Transcription: config-driven OpenAI-compatible STT with OpenAI fallback (server-26#297, server-26#83)

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>

drb-c2-core/app/internal/recorrelation_sweep.py

@@ -65,7 +65,11 @@ def pipeline_worst_case_seconds(n_scenes: int = _BOUND_SCENES) -> float:
     _run_intelligence_pipeline."""
     openai_attempts = 1 + max(0, settings.openai_max_retries)
     stt_rounds = 2 if settings.stt_retry_on_degenerate else 1
-    stt = stt_rounds * openai_attempts * settings.stt_timeout_seconds
+    # A failed primary STT provider falls back to OpenAI (server-26#297), so
+    # the worst case is every configured target timing out in turn.
+    from app.internal.transcription import stt_targets
+    stt_providers = max(1, len(stt_targets()))
+    stt = stt_providers * stt_rounds * openai_attempts * settings.stt_timeout_seconds
     # Transcript correction (inside transcribe_call). gemini.generate_json only
     # re-issues a request when the model rejects a thinking level — a fast
     # 400, not a timeout — and google-genai itself does not retry.