| feat: define schema-driven extraction prompts
| 11 天前 |
| feat: define schema-driven extraction prompts
| 11 天前 |
| refactor: cleanup unused exports and obsolete verification scripts
Remove unused validation re-exports from core/__init__.py,
unused EXTRACTION_TOOLS/TOOL_TO_CATEGORY from extraction/__init__.py,
unused collect_tool_stats from tool_collector.py,
and obsolete scripts/verify_agfs_*.py files.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
| 1 个月前 |
| feat: L0 structured summary generation + extraction prompt optimization
Add compact-style L0 session summaries with 6 dimensions (events, facts,
preferences, plans, emotions, key_details). Implement two-round retrieval:
structured nodes for retrievedEvidence + session_summary for sessionContext.
Strengthen extraction prompts for temporal precision and detail richness.
Benchmark: run69 = 90.1% (385 questions, 3 samples), +8.5% over run68.
Cat4 forgetting: 78.6% → 91.0%, Cat1 single: 84.4% → 93.2%,
Cat2 cross: 78.4% → 86.7%.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
| 18 天前 |
| feat: formalize schema-driven extraction
| 11 天前 |
| feat: attribute internal tool usage
| 11 天前 |
| feat: L0 structured summary generation + extraction prompt optimization
Add compact-style L0 session summaries with 6 dimensions (events, facts,
preferences, plans, emotions, key_details). Implement two-round retrieval:
structured nodes for retrievedEvidence + session_summary for sessionContext.
Strengthen extraction prompts for temporal precision and detail richness.
Benchmark: run69 = 90.1% (385 questions, 3 samples), +8.5% over run68.
Cat4 forgetting: 78.6% → 91.0%, Cat1 single: 84.4% → 93.2%,
Cat2 cross: 78.4% → 86.7%.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
| 18 天前 |
| feat: formalize schema-driven extraction
| 11 天前 |
| feat: unify session usage tracking
| 11 天前 |
| feat: formalize schema-driven extraction
| 11 天前 |
