Block a user
incident_correlator fast/thin path has the same dispatch/tactical name-guess as the #115 escape hatch, but it changes link decisions
correlator: drop the dispatch/tactical name-guess from the escape hatch (#115)
logan
deleted branch fix/115-drop-dispatch-tactical-split from logan/server-26
2026-09-13 14:07:37 -04:00
correlator: drop the dispatch/tactical name-guess from the escape hatch (#115)
logan
created branch fix/115-drop-dispatch-tactical-split in logan/server-26
2026-09-13 14:07:04 -04:00
correlator+summarizer: per-scene call-doc storage, fixes #96 and #114's real fix
corr_debug is overwritten per scene on the shared call doc, so #35's "LLM tier decides 3.5% of links" is a per-call blend and cannot answer whether the tier works
corr_debug is overwritten per scene on the shared call doc, so #35's "LLM tier decides 3.5% of links" is a per-call blend and cannot answer whether the tier works
Review found and fixed one blocker (commit 0fe6d3b):
Blocker — stale scenes entries survived re-extraction. PATCH /calls/{id}/transcript wipes tags/severity/location/units/`embe…
summarizer reads the whole-call transcript per incident — next leg of the #80/#95/#102 scene-context leak
Review found and fixed one blocker (commit 0fe6d3b):
Blocker — stale scenes entries survived re-extraction. PATCH /calls/{id}/transcript wipes tags/severity/location/units/`embe…
corr_debug is overwritten per scene on the shared call doc, so #35's "LLM tier decides 3.5% of links" is a per-call blend and cannot answer whether the tier works
Fixed in #132 (fix/96-114-per-scene-call-doc).
Added a per-scene scenes.<scene_index> map on the call doc (incident_correlator._apply_and_log, additive, doc_set(..., merge=True) —…
summarizer reads the whole-call transcript per incident — next leg of the #80/#95/#102 scene-context leak
Fixed in #132 (fix/96-114-per-scene-call-doc), option (a) from the issue's fix shape (the real fix, riding with #96 as predicted).
Each scene's own text is now persisted on the call doc under…