Merged
Conversation
🦋 Changeset detectedLatest commit: ddbd1c1 The changes in this PR will be included in the next version bump. Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
Contributor
WalkthroughThis PR adds structured output support for Z.ai providers by updating the parse-prd schema to use union types with defaults for metadata, implementing array-property detection in the ZAI provider, normalizing GLM responses, and rewriting system prompts to enforce strict JSON envelopes. Additional changes include error token extraction improvements in base providers and ZAICodingProvider inheritance restructuring. Changes
Sequence Diagram(s)sequenceDiagram
actor User
participant Prompt
participant AIProvider
participant ZAIProvider
participant Schema
User->>Prompt: Request task analysis
Prompt->>AIProvider: Generate structured object
AIProvider->>ZAIProvider: Call generateObject()
ZAIProvider->>Schema: introspect schema for arrays
Schema-->>ZAIProvider: return array property name
ZAIProvider->>AIProvider: normalize response (wrap if array)
AIProvider-->>User: return normalized object
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes
Possibly related PRs
Suggested reviewers
Pre-merge checks and finishing touches✅ Passed checks (2 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Comment |
Crunchyman-ralph
changed the title
Crunchyman-ralph
commented
Nov 3, 2025
Collaborator
Author
Crunchyman-ralph
left a comment
Crunchyman-ralph
left a comment
There was a problem hiding this comment.
self-reviewed
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
scripts/modules/task-manager/analyze-task-complexity.js (1)
429-433: Critical: Optional chaining breaks downstream array operations.The optional chaining on line 429 allows
complexityAnalysisto beundefined, but line 431 immediately attempts.lengthaccess, which will throw a TypeError. Lines 436, 457, 476, and 531-540 also assumecomplexityAnalysisis a valid array.Apply this diff to validate the response structure and fail fast with a clear error:
// With generateObject, we get structured data directly - complexityAnalysis = aiServiceResponse.mainResult?.complexityAnalysis; + if (!aiServiceResponse.mainResult?.complexityAnalysis) { + throw new Error('AI service returned invalid response: missing mainResult.complexityAnalysis'); + } + complexityAnalysis = aiServiceResponse.mainResult.complexityAnalysis; reportLog( `Received ${complexityAnalysis.length} complexity analyses from AI.`, 'info' );
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (15)
.changeset/cyan-worms-count.md(1 hunks).changeset/grumpy-signs-type.md(1 hunks).changeset/ready-cities-marry.md(1 hunks)scripts/modules/task-manager/analyze-task-complexity.js(1 hunks)scripts/modules/task-manager/parse-prd/parse-prd-config.js(1 hunks)src/ai-providers/base-provider.js(1 hunks)src/ai-providers/zai-coding.js(1 hunks)src/ai-providers/zai.js(1 hunks)src/prompts/add-task.json(1 hunks)src/prompts/analyze-complexity.json(1 hunks)src/prompts/expand-task.json(1 hunks)tests/integration/cli/parse-prd-usage-tracking.test.js(1 hunks)tests/unit/ai-providers/zai-provider.test.js(1 hunks)tests/unit/ai-providers/zai-schema-introspection.test.js(1 hunks)tests/unit/scripts/modules/task-manager/parse-prd-schema.test.js(1 hunks)
🧰 Additional context used
📓 Path-based instructions (18)
tests/unit/ai-providers/*.test.js
📄 CodeRabbit inference engine (.cursor/rules/ai_providers.mdc)
Create unit tests for the new provider in tests/unit/ai-providers/.test.js, mocking @ai-sdk/ and core ai module functions, and testing all exported functions for correct behavior and error handling.
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.js
tests/{unit,integration,e2e,fixtures}/**/*.js
📄 CodeRabbit inference engine (.cursor/rules/architecture.mdc)
Test files must be organized as follows: unit tests in tests/unit/, integration tests in tests/integration/, end-to-end tests in tests/e2e/, and test fixtures in tests/fixtures/.
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
**/*.{test,spec}.{js,ts,jsx,tsx}
📄 CodeRabbit inference engine (.cursor/rules/git_workflow.mdc)
**/*.{test,spec}.{js,ts,jsx,tsx}: Create a test file and ensure all tests pass when all subtasks are complete; commit tests if added or modified
When all subtasks are complete, run final testing using the appropriate test runner (e.g., npm test, jest, or manual testing)
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
**/*.test.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
**/*.test.js: Never use asynchronous operations in tests. Make all mocks return synchronous values when possible.
Always mock tests properly based on the way the tested functions are defined and used.
Follow the test file organization: mocks must be set up before importing modules under test, and spies on mocked modules should be set up after imports.
Use fixtures from tests/fixtures/ for consistent sample data across tests.
Always declare mocks before importing the modules being tested in Jest test files.
Use jest.spyOn() after imports to create spies on mock functions and reference these spies in test assertions.
When testing functions with callbacks, get the callback from your mock's call arguments, execute it directly with test inputs, and verify the results.
For ES modules, use jest.mock() before static imports and jest.unstable_mockModule() before dynamic imports to mock dependencies.
Reset mock functions (mockFn.mockReset()) before dynamic imports if they might have been called previously.
When verifying console assertions, assert against the actual arguments passed (single formatted string), not multiple arguments.
Use mock-fs to mock file system operations in tests, and restore the file system after each test.
Mock API calls (e.g., Anthropic/Claude) by mocking the entire module and providing predictable responses.
Set mock environment variables in test setup and restore them after each test.
Maintain test fixtures separate from test logic.
Follow the mock-first-then-import pattern for all Jest mocks.
Do not define mock variables before jest.mock() calls (they won't be accessible due to hoisting).
Use test-specific file paths (e.g., 'test-tasks.json') for all file operations in tests.
Mock readJSON and writeJSON to avoid real file system interactions in tests.
Verify file operations use the correct paths in expect statements.
Use different file paths for each test to avoid test interdependence.
Verify modifications on the in-memory task objects passed to w...
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
tests/unit/**/*.test.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
tests/unit/**/*.test.js: Unit tests must be located in tests/unit/, test individual functions and utilities in isolation, mock all external dependencies, and keep tests small, focused, and fast.
Do not include actual command execution in unit tests.
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.js
tests/{unit,integration,e2e}/**/*.test.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
tests/{unit,integration,e2e}/**/*.test.js: When testing CLI commands built with Commander.js, test the command action handlers directly rather than trying to mock the entire Commander.js chain.
When mocking the Commander.js chain, mock ALL chainable methods (option, argument, action, on, etc.) and return this (or the mock object) from all chainable method mocks.
