Conversation
devsergiy
requested review from
Noroth,
StarpTech,
endigma and
jensneuse
as code owners
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (2)
📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
WalkthroughThis PR updates the Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Tip Try Coding Plans. Let us write the prompt for your AI agent so you can ship faster (with fewer bugs). Comment |
❌ Internal Query Planner CI checks failedThe Internal Query Planner CI checks failed in the celestial repository, and this is going to stop the merge of this PR. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@router/go.mod`:
- Line 34: The go.mod currently pseudo-pins
github.com/wundergraph/graphql-go-tools/v2 to commit 726700149835 claiming it
contains "fix selecting parent of unique nodes" but that commit isn't documented
in the rc.259 release notes; verify that commit 726700149835 in module
github.com/wundergraph/graphql-go-tools/v2 is the intended fix by checking the
commit diff and changelog, run the project's integration and unit tests
(including resolver/field-resolver and selection logic tests) against that
commit to detect regressions, and then either (A) update go.mod to point to the
official release that contains the fix (if one exists) or (B) keep the
pseudo-version but add a clear comment above the module line documenting the
exact commit hash and reason for pinning; if tests fail, revert the pin and open
a follow-up issue/pr discussing the conflicting changes in field resolver logic.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 7a6929e0-9cbe-4bd0-8d55-84daaf67c050
⛔ Files ignored due to path filters (2)
router-tests/go.sumis excluded by!**/*.sumrouter/go.sumis excluded by!**/*.sum
📒 Files selected for processing (2)
router-tests/go.modrouter/go.mod
| github.com/tidwall/sjson v1.2.5 | ||
| github.com/twmb/franz-go v1.16.1 | ||
| github.com/wundergraph/graphql-go-tools/v2 v2.0.0-rc.257 | ||
| github.com/wundergraph/graphql-go-tools/v2 v2.0.0-rc.259.0.20260305233335-726700149835 |
There was a problem hiding this comment.
🧩 Analysis chain
🌐 Web query:
github.com/wundergraph/graphql-go-tools v2.0.0-rc.259 commit 726700149835 changelog
💡 Result:
- v2.0.0-rc.259 changelog (released 2026-03-05): Bug Fixes → “skip invocation for empty context in field resolvers” (PR fix: ignore internal cost for ristretto caches #1413, commit 5885c48). [1][2]
- Commit
726700149835(subject): “fix selecting parent of unique nodes” — changesv2/pkg/engine/plan/datasource_filter_visitor.goto stop walking up the parent chain when the parent is fully external (it now breaks instead of continuing). [3]
Sources: [1] Tags page (rc.259 notes), [2] Release page v2.0.0-rc.259, [3] Commit 726700149835.
🌐 Web query:
wundergraph graphql-go-tools v2 "parent of unique nodes" fix rc.259
💡 Result:
In wundergraph/graphql-go-tools v2, the GitHub tag/release v2.0.0-rc.259 (dated 2026-03-05) contains a single listed bug fix:
- “skip invocation for empty context in field resolvers” (PR fix: ignore internal cost for ristretto caches #1413, commit 5885c48) — the engine avoids invoking nested field resolver RPCs when the parent data/context is missing/empty, returning
nullinstead of making unnecessary calls. [1], [2]
I couldn’t find any release note, PR title, or commit message in rc.259 that matches the exact phrase “parent of unique nodes”. If you can paste the exact error/log line (or link the issue/PR), I can track the specific fix to the right tag/commit.
Sources: [1], [2]
🌐 Web query:
site:github.com wundergraph graphql-go-tools/v2 rc.259 rc.257 commits
💡 Result:
Commits included in wundergraph/graphql-go-tools between v2.0.0-rc.257 and v2.0.0-rc.259 (i.e., v2.0.0-rc.257...v2.0.0-rc.259) are these 5 commits: [1]
6fa1cdb— chore: move cost tests into separate file (PR#1418) [1]3b4dbcb— fix: handle complex types inside inline fragments in gRPC execution plan (PR#1411) [1]0bc474f— chore(master): release 2.0.0-rc.258 (PR#1425) [1]5885c48— fix: skip invocation for empty context in field resolvers (PR#1413) [1]5940d31— chore(master): release 2.0.0-rc.259 (PR#1427) [1]
The tags page also shows v2.0.0-rc.258 and v2.0.0-rc.259 were both created on Mar 5, 2026, with their release PRs (#1425, #1427) matching the commits above. [2]
Sources: [1] [2]
Clarify that the pinned commit contains the intended fix but is not in the rc.259 release notes.
The pseudo-version pins to commit 726700149835 which contains "fix selecting parent of unique nodes", but this fix is not listed in the v2.0.0-rc.259 (2026-03-05) changelog. The official rc.259 release documents only "skip invocation for empty context in field resolvers" (commit 5885c48). Confirm that commit 726700149835 is the correct intended fix before merge and verify it does not introduce regressions to the field resolver logic changes.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@router/go.mod` at line 34, The go.mod currently pseudo-pins
github.com/wundergraph/graphql-go-tools/v2 to commit 726700149835 claiming it
contains "fix selecting parent of unique nodes" but that commit isn't documented
in the rc.259 release notes; verify that commit 726700149835 in module
github.com/wundergraph/graphql-go-tools/v2 is the intended fix by checking the
commit diff and changelog, run the project's integration and unit tests
(including resolver/field-resolver and selection logic tests) against that
commit to detect regressions, and then either (A) update go.mod to point to the
official release that contains the fix (if one exists) or (B) keep the
pseudo-version but add a clear comment above the module line documenting the
exact commit hash and reason for pinning; if tests fail, revert the pin and open
a follow-up issue/pr discussing the conflicting changes in field resolver logic.
…lection-when-use-interfaces
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2592 +/- ##
==========================================
- Coverage 63.29% 63.10% -0.20%
==========================================
Files 244 244
Lines 25757 25757
==========================================
- Hits 16303 16253 -50
- Misses 8087 8123 +36
- Partials 1367 1381 +14 🚀 New features to boost your workflow:
|
devsergiy
deleted the
sergiy/eng-9097-fix-wrong-external-parent-selection-when-use-interfaces
branch
2 participants
Summary by CodeRabbit
Checklist