27 lines
1.3 KiB
Markdown
27 lines
1.3 KiB
Markdown
## Evidence runtime contributor
|
|
|
|
Evidence contributes to existing semantic stages; it is never a visible phase and does
|
|
not write decisions, canonical artifacts, or workflow state. Candidates are not truth:
|
|
show their provenance and let the reviewer decide. A formula is `kind=formula`, not a
|
|
separate store.
|
|
|
|
Use the phase-appropriate Evidence purpose, and make every mapped stage search
|
|
independently:
|
|
|
|
- `clarification` → `disambiguation`;
|
|
- `rewriting` → `rewriting`;
|
|
- `schema_linking` → `schema_linking`;
|
|
- `cte` and `final_sql` → `sql_generation`.
|
|
|
|
After consuming the F1 retrieval pack, and before making a proposal in every other
|
|
mapped stage, call `tht search evidence "<current stage context>"
|
|
--stage <semantic-stage> --session <id> --json` before making the stage proposal. Add
|
|
only the available approved context (`--concept`, `--table`, `--column`) and use
|
|
`--require-*` only for a mandatory constraint. In `final_sql`, include the approved CTE
|
|
plan in the current stage context. The command records only its minimal receipt.
|
|
|
|
An `available` outcome with zero results is visible but does not block the stage. An
|
|
`unavailable` outcome blocks the calling stage: report the sanitized failure and retry
|
|
the same stage later. Never use a stale generation or retry with another purpose.
|
|
Never call Evidence from `memory` or `synthesis`.
|