Explicitly handle all options, including defaults and shorthand flags (e.g., -p for --prompt), and include null/undefined checks in test implementations for parameters that might be optional.
Do not try to use the real action implementation without proper mocking, and do not mock Commander partially—either mock it completely or test the action directly.
Mock the action handlers for CLI commands and verify they're called with correct arguments.
Use sample task fixtures for consistent test data, mock file system operations, and test both success and error paths for task operations.
Mock console output and verify correct formatting in UI function tests. Use flexible assertions like toContain() or toMatch() for formatted output.
Mock chalk functions to return the input text to make testing easier while still verifying correct function calls.
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
**/*.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
**/*.js: Declare and initialize global variables at the top of modules to avoid hoisting issues.
Use proper function declarations to avoid hoisting issues and initialize variables before they are referenced.
Do not reference variables before their declaration in module scope.
Use dynamic imports (import()) to avoid initialization order issues in modules.
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jssrc/ai-providers/base-provider.jsscripts/modules/task-manager/analyze-task-complexity.jstests/integration/cli/parse-prd-usage-tracking.test.jsscripts/modules/task-manager/parse-prd/parse-prd-config.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
**/*.{test,spec}.*
📄 CodeRabbit inference engine (.cursor/rules/test_workflow.mdc)
Test files should follow naming conventions: .test., .spec., or _test. depending on the language
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
tests/{unit,integration,e2e}/**
📄 CodeRabbit inference engine (.cursor/rules/test_workflow.mdc)
Organize test directories by test type (unit, integration, e2e) and mirror source structure where possible
Files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
src/ai-providers/*.js
📄 CodeRabbit inference engine (.cursor/rules/ai_providers.mdc)
src/ai-providers/*.js: Create a new provider module file in src/ai-providers/ named .js when adding a new AI provider.
Provider modules must export three functions: generateText, streamText, and generateObject.
Provider modules must import the provider's create function from @ai-sdk/, and import generateText, streamText, generateObject from the core ai package, as well as the log utility from ../../scripts/modules/utils.js.
Implement generateText, streamText, and generateObject functions in provider modules with basic validation and try/catch error handling.Provider-specific wrappers for Vercel AI SDK functions must be implemented in src/ai-providers/*.js, each file corresponding to a provider.
Files:
src/ai-providers/base-provider.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
scripts/modules/task-manager/*.js
📄 CodeRabbit inference engine (.cursor/rules/ai_services.mdc)
scripts/modules/task-manager/*.js: Centralize all LLM calls throughgenerateTextServiceorgenerateObjectService.
Do not import or call anything from the oldai-services.js,ai-client-factory.js, orai-client-utils.jsfiles.
Do not initialize AI clients (Anthropic, Perplexity, etc.) directly within core logic (task-manager/) or MCP direct functions.
Do not fetch AI-specific parameters (model ID, max tokens, temp) usingconfig-manager.jsgetters for the AI call. Pass theroleinstead.
Do not implement fallback or retry logic outsideai-services-unified.js.
Do not handle API key resolution outside the service layer (it usesutils.jsinternally).
Determine the appropriaterole(main,research,fallback) in your core logic and pass it to the service.
Pass thesessionobject (received in thecontextparameter, especially from direct function wrappers) to the service call when in MCP context.
UsegenerateTextServiceand implement robust manual JSON parsing (with Zod validation after parsing) when structured output is needed, asgenerateObjectServicehas shown unreliability with some providers/schemas.
Be aware of potential reliability issues withgenerateObjectServiceacross different providers and complex schemas. PrefergenerateTextService+ manual parsing as a more robust alternative for structured data needs.Files in scripts/modules/task-manager/ should each handle a specific action related to task management (e.g., add-task.js, expand-task.js), supporting the tagged task lists system and backward compatibility.
Files:
scripts/modules/task-manager/analyze-task-complexity.js
scripts/modules/**
📄 CodeRabbit inference engine (.cursor/rules/dev_workflow.mdc)
When using the MCP server, restart it if core logic in
scripts/modulesor MCP tool/direct function definitions change.
Files:
scripts/modules/task-manager/analyze-task-complexity.jsscripts/modules/task-manager/parse-prd/parse-prd-config.js
scripts/modules/task-manager/*
📄 CodeRabbit inference engine (.cursor/rules/tags.mdc)
scripts/modules/task-manager/*: All core functions in scripts/modules/task-manager/ must accept a context parameter and use it to extract projectRoot and tag
All core functions in scripts/modules/task-manager/ must use readJSON(tasksPath, projectRoot, tag) and writeJSON(tasksPath, data, projectRoot, tag)
Files:
scripts/modules/task-manager/analyze-task-complexity.js
scripts/modules/task-manager/**/*.js
📄 CodeRabbit inference engine (.cursor/rules/telemetry.mdc)
scripts/modules/task-manager/**/*.js: Functions in scripts/modules/task-manager/ that invoke AI services must call the appropriate AI service function (e.g., generateObjectService), passing commandName and outputType in the params object.
Core logic functions in scripts/modules/task-manager/ must return an object that includes aiServiceResponse.telemetryData.
If the core logic function handles CLI output (outputFormat === 'text' or 'cli'), and aiServiceResponse.telemetryData is available, it must call displayAiUsageSummary(aiServiceResponse.telemetryData, 'cli') from scripts/modules/ui.js.Do not call AI-specific getters (like
getMainModelId,getMainMaxTokens) from core logic functions inscripts/modules/task-manager/*; instead, pass theroleto the unified AI service.
Files:
scripts/modules/task-manager/analyze-task-complexity.jsscripts/modules/task-manager/parse-prd/parse-prd-config.js
tests/integration/**/*.test.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
Integration tests must be located in tests/integration/, test interactions between modules, and focus on component interfaces rather than implementation details.
Files:
tests/integration/cli/parse-prd-usage-tracking.test.js
tests/{integration,e2e}/**/*.test.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
Properly mock session objects when required by functions, and reset environment variables between tests if modified.
Files:
tests/integration/cli/parse-prd-usage-tracking.test.js
.changeset/*.md
📄 CodeRabbit inference engine (.cursor/rules/changeset.mdc)
.changeset/*.md: When runningnpm run changesetornpx changeset add, provide a concise summary of the changes for theCHANGELOG.mdin imperative mood, typically a single line, and not a detailed Git commit message.
The changeset summary should be user-facing, describing what changed in the released version that is relevant to users or consumers of the package.
Do not use your detailed Git commit message body as the changeset summary.
