the session is
deleted before the queued subagent run reads it, silently dropping cron
diary entries.
Skip the eager cleanup branch when params.detachNarratives is true.
generateAndAppendDreamNarrative still runs its own deleteSession in the
finally{} block, so the cleanup intent is preserved without the race.
Heartbeat-driven (non-detached) runs keep the original eager-cleanup
behavior.
* fix(plugin-sdk): restore heartbeat-summary re-export
Per PR #70737 review (chatgpt-codex-connector, P1): the revert of
PR #69875 dropped the `heartbeat-summary` re-export from
`openclaw/plugin-sdk/infra-runtime`. That subpath shipped publicly two
days earlier, so removing it is technically a breaking change to a
public SDK surface — third-party plugins importing
`isHeartbeatEnabledForAgent` / `resolveHeartbeatIntervalMs` from this
path would fail with no replacement contract introduced.
Restore the re-export. Costs nothing to keep; the helpers are already
public via `../infra/heartbeat-summary.ts`. SDK additions are by
default backwards-compatible (CLAUDE.md), so removing within days of
introduction violates that intent.
* changelog: note dreaming decoupling from heartbeat
Refs PR #70737.
---------
Co-authored-by: Josh Lehman <josh@martian.engineering>
Require the Codex app-server bridge to wait for the final two-phase approval decision, while preserving the explicit no-route sentinel behavior.
Local gate on rebased branch: pnpm check:changed (20 files, 157 tests).
Thanks @Lucenx9.
Co-authored-by: Lucenx9 <185146821+Lucenx9@users.noreply.github.com>
Harden Codex app-server approval preview text sanitization and truncation handling.
Thanks @Lucenx9.
Co-authored-by: Lucenx9 <185146821+Lucenx9@users.noreply.github.com>
Port the Codex app-server harness onto the context-engine lifecycle, add Codex context projection and compaction integration, and cover bootstrap/history/compaction fallback behavior.
Thanks @jalehman.
* fix(whatsapp): normalize outbound media payloads
* fix(embedded-runner): preserve final media directives
* fix(auto-reply): keep non-streaming media on final path
* fix(auto-reply): warn when reply media is dropped
* fix(whatsapp): align auto-reply media delivery
* docs(changelog): note whatsapp media normalization
* fix: propagate timeoutMs to guarded dispatchers
Thread timeoutMs through the dispatcher creation chain so that
per-request (guarded) dispatchers honor the configured LLM timeout
instead of falling back to undici's hardcoded 60s bodyTimeout/headersTimeout.
Changes:
- undici-runtime.ts: createHttp1Agent/ProxyAgent/EnvHttpProxyAgent now accept
timeoutMs and apply bodyTimeout/headersTimeout to dispatcher options
- ssrf.ts: createPinnedDispatcher accepts timeoutMs and passes it through
- fetch-guard.ts: fetchWithSsrFGuard reads timeout from params or falls back
to global dispatcher bodyTimeout via getGlobalDispatcher()
- provider-transport-fetch.ts: buildGuardedModelFetch accepts optional
timeoutMs and passes it to fetchWithSsrFGuard
The global dispatcher timeout (set by ensureGlobalUndiciStreamTimeouts)
is still applied to non-guarded requests. Guarded requests (used by LLM
transports) now also receive the timeout via a fallback to the global
dispatcher when not explicitly provided.
Fixes#70829
* fix: resolve fallback timeout via module-level bridge variable
Replace dead-code .options.bodyTimeout read in resolveDispatcherTimeoutMs
with a module-level bridge (_globalUndiciStreamTimeoutMs) set by
ensureGlobalUndiciStreamTimeouts. This avoids reliance on Undici's
non-public .options field and ensures guarded dispatchers inherit the
configured stream timeout instead of falling back to undici's 60s default.
Fixes Greptile P1 and Codex comments on PR #70831
* chore: re-run CI smoke tests
* test: cover guarded dispatcher timeout propagation
* test: align timeout bridge expectation
* docs: note guarded dispatcher timeout fix
---------
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Surface non-retryable assistant provider failures from the embedded runner instead of letting surface_error fall through to continue_normal.
- Preserve external abort and plain timeout fall-through paths.
- Preserve raw provider error diagnostics on surfaced FailoverError.
- Add regression coverage for billing/auth/rate-limit/null-reason/error fall-through cases.
- Update changelog.
Fixes#70124.
Thanks @truffle-dev.
When a packaged bundled plugin's `pluginRoot` is used directly as the npm
execution cwd, `npm install <specs>` resolves the plugin's own
`package.json` as the project manifest and fails with
`EUNSUPPORTEDPROTOCOL: Unsupported URL Type "workspace:": workspace:*`
whenever that manifest declares a `workspace:` runtime dep (e.g.
`"@openclaw/plugin-sdk": "workspace:*"`). This takes out every plugin
with any runtime deps at gateway startup.
`ensureBundledPluginRuntimeDeps` already filters `workspace:` specs from
the CLI arguments, but npm's own resolver reads the cwd manifest
regardless, so the filter alone is not enough. The existing isolated
execution-root + `replaceNodeModulesDir` machinery handles this exact
problem for source-checkout + cache-hit installs. This change activates
the same staging path for the packaged case: when `installRoot ===
pluginRoot` and we are not in the source-checkout cache path, stage the
install inside `<pluginRoot>/.openclaw-install-stage` (which has a
minimal generated `package.json`) and move the produced `node_modules/`
back to the plugin root as before.
- Add regression test `stages plugin-root install when the plugin's own
package.json declares workspace:* deps` covering the Docker scenario
(mixed `workspace:*` + concrete runtime dep, e.g. anthropic-style
`@openclaw/plugin-sdk` + `@anthropic-ai/sdk`).
- Update existing plugin-root-install expectations (`installs
plugin-local runtime deps when one is missing`, `skips workspace-only
runtime deps before npm install`, `installs deps that are only present
in the package root`, `does not trust runtime deps that only resolve
from the package root`, `does not treat sibling extension runtime deps
as satisfying a plugin`) to assert the new `installExecutionRoot`.
Reported in #70844; same root cause as #70701, #70756, #70773, #70818,
#70839 which see the downstream "Cannot find package 'openclaw' from
plugin-runtime-deps" symptom because their
`resolveBundledRuntimeDependencyInstallRoot` resolves to an external
stage dir (clean manifest) so the install succeeds but the resulting
node_modules tree cannot satisfy the filtered-out workspace packages at
ESM import time.
## AI assistance
This PR was AI-assisted with Claude Code.
Testing degree: fully tested for the touched `bundled-runtime-deps`
install staging surface.
