Restore skip and move search to find

This commit is contained in:
ben
2026-03-20 13:35:07 -04:00
parent 2847d2d59f
commit afadd0c0d0
3 changed files with 90 additions and 8 deletions

View File

@@ -718,12 +718,12 @@ replace the old observed/canonical workflow with a review-first pipeline that us
- Direct numeric selection works well for suggestion-heavy review, while `[l]ink existing` remains available as a fallback when the suggestion list is empty or incomplete.
- I kept the review data model unchanged from `t1.15`; this task only tightened the prompt format, field order, and save behavior.
* [x] t1.16.1: add catalog search flow to review ui (2-3 commits)
* [X] t1.16.1: add catalog search flow to review ui (2-3 commits)
enable fast lookup of catalog items during review via tokenized search and replace manual list scanning
** acceptance criteria
1. replace `[l]ink existing` with `[s]earch` in review prompt:
- `[#] link to suggestion [s]earch [n]ew [x]exclude [q]uit >`
1. replace `[l]ink existing` with `[f]ind` in review prompt:
- `[#] link to suggestion [f]ind [n]ew [s]kip [x]exclude [q]uit >`
2. implement search flow:
- on `s`, prompt: `search: `
- tokenize input using same normalization rules as suggestion matching
@@ -755,12 +755,13 @@ enable fast lookup of catalog items during review via tokenized search and repla
** evidence
- commit: `f93b9aa`
- tests: `./venv/bin/python -m unittest discover -s tests`; `./venv/bin/python review_products.py --help`; `./venv/bin/python review_products.py --refresh-only`
- datetime: 2026-03-20 13:32:09 EDT
- datetime: 2026-03-20 13:34:57 EDT
** notes
- The search path reuses the same lightweight token matching rules as suggestion ranking, so there is still only one matching system to maintain.
- Direct numeric suggestion-pick remains the fastest happy path; search is the fallback when suggestions are sparse or missing.
- Search intentionally optimizes for manual speed rather than smart ranking: simple token overlap, max 10 rows, and immediate persistence on selection.
- Follow-up fix: search moved to `[f]ind` so `[s]kip` remains available at the main prompt.
* [ ] 1t.10: add optional llm-assisted suggestion workflow for unresolved normalized retailer items (2-4 commits)

View File

@@ -382,7 +382,7 @@ def prompt_resolution(queue_row, related_rows, purchase_rows, catalog_rows, queu
prompt_bits = []
if suggestions:
prompt_bits.append("[#] link to suggestion")
prompt_bits.extend(["[s]earch", "[n]ew", "e[x]clude", "[q]uit"])
prompt_bits.extend(["[f]ind", "[n]ew", "[s]kip", "e[x]clude", "[q]uit"])
click.secho(" ".join(prompt_bits) + " >", fg=PROMPT_COLOR)
action = click.prompt("", type=str, prompt_suffix=" ").strip().lower()
if action.isdigit() and suggestions:
@@ -403,6 +403,15 @@ def prompt_resolution(queue_row, related_rows, purchase_rows, catalog_rows, queu
if action == "q":
return None, None
if action == "s":
return {
"normalized_item_id": queue_row["normalized_item_id"],
"catalog_id": "",
"resolution_action": "skip",
"status": "pending",
"resolution_notes": queue_row.get("resolution_notes", ""),
"reviewed_at": str(date.today()),
}, None
if action == "f":
while True:
query = click.prompt(click.style("search", fg=PROMPT_COLOR), default="", show_default=False).strip()
if not query:

View File

@@ -219,7 +219,7 @@ class ReviewWorkflowTests(unittest.TestCase):
self.assertIn("Review guide:", result.output)
self.assertIn("Review 1/1: MIXED PEPPER", result.output)
self.assertIn("2 matched items:", result.output)
self.assertIn("[#] link to suggestion [s]earch [n]ew e[x]clude [q]uit >", result.output)
self.assertIn("[#] link to suggestion [f]ind [n]ew [s]kip e[x]clude [q]uit >", result.output)
first_item = result.output.index("[1] MIXED PEPPER 6-PACK | costco | 2026-03-14 | 7.49 | ")
second_item = result.output.index("[2] MIXED PEPPER 6-PACK | costco | 2026-03-12 | 6.99 | https://example.test/mixed-pepper.jpg")
self.assertLess(first_item, second_item)
@@ -401,7 +401,7 @@ class ReviewWorkflowTests(unittest.TestCase):
"--limit",
"1",
],
input="s\nmixed pepper\n1\nlinked by test\n",
input="f\nmixed pepper\n1\nlinked by test\n",
color=True,
)
@@ -492,13 +492,85 @@ class ReviewWorkflowTests(unittest.TestCase):
"--links-csv",
str(links_csv),
],
input="s\nzzz\nq\nq\n",
input="f\nzzz\nq\nq\n",
color=True,
)
self.assertEqual(0, result.exit_code)
self.assertIn("no matches found", result.output)
def test_skip_remains_available_from_main_prompt(self):
with tempfile.TemporaryDirectory() as tmpdir:
purchases_csv = Path(tmpdir) / "purchases.csv"
queue_csv = Path(tmpdir) / "review_queue.csv"
resolutions_csv = Path(tmpdir) / "review_resolutions.csv"
catalog_csv = Path(tmpdir) / "catalog.csv"
links_csv = Path(tmpdir) / "product_links.csv"
with purchases_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(
handle,
fieldnames=[
"purchase_date",
"retailer",
"order_id",
"line_no",
"normalized_item_id",
"catalog_id",
"raw_item_name",
"normalized_item_name",
"image_url",
"upc",
"line_total",
],
)
writer.writeheader()
writer.writerow(
{
"purchase_date": "2026-03-14",
"retailer": "giant",
"order_id": "g1",
"line_no": "1",
"normalized_item_id": "gnorm_skip",
"catalog_id": "",
"raw_item_name": "TEST ITEM",
"normalized_item_name": "TEST ITEM",
"image_url": "",
"upc": "",
"line_total": "1.00",
}
)
with catalog_csv.open("w", newline="", encoding="utf-8") as handle:
writer = csv.DictWriter(handle, fieldnames=review_products.build_purchases.CATALOG_FIELDS)
writer.writeheader()
result = CliRunner().invoke(
review_products.main,
[
"--purchases-csv",
str(purchases_csv),
"--queue-csv",
str(queue_csv),
"--resolutions-csv",
str(resolutions_csv),
"--catalog-csv",
str(catalog_csv),
"--links-csv",
str(links_csv),
"--limit",
"1",
],
input="s\n",
color=True,
)
self.assertEqual(0, result.exit_code)
with resolutions_csv.open(newline="", encoding="utf-8") as handle:
rows = list(csv.DictReader(handle))
self.assertEqual("skip", rows[0]["resolution_action"])
self.assertEqual("pending", rows[0]["status"])
def test_review_products_creates_catalog_and_resolution(self):
with tempfile.TemporaryDirectory() as tmpdir:
purchases_csv = Path(tmpdir) / "purchases.csv"