merge dev to main (v3.0.0-alpha.19) #149
Conversation
…ted (#144) * fix: issue with in memory distinct when distinct fields are not selected * addressing PR comments
…ibility with Prisma (#147) * fix: tighten up query input validation, fixed case-sensitivity compatibility with Prisma * update
Co-authored-by: ymc9 <104139426+ymc9@users.noreply.github.com>
* Update `better-sqlite3` version range * update lockfile --------- Co-authored-by: Yiming Cao <yiming@whimslab.io> Co-authored-by: ymc9 <104139426+ymc9@users.noreply.github.com>
Co-authored-by: ymc9 <104139426+ymc9@users.noreply.github.com>
WalkthroughThis update advances the version numbers of multiple packages from "3.0.0-alpha.18" to "3.0.0-alpha.19" and introduces significant enhancements to runtime type safety, filter logic, and validation schemas. It refines string filter behavior, count selection, and relation handling, adds provider-aware case sensitivity, and expands test coverage for filters and selection. Changes
Estimated code review effort🎯 4 (Complex) | ⏱️ ~40 minutes Possibly related PRs
Poem
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. ✨ Finishing Touches
🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
|
Claude finished @ymc9's task —— View job Pull Request ReviewReviewing this dev → main merge for code quality, potential issues, performance, and security concerns. Todo List
Review SummaryThis PR merges dev to main with 6 commits containing version bumps, dependency updates, and important bug fixes. The changes are well-structured and address specific issues while maintaining compatibility. Key Changes Reviewed1. Version Management ✅
2. Dependency Updates ✅
3. Critical Bug Fixes 🔧Query Input Validation & Case Sensitivity (commit 3a49973)
In-Memory Distinct Operations (commit 6a62a2c)
Relation Count Selection (commit 192cc01)
4. Code Quality Assessment ✅Strengths:
Architecture:
5. Security Considerations 🔒Positive aspects:
No security vulnerabilities detected. 6. Performance Implications 📊Improvements:
7. Test Coverage 📋Strong test additions:
Potential Areas for Improvement
Recommendation✅ APPROVE - This PR is ready for merge. The changes are:
The bug fixes are particularly important for production stability, and the version consistency across packages ensures smooth deployment. |
There was a problem hiding this comment.
Pull Request Overview
This PR merges development branch changes to main, incrementing the version number from 3.0.0-alpha.18 to 3.0.0-alpha.19 across all packages and implementing several runtime improvements.
- Version bump across all package.json files to alpha.19
- Enhanced string filtering with case sensitivity support for PostgreSQL
- Improved client API functionality for distinct queries and count operations
- Better error handling and type safety improvements in the runtime
Reviewed Changes
Copilot reviewed 26 out of 27 changed files in this pull request and generated no comments.
Show a summary per file
| File | Description |
|---|---|
| Multiple package.json files | Version increment from alpha.18 to alpha.19 |
| packages/runtime/src/client/query-utils.ts | Replace requireField with getField for safer field access |
| packages/runtime/src/client/crud/validator.ts | Enhanced validation schemas with strictObject and string filtering improvements |
| packages/runtime/src/client/crud/operations/base.ts | Improved distinct query handling and count JSON building |
| packages/runtime/src/client/crud/dialects/*.ts | Database dialect improvements for relation handling and count operations |
| packages/runtime/src/client/crud-types.ts | Enhanced type definitions for filtering with provider-specific features |
| packages/runtime/test/client-api/*.test.ts | Extended test coverage for distinct queries and provider-specific filtering |
Files not reviewed (1)
- pnpm-lock.yaml: Language not supported
Comments suppressed due to low confidence (3)
packages/runtime/package.json:78
- The version
^12.2.0for better-sqlite3 may not exist. As of my knowledge cutoff in January 2025, better-sqlite3 was at version 11.x. Please verify this version exists before merging.