- `pnpm exec vitest run --config test/vitest/vitest.plugins.config.ts src/plugins/bundled-runtime-deps.test.ts` (31/31)
- `pnpm exec vitest run --config test/vitest/vitest.plugins.config.ts src/plugins/` (43/43 across 8 files)
- `pnpm exec tsgo --noEmit -p tsconfig.core.json`, `pnpm exec tsgo --noEmit -p tsconfig.core.test.json` (clean)
- `pnpm exec oxlint src/plugins/bundled-runtime-deps.ts src/plugins/bundled-runtime-deps.test.ts` (0 warnings, 0 errors)
- `node scripts/check-src-extension-import-boundary.mjs --json` and `node scripts/check-sdk-package-extension-import-boundary.mjs --json` (both `[]`)
I understand the code path changed here: packaged bundled plugins now
stage their runtime-dep install one directory below `pluginRoot` so npm
never reads the plugin's `workspace:*`-containing manifest during
install; after install completes, the produced `node_modules/` is moved
back to `pluginRoot` via the existing `replaceNodeModulesDir` helper.
Signed-off-by: Simone Macario <simone@sharly.ai>
Fix standalone memory CLI resolution for the built-in local embedding provider by declaring the memory-core capability contract.\n\nFixes #70836.\nThanks @mattznojassist.
description: Use gitcrawl for OpenClaw issue and PR archive search, duplicate discovery, related-thread clustering, and local GitHub mirror freshness checks.
metadata:
openclaw:
requires:
bins:
- gitcrawl
---
# Gitcrawl
Use this skill before live GitHub search when triaging OpenClaw issues or PRs.
`gitcrawl` is the local candidate-discovery layer. It is fast, includes open and closed threads, and can surface duplicate attempts, related issues, and already-landed fixes. It is not the final source of truth for comments, labels, merges, closes, or current CI.
- Treat `gitcrawl` as stale if `doctor` shows no target thread, an old `last_sync_at`, missing embeddings for neighbor/search commands, or a clearly wrong open/closed state.
- If stale data blocks the decision, refresh the portable store first:
- Run expensive update commands such as `gitcrawl sync --include-comments` only when the user asked to update the local store or stale data is blocking the decision.
- The sync default is all GitHub thread states; pass `--state open`, `--state closed`, or `--state all` only when a task requires a narrower or explicit scope.
## Boundaries
- Use `gitcrawl` for candidates, clusters, and historical context.
- Use `gh`, `gh api`, and the current checkout for live state before commenting, labeling, closing, reopening, merging, or filing a PR review.
- Do not close or label based only on `gitcrawl` similarity. Require matching problem intent plus live verification.
- If `gitcrawl` is unavailable, say so and fall back to targeted `gh search` rather than blocking normal maintainer work.
short_description:"Search local OpenClaw issue and PR history before live GitHub triage"
default_prompt:"Use $gitcrawl to inspect OpenClaw issue and PR history, find related threads and duplicate candidates, then verify actionable decisions with live GitHub."
@@ -7,6 +7,23 @@ description: Review, triage, close, label, comment on, or land OpenClaw PRs/issu
Use this skill for maintainer-facing GitHub workflow, not for ordinary code changes.
## Start issue and PR triage with gitcrawl
- Use `$gitcrawl` first anytime you inspect OpenClaw issues or PRs.
- Check local `gitcrawl` data first for related threads, duplicate attempts, and already-landed fixes.
- Use `gitcrawl` for candidate discovery and clustering; use `gh`, `gh api`, and the current checkout to verify live state before commenting, labeling, closing, or landing.
- If `gitcrawl` is missing, stale, lacks the target thread, or has no embeddings for neighbor/search commands, fall back to the GitHub search workflow below.
- Do not run expensive/update commands such as `gitcrawl sync --include-comments`, future enrichment commands, or broad reclustering unless the user asked to update the local store or stale data is blocking the decision.
- If an issue or PR matches an auto-close reason, apply the label and let `.github/workflows/auto-response.yml` handle the comment/close/lock flow.
@@ -35,6 +52,21 @@ Use this skill for maintainer-facing GitHub workflow, not for ordinary code chan
- If the claim is unsubstantiated or likely wrong, request evidence or changes instead of merging.
- If the linked issue appears outdated or incorrect, correct triage first. Do not merge a speculative fix.
## Close low-signal manual PRs carefully
- Do not close for red CI alone. Require a clear low-signal category plus stale or failed validation.
- Good manual-close categories:
- blank or mostly untouched PR template with no concrete OpenClaw problem/fix
- random docs-only churn such as root README translations, generic wording tweaks, or community-plugin discoverability docs that should go through ClawHub
- test-only coverage without a linked bug, owner request, or behavior change
- refactor-only cleanup, variable renames, formatting, or generated/baseline churn without maintainer request
- third-party channel/provider/tool/skill/plugin work that belongs on ClawHub instead of core
- risky ops/infra drive-bys such as new external CI services, release workflows, host upgrade scripts, Docker base migrations, or apt retry/fix-missing tweaks without owner request and green validation
- dirty branches where a narrow stated change includes unrelated docs/generated/runtime/extension files
- repeated bot-review spam or copied bot output without author-owned fixes
- Keep or escalate plausible focused bug fixes, green PRs, active maintainer discussions, assigned work, recent author follow-up, and unique reproduction details.
- For third-party capabilities, prefer the `r: third-party-extension` auto-response label when it applies; it points contributors to publish on ClawHub.
## Handle GitHub text safely
- For issue comments and PR comments, use literal multiline strings or `-F - <<'EOF'` for real newlines. Never embed `\n`.
@@ -44,9 +76,9 @@ Use this skill for maintainer-facing GitHub workflow, not for ordinary code chan
## Search broadly before deciding
- Prefer targeted keyword search before proposing new work or closing something as duplicate.
- Use `--repo openclaw/openclaw` with `--match title,body` first.
- Add `--match comments` when triaging follow-up discussion.
- Prefer `gitcrawl` first. Then use targeted GitHub keyword search to verify gaps, live status, comments, and candidates not present in the local store.
- Use `--repo openclaw/openclaw` with `--match title,body` first when using `gh search`.
- Add `--match comments` when triaging follow-up discussion or closed-as-duplicate chains.
- Do not stop at the first 500 results when the task requires a full search.
- Keep commit messages concise and action-oriented.
- Group related changes; avoid bundling unrelated refactors.
- Use `.github/pull_request_template.md` for PR submissions and `.github/ISSUE_TEMPLATE/` for issues.
