word_problem_to_calc_plan v1

Output: LLM JSON with variables, expression, steps; runtime adds computed_value via formula_eval_safe.

Failure modes

• TransportFailure — chat transport errors.
• ParseFailure — assistant output not valid JSON.
• SchemaFailure — input or output rejected vs contract schemas.
• GatewayFailure — upstream/provider errors.

Verification

Task-internal validation and JSON schema checks per contract.json verification_policy.

Changelog

• v1 — Maintained in catalog; see git history for semantic changes.

Examples

Minimal illustration (see sidecar examples for real payloads):

{}