feat: improve PR and add changeset

- Introduced multiple Kiro hooks to automate task management workflows, including:
  - Code Change Task Tracker
  - Complexity Analyzer
  - Daily Standup Assistant
  - Git Commit Task Linker
  - Import Cleanup on Delete
  - New File Boilerplate
  - PR Readiness Checker
  - Task Dependency Auto-Progression
  - Test Success Task Completer
- Added .mcp.json configuration for Taskmaster AI integration.
- Updated development workflow documentation to reflect new hook-driven processes and best practices.

This commit enhances the automation capabilities of Taskmaster, streamlining task management and improving developer efficiency.

.changeset/fix-gemini-cli-dependency.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.

.changeset/pre.json

@@ -1,16 +0,0 @@
-{
-  "mode": "pre",
-  "tag": "rc",
-  "initialVersions": {
-    "task-master-ai": "0.21.0",
-    "extension": "0.20.0"
-  },
-  "changesets": [
-    "fix-gemini-cli-dependency",
-    "fresh-bugs-squashed",
-    "happy-sites-stay",
-    "orange-pots-add",
-    "quiet-rabbits-bathe",
-    "swift-otters-argue"
-  ]
-}

.changeset/quiet-rabbits-bathe.md

@@ -1,10 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix max_tokens limits for OpenRouter and Groq models
-
-- Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
-- Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
-- Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
-- This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list

.changeset/thick-squids-attend.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Prompt to generate a complexity report when it is missing

.github/workflows/pre-release.yml

@@ -16,7 +16,7 @@ jobs:
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: "npm"
+          cache: 'npm'
 
       - name: Cache node_modules
         uses: actions/cache@v4
@@ -32,13 +32,10 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
-      - name: Enter RC mode (if not already in RC mode)
+      - name: Enter RC mode
         run: |
-          # ensure we’re in the right pre-mode (tag "rc")
-          if [ ! -f .changeset/pre.json ] \
-            || [ "$(jq -r '.tag' .changeset/pre.json 2>/dev/null || echo '')" != "rc" ]; then
-            npx changeset pre enter rc
-          fi
+          npx changeset pre exit || true
+          npx changeset pre enter rc
 
       - name: Version RC packages
         run: npx changeset version
@@ -54,9 +51,12 @@ jobs:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
 
+      - name: Exit RC mode
+        run: npx changeset pre exit
+
       - name: Commit & Push changes
         uses: actions-js/push@master
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           branch: ${{ github.ref }}
-          message: "chore: rc version bump"
+          message: 'chore: rc version bump'

.kiro/steering/test.md

@@ -0,0 +1,3 @@
+Testing rules that you can help me improve to see how it works<!------------------------------------------------------------------------------------
+Add Rules to this file or a short description and have Kiro refine them for you:  
+------------------------------------------------------------------------------------->

