Alex 8a0f7024e3 fix(wiki): convert reassembles pages from existing chunks (crawler/remote) ...

convert_source_to_wiki now builds pages from the source's already-ingested vector-store chunks instead of re-parsing storage files, so it works for crawler/remote/connector sources (which have no stored files; file_path empty). Groups by metadata file_path/file_name (URL- and connector-aware; URLs normalized to virtual paths) rather than the raw source. Passes embeddings_key to create_vectorstore in BOTH convert and reembed_wiki_page (fixes a TypeError crash on faiss/elasticsearch). Conservative overlap-trim (min length). Deletes the original chunks after reassembling so retrieval has no duplicate/stale content.

2026-06-22 23:03:52 +01:00

..

__init__.py

Pg 4 (#2390)

2026-04-18 13:13:57 +01:00

conftest.py

Feat notification system (#2472)

2026-05-15 12:23:31 +01:00

test_agent_workers.py

feat: default tools (#2485)

2026-05-22 16:05:03 +01:00

test_attachment_worker.py

Pg 4 (#2390)

2026-04-18 13:13:57 +01:00

test_convert_source_to_wiki.py

fix(wiki): convert reassembles pages from existing chunks (crawler/remote)

2026-06-22 23:03:52 +01:00

test_ingest_checkpoint.py

feat: durability and idempotency keys (#2450)

2026-05-04 23:25:41 +01:00

test_ingest_connector.py

feat: durability and idempotency keys (#2450)

2026-05-04 23:25:41 +01:00

test_ingest_worker.py

feat: per-source RAG configuration (retrieval strategies, chunking, exposure, prescreen)

2026-06-20 21:54:23 +01:00

test_reembed_wiki_page.py

feat(wiki): reembed_wiki_page durable task

2026-06-22 17:49:04 +01:00

test_reingest_source_worker.py

feat: per-source RAG configuration (retrieval strategies, chunking, exposure, prescreen)

2026-06-20 21:54:23 +01:00

test_remote_worker.py

fix: broken syncs (#2480)

2026-05-17 23:58:28 +01:00

test_worker_sse_publishes.py

Feat notification system (#2472)

2026-05-15 12:23:31 +01:00