turnstone/app/services
pyr0ball 25b7ae340b fix: invert suppress_threshold semantics to similarity_threshold in FalsePositiveSuppressor
Was suppressing when novelty_score < 0.85 (i.e. similarity > 0.15), which
would suppress nearly every hypothesis once embeddings are active.

Now suppresses when max_sim >= similarity_threshold (0.85), meaning only
hypotheses that are 85%+ similar to a resolved incident are suppressed.

Also renames suppress_threshold → similarity_threshold for clarity and
adds a borderline boundary test (0.85 suppressed, 0.84 not suppressed).

Closes: #29
2026-05-25 18:58:52 -07:00
..
diagnose fix: invert suppress_threshold semantics to similarity_threshold in FalsePositiveSuppressor 2026-05-25 18:58:52 -07:00
__init__.py feat: initial Turnstone POC — ingest, FTS search, MCP server 2026-05-08 12:12:34 -07:00
blocklist.py fix(blocklist): get_candidate for O(1) push/unblock, 400 on malformed device_names JSON 2026-05-15 21:19:02 -07:00
embeddings.py refactor: extract embeddings service layer — decouple context embedder from Ollama 2026-05-25 11:01:25 -07:00
incidents.py refactor: rename ingest → glean throughout codebase 2026-05-20 23:02:55 -07:00
llm.py feat: inject environment context into diagnose pipeline and LLM prompt 2026-05-13 16:29:26 -07:00
models.py refactor: rename ingest → glean throughout codebase 2026-05-20 23:02:55 -07:00
pihole.py feat(blocklist): 6 REST endpoints + Pi-hole settings fields 2026-05-15 21:15:09 -07:00
search.py refactor: rename ingest → glean throughout codebase 2026-05-20 23:02:55 -07:00