.taskmaster/docs/tm-core-phase-1.txt

@@ -1,343 +0,0 @@
-# Product Requirements Document: tm-core Package - Parse PRD Feature
-
-## Project Overview
-Create a TypeScript package named `tm-core` at `packages/tm-core` that implements parse-prd functionality using class-based architecture similar to the existing AI providers pattern.
-
-## Design Patterns & Architecture
-
-### Patterns to Apply
-1. **Factory Pattern**: Use for `ProviderFactory` to create AI provider instances
-2. **Strategy Pattern**: Use for `IAIProvider` implementations and `IStorage` implementations
-3. **Facade Pattern**: Use for `TaskMasterCore` as the main API entry point
-4. **Template Method Pattern**: Use for `BaseProvider` abstract class
-5. **Dependency Injection**: Use throughout for testability (pass dependencies via constructor)
-6. **Repository Pattern**: Use for `FileStorage` to abstract data persistence
-
-### Naming Conventions
-- **Files**: kebab-case (e.g., `task-parser.ts`, `file-storage.ts`)
-- **Classes**: PascalCase (e.g., `TaskParser`, `FileStorage`)
-- **Interfaces**: PascalCase with 'I' prefix (e.g., `IStorage`, `IAIProvider`)
-- **Methods**: camelCase (e.g., `parsePRD`, `loadTasks`)
-- **Constants**: UPPER_SNAKE_CASE (e.g., `DEFAULT_MODEL`)
-- **Type aliases**: PascalCase (e.g., `TaskStatus`, `ParseOptions`)
-
-## Exact Folder Structure Required
-```
-packages/tm-core/
-├── src/
-│   ├── index.ts
-│   ├── types/
-│   │   └── index.ts
-│   ├── interfaces/
-│   │   ├── index.ts              # Barrel export
-│   │   ├── storage.interface.ts
-│   │   ├── ai-provider.interface.ts
-│   │   └── configuration.interface.ts
-│   ├── tasks/
-│   │   ├── index.ts              # Barrel export
-│   │   └── task-parser.ts
-│   ├── ai/
-│   │   ├── index.ts              # Barrel export
-│   │   ├── base-provider.ts
-│   │   ├── provider-factory.ts
-│   │   ├── prompt-builder.ts
-│   │   └── providers/
-│   │       ├── index.ts          # Barrel export
-│   │       ├── anthropic-provider.ts
-│   │       ├── openai-provider.ts
-│   │       └── google-provider.ts
-│   ├── storage/
-│   │   ├── index.ts              # Barrel export
-│   │   └── file-storage.ts
-│   ├── config/
-│   │   ├── index.ts              # Barrel export
-│   │   └── config-manager.ts
-│   ├── utils/
-│   │   ├── index.ts              # Barrel export
-│   │   └── id-generator.ts
-│   └── errors/
-│       ├── index.ts              # Barrel export
-│       └── task-master-error.ts
-├── tests/
-│   ├── task-parser.test.ts
-│   ├── integration/
-│   │   └── parse-prd.test.ts
-│   └── mocks/
-│       └── mock-provider.ts
-├── package.json
-├── tsconfig.json
-├── tsup.config.js
-└── jest.config.js
-```
-
-## Specific Implementation Requirements
-
-### 1. Create types/index.ts
-Define these exact TypeScript interfaces:
-- `Task` interface with fields: id, title, description, status, priority, complexity, dependencies, subtasks, metadata, createdAt, updatedAt, source
-- `Subtask` interface with fields: id, title, description, completed
-- `TaskMetadata` interface with fields: parsedFrom, aiProvider, version, tags (optional)
-- Type literals: `TaskStatus` = 'pending' | 'in-progress' | 'completed' | 'blocked'
-- Type literals: `TaskPriority` = 'low' | 'medium' | 'high' | 'critical'
-- Type literals: `TaskComplexity` = 'simple' | 'moderate' | 'complex'
-- `ParseOptions` interface with fields: dryRun (optional), additionalContext (optional), tag (optional), maxTasks (optional)
-
-### 2. Create interfaces/storage.interface.ts
-Define `IStorage` interface with these exact methods:
-- `loadTasks(tag?: string): Promise<Task[]>`
-- `saveTasks(tasks: Task[], tag?: string): Promise<void>`
-- `appendTasks(tasks: Task[], tag?: string): Promise<void>`
-- `updateTask(id: string, task: Partial<Task>, tag?: string): Promise<void>`
-- `deleteTask(id: string, tag?: string): Promise<void>`
-- `exists(tag?: string): Promise<boolean>`
-
-### 3. Create interfaces/ai-provider.interface.ts
-Define `IAIProvider` interface with these exact methods:
-- `generateCompletion(prompt: string, options?: AIOptions): Promise<string>`
-- `calculateTokens(text: string): number`
-- `getName(): string`
-- `getModel(): string`
-
-Define `AIOptions` interface with fields: temperature (optional), maxTokens (optional), systemPrompt (optional)
-
-### 4. Create interfaces/configuration.interface.ts
-Define `IConfiguration` interface with fields:
-- `projectPath: string`
-- `aiProvider: string`
-- `apiKey?: string`
-- `aiOptions?: AIOptions`
-- `mainModel?: string`
-- `researchModel?: string`
-- `fallbackModel?: string`
-- `tasksPath?: string`
-- `enableTags?: boolean`
-
-### 5. Create tasks/task-parser.ts
-Create class `TaskParser` with:
-- Constructor accepting `aiProvider: IAIProvider` and `config: IConfiguration`
-- Private property `promptBuilder: PromptBuilder`
-- Public method `parsePRD(prdPath: string, options: ParseOptions = {}): Promise<Task[]>`
-- Private method `readPRD(prdPath: string): Promise<string>`
-- Private method `extractTasks(aiResponse: string): Partial<Task>[]`
-- Private method `enrichTasks(rawTasks: Partial<Task>[], prdPath: string): Task[]`
-- Apply **Dependency Injection** pattern via constructor
-
-### 6. Create ai/base-provider.ts
-Copy existing base-provider.js and convert to TypeScript abstract class:
-- Abstract class `BaseProvider` implementing `IAIProvider`
-- Protected properties: `apiKey: string`, `model: string`
-- Constructor accepting `apiKey: string` and `options: { model?: string }`
-- Abstract methods matching IAIProvider interface
-- Abstract method `getDefaultModel(): string`
-- Apply **Template Method** pattern for common provider logic
-
-### 7. Create ai/provider-factory.ts
-Create class `ProviderFactory` with:
-- Static method `create(config: { provider: string; apiKey?: string; model?: string }): Promise<IAIProvider>`
-- Switch statement for providers: 'anthropic', 'openai', 'google'
-- Dynamic imports for each provider
-- Throw error for unknown providers
-- Apply **Factory** pattern for creating provider instances
-
-Example implementation structure:
-```typescript
-switch (provider.toLowerCase()) {
-  case 'anthropic':
-    const { AnthropicProvider } = await import('./providers/anthropic-provider.js');
-    return new AnthropicProvider(apiKey, { model });
-}
-```
-
-### 8. Create ai/providers/anthropic-provider.ts
-Create class `AnthropicProvider` extending `BaseProvider`:
-- Import Anthropic SDK: `import { Anthropic } from '@anthropic-ai/sdk'`
-- Private property `client: Anthropic`
-- Implement all abstract methods from BaseProvider
-- Default model: 'claude-3-sonnet-20240229'
-- Handle API errors and wrap with meaningful messages
-
-### 9. Create ai/providers/openai-provider.ts (placeholder)
-Create class `OpenAIProvider` extending `BaseProvider`:
-- Import OpenAI SDK when implemented
-- For now, throw error: "OpenAI provider not yet implemented"
-
-### 10. Create ai/providers/google-provider.ts (placeholder)
-Create class `GoogleProvider` extending `BaseProvider`:
-- Import Google Generative AI SDK when implemented
-- For now, throw error: "Google provider not yet implemented"
-
-### 11. Create ai/prompt-builder.ts
-Create class `PromptBuilder` with:
-- Method `buildParsePrompt(prdContent: string, options: ParseOptions = {}): string`
-- Method `buildExpandPrompt(task: string, context?: string): string`
-- Use template literals for prompt construction
-- Include specific JSON format instructions in prompts
-
-### 9. Create storage/file-storage.ts
-Create class `FileStorage` implementing `IStorage`:
-- Private property `basePath: string` set to `{projectPath}/.taskmaster`
-- Constructor accepting `projectPath: string`
-- Private method `getTasksPath(tag?: string): string` returning correct path based on tag
-- Private method `ensureDirectory(dir: string): Promise<void>`
-- Implement all IStorage methods
-- Handle ENOENT errors by returning empty arrays
-- Use JSON format with structure: `{ tasks: Task[], metadata: { version: string, lastModified: string } }`
-- Apply **Repository** pattern for data access abstraction
-
-### 10. Create config/config-manager.ts
-Create class `ConfigManager`:
-- Private property `config: IConfiguration`
-- Constructor accepting `options: Partial<IConfiguration>`
-- Use Zod for validation with schema matching IConfiguration
-- Method `get<K extends keyof IConfiguration>(key: K): IConfiguration[K]`
-- Method `getAll(): IConfiguration`
-- Method `validate(): boolean`
-- Default values: projectPath = process.cwd(), aiProvider = 'anthropic', enableTags = true
-
-### 11. Create utils/id-generator.ts
-Export functions:
-- `generateTaskId(index: number = 0): string` returning format `task_{timestamp}_{index}_{random}`
-- `generateSubtaskId(parentId: string, index: number = 0): string` returning format `{parentId}_sub_{index}_{random}`
-
-### 16. Create src/index.ts
-Create main class `TaskMasterCore`:
-- Private properties: `config: ConfigManager`, `storage: IStorage`, `aiProvider?: IAIProvider`, `parser?: TaskParser`
-- Constructor accepting `options: Partial<IConfiguration>`
-- Method `initialize(): Promise<void>` for lazy loading
-- Method `parsePRD(prdPath: string, options: ParseOptions = {}): Promise<Task[]>`
-- Method `getTasks(tag?: string): Promise<Task[]>`
-- Apply **Facade** pattern to provide simple API over complex subsystems
-
-Export:
-- Class `TaskMasterCore`
-- Function `createTaskMaster(options: Partial<IConfiguration>): TaskMasterCore`
-- All types from './types'
-- All interfaces from './interfaces/*'
-
-Import statements should use kebab-case:
-```typescript
-import { TaskParser } from './tasks/task-parser';
-import { FileStorage } from './storage/file-storage';
-import { ConfigManager } from './config/config-manager';
-import { ProviderFactory } from './ai/provider-factory';
-```
-
-### 17. Configure package.json
-Create package.json with:
-- name: "@task-master/core"
-- version: "0.1.0"
-- type: "module"
-- main: "./dist/index.js"
-- module: "./dist/index.mjs"
-- types: "./dist/index.d.ts"
-- exports map for proper ESM/CJS support
-- scripts: build (tsup), dev (tsup --watch), test (jest), typecheck (tsc --noEmit)
-- dependencies: zod@^3.23.8
-- peerDependencies: @anthropic-ai/sdk, openai, @google/generative-ai
-- devDependencies: typescript, tsup, jest, ts-jest, @types/node, @types/jest
-
-### 18. Configure TypeScript
-Create tsconfig.json with:
-- target: "ES2022"
-- module: "ESNext"
-- strict: true (with all strict flags enabled)
-- declaration: true
-- outDir: "./dist"
-- rootDir: "./src"
-
-### 19. Configure tsup
-Create tsup.config.js with:
-- entry: ['src/index.ts']
-- format: ['cjs', 'esm']
-- dts: true
-- sourcemap: true
-- clean: true
-- external: AI provider SDKs
-
-### 20. Configure Jest
-Create jest.config.js with:
-- preset: 'ts-jest'
-- testEnvironment: 'node'
-- Coverage threshold: 80% for all metrics
-
-## Build Process
-1. Use tsup to compile TypeScript to both CommonJS and ESM
-2. Generate .d.ts files for TypeScript consumers
-3. Output to dist/ directory
-4. Ensure tree-shaking works properly
-
-## Testing Requirements
-- Create unit tests for TaskParser in tests/task-parser.test.ts
-- Create MockProvider class in tests/mocks/mock-provider.ts for testing without API calls
-- Test error scenarios (file not found, invalid JSON, etc.)
-- Create integration test in tests/integration/parse-prd.test.ts
-- Follow kebab-case naming for all test files
-
-## Success Criteria
-- TypeScript compilation with zero errors
-- No use of 'any' type
-- All interfaces properly exported
-- Compatible with existing tasks.json format
-- Feature flag support via USE_TM_CORE environment variable
-
-## Import/Export Conventions
-- Use named exports for all classes and interfaces
-- Use barrel exports (index.ts) in each directory
-- Import types/interfaces with type-only imports: `import type { Task } from '../types'`
-- Group imports in order: Node built-ins, external packages, internal packages, relative imports
-- Use .js extension in import paths for ESM compatibility
-
-## Error Handling Patterns
-- Create custom error classes in `src/errors/` directory
-- All public methods should catch and wrap errors with context
-- Use error codes for different error types (e.g., 'FILE_NOT_FOUND', 'PARSE_ERROR')
-- Never expose internal implementation details in error messages
-- Log errors to console.error only in development mode
-
-## Barrel Exports Content
-
-### interfaces/index.ts
-```typescript
-export type { IStorage } from './storage.interface';
-export type { IAIProvider, AIOptions } from './ai-provider.interface';
-export type { IConfiguration } from './configuration.interface';
-```
-
-### tasks/index.ts
-```typescript
-export { TaskParser } from './task-parser';
-```
-
-### ai/index.ts
-```typescript
-export { BaseProvider } from './base-provider';
-export { ProviderFactory } from './provider-factory';
-export { PromptBuilder } from './prompt-builder';
-```
-
-### ai/providers/index.ts
-```typescript
-export { AnthropicProvider } from './anthropic-provider';
-export { OpenAIProvider } from './openai-provider';
-export { GoogleProvider } from './google-provider';
-```
-
-### storage/index.ts
-```typescript
-export { FileStorage } from './file-storage';
-```
-
-### config/index.ts
-```typescript
-export { ConfigManager } from './config-manager';
-```
-
-### utils/index.ts
-```typescript
-export { generateTaskId, generateSubtaskId } from './id-generator';
-```
-
-### errors/index.ts
-```typescript
-export { TaskMasterError } from './task-master-error';
-```