"better-sqlite3": "^12.2.0",
packages/runtime/test/client-api/find.test.ts:867
- This test case is checking TypeScript compilation errors with @ts-expect-error but doesn't include an assertion. Consider adding an explicit test that verifies the runtime behavior or removes this if it's only for type checking.
client.comment.findFirst({
packages/runtime/test/client-api/find.test.ts:872
- Similar to the previous comment, this test case with @ts-expect-error doesn't include runtime assertions. Consider adding explicit verification of the expected behavior.
client.post.findFirst({
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
package.json (1)
3-3: Root version updated correctly.
Ensure you also tagv3.0.0-alpha.19and update the changelog before publishing.
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
pnpm-lock.yamlis excluded by!**/pnpm-lock.yaml
📒 Files selected for processing (26)
package.json(1 hunks)packages/cli/package.json(1 hunks)packages/common-helpers/package.json(1 hunks)packages/create-zenstack/package.json(1 hunks)packages/dialects/sql.js/package.json(1 hunks)packages/eslint-config/package.json(1 hunks)packages/ide/vscode/package.json(1 hunks)packages/language/package.json(1 hunks)packages/runtime/package.json(2 hunks)packages/runtime/src/client/crud-types.ts(4 hunks)packages/runtime/src/client/crud/dialects/base.ts(7 hunks)packages/runtime/src/client/crud/dialects/postgresql.ts(3 hunks)packages/runtime/src/client/crud/dialects/sqlite.ts(4 hunks)packages/runtime/src/client/crud/operations/base.ts(3 hunks)packages/runtime/src/client/crud/validator.ts(35 hunks)packages/runtime/src/client/query-utils.ts(1 hunks)packages/runtime/test/client-api/filter.test.ts(3 hunks)packages/runtime/test/client-api/find.test.ts(4 hunks)packages/sdk/package.json(1 hunks)packages/tanstack-query/package.json(1 hunks)packages/testtools/package.json(1 hunks)packages/typescript-config/package.json(1 hunks)packages/vitest-config/package.json(1 hunks)packages/zod/package.json(1 hunks)samples/blog/package.json(1 hunks)tests/e2e/package.json(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
{packages,samples,tests}/**
📄 CodeRabbit Inference Engine (CLAUDE.md)
Packages are located in
packages/,samples/, andtests/
Files:
packages/language/package.jsonpackages/dialects/sql.js/package.jsonpackages/zod/package.jsonpackages/testtools/package.jsonpackages/runtime/package.jsonpackages/eslint-config/package.jsontests/e2e/package.jsonpackages/ide/vscode/package.jsonpackages/tanstack-query/package.jsonpackages/cli/package.jsonsamples/blog/package.jsonpackages/typescript-config/package.jsonpackages/create-zenstack/package.jsonpackages/vitest-config/package.jsonpackages/sdk/package.jsonpackages/common-helpers/package.jsonpackages/runtime/test/client-api/filter.test.tspackages/runtime/src/client/query-utils.tspackages/runtime/src/client/crud/dialects/sqlite.tspackages/runtime/test/client-api/find.test.tspackages/runtime/src/client/crud-types.tspackages/runtime/src/client/crud/dialects/base.tspackages/runtime/src/client/crud/operations/base.tspackages/runtime/src/client/crud/dialects/postgresql.tspackages/runtime/src/client/crud/validator.ts
tests/e2e/**
📄 CodeRabbit Inference Engine (CLAUDE.md)
E2E tests are in
tests/e2e/directory
Files:
tests/e2e/package.json
🧠 Learnings (11)
📚 Learning: `zenstack generate` compiles zmodel to typescript schema (`schema.ts`)...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: `zenstack generate` compiles ZModel to TypeScript schema (`schema.ts`)
Applied to files:
packages/language/package.jsonpackage.jsonpackages/zod/package.jsonpackages/ide/vscode/package.jsonpackages/tanstack-query/package.jsonpackages/cli/package.jsonpackages/typescript-config/package.jsonpackages/create-zenstack/package.jsonpackages/vitest-config/package.jsonpackages/sdk/package.jsonpackages/runtime/src/client/crud/validator.ts
📚 Learning: language-first design: zmodel dsl compiles to typescript, not runtime code generation...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Language-First Design: ZModel DSL compiles to TypeScript, not runtime code generation
Applied to files:
packages/language/package.jsonpackages/runtime/src/client/crud/validator.ts
📚 Learning: schema-first approach with zmodel dsl extension of prisma schema language...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Schema-first approach with ZModel DSL extension of Prisma schema language
Applied to files:
