@sreetej510/pi-shipd-checks 0.5.0 → 0.5.2
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 +3 -2
- package/dist/index.js +67 -56
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -26,9 +26,10 @@ The agent-callable `analyze_task_tests` tool provides the separate test-analysis
|
|
|
26
26
|
|
|
27
27
|
- `mode: "gaps"` (default) finds and validates sentence-by-sentence behavioral coverage gaps.
|
|
28
28
|
- `mode: "test-audit"` runs an Auditor followed by an independent validator over implemented tests,
|
|
29
|
-
filtering unfair assertions, prompt ambiguity, and broken fixtures.
|
|
29
|
+
filtering unfair assertions, prompt ambiguity, and broken fixtures. Auditors receive the in-memory
|
|
30
|
+
HEAD diff for changed code files so they can distinguish old and new behavior.
|
|
30
31
|
- `mode: "solution-audit"` runs the same Auditor/validator workflow over the implementation,
|
|
31
|
-
using the `# Solution implementation` rules from `rules.md
|
|
32
|
+
using the `# Solution implementation` rules from `rules.md` and the same in-memory changed-code diff.
|
|
32
33
|
|
|
33
34
|
All modes are read-only. Invoke the tool only when the user asks, never in parallel, and run
|
|
34
35
|
repeated requests sequentially after applying each result.
|