- Do not commit PR-only artifacts such as screenshots under `.github/pr-assets`; attach them to the PR/comment or use an external artifact store instead.
default_prompt:"Use $openclaw-pre-release-plugin-testing to plan or run pre-release OpenClaw plugin validation across package, lifecycle, doctor, gateway, SDK, and live-ish proof."
5. If the user wants to watch the live UI, find the current `openclaw-qa` listen port and report `http://127.0.0.1:<port>`.
6. If a scenario fails, fix the product or harness root cause, then rerun the full lane.
## OTEL smoke
For local QA-lab OpenTelemetry validation, use:
```bash
pnpm qa:otel:smoke
```
This starts a local OTLP/HTTP trace receiver, runs the `otel-trace-smoke`
scenario through qa-channel, decodes the emitted protobuf spans, and verifies
the exported trace names and privacy contract. It does not require Opik,
Langfuse, or external collector credentials.
## Matrix live profiles
`pnpm openclaw qa matrix` defaults to the full `all` profile. Use explicit
profiles for faster CI/release proof:
```bash
OPENCLAW_QA_MATRIX_NO_REPLY_WINDOW_MS=3000\
pnpm openclaw qa matrix --profile fast --fail-fast
```
-`fast`: release-critical transport contract, excluding generated image and
deep E2EE recovery inventory.
-`transport`, `media`, `e2ee-smoke`, `e2ee-deep`, `e2ee-cli`: sharded full
Matrix coverage.
-`QA-Lab - All Lanes` uses explicit `fast` Matrix on scheduled runs. Manual
dispatch keeps `matrix_profile=all` as the default and always shards that full
Matrix selection.
## QA credentials and 1Password
- Use `op` only inside `tmux` for QA secret lookup in this repo.
- Quick auth check inside tmux:
```bash
op account list
```
- Direct Telegram npm live test secrets currently live in 1Password item:
- vault: `OpenClaw`
- item: `Telegram E2E`
- That item is the first place to look for:
-`OPENCLAW_QA_TELEGRAM_DRIVER_BOT_TOKEN`
-`OPENCLAW_QA_TELEGRAM_SUT_BOT_TOKEN`
-`OPENCLAW_QA_PROVIDER_MODE`
-`OPENCLAW_NPM_TELEGRAM_PACKAGE_SPEC`
- Convex QA secrets currently live in 1Password items:
- vault: `OpenClaw`
- item: `OPENCLAW_QA_CONVEX_SITE_URL`
- item: `OPENCLAW_QA_CONVEX_SECRET_MAINTAINER`
- item: `OPENCLAW_QA_CONVEX_SECRET_CI`
- Additional related notes/login items seen during QA credential work:
- vault: `Private`
- items: `OPENCLAW QA`, `Convex`, `Telegram`
- If a required value is missing from those notes:
- do not guess
- ask the maintainer/operator for the current value or the current 1Password item name
- for Telegram direct runs, `OPENCLAW_QA_TELEGRAM_GROUP_ID` may be stored separately from `Telegram E2E`
- for Convex runs, the leased Telegram credential should provide the Telegram group id and bot tokens together; do not require a separate `OPENCLAW_QA_TELEGRAM_GROUP_ID`
- for Convex runs, prefer `OpenClaw/OPENCLAW_QA_CONVEX_SITE_URL`; if that is stale or unclear, ask for the active pool URL before running
- Prefer direct Telegram envs for the npm Telegram Docker lane when available:
- do not assume `OPENCLAW_QA_PROVIDER_MODE` is consumed by that wrapper
- if a 1Password note only gives `OPENCLAW_QA_PROVIDER_MODE`, map it explicitly to `OPENCLAW_NPM_TELEGRAM_PROVIDER_MODE` before running the Docker lane
- Verified live shape:
- Convex mode can pass the real Docker lane without direct Telegram env vars
- leased Telegram payload includes the group id coupled to the driver/SUT tokens
- a real run of `pnpm test:docker:npm-telegram-live` passed with:
short_description:"Benchmark and fix slow OpenClaw tests"
default_prompt:"Use $openclaw-test-performance to reassess the OpenClaw test benchmark, identify the next real hotspot, fix it without losing coverage, update the report, and commit scoped changes."
short_description:"Benchmark tests, plugin suites, CPU, RSS, and heap growth"
default_prompt:"Use $openclaw-test-performance to reassess OpenClaw test and plugin-suite performance, collect wall/import/CPU/RSS metrics, investigate memory growth when needed, fix the next real hotspot without losing coverage, update the report, and commit scoped changes."
description: Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.
---
# OpenClaw Testing
Use this skill when deciding what to test, debugging failures, rerunning CI,
or validating a change without wasting hours.
## Read First
-`docs/reference/test.md` for local test commands.
-`docs/ci.md` for CI scope, release checks, Docker chunks, and runner behavior.
- Scoped `AGENTS.md` files before editing code under a subtree.
## Default Rule
Prove the touched surface first. Do not reflexively run the whole suite.
1. Inspect the diff and classify the touched surface:
- source: `pnpm changed:lanes --json`, then `pnpm check:changed`
- tests only: `pnpm test:changed`
- one failing file: `pnpm test <path-or-filter> -- --reporter=verbose`
- workflow-only: `git diff --check`, workflow syntax/lint (`actionlint` when available)
- docs-only: `pnpm docs:list`, docs formatter/lint only if docs tooling changed or requested
2. Reproduce narrowly before fixing.
3. Fix root cause.
4. Rerun the same narrow proof.
5. Broaden only when the touched contract demands it.
## Guardrails
- Do not kill unrelated processes or tests. If something is running elsewhere, treat it as owned by the user or another agent.
- Do not run expensive local Docker, full release checks, full `pnpm test`, or full `pnpm check` unless the user asks or the change genuinely requires it.
- Prefer GitHub Actions for release/Docker proof when the workflow already has the prepared image and secrets.
- Use `scripts/committer "<msg>" <paths...>` when committing; stage only your files.
- If deps are missing, run `pnpm install`, retry once, then report the first actionable error.
## Local Test Shortcuts
```bash
pnpm changed:lanes --json
pnpm check:changed # changed typecheck/lint/guards; no Vitest
default_prompt:"Use $openclaw-testing to choose the cheapest safe test or CI verification path, inspect failures, and rerun only the relevant OpenClaw lane."
If `uvx --from pr-search-cli pr-search ...` fails because `uvx` or the `pr-search` launcher is not available, ask the user to make that command work before continuing.
If `prtags auth status` shows that the user is not logged in, ask the user to run:
```bash
@@ -90,19 +67,19 @@ Resume only after the missing tool or login state has been fixed.
