waypoint-codex 1.1.1 → 1.1.2
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/package.json
CHANGED
|
@@ -20,6 +20,8 @@ Run this loop until exit criteria are satisfied.
|
|
|
20
20
|
1. Load PR state:
|
|
21
21
|
- collect all current review threads and comments, including existing comments present before the skill started
|
|
22
22
|
- collect CI/CD status for required checks
|
|
23
|
+
- for each reviewer (`Codex`, `CodeRabbit`), identify only that reviewer's latest top-level PR comment as the source of truth for the current reviewer state
|
|
24
|
+
- do not bind Codex parsing to one exact phrase; use author identity plus the latest comment/findings content (including explicit "no meaningful issues" style outcomes)
|
|
23
25
|
|
|
24
26
|
2. Triage and act:
|
|
25
27
|
- classify each reviewer finding as either major (`P1+`) or minor/nitpick
|
|
@@ -27,21 +29,31 @@ Run this loop until exit criteria are satisfied.
|
|
|
27
29
|
- fix all non-false-positive major (`P1+`) findings in code/docs/tests
|
|
28
30
|
- minor/nitpick findings may be accepted without code changes, but must still be replied to inline and resolved
|
|
29
31
|
- if CI/CD has failures, fix those failures as part of the same loop
|
|
32
|
+
- for CodeRabbit state handling:
|
|
33
|
+
- if latest CodeRabbit comment is `Actions performed -> Review triggered`, treat CodeRabbit as `pending` and wait for its next latest comment before triaging CodeRabbit findings
|
|
34
|
+
- do not use CodeRabbit CI/CD or check-run status as reviewer truth; comments are authoritative
|
|
30
35
|
|
|
31
36
|
3. Thread discipline for every addressed or skipped finding:
|
|
32
37
|
- post an inline reply on that thread explaining the fix or why it is a false positive
|
|
33
38
|
- resolve the thread after replying
|
|
34
39
|
|
|
35
|
-
4. Push and re-
|
|
40
|
+
4. Push and request reviewer-specific re-review only when needed:
|
|
36
41
|
- push commits
|
|
37
|
-
-
|
|
38
|
-
- post comment: `@codex review`
|
|
42
|
+
- determine which reviewer findings were addressed this round:
|
|
43
|
+
- if Codex findings were addressed, post comment: `@codex review`
|
|
44
|
+
- if CodeRabbit findings were addressed, post comment: `@coderabbitai review`
|
|
45
|
+
- if both were addressed, post both comments
|
|
46
|
+
- if neither reviewer's findings were addressed, do not trigger either reviewer
|
|
39
47
|
|
|
40
48
|
5. Wait for review/check updates:
|
|
41
49
|
- wait up to 30 minutes total
|
|
42
50
|
- check every 5 minutes using a sleep interval (`sleep 300`)
|
|
43
51
|
- on each check, re-read both review and CI/CD status
|
|
44
52
|
- if major (`P1+`) findings or CI/CD failures appear, continue the loop immediately
|
|
53
|
+
- when both reviewers' latest completed comments (not pending triggers) contain no major (`P1+`) findings, enter terminal cleanup mode:
|
|
54
|
+
- fix and resolve that round's remaining findings
|
|
55
|
+
- push commits if needed
|
|
56
|
+
- do not post any further `@codex review` or `@coderabbitai review` comments
|
|
45
57
|
|
|
46
58
|
## Exit Criteria
|
|
47
59
|
|
|
@@ -51,12 +63,16 @@ You may end the loop only when all are true:
|
|
|
51
63
|
- no unresolved major (`P1+`) Codex findings remain
|
|
52
64
|
- every addressed or skipped finding has an inline reply and is resolved
|
|
53
65
|
- CI/CD is green (or explicitly non-blocking per repo policy)
|
|
54
|
-
- the latest reviewer
|
|
66
|
+
- the latest completed reviewer comments from both bots contain only nitpicks/minor issues (no major `P1+` issues)
|
|
67
|
+
- terminal cleanup mode has been completed (remaining minor/nitpick findings handled, with no retrigger afterward)
|
|
55
68
|
|
|
56
69
|
## Required Behavior
|
|
57
70
|
|
|
58
71
|
- Do not ignore existing comments that were already open when the skill was invoked.
|
|
59
72
|
- Do not stop after one pass if reviewer bots are still producing new findings.
|
|
73
|
+
- Distinguish reviewer ownership of findings and retrigger only the reviewer whose findings were addressed.
|
|
74
|
+
- Use each reviewer's latest comment as reviewer truth; do not infer reviewer completion from CodeRabbit CI/CD status.
|
|
75
|
+
- Treat CodeRabbit `Actions performed -> Review triggered` as pending review, not as final findings.
|
|
60
76
|
- Do not mark false positives without a concrete reason in the inline reply.
|
|
61
77
|
- Do not leave handled threads unresolved.
|
|
62
78
|
- Do not declare completion while CI/CD is failing for actionable reasons.
|
|
@@ -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,
|
|
4
|
+
default_prompt: "Use $pr-review: address all existing PR review findings, fix actionable CI/CD failures, reply inline and resolve each handled thread, and request re-review per reviewer ownership (`@codex review` only if Codex findings were addressed, `@coderabbitai review` only if CodeRabbit findings were addressed). Treat each reviewer's latest comment as source of truth (CodeRabbit `Actions performed -> Review triggered` means pending); for Codex, do not key detection to one exact phrase, use latest authored comment/findings content. When both reviewers' latest completed comments have no major (P1+) findings, do one terminal cleanup pass and do not retrigger either reviewer."
|