28a4e9b1b8
fix: worker/processor.rs ASRX 使用正確的 start_frame
...
- 使用 segment.start_frame 取代 i (sequential index)
- data JSON 加入 start_frame, end_frame
2026-07-02 17:10:24 +08:00
3eabd45882
fix: ASRX duplication, TKG edges, trace ingest, and add pipeline progress publishing
...
- ASRX handler no longer stores duplicate 'asr' pre_chunks
- Pre_chunks storage made idempotent (delete-before-insert)
- Rule 1 + trace_ingest changed to query 'asrx' not 'asr'
- Trace chunks removed (dynamic from TKG/Qdrant)
- TKG scroll_face_points fixed: trace_id >= 1 (not == 1)
- TKG AsrxSegmentEntry: start/end -> start_time/end_time (match ASRX JSON)
- Unregister error handling: log instead of silent discard
- Add publish_pipeline_progress calls at each pipeline stage
(processors, rule1, face_trace, identity_agent, TKG, rule2, completion)
2026-07-02 10:43:46 +08:00
074cdcdbed
refactor: remove face embedding architecture - single Qdrant _faces collection
...
- Delete FaceEmbeddingDb module (face_embedding_db.rs)
- Stub match_faces_iterative, generate_seed_embeddings, tmdb_match_handler
- Remove sync_trace_embeddings, populate_face_embeddings_to_qdrant
- Remove embedding from face.json output (face_processor.py)
- Remove embedding from PG UPDATE (store_traced_faces.py)
- Remove workspace traces staging (checkin.rs, qdrant_workspace.rs)
- Fix tests: add pose_angle to Face, hand_nodes to TkgResult
Disabled functions (need reimplement with _faces):
- match_faces_iterative (identity agent)
- generate_seed_embeddings (TMDb seeds)
- tmdb_match_handler (TMDb matching)
- cluster_face_embeddings, search_similar_faces
- merge_traces_within_cuts
2026-06-24 22:27:09 +08:00
14e886cc08
feat: progressive multi-round face matching + pending person API
...
- Identity agent: per-face max matching, multi-round with derived
seeds from high-confidence faces, angle diversity filter (cosine sim < 0.90)
- Pending person API: POST /file/:file_uuid/pending-person
+ GET /file/:file_uuid/pending-persons with status=pending, source=manual
- Update API docs (07_identity.md)
2026-06-24 03:42:04 +08:00
766a1d9a6d
feat: Swift Face Pose integration + TKG 方案 B
...
Major Changes:
- swift_face_pose: output pose angles (yaw/pitch/roll) in face.json
- face_processor.py: call swift_face_pose (dual output: face.json + pose.json)
- Face struct: add pose_angle field
- TKG 方案 B: gaze/lip_track nodes from face.json (no face_detections dependency)
- Chunk cleanup: delete old data before rebuild (avoid duplicate key)
- Hand nodes: classify by hand_type + gesture (15 combinations)
- HAND_OBJECT edges: bbox spatial matching (174 matches)
Test Results:
- Blake Jones: 8 faces, pose_angle ✓, 66 nodes, 174 edges
- FilmRiot: 394 faces, pose_angle ✓, 35 nodes, 39 edges
- Left hands: 132, Right hands: 2
Architecture:
- All TKG nodes built from JSON files (face.json, hand.json, yolo.json)
- Swift processors: sample_interval=3 (Face/Pose/Hand sync)
- Cleanup functions: delete_tkg_nodes_by_uuid, delete_tkg_edges_by_uuid
2026-06-23 05:47:24 +08:00
2cfcfdd1af
feat: Phase 2.6 edges migration to Qdrant (TKG-only architecture)
...