## Read-Path Default
For read-only GitHub operations in this workflow, use `ghr` as the default CLI.
Treat it as a drop-in replacement for the `gh` read operations you would normally use for PRs, issues, comments, reviews, and duplicate-search evidence.
For candidate discovery in this workflow, use `gitcrawl` first.
Treat it as the local history and clustering layer for related issues, duplicate attempts, and closed threads.
Only fall back to `gh` when `ghr` is failing for a concrete reason, such as:
Use live `gh` or `gh api` for the target thread and for any candidate before making an actionable judgment.
Use live GitHub when `gitcrawl` is missing or stale for a concrete reason, such as:
- the mirrored object is not present yet
- the mirror data is clearly stale or incomplete for the decision you need to make
-the `ghr` command errors, times out, or does not expose the specific read you need
- the target or candidate is not present yet
- the local data is clearly stale or incomplete for the decision you need to make
-`gitcrawl` errors, times out, or lacks the needed neighbor/search data
When you fall back to `gh`, note that you did so and why.
When you fall back to live GitHub search, note that you did so and why.
If `ghr` is missing a fresh PR or issue but `gh` can read it, you may use `gh` for the read-side judgment.
If a later `prtags` target-level write fails because the same object is still missing from `ghreplica`, stop and report that the mirror has not caught up yet instead of forcing the write.
If a later `prtags` target-level write fails because its own mirror has not caught up, stop and report that the curation backend is missing the target object instead of forcing a fallback write.
## Goal
@@ -118,14 +95,12 @@ For each target PR or issue:
Use the tools with these boundaries:
-`ghreplica` is the raw evidence source
- use `ghr` first for normal GitHub read operations in this workflow
-use it for title/body/comment search, related PRs, overlapping files, overlapping ranges, and current PR or issue status
-resort to `gh` only when `ghr` cannot provide the needed read cleanly
-`pr-search-cli` is candidate generation and ranking
- use it to suggest likely duplicate PRs or issue-cluster context
- do not treat it as final truth
- do not create or expand a duplicate group only because `pr-search-cli` put multiple PRs in the same issue or duplicate cluster
-`gitcrawl` is candidate generation and historical context
- use it first for local title/body search, neighbors, clusters, and closed-thread discovery
-treat every candidate as a lead until live GitHub confirms it
-`gh` is live GitHub truth
-use it for target state, body, comments, reviews, files, linked issues, and current open/closed/merged status
- use `gh search` only when `gitcrawl` is stale, missing data, or cannot express the needed query
-`prtags` is the maintainer curation layer
- use it to create or reuse one duplicate group
- use it to save the duplicate status, confidence, rationale, and group summary
@@ -182,7 +157,7 @@ Examples:
## Evidence Checklist
Before declaring a duplicate, gather evidence from at least two categories.
Same-issue or same-cluster output from `pr-search-cli` counts only as candidate generation, not as one of the required proof categories by itself.
`gitcrawl` neighbors, search hits, and cluster membership count as candidate generation, not as enough proof by themselves.
For PRs:
@@ -205,21 +180,18 @@ If you only have wording similarity, that is not enough.
## Step 1: Read The Target
Start by reading the target itself.
Use `ghr` first for this step even if you would normally reach for `gh`.
Do not widen an existing group just because `pr-search-cli` placed several PRs under the same issue or duplicate cluster.
Do not widen an existing group just because `gitcrawl` placed several PRs or issues near each other.
Confirm that the actual implementation path and maintainer intent still match before adding the new member.
Create a new group only when no existing group clearly fits.
@@ -423,8 +377,8 @@ prtags annotation group set <group-id> \
When the evidence is incomplete, set `duplicate_status=candidate` and lower the confidence.
If a per-PR or per-issue annotation write fails because `prtags` cannot resolve the target through `ghreplica`, do not force a fallback write path.
Keep the group state you were able to write, report that the mirror is still missing the target object, and defer the target-level annotation until `ghreplica` catches up.
If a per-PR or per-issue annotation write fails because `prtags` cannot resolve the target, do not force a fallback write path.
Keep the group state you were able to write, report that the curation backend is still missing the target object, and defer the target-level annotation until `prtags` catches up.
short_description:"Find duplicate PRs and issues, group them in prtags, and let prtags sync the GitHub comment"
default_prompt:"Use $tag-duplicate-prs-issues to decide whether an OpenClaw PR or issue is a duplicate, gather evidence with ghreplica and pr-search-cli, group related items in prtags, and save the duplicate judgment."
short_description:"Find duplicate PRs and issues with gitcrawl, group them in prtags, and let prtags sync the GitHub comment"
default_prompt:"Use $tag-duplicate-prs-issues to decide whether an OpenClaw PR or issue is a duplicate, gather candidates with gitcrawl, verify live state with GitHub, group related items in prtags, and save the duplicate judgment."
// Labels prefixed with "r:" are auto-response triggers.
