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/routers/upload.py

@@ -586,7 +586,7 @@ async def _run_intelligence_pipeline(
         if _flag("stt_enabled"):
             transcript, segments = await transcription.transcribe_call(
                 call_id, gcs_uri, talkgroup_name,
-                system_id=system_id, talkgroup_id=talkgroup_id,
+                system_id=system_id, talkgroup_id=talkgroup_id, node_id=node_id,
             )
         else:
             scope = "globally" if not flags["stt_enabled"] else f"system {system_id}"