Phase 2.6.1: co_occurrence_edges migration
- build_co_occurrence_edges_from_qdrant()
- Qdrant embeddings → frame grouping → YOLO objects
- Result: 6679 edges (vs 6701 PostgreSQL)
Phase 2.6.2: face_face_edges migration
- build_face_face_edges_from_qdrant()
- Qdrant embeddings → frame grouping → face pairs
- mutual_gaze detection preserved
- Result: 6 edges (exact match)
Phase 2.6.3: speaker_face_edges migration
- build_speaker_face_edges_from_qdrant()
- Qdrant embeddings → trace_id frame ranges
- SPEAKS_AS edge creation
Architecture:
- All edges use Qdrant payload (no face_detections queries)
- PostgreSQL fallback for empty Qdrant
- Estimated 3.6x performance improvement
Testing:
- Playground (3003): ✓ All Phase 2.6 logs verified
- Edge counts: ✓ Close match with PostgreSQL
- Fallback: ✓ Working
Docs:
- docs_v1.0/DESIGN/TKG_PHASE2_6_EDGES_MIGRATION.md
- docs_v1.0/M4_workspace/2026-06-21_phase2_6_test.md
2026-06-21 04:47:49 +08:00
17e4e15860
feat: add Vision LLM integration (CLIP + Qwen3-VL cascade)
...
- Add Qwen3-VL dynamic management (start/stop/status CLI)
- Add CLIP + Qwen3-VL cascade detection strategy
- Add Vision CLI commands (vision start/stop/status, detect)
- Add cascade_vision processor module
- Add clip processor module
- Add qwen_vl_manager module
Changes:
- scripts/start_qwen3vl.sh, stop_qwen3vl.sh: Qwen3-VL management scripts
- src/core/vision/: Qwen3-VL manager module
- src/core/processor/cascade_vision.rs: CLIP + Qwen3-VL cascade logic
- src/core/processor/clip.rs: CLIP classification and detection
- src/api/clip_api.rs: CLIP API endpoints
- src/cli/vision.rs: Vision CLI implementation
- src/cli/args.rs: Add Vision and Detect commands
- src/main.rs: Integrate Vision CLI
- src/core/mod.rs: Add vision module
- src/core/processor/mod.rs: Add cascade_vision module
2026-06-13 16:25:52 +08:00
e1572907ae
feat: ASRX hybrid pipeline, identity history, worker fixes, checkpoint system
2026-06-02 07:13:23 +08:00
f8bcc0356c
feat: frame/time pipeline split + output validation
...
- Add PipelineType enum + pipeline() to ProcessorType
- Split ProcessorPool into frame_slots (max 2) and time_slots (max 1)
- Add can_start_for() for pipeline-aware scheduling
- Add validate_output_file() — checks JSON validity before marking complete
- Add 3 unit tests for validate_output_file()
- Create DESIGN/FRAME_TIME_PIPELINE_V1.0.md (492 lines)
2026-05-23 21:14:28 +08:00
bebaa743ed
feat: trace-level matching, health watcher/worker status, timezone config
2026-05-21 01:08:30 +08:00
67ca846ccd
feat: ASR output frame numbers + rename start/end to start_time/end_time
...
- Python: asr_processor.py detects FPS from CUT/ffprobe (no fallback), outputs start_frame/end_frame
- Rust: All AsrSegment structs use start_time/end_time with #[serde(alias)] for backward compat
- store_asr_chunks: prefers ASR output frames, falls back to time-based conversion
- Added backward compatibility test for old JSON format (start/end)
Breaking change: ffprobe/CUT FPS failure now aborts instead of using default 24fps
2026-05-19 13:22:38 +08:00
a880c80556
fix: face_detections INSERT in pipeline, add dependency graph doc
2026-05-17 22:16:20 +08:00
3164a65554
update: pipeline, search, clip, embedding fixes
2026-05-17 19:46:35 +08:00
301a95e2bc
refactor: remove all dev.* and public.* schema hardcodes from runtime code
...
14 files updated to use schema::table_name() instead of hardcoded schema
prefixes. Only src/bin/release.rs intentionally retains dev.* references.
2026-05-14 14:40:14 +08:00
cac60c6093
fix: M4 Phase 1 bugs - dev.chunks refs, search_path, uuid column
...
