@sreetej510/pi-shipd-checks 0.7.2 → 0.7.4
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.
- package/README.md +7 -2
- package/dist/index.js +54 -54
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -38,8 +38,12 @@ Quality and then Solution Quality reruns in one browser tab, waits for both jobs
|
|
|
38
38
|
shows live elapsed time, and only displays unfair-test count, suggestion count, code-quality score, and
|
|
39
39
|
comprehensiveness score. It takes no parameters. Set the session's
|
|
40
40
|
job link with `/shipd:link <job-link>`; the link is stored in that chat session only. It uses one fresh headless
|
|
41
|
-
browser tab
|
|
42
|
-
|
|
41
|
+
browser tab at a time: it closes the browser after starting both jobs, checks after 5 minutes, then reopens every
|
|
42
|
+
90 seconds until both jobs finish. Each browser context blocks images, fonts, and media to reduce memory use. It does not
|
|
43
|
+
click the final orange challenge-submit button. Authentication comes from
|
|
44
|
+
`SHIPD_STORAGE_STATE` or the saved state created by `/shipd:auth`. `/shipd:auth` launches the installed browser
|
|
45
|
+
as a normal visible process and attaches over local CDP, which supports Google/SSO sign-in better than an automated
|
|
46
|
+
browser launch.
|
|
43
47
|
|
|
44
48
|
All analysis modes are read-only. Gap analysis uses two agents: a gap finder followed by a fairness reviewer.
|
|
45
49
|
Each audit uses one agent to keep the tool affordable. Invoke analysis only when the user asks, never in
|
|
@@ -55,6 +59,7 @@ do not run overlapping invocations for the same challenge.
|
|
|
55
59
|
| `/checks` | Open a menu with config and solver-gap-finder options |
|
|
56
60
|
| `/checks --config` | Configure reviewer, solver, gap-analysis, and Auditor models |
|
|
57
61
|
| `/checks --solver-gap-finder` | Run several solver agents TDD-style against `agent_prompt.md` + `test.patch`, then compare their solutions to the real solution to find gaps |
|
|
62
|
+
| `/shipd:auth` | Open a browser for first-time Shipd sign-in and save the session |
|
|
58
63
|
| `/shipd:link <url>` | Save the Shipd job link for the current chat session |
|
|
59
64
|
| `/analyze:on` | Enable the agent-callable test-analysis tool for the current project |
|
|
60
65
|
| `/analyze:off` | Disable the agent-callable test-analysis tool for the current project |
|