packages/language/package.jsonpackages/runtime/src/client/crud-types.tspackages/runtime/src/client/crud/validator.ts
📚 Learning: zmodel schema (`schema.zmodel`) defines database structure and policies...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: ZModel schema (`schema.zmodel`) defines database structure and policies
Applied to files:
packages/language/package.jsonpackages/runtime/src/client/crud/validator.ts
📚 Learning: kysely-based orm: v3 uses kysely as query builder instead of prisma runtime dependency...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Kysely-Based ORM: V3 uses Kysely as query builder instead of Prisma runtime dependency
Applied to files:
packages/dialects/sql.js/package.jsonpackages/runtime/src/client/crud/operations/base.ts
📚 Learning: no runtime dependency on @prisma/client...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: No runtime dependency on prisma/client
Applied to files:
packages/runtime/package.json
📚 Learning: applies to tests/e2e/** : e2e tests are in `tests/e2e/` directory...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Applies to tests/e2e/** : E2E tests are in `tests/e2e/` directory
Applied to files:
tests/e2e/package.jsonpackages/runtime/test/client-api/filter.test.ts
📚 Learning: type coverage tests ensure typescript inference works correctly...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Type coverage tests ensure TypeScript inference works correctly
Applied to files:
packages/runtime/test/client-api/filter.test.tspackages/runtime/test/client-api/find.test.ts
📚 Learning: client provides both high-level orm api and low-level kysely query builder...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Client provides both high-level ORM API and low-level Kysely query builder
Applied to files:
packages/runtime/src/client/crud/operations/base.ts
📚 Learning: kysely query builder as escape hatch instead of raw sql...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Kysely query builder as escape hatch instead of raw SQL
Applied to files:
packages/runtime/src/client/crud/operations/base.ts
📚 Learning: applies to **/schema.zmodel : always run `zenstack generate` after modifying zmodel schemas...
Learnt from: CR
PR: zenstackhq/zenstack-v3#0
File: CLAUDE.md:0-0
Timestamp: 2025-08-04T08:43:33.161Z
Learning: Applies to **/schema.zmodel : Always run `zenstack generate` after modifying ZModel schemas
Applied to files:
packages/runtime/src/client/crud/validator.ts
🧬 Code Graph Analysis (6)
packages/runtime/test/client-api/filter.test.ts (3)
packages/runtime/test/client-api/client-specs.ts (1)
createClientSpecs(6-42)packages/runtime/src/client/crud/dialects/postgresql.ts (1)
provider(27-29)packages/runtime/src/client/crud/dialects/sqlite.ts (1)
provider(27-29)
packages/runtime/src/client/query-utils.ts (3)
packages/runtime/src/client/crud/operations/base.ts (2)
getField(124-126)schema(89-91)samples/blog/zenstack/schema.ts (1)
schema(9-228)packages/sdk/src/schema/schema.ts (1)
SchemaDef(10-18)
packages/runtime/test/client-api/find.test.ts (1)
packages/runtime/test/client-api/utils.ts (1)
createUser(6-21)
packages/runtime/src/client/crud-types.ts (2)
packages/sdk/src/schema/schema.ts (7)
GetModelFieldType(151-155)ModelFieldIsOptional(217-221)SchemaDef(10-18)BuiltinType(84-94)GetModels(108-108)RelationFields(196-200)FieldIsArray(235-239)packages/runtime/src/utils/type-utils.ts (1)
NullableIf(5-5)
packages/runtime/src/client/crud/operations/base.ts (1)
packages/runtime/src/client/query-utils.ts (3)
ensureArray(267-273)buildFieldRef(154-176)safeJSONStringify(275-283)
packages/runtime/src/client/crud/dialects/postgresql.ts (3)
packages/sdk/src/schema/schema.ts (1)
GetModels(108-108)packages/runtime/src/client/query-utils.ts (2)
requireField(30-36)buildFieldRef(154-176)packages/runtime/src/client/crud/operations/base.ts (1)
requireField(120-122)
⏰ 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). (3)
- GitHub Check: claude-review
- GitHub Check: build-test (20.x)
- GitHub Check: Analyze (javascript-typescript)
🔇 Additional comments (48)
packages/runtime/src/client/query-utils.ts (4)
99-102: LGTM: Safer field handling with graceful fallback.The change from
requireFieldtogetFieldwith optional chaining makes this function more defensive by returningfalsefor non-existent fields instead of throwing errors. This aligns with the broader improvements mentioned in the AI summary for safer schema field handling.
