e1108b6112
Adds corporate memory v1 (verification flywheel + contradiction detection + confidence scoring) and v1.5 (audience-based distribution + per-item privacy + admin curation). Server: GET /api/memory/bundle returns mandatory + ranked-approved items within a token budget; POST /api/memory/admin/mandate accepts an audience field gated against user_group_members; /api/memory/stats uses SQL aggregation. CLI: da sync writes received items to .claude/rules/km_*.md. Verification detector extracts knowledge candidates from session JSONL files. Auto-tagging via Haiku when ai: is configured. Adapted from the v9-era branch onto v13/v14 RBAC: _is_privileged_viewer + _effective_groups now query user_group_members JOIN user_groups; require_role(Role.KM_ADMIN) replaced with require_admin (km_admin collapsed into admin). Schema v15: knowledge_items context-engineering columns + knowledge_contradictions + session_extraction_state. Schema v16: verification_evidence. Cuts release v0.15.0 (also bundles #116 /me/debug page).
3 lines
379 B
JSON
3 lines
379 B
JSON
{"role": "assistant", "content": "I'll query the orders table to get the revenue data. The primary key appears to be order_id."}
|
|
{"role": "user", "content": "Yes, that's correct. order_id is the primary key and the revenue column is net_revenue_usd."}
|
|
{"role": "assistant", "content": "Got it. Let me query using net_revenue_usd from the orders table with order_id as the key."}
|