@sreetej510/pi-shipd-checks 0.8.2 → 0.8.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +5 -4
  2. package/dist/index.js +50 -50
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -31,14 +31,15 @@ The agent-callable `solution-precheck` tool runs one exhaustive read-only soluti
31
31
  unrelated changes.
32
32
 
33
33
  The agent-callable `quality-check` tool runs `create_patches.sh` in the current working directory, reads
34
- `agent_prompt.md`, `test.patch`, and `solution.patch`, fills the authenticated Shipd draft fields, reruns only checks whose status is
35
- `Stale`, starts Test Quality before Solution Quality in one browser tab, waits for any started jobs, and returns only the useful report data:
34
+ `agent_prompt.md`, `test.patch`, and `solution.patch`, fills the authenticated Shipd draft fields, runs fresh checks with a
35
+ `Run` button, reruns checks marked `Stale`, skips current checks, starts Test Quality before Solution Quality in one
36
+ browser tab, waits for any started jobs, and returns only the useful report data:
36
37
  `details.testQuality.coverageSuggestions`, `details.testQuality.tests` filtered to items whose `fairness` is exactly
37
38
  `"Not fair"`, and the complete `details.solutionQuality.evaluation` block. Its compact UI is labeled `Quality Checks`,
38
39
  shows live elapsed time, and only displays unfair-test count, suggestion count, code-quality score, and
39
40
  comprehensiveness score. It takes no parameters. It uses one fresh headless browser tab at a time: it closes the
40
- browser after starting the stale jobs, checks after 5 minutes, then reopens every 90 seconds until those jobs finish. If
41
- no check is stale, it uses the existing reports without starting a job. Each
41
+ browser after starting the needed jobs, checks after 5 minutes, then reopens every 90 seconds until those jobs finish. If
42
+ all checks are current, it uses existing reports without starting a job. Each
42
43
  browser context blocks images, fonts, and media to reduce memory use. It does not click the final orange
43
44
  challenge-submit button. Authentication comes from `SHIPD_STORAGE_STATE` or the saved state created by
44
45
  `/shipd:auth`. `/shipd:auth` launches the installed browser as a normal visible process and attaches over local CDP,