Zero temperature was too rigid, causing LLM to miss implied entities
and relations. 0.2 allows picking up contextual connections while
staying deterministic for structured JSON output.
Add 3 new entity types: technology, product, document — reducing
concept catch-all bucket. Add 4 new relation types: authored,
references, provides, requires. Improve prompt with disambiguation
guide between similar types, stricter related_to usage, and varied
confidence examples. Update graph view colors and mass for new types.
- Enable merge UI for linking channel contacts to tenant_users
- Contact → tenant_user resolution with cached lookup (60s TTL)
- MCP per-user credentials via user-keyed connection pool
- Secure CLI per-user credentials with AES-256-GCM encryption
- Unified UserPickerCombobox searching contacts + tenant_users
- Group contact collection with chat title in all channels
- Group permission inheritance via wildcard user_id="*"
- Fix heartbeat using wrong userID in group chats
- Filter internal senders from contact collection
- Add contact_type column (user/group) to channel_contacts
- SQLite schema v2 migration for desktop edition
- Replace ILIKE search with PostgreSQL tsvector/GIN full-text search
for KG entities (migration 000031)
- Add entity deduplication system with dual-threshold strategy:
auto-merge at 0.98+ similarity with Jaro-Winkler name match,
flag 0.90-0.98 as candidates for manual review
- Add ScanDuplicates for bulk on-demand duplicate detection
- Add MergeEntities with advisory lock and tenant-scoped relation
re-pointing (delete-then-update to avoid ON CONFLICT on UPDATE)
- Wire dedup inline after KG extraction pipeline
- Fix BackfillKGEmbeddings: was failing silently due to
context.Background() missing tenant_id; now runs cross-tenant
- Fix BackfillKGEmbeddings: break on error → continue with failed
ID tracking and max consecutive error cap
- Add EmbedEntity helper; UpsertEntity now generates embeddings
in background goroutine
- Add HTTP endpoints: POST /kg/dedup/scan, GET /kg/dedup,
POST /kg/merge, POST /kg/dedup/dismiss
- Add web UI: Dedup dialog with Scan All button, side-by-side
entity comparison, merge/dismiss actions
- Add Jaro-Winkler similarity algorithm with 34 unit tests
- Update IngestExtraction to return upserted entity IDs
- Bump RequiredSchemaVersion to 31
Two related fixes:
1. Memory interceptor now resolves workspace from request context
(per-user workspace) instead of using the static global workspace.
This fixes memory writes with absolute paths under per-user
workspaces (e.g. workspace/channel/userID/memory/) being bypassed
and written to disk instead of the database, which also prevented
KG extraction, memory indexing, and cross-session recall.
2. KG extractor: increase max_tokens 4096→8192, add retry on
truncation (finish_reason=length), and support chunking for
long inputs with deduplication on merge.
Add domain context, coreference rules, controlled relation types (15 predefined),
few-shot example, and dynamic entity count (3-15). Increase max input from 6000
to 12000 chars, reduce max output tokens from 8192 to 4096.
- Update go.mod and Dockerfile to Go 1.26
- Apply `go fix ./...` stdlib modernizations across 170+ files
- Add `go fix` to post-implementation checklist in CLAUDE.md
- Fix go fix misapplied rewrite in loop_history.go
viettranx