Files:
.changeset/cyan-worms-count.md.changeset/ready-cities-marry.md.changeset/grumpy-signs-type.md
.changeset/*
📄 CodeRabbit inference engine (.cursor/rules/new_features.mdc)
Create appropriate changesets for new features, use semantic versioning, include tagged system information in release notes, and document breaking changes if any.
Files:
.changeset/cyan-worms-count.md.changeset/ready-cities-marry.md.changeset/grumpy-signs-type.md
🧠 Learnings (70)
📓 Common learnings
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/git_workflow.mdc:0-0
Timestamp: 2025-07-18T17:10:31.810Z
Learning: Pull Request descriptions must use the provided template, including Task Overview, Subtasks Completed, Implementation Details, Testing, Breaking Changes, and Related Tasks
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1069
File: .changeset/fix-tag-complexity-detection.md:0-0
Timestamp: 2025-08-02T15:33:22.656Z
Learning: For changeset files (.changeset/*.md), Crunchyman-ralph prefers to ignore formatting nitpicks about blank lines between frontmatter and descriptions, as he doesn't mind having them and wants to avoid such comments in future reviews.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1262
File: scripts/modules/task-manager/update-tasks.js:216-233
Timestamp: 2025-10-01T19:53:34.261Z
Learning: For scripts/modules/task-manager/*.js: Use generateObjectService with Zod schemas for structured AI responses rather than generateTextService + manual JSON parsing, as modern AI providers increasingly support the tool use and generateObject paradigm with improved reliability.
Learnt from: rtmcrc
Repo: eyaltoledano/claude-task-master PR: 933
File: scripts/modules/supported-models.json:238-238
Timestamp: 2025-07-21T14:14:48.694Z
Learning: Model version updates in scripts/modules/supported-models.json may be included in feature PRs if they provide practical improvements like reduced error rates, even if not directly related to the main feature being implemented.
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Implement generate<ProviderName>Text, stream<ProviderName>Text, and generate<ProviderName>Object functions in provider modules with basic validation and try/catch error handling.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/src/auth/config.ts:5-7
Timestamp: 2025-09-02T21:51:27.921Z
Learning: The user Crunchyman-ralph prefers not to use node: scheme imports (e.g., 'node:os', 'node:path') for Node.js core modules and considers suggestions to change bare imports to node: scheme as too nitpicky.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1132
File: .github/workflows/weekly-metrics-discord.yml:81-93
Timestamp: 2025-08-13T22:10:46.958Z
Learning: Crunchyman-ralph ignores YAML formatting nitpicks about trailing spaces when there's no project-specific YAML formatter configured, preferring to focus on functionality over cosmetic formatting issues.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1132
File: .github/workflows/weekly-metrics-discord.yml:81-93
Timestamp: 2025-08-13T22:10:46.958Z
Learning: Crunchyman-ralph ignores YAML formatting nitpicks about trailing spaces when there's no project-specific YAML formatter configured, preferring to focus on functionality over cosmetic formatting issues.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1200
File: src/ai-providers/custom-sdk/grok-cli/language-model.js:96-100
Timestamp: 2025-09-19T16:06:42.182Z
Learning: The user Crunchyman-ralph prefers to keep environment variable names explicit (like GROK_CLI_API_KEY) rather than supporting multiple aliases, to avoid overlap and ensure clear separation between different CLI implementations.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/src/subpath-exports.test.ts:6-9
Timestamp: 2025-09-03T12:45:30.724Z
Learning: The user Crunchyman-ralph prefers to avoid overly nitpicky or detailed suggestions in code reviews, especially for test coverage of minor import paths. Focus on more substantial issues rather than comprehensive coverage of all possible edge cases.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1105
File: scripts/modules/supported-models.json:242-254
Timestamp: 2025-08-08T11:33:15.297Z
Learning: Preference: In scripts/modules/supported-models.json, the "name" field is optional. For OpenAI entries (e.g., "gpt-5"), Crunchyman-ralph prefers omitting "name" when the id is explicit enough; avoid nitpicks requesting a "name" in such cases.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1217
File: apps/cli/src/index.ts:16-21
Timestamp: 2025-09-18T16:35:35.147Z
Learning: The user Crunchyman-ralph considers suggestions to export types for better ergonomics (like exporting UpdateInfo type alongside related functions) as nitpicky and prefers not to implement such suggestions.
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to tests/unit/ai-providers/*.test.js : Create unit tests for the new provider in tests/unit/ai-providers/<provider-name>.test.js, mocking ai-sdk/<provider-name> and core ai module functions, and testing all exported functions for correct behavior and error handling.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/integration/cli/parse-prd-usage-tracking.test.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to **/*.test.js : Do not import real AI service clients in tests; create fully mocked versions that return predictable responses.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to tests/{unit,integration,e2e}/**/*.test.js : Use sample task fixtures for consistent test data, mock file system operations, and test both success and error paths for task operations.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to **/*.test.js : Do not use real AI client initialization logic in tests; create test-specific paths that bypass client initialization.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to scripts/modules/**/*.test.js : Test core logic independently with both data formats, mock file system operations, test tag resolution behavior, and verify migration compatibility in unit tests.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to **/*.test.js : Verify modifications on the in-memory task objects passed to writeJSON.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.jssrc/prompts/add-task.json
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to tests/fixtures/**/* : Test fixtures must be located in tests/fixtures/, provide reusable test data, and be exported as named exports for reuse.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.js
📚 Learning: 2025-07-18T17:07:39.336Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/architecture.mdc:0-0
Timestamp: 2025-07-18T17:07:39.336Z
Learning: Applies to tests/{unit,integration,e2e,fixtures}/**/*.js : Test files must be organized as follows: unit tests in tests/unit/, integration tests in tests/integration/, end-to-end tests in tests/e2e/, and test fixtures in tests/fixtures/.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.js
📚 Learning: 2025-10-01T19:53:34.261Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1262
File: scripts/modules/task-manager/update-tasks.js:216-233
Timestamp: 2025-10-01T19:53:34.261Z
Learning: For scripts/modules/task-manager/*.js: Use generateObjectService with Zod schemas for structured AI responses rather than generateTextService + manual JSON parsing, as modern AI providers increasingly support the tool use and generateObject paradigm with improved reliability.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.jsscripts/modules/task-manager/analyze-task-complexity.jssrc/prompts/add-task.jsonsrc/prompts/expand-task.jsonscripts/modules/task-manager/parse-prd/parse-prd-config.jssrc/prompts/analyze-complexity.jsonsrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js.changeset/ready-cities-marry.md
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Implement generate<ProviderName>Text, stream<ProviderName>Text, and generate<ProviderName>Object functions in provider modules with basic validation and try/catch error handling.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jssrc/ai-providers/base-provider.jstests/integration/cli/parse-prd-usage-tracking.test.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:07:39.336Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/architecture.mdc:0-0
Timestamp: 2025-07-18T17:07:39.336Z
Learning: Applies to src/ai-providers/*.js : Provider-specific wrappers for Vercel AI SDK functions must be implemented in src/ai-providers/*.js, each file corresponding to a provider.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Provider modules must import the provider's create<ProviderName> function from ai-sdk/<provider-name>, and import generateText, streamText, generateObject from the core ai package, as well as the log utility from ../../scripts/modules/utils.js.