Bug fixes from M4 report:
- 4 remaining dev.chunks → dev.chunk in SQL queries
- search_path includes public for pgvector extension
- get_chunk_by_chunk_id_and_uuid: uuid → file_uuid
- New endpoint: GET /api/v1/file/:uuid/chunk/:chunk_id
2026-05-11 10:21:06 +08:00
39ba5ddf76
feat: Phase 1 handover - schema migration, correction mechanism, API fixes
...
Schema changes: dev.chunks->dev.chunk, remove old_chunk_id/chunk_index
Correction: asr-1.json format, generate/apply scripts
API: 37/37 endpoints fixed and tested
Docs: HANDOVER_V2.0.md for M4
2026-05-11 07:03:22 +08:00
7237a1811e
feat: verification agent for processor output validation
...
- New src/verification/ module: verify_output() checks JSON structure/completeness per processor type
- Worker: after processor succeeds, verification agent gates the result
- Passed -> mark completed + cleanup_temp_files (remove .tmp/.partial/.err/timestamp backups)
- Failed -> mark failed with verification details, preserve files for inspection
- cleanup_temp_files() keeps only the canonical {uuid}.{proc}.json
2026-05-09 13:30:00 +08:00
573714788f
Release v1.0.0 candidate
2026-05-08 00:48:15 +08:00
74b6182eba
feat: media API (video/bbox/thumbnail), UUID unification, dot matrix text, portal fixes, API dictionary V1.3
2026-05-06 13:34:49 +08:00
e75c4d6f07
cleanup: remove dead code and duplicate docs
...
- Remove session-ses_2f27.md (161KB raw session log)
- Remove 49 ROOT_* duplicate files across REFERENCE/
- Remove 14 duplicate files between REFERENCE/ root and history/
- Remove asr_legacy.rs (dead code, replaced by asr.rs)
- Remove src/core/worker/ (duplicate JobWorker)
- Remove src/core/layers/ (empty directory)
- Remove 4 .bak files in src/
- Remove 7 dead private methods in worker/processor.rs
- Remove backup directory from git tracking
2026-05-04 01:31:21 +08:00
2b23d1cfbd
feat: update core API, database layer, and worker modules
...
- Remove unused imports (n8n_search, universal_search, Client, Arc, etc.)
- Update API endpoints for identity, face recognition, search
- Fix postgres_db.rs search_videos parent_uuid column
- Add snapshot API and identity agent API
- Clean up backup files (.bak, .bak2)
2026-04-30 15:07:02 +08:00
59809dae1f
chore: backup before migration to new repo
2026-04-23 16:46:02 +08:00
2393d81a3f
feat: fix Chinese text search and duplicate chunk_id bug
...
- Add helper functions to extract text from nested content structure
- Update SearchResult to include uuid field
- Add PostgreSQL function get_chunk_by_chunk_id_and_uuid to handle duplicate chunk_ids
- Update Qdrant search functions to extract uuid from payload
- Change embedding model to nomic-embed-text-v2-moe:latest
- Update Qdrant collection name to momentry_rule1
- Fix MongoDB authentication and disable cache for development
- Improve error handling in processor.rs
- Update documentation with new embedding model
2026-03-29 04:44:28 +08:00
82955504f3
feat: 新增 Job Worker 系統與 API 文檔全面更新
2026-03-26 16:16:34 +08:00
12a7b59232
feat: add job worker and duplicate registration check
...
Job Worker System:
- Add polling-based job worker (max 2 concurrent processors)
- Create monitor_jobs records when videos are registered
- Link videos.job_id to monitor_jobs
- Fix type mismatches (i32 vs i64) for database IDs
Duplicate Registration:
- Check if video already exists before registering
- Return existing video info with already_exists: true
- Use canonical path for UUID computation
USER_DATA_ROOT Configuration:
- Add MOMENTRY_USER_DATA_ROOT environment variable
- UUID computed from relative path (username/filename)
- Ensures consistent UUIDs when data root changes
2026-03-25 14:53:41 +08:00
Accusys