|
|
206cfbb498
|
fix(#7): redesign knowledge extraction prompt
- Tightened to ~700 tokens (target: ~1k)
- Added evidence field: every fact must cite transcript source
- Added meta block: session_outcome, tools_used, repos_touched
- Explicit handling of partial/failed sessions
- Front-loaded rules before transcript for mimo-v2-pro
Closes #7
|
2026-04-15 00:22:39 +00:00 |
|
|
|
8d716ff03f
|
Add comprehensive test script for harvest prompt validation
|
2026-04-14 19:02:41 +00:00 |
|
|
|
920510996e
|
Add test session 5: Session with questions
|
2026-04-14 19:01:03 +00:00 |
|
|
|
1fafeaf5a4
|
Add test session 4: Session with patterns
|
2026-04-14 19:01:00 +00:00 |
|
|
|
36b440f998
|
Add test session 3: Partial session with tool quirks
|
2026-04-14 19:00:58 +00:00 |
|
|
|
9f3caabf42
|
Add test session 2: Failed session with pitfalls
|
2026-04-14 19:00:56 +00:00 |
|
|
|
a21f3a44e1
|
Add test session 1: Successful session
|
2026-04-14 18:58:05 +00:00 |
|
|
|
102ef67a8e
|
Add test script for knowledge extraction prompt
|
2026-04-14 17:22:17 +00:00 |
|
|
|
d9f51b30a9
|
Add knowledge extraction prompt template for issue #7
|
2026-04-14 17:21:25 +00:00 |
|
Alexander Whitestone
|
b5873e9e3d
|
Initial structure: knowledge store, scripts, metrics, templates
|
2026-04-14 11:17:01 -04:00 |
|
|
|
8252ef5b80
|
Initial commit
|
2026-04-14 15:11:53 +00:00 |
|
