merge dev to main

[ymc9]

Summary by CodeRabbit

• New Features

  • Computed fields now support a context parameter, enabling more flexible evaluations.

• Chores

  • Removed support for the client initialization option that enabled automatic query logging.

• Documentation

  • Updated TODO status for the V3 Alpha item.

• Tests

  • Adjusted typing and type-check scenarios to align with the new computed field context behavior.

[coderabbitai]

Walkthrough

Updates a TODO checklist, adjusts the User model’s computed field signature to accept a context parameter, aligns a related typecheck condition, and removes query logging configuration from a sample client initialization.

Changes

Cohort / File(s)	Summary of changes
Documentation checklist TODO.md	Marked “Self relation” as completed in V3 Alpha Todo.
Runtime test schemas (typing) packages/runtime/test/schemas/typing/schema.ts, packages/runtime/test/schemas/typing/typecheck.ts	Updated User.computedFields.postCount signature to accept _context: { currentModel: string; }; adjusted whereRef comparison from User.id to id in related typecheck.
Samples: blog app samples/blog/main.ts	Removed log: ['query'] from ZenStackClient initialization options.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• chore: update typing test #24 — Also modifies the User model’s postCount computed field in the same typing schema area, indicating related evolution of the API.

Poem

A nibble of code, a checkbox checked,
A context passed where none had trekked.
Quiet logs now softly sleep,
While counts of posts their cadence keep.
Hop, hop—tests align in time,
A rabbit stamps “merged” in rhyme. 🐇✨

Tip

🔌 Remote MCP (Model Context Protocol) integration is now available!

Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats.

✨ Finishing Touches

• 📝 Generate Docstrings

🧪 Generate unit tests

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch dev

---

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

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

Status, Documentation and Community

• Visit our Status Page to check the current availability of CodeRabbit.
• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[claude]

Claude finished @ymc9's task —— View job

---

Code Review Analysis

Reviewing this dev-to-main merge PR. Here's my task list:

• Read CLAUDE.md for repository guidelines
• Examine changed files and understand modifications
• Analyze code quality and best practices
• Check for potential bugs or issues
• Review performance considerations
• Assess security concerns
• Evaluate test coverage
• Provide comprehensive review feedback

Review Summary

This PR contains clean, focused changes that improve the codebase without introducing any significant issues. All changes appear to be routine maintenance and improvements.

Changes Analysis

✅ TODO.md (Line 80)

• Change: Marked "Self relation" as completed ([ ] → [x])
• Assessment: Appropriate documentation update reflecting implemented functionality

✅ schema.ts (Lines 83-85)

• Change: Enhanced postCount computed field signature with proper context parameter
• Assessment: Good improvement - adds proper typing for the context parameter that includes currentModel
• Code Quality: Follows TypeScript best practices with explicit parameter typing

✅ typecheck.ts (Line 14)

• Change: Fixed column reference from 'User.id' to 'id' in Kysely query
• Assessment: Correct fix - when using whereRef, the second parameter should be the local column name
• Performance: More efficient query generation, eliminates potential ambiguity

✅ main.ts (Line 9)

• Change: Removed unused log: ['query'] configuration option
• Assessment: Good cleanup - removes unnecessary configuration that wasn't being used

Code Quality Assessment

Strengths:

• All changes follow established TypeScript and ZenStack patterns
• Proper typing improvements in computed field signatures
• Consistent with existing codebase style and conventions
• Clean removal of unused code

Best Practices Followed:

• Type-safe parameter definitions
• Proper Kysely query syntax
• Minimal, focused changes
• Clear separation of concerns

Security & Performance

Security: ✅ No security concerns identified

• Changes are internal improvements without external-facing modifications
• No sensitive data exposure or injection vulnerabilities introduced

Performance: ✅ Positive performance impact

• Fixed column reference improves query efficiency
• Removed unnecessary logging configuration reduces overhead

Test Coverage

Assessment: ✅ Well covered

• Changes are in test schemas and typing files, indicating good test infrastructure
• The typecheck.ts file specifically validates TypeScript compilation and type safety
• No new functionality requiring additional test coverage

Final Recommendation

✅ APPROVE - This is a high-quality PR with beneficial changes:

1. Proper functionality completion tracking
2. Improved type safety
3. Query optimization
4. Code cleanup

All changes align with repository standards and improve the codebase without introducing risks.

