Add SURYA_STREAM_MODE streaming (off/on/abort) for chat completions

- _generate_one_stream: streams responses, optional live repeat-loop
  detection (abort) that closes the stream early and flags the partial
  result as repeat=True so the existing retry loop re-runs with higher
  temperature
- _should_retry honors result.repeat; stream_mode threaded through both
  first attempt and retry calls in chat_completions_batch
- GenerationResult.repeat field; SURYA_STREAM_MODE setting (default off)
- diagnostic retry logs (reason=repeat|error|detected, temp)
- docker-compose: SURYA_STREAM_MODE=off, 4090 GPU profile, logs volume
- logger.yaml: TimedRotatingFileHandler for error handler (fixes startup
  crash without maxBytes)

surya/inference/schema.py

@@ -29,6 +29,9 @@ class GenerationResult:
     raw: str
     token_count: int
     error: bool = False
+    # True when streaming mode aborted generation early due to a detected
+    # token repetition loop (see SURYA_STREAM_MODE=abort)
+    repeat: bool = False
     # Mean of exp(logprob) across response tokens, if logprobs requested
     mean_token_prob: Optional[float] = None
     # Per-token logprobs (raw OpenAI-style content list), if requested - phase 2 use