Distinguish a requested Scribe run from confirmed active execution, preserving existing run behavior and the integrated enable/disable/remove controls.
Co-authored-by: vyctorbrzezowski <51521767+vyctorbrzezowski@users.noreply.github.com>
* fix(knowledge): upgrade scribe run messages and start each scribe run fresh
* fix(knowledge): consolidation scribe runs every step of its skill
* fix(knowledge): clearer scribe run-message updates, update refresh, and Granola pending rules
* fix(knowledge): settle scribe updates per agent, after the whole update, and stop with the page
* fix(knowledge): scribe updates keep saved options and other agents' scribes, and retry failed sends
* fix(knowledge): scribe updates keep trigger, delivery and failure alert, and retry after reopening
* fix(knowledge): offer Try again as a new request when a scribe update leaves its automation unchanged
* fix(knowledge): scribe updates keep explicit tool lists exact, and Replace retries repeat the same request
* fix(knowledge): keep a scribe update late when Try again fails to send
* feat(knowledge): route skills by task and keep subject pages current
Turn the consolidation and ingestion skills into short routers with a rules card and per-task references, add one page-layout reference per entity type, make leave-alone the default for current pages, retire dated sections into State without losing citations, and ask agents to keep page State current when remembered claims change it.
Reapplies the intent of the unpushed knowledge-page-curation commits on current main.
* fix(knowledge): address skill review findings
Use the lean record nextOffset, drop the unavailable updatedAt, check citing sentences before repointing retired claims, and report legacy dated sections beyond the ingestion allowance instead of failing the meeting gate.
* feat(knowledge): route skills by task and keep subject pages current
OpenClaw-Publication: 0358b549-b67e-459d-a2df-f1fd1a8e4d07
* fix(knowledge): fail page reviews that bury type sections in State
Layout fails when decisions, milestones or commitments sit in State or a supported leading section is missing; prose fails on repeated hedges or more than about three citations per sentence. State is the short current picture.
* Publish openclaw/mellow-barnacle
OpenClaw-Publication: 5572e2f3-2ecf-46a4-8967-bb0ba89f29bb
* test(knowledge): fold page-State prompt check into provider entry suite
* Publish openclaw/mellow-barnacle
OpenClaw-Publication: 33f7db40-cf86-41bf-a2ac-e2b208b1e77f
* test(knowledge): pass a join separator in the prompt check
* Publish openclaw/mellow-barnacle
OpenClaw-Publication: 3b881ff3-dff7-4063-9258-c6fe9e482c89
* test(knowledge): allocate test lines for the page-State prompt check
* Publish openclaw/mellow-barnacle
OpenClaw-Publication: c624bdb4-e1e6-4f28-93b4-52df28f311d9
* fix(knowledge): move page claims before retiring them and keep distinctly dated Timeline entries
* fix(knowledge): scroll tall dialogs on small screens
* fix(knowledge): pair scribes by session key and make Repair turn them back on
* test(knowledge): consolidate scribe pairing tests under the test-line ceiling
* feat(knowledge): readable scribe prompts the operator can edit
* fix(knowledge): drop unused scribe job field and point the dialog at its prompt
* fix(knowledge): keep underscores in scribe status sentences
* test(knowledge): consolidate scribe prompt assertions
* fix(knowledge): stop maintenance from queuing the agent review
* fix(knowledge): show the review scribe's schedule choice in its options
* test(knowledge): pause the pass without an unbound registry method
* fix(knowledge): default start-dialog options per scribe
* chore: drop a generated lint config committed by mistake
* fix(knowledge): doctor removes the retired maintenance.reviewJobId
* feat(knowledge): add Scribes tab to start and control scribes
* fix(knowledge): give each scribe start attempt its own idempotency key
* fix(knowledge): reuse a scribe conversation created by a failed start
* fix(knowledge): reuse a scribe conversation created by a failed start
* fix(knowledge): show skipped scribe runs that could not complete as failed
* fix(knowledge): name the session incarnation when restoring a scribe conversation
* fix(knowledge): show a scribe run's result line instead of its whole reply
* fix(knowledge): show a restarted scribe as Starting until it answers
* fix(knowledge): read weekly scribe schedules as a day and time
* feat(knowledge): force an ongoing scribe's first run from the page and retry once scribes with their setup
* test(knowledge): one setup key per start dialog, reused on retry
* fix(knowledge): read the scribe job that targets the scribe's own conversation
* fix(knowledge): title scribe conversations with a display name instead of a unique label
* fix(knowledge): reread the Scribes tab on every resync
* fix(knowledge): stay on the Scribes tab when a scribe's first write creates the store
* fix(knowledge): recover scribes whose setup never arrived or stopped, and retry a first run that did not start
* fix(knowledge): show a failed scribe result over a healthy job and retry a first run the scheduler did not admit
* fix(knowledge): report a Run now the scheduler did not admit