Commit Graph

3 Commits

Author SHA1 Message Date
kami 4c40a183cf feat: event store, pattern inference, and routine proposals
- Add events table (migration #4): stores normalized (action, object, ts)
  triples extracted from facts, indexed for recurrence detection.
- Add proposed_routines table: stores inferred recurring patterns with
  proposed/accepted/dismissed status and optional linked reminder.
- Add pattern package: Extractor normalizes fact text into (action, object)
  pairs with TTS normalization; Detector groups events to find recurring
  patterns and proposes routines.
- Add internal/ttsnorm: text normalization pipeline for Russian/English
  (lowercase, punctuation strip, number normalization, stopword removal).
- Add chat seed file for LLM phraser.
2026-07-10 15:49:03 +04:00
kami bf4009ca4f voice/seeds: track seed files, add russian time parser, guard replySystem
five fixes spotted during routing investigation:

- gitignore: replace blanket models/ ignore with per-dir exceptions
  (/models/embedder/, /models/stt/, /models/tts/) so the seed text
  files under models/seeds/ are tracked in version control
- query.txt: fix merged line — 'сколько стоит свет в этом месяце' and
  'найди заметку про сервер' were fused with no separator
- reminder.txt: add 11 pure-verb reminder seeds without time expressions
  to shift centroid toward the reminding intent rather than time-lexicon
- StubDateTimeParser: add Russian 'через <N> <unit>'/'через час'/'через
  полчаса', 'сегодня'/'завтра'/'послезавтра' with optional clock, and
  'в <clock>' scan. Add Russian word numbers (один-десять) and unit
  inflections (час/часа/часов, минута/минуты/минут, день/дня/дней,
  неделя/недели/недель). Also adds missing English day/week units.
- replySystem: guard time branch against duration queries ('сколько
  времени прошло') reaching it via the classifier path after the
  stage-0 grammar's build filter rejects them. Mirrors stage0.go
  duration keywords.
2026-07-06 18:38:48 +04:00
kami ce3d8e65f2 voice/routing: fix time-query misroute (seed collision, threshold, stage-0 grammars)
three bugs causing time queries to land on reminder or fact intent:

- seed collision: query.txt and system.txt shared identical time/date
  seeds (который час, сколько времени), making system intent
  indistinguishable from query intent in centroid space
- threshold (0.35) too low for ONNX embedder — cosine similarities
  cluster 0.5-0.7 for related intents, so Clarify never fired
- reminder centroid contaminated by time-lexicon (every seed has a time
  expression), pulling any time-word utterance toward reminder intent

fixes:
- remove 3 duplicate time/date seeds from query.txt (keep in system.txt)
- DefaultRouterThreshold 0.35 -> 0.55
- stage-0 grammar for напомни/remind me -> IntentReminder, bypasses
  classifier (fixes 'напомни через час' being misrouted to fact)
- stage-0 grammars for time/date system queries (сколько времени,
  который час, какой сегодня день) -> IntentSystem, with Build filter
  to exclude elapsed/duration queries (сколько времени прошло)
- time parser fallback in applyAction for stage-0 reminder matches
  (extractor doesn't run on stage-0 decisions)
2026-07-06 18:23:13 +04:00