refactor(handler): optimize stream processing and telemetry pipeline

- Enhance stream context for better token and latency tracking
- Refactor stream processor for improved performance metrics
- Improve telemetry integration with first_byte_time_ms support
- Add comprehensive stream context unit tests
This commit is contained in:
fawney19
2025-12-16 02:39:03 +08:00
parent 9b496abb73
commit ad1c8c394c
8 changed files with 428 additions and 108 deletions

View File

@@ -100,6 +100,8 @@ class MessageTelemetry:
cache_read_tokens: int = 0,
is_stream: bool = False,
provider_request_headers: Optional[Dict[str, Any]] = None,
# 时间指标
first_byte_time_ms: Optional[int] = None, # 首字时间/TTFB
# Provider 侧追踪信息(用于记录真实成本)
provider_id: Optional[str] = None,
provider_endpoint_id: Optional[str] = None,
@@ -133,6 +135,7 @@ class MessageTelemetry:
api_format=api_format,
is_stream=is_stream,
response_time_ms=response_time_ms,
first_byte_time_ms=first_byte_time_ms, # 传递首字时间
status_code=status_code,
request_headers=request_headers,
request_body=request_body,