Applied to files:
tests/unit/ai-providers/zai-schema-introspection.test.jstests/unit/ai-providers/zai-provider.test.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Create a new provider module file in src/ai-providers/ named <provider-name>.js when adding a new AI provider.
Applied to files:
tests/unit/ai-providers/zai-provider.test.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to **/*.test.js : Do not rely on environment variables for API keys in tests; set mock environment variables in test setup.
Applied to files:
tests/unit/ai-providers/zai-provider.test.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to **/*.test.js : Mock API calls (e.g., Anthropic/Claude) by mocking the entire module and providing predictable responses.
Applied to files:
tests/unit/ai-providers/zai-provider.test.jstests/unit/scripts/modules/task-manager/parse-prd-schema.test.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to tests/{integration,e2e}/**/*.test.js : Properly mock session objects when required by functions, and reset environment variables between tests if modified.
Applied to files:
tests/unit/ai-providers/zai-provider.test.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Provider modules must export three functions: generate<ProviderName>Text, stream<ProviderName>Text, and generate<ProviderName>Object.
Applied to files:
tests/unit/ai-providers/zai-provider.test.jssrc/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:07:39.336Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/architecture.mdc:0-0
Timestamp: 2025-07-18T17:07:39.336Z
Learning: Module dependencies should be mocked before importing the test module, following Jest's hoisting behavior.
Applied to files:
tests/unit/ai-providers/zai-provider.test.js
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to scripts/modules/**/*.test.js : Test CLI and MCP interfaces with real task data, verify end-to-end workflows across tag contexts, and test error scenarios and recovery in integration tests.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:14:29.399Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tasks.mdc:0-0
Timestamp: 2025-07-18T17:14:29.399Z
Learning: Applies to scripts/modules/task-manager.js : Each task object must include all required properties (id, title, description, status, dependencies, priority, details, testStrategy, subtasks) and provide default values for optional properties. Extra properties not in the standard schema must not be added.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jssrc/prompts/add-task.jsonsrc/prompts/expand-task.jsonscripts/modules/task-manager/parse-prd/parse-prd-config.jssrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-20T01:35:05.831Z
Learnt from: rtmcrc
Repo: eyaltoledano/claude-task-master PR: 933
File: scripts/modules/task-manager/parse-prd.js:226-226
Timestamp: 2025-07-20T01:35:05.831Z
Learning: The parsePRD function in scripts/modules/task-manager/parse-prd.js has a different parameter structure than other task-manager functions - it uses `options` parameter instead of `context` parameter because it generates tasks from PRD documents rather than operating on existing tasks.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jsscripts/modules/task-manager/parse-prd/parse-prd-config.js
📚 Learning: 2025-07-18T17:14:29.399Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tasks.mdc:0-0
Timestamp: 2025-07-18T17:14:29.399Z
Learning: Applies to scripts/modules/task-manager.js : Extract tasks from PRD documents using AI, create them in the current tag context (defaulting to 'master'), provide clear prompts to guide AI task generation, and validate/clean up AI-generated tasks.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.jssrc/prompts/add-task.jsonsrc/prompts/expand-task.jsonscripts/modules/task-manager/parse-prd/parse-prd-config.js
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to tests/{unit,integration,e2e}/**/*.test.js : Explicitly handle all options, including defaults and shorthand flags (e.g., -p for --prompt), and include null/undefined checks in test implementations for parameters that might be optional.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:14:54.131Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/telemetry.mdc:0-0
Timestamp: 2025-07-18T17:14:54.131Z
Learning: Applies to scripts/modules/task-manager/**/*.js : Core logic functions in scripts/modules/task-manager/ must return an object that includes aiServiceResponse.telemetryData.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jsscripts/modules/task-manager/analyze-task-complexity.jsscripts/modules/task-manager/parse-prd/parse-prd-config.jssrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-18T17:16:13.793Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tests.mdc:0-0
Timestamp: 2025-07-18T17:16:13.793Z
Learning: Applies to tests/{unit,integration,e2e}/**/*.test.js : Mock console output and verify correct formatting in UI function tests. Use flexible assertions like toContain() or toMatch() for formatted output.
Applied to files:
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.jstests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:09:13.815Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/context_gathering.mdc:0-0
Timestamp: 2025-07-18T17:09:13.815Z
Learning: Commands such as `analyze-complexity`, `expand-task`, `update-task`, and `add-task` should consider adopting the context gathering pattern for improved AI-powered assistance.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.jssrc/prompts/expand-task.jsonsrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-18T17:14:29.399Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tasks.mdc:0-0
Timestamp: 2025-07-18T17:14:29.399Z
Learning: Applies to scripts/modules/task-manager.js : Use AI to generate detailed subtasks within the current tag context, considering complexity analysis for subtask counts and ensuring proper IDs for newly created subtasks.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.jssrc/prompts/expand-task.jsonsrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-18T17:18:17.759Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/utilities.mdc:0-0
Timestamp: 2025-07-18T17:18:17.759Z
Learning: Applies to scripts/modules/task-manager/**/*.js : Do not call AI-specific getters (like `getMainModelId`, `getMainMaxTokens`) from core logic functions in `scripts/modules/task-manager/*`; instead, pass the `role` to the unified AI service.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.js
📚 Learning: 2025-07-18T17:06:57.833Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_services.mdc:0-0
Timestamp: 2025-07-18T17:06:57.833Z
Learning: Applies to scripts/modules/task-manager/*.js : Do not import or call anything from the old `ai-services.js`, `ai-client-factory.js`, or `ai-client-utils.js` files.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.js
📚 Learning: 2025-09-24T15:12:12.658Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/.windsurfrules:0-0
Timestamp: 2025-09-24T15:12:12.658Z
Learning: Analyze task complexity with task-master analyze-complexity --research and use results to plan breakdown
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.jssrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-18T17:14:54.131Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/telemetry.mdc:0-0
Timestamp: 2025-07-18T17:14:54.131Z
Learning: Applies to scripts/modules/task-manager/**/*.js : If the core logic function handles CLI output (outputFormat === 'text' or 'cli'), and aiServiceResponse.telemetryData is available, it must call displayAiUsageSummary(aiServiceResponse.telemetryData, 'cli') from scripts/modules/ui.js.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.js
📚 Learning: 2025-07-18T17:06:57.833Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_services.mdc:0-0
Timestamp: 2025-07-18T17:06:57.833Z
Learning: Applies to scripts/modules/task-manager/*.js : Do not initialize AI clients (Anthropic, Perplexity, etc.) directly within core logic (`task-manager/`) or MCP direct functions.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.js
📚 Learning: 2025-07-18T17:06:57.833Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_services.mdc:0-0
Timestamp: 2025-07-18T17:06:57.833Z
Learning: Applies to scripts/modules/task-manager/*.js : Do not implement fallback or retry logic outside `ai-services-unified.js`.