const activePrLimit = 10;
const rules = [
{
label: "r: skill",
close: true,
message:
"Thanks for the contribution! New skills should be published to [Clawhub](https://clawhub.ai) for everyone to use. We’re keeping the core lean on skills, so I’m closing this out.",
},
{
label: "r: support",
close: true,
message:
"Please use [our support server](https://discord.gg/clawd) and ask in #help or #users-helping-users to resolve this, or follow the stuck FAQ at https://docs.openclaw.ai/help/faq#im-stuck-whats-the-fastest-way-to-get-unstuck.",
},
{
label: "r: no-ci-pr",
close: true,
message:
"Please don't make PRs for test failures on main.\n\n" +
"The team is aware of those and will handle them directly on the codebase, not only fixing the tests but also investigating what the root cause is. Having to sift through test-fix-PRs (including some that have been out of date for weeks...) on top of that doesn't help. There are already way too many PRs for humans to manage; please don't make the flood worse.\n\n" +
"Thank you.",
},
{
label: "r: too-many-prs",
close: true,
message:
`Closing this PR because the author has more than ${activePrLimit} active PRs in this repo. ` +
"Please reduce the active PR queue and reopen or resubmit once it is back under the limit. You can close your own PRs to get back under the limit.",
},
{
label: "r: testflight",
close: true,
commentTriggers: ["testflight"],
message: "Not available, build from source.",
},
{
label: "r: third-party-extension",
close: true,
message:
"Please make this as a third-party plugin that you maintain yourself in your own repo. Docs: https://docs.openclaw.ai/plugin. Feel free to open a PR after to add it to our community plugins page: https://docs.openclaw.ai/plugins/community",
},
{
label: "r: moltbook",
close: true,
lock: true,
lockReason: "off-topic",
commentTriggers: ["moltbook"],
message:
"OpenClaw is not affiliated with Moltbook, and issues related to Moltbook should not be submitted here.",
},
];
const maintainerTeam = "maintainer";
const pingWarningMessage =
"Please don’t spam-ping multiple maintainers at once. Be patient, or join our community Discord for help: https://discord.gg/clawd";
if (title.toLowerCase().includes("security") && !hasSecurityLabel) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
labels: ["security"],
});
labelSet.add("security");
}
if (title.toLowerCase().includes("testflight") && !hasTestflightLabel) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
labels: ["r: testflight"],
});
labelSet.add("r: testflight");
}
if (haystack.includes("moltbook") && !hasMoltbookLabel) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
labels: ["r: moltbook"],
});
labelSet.add("r: moltbook");
}
}
const invalidLabel = "invalid";
const spamLabel = "r: spam";
const dirtyLabel = "dirty";
const badBarnacleLabel = "bad-barnacle";
const noisyPrMessage =
"Closing this PR because it looks dirty (too many unrelated or unexpected changes). This usually happens when a branch picks up unrelated commits or a merge went sideways. Please recreate the PR from a clean branch.";
if (pullRequest) {
if (labelSet.has(badBarnacleLabel)) {
core.info(`Skipping PR auto-response checks for #${pullRequest.number} because ${badBarnacleLabel} is present.`);
return;
}
if (labelSet.has(dirtyLabel)) {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
body: noisyPrMessage,
});
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
state: "closed",
});
return;
}
const labelCount = labelSet.size;
if (labelCount > 20) {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
body: noisyPrMessage,
});
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
state: "closed",
});
return;
}
if (labelSet.has(spamLabel)) {
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
state: "closed",
});
await github.rest.issues.lock({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
lock_reason: "spam",
});
return;
}
if (labelSet.has(invalidLabel)) {
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: pullRequest.number,
state: "closed",
});
return;
}
}
if (issue && labelSet.has(spamLabel)) {
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
state: "closed",
state_reason: "not_planned",
});
await github.rest.issues.lock({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
lock_reason: "spam",
});
return;
}
if (issue && labelSet.has(invalidLabel)) {
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
state: "closed",
state_reason: "not_planned",
});
return;
}
if (pullRequest && labelSet.has(activePrLimitOverrideLabel)) {
--arg notes "Automatically requested by Full Release Validation ${GITHUB_RUN_ID_VALUE} after child workflows completed; the parent summary re-checks current child run conclusions." \
description:Existing release tag or current full 40-character workflow-branch commit SHA to validate (for example v2026.4.12 or 0123456789abcdef0123456789abcdef01234567)
description:Branch, tag, or full commit SHA to validate
required:true
type:string
expected_sha:
description:Optional full SHA that ref must resolve to
required:false
default:""
type:string
provider:
description:Provider lane for cross-OS onboarding and the end-to-end agent turn
required:false
@@ -25,27 +30,53 @@ on:
- fresh
- upgrade
- both
release_profile:
description:Release coverage profile for live/Docker/provider breadth
echo "- This run will execute cross-OS release validation, install smoke, QA Lab parity, Matrix, and Telegram lanes, and the non-Parallels Docker/live/openwebui coverage from the CI migration plan."
- Replies: repo-root file refs only, e.g.`extensions/telegram/src/index.ts:80`. No absolute paths, no `~/`.
-CODEOWNERS: maintenance/refactors/tests are ok. For larger behavior, product, security, or ownership-sensitive changes, get a listed owner request/review first.
-First pass: run docs list (`pnpm docs:list`; ignore if unavailable), then read only relevant docs/guides.
-Missing deps: run `pnpm install`, rerun once, then report first actionable error.
-Use "plugin/plugins" in docs/UI/changelog. `extensions/` remains internal workspace layout.
-Add channel/plugin/app/doc surface: update `.github/labeler.yml` and matching GitHub labels.
-New `AGENTS.md`: add sibling `CLAUDE.md` symlink to it.
- Replies: repo-root refs only:`extensions/telegram/src/index.ts:80`. No absolute paths, no `~/`.
-Run docs list first: `pnpm docs:list` if available; read relevant docs only.
-High-confidence answers only when fixing/triaging: verify source, tests, shipped/current behavior, and dependency contracts before deciding.
-Dependency-backed behavior: read upstream dependency docs/source/types first. Do not assume APIs, defaults, errors, timing, or runtime behavior.
-Live-verify when feasible. Check env/`~/.profile` for keys before assuming live tests are blocked; keep secret output redacted.
-Missing deps: `pnpm install`, retry once, then report first actionable error.
-CODEOWNERS: maint/refactor/tests ok. Larger behavior/product/security/ownership: owner ask/review.
- Wording: product/docs/UI/changelog say "plugin/plugins"; `extensions/` is internal.
- New channel/plugin/app/doc surface: update `.github/labeler.yml` + GH labels.
- New `AGENTS.md`: add sibling `CLAUDE.md` symlink.
- Core must stay extension-agnostic. No core special cases for bundled plugin/provider/channel ids when manifest/registry/capability contracts can express it.
- Extensions cross into core only via `openclaw/plugin-sdk/*`, manifest metadata, injected runtime helpers, and documented local barrels (`api.ts`, `runtime-api.ts`).
- Extension production code must not import core `src/**`, `src/plugin-sdk-internal/**`, another extension's`src/**`, or relative paths outside its package.
- Core code/tests must not deep-import plugin internals (`extensions/*/src/**`, `onboard.js`). Use plugin `api.ts` / public SDK facade / generic contract.
- Extension-owned behavior stays in the extension: legacy repair, detection, onboarding, auth/provider defaults, provider tools/settings.
-Legacy config repair: prefer doctor/fix paths over startup/load-time core migrations.
-If a core test asserts extension-specific behavior, move it to the owning extension or a generic contract test.
- Core stays extension-agnostic. No bundled ids in core when manifest/registry/capability contracts work.
- Extensions cross into core only via `openclaw/plugin-sdk/*`, manifest metadata, injected runtime helpers, documented barrels (`api.ts`, `runtime-api.ts`).
- Extension prod code: no core `src/**`, `src/plugin-sdk-internal/**`, other extension `src/**`, or relative outside package.
- Core/tests: no deep plugin internals (`extensions/*/src/**`, `onboard.js`). Use `api.ts`, SDK facade, generic contracts.
-Owner boundary: fix owner-specific behavior in the owner module. Shared/core gets generic seams only; no owner ids, dependency strings, defaults, migrations, or recovery policy. If a bug names an extension or its dependency, start in that extension and add a generic core seam only when multiple owners need it.
