marcopanandClaude Opus 4.6 1e4bc11418 fix(embed): fast-fail + auto-restart Ollama on solved-search hang ...

Embeddings timeout was 120s, causing multi-minute hangs when Ollama was
down during F4/F6/F7 solved-search. Now: connect_timeout=5s across all
HTTP clients (REST + Ollama), read_timeout reduced to 30s for embeddings,
and OllamaEmbeddings auto-restarts the server on ConnectionError before
degrading gracefully.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-07-07 19:49:55 +02:00

..

__init__.py

refactor(harness): renaming prodotto tht (Onda -1)

2026-06-27 10:33:16 +02:00

embeddings.py

fix(embed): fast-fail + auto-restart Ollama on solved-search hang

2026-07-07 19:49:55 +02:00

reader.py

feat(vector): server-side kinds filter for search_similar (legacy fallback) + graceful solved-search degrade

2026-07-07 14:23:28 +02:00

records.py

refactor(harness): renaming prodotto tht (Onda -1)

2026-06-27 10:33:16 +02:00

rest_client.py

fix(embed): fast-fail + auto-restart Ollama on solved-search hang

2026-07-07 19:49:55 +02:00

rest_writer.py

feat(solved): solved_question vector kind + one-row upsert (D11 pattern)

2026-07-07 13:38:10 +02:00

store.py

refactor(harness): renaming prodotto tht (Onda -1)

2026-06-27 10:33:16 +02:00