CHANGELOG.md

@@ -1,44 +1,5 @@
 # task-master-ai
 
-## 0.22.0-rc.0
-
-### Minor Changes
-
-- [#1032](https://github.com/eyaltoledano/claude-task-master/pull/1032) [`4423119`](https://github.com/eyaltoledano/claude-task-master/commit/4423119a5ec53958c9dffa8bf564da8be7a2827d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add comprehensive Kiro IDE integration with autonomous task management hooks
-  - **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
-  - **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
-  - **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
-  - **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
-  - **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
-  - **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
-
-  Key hooks included:
-  - Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
-  - Code Change Task Tracker: Updates task progress as you save files
-  - Test Success Task Completer: Marks tasks done when tests pass
-  - Daily Standup Assistant: Provides personalized task status summaries
-  - PR Readiness Checker: Validates task completion before creating pull requests
-  - Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
-  - Git Commit Task Linker: Links commits to tasks for better traceability
-
-  This creates a truly autonomous development workflow where task management happens naturally as you code!
-
-### Patch Changes
-
-- [#1033](https://github.com/eyaltoledano/claude-task-master/pull/1033) [`7b90568`](https://github.com/eyaltoledano/claude-task-master/commit/7b9056832653464f934c91c22997077065d738c4) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.
-
-- [#1038](https://github.com/eyaltoledano/claude-task-master/pull/1038) [`77cc5e4`](https://github.com/eyaltoledano/claude-task-master/commit/77cc5e4537397642f2664f61940a101433ee6fb4) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.
-
-- [#1025](https://github.com/eyaltoledano/claude-task-master/pull/1025) [`8781794`](https://github.com/eyaltoledano/claude-task-master/commit/8781794c56d454697fc92c88a3925982d6b81205) Thanks [@joedanz](https://github.com/joedanz)! - Clean up remaining automatic task file generation calls
-
-- [#1035](https://github.com/eyaltoledano/claude-task-master/pull/1035) [`fb7d588`](https://github.com/eyaltoledano/claude-task-master/commit/fb7d588137e8c53b0d0f54bd1dd8d387648583ee) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens limits for OpenRouter and Groq models
-  - Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
-  - Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
-  - Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
-  - This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list
-
-- [#1027](https://github.com/eyaltoledano/claude-task-master/pull/1027) [`6ae66b2`](https://github.com/eyaltoledano/claude-task-master/commit/6ae66b2afbfe911340fa25e0236c3db83deaa7eb) Thanks [@andreswebs](https://github.com/andreswebs)! - Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).
-
 ## 0.21.0
 
 ### Minor Changes

docs/models.md

@@ -1,4 +1,4 @@
-# Available Models as of July 23, 2025
+# Available Models as of July 19, 2025
 