-Legacy config repair: doctor/fix paths, not startup/load-time core migrations.
- Core test asserting extension-specific behavior: move to owner extension or generic contract test.
- New seams: backwards-compatible, documented, versioned. Third-party plugins exist.
- Channels: `src/channels/**` is implementation. Plugin authors get SDK seams, not channel internals.
- Config contract: keep exported types, schema/help, generated metadata, baselines, docs aligned. Retired public keys stay retired; compatibility belongs in raw migration/doctor paths.
-Plugin architecture direction: manifest-first control plane; targeted runtime loaders; no hidden paths around declared contracts; broad mutable registries are transitional.
- Prompt-cache rule: deterministic ordering for maps/sets/registries/plugin lists/files/network results before model/tool payloads. Preserve old transcript bytes when possible.
- Channels: `src/channels/**` is implementation; plugin authors get SDK seams.
- Config contract: exported types, schema/help, metadata, baselines, docs aligned. Retired public keys stay retired; compat in raw migration/doctor.
-Direction: manifest-first control plane; targeted runtime loaders; no hidden contract bypasses; broad mutable registries transitional.
- Promptcache: deterministic ordering for maps/sets/registries/plugin lists/files/network results before model/tool payloads. Preserve old transcript bytes when possible.
## Commands
- Runtime: Node 22+. Keep Node and Bun paths working.
-Normal full prod sweep: `pnpm check` (prod typecheck/lint/guards, no tests)
-Full tests: `pnpm test`
-Changed tests only: `pnpm test:changed`
-Local serial loop: `pnpm test:serial`
-Extension tests: `pnpm test:extensions` or `pnpm test extensions` = all extension shards; `pnpm test extensions/<id>` = one extension lane. Heavy channels/OpenAI have dedicated shards.
-Shard timing artifact: `.artifacts/vitest-shard-timings.json`; auto-used for balanced shard ordering. Disable with `OPENCLAW_TEST_PROJECTS_TIMINGS=0`.
-Targeted tests: `pnpm test <path-or-filter> [vitest args...]`; do not call raw `vitest`.
-`pnpm lint:apps`: Swift/app surface, separate from TS lint
-`pnpm lint:all`: legacy comparison lane
- Local heavy-check behavior: `OPENCLAW_LOCAL_CHECK=1` default; `OPENCLAW_LOCAL_CHECK_MODE=throttled|full`; `OPENCLAW_LOCAL_CHECK=0` for CI/shared runs.
- Local validation is local-first. Do not default to Blacksmith/Testbox for routine OpenClaw iteration; it burns warm caches and startup time. Use repo `pnpm` lanes first, then reach for remote CI/Testbox only for parity-only failures, secrets/services, or when explicitly requested.
- Runtime: Node 22+. Keep Node + Bun paths working.
- Install: `pnpm install` (keep Bun lock/patches aligned if touched).
- Sparse worktrees: `pnpm check:changed`is sparse-safe and may skip sparse-missing typecheck projects; do not expand sparse checkout just to satisfy changed-gate tsgo. Direct `pnpm tsgo*` remains strict; use a fuller worktree when you need direct typecheck proof.
-Extension tests: `pnpm test:extensions`, `pnpm test extensions`, `pnpm test extensions/<id>`.
-Targeted tests: `pnpm test <path-or-filter> [vitest args...]`; never raw `vitest`.
-Vitest flags only; no Jest flags like `--runInBand`. For serial runs use `pnpm test:serial` or `OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test ...`.
-Typecheck: `tsgo` lanes only (`pnpm tsgo*`, `pnpm check:test-types`); do not add `tsc --noEmit`, `typecheck`, `check:types`.
-Formatting: use `oxfmt`, not Prettier. Prefer `pnpm format:check` / `pnpm format`; for targeted files use `pnpm exec oxfmt --check --threads=1 <files...>` or `pnpm exec oxfmt --write --threads=1 <files...>`.
-Linting: use repo wrappers (`pnpm lint:*`, `scripts/run-oxlint.mjs`); do not invoke generic JS formatters/lints unless a repo script uses them.
-Heavy checks: `OPENCLAW_LOCAL_CHECK=1`, mode `OPENCLAW_LOCAL_CHECK_MODE=throttled|full`; CI/shared use `OPENCLAW_LOCAL_CHECK=0`.
-Blacksmith/Testbox: on maintainer machines with Blacksmith access, broad/shared validation defaults to Testbox. This includes `pnpm check`, `pnpm check:changed`, `pnpm test`, `pnpm test:changed`, Docker/E2E/live/package/build gates, and any command likely to fan out across many Vitest projects. Do not start those broad gates locally unless the user explicitly asks for local proof or sets `OPENCLAW_LOCAL_CHECK_MODE=throttled|full`.
-Local validation: targeted edit loops only, such as `pnpm test <specific-file>`, targeted formatter checks, and small lint/type probes. If a local command expands beyond targeted proof, stop it and move the broad gate to Testbox.
-Testbox use: run from repo root, pre-warm early with `blacksmith testbox warmup ci-check-testbox.yml --ref main --idle-timeout 90`, reuse the returned `tbx_...` id for all `run`/`download` commands, and stop boxes you created before handoff. Timeout bins: `90` minutes default, `240` multi-hour, `720` all-day, `1440` overnight; anything above `1440` needs explicit approval and cleanup.
- Testbox full-suite profile: `blacksmith testbox run --id <ID> "env NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test"`. For installable package proof, prefer the GitHub `Package Acceptance` workflow over ad hoc Testbox commands.
## GitHub API
## GitHub / CI
-Issue/PR triage: list first, hydrate few. Use bounded fields + `--jq`, e.g. `gh issue list --state open --limit 80 --json number,title,labels,updatedAt,comments --jq '.[]|[.number,.updatedAt,.comments,.title]|@tsv'`; then `gh issue view <n> --json title,body,comments,labels,createdAt,updatedAt,url --jq '{title,labels,createdAt,updatedAt,url,body,comments:[.comments[]|{author:.author.login,createdAt,body}]}'` only for shortlisted items.
-After landing a PR: search for duplicate open issues/PRs that can be closed.
-Before closing an issue/PR: add a comment explaining why, usually duplicate/invalid, with the canonical issue/PR when relevant.
-PR links: `gh pr list --state open --search '<issue-or-terms>' --json number,title,updatedAt,headRefName --limit 20`; use `gh pr view <n> --json number,title,body,closingIssuesReferences,files,statusCheckRollup,reviewDecision` only after shortlist.
-CI polling: keep full `gh` capability, but request only needed fields. Known run status: `gh api repos/<owner>/<repo>/actions/runs/<id> --jq '{status,conclusion,head_sha,updated_at,name,path}'`.
