liyizhouAI 2fda12c8a4 fix: report generation uses separate LLM (SiliconFlow) to avoid GLM 429 ... Report generation now supports REPORT_LLM_* env vars to route report LLM calls through a separate provider (SiliconFlow Qwen-32B) instead of sharing the GLM rate limit with simulation. Also passes the report LLM client to ZepToolsService so tool calls (PanoramaSearch, QuickSearch, InsightForge, InterviewAgents) use the same provider.		2026-04-17 12:15:28 +08:00
..
api	fix: v0.3.4 - production stability fixes for simulation pipeline	2026-04-16 22:44:40 +08:00
models	feat: v0.3.2 - CustomGraphBuilder replaces Graphiti for step 2 graph build	2026-04-16 07:54:07 +08:00
services	fix: report generation uses separate LLM (SiliconFlow) to avoid GLM 429	2026-04-17 12:15:28 +08:00
utils	fix: report 429 retry + theme toggle on all pages	2026-04-17 08:36:58 +08:00
__init__.py	fix: v0.3.4 - production stability fixes for simulation pipeline	2026-04-16 22:44:40 +08:00
config.py	perf: 4x speedup for graph building	2026-04-14 14:09:41 +08:00