4 Commits

Author	SHA1	Message	Date
fawney19	cd06169b2f	fix: detect OpenAI format stream completion via finish_reason ... - Add detection of finish_reason in OpenAI API responses to mark stream completion - Ensures OpenAI API streams are properly marked as complete even without explicit completion events - Complements existing completion event detection for other API formats	2025-12-19 01:44:35 +08:00
fawney19	50ffd47546	fix: handle client disconnection after stream completion gracefully ... - Check has_completion flag before marking client disconnection as failure - Allow graceful termination if response already completed when client disconnects - Change logging level to info for post-completion disconnections - Prevent false error reporting when client closes connection after receiving full response	2025-12-19 01:36:20 +08:00
fawney19	ad1c8c394c	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	2025-12-16 02:39:03 +08:00
fawney19	53bf74429e	refactor: 重构流式处理模块，提取 StreamContext/Processor/Telemetry ... - 将 chat_handler_base.py 中的流式处理逻辑拆分为三个独立模块： - StreamContext: 类型安全的流式上下文数据类，替代原有的 ctx dict - StreamProcessor: SSE 解析、预读、嵌套错误检测 - StreamTelemetryRecorder: 统计记录（Usage/Audit/Candidate） - 将硬编码配置外置到 settings.py，支持环境变量覆盖： - HTTP 超时配置（connect/write/pool） - 流式处理配置（预读行数、统计延迟） - 并发控制配置（槽位 TTL、缓存预留比例）	2025-12-12 15:42:45 +08:00