|
compression: keep the last four turns verbatim, not eight
Four turns still carry the current task word for word; everything older is already summarised, so eight bought little and pushed the compression trigger later than it needed to be. The mid-turn window is unchanged: it counts messages, not turns, and max(12, keep_recent*2) still floors at 12. navi_code keeps its own override of 12 turns. Examples, docs and the two tests that assert the default follow. |
|---|
|
|
| .env.example |
|---|
| .env.navi_code.example |
|---|
| docs/api.md |
|---|
| docs/config.md |
|---|
| docs/sessions.md |
|---|
| navi/config.py |
|---|
| tests/unit/api/test_session_info.py |
|---|
| tests/unit/core/test_agent.py |
|---|