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.js
📚 Learning: 2025-09-24T15:12:12.658Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/.windsurfrules:0-0
Timestamp: 2025-09-24T15:12:12.658Z
Learning: Use task-master complexity-report to view formatted complexity insights and recommendations
Applied to files:
scripts/modules/task-manager/analyze-task-complexity.jssrc/prompts/analyze-complexity.json
📚 Learning: 2025-08-03T12:13:33.875Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/test_workflow.mdc:0-0
Timestamp: 2025-08-03T12:13:33.875Z
Learning: Applies to {tests/setup.ts,tests/setup/integration.ts,tests/teardown.ts} : Test setup files should be created at tests/setup.ts, tests/setup/integration.ts, and tests/teardown.ts
Applied to files:
tests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:07:39.336Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/architecture.mdc:0-0
Timestamp: 2025-07-18T17:07:39.336Z
Learning: Applies to tests/integration/*.js : Integration tests in tests/integration/ should test interactions between modules.
Applied to files:
tests/integration/cli/parse-prd-usage-tracking.test.js
📚 Learning: 2025-07-18T17:14:29.399Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tasks.mdc:0-0
Timestamp: 2025-07-18T17:14:29.399Z
Learning: Applies to scripts/modules/task-manager.js : Use consistent formatting for task files, include all task properties in text files, and format dependencies with status indicators.
Applied to files:
src/prompts/add-task.jsonsrc/prompts/expand-task.jsonscripts/modules/task-manager/parse-prd/parse-prd-config.jssrc/prompts/analyze-complexity.json
📚 Learning: 2025-09-24T15:12:58.855Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/AGENTS.md:0-0
Timestamp: 2025-09-24T15:12:58.855Z
Learning: Applies to assets/.taskmaster/tasks/tasks.json : Never manually edit .taskmaster/tasks/tasks.json; use task-master commands to modify tasks
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-09-24T15:12:12.658Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/.windsurfrules:0-0
Timestamp: 2025-09-24T15:12:12.658Z
Learning: Add tasks with task-master add-task using AI with prompt, dependencies, and priority options
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-07-18T17:14:29.399Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tasks.mdc:0-0
Timestamp: 2025-07-18T17:14:29.399Z
Learning: Applies to scripts/modules/task-manager.js : Tasks must be organized into separate contexts (tags) within tasks.json, using the tagged format: {"master": {"tasks": [...]}, "feature-branch": {"tasks": [...]}}. Legacy format {"tasks": [...]} must be silently migrated to the tagged format on first use.
Applied to files:
src/prompts/add-task.jsonsrc/prompts/expand-task.jsonsrc/prompts/analyze-complexity.json
📚 Learning: 2025-09-24T15:12:58.855Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/AGENTS.md:0-0
Timestamp: 2025-09-24T15:12:58.855Z
Learning: Applies to assets/.taskmaster/tasks/tasks.json : If tasks.json is manually changed, run task-master generate to regenerate task files
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-07-18T17:10:53.657Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/glossary.mdc:0-0
Timestamp: 2025-07-18T17:10:53.657Z
Learning: Guidelines for integrating new features into the Task Master CLI with tagged system considerations (new_features.mdc).
Applied to files:
src/prompts/add-task.jsonsrc/prompts/analyze-complexity.json
📚 Learning: 2025-09-24T15:12:12.658Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/.windsurfrules:0-0
Timestamp: 2025-09-24T15:12:12.658Z
Learning: Follow the Task File Format template when writing task files: include ID, title, status, dependencies, priority, details, test strategy, and subtasks
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-07-31T22:07:49.716Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/commands.mdc:0-0
Timestamp: 2025-07-31T22:07:49.716Z
Learning: Applies to scripts/modules/commands.js : For AI-powered commands that benefit from project context, use the ContextGatherer utility for multi-source context extraction, support task IDs, file paths, custom context, and project tree, implement fuzzy search for automatic task discovery, and display detailed token breakdown for transparency.
Applied to files:
src/prompts/add-task.jsonsrc/prompts/expand-task.json
📚 Learning: 2025-07-18T17:08:48.695Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/commands.mdc:0-0
Timestamp: 2025-07-18T17:08:48.695Z
Learning: Applies to scripts/modules/commands.js : Follow the provided structure for adding subtasks, including required options and detailed error handling.
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-07-18T17:10:31.810Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/git_workflow.mdc:0-0
Timestamp: 2025-07-18T17:10:31.810Z
Learning: Pull Request descriptions must use the provided template, including Task Overview, Subtasks Completed, Implementation Details, Testing, Breaking Changes, and Related Tasks
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-07-31T22:07:49.716Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/commands.mdc:0-0
Timestamp: 2025-07-31T22:07:49.716Z
Learning: Applies to scripts/modules/commands.js : Follow the provided structure for adding subtasks, including required and optional options, parameter validation, and detailed error handling.
Applied to files:
src/prompts/add-task.json
📚 Learning: 2025-07-18T17:10:02.683Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/dev_workflow.mdc:0-0
Timestamp: 2025-07-18T17:10:02.683Z
Learning: When breaking down complex tasks in Taskmaster, use the `expand_task` command with appropriate flags (`--num`, `--research`, `--force`, `--prompt`) and review generated subtasks for accuracy.
Applied to files:
src/prompts/expand-task.jsonsrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-31T22:08:16.039Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/taskmaster.mdc:0-0
Timestamp: 2025-07-31T22:08:16.039Z
Learning: Applies to {.taskmaster/tasks/tasks.json,.taskmaster/reports/task-complexity-report.json,.taskmaster/docs/research/**} : Do not manually edit generated files such as .taskmaster/tasks/tasks.json, .taskmaster/reports/task-complexity-report.json, or files in .taskmaster/docs/research/. Always use Taskmaster commands to modify these files.
