ci: fix gh api review-state query in ready-for-review workflow

[xdustinface]

gh api does not support combining --slurp with --jq. Pipe paginated output to jq -rs instead so pages are concatenated into a single array before the filter runs.

This is issue was preventing the ready-for-review label from being added when CI completes after CodeRabbit approval.

Summary by CodeRabbit

• Chores
  • Updated CI workflow logic to normalize paginated review data client-side, improving reliability of automated review aggregation and ensuring consistent detection of the latest bot review state.

[coderabbitai]

📝 Walkthrough

Walkthrough

The workflow changes how PR reviews are fetched: the gh api call now uses --paginate piped to jq -rs (client-side aggregation) instead of prior server-side --slurp/--jq filtering; the downstream add → map(select) → sort_by → last → .state // "NONE" pipeline remains.

Changes

Cohort / File(s)	Summary
GitHub Actions Workflow ​.github/workflows/ready-for-review.yml	Replaced server-side gh api --jq/--slurp usage with gh api --paginate piped into jq -rs to aggregate paginated review results before applying existing filtering/sorting to derive the bot review .state.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Poem

🐇 I nibble logs where actions play,
From server trims to client array—
Pages pooled in a gentle heap,
One last review the workflow keeps.

🚥 Pre-merge checks | ✅ 3

✅ Passed checks (3 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly indicates a fix to the gh api review-state query in the ready-for-review workflow, which directly corresponds to the main change of switching from server-side --slurp --jq flags to client-side jq -rs piping.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch ci/ready-for-review-slurp-compat

📝 Coding Plan

• Generate coding plan for human review comments

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

.github/workflows/ready-for-review.yml (1)

130-142: ⚠️ Potential issue | 🔴 Critical

Critical: Missing -r flag causes comparison to always fail.

The jq -s command outputs JSON strings with quotes (e.g., "APPROVED"), but gh api --jq outputs raw strings by default. Without the -r flag, $CODERABBIT_STATE will contain "APPROVED" (with literal quote characters), and the comparison on line 139 against APPROVED (without quotes) will never match.

This means the ready-for-review label will never be added, defeating the purpose of this fix.

🐛 Proposed fix: Add `-r` flag to jq

-            CODERABBIT_STATE=$(gh api --paginate "repos/$REPO/pulls/$PR_NUMBER/reviews" | jq -s '
+            CODERABBIT_STATE=$(gh api --paginate "repos/$REPO/pulls/$PR_NUMBER/reviews" | jq -rs '
               add
               | map(select(.user.login == "coderabbitai[bot]"))
               | sort_by(.submitted_at)
               | last
               | .state // "NONE"
             ')

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In @.github/workflows/ready-for-review.yml around lines 130 - 142, The
comparison fails because jq -s produces quoted JSON strings so CODERABBIT_STATE
contains quotes (e.g., "APPROVED"); update the command that sets
CODERABBIT_STATE (the gh api | jq -s ... pipeline) to output raw strings by
adding the jq -r option so the variable holds APPROVED without quotes, ensuring
the subsequent if [ "$CODERABBIT_STATE" != "APPROVED" ] check works as intended.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Outside diff comments:
In @.github/workflows/ready-for-review.yml:
- Around line 130-142: The comparison fails because jq -s produces quoted JSON
strings so CODERABBIT_STATE contains quotes (e.g., "APPROVED"); update the
command that sets CODERABBIT_STATE (the gh api | jq -s ... pipeline) to output
raw strings by adding the jq -r option so the variable holds APPROVED without
quotes, ensuring the subsequent if [ "$CODERABBIT_STATE" != "APPROVED" ] check
works as intended.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 4e31c882-7592-4a51-93f6-ddfdb147b353

📥 Commits

Reviewing files that changed from the base of the PR and between 1de2479 and 12db4eb.

📒 Files selected for processing (1)

• .github/workflows/ready-for-review.yml

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 66.36%. Comparing base (1de2479) to head (0799eb6).
⚠️ Report is 1 commits behind head on v0.42-dev.

Additional details and impacted files

@@              Coverage Diff              @@
##           v0.42-dev     #566      +/-   ##
=============================================
- Coverage      66.37%   66.36%   -0.02%     
=============================================
  Files            311      311              
  Lines          64979    64979              
=============================================
- Hits           43130    43121       -9     
- Misses         21849    21858       +9     

Flag	Coverage Δ
core	75.13% <ø> (ø)
ffi	37.53% <ø> (+0.01%)	⬆️
rpc	28.28% <ø> (ø)
spv	81.12% <ø> (-0.09%)	⬇️
wallet	65.93% <ø> (ø)
see 5 files with indirect coverage changes