104-107: LGTM: Consistent defensive pattern applied.Similar to
isScalarField, this change provides graceful handling of missing fields by returningfalseinstead of throwing errors.
109-112: LGTM: Maintains consistency with other field checking utilities.The defensive approach is consistently applied across all field type checking functions.
114-117: LGTM: Completes the consistent refactoring pattern.All four field checking utilities now follow the same safe pattern of using
getFieldwith optional chaining.packages/runtime/test/client-api/find.test.ts (4)
247-247: LGTM: Profile creation supports the enhanced distinct tests.The addition of profile creation with bio fields supports the new distinct test cases that verify include/select behavior.
Also applies to: 256-256
273-287: LGTM: Comprehensive distinct query testing.The new test cases properly verify that distinct queries work correctly with both
includeandselectclauses, ensuring that related data (profile) is properly included/selected while maintaining distinct behavior on the specified fields.
852-866: LGTM: Nested relation count selection test.This test verifies that selecting
_counton nested relations (posts with their comments count) works correctly, returning the expected structure with zero comments for each post.
867-876: LGTM: TypeScript type safety validation.The
@ts-expect-errortests properly validate that TypeScript correctly prevents selecting_counton entities that don't have to-many relations (Comment model) and prevents invalid nested_countusage. This ensures type safety as mentioned in the AI summary.packages/runtime/src/client/crud/operations/base.ts (3)
180-196: LGTM! Solid approach for cross-dialect distinct handling.The aliasing strategy using
$distinct$prefix ensures distinct fields are available for in-memory filtering when the dialect lacksdistinctOnsupport. The implementation correctly usesbuildFieldReffor consistent field reference building.
233-251: LGTM! Well-implemented in-memory distinct filtering.The deduplication logic properly uses
safeJSONStringifyfor composite key generation and cleanly removes temporary fields. The algorithm preserves insertion order while efficiently handling duplicates.
315-315: LGTM! Clean refactoring delegating to dialect implementation.Excellent simplification that centralizes count JSON construction in the dialect layer while maintaining clean separation of concerns. This allows for dialect-specific optimizations and reduces code duplication.
packages/runtime/src/client/crud/dialects/postgresql.ts (2)
203-203: LGTM! Good consistency improvement with parameter naming.The rename from
parentNametoparentAliasis more semantically accurate and aligns with similar changes across dialect implementations. All usages are updated consistently.
241-259: LGTM! Well-implemented_countfield handling.The conditional logic properly separates
_countfield handling from regular fields, delegating to the centralizedbuildCountJsonmethod. The alias path construction is correct and maintains consistency with the existing relation handling patterns.packages/runtime/test/client-api/filter.test.ts (3)
8-8: LGTM! Provider-aware test configuration.The addition of the
providerparameter to the test describe block enables provider-specific test logic, which aligns with the enhanced filter functionality that supports database-specific behavior.
