Explicit timeouts on every OpenAI and Gemini request (#153)

No AI client set a timeout: OpenAI's SDK waits 600s per attempt and retries
twice (timeouts included); google-genai waits forever. A hung provider call
had no upper bound, so recorrelation_sweep's 15-minute pipeline hold-back was
a guess against an unbounded tail.

- config: stt_timeout_seconds (120), openai_timeout_seconds (60),
  openai_max_retries (1), gemini_timeout_seconds (60).
- app/internal/ai_clients.py builds every OpenAI/AsyncOpenAI client with them
  (transcription, extraction, embeddings, summarizer, vocabulary learner,
  trip chat). gemini.py's shared client gets HttpOptions(timeout=ms).
- A timeout raises like any other provider error, so existing fallbacks are
  unchanged: rules-only correlation, rules decision on tiebreak, raw
  transcript on correction, ai_health "transient".
- MIN_MINUTES_SINCE_PIPELINE_START is now derived from those timeouts
  (pipeline_worst_case_seconds, 3-scene budget + 2 min non-AI slack), floor
  15: 21 min with the defaults. Loop warns if it reaches the scan window.
- tests/test_ai_timeouts.py: client limits, a real hung-socket request that
  gives up in <5s, timeout fallback per tier, the derived bound, and a guard
  against any new OpenAI( outside ai_clients.py.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

drb-c2-core/tests/test_recorrelation_sweep.py

@@ -66,11 +66,14 @@ async def test_sweep_pass_skips_a_call_whose_pipeline_just_started():
         "ended_at": _iso(now - timedelta(minutes=1)),
         "intelligence_started_at": _iso(now - timedelta(seconds=30)),
     }
+    # Relative to the hold-back, which is now derived from the AI timeouts
+    # (server-26#153) rather than a fixed 15 minutes.
+    past_hold = recorrelation_sweep.MIN_MINUTES_SINCE_PIPELINE_START + 4
     genuinely_orphaned_call = {
         "call_id": "call-genuine-orphan",
-        "started_at": _iso(now - timedelta(minutes=20)),
-        "ended_at": _iso(now - timedelta(minutes=19)),
-        "intelligence_started_at": _iso(now - timedelta(minutes=19)),
+        "started_at": _iso(now - timedelta(minutes=past_hold + 1)),
+        "ended_at": _iso(now - timedelta(minutes=past_hold)),
+        "intelligence_started_at": _iso(now - timedelta(minutes=past_hold)),
     }
 
     async def fake_collection_where(collection, clauses):