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/backends/vllm.py

@@ -221,4 +221,5 @@ class VllmBackend(Backend):
                 ),
                 max_retries=settings.SURYA_INFERENCE_MAX_RETRIES,
                 request_logprobs_default=settings.SURYA_INFERENCE_LOGPROBS,
+                stream_mode=settings.SURYA_STREAM_MODE,
             )