Resolve upload.py (no-scene fallback uses the new _correlate with #298's
non_event_chatter reason) and chatter_classifier docstring (gate built, off by
default). Fold intelligence._llm_bool into incident_correlator.parse_llm_bool (#88).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
STT_PROVIDER=auto picks Groq whisper-large-v3-turbo only when GROQ_API_KEY is
set (else OpenAI, unchanged); compat covers any OpenAI-compatible server via
STT_BASE_URL/STT_API_KEY. A failed primary falls back to OpenAI STT_MODEL on
the same downloaded audio; the fallback reports to its own ai_health tier so
a dead primary stays red. The non-OpenAI provider gets a token-budgeted
glossary prompt (area places, local_knowledge, vocabulary; never ten-codes),
guarded by a narrow prompt-echo check. A per-30s-window zlib compression
check (Whisper's 2.4) adds a noise gate that survives correction being off
(#83, partial). Call docs record stt_provider/model/audio_seconds/confidence.
The sweep hold-back counts the fallback attempt. gate_chatter added to
chatter_classifier (used by transcription to skip correction when
CHATTER_GATE_ENABLED). GROQ_API_KEY templated with default ''.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The rules engine now commits every confident decision alone. _run_decision
marks a decision ambiguous (new_with_candidates, unfit_tg_candidate,
unverified_unit_link) and only then does upload._correlate make ONE
llm_correlator.decide call; a usable answer is committed, otherwise the rules
decision stands. Removed: _correlate_with_consensus, llm_correlator.tiebreak /
decisions_agree / tiebreak prompt, corr_smart_model, the correlation_smart
health tier, the LLM-orphan gate (_call_is_substanceless, effectively dead:
it could only fire on minor-severity untyped calls) and its sweep budget.
corr_consensus is now rules_only | llm | rules_fallback | rules_guard, with
corr_band naming why; admin debug and replay metrics read the new values.
Section fixes in the same pass:
- #115: no tiebreaker left to manufacture incidents; an LLM orphan of a
rules "new" is honoured only for untyped, substanceless, routine/minor calls.
- #86: divergence veto bar moved to config (embedding_divergence_threshold);
the band between it and the match bar is ambiguous, not a silent merge.
- #103: a unit link with no embedding is "unit_overlap_unverified" ->
ambiguous, instead of skipping the veto and linking as verified.
- #189: unit-only and LLM links refused once an incident is open 90 min;
unit links on incidents open >30 min are ambiguous; LLM links distance-
guarded (incident_max_spread_km) and only to shown candidates.
- #190: severity steps down on an explicit stand-down phrase; new
severity_peak keeps the monotonic max.
- #88: parse_llm_bool fails closed on "false"; scene closures honoured only
on confident links or the incident the scene opened.
- #27: sweep budget is the scan window (wall clock), not 3 attempts.
- LLM prompt: "Reserve new" bullet no longer contradicts the #189 EXCEPT.
- updated_at never moves backward on a back-dated link.
Unmeasured: no live AI or replay (credits unfunded); band frequency, F1 and
thresholds are unverified. Must be re-scored on both answer keys in Replay
before merge.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Three live measurement windows and two consensus-layer fixes (#125, #126)
converged on one decision (CORRELATION_REVIEW_0907b.md, _0912.md): stop
iterating the correlator's consensus layer, the actual lever is upstream —
a classifier in scene extraction that recognizes radio housekeeping (roll
call, bare 10-4/10-8/98 acknowledgements, unit check-ins) before it ever
becomes a scene for the correlator to judge.
Adds app/internal/chatter_classifier.py: a pure classify_chatter(transcript)
function recognizing two shapes drawn from hand-labeled examples in the
review docs, cross-referenced against the real dumps — not invented regexes.
Deliberately conservative: anything that doesn't cleanly reduce to a known
shape returns (False, None) and the existing pipeline runs unchanged.
SHADOW MODE ONLY. intelligence.extract_scenes computes the verdict next to
the existing _is_garbage_transcript / transcript_too_short gates and writes
chatter_classifier_verdict / chatter_classifier_reason onto the call doc,
but does not skip extraction. admin.py's correlation-debug _call_summary
surfaces both fields, same pattern as corr_gate_veto (#115/#126), so the
next live window can measure the real-world false-positive rate before
anything is wired to actually skip extraction. TODO(server-26#127) marks
the call site.
Backtest against all three existing dumps (1002 calls): 154 flagged, 0
false positives (no flagged call carries tags, coords, non-routine severity,
or matches any review-doc-named dangerous-to-drop transcript — the major
extinguishing-fire call, geocoded calls, pursuit updates, the Pelham Station
subject check, the property-retrieval call, all individually verified).
tests/test_chatter_classifier.py: real transcripts from the dumps/review
docs in both directions. Sandboxed pytest 332 -> 364, green.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tbknwttzou4s46PAykmtix
Logan CusanoandClaude Opus 5.5