@sreetej510/pi-shipd-checks 0.11.1 → 0.11.3

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 +9 -8
  2. package/dist/index.js +67 -67
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -40,24 +40,25 @@ The agent-callable `quality-check` tool runs `create_patches.sh` in the current
40
40
  `agent_prompt.md`, `test.patch`, and `solution.patch`. It fills the authenticated Shipd draft fields and computes a SHA-256
41
41
  of the exact prompt content. The last passing prompt hash is stored as a custom entry in the current chat session. If the
42
42
  hash matches, it skips the Shipd Prompt Quality check entirely and reports a cached `PASS`; if it differs or is absent, it
43
- force-runs Shipd's Task Prompt Quality check even if Shipd labels the existing report current. A new hash is saved only after
44
- Prompt Quality passes. On failure, only `promptQuality` is returned; there are no Test/Solution results or `stoppedReason`.
43
+ checks the refreshed status after filling the fields and runs only when the check is stale or has a `Run` button. Otherwise it
44
+ uses the current report. A new hash is saved only after Prompt Quality passes. On failure, only `promptQuality` is returned; there are no Test/Solution results or `stoppedReason`.
45
45
  Only after Prompt Quality passes or has a matching cached pass does it run the Fargate patch precheck against a clean `HEAD`;
46
46
  only if that passes does it run Test Quality and Solution Quality. Those checks run fresh jobs, rerun stale reports, skip
47
47
  current reports, and wait for started jobs. It returns only the useful report data:
48
48
  `details.testQuality.verdict`, `details.testQuality.coverageSuggestions`, `details.testQuality.unfairnessCount`, and
49
49
  `details.testQuality.tests` filtered to blocks whose `concerns` array is non-empty or whose `fairness` is exactly `"Not fair"`,
50
- `details.promptQuality` and its verdict, reason, and major comments (only `category`, `quote`, and `suggestion`), plus
50
+ `details.promptQuality` and its verdict, reason, and major non-AI comments (only `category`, `quote`, and `suggestion`; AI-category comments are omitted), plus
51
51
  `details.solutionQuality.verdict` and its evaluation fields with `level` and `overall_feedback` removed. Fairness-only blocks
52
- with an empty `concerns` array are marked `Not fully fair`. Test Quality is `PASS` only when both filtered tests and coverage
53
- suggestions are empty; otherwise it is `FAIL`. Prompt Quality is `PASS` only when the completed report and evaluation
52
+ with an empty `concerns` array are marked `Not fully fair`. Test Quality is `PASS` only when there are no filtered unfair
53
+ tests, reported `unfairTestCount` is zero (when present), and coverage suggestions are empty. Prompt Quality is `PASS` only when the completed report and evaluation
54
54
  verdicts are both `PASS`, `requirementCount` is not blocking, and the AI gate does not flag the prompt. The prompt is
55
- flagged as AI only when `aiDetection.blocking` is `true` and `aiDetection.fractionAi` is at least `0.5`; the prediction
56
- label is not a gate. A cached Prompt Quality pass is marked
55
+ flagged as AI when a Prompt Quality comment category identifies AI (for example, `ai_generated`). AI-category quote and suggestion details are omitted; guidance recommends humanizer for a broader rewrite or a small targeted manual edit for a recent change. A cached Prompt Quality pass is marked
57
56
  `cached: true`. Test and Solution Quality return compact `PASS` results; failures include only actionable feedback. Prompt
58
57
  Quality failures return a concise reason or major comments. Returned quality results omit `completed` and `skipped`. Its
59
58
  compact UI is labeled `Quality Checks`, shows live elapsed time, and summarizes each stage; it does not print full pass
60
- criteria in the tool description. It takes no parameters. It uses one fresh headless browser tab at a time: for Prompt Quality
59
+ criteria in the tool description. It takes no parameters. Transient status and report-dialog operations retry up to three
60
+ times; after clicking Run, the tool verifies the stale state clears or the job shows running before it begins polling. It
61
+ uses one fresh headless browser tab at a time: for Prompt Quality
61
62
  it checks after 2 minutes, then every 30 seconds; for Test and Solution Quality it checks after 5 minutes, then reopens
62
63
  every 90 seconds until those jobs finish, with no client-side overall timeout. If all checks are current, it uses existing
63
64
  reports without starting a job. Each browser context blocks images, fonts, and media to reduce memory use. It does not click the final orange