waypoint-codex 1.0.18 → 1.0.19
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/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: pr-review
|
|
3
|
-
description: Run and close the full PR review loop with CodeRabbit and Codex reviewers. Use when a PR already has review activity or when you need to request, wait for, triage, fix, and re-request automated review until no
|
|
3
|
+
description: Run and close the full PR review loop with CodeRabbit and Codex reviewers. Use when a PR already has review activity or when you need to request, wait for, triage, fix, and re-request automated review until no major (`P1+`) issues remain and CI/CD is green.
|
|
4
4
|
---
|
|
5
5
|
|
|
6
6
|
# PR review
|
|
@@ -22,8 +22,10 @@ Run this loop until exit criteria are satisfied.
|
|
|
22
22
|
- collect CI/CD status for required checks
|
|
23
23
|
|
|
24
24
|
2. Triage and act:
|
|
25
|
-
-
|
|
26
|
-
-
|
|
25
|
+
- classify each reviewer finding as either major (`P1+`) or minor/nitpick
|
|
26
|
+
- treat major (`P1+`) findings as mandatory unless they are clearly false positives
|
|
27
|
+
- fix all non-false-positive major (`P1+`) findings in code/docs/tests
|
|
28
|
+
- minor/nitpick findings may be accepted without code changes, but must still be replied to inline and resolved
|
|
27
29
|
- if CI/CD has failures, fix those failures as part of the same loop
|
|
28
30
|
|
|
29
31
|
3. Thread discipline for every addressed or skipped finding:
|
|
@@ -39,17 +41,17 @@ Run this loop until exit criteria are satisfied.
|
|
|
39
41
|
- wait up to 30 minutes total
|
|
40
42
|
- check every 5 minutes using a sleep interval (`sleep 300`)
|
|
41
43
|
- on each check, re-read both review and CI/CD status
|
|
42
|
-
- if
|
|
44
|
+
- if major (`P1+`) findings or CI/CD failures appear, continue the loop immediately
|
|
43
45
|
|
|
44
46
|
## Exit Criteria
|
|
45
47
|
|
|
46
48
|
You may end the loop only when all are true:
|
|
47
49
|
|
|
48
|
-
- no unresolved
|
|
49
|
-
- no unresolved
|
|
50
|
+
- no unresolved major (`P1+`) CodeRabbit findings remain
|
|
51
|
+
- no unresolved major (`P1+`) Codex findings remain
|
|
50
52
|
- every addressed or skipped finding has an inline reply and is resolved
|
|
51
53
|
- CI/CD is green (or explicitly non-blocking per repo policy)
|
|
52
|
-
- the latest reviewer rounds contain no
|
|
54
|
+
- the latest reviewer rounds contain only nitpicks/minor issues (no major `P1+` issues)
|
|
53
55
|
|
|
54
56
|
## Required Behavior
|
|
55
57
|
|
|
@@ -1,4 +1,4 @@
|
|
|
1
1
|
interface:
|
|
2
2
|
display_name: "PR Review"
|
|
3
3
|
short_description: "Close the review loop with CodeRabbit, Codex, and CI/CD"
|
|
4
|
-
default_prompt: "Use $pr-review: address all existing PR review findings, fix actionable CI/CD failures, reply inline and resolve each handled thread, push fixes, comment '@coderabbitai review' and '@codex review', then poll every 5 minutes for up to 30 minutes per round until no
|
|
4
|
+
default_prompt: "Use $pr-review: address all existing PR review findings, fix actionable CI/CD failures, reply inline and resolve each handled thread, push fixes, comment '@coderabbitai review' and '@codex review', then poll every 5 minutes for up to 30 minutes per round until no major (P1+) issues remain and latest comments are only minor or nitpicks."
|