lintsinghua 147dfbaf5e feat(agent): enhance streaming with in-memory event manager and fallback polling ... - Implement dual-mode streaming: prioritize in-memory EventManager for running tasks with thinking_token support - Add fallback to database polling for completed tasks without thinking_token replay capability - Introduce SSE event formatter utility for consistent event serialization across streaming modes - Add 10ms micro-delay for thinking_token events to ensure proper TCP packet separation and frontend incremental rendering - Refactor stream_agent_with_thinking endpoint to support both runtime and historical event streaming - Update event filtering logic to handle both in-memory and database event sources - Improve logging with debug markers for thinking_token tracking and stream mode selection - Optimize polling intervals: 0.3s for running tasks, 2.0s for completed tasks - Reduce idle timeout from 10 minutes to 1 minute for completed task streams - Update frontend useAgentStream hook to handle unified event format from dual-mode streaming - Enhance AgentAudit UI to properly display streamed events from both sources		2025-12-12 10:39:32 +08:00
..
agent	feat(agent): enhance streaming with in-memory event manager and fallback polling	2025-12-12 10:39:32 +08:00
llm	feat: Introduce structured agent collaboration with `TaskHandoff` and `analysis_v2` agent, updating core agent logic, tools, and audit UI.	2025-12-11 23:29:04 +08:00
rag	feat(agent): implement Agent audit module with LangGraph integration	2025-12-11 19:09:10 +08:00
init_templates.py	feat(prompts-rules): add prompt templates and audit rules management	2025-12-09 21:42:00 +08:00
report_generator.py	fix: 修复时间显示问题，使用带时区的UTC时间	2025-12-09 17:47:34 +08:00
scanner.py	feat(prompts-scan): integrate prompt templates and audit rules into scan and analysis workflows	2025-12-09 23:03:08 +08:00
zip_storage.py	fix: 修复时间显示问题，使用带时区的UTC时间	2025-12-09 17:47:34 +08:00