 ## Main Models
 
@@ -48,6 +48,7 @@
 | openrouter  | google/gemini-2.5-flash-preview-05-20          | —         | 0.15       | 0.6         |
 | openrouter  | google/gemini-2.5-flash-preview-05-20:thinking | —         | 0.15       | 3.5         |
 | openrouter  | google/gemini-2.5-pro-exp-03-25                | —         | 0          | 0           |
+| openrouter  | deepseek/deepseek-chat-v3-0324:free            | —         | 0          | 0           |
 | openrouter  | deepseek/deepseek-chat-v3-0324                 | —         | 0.27       | 1.1         |
 | openrouter  | openai/gpt-4.1                                 | —         | 2          | 8           |
 | openrouter  | openai/gpt-4.1-mini                            | —         | 0.4        | 1.6         |
@@ -64,9 +65,11 @@
 | openrouter  | qwen/qwen-max                                  | —         | 1.6        | 6.4         |
 | openrouter  | qwen/qwen-turbo                                | —         | 0.05       | 0.2         |
 | openrouter  | qwen/qwen3-235b-a22b                           | —         | 0.14       | 2           |
+| openrouter  | mistralai/mistral-small-3.1-24b-instruct:free  | —         | 0          | 0           |
 | openrouter  | mistralai/mistral-small-3.1-24b-instruct       | —         | 0.1        | 0.3         |
 | openrouter  | mistralai/devstral-small                       | —         | 0.1        | 0.3         |
 | openrouter  | mistralai/mistral-nemo                         | —         | 0.03       | 0.07        |
+| openrouter  | thudm/glm-4-32b:free                           | —         | 0          | 0           |
 | ollama      | devstral:latest                                | —         | 0          | 0           |
 | ollama      | qwen3:latest                                   | —         | 0          | 0           |
 | ollama      | qwen3:14b                                      | —         | 0          | 0           |
@@ -155,6 +158,7 @@
 | openrouter  | google/gemini-2.5-flash-preview-05-20          | —         | 0.15       | 0.6         |
 | openrouter  | google/gemini-2.5-flash-preview-05-20:thinking | —         | 0.15       | 3.5         |
 | openrouter  | google/gemini-2.5-pro-exp-03-25                | —         | 0          | 0           |
+| openrouter  | deepseek/deepseek-chat-v3-0324:free            | —         | 0          | 0           |
 | openrouter  | openai/gpt-4.1                                 | —         | 2          | 8           |
 | openrouter  | openai/gpt-4.1-mini                            | —         | 0.4        | 1.6         |
 | openrouter  | openai/gpt-4.1-nano                            | —         | 0.1        | 0.4         |
@@ -170,8 +174,10 @@
 | openrouter  | qwen/qwen-max                                  | —         | 1.6        | 6.4         |
 | openrouter  | qwen/qwen-turbo                                | —         | 0.05       | 0.2         |
 | openrouter  | qwen/qwen3-235b-a22b                           | —         | 0.14       | 2           |
+| openrouter  | mistralai/mistral-small-3.1-24b-instruct:free  | —         | 0          | 0           |
 | openrouter  | mistralai/mistral-small-3.1-24b-instruct       | —         | 0.1        | 0.3         |
 | openrouter  | mistralai/mistral-nemo                         | —         | 0.03       | 0.07        |
+| openrouter  | thudm/glm-4-32b:free                           | —         | 0          | 0           |
 | ollama      | devstral:latest                                | —         | 0          | 0           |
 | ollama      | qwen3:latest                                   | —         | 0          | 0           |
 | ollama      | qwen3:14b                                      | —         | 0          | 0           |
@@ -190,11 +196,3 @@
 | bedrock     | us.anthropic.claude-3-5-haiku-20241022-v1:0    | 0.4       | 0.8        | 4           |
 | bedrock     | us.anthropic.claude-opus-4-20250514-v1:0       | 0.725     | 15         | 75          |
 | bedrock     | us.anthropic.claude-sonnet-4-20250514-v1:0     | 0.727     | 3          | 15          |
-
-## Unsupported Models
-
-| Provider   | Model Name                                    | Reason                                                                                                                                                                    |
-| ---------- | --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| openrouter | deepseek/deepseek-chat-v3-0324:free           | Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use. |
-| openrouter | mistralai/mistral-small-3.1-24b-instruct:free | Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use. |
-| openrouter | thudm/glm-4-32b:free                          | Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use. |

docs/scripts/models-json-to-markdown.js

@@ -47,20 +47,6 @@ function generateMarkdownTable(title, models) {
 	return table;
 }
 
-function generateUnsupportedTable(models) {
-	if (!models || models.length === 0) {
-		return '## Unsupported Models\n\nNo unsupported models found.\n\n';
-	}
-	let table = '## Unsupported Models\n\n';
-	table += '| Provider | Model Name | Reason |\n';
-	table += '|---|---|---|\n';
-	models.forEach((model) => {
-		table += `| ${model.provider} | ${model.modelName} | ${model.reason || '—'} |\n`;
-	});
-	table += '\n';
-	return table;
-}
-
 function main() {
 	try {
 		const correctSupportedModelsPath = path.join(
@@ -82,46 +68,31 @@ function main() {
 		const mainModels = [];
 		const researchModels = [];
 		const fallbackModels = [];
-		const unsupportedModels = [];
 
 		for (const provider in supportedModels) {
 			if (Object.hasOwnProperty.call(supportedModels, provider)) {
 				const models = supportedModels[provider];
 				models.forEach((model) => {
-					const isSupported = model.supported !== false; // default to true if missing
-					if (isSupported) {
-						const modelEntry = {
-							provider: provider,
-							modelName: model.id,
-							sweScore: model.swe_score,
-							inputCost: model.cost_per_1m_tokens
-								? model.cost_per_1m_tokens.input
-								: null,
-							outputCost: model.cost_per_1m_tokens
-								? model.cost_per_1m_tokens.output
-								: null
-						};
-						if (model.allowed_roles && model.allowed_roles.includes('main')) {
-							mainModels.push(modelEntry);
-						}
-						if (
-							model.allowed_roles &&
-							model.allowed_roles.includes('research')
-						) {
-							researchModels.push(modelEntry);
-						}
-						if (
-							model.allowed_roles &&
-							model.allowed_roles.includes('fallback')
-						) {
-							fallbackModels.push(modelEntry);
-						}
-					} else {
-						unsupportedModels.push({
-							provider: provider,
-							modelName: model.id,
-							reason: model.reason || 'Not specified'
-						});
+					const modelEntry = {
+						provider: provider,
+						modelName: model.id,
+						sweScore: model.swe_score,
+						inputCost: model.cost_per_1m_tokens
+							? model.cost_per_1m_tokens.input
+							: null,
+						outputCost: model.cost_per_1m_tokens
+							? model.cost_per_1m_tokens.output
+							: null
+					};
+
+					if (model.allowed_roles.includes('main')) {
+						mainModels.push(modelEntry);
+					}
+					if (model.allowed_roles.includes('research')) {
+						researchModels.push(modelEntry);
+					}
+					if (model.allowed_roles.includes('fallback')) {
+						fallbackModels.push(modelEntry);
 					}
 				});
 			}
@@ -148,7 +119,6 @@ function main() {
 		markdownContent += generateMarkdownTable('Main Models', mainModels);
 		markdownContent += generateMarkdownTable('Research Models', researchModels);
 		markdownContent += generateMarkdownTable('Fallback Models', fallbackModels);
-		markdownContent += generateUnsupportedTable(unsupportedModels);
 
 		fs.writeFileSync(correctOutputMarkdownPath, markdownContent, 'utf8');
 		console.log(`Successfully updated ${correctOutputMarkdownPath}`);

