I3369 — Four medium and three small tasks join the economics corpus, each failing on its start, passing on its reference and reviewed by someone other than its author
Add medium tasks due-dates-overdue, invoice-numbering, report-by-country and csv-delimiter-option and small tasks money-parse-validation, report-month-boundary and currency-symbol-format on the ledgerlite fixture within the registered cut-offs, so with I3368 the corpus holds 7 small, 7 medium and 6 large tasks; record an answered review id for each as I3368 does.
BLOCKED wave 3 · p1 · implementation profile · parallel safe
Blocked. This issue cannot start until I3374 is done. The status is derived from that, not declared.
Objective
Add medium tasks due-dates-overdue, invoice-numbering, report-by-country and csv-delimiter-option and small tasks money-parse-validation, report-month-boundary and currency-symbol-format on the ledgerlite fixture within the registered cut-offs, so with I3368 the corpus holds 7 small, 7 medium and 6 large tasks; record an answered review id for each as I3368 does.
Why
T2 of the owner's report of 2026-10-19 asks for 20 tasks split by difficulty. Balancing the strata lets each be reported; the same fixture and layout keep the new tasks comparable with the proven ones.
Current state
grep complexity gives 4 small (csv-credit-notes, currency-czk, test-repair, vat-rounding) and 3 medium (invoice-discounts, recurring-invoices, storage-v2).
Desired state
Seven new tasks proven by economics references and reviewed.
Scope
- .ai/repo/benchmarks/economics/tasks
- test/fixtures/economics/acceptance
- test/fixtures/economics/reference
Out of scope
- Editing the fixture or an existing task
- Adding the tasks to the pilot suite
Dependencies
What waits on this
Acceptance criteria
- Four tasks declare medium and three small, each inside its registered cut-offs
- economics references reports each failing on its start and passing on its reference
- No prompt names the hidden tests or the reference
- Across the corpus at least four categories hold two or more tasks
- Each task names an answered review id from a reviewer who did not write it
Validation
- majordomus economics references --work-dir \"$(mktemp -d)\"
- bash test/run.sh 430_economics
- majordomus plan validate
Evidence required
- references_small_and_medium_strata
Evidence
None recorded. Every token above needs a command or an artifact behind it before this issue can be completed; narrative is refused.
Timeline
- started
- —
- verified
- —
- completed
- —
Those three fields, the evidence above and the state of the dependencies are all the status is made of. There is no status field to disagree with them.
Canonical record: .ai/repo/project/issues/I3369.yaml. Read it back with majordomus plan show I3369.