79-189: Excellent comprehensive provider-specific test coverage!The provider-specific string filter tests are well-structured and thorough:
SQLite tests (79-128): Correctly validate that equality operations are case-sensitive while
contains,startsWith, andinoperations are case-insensitive, which aligns with SQLite's documented behavior.PostgreSQL tests (129-188): Properly test the new
modeparameter functionality for case-insensitive filtering, coveringequals,contains,endsWith, andinoperations with both default and explicitinsensitivemodes.The use of
as anytype assertions for themodeproperty is appropriate for testing new functionality during development.
326-328: LGTM! Minor formatting improvement.The multiline formatting of the
toMatchObjectassertion enhances readability and maintains consistency with similar assertions in the test file.packages/runtime/src/client/crud/dialects/sqlite.ts (4)
70-70: LGTM! Parameter naming improvement.The rename from
parentNametoparentAliasprovides better semantic clarity about the parameter's role in SQL alias generation.
77-147: LGTM! Consistent parameter renaming throughout.All references to the renamed parameter have been properly updated across subquery alias naming and SQL reference strings, maintaining consistency and improving code clarity.
186-211: LGTM! Improved count handling with clear separation of concerns.The explicit handling of the
_countfield before processing relation fields provides better code organization. The logic properly delegates count JSON construction to the base dialect'sbuildCountJsonmethod, maintaining consistency with the broader refactoring effort.
227-227: LGTM! Consistent parameter usage in include logic.The
parentAliasparameter is correctly used in the relation JSON building for included fields, maintaining consistency with the parameter renaming.packages/runtime/src/client/crud-types.ts (4)
226-226: LGTM! Schema-aware primitive filter integration.The addition of the
Schemageneric parameter toPrimitiveFilterenables schema-aware filtering capabilities, which is essential for the provider-specific features being introduced.
252-287: Excellent schema-aware filter type design!The enhancement of filter types to be schema-aware is well-implemented:
- Schema integration: All primitive filter types now accept the
Schemageneric parameter, enabling provider-specific behavior- Conditional mode property:
StringFilterconditionally includes themodeproperty only for providers that support case sensitivity (PostgreSQL), maintaining type safety- Consistent propagation: The schema parameter is properly threaded through all filter type hierarchies including the
notfieldThe use of conditional types with
ProviderSupportsCaseSensitivity<Schema>ensures type-safe access to provider-specific features.
401-406: Smart conditional _count field inclusion!The conditional inclusion of the
_countfield only when the model has to-many relations prevents meaningless count selections on models without array relations. TheHasToManyRelations<Schema, Model>type correctly identifies models with array-type relation fields.
1194-1201: Well-designed utility types for feature detection!The utility types are excellently structured:
HasToManyRelations: Uses mapped types to identify models with array-type relation fields, enabling conditional _count field inclusionProviderSupportsCaseSensitivity: Currently supports PostgreSQL with a design that's easily extensible to other providersBoth types follow TypeScript best practices for conditional type logic and provide clear semantic constraints for the type system.
packages/runtime/src/client/crud/dialects/base.ts (3)
459-478: LGTM! Good enhancement to filter flexibility.The addition of the
excludeKeysparameter alongside the existingonlyForKeysprovides comprehensive control over which filter keys to process.
520-591: Well-implemented case-insensitive string filtering support.The refactoring properly handles both 'default' and 'insensitive' modes, using appropriate SQL functions (
lower,ilike) for case-insensitive comparisons. The recursive handling inprepStringCasingfor arrays is correct.Note: The
ilikeoperator is PostgreSQL-specific, which aligns with the validator's provider-aware implementation.
