Extract shouldSkipEnrichment() replacing 4 scattered goclaw_gen_ checks.
Filter also skips UUID, hex hash, digit-only, short, and known junk filenames.
Fix cancelFuncs never being populated — Stop() was a no-op leaving UI stuck.
Backend:
- Add error tracking to EnrichProgress (error_count, last_error)
- Broadcast error events when LLM calls fail
- Add POST /v1/vault/enrichment/stop endpoint
- Wire enrichWorker to VaultHandler for stop functionality
Web UI:
- Add stop button (appears when enriching)
- Show error toast when enrichment errors occur
- Display error count in progress bar
- Add useStopEnrichment hook
i18n: en/vi/zh translations for new strings
- Increase classify max_tokens 1024→2048, summarize 1536→4096 to
prevent truncated JSON from models like gemini-2.5-pro
- Add debug logging: raw LLM output on parse failures, finish_reason
truncation warnings with model name
- Hot-swap vault enrichment provider/model on config change without
restart (wired into TopicSystemConfigChanged handler)
- Use RWMutex-guarded llm() accessor for thread-safe provider reads
9 fixes for vault enrichment pipeline:
1. Queue key = tenant-only (was per-agent, caused multiple batches
blocking EventBus workers and progress bar flashing)
2. Classify chunks 5 candidates per LLM call (prevents response
truncation that caused parse_still_failed errors)
3. Classify prompt improved: explicit "EXACTLY one entry per
candidate", 5-entry example, ctx capped at 30 words
4. max_tokens kept at 1024 (sufficient for 5 candidates)
5. Progress AddDone removes !running guard (safe before Start)
6. Rescan defers event publishing via PendingEvents — Start()
called before workers receive events, eliminating race
7. Upload handler same deferred publish pattern
8. Frontend enrichment timer cancels stale "complete" timeout
when new enrichment starts (prevents bar disappearing)
9. Sidebar tree reloads after rescan completes
Classify now searches across entire tenant (empty agentID) to
build cross-agent links for future vault sharing. Access control
enforced at query time — agents only see their own docs.
With 10 candidates, classify response can exceed 1024 tokens when
ctx descriptions are verbose, causing json unmarshal failures.
Bump to 2048 to accommodate worst-case 10-candidate responses.
- Convert importCron/importUserProfiles/importUserOverrides to multi-row
UPSERT with chunking (200→2 queries per import)
- Add GetTenantsByIDs batch method to TenantStore (PG+SQLite), refactor
handleMine() to single-query tenant fetch (N→1)
- Refactor buildAgentKeyMap() to use existing GetByKeys with tenant-scoped
context instead of per-key SELECT (N→1)
- Add GetDocumentsByIDs, GetDocumentByBasename, CreateLinks batch methods
to VaultStore (PG+SQLite)
- Batch-fetch docs in enrichment Phase 0, carry title through pipeline to
avoid per-doc refetch in classify phase
- Replace ListDocuments(limit=500) fallback in wikilink resolution with
targeted GetDocumentByBasename DB query
- Batch CreateLink calls in SyncDocLinks and classifyLinks
- Refactor usage handleGet/handleSummary to use ListPagedRich instead of
List+GetOrCreate N+1 loop (100→1 queries)
- Batch INSERT for team import members/comments/events/links (250→5)
- Add migration 47: UNIQUE constraint on cron_jobs(agent_id,tenant_id,name)
with dedup, SQLite schema v15
- Fix rescan storing stripped paths (teams/{uuid}/... → file.md) causing
enrichment worker to fail locating files on disk. Now stores full
workspace-relative path with backward-compat fallback for old records.
- Refactor enrichment into chunked pipeline: batch 5 files per LLM call
(was 1:1), 3 parallel goroutines via semaphore — reduces LLM calls ~80%.
- Extract shared chatWithRetry for summarize + classify (3 retries,
escalating timeouts 5m→7m→10m).
- Add POST /v1/vault/documents route for cross-agent doc creation
(agentID optional, defaults scope to shared when no agent).
- Add path traversal validation (reject .. and leading /) on create.
- Skip media files in syncWikilinks to prevent binary garbage parsing.
- Bound syncWikilinks file read to 4MB.
Goon