Commit History
-
[KM-644] planner: infeasible plan outcome + entity-ranking few-shots
Rifqi Hafizuddin +1: Claude Fable 5TaskList.infeasible_reason lets the planner decline questions no catalog column can answer (was force-mapping, e.g. pa AS revenue); coordinator short-circuits to a deterministic EN/ID data-gap reply and a non-substantive record. Few-shots add top-N entity ranking (G) and an infeasible example (H); planner.md gains hard rule 6 + 'When the catalog cannot answer'. Live-verified 2026-07-08 on the PA analysis. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>089b69d
-
/fix validator and report (#10)
- /fix report: remove record_id hash citations, EDA (for future tool) change to data source, transform to mdx-safe (b1b101730ccf5628e43e80f2ad654f78fbed5207) - [NOTICKET] fix(planner): repair near-miss catalog ids in QueryIR before validation (aacd4d13def258a9815761aecbd7b246a8dae9fc) - /fix report: group findings by analysis, dedup, code-span-safe MDX escaping (029b48894e9f79af6c0d81c00a2d811a982f87ae) - [NOTICKET] fix(tools): log swallowed analytics tool errors in AnalyticsToolInvoker (93d9381b2a5f5efe058c913fe0b793ce994a9097) - fix(planner): harden plan validation to reduce retry thrash on structured questions (1619dd3c0fa74825010c7af6d4b375e3b9404847) - [NOTICKET] fix(tools): coerce numeric-string columns before analyze_* compute (6bda333866a1a8ccf1b3fe6fcee7a8e1832f28d7) - fix(planner): correct top-N guidance — in-query ranking IS supported (99aa4141aed8241a625d290fb170f74192a6d831) - feat(guardrails): add input guard, out_of_scope intent, and refusal handling (0bbc27bc40ba20e7a8e…0e5fdb5