865-913: Excellent implementation of relation count JSON building.The
buildCountJsonmethod provides a clean abstraction for generating nested count queries for to-many relations. It properly handles:
- Selective counting based on payload
- Join conditions via
buildJoinPairs- Optional filtering with where clauses
- JSON object construction for the results
packages/runtime/src/client/crud/validator.ts (4)
698-703: Verify intentional use of non-strict objects at top level.While most schemas have been refactored to use
z.strictObject(), several top-level schemas in create, update, upsert, and delete operations usez.object()without strict mode. Is this intentional for flexibility, or should these also be strict for consistency?Also applies to: 962-968, 992-999, 1104-1108
521-542: Well-designed provider-aware string filter enhancements.The string filter schema properly:
- Adds missing string operations (startsWith, endsWith, contains)
- Conditionally includes the
modefield only for PostgreSQL- Uses appropriate schema validation with literal types
The provider check ensures compatibility across different database systems.
Also applies to: 1295-1297
1261-1267: Good refactoring of skip/take schemas.Centralizing the skip and take schema definitions improves maintainability and ensures consistent validation across all usages. The validation rules are correct:
skip: non-negative integers onlytake: allows negative values for reverse limiting
564-590: Excellent conditional _count field implementation.The schema correctly:
- Includes
_countonly for models with to-many relations (optimization)- Supports both simple (
true) and detailed count selection- Allows per-relation count filtering with where clauses
This aligns perfectly with the
buildCountJsonmethod in the dialect layer.tests/e2e/package.json (1)
3-3: Version bump looks good – remember to regenerate workspace lockfileThe version update is consistent with the coordinated alpha.19 release. After merging, run your monorepo’s install/bootstrap step (e.g.,
pnpm installornpm install) to refresh the root lockfile and avoid mismatched workspace ranges.samples/blog/package.json (1)
3-3: Blog sample version aligned – no issues spottedChange is straightforward and keeps the sample in sync with the rest of the repo.
packages/common-helpers/package.json (1)
3-3: Helper package version updated correctlyNo additional metadata changes detected; version bump is clean.
packages/eslint-config/package.json (1)
3-3: ESLint config version bump acknowledgedUpdate is in line with the overall release cadence.
packages/typescript-config/package.json (1)
3-3: TypeScript config package version synchronizedLooks good; nothing else to address.
packages/zod/package.json (1)
3-3: Version bump looks good and stays in sync with the monorepo.
Nothing else changed in the manifest, so no additional action required.packages/testtools/package.json (1)
3-3: Consistent version update.
Change is straightforward and aligned with the rest of the packages.packages/sdk/package.json (1)
3-3: SDK package version bump confirmed.
No further issues spotted.packages/dialects/sql.js/package.json (1)
3-3: Dialect package version bump confirmed.
Looks ready to merge.packages/tanstack-query/package.json (1)
3-3: Version bump looks consistent; LGTM
No further action required.packages/language/package.json (1)
4-4: Version synced with monorepo release; LGTMpackages/vitest-config/package.json (1)
4-4: Version update is correct; LGTMpackages/create-zenstack/package.json (1)
3-3: Version bump aligns with broader release; LGTMpackages/cli/package.json (1)
6-6: CLI package version updated consistently; LGTMpackages/ide/vscode/package.json (1)
4-4: Version bump is fine; ensure ancillary release assets are updatedOnly the
versionfield changed. Please double-check that:
CHANGELOG.md(or equivalent) contains an entry for 3.0.0-alpha.19.- The pre-release published to the VS Code Marketplace will be tagged
alpha.19so users get the correct update.No code issues detected.
packages/runtime/package.json (2)
3-3: Runtime package version bump acknowledgedThe version aligns with the monorepo’s alpha.19 release train. LGTM.
78-78: Confirm compatibility withbetter-sqlite3@^12.2.0
better-sqlite3jumped a major version (11 → 12). ABI or build-time changes are common with this library.Recommended actions:
- Run the full test suite against Node 18 and Node 20 to catch native-addon regressions.
- Verify the minimum Node version stated in project docs still satisfies
better-sqlite3≥ 12.No blocking issue, but please confirm before publishing.
Summary by CodeRabbit
New Features
_count) only for models with to-many relations, improving query precision.Bug Fixes
Tests
Chores