Applied to files:
src/prompts/expand-task.json
📚 Learning: 2025-07-18T17:10:12.881Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/dev_workflow.mdc:0-0
Timestamp: 2025-07-18T17:10:12.881Z
Learning: When breaking down complex tasks, use the `expand_task` command with appropriate flags (`--force`, `--research`, `--num`, `--prompt`) and review generated subtasks for accuracy.
Applied to files:
src/prompts/expand-task.jsonsrc/prompts/analyze-complexity.json
📚 Learning: 2025-07-18T17:09:13.815Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/context_gathering.mdc:0-0
Timestamp: 2025-07-18T17:09:13.815Z
Learning: Use context gathering for AI-powered commands that benefit from project context, when users might want to reference specific tasks or files, or for research, analysis, or generation commands. Do not use for simple CRUD operations that don't need AI context.
Applied to files:
src/prompts/expand-task.json
📚 Learning: 2025-07-18T17:09:16.839Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/context_gathering.mdc:0-0
Timestamp: 2025-07-18T17:09:16.839Z
Learning: For AI-powered commands, always use context gathering when the command benefits from project context, references specific tasks or files, or is used for research, analysis, or generation.
Applied to files:
src/prompts/expand-task.json
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to scripts/modules/*.js : Ensure new features work with existing projects seamlessly, supporting both legacy and tagged task data formats, and support silent migration during feature usage.
Applied to files:
scripts/modules/task-manager/parse-prd/parse-prd-config.js
📚 Learning: 2025-07-18T17:09:45.690Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/dependencies.mdc:0-0
Timestamp: 2025-07-18T17:09:45.690Z
Learning: Applies to scripts/modules/dependency-manager.js : Remove references to non-existent tasks during validation
Applied to files:
scripts/modules/task-manager/parse-prd/parse-prd-config.js
📚 Learning: 2025-07-18T17:14:29.399Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/tasks.mdc:0-0
Timestamp: 2025-07-18T17:14:29.399Z
Learning: Applies to scripts/modules/task-manager.js : Implement silent migration from legacy to tagged format in the readJSON() function, detect legacy format, convert automatically, and preserve all existing task data during migration.
Applied to files:
scripts/modules/task-manager/parse-prd/parse-prd-config.js
📚 Learning: 2025-07-18T17:13:11.229Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/self_improve.mdc:0-0
Timestamp: 2025-07-18T17:13:11.229Z
Learning: Document breaking changes
Applied to files:
src/prompts/analyze-complexity.json
📚 Learning: 2025-07-18T05:38:17.352Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 943
File: scripts/modules/task-manager/move-task.js:24-24
Timestamp: 2025-07-18T05:38:17.352Z
Learning: In the Claude Task Master system, core task-manager functions are designed with fallback mechanisms for missing projectRoot parameters using the pattern `const projectRoot = providedProjectRoot || findProjectRoot();`. The readJSON and writeJSON functions have default parameters (projectRoot = null, tag = null) and handle missing parameters gracefully. Adding strict validation to these core functions would break the established flexible architecture pattern.
Applied to files:
src/prompts/analyze-complexity.json
📚 Learning: 2025-09-03T13:46:00.640Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/src/auth/oauth-service.ts:20-20
Timestamp: 2025-09-03T13:46:00.640Z
Learning: For Node.js v22 and later, JSON imports should use `with { type: 'json' }` syntax, not `assert { type: 'json' }`. The `assert` syntax was removed in Node.js v22 in favor of the `with` syntax for import attributes. This applies to the eyaltoledano/claude-task-master codebase which uses Node.js v24.
Applied to files:
src/prompts/analyze-complexity.json
📚 Learning: 2025-07-31T22:08:16.039Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/taskmaster.mdc:0-0
Timestamp: 2025-07-31T22:08:16.039Z
Learning: For AI-powered tools (parse_prd, analyze_project_complexity, update_subtask, update_task, update, expand_all, expand_task, add_task), inform users that these operations may take up to a minute to complete.
Applied to files:
src/prompts/analyze-complexity.json
📚 Learning: 2025-10-31T18:07:17.384Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1360
File: src/ai-providers/glm.js:0-0
Timestamp: 2025-10-31T18:07:17.384Z
Learning: In src/ai-providers/glm.js, the GLM provider's getClient method should allow defaulting to the 'coding' endpoint when an invalid or unspecified route parameter is provided, as this is the correct behavior per Z.ai's OpenAI-compatible API documentation. Do not enforce strict route validation that throws errors for unknown routes.
Applied to files:
src/ai-providers/zai-coding.jssrc/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to scripts/modules/ai-services-unified.js : Integrate the new provider module with scripts/modules/ai-services-unified.js by importing it and adding an entry to the PROVIDER_FUNCTIONS map.
Applied to files:
src/ai-providers/zai-coding.js
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to scripts/modules/ai-services.js : Features that use AI models belong in 'scripts/modules/ai-services.js'.
Applied to files:
src/ai-providers/zai-coding.js
📚 Learning: 2025-09-29T13:33:46.952Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1246
File: src/ai-providers/claude-code.js:40-42
Timestamp: 2025-09-29T13:33:46.952Z
Learning: Claude Code provider should use environment variable isolation to control API key access, temporarily managing ANTHROPIC_API_KEY during client creation to prevent the ai-sdk-provider-claude-code package from automatically picking up API keys intended for other providers, while allowing explicit CLAUDE_CODE_API_KEY usage as a fallback to OAuth authentication.
Applied to files:
src/ai-providers/zai-coding.js
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to .changeset/* : Create appropriate changesets for new features, use semantic versioning, include tagged system information in release notes, and document breaking changes if any.
Applied to files:
.changeset/cyan-worms-count.md.changeset/ready-cities-marry.md
📚 Learning: 2025-07-21T14:14:48.694Z
Learnt from: rtmcrc
Repo: eyaltoledano/claude-task-master PR: 933
File: scripts/modules/supported-models.json:238-238
Timestamp: 2025-07-21T14:14:48.694Z
Learning: Model version updates in scripts/modules/supported-models.json may be included in feature PRs if they provide practical improvements like reduced error rates, even if not directly related to the main feature being implemented.
