Self-learning reviewer edits existing skills via targeted patches: it quotes the exact live text (or appends a section) and the service composes the full body inside the receipt-pinned read that hash-binds the proposal — untouched content survives by construction, and patches auto-apply through the scanner-gated pipeline. Full-body rewrites and oversized-skill edits stay pending for the operator. The review prompt shifts to active capture within the existing evidence gates, and shallow same-sender turns accumulate per session (provider-identity scoped, zero-iteration and duplicate-run contracts honored, aborted provenance carried, bounded state) so quick corrections get reviewed with their own transcripts. Replaces closed#119856.
Emit usage once at the shared plugin completion boundary and expose host-derived plugin identity only on OTel usage spans. Preserve aggregate metric labels and cover the redacted Gateway path end to end.
Refs #98968
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Co-authored-by: ZengWen-DT <ceng.wen@xydigit.com>
Deletes the deterministic regex capture path that templated raw chat text into skill proposals (junk like a proposal whose whole procedure was one slugified user message). All autonomous learning now flows through the isolated experience reviewer: it sees a bounded workspace skill list, prefers revising pending proposals or updating the governing skill over creating new ones, and treats durable user corrections as first-class evidence. Update proposals are reviewer-only (explicit opt-in) and never auto-apply, since the reviewer drafts them without the live skill body. Removes the producerless pending-suggestion session machinery. Regression test proves the junk path is gone; real-Telegram E2E verdict in the PR body.
Defer Telegram final-mode text until speech settles, then deliver one captioned voice note or a proven-safe text fallback.
Co-authored-by: Jerry-Xin <jerryxin0@gmail.com>
* fix(diagnostics-otel): harness.run root span adopts diagnostic trace context
Fall back to internalOrTrustedParentContext when there is no active
tracked parent, so the openclaw.harness.run root span (and its whole
OTel subtree) adopts the diagnostic traceId instead of minting a new
OTel root. This lets spans propagated via the diagnostic traceparent
(e.g. a2a-gateway a2a.call / downstream a2a.task) share one trace with
the run internals.
* fix(diagnostics-otel): propagate exported span context
Co-authored-by: HughTang <44694613+HughTang@users.noreply.github.com>
* fix(diagnostics): break propagation import cycle
* fix(diagnostics): preserve trace propagation contracts
---------
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
* docs(slack): drop retired socketMode transport tuning
channels.slack.socketMode is rejected by Slack config validation, pinned by
the 'rejects retired Socket Mode ping/pong transport tuning' schema test, and
the client pong timeout is now a hardcoded 15s constant. The page still told
operators to configure it.
* fix(slack): migrate retired socketMode with doctor instead of hand-editing
The retired object fails schema validation at root and account scope, so the
docs previously left manual removal as the only recovery. Slack already owns
legacyConfigRules and normalizeCompatibilityConfig, so the strip belongs there.
* test(slack): narrow the doctor contract config record for check-test-types
normalizeCompatibilityConfig returns a possibly-absent channel entry, so the
socketMode assertions need expectDefined before indexing.
* docs(slack): describe socketMode retirement by observed behavior
openclaw config validate reports a config carrying the retired object as valid,
so the earlier 'validation rejects it / fails to load' wording was wrong. The
observable facts are that it is not read and that doctor --fix removes it.
* revert(slack): drop the duplicate socketMode doctor migration
Core already strips channels.slack.socketMode at root and account scope in
legacy-config-migrations.runtime.retired.ts via visitChannelEntries, so the
plugin-side rule was duplicate policy. Keeps this PR to the docs correction.
* docs(slack): state what doctor actually cleans up for socketMode
Doctor flags retired layout knobs with a general notice, and --fix removes the
three named fields and drops the object only once empty, so an unknown key
inside it survives.
Keep shared endpoint routing signal-aware while preserving explicit signal-specific URLs exactly. Cover the resolver through mocked constructors and real OTLP/HTTP trace, metric, and log exporters.
Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
Prevent stale top-level buttons arguments from silently sending text-only Telegram messages. Point model guidance and docs to typed presentation actions, and reject retired input before delivery.
Separate durable ClickClack room identity from replaceable exact-session attachments. Session archive, reset, deletion, and recreation retain the existing room and history while rotating local routing authority and preserving fail-closed exact-incarnation grants.
Pin ambiguous room recovery to the originating account and credential, and retain prior attachments when persistence fails.
Closes#119300
Co-authored-by: Chisel <chisel@psiclawops.dev>
Run the built local TUI PTY lane after the other artifact checks so its real Gateway fixture has exclusive process and event-loop capacity.
Punchcard-Session: cobalt-brook-meadow-m9
Recover Telegram forum reaction topics from provider-observed message context before authorization, and drop unknown topics instead of routing them to General. Serialize each forum message with its reaction update to avoid cache races. Thanks @vovapetry.
Vincent Koc