- Outcome
- FAIL15m
- Reward
- 0.0%
- Checks passed
- 15 / 17
- Runtime
- 15m 13s
- Harness
- Cursor CLI
- Task version
- v3.2.0
Checks
| Check | Result | Credit | Weight |
|---|---|---|---|
| baseline: the service answers a search | PASS | 100% | 1% |
| baseline: the web app answers a search | PASS | 100% | 1% |
| backend: search API results carry the best passage's page range | PASS | 100% | 18% |
| backend: MCP search results carry the page range | PASS | 100% | 8% |
| backend: one result per document, and a big PDF does not crowd out the others | PASS | 100% | 10% |
| backend: a search does not page through every passage of a huge PDF | PASS | 100% | 8% |
| web: search route results carry the page range | PASS | 100% | 12% |
| web: one result per document, and a big PDF does not crowd out the others | PASS | 100% | 8% |
| web: a search does not page through every passage of a huge PDF | PASS | 100% | 6% |
| web card: the result card shows Page N or Pages N–M, and nothing without pages | PASS | 100% | 22% |
| partial spans: a span with one bound shows no page 0 or dangling range | PASS | 100% | 6% |
| preserve: the search API | FAIL | 0% | 0% |
| preserve: the MCP search tool | FAIL | 0% | 0% |
| preserve: the web app's search route | PASS | 100% | 0% |
| preserve: the web app's search result card | PASS | 100% | 0% |
| preserve: the backend's ruff and strict mypy | PASS | 100% | 0% |
| preserve: the web app type-checks | PASS | 100% | 0% |