package-lock.json

@@ -81,7 +81,7 @@
 			"optionalDependencies": {
 				"@anthropic-ai/claude-code": "^1.0.25",
 				"@biomejs/cli-linux-x64": "^1.9.4",
-				"ai-sdk-provider-gemini-cli": "^0.1.1"
+				"ai-sdk-provider-gemini-cli": "^0.0.4"
 			}
 		},
 		"apps/extension": {
@@ -2065,12 +2065,12 @@
 			}
 		},
 		"node_modules/@google/gemini-cli-core": {
-			"version": "0.1.13",
-			"resolved": "https://registry.npmjs.org/@google/gemini-cli-core/-/gemini-cli-core-0.1.13.tgz",
-			"integrity": "sha512-Vx3CbRpLJiGs/sj4SXlGH2ALKyON5skV/p+SCAoRuS6yRsANS1+diEeXbp6jlWT2TTiGoa8+GolqeNIU7wbN8w==",
+			"version": "0.1.9",
+			"resolved": "https://registry.npmjs.org/@google/gemini-cli-core/-/gemini-cli-core-0.1.9.tgz",
+			"integrity": "sha512-NFmu0qivppBZ3JT6to0A2+tEtcvWcWuhbfyTz42Wm2AoAtl941lTbcd/TiBryK0yWz3WCkqukuDxl+L7axLpvA==",
 			"optional": true,
 			"dependencies": {
-				"@google/genai": "1.9.0",
+				"@google/genai": "^1.4.0",
 				"@modelcontextprotocol/sdk": "^1.11.0",
 				"@opentelemetry/api": "^1.9.0",
 				"@opentelemetry/exporter-logs-otlp-grpc": "^0.52.0",
@@ -2080,46 +2080,23 @@
 				"@opentelemetry/sdk-node": "^0.52.0",
 				"@types/glob": "^8.1.0",
 				"@types/html-to-text": "^9.0.4",
-				"ajv": "^8.17.1",
 				"diff": "^7.0.0",
-				"dotenv": "^17.1.0",
+				"dotenv": "^16.6.1",
+				"gaxios": "^6.1.1",
 				"glob": "^10.4.5",
 				"google-auth-library": "^9.11.0",
 				"html-to-text": "^9.0.5",
-				"https-proxy-agent": "^7.0.6",
 				"ignore": "^7.0.0",
 				"micromatch": "^4.0.8",
 				"open": "^10.1.2",
-				"shell-quote": "^1.8.3",
+				"shell-quote": "^1.8.2",
 				"simple-git": "^3.28.0",
 				"strip-ansi": "^7.1.0",
 				"undici": "^7.10.0",
 				"ws": "^8.18.0"
 			},
 			"engines": {
-				"node": ">=20"
-			}
-		},
-		"node_modules/@google/gemini-cli-core/node_modules/@google/genai": {
-			"version": "1.9.0",
-			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.9.0.tgz",
-			"integrity": "sha512-w9P93OXKPMs9H1mfAx9+p3zJqQGrWBGdvK/SVc7cLZEXNHr/3+vW2eif7ZShA6wU24rNLn9z9MK2vQFUvNRI2Q==",
-			"license": "Apache-2.0",
-			"optional": true,
-			"dependencies": {
-				"google-auth-library": "^9.14.2",
-				"ws": "^8.18.0"
-			},
-			"engines": {
-				"node": ">=20.0.0"
-			},
-			"peerDependencies": {
-				"@modelcontextprotocol/sdk": "^1.11.0"
-			},
-			"peerDependenciesMeta": {
-				"@modelcontextprotocol/sdk": {
-					"optional": true
-				}
+				"node": ">=18"
 			}
 		},
 		"node_modules/@google/gemini-cli-core/node_modules/ansi-regex": {
@@ -2145,19 +2122,6 @@
 				"balanced-match": "^1.0.0"
 			}
 		},
-		"node_modules/@google/gemini-cli-core/node_modules/dotenv": {
-			"version": "17.2.0",
-			"resolved": "https://registry.npmjs.org/dotenv/-/dotenv-17.2.0.tgz",
-			"integrity": "sha512-Q4sgBT60gzd0BB0lSyYD3xM4YxrXA9y4uBDof1JNYGzOXrQdQ6yX+7XIAqoFOGQFOTK1D3Hts5OllpxMDZFONQ==",
-			"license": "BSD-2-Clause",
-			"optional": true,
-			"engines": {
-				"node": ">=12"
-			},
-			"funding": {
-				"url": "https://dotenvx.com"
-			}
-		},
 		"node_modules/@google/gemini-cli-core/node_modules/glob": {
 			"version": "10.4.5",
 			"resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
@@ -2222,14 +2186,16 @@
 			}
 		},
 		"node_modules/@google/genai": {
-			"version": "1.10.0",
-			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.10.0.tgz",
-			"integrity": "sha512-PR4tLuiIFMrpAiiCko2Z16ydikFsPF1c5TBfI64hlZcv3xBEApSCceLuDYu1pNMq2SkNh4r66J4AG+ZexBnMLw==",
+			"version": "1.8.0",
+			"resolved": "https://registry.npmjs.org/@google/genai/-/genai-1.8.0.tgz",
+			"integrity": "sha512-n3KiMFesQCy2R9iSdBIuJ0JWYQ1HZBJJkmt4PPZMGZKvlgHhBAGw1kUMyX+vsAIzprN3lK45DI755lm70wPOOg==",
 			"license": "Apache-2.0",
 			"optional": true,
 			"dependencies": {
 				"google-auth-library": "^9.14.2",
-				"ws": "^8.18.0"
+				"ws": "^8.18.0",
+				"zod": "^3.22.4",
+				"zod-to-json-schema": "^3.22.4"
 			},
 			"engines": {
 				"node": ">=20.0.0"
@@ -5457,15 +5423,15 @@
 			}
 		},
 		"node_modules/ai-sdk-provider-gemini-cli": {
-			"version": "0.1.1",
-			"resolved": "https://registry.npmjs.org/ai-sdk-provider-gemini-cli/-/ai-sdk-provider-gemini-cli-0.1.1.tgz",
-			"integrity": "sha512-fvX3n9jTt8JaTyc+qDv5Og0H4NQMpS6B1VdaTT71AN2F+3u2Bz9/OSd7ATokrV2Rmv+ZlEnUCmJnke58zHXUSQ==",
+			"version": "0.0.4",
+			"resolved": "https://registry.npmjs.org/ai-sdk-provider-gemini-cli/-/ai-sdk-provider-gemini-cli-0.0.4.tgz",
+			"integrity": "sha512-rXxNM/+wVHL8Syf/SjyoVmFJgTMwLnVSPPhqkLzbP6JKBvp81qZfkBFQiI9l6VMF1ctb6L+iSdVNd0/G1pTVZg==",
 			"license": "MIT",
 			"optional": true,
 			"dependencies": {
 				"@ai-sdk/provider": "^1.1.3",
 				"@ai-sdk/provider-utils": "^2.2.8",
-				"@google/gemini-cli-core": "^0.1.13",
+				"@google/gemini-cli-core": "^0.1.4",
 				"@google/genai": "^1.7.0",
 				"google-auth-library": "^9.0.0",
 				"zod": "^3.23.8",
@@ -11270,16 +11236,16 @@
 			}
 		},
 		"node_modules/open": {
-			"version": "10.2.0",
-			"resolved": "https://registry.npmjs.org/open/-/open-10.2.0.tgz",
-			"integrity": "sha512-YgBpdJHPyQ2UE5x+hlSXcnejzAvD0b22U2OuAP+8OnlJT+PjWPxtgmGqKKc+RgTM63U9gN0YzrYc71R2WT/hTA==",
+			"version": "10.1.2",
+			"resolved": "https://registry.npmjs.org/open/-/open-10.1.2.tgz",
+			"integrity": "sha512-cxN6aIDPz6rm8hbebcP7vrQNhvRcveZoJU72Y7vskh4oIm+BZwBECnx5nTmrlres1Qapvx27Qo1Auukpf8PKXw==",
 			"license": "MIT",
 			"optional": true,
 			"dependencies": {
 				"default-browser": "^5.2.1",
 				"define-lazy-prop": "^3.0.0",
 				"is-inside-container": "^1.0.0",
-				"wsl-utils": "^0.1.0"
+				"is-wsl": "^3.1.0"
 			},
 			"engines": {
 				"node": ">=18"
@@ -13656,22 +13622,6 @@
 				}
 			}
 		},
-		"node_modules/wsl-utils": {
-			"version": "0.1.0",
-			"resolved": "https://registry.npmjs.org/wsl-utils/-/wsl-utils-0.1.0.tgz",
-			"integrity": "sha512-h3Fbisa2nKGPxCpm89Hk33lBLsnaGBvctQopaBSOW/uIs6FTe1ATyAnKFJrzVs9vpGdsTe73WF3V4lIsk4Gacw==",
-			"license": "MIT",
-			"optional": true,
-			"dependencies": {
-				"is-wsl": "^3.1.0"
-			},
-			"engines": {
-				"node": ">=18"
-			},
-			"funding": {
-				"url": "https://github.com/sponsors/sindresorhus"
-			}
-		},
 		"node_modules/xsschema": {
 			"version": "0.3.0-beta.8",
 			"resolved": "https://registry.npmjs.org/xsschema/-/xsschema-0.3.0-beta.8.tgz",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "task-master-ai",
-	"version": "0.22.0-rc.0",
+	"version": "0.21.0",
 	"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
 	"main": "index.js",
 	"type": "module",
@@ -84,8 +84,8 @@
 	},
 	"optionalDependencies": {
 		"@anthropic-ai/claude-code": "^1.0.25",
-		"@biomejs/cli-linux-x64": "^1.9.4",
-		"ai-sdk-provider-gemini-cli": "^0.1.1"
+		"ai-sdk-provider-gemini-cli": "^0.0.4",
+		"@biomejs/cli-linux-x64": "^1.9.4"
 	},
 	"engines": {
 		"node": ">=18.0.0"

