@groupby/ai-dev 0.4.1 → 0.4.2
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
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
# Fix Review Findings
|
|
2
|
+
|
|
3
|
+
Apply actionable findings from `prompts/review-change.md` to the current changes in `components/`.
|
|
4
|
+
|
|
5
|
+
## Goal
|
|
6
|
+
|
|
7
|
+
Take the review findings/suggestions already produced, implement concrete fixes, run relevant verification, and report
|
|
8
|
+
what was addressed versus what still needs clarification.
|
|
9
|
+
|
|
10
|
+
## Inputs
|
|
11
|
+
|
|
12
|
+
Use the latest review output from this session. If no findings were reported, stop and state that no fix work is needed.
|
|
13
|
+
|
|
14
|
+
If findings are missing required detail (for example no file path, unclear recommendation, or conflicting guidance), ask
|
|
15
|
+
for clarification before editing.
|
|
16
|
+
|
|
17
|
+
## Prioritization Rules
|
|
18
|
+
|
|
19
|
+
Process findings in this order:
|
|
20
|
+
|
|
21
|
+
1. Critical and high-severity correctness/regression issues
|
|
22
|
+
2. Contract/schema/API mismatches
|
|
23
|
+
3. Validation and error-handling gaps
|
|
24
|
+
4. Missing or weak tests
|
|
25
|
+
5. Medium/low maintainability or style items
|
|
26
|
+
|
|
27
|
+
## Implementation Rules
|
|
28
|
+
|
|
29
|
+
- Apply minimal, targeted changes per finding.
|
|
30
|
+
- Keep scope limited to the reviewed change set.
|
|
31
|
+
- Do not perform unrelated refactors.
|
|
32
|
+
- If behavior changes, add or update focused tests.
|
|
33
|
+
- If contract/schema changes are required, update specs/contracts first, then runtime code.
|
|
34
|
+
- If a finding is intentionally not implemented, record why.
|
|
35
|
+
|
|
36
|
+
## Verification
|
|
37
|
+
|
|
38
|
+
Run relevant checks for touched components:
|
|
39
|
+
|
|
40
|
+
```bash
|
|
41
|
+
uv run pytest test/ -v # bc-agent, bc-mcp
|
|
42
|
+
mix test # bc-api
|
|
43
|
+
mix format --check-formatted # bc-api
|
|
44
|
+
./gradlew :bc-pay-core:test # bc-pay
|
|
45
|
+
./gradlew spotlessCheck # bc-pay
|
|
46
|
+
./gradlew test --no-daemon # bc-pay-stripe
|
|
47
|
+
./gradlew spotlessCheck --no-daemon # bc-pay-stripe
|
|
48
|
+
./gradlew test # bc-magento, bc-salesforce, bc-shopify, bc-webhooks
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
If full verification is too expensive, run focused checks for touched areas and state what was not run.
|
|
52
|
+
|
|
53
|
+
## Final Response
|
|
54
|
+
|
|
55
|
+
Lead with outcome and provide:
|
|
56
|
+
|
|
57
|
+
- Findings addressed (mapped to files changed)
|
|
58
|
+
- Findings deferred or blocked (with reason)
|
|
59
|
+
- Checks run and results
|
|
60
|
+
- Remaining risks
|
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
# Review Brain Checkout Component Change
|
|
2
|
+
|
|
3
|
+
Review the current changes in `components/`.
|
|
4
|
+
|
|
5
|
+
## Review Focus
|
|
6
|
+
|
|
7
|
+
- Correctness and regressions
|
|
8
|
+
- Contract compatibility
|
|
9
|
+
- Producer/consumer alignment for events and APIs
|
|
10
|
+
- Validation and error handling
|
|
11
|
+
- Secret leakage in logs/config/examples
|
|
12
|
+
- Missing or weak tests
|
|
13
|
+
- Build/test risk
|
|
14
|
+
|
|
15
|
+
## Output Format
|
|
16
|
+
|
|
17
|
+
Lead with findings:
|
|
18
|
+
|
|
19
|
+
```markdown
|
|
20
|
+
## Findings
|
|
21
|
+
|
|
22
|
+
- Severity: {critical|high|medium|low}
|
|
23
|
+
File: `{path}:{line}`
|
|
24
|
+
Issue: {specific issue}
|
|
25
|
+
Recommendation: {specific fix}
|
|
26
|
+
|
|
27
|
+
## Open Questions
|
|
28
|
+
|
|
29
|
+
- {question or "None"}
|
|
30
|
+
|
|
31
|
+
## Checks
|
|
32
|
+
|
|
33
|
+
- {command}: {result}
|
|
34
|
+
|
|
35
|
+
## Summary
|
|
36
|
+
|
|
37
|
+
{brief summary}
|
|
38
|
+
```
|
|
39
|
+
|
|
40
|
+
If no issues are found, say that clearly and list residual risks.
|
|
41
|
+
|
|
42
|
+
## Optional Next Step
|
|
43
|
+
|
|
44
|
+
If findings or suggestions are reported and code updates are required, run `prompts/fix-review-findings.md`.
|