`chunkDiscordText` reserved closing-fence space from the post-line fence state
(`nextOpenFence`), but a flush during a line's segment loop appends the closing
fence based on the still-open `openFence`, which is only advanced after the
line. On a line that closes a fence yet carries trailing text, `reserveChars`
was 0 while `flush()` still appended a `` ``` ``, producing a chunk of
`maxChars + 4` (e.g. 2004 > 2000) that Discord rejects with HTTP 400.
Reserve against `nextOpenFence ?? openFence` so whichever fence a flush can
close is accounted for, keeping a fence-closing line's chunk within `maxChars`.
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Change "optional capability" to "optional capabilities" to better match the plural "plugins" in the same sentence.
No functional changes. Documentation only.
Overview surfaces counted any job whose lastRunStatus was "error" as a
current failure, so an intentionally disabled job that previously failed
kept inflating the top-level "failed cron" badge and attention callout.
Add a shared isCronJobActiveFailure predicate that gates the error status
on enabled, matching the adjacent overdue filter, and use it in both the
overview card and the attention items list. Historical status stays
visible in detail views via resolveCronJobLastRunStatus.
* fix(memory-wiki): preserve human notes block on source re-ingest
Re-ingesting an existing source regenerated the page with an empty
wrote inside the human-managed markers. This broke the documented
contract that human note blocks are preserved, and diverged from the
synthesis and chatgpt-import writers that already preserve the block.
When a source page already exists, read it and re-inject its human Notes
block before writing. The block is located by scanning past the fenced
the content, then taking the first human start marker and the last end
marker, so the whole Notes block is preserved verbatim even when the
source content or the note text contains the markers or Markdown
headings. The same preservation is applied to writeImportedSourcePage so
the bridge and unsafe-local source-update writers keep notes too. New
page creation is unchanged.
Adds regressions for plain re-ingest, marker text in source content,
marker text inside the note, a heading inside the note, and an imported
source page update.
* fix(memory-wiki): preserve notes on CRLF source pages
Gate the QQ Bot symlink-media helper regression test on actual file-symlink capability, so environments that cannot create file symlinks skip that specific test while capable hosts still run it.
Validation:
- Windows Vitest proof in the PR body: `extensions/qqbot/src/engine/utils/file-utils.test.ts` passed with 4 tests passed and 1 symlink test skipped when file symlinks were unavailable.
- Current CI is clean at `cb7d5a162e24f7ec5be6985e97b2b74ae45b20f9`, including the refreshed Real behavior proof run `27992101343`.
Co-authored-by: Aniruddha Adak <aniruddhaadak80@users.noreply.github.com>
Co-authored-by: openclaw-clownfish[bot] <280122609+openclaw-clownfish[bot]@users.noreply.github.com>
* fix(memory-core): report active dreaming phases in status
* fix(memory-core): repair active dreaming status phases
---------
Co-authored-by: openclaw-clownfish[bot] <280122609+openclaw-clownfish[bot]@users.noreply.github.com>
Checkout the trusted workflow revision for the Real behavior proof gate so old PR events with stale base SHAs can still run the current checker scripts.
Proof:
- `tbx_01kvrrqq6tnwee3r41p22sy0qk`: touched-file format check passed.
- `tbx_01kvrrqq6tnwee3r41p22sy0qk`: `corepack pnpm test:serial test/scripts/ci-workflow-guards.test.ts` passed.
- `tbx_01kvrrqq6tnwee3r41p22sy0qk`: `corepack pnpm check:changed` passed for tooling.
- PR CI passed with no failing or pending checks.