scripts/modules/config-manager.js

@@ -584,21 +584,10 @@ function getParametersForRole(role, explicitRoot = null) {
 				);
 			}
 		} else {
-			// Special handling for custom OpenRouter models
-			if (providerName === CUSTOM_PROVIDERS.OPENROUTER) {
-				// Use a conservative default for OpenRouter models not in our list
-				const openrouterDefault = 32768;
-				effectiveMaxTokens = Math.min(roleMaxTokens, openrouterDefault);
-				log(
-					'debug',
-					`Custom OpenRouter model ${modelId} detected. Using conservative max_tokens: ${effectiveMaxTokens}`
-				);
-			} else {
-				log(
-					'debug',
-					`No model definitions found for provider ${providerName} in MODEL_MAP. Using role default maxTokens: ${roleMaxTokens}`
-				);
-			}
+			log(
+				'debug',
+				`No model definitions found for provider ${providerName} in MODEL_MAP. Using role default maxTokens: ${roleMaxTokens}`
+			);
 		}
 	} catch (lookupError) {
 		log(
@@ -783,38 +772,36 @@ function getAvailableModels() {
 	const available = [];
 	for (const [provider, models] of Object.entries(MODEL_MAP)) {
 		if (models.length > 0) {
-			models
-				.filter((modelObj) => Boolean(modelObj.supported))
-				.forEach((modelObj) => {
-					// Basic name generation - can be improved
-					const modelId = modelObj.id;
-					const sweScore = modelObj.swe_score;
-					const cost = modelObj.cost_per_1m_tokens;
-					const allowedRoles = modelObj.allowed_roles || ['main', 'fallback'];
-					const nameParts = modelId
-						.split('-')
-						.map((p) => p.charAt(0).toUpperCase() + p.slice(1));
-					// Handle specific known names better if needed
-					let name = nameParts.join(' ');
-					if (modelId === 'claude-3.5-sonnet-20240620')
-						name = 'Claude 3.5 Sonnet';
-					if (modelId === 'claude-3-7-sonnet-20250219')
-						name = 'Claude 3.7 Sonnet';
-					if (modelId === 'gpt-4o') name = 'GPT-4o';
-					if (modelId === 'gpt-4-turbo') name = 'GPT-4 Turbo';
-					if (modelId === 'sonar-pro') name = 'Perplexity Sonar Pro';
-					if (modelId === 'sonar-mini') name = 'Perplexity Sonar Mini';
+			models.forEach((modelObj) => {
+				// Basic name generation - can be improved
+				const modelId = modelObj.id;
+				const sweScore = modelObj.swe_score;
+				const cost = modelObj.cost_per_1m_tokens;
+				const allowedRoles = modelObj.allowed_roles || ['main', 'fallback'];
+				const nameParts = modelId
+					.split('-')
+					.map((p) => p.charAt(0).toUpperCase() + p.slice(1));
+				// Handle specific known names better if needed
+				let name = nameParts.join(' ');
+				if (modelId === 'claude-3.5-sonnet-20240620')
+					name = 'Claude 3.5 Sonnet';
+				if (modelId === 'claude-3-7-sonnet-20250219')
+					name = 'Claude 3.7 Sonnet';
+				if (modelId === 'gpt-4o') name = 'GPT-4o';
+				if (modelId === 'gpt-4-turbo') name = 'GPT-4 Turbo';
+				if (modelId === 'sonar-pro') name = 'Perplexity Sonar Pro';
+				if (modelId === 'sonar-mini') name = 'Perplexity Sonar Mini';
 
-					available.push({
-						id: modelId,
-						name: name,
-						provider: provider,
-						swe_score: sweScore,
-						cost_per_1m_tokens: cost,
-						allowed_roles: allowedRoles,
-						max_tokens: modelObj.max_tokens
-					});
+				available.push({
+					id: modelId,
+					name: name,
+					provider: provider,
+					swe_score: sweScore,
+					cost_per_1m_tokens: cost,
+					allowed_roles: allowedRoles,
+					max_tokens: modelObj.max_tokens
 				});
+			});
 		} else {
 			// For providers with empty lists (like ollama), maybe add a placeholder or skip
 			available.push({

