Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.
Refactor memory close provider draining so providers created during shutdown are closed through the same bounded retry path.
Co-authored-by: spacegeologist <zheng.zuo0@gmail.com>
Summary:
- The PR extracts the CJK-aware memory tokenizer into a shared helper, routes dreaming dedupe through it, preserves MMR re-exports, and adds regression coverage for CJK and empty-token cases.
- PR surface: Source +15, Tests +96. Total +111 across 5 files.
- Reproducibility: yes. Current main has an ASCII-only tokenizeSnippet path in dreaming dedupe, and the source ... ction source bytes for the CJK failure modes; I did not run tests locally because this review is read-only.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(memory-core): use Array.toSorted for #80613 lint fix
- PR branch already contained follow-up commit before automerge: fix(memory-core): preserve dedupe identity when both snippets tokeniz…
- PR branch already contained follow-up commit before automerge: fix(memory-core): rename __testing to testing in CJK regression tests…
- PR branch already contained follow-up commit before automerge: fix(memory-core): use CJK-aware tokenizer for dreaming dedupe (#80613)
Validation:
- ClawSweeper review passed for head ca9c02734c.
- Required merge gates passed before the squash merge.
Prepared head SHA: ca9c02734c
Review: https://github.com/openclaw/openclaw/pull/86645#issuecomment-4537414471
Co-authored-by: MoerAI <friendnt@g.skku.edu>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
* fix(memory): prevent silent vector index degradation when embedding provider temporarily unavailable
Two related bugs cause complete loss of semantic vector data:
1. Promise cache deadlock in ensureProviderInitialized():
When the embedding provider (e.g. local MLX server on port 8123) is
temporarily unreachable at Gateway startup, loadProviderResult() throws
and providerInitPromise becomes a permanently-cached Rejected Promise.
The block only clears it on success (providerInitialized=true),
so the stale rejection blocks all future init attempts until Gateway restart.
2. Silent fts-only overwrite in runSync():
With the provider stuck at null, shouldRunFullMemoryReindex() compares
the stored meta.model (e.g. 'jina-embeddings-v5-text-small') against the
runtime provider model, and since provider is null, falls through to the
'meta.model !== fts-only' check — returning true. This triggers a full
reindex where every file is written as fts-only, silently erasing all
existing 11k+ semantic vectors.
Fix 1: Clear providerInitPromise in the catch block so the next call can
retry initialization (self-healing when the provider comes back online).
Fix 2: Guard runSync() — if requestedProvider is set and not 'none', but
the runtime provider is null, throw an error instead of silently degrading
to fts-only. This protects existing vector data by failing loudly.
Tested on production: 11,715 chunks + 1024-dim vectors fully preserved
after Gateway restart with the fix applied. The guard correctly blocks
sync when MLX is offline and allows normal operation when it recovers.
* fix: use this.settings.provider instead of private requestedProvider
The guard clause in runSync() was referencing this.requestedProvider
which is a private property on the MemoryIndexManager subclass and not
accessible from MemoryManagerSyncOps. Use this.settings.provider
instead, which is the same value and is accessible via the protected
abstract settings property.
* fix(memory): narrow degradation guard to only protect existing semantic indexes
The previous guard was too broad — it blocked sync for ALL non-none
provider configurations when provider was null, including the default
'auto' path where users without embedding credentials legitimately
build FTS-only indexes.
Narrow the guard to only abort when:
1. provider is null (embedding unavailable)
2. existing index metadata has a semantic model (not 'fts-only')
3. settings.provider is configured and not 'none'
This preserves the legitimate FTS-only fallback for auto/no-provider
users while still protecting existing semantic vector indexes from
silent degradation.
Reported-by: ClawSweeper (PR #85704 review)
* test: cover memory semantic index outage guard
* fix: protect semantic memory index fallback paths
* test: update memory sync harnesses
---------
Co-authored-by: Bo Yan <yaaboo-gif@users.noreply.github.com>
Co-authored-by: Yan Bo <yanbo@Mac.lan>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Summary:
- The PR routes local GGUF memory embeddings through a bundled worker sidecar, adds structured degradation and fallback handling, updates memory tests/build output, and keeps the local config contract unchanged.
- PR surface: Source +831, Tests +503, Docs +1, Other +2. Total +1337 across 23 files.