-Non-blocking background workflows: `Auto response`, `Docs Sync Publish Repo`, `Docs Agent`, and `Test Performance Agent` are service/agent work. Do not wait on, rerun, or fix them during normal push/PR verification unless the user explicitly asks or the task is about those workflows. Report them as background if mentioned.
-`/landpr` CI wait scope: do not idle on pending `auto-response`/`Auto response` or `check-docs`. Treat docs as local proof unless `check-docs` already failed with a relevant, actionable error. If required product/code gates and touched-surface local gates are green, proceed without waiting for docs-only or auto-response automation.
-Waiting: poll lightly, usually 30-60s backoff. Fetch jobs/logs/artifacts only after completion/failure or when job detail is needed; avoid repeated workflow + run + jobs loops.
-Triage: list first, hydrate few. Use bounded `gh --json --jq`; avoid repeated full comment scans.
-Automatic PR/issue discovery: skip maintainer-owned items unless directly relevant. Do not comment, close, label, retitle, rebase, fix up, or land them without Peter asking.
-PR scan/triage: no unsolicited PR comments/reviews. Report in chat only unless explicitly asked, or a close/duplicate action needs a reason comment.
-GitHub search boolean text is fussy. If `OR` queries return empty, split exact terms and search title/body/comments separately before concluding no hits.
-PR shortlist: `gh pr list ...`; then `gh pr view <n> --json number,title,body,closingIssuesReferences,files,statusCheckRollup,reviewDecision`.
-After landing PR: search duplicate open issues/PRs. Before closing: comment why + canonical link.
-GH comments with markdown backticks, `$`, or shell snippets: avoid inline double-quoted `--body`; use single quotes or `--body-file`.
-PR execution artifacts/screenshots: attach them to the PR, comment, or an external artifact store. Do not add `.github/pr-assets` or other PR-only assets to the repo.
- PR review answer must explicitly cover: what bug/behavior we are trying to fix; PR/issue URL(s) and affected endpoint/surface; whether this is the best possible fix, with high-certainty evidence from code, tests, CI, and shipped/current behavior.
- CI polling: exact SHA, needed fields only. Example: `gh api repos/<owner>/<repo>/actions/runs/<id> --jq '{status,conclusion,head_sha,updated_at,name,path}'`.
- Post-land wait: minimal. Exact landed SHA only. If superseded on `main`, same-branch `cancel-in-progress` cancellations are expected; stop once local touched-surface proof exists. Never wait for newer unrelated `main` unless asked.
- explicit/surface only: `QA-Lab - All Lanes`, `Scheduled Live And E2E`, `Install Smoke`, `CodeQL`, `Sandbox Common Smoke`, `Parity gate`, `Blacksmith Testbox`, `Control UI Locale Refresh`.
-`/landpr`: do not idle on `auto-response` or `check-docs`. Treat docs as local proof unless `check-docs` already failed with actionable relevant error.
- Poll 30-60s. Fetch jobs/logs/artifacts only after failure/completion or concrete need.
## Gates
- Pre-commit hook: staged formatting only. It does not run lint, typecheck, or tests.
- extension tests => extension test typecheck/tests only
- public SDK/plugin contract => extension prod/test validation too
- unknown root/config => all lanes
-Local loop: run `pnpm check:changed` explicitly before handoff/push; use `pnpm test:changed` for tests only; use `pnpm check` for full prod TS/lint sweep without tests.
-Landing on`main`: verify touched surface near landing; default bar is `pnpm check` + `pnpm test` when feasible.
-Hard build gate: run/pass `pnpm build` before push if build output, packaging, lazy/module boundaries, or published surfaces can change.
-Do not land related failing format/lint/type/build/tests. If failures are unrelated on latest `origin/main`, say so and give scoped proof.
- Commit helper is formatting-only; validation gates are explicit commands, not commit side effects.
- CI architecture gate: `check-additional`; local equivalent `pnpm check:architecture`.
- Config docs drift: `pnpm config:docs:gen/check`
- Plugin SDK API drift: `pnpm plugin-sdk:api:gen/check`
- Generated docs baselines: tracked `docs/.generated/*.sha256`; full JSON ignored.
- public SDK/plugin contract: extension prod/test too
- unknown root/config: all lanes
-Before handoff/push for code/test/runtime/config changes: run `pnpm check:changed` in Testbox by default on maintainer machines. Tests-only: run `pnpm test:changed` in Testbox by default. Full prod sweep: run `pnpm check` in Testbox. Use local only for narrow targeted proof or when explicitly requested.
-If `pnpm test:changed` or`pnpm check:changed` selects broad/shared lanes, it belongs in Testbox; do not let it continue locally after it fans out.
-Docs/changelog-only and CI/workflow metadata-only changes are not changed-gate work by default. Use `git diff --check` plus the relevant formatter/docs/workflow sanity check; escalate to `pnpm check:changed` only when scripts, test config, generated docs/API, package metadata, or runtime/build behavior changed.
-Rebase sanity: after a green `pnpm check:changed`, a clean rebase onto current
`origin/main` does not require rerunning the full changed gate when the rebase
has no conflicts and the branch diff is materially unchanged. Do a quick
`git status`, `git diff --check`, and diff/stat sanity check; rerun targeted or
full checks only if conflict resolution, upstream overlap, generated drift,
dependency/config changes, or touched-file content changes make the prior
result stale.
- Landing on `main`: verify touched surface near landing. Default feasible bar: `pnpm check` + `pnpm test`.
- Hard build gate: `pnpm build` before push if build output, packaging, lazy/module boundaries, or published surfaces can change.
- Do not land related failing format/lint/type/build/tests. If unrelated on latest `origin/main`, say so with scoped proof.
- Dynamic import: do not mix static and dynamic import for same module in prod path. Use dedicated`*.runtime.ts` lazy boundary. After lazy-boundary edits, run`pnpm build` and check `[INEFFECTIVE_DYNAMIC_IMPORT]`.
- Runtime branching: discriminated unions/closed codes over freeform strings.
- Avoid semantic sentinels:`?? 0`, empty object/string, etc.
- Dynamic import: no static+dynamic import for same prod module. Use`*.runtime.ts` lazy boundary. After edits:`pnpm build`; check `[INEFFECTIVE_DYNAMIC_IMPORT]`.
-Prefer injected deps over module mocks; if mocking modules, mock narrow local `*.runtime.ts` seams, not broad barrels.
-Share fixtures/builders; do not recreate temp dirs, package manifests, or plugin workspaces in every case unless state isolation needs it.
