gitdataai/libs/agent/chat
ZhenYi 6edacbcdf2 fix(billing): track actual tokens in ReAct mode instead of hardcoded 0/0
- process_react now returns (String, i64, i64) tuple with token counts
- Extract token stats from rig Agent FinalResponse usage field
- Both streaming and non-streaming ReAct modes now bill correctly
2026-04-28 10:04:54 +08:00
..
context.rs refactor(agent): split into submodules and add Qdrant embedding 2026-04-25 20:09:33 +08:00
mod.rs refactor(agent): split into submodules and add Qdrant embedding 2026-04-25 20:09:33 +08:00
service.rs fix(billing): track actual tokens in ReAct mode instead of hardcoded 0/0 2026-04-28 10:04:54 +08:00