- Reproducibility: Do we have a high-confidence way to reproduce the issue? Source and report evidence are str ... cludes native crash logs; the exact Metal teardown abort was not reproduced in this review or the PR proof.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(memory): keep local embedding config unchanged
- PR branch already contained follow-up commit before automerge: fix(memory): type local embedding degradation
- PR branch already contained follow-up commit before automerge: fix(memory): refresh keywords after embedding fallback
- PR branch already contained follow-up commit before automerge: fix(memory): keep worker errors internal
- PR branch already contained follow-up commit before automerge: test: satisfy memory provider lifecycle harnesses
- PR branch already contained follow-up commit before automerge: fix: harden local embedding worker fallback
Validation:
- ClawSweeper review passed for head 1d1fe41c4e.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1d1fe41c4e
Review: https://github.com/openclaw/openclaw/pull/85348#issuecomment-4518516047
Co-authored-by: Onur Solmaz <onur@Onurs-MacBook-Pro.local>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: osolmaz
Co-authored-by: osolmaz <2453968+osolmaz@users.noreply.github.com>
* fix(memory-core): filter REM dreaming candidates to light-staged entries
REM dreaming re-ingested the full short-term recall store independently,
ignoring which entries were staged by the light sleep phase. Because the
confidence formula heavily weights accumulated averageScore (45%) and
recallStrength (25%), old high-recall entries permanently dominated
freshly staged candidates. The intended light→REM→deep pipeline was
broken: light correctly staged current material, but REM selected a
different set entirely, so lightHits never paired with remHits for deep
ranking.
Fix: in runRemDreaming(), read the phase-signals store for keys with
lightHits > 0 and filter entries to that set before passing to
previewRemDreaming(). When no light-staged keys exist (light disabled
or first run), fall back to the full entry set for backward
compatibility.
Added readLightStagedKeys() to short-term-promotion.ts as a clean
export for reading the light-staged key set from the phase signal store.
Closes#86249
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
* fix(memory-core): keep REM staging pending
* fix(memory-core): mark REM-considered staged entries
---------
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
Co-authored-by: Peter Steinberger <steipete@gmail.com>
Summary:
- The branch adds a close lifecycle for local memory embedding providers, scoped memory search/index teardown for one agent, Active Memory timeout cleanup, focused tests, and a changelog entry.
- Reproducibility: yes. The linked issue gives a concrete OpenClaw 2026.5.18 Telegram Active Memory timeout pa ... current-main source inspection confirms there is no timeout cleanup for that local embedding provider path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(memory): close local embedding providers on timeout
Validation:
- ClawSweeper review passed for head 8e2e369b5c.
- Required merge gates passed before the squash merge.
Prepared head SHA: 8e2e369b5c
Review: https://github.com/openclaw/openclaw/pull/84048#issuecomment-4485705481
Co-authored-by: brokemac79 <martin_cleary@yahoo.co.uk>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Summary:
- The branch changes memory-core fallback vector search to scan chunks in 256-row rowid batches with `setImmediate` yields, updates regression tests, and adds a changelog entry.
- Reproducibility: yes. from source and supplied live output. Current main synchronously scans fallback vector ... and the PR body shows the before/after heartbeat behavior through the actual `searchVector` fallback path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test(memory-core): add boundary, parity, and concurrent-insert covera…
- PR branch already contained follow-up commit before automerge: fix(memory-core): yield event loop during fallback vector search (#81…
Validation:
- ClawSweeper review passed for head 0ede3d7168.
- Required merge gates passed before the squash merge.
Prepared head SHA: 0ede3d7168
Review: https://github.com/openclaw/openclaw/pull/83758#issuecomment-4482137790
Co-authored-by: NW <nitinwadhawan66@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Keep QMD-exported archived session transcript hits visible by resolving QMD `.md` archive stems back to their live session ids before applying session visibility policy. Preserve normal markdown session ids that only resemble archive names, reject ambiguous slug fallback matches, and keep deleted same-agent QMD archives readable when the live store entry is gone.
Fixes#83506.
Co-authored-by: tanshanshan <tanshanshan@users.noreply.github.com>
* fix(memory): catch up stale sessions on startup
Add a startup catch-up scan for memory session source files so clean gateway restarts compare on-disk transcripts against persisted index file state and mark only missing/newer/resized session files dirty for a normal incremental sync.
* fix(memory): catch up sessions for cli indexing
Ensure one-shot memory index managers also compare session transcripts against persisted source state before no-force CLI syncs, so openclaw memory index can recover stale session rows without requiring --force.
* chore: refresh CI after main repairs
Fix CLI web search/fetch command SecretRef resolution for provider-scoped plugin credentials.
- Carry command provider overrides through gateway and local secret resolution.
- Mark the selected web provider targets active and unrelated plugin refs inactive.
- Cover Tavily, DuckDuckGo, legacy Firecrawl fetch, protocol overrides, and runtime command-secret behavior.
- Add public plugin-sdk test mock exports needed by existing plugin tests after CI boundary enforcement.
Fixes#82621.
Replacement for #82699.
Co-authored-by: 吴杨帆 <39647285+leno23@users.noreply.github.com>