- Delete duplicate assertions when another test owns the boundary; assert only the behavior that can regress here.
-Avoid broad `importOriginal()` / broad `openclaw/plugin-sdk/*` partial mocks in hot tests. Add narrow local `*.runtime.ts` seam and mock it.
-Use existing deps/callback/runtime injection seams before module mocks.
-Import-dominated test time is a boundary smell; shrink import surface before adding cases.
- Replacing slow integration coverage: extract production composition into a named helper and test that helper.
- Do not modify baseline/inventory/ignore/snapshot/expected-failure files to silence checks without explicit approval.
- Do not set test workers above 16. For memory pressure: `OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test`.
- Live: `OPENCLAW_LIVE_TEST=1 pnpm test:live`; full logs `OPENCLAW_LIVE_TEST_QUIET=0`.
- Full testing guide: `docs/help/testing.md`.
- Vitest. Colocated `*.test.ts`; e2e `*.e2e.test.ts`; example models `sonnet-4.6`, `gpt-5.4`.
-Avoid brittle tests that grep workflow/docs strings for operator policy. Prefer executable behavior, parsed config/schema checks, or live run proof; put release/CI policy reminders in AGENTS/docs instead.
-Prefer injection; if module mocking, mock narrow local `*.runtime.ts`, not broad barrels or `openclaw/plugin-sdk/*`.
-Share fixtures/builders; delete duplicate assertions; assert behavior that can regress here.
-Do not edit baseline/inventory/ignore/snapshot/expected-failure files to silence checks without explicit approval.
- Do not run multiple independent `pnpm test`/Vitest commands concurrently in the same worktree. They can race on `node_modules/.experimental-vitest-cache` and fail with `ENOTEMPTY`. Use one grouped `pnpm test ...` invocation, run targeted lanes sequentially, or set distinct `OPENCLAW_VITEST_FS_MODULE_CACHE_PATH` values when true parallel Vitest processes are needed.
-Test workers max 16. Memory pressure: `OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test`.
-Update docs when behavior/API changes. Use docs list/read_when hints.
-Docs links: see `docs/AGENTS.md`.
- Changelog: user-facing only. Pure test/internal changes usually no entry.
- Changelog placement: append to active version `### Changes`/`### Fixes`; at most one contributor mention, prefer `Thanks @user`.
-Docs change with behavior/API. Use docs list/read_when hints; docs links per `docs/AGENTS.md`.
-Changelog user-facing only; pure test/internal usually no entry.
- Changelog placement: active version `### Changes`/`### Fixes`; every added entry must include at least one `Thanks @author` attribution, using credited GitHub username(s). Never add `Thanks @codex`, `Thanks @openclaw`, or `Thanks @steipete`.
- Changelog bullets are always single-line. No wrapping/continuation across multiple lines. Long entries stay on one long line so dedupe, PR-ref, and credit-audit tooling work and so the visual style stays uniform.
## Git
-Use`scripts/committer "<msg>" <file...>`; stage only intended files. It formats staged files only; run validation separately.
- Commits: conventional-ish, concise/action-oriented. Group related changes.
- No manual stash/autostash unless explicitly requested. No branch/worktree changes unless requested.
-No merge commits on `main`; rebase on latest `origin/main` before push.
- User says "commit": commit your changes only. "commit all": commit everything in grouped chunks. "push": may `git pull --rebase` first.
- Do not delete/rename unexpected files; ask if it blocks. Otherwise ignore unrelated WIP.
- Mobile LAN pairing: plaintext `ws://` is loopback-only by default. Trusted private-network `ws://` needs `OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1`; Tailscale/public use `wss://` or a tunnel.
- SwiftUI: Observation (`@Observable`, `@Bindable`) over new `ObservableObject`.
-Mac gateway: use app or `openclaw gateway restart/status --deep`; no ad-hoc tmux gateway. Logs: `./scripts/clawlog.sh`.
-Version bump touches: `package.json`, `apps/android/app/build.gradle.kts`, `apps/ios/version.json` + `pnpm ios:version:sync`, macOS `Info.plist`, `docs/install/updating.md`. Appcast only for Sparkle release.
-Mobile LAN pairing: plaintext `ws://` loopback-only. Private-network `ws://` needs `OPENCLAW_ALLOW_INSECURE_PRIVATE_WS=1`; Tailscale/public use `wss://` or tunnel.
- Provider-facing tool schemas: prefer flat string enum helpers over `Type.Union([Type.Literal(...)])`; some providers reject generated `anyOf`. Do not treat this as a repo-wide protocol/schema ban.
- External messaging surfaces: no token-delta channel messages. Follow `docs/concepts/streaming.md`; preview/block streaming uses message edits/chunks and must preserve final/fallback delivery.
- Provider tool schemas: prefer flat string enum helpers over `Type.Union([Type.Literal(...)])`; some providers reject `anyOf`. Not a repo-wide protocol/schema ban.
- External messaging: no token-delta channel messages. Follow `docs/concepts/streaming.md`; preview/block streaming uses edits/chunks and preserves final/fallback delivery.
openclaw message send --to +1234567890 --message "Hello from OpenClaw"
openclaw message send --target +1234567890 --message "Hello from OpenClaw"
# Talk to the assistant (optionally deliver back to any connected channel: WhatsApp/Telegram/Slack/Discord/Google Chat/Signal/iMessage/BlueBubbles/IRC/Microsoft Teams/Matrix/Feishu/LINE/Mattermost/Nextcloud Talk/Nostr/Synology Chat/Tlon/Twitch/Zalo/Zalo Personal/WeChat/QQ/WebChat)
openclaw agent --message "Ship checklist" --thinking high
@@ -53,12 +53,24 @@ We prioritize secure defaults, but also expose clear knobs for trusted high-powe
OpenClaw has an extensive plugin API.
Core stays lean; optional capability should usually ship as plugins.
We are generally slimming down core while expanding what plugins can do.
If a useful feature cannot be built as a plugin yet, we welcome PRs and design discussions that extend the plugin API instead of adding one-off core behavior.
There are two broad plugin styles:
- Code plugins run OpenClaw plugin code and are appropriate for deeper runtime extension.
- Bundle-style plugins package stable external surfaces such as skills, MCP servers, and related configuration.
Prefer bundle-style plugins when they can express the capability.
They have a smaller, more stable interface and better security boundaries.
Use code plugins when the capability needs runtime hooks, providers, channels, tools, or other in-process extension points.
Preferred plugin path is npm package distribution plus local extension loading for development.
If you build a plugin, host and maintain it in your own repository.
The bar for adding optional plugins to core is intentionally high.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