scripts/modules/supported-models.json

@@ -8,8 +8,7 @@
 				"output": 15.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 64000,
-			"supported": true
+			"max_tokens": 64000
 		},
 		{
 			"id": "claude-opus-4-20250514",
@@ -19,8 +18,7 @@
 				"output": 75.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32000,
-			"supported": true
+			"max_tokens": 32000
 		},
 		{
 			"id": "claude-3-7-sonnet-20250219",
@@ -30,8 +28,7 @@
 				"output": 15.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 120000,
-			"supported": true
+			"max_tokens": 120000
 		},
 		{
 			"id": "claude-3-5-sonnet-20241022",
@@ -41,8 +38,7 @@
 				"output": 15.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 8192,
-			"supported": true
+			"max_tokens": 8192
 		}
 	],
 	"claude-code": [
@@ -54,8 +50,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32000,
-			"supported": true
+			"max_tokens": 32000
 		},
 		{
 			"id": "sonnet",
@@ -65,8 +60,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 64000,
-			"supported": true
+			"max_tokens": 64000
 		}
 	],
 	"mcp": [
@@ -78,8 +72,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		}
 	],
 	"gemini-cli": [
@@ -91,8 +84,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 65536,
-			"supported": true
+			"max_tokens": 65536
 		},
 		{
 			"id": "gemini-2.5-flash",
@@ -102,8 +94,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 65536,
-			"supported": true
+			"max_tokens": 65536
 		}
 	],
 	"openai": [
@@ -115,8 +106,7 @@
 				"output": 10.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384,
-			"supported": true
+			"max_tokens": 16384
 		},
 		{
 			"id": "o1",
@@ -125,8 +115,7 @@
 				"input": 15.0,
 				"output": 60.0
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "o3",
@@ -136,8 +125,7 @@
 				"output": 8.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "o3-mini",
@@ -147,8 +135,7 @@
 				"output": 4.4
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "o4-mini",
@@ -157,8 +144,7 @@
 				"input": 1.1,
 				"output": 4.4
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "o1-mini",
@@ -167,8 +153,7 @@
 				"input": 1.1,
 				"output": 4.4
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "o1-pro",
@@ -177,8 +162,7 @@
 				"input": 150.0,
 				"output": 600.0
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "gpt-4-5-preview",
@@ -187,8 +171,7 @@
 				"input": 75.0,
 				"output": 150.0
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "gpt-4-1-mini",
@@ -197,8 +180,7 @@
 				"input": 0.4,
 				"output": 1.6
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "gpt-4-1-nano",
@@ -207,8 +189,7 @@
 				"input": 0.1,
 				"output": 0.4
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "gpt-4o-mini",
@@ -217,8 +198,7 @@
 				"input": 0.15,
 				"output": 0.6
 			},
-			"allowed_roles": ["main"],
-			"supported": true
+			"allowed_roles": ["main"]
 		},
 		{
 			"id": "gpt-4o-search-preview",
@@ -227,8 +207,7 @@
 				"input": 2.5,
 				"output": 10.0
 			},
-			"allowed_roles": ["research"],
-			"supported": true
+			"allowed_roles": ["research"]
 		},
 		{
 			"id": "gpt-4o-mini-search-preview",
@@ -237,8 +216,7 @@
 				"input": 0.15,
 				"output": 0.6
 			},
-			"allowed_roles": ["research"],
-			"supported": true
+			"allowed_roles": ["research"]
 		}
 	],
 	"google": [
@@ -247,24 +225,21 @@
 			"swe_score": 0.638,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000,
-			"supported": true
+			"max_tokens": 1048000
 		},
 		{
 			"id": "gemini-2.5-pro-preview-03-25",
 			"swe_score": 0.638,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000,
-			"supported": true
+			"max_tokens": 1048000
 		},
 		{
 			"id": "gemini-2.5-flash-preview-04-17",
 			"swe_score": 0.604,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000,
-			"supported": true
+			"max_tokens": 1048000
 		},
 		{
 			"id": "gemini-2.0-flash",
@@ -274,16 +249,14 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000,
-			"supported": true
+			"max_tokens": 1048000
 		},
 		{
 			"id": "gemini-2.0-flash-lite",
 			"swe_score": 0,
 			"cost_per_1m_tokens": null,
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048000,
-			"supported": true
+			"max_tokens": 1048000
 		}
 	],
 	"xai": [
@@ -296,8 +269,7 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 131072,
-			"supported": true
+			"max_tokens": 131072
 		},
 		{
 			"id": "grok-3-fast",
@@ -308,8 +280,7 @@
 				"output": 25
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 131072,
-			"supported": true
+			"max_tokens": 131072
 		},
 		{
 			"id": "grok-4",
@@ -320,8 +291,7 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 131072,
-			"supported": true
+			"max_tokens": 131072
 		}
 	],
 	"groq": [
@@ -333,8 +303,7 @@
 				"output": 3.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384,
-			"supported": true
+			"max_tokens": 131072
 		},
 		{
 			"id": "llama-3.3-70b-versatile",
@@ -344,8 +313,7 @@
 				"output": 0.79
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 32768
 		},
 		{
 			"id": "llama-3.1-8b-instant",
@@ -355,8 +323,7 @@
 				"output": 0.08
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 131072,
-			"supported": true
+			"max_tokens": 131072
 		},
 		{
 			"id": "llama-4-scout",
@@ -366,8 +333,7 @@
 				"output": 0.34
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 32768
 		},
 		{
 			"id": "llama-4-maverick",
@@ -377,8 +343,7 @@
 				"output": 0.77
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 32768
 		},
 		{
 			"id": "mixtral-8x7b-32768",
@@ -388,8 +353,7 @@
 				"output": 0.24
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 32768
 		},
 		{
 			"id": "qwen-qwq-32b-preview",
@@ -399,8 +363,7 @@
 				"output": 0.18
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 32768
 		},
 		{
 			"id": "deepseek-r1-distill-llama-70b",
@@ -410,8 +373,7 @@
 				"output": 0.99
 			},
 			"allowed_roles": ["main", "research"],
-			"max_tokens": 8192,
-			"supported": true
+			"max_tokens": 8192
 		},
 		{
 			"id": "gemma2-9b-it",
@@ -421,8 +383,7 @@
 				"output": 0.2
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 8192,
-			"supported": true
+			"max_tokens": 8192
 		},
 		{
 			"id": "whisper-large-v3",
@@ -432,8 +393,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 0,
-			"supported": true
+			"max_tokens": 0
 		}
 	],
 	"perplexity": [
@@ -445,8 +405,7 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "research"],
-			"max_tokens": 8700,
-			"supported": true
+			"max_tokens": 8700
 		},
 		{
 			"id": "sonar",
@@ -456,8 +415,7 @@
 				"output": 1
 			},
 			"allowed_roles": ["research"],
-			"max_tokens": 8700,
-			"supported": true
+			"max_tokens": 8700
 		},
 		{
 			"id": "deep-research",
@@ -467,8 +425,7 @@
 				"output": 8
 			},
 			"allowed_roles": ["research"],
-			"max_tokens": 8700,
-			"supported": true
+			"max_tokens": 8700
 		},
 		{
 			"id": "sonar-reasoning-pro",
@@ -478,8 +435,7 @@
 				"output": 8
 			},
 			"allowed_roles": ["main", "research", "fallback"],
-			"max_tokens": 8700,
-			"supported": true
+			"max_tokens": 8700
 		},
 		{
 			"id": "sonar-reasoning",
@@ -489,8 +445,7 @@
 				"output": 5
 			},
 			"allowed_roles": ["main", "research", "fallback"],
-			"max_tokens": 8700,
-			"supported": true
+			"max_tokens": 8700
 		}
 	],
 	"openrouter": [
@@ -502,8 +457,7 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048576,
-			"supported": true
+			"max_tokens": 1048576
 		},
 		{
 			"id": "google/gemini-2.5-flash-preview-05-20:thinking",
@@ -513,8 +467,7 @@
 				"output": 3.5
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048576,
-			"supported": true
+			"max_tokens": 1048576
 		},
 		{
 			"id": "google/gemini-2.5-pro-exp-03-25",
@@ -524,8 +477,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "deepseek/deepseek-chat-v3-0324:free",
@@ -535,9 +487,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 163840,
-			"supported": false,
-			"reason": "Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use."
+			"max_tokens": 163840
 		},
 		{
 			"id": "deepseek/deepseek-chat-v3-0324",
@@ -547,8 +497,7 @@
 				"output": 1.1
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 64000,
-			"supported": true
+			"max_tokens": 64000
 		},
 		{
 			"id": "openai/gpt-4.1",
@@ -558,8 +507,7 @@
 				"output": 8
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "openai/gpt-4.1-mini",
@@ -569,8 +517,7 @@
 				"output": 1.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "openai/gpt-4.1-nano",
@@ -580,8 +527,7 @@
 				"output": 0.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "openai/o3",
@@ -591,8 +537,7 @@
 				"output": 40
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 200000,
-			"supported": true
+			"max_tokens": 200000
 		},
 		{
 			"id": "openai/codex-mini",
@@ -602,8 +547,7 @@
 				"output": 6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "openai/gpt-4o-mini",
@@ -613,8 +557,7 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "openai/o4-mini",
@@ -624,8 +567,7 @@
 				"output": 4.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "openai/o4-mini-high",
@@ -635,8 +577,7 @@
 				"output": 4.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "openai/o1-pro",
@@ -646,8 +587,7 @@
 				"output": 600
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "meta-llama/llama-3.3-70b-instruct",
@@ -657,8 +597,7 @@
 				"output": 600
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1048576,
-			"supported": true
+			"max_tokens": 1048576
 		},
 		{
 			"id": "meta-llama/llama-4-maverick",
@@ -668,8 +607,7 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "meta-llama/llama-4-scout",
@@ -679,8 +617,7 @@
 				"output": 0.3
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 1000000,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "qwen/qwen-max",
@@ -690,8 +627,7 @@
 				"output": 6.4
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 32768
 		},
 		{
 			"id": "qwen/qwen-turbo",
@@ -701,8 +637,7 @@
 				"output": 0.2
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768,
-			"supported": true
+			"max_tokens": 1000000
 		},
 		{
 			"id": "qwen/qwen3-235b-a22b",
@@ -712,8 +647,7 @@
 				"output": 2
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 24000,
-			"supported": true
+			"max_tokens": 24000
 		},
 		{
 			"id": "mistralai/mistral-small-3.1-24b-instruct:free",
@@ -723,9 +657,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 96000,
-			"supported": false,
-			"reason": "Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use."
+			"max_tokens": 96000
 		},
 		{
 			"id": "mistralai/mistral-small-3.1-24b-instruct",
@@ -735,8 +667,7 @@
 				"output": 0.3
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 128000,
-			"supported": true
+			"max_tokens": 128000
 		},
 		{
 			"id": "mistralai/devstral-small",
@@ -746,8 +677,7 @@
 				"output": 0.3
 			},
 			"allowed_roles": ["main"],
-			"max_tokens": 110000,
-			"supported": true
+			"max_tokens": 110000
 		},
 		{
 			"id": "mistralai/mistral-nemo",
@@ -757,8 +687,7 @@
 				"output": 0.07
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 100000,
-			"supported": true
+			"max_tokens": 100000
 		},
 		{
 			"id": "thudm/glm-4-32b:free",
@@ -768,9 +697,7 @@
 				"output": 0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 32768,
-			"supported": false,
-			"reason": "Free OpenRouter models are not supported due to severe rate limits, lack of tool use support, and other reliability issues that make them impractical for production use."
+			"max_tokens": 32768
 		}
 	],
 	"ollama": [
@@ -781,8 +708,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "qwen3:latest",
@@ -791,8 +717,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "qwen3:14b",
@@ -801,8 +726,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "qwen3:32b",
@@ -811,8 +735,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "mistral-small3.1:latest",
@@ -821,8 +744,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "llama3.3:latest",
@@ -831,8 +753,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "phi4:latest",
@@ -841,8 +762,7 @@
 				"input": 0,
 				"output": 0
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		}
 	],
 	"azure": [
@@ -851,11 +771,10 @@
 			"swe_score": 0.332,
 			"cost_per_1m_tokens": {
 				"input": 2.5,
-				"output": 10
+				"output": 10.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384,
-			"supported": true
+			"max_tokens": 16384
 		},
 		{
 			"id": "gpt-4o-mini",
@@ -865,8 +784,7 @@
 				"output": 0.6
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384,
-			"supported": true
+			"max_tokens": 16384
 		},
 		{
 			"id": "gpt-4-1",
@@ -876,8 +794,7 @@
 				"output": 10.0
 			},
 			"allowed_roles": ["main", "fallback"],
-			"max_tokens": 16384,
-			"supported": true
+			"max_tokens": 16384
 		}
 	],
 	"bedrock": [
@@ -888,8 +805,7 @@
 				"input": 0.25,
 				"output": 1.25
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "us.anthropic.claude-3-opus-20240229-v1:0",
@@ -898,8 +814,7 @@
 				"input": 15,
 				"output": 75
 			},
-			"allowed_roles": ["main", "fallback", "research"],
-			"supported": true
+			"allowed_roles": ["main", "fallback", "research"]
 		},
 		{
 			"id": "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
@@ -908,8 +823,7 @@
 				"input": 3,
 				"output": 15
 			},
-			"allowed_roles": ["main", "fallback", "research"],
-			"supported": true
+			"allowed_roles": ["main", "fallback", "research"]
 		},
 		{
 			"id": "us.anthropic.claude-3-5-sonnet-20241022-v2:0",
@@ -918,8 +832,7 @@
 				"input": 3,
 				"output": 15
 			},
-			"allowed_roles": ["main", "fallback", "research"],
-			"supported": true
+			"allowed_roles": ["main", "fallback", "research"]
 		},
 		{
 			"id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
@@ -929,8 +842,7 @@
 				"output": 15
 			},
 			"allowed_roles": ["main", "fallback", "research"],
-			"max_tokens": 65536,
-			"supported": true
+			"max_tokens": 65536
 		},
 		{
 			"id": "us.anthropic.claude-3-5-haiku-20241022-v1:0",
@@ -939,8 +851,7 @@
 				"input": 0.8,
 				"output": 4
 			},
-			"allowed_roles": ["main", "fallback"],
-			"supported": true
+			"allowed_roles": ["main", "fallback"]
 		},
 		{
 			"id": "us.anthropic.claude-opus-4-20250514-v1:0",
@@ -949,8 +860,7 @@
 				"input": 15,
 				"output": 75
 			},
-			"allowed_roles": ["main", "fallback", "research"],
-			"supported": true
+			"allowed_roles": ["main", "fallback", "research"]
 		},
 		{
 			"id": "us.anthropic.claude-sonnet-4-20250514-v1:0",
@@ -959,8 +869,7 @@
 				"input": 3,
 				"output": 15
 			},
-			"allowed_roles": ["main", "fallback", "research"],
-			"supported": true
+			"allowed_roles": ["main", "fallback", "research"]
 		},
 		{
 			"id": "us.deepseek.r1-v1:0",
@@ -970,8 +879,7 @@
 				"output": 5.4
 			},
 			"allowed_roles": ["research"],
-			"max_tokens": 65536,
-			"supported": true
+			"max_tokens": 65536
 		}
 	]
 }