[Copilot]

Pull Request Overview

This PR merges changes from the dev branch to main, updating ZenStack client configurations and computed field implementations. The changes focus on simplifying database query configurations and refining computed field parameter handling.

• Removed query logging configuration from sample application
• Updated computed field reference patterns in test schemas
• Added context parameter to computed field type definitions

Reviewed Changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
samples/blog/main.ts	Removed query logging configuration from ZenStackClient setup
packages/runtime/test/schemas/typing/typecheck.ts	Simplified whereRef clause by removing table prefix
packages/runtime/test/schemas/typing/schema.ts	Added context parameter with currentModel to computed field signature
TODO.md	Marked self relation feature as completed

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (3)

TODO.md (1)

80-80: Fix markdown list indentation (MD007) on this line

markdownlint flagged this item: Expected indent 4; actual 8. Align it with the configured nesting level.

Apply this minimal diff:

-        - [x] Self relation
+    - [x] Self relation

Note: Other sibling items under “Misc” also appear indented by 8 spaces; consider running markdownlint --fix or your formatter to normalize the entire section.

packages/runtime/test/schemas/typing/schema.ts (1)

83-85: Optional: strengthen context typing to aid tooling and future readers

If feasible in the generator, consider a named type with a model literal for better inference in downstream usages (kept out of the generated file body, implemented in the generator):

For example, the generator could emit:

type ComputedFieldContext<M extends string> = { currentModel: M };

and then for User:

postCount(_context: ComputedFieldContext<'User'>): OperandExpression<number> { ... }

This preserves intent and helps editors/tooling.

packages/runtime/test/schemas/typing/typecheck.ts (1)

14-14: Relying on current-model context is good; add a clarifying comment

Using 'id' (unqualified) showcases the new context-based resolution. To aid future readers, add a brief comment noting it refers to User.id via the computed-field context.

-                    .whereRef('Post.authorId', '=', 'id')
+                    .whereRef('Post.authorId', '=', 'id') // 'id' resolves to User.id via computed field context

📜 Review details

Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro

💡 Knowledge Base configuration:

• MCP integration is disabled by default for public repositories
• Jira integration is disabled by default for public repositories
• Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between 23c58bd and 88e4381.

📒 Files selected for processing (4)

• TODO.md (1 hunks)
• packages/runtime/test/schemas/typing/schema.ts (1 hunks)
• packages/runtime/test/schemas/typing/typecheck.ts (1 hunks)
• samples/blog/main.ts (0 hunks)

💤 Files with no reviewable changes (1)

• samples/blog/main.ts

🧰 Additional context used

📓 Path-based instructions (1)

{packages,samples,tests}/**

📄 CodeRabbit Inference Engine (CLAUDE.md)

Packages are located in packages/, samples/, and tests/

Files:

• packages/runtime/test/schemas/typing/typecheck.ts
• packages/runtime/test/schemas/typing/schema.ts

🪛 markdownlint-cli2 (0.17.2)

TODO.md

80-80: Unordered list indentation
Expected: 4; Actual: 8

(MD007, ul-indent)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

• GitHub Check: build-test (20.x)

🔇 Additional comments (2)

TODO.md (1)

80-80: Marking “Self relation” as done is fine; ensure coverage across the stack

Nice to see this checked off. Please confirm we have:

• Unit tests for self-referential to-one and to-many relations (create/connect/disconnect/delete paths, nested mutations).
• Query behaviors covered (include/filter/order/groupBy/aggregate) involving self-relations.
• Typing tests that assert strict types for self-relations in the client.

I can generate a quick script to list existing self-relation tests and highlight gaps if you want.

packages/runtime/test/schemas/typing/schema.ts (1)

83-85: Context-aware computed field signature: LGTM

Adding _context to the postCount computed field stub is consistent with enabling unqualified refs to resolve against the current model. No functional impact here since this is a stub, but it improves type expressiveness.