Applied to files:
.changeset/cyan-worms-count.md
📚 Learning: 2025-09-24T15:12:58.855Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/AGENTS.md:0-0
Timestamp: 2025-09-24T15:12:58.855Z
Learning: Applies to assets/.taskmaster/docs/*.{txt,md} : Keep PRDs as .txt or .md under .taskmaster/docs and parse them with task-master parse-prd (use --append for incremental updates)
Applied to files:
.changeset/cyan-worms-count.md
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to scripts/modules/ai-services*.js : Ensure AI calls correctly handle and propagate telemetryData as described in 'telemetry.mdc'.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:57.833Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_services.mdc:0-0
Timestamp: 2025-07-18T17:06:57.833Z
Learning: Applies to scripts/modules/ai-services-unified.js : Do not fetch AI-specific parameters (model ID, max tokens, temp) using `config-manager.js` getters for the AI call. Pass the `role` instead.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-09-24T15:12:58.855Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: assets/AGENTS.md:0-0
Timestamp: 2025-09-24T15:12:58.855Z
Learning: Applies to assets/.taskmaster/config.json : Never manually edit .taskmaster/config.json; use task-master models to change AI model settings
Applied to files:
.changeset/grumpy-signs-type.md
🧬 Code graph analysis (6)
tests/unit/ai-providers/zai-schema-introspection.test.js (1)
src/ai-providers/zai.js (1)
ZAIProvider(12-119)
tests/unit/ai-providers/zai-provider.test.js (2)
src/ai-providers/zai.js (1)
ZAIProvider(12-119)src/ai-providers/zai-coding.js (1)
ZAICodingProvider(13-20)
tests/unit/scripts/modules/task-manager/parse-prd-schema.test.js (1)
scripts/modules/task-manager/parse-prd/parse-prd-config.js (2)
prdResponseSchema(28-43)prdResponseSchema(28-43)
tests/integration/cli/parse-prd-usage-tracking.test.js (1)
src/ai-providers/zai.js (1)
ZAIProvider(12-119)
src/ai-providers/zai-coding.js (1)
src/ai-providers/zai.js (1)
ZAIProvider(12-119)
src/ai-providers/zai.js (2)
mcp-server/src/custom-sdk/schema-converter.js (1)
shape(69-69)scripts/modules/ai-services-unified.js (1)
result(441-441)
⏰ 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: Test
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
src/ai-providers/zai.js(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
src/ai-providers/*.js
📄 CodeRabbit inference engine (.cursor/rules/ai_providers.mdc)
src/ai-providers/*.js: Create a new provider module file in src/ai-providers/ named .js when adding a new AI provider.
Provider modules must export three functions: generateText, streamText, and generateObject.
Provider modules must import the provider's create function from @ai-sdk/, and import generateText, streamText, generateObject from the core ai package, as well as the log utility from ../../scripts/modules/utils.js.
Implement generateText, streamText, and generateObject functions in provider modules with basic validation and try/catch error handling.Provider-specific wrappers for Vercel AI SDK functions must be implemented in src/ai-providers/*.js, each file corresponding to a provider.
Files:
src/ai-providers/zai.js
**/*.js
📄 CodeRabbit inference engine (.cursor/rules/tests.mdc)
**/*.js: Declare and initialize global variables at the top of modules to avoid hoisting issues.
Use proper function declarations to avoid hoisting issues and initialize variables before they are referenced.
Do not reference variables before their declaration in module scope.
Use dynamic imports (import()) to avoid initialization order issues in modules.
Files:
src/ai-providers/zai.js
🧠 Learnings (16)
📓 Common learnings
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1262
File: scripts/modules/task-manager/update-tasks.js:216-233
Timestamp: 2025-10-01T19:53:34.261Z
Learning: For scripts/modules/task-manager/*.js: Use generateObjectService with Zod schemas for structured AI responses rather than generateTextService + manual JSON parsing, as modern AI providers increasingly support the tool use and generateObject paradigm with improved reliability.
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Implement generate<ProviderName>Text, stream<ProviderName>Text, and generate<ProviderName>Object functions in provider modules with basic validation and try/catch error handling.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/src/auth/config.ts:5-7
Timestamp: 2025-09-02T21:51:27.921Z
Learning: The user Crunchyman-ralph prefers not to use node: scheme imports (e.g., 'node:os', 'node:path') for Node.js core modules and considers suggestions to change bare imports to node: scheme as too nitpicky.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1069
File: .changeset/fix-tag-complexity-detection.md:0-0
Timestamp: 2025-08-02T15:33:22.656Z
Learning: For changeset files (.changeset/*.md), Crunchyman-ralph prefers to ignore formatting nitpicks about blank lines between frontmatter and descriptions, as he doesn't mind having them and wants to avoid such comments in future reviews.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1132
File: .github/workflows/weekly-metrics-discord.yml:81-93
Timestamp: 2025-08-13T22:10:46.958Z
Learning: Crunchyman-ralph ignores YAML formatting nitpicks about trailing spaces when there's no project-specific YAML formatter configured, preferring to focus on functionality over cosmetic formatting issues.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1132
File: .github/workflows/weekly-metrics-discord.yml:81-93
Timestamp: 2025-08-13T22:10:46.958Z
Learning: Crunchyman-ralph ignores YAML formatting nitpicks about trailing spaces when there's no project-specific YAML formatter configured, preferring to focus on functionality over cosmetic formatting issues.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1200
File: src/ai-providers/custom-sdk/grok-cli/language-model.js:96-100
Timestamp: 2025-09-19T16:06:42.182Z
Learning: The user Crunchyman-ralph prefers to keep environment variable names explicit (like GROK_CLI_API_KEY) rather than supporting multiple aliases, to avoid overlap and ensure clear separation between different CLI implementations.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/src/subpath-exports.test.ts:6-9
Timestamp: 2025-09-03T12:45:30.724Z
Learning: The user Crunchyman-ralph prefers to avoid overly nitpicky or detailed suggestions in code reviews, especially for test coverage of minor import paths. Focus on more substantial issues rather than comprehensive coverage of all possible edge cases.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1105
File: scripts/modules/supported-models.json:242-254
Timestamp: 2025-08-08T11:33:15.297Z
Learning: Preference: In scripts/modules/supported-models.json, the "name" field is optional. For OpenAI entries (e.g., "gpt-5"), Crunchyman-ralph prefers omitting "name" when the id is explicit enough; avoid nitpicks requesting a "name" in such cases.
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1217
File: apps/cli/src/index.ts:16-21
Timestamp: 2025-09-18T16:35:35.147Z
Learning: The user Crunchyman-ralph considers suggestions to export types for better ergonomics (like exporting UpdateInfo type alongside related functions) as nitpicky and prefers not to implement such suggestions.
