Record t1.11 task evidence
This commit is contained in:
34
pm/tasks.org
34
pm/tasks.org
@@ -343,23 +343,7 @@
|
|||||||
- tests: `./venv/bin/python -m unittest discover -s tests`; `./venv/bin/python build_purchases.py`; verified `combined_output/purchases.csv` and `combined_output/comparison_examples.csv` on the current Giant + Costco dataset
|
- tests: `./venv/bin/python -m unittest discover -s tests`; `./venv/bin/python build_purchases.py`; verified `combined_output/purchases.csv` and `combined_output/comparison_examples.csv` on the current Giant + Costco dataset
|
||||||
- date: 2026-03-16
|
- date: 2026-03-16
|
||||||
|
|
||||||
* [ ] t1.10: add optional llm-assisted suggestion workflow for unresolved products (2-4 commits)
|
* [X] t1.11: define review and item-resolution workflow for unresolved products (2-3 commits)
|
||||||
|
|
||||||
** acceptance criteria
|
|
||||||
- llm suggestions are generated only for unresolved observed products
|
|
||||||
- llm outputs are stored as suggestions, not auto-applied truth
|
|
||||||
- reviewer can approve/edit/reject suggestions
|
|
||||||
- approved decisions are persisted into canonical/link files
|
|
||||||
|
|
||||||
** notes
|
|
||||||
- bounded assistant, not autonomous goblin
|
|
||||||
- image urls may become useful here
|
|
||||||
|
|
||||||
** evidence
|
|
||||||
- commit:
|
|
||||||
- tests:
|
|
||||||
- date:
|
|
||||||
* [ ] t1.11: define review and item-resolution workflow for unresolved products (2-3 commits)
|
|
||||||
|
|
||||||
** acceptance criteria
|
** acceptance criteria
|
||||||
- define the persistent files used to resolve unknown items, including:
|
- define the persistent files used to resolve unknown items, including:
|
||||||
@@ -379,6 +363,22 @@
|
|||||||
- keep the workflow simple and auditable
|
- keep the workflow simple and auditable
|
||||||
- manual review is fine; the important part is making it durable and rerunnable
|
- manual review is fine; the important part is making it durable and rerunnable
|
||||||
|
|
||||||
|
** evidence
|
||||||
|
- commit: `c7dad54` on branch `cx`
|
||||||
|
- tests: `./venv/bin/python -m unittest discover -s tests`; `./venv/bin/python build_purchases.py`; `./venv/bin/python review_products.py --refresh-only`; verified `combined_output/review_queue.csv`, `combined_output/review_resolutions.csv` workflow, and `combined_output/canonical_catalog.csv`
|
||||||
|
- date: 2026-03-16
|
||||||
|
* [ ] t1.10: add optional llm-assisted suggestion workflow for unresolved products (2-4 commits)
|
||||||
|
|
||||||
|
** acceptance criteria
|
||||||
|
- llm suggestions are generated only for unresolved observed products
|
||||||
|
- llm outputs are stored as suggestions, not auto-applied truth
|
||||||
|
- reviewer can approve/edit/reject suggestions
|
||||||
|
- approved decisions are persisted into canonical/link files
|
||||||
|
|
||||||
|
** notes
|
||||||
|
- bounded assistant, not autonomous goblin
|
||||||
|
- image urls may become useful here
|
||||||
|
|
||||||
** evidence
|
** evidence
|
||||||
- commit:
|
- commit:
|
||||||
- tests:
|
- tests:
|
||||||
|
|||||||
Reference in New Issue
Block a user