scripts/modules/ui.js

@@ -9,7 +9,6 @@ import boxen from 'boxen';
 import ora from 'ora';
 import Table from 'cli-table3';
 import gradient from 'gradient-string';
-import readline from 'readline';
 import {
 	log,
 	findTaskById,
@@ -1683,15 +1682,18 @@ async function displayComplexityReport(reportPath) {
 			)
 		);
 
-		const rl = readline.createInterface({
+		const readline = require('readline').createInterface({
 			input: process.stdin,
 			output: process.stdout
 		});
 
 		const answer = await new Promise((resolve) => {
-			rl.question(chalk.cyan('Generate complexity report? (y/n): '), resolve);
+			readline.question(
+				chalk.cyan('Generate complexity report? (y/n): '),
+				resolve
+			);
 		});
-		rl.close();
+		readline.close();
 
 		if (answer.toLowerCase() === 'y' || answer.toLowerCase() === 'yes') {
 			// Call the analyze-complexity command
@@ -1972,6 +1974,8 @@ async function confirmTaskOverwrite(tasksPath) {
 		)
 	);
 
+	// Use dynamic import to get the readline module
+	const readline = await import('readline');
 	const rl = readline.createInterface({
 		input: process.stdin,
 		output: process.stdout
@@ -2459,6 +2463,8 @@ async function displayMultipleTasksSummary(
 			)
 		);
 
+		// Use dynamic import for readline
+		const readline = await import('readline');
 		const rl = readline.createInterface({
 			input: process.stdin,
 			output: process.stdout