📚 Learning: 2025-10-01T19:53:34.261Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1262
File: scripts/modules/task-manager/update-tasks.js:216-233
Timestamp: 2025-10-01T19:53:34.261Z
Learning: For scripts/modules/task-manager/*.js: Use generateObjectService with Zod schemas for structured AI responses rather than generateTextService + manual JSON parsing, as modern AI providers increasingly support the tool use and generateObject paradigm with improved reliability.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Provider modules must import the provider's create<ProviderName> function from ai-sdk/<provider-name>, and import generateText, streamText, generateObject from the core ai package, as well as the log utility from ../../scripts/modules/utils.js.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Implement generate<ProviderName>Text, stream<ProviderName>Text, and generate<ProviderName>Object functions in provider modules with basic validation and try/catch error handling.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:07:39.336Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/architecture.mdc:0-0
Timestamp: 2025-07-18T17:07:39.336Z
Learning: Applies to src/ai-providers/*.js : Provider-specific wrappers for Vercel AI SDK functions must be implemented in src/ai-providers/*.js, each file corresponding to a provider.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Create a new provider module file in src/ai-providers/ named <provider-name>.js when adding a new AI provider.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to tests/unit/ai-providers/*.test.js : Create unit tests for the new provider in tests/unit/ai-providers/<provider-name>.test.js, mocking ai-sdk/<provider-name> and core ai module functions, and testing all exported functions for correct behavior and error handling.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:04.909Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_providers.mdc:0-0
Timestamp: 2025-07-18T17:06:04.909Z
Learning: Applies to src/ai-providers/*.js : Provider modules must export three functions: generate<ProviderName>Text, stream<ProviderName>Text, and generate<ProviderName>Object.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-10-31T18:07:17.384Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1360
File: src/ai-providers/glm.js:0-0
Timestamp: 2025-10-31T18:07:17.384Z
Learning: In src/ai-providers/glm.js, the GLM provider's getClient method should allow defaulting to the 'coding' endpoint when an invalid or unspecified route parameter is provided, as this is the correct behavior per Z.ai's OpenAI-compatible API documentation. Do not enforce strict route validation that throws errors for unknown routes.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to scripts/modules/ai-services*.js : Ensure AI calls correctly handle and propagate telemetryData as described in 'telemetry.mdc'.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:06:57.833Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/ai_services.mdc:0-0
Timestamp: 2025-07-18T17:06:57.833Z
Learning: Applies to scripts/modules/ai-services-unified.js : Do not fetch AI-specific parameters (model ID, max tokens, temp) using `config-manager.js` getters for the AI call. Pass the `role` instead.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-10-05T10:14:41.302Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1273
File: packages/tm-core/src/repositories/supabase-task-repository.ts:165-167
Timestamp: 2025-10-05T10:14:41.302Z
Learning: In Zod v4, validation errors from ZodError are accessed via the `issues` property, not `errors` (which was used in Zod v3). When handling ZodError in TypeScript, use `error.issues` to access the array of validation issues.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-09-03T12:16:15.866Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/package.json:13-64
Timestamp: 2025-09-03T12:16:15.866Z
Learning: For internal packages in the claude-task-master project, Crunchyman-ralph prefers pointing package.json "types" entries to src .ts files rather than dist .d.ts files for better developer experience (DX), as the packages are not being exported as SDKs.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-09-03T13:46:00.640Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 1178
File: packages/tm-core/src/auth/oauth-service.ts:20-20
Timestamp: 2025-09-03T13:46:00.640Z
Learning: For Node.js v22 and later, JSON imports should use `with { type: 'json' }` syntax, not `assert { type: 'json' }`. The `assert` syntax was removed in Node.js v22 in favor of the `with` syntax for import attributes. This applies to the eyaltoledano/claude-task-master codebase which uses Node.js v24.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T17:12:57.903Z
Learnt from: CR
Repo: eyaltoledano/claude-task-master PR: 0
File: .cursor/rules/new_features.mdc:0-0
Timestamp: 2025-07-18T17:12:57.903Z
Learning: Applies to mcp-server/src/tools/*.js : Create tool definitions in 'mcp-server/src/tools/', use Zod for parameter validation, include optional tag parameter for multi-context support, and follow established naming conventions.
Applied to files:
src/ai-providers/zai.js
📚 Learning: 2025-07-18T05:38:17.352Z
Learnt from: Crunchyman-ralph
Repo: eyaltoledano/claude-task-master PR: 943
File: scripts/modules/task-manager/move-task.js:24-24
Timestamp: 2025-07-18T05:38:17.352Z
Learning: In the Claude Task Master system, core task-manager functions are designed with fallback mechanisms for missing projectRoot parameters using the pattern `const projectRoot = providedProjectRoot || findProjectRoot();`. The readJSON and writeJSON functions have default parameters (projectRoot = null, tag = null) and handle missing parameters gracefully. Adding strict validation to these core functions would break the established flexible architecture pattern.
Applied to files:
src/ai-providers/zai.js
🧬 Code graph analysis (1)
src/ai-providers/zai.js (2)
mcp-server/src/custom-sdk/schema-converter.js (2)
def(64-64)shape(69-69)scripts/modules/ai-services-unified.js (1)
result(441-441)
⏰ 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: Test
🔇 Additional comments (3)
src/ai-providers/zai.js (3)
18-20: LGTM! Configuration enables structured outputs.The
supportsStructuredOutputs: trueflag and updated base URL correctly enable structured output support for Z.ai GLM models.
23-31: LGTM! Correctly handles ZAI's token parameter restriction.The override appropriately prevents sending
max_tokensto avoid API error 1210.
89-121: Verify fallback behavior when GLM returns unexpected array.The normalization logic correctly handles GLM's bare array responses by introspecting the schema and wrapping under the detected array property. However, the fallback at lines 106-117 wraps the array under
objectNameeven when schema introspection fails or returns null.This means if GLM returns an array for a schema that doesn't expect an array property at all, the code will still wrap it rather than surfacing an error. Is this the intended behavior?
Consider whether the fallback should:
- Keep current behavior: Always wrap to avoid breaking consumers (current implementation)
- Fail fast: Throw an error when GLM returns an array for a non-array schema
- Return as-is: Return the bare array and let validation fail downstream
If the current behavior is intentional (defensive wrapping for edge cases), the implementation is correct.
github-actions bot
added a commit
that referenced
this pull request
Nov 3, 2025
This PR was automatically generated to update documentation based on recent changes. Original commit: fix: zai glm generation issues (#1377)\n\n\n Co-authored-by: Claude <claude-assistant@anthropic.com>
Merged
Merged
10 tasks
sfc-gh-dflippo
pushed a commit
to sfc-gh-dflippo/task-master-ai
that referenced
this pull request
Dec 4, 2025
7 tasks
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What type of PR is this?
Description
Related Issues
How to Test This
# Example commands or stepsExpected result:
Contributor Checklist
npm run changesetnpm testnpm run format-check(ornpm run formatto fix)Changelog Entry
For Maintainers
Summary by CodeRabbit
Release Notes
Bug Fixes
New Features