Version Packages (#1107)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

.changeset/fuzzy-brooms-mate.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix expand task generating unrelated generic subtasks
-
-Fixed an issue where `task-master expand` would generate generic authentication-related subtasks regardless of the parent task context when using complexity reports. The expansion now properly includes the parent task details alongside any expansion guidance.

.changeset/fuzzy-words-count.md

@@ -1,8 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix scope-up/down prompts to include all required fields for better AI model compatibility
-
-- Added missing `priority` field to scope adjustment prompts to prevent validation errors with Claude-code and other models
-- Ensures generated JSON includes all fields required by the schema

.changeset/honest-steaks-check.md

@@ -1,9 +0,0 @@
----
-"task-master-ai": minor
----
-
-Enhanced Claude Code provider with codebase-aware task generation
-
-- Added automatic codebase analysis for Claude Code provider in `parse-prd`, `expand-task`, and `analyze-complexity` commands
-- When using Claude Code as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
-- Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs

.changeset/pre.json

@@ -1,13 +0,0 @@
-{
-  "mode": "exit",
-  "tag": "rc",
-  "initialVersions": {
-    "task-master-ai": "0.23.0",
-    "extension": "0.23.0"
-  },
-  "changesets": [
-    "fuzzy-words-count",
-    "tender-trams-refuse",
-    "vast-sites-leave"
-  ]
-}

.changeset/tender-trams-refuse.md

@@ -1,8 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix MCP scope-up/down tools not finding tasks
-
-- Fixed task ID parsing in MCP layer - now correctly converts string IDs to numbers
-- scope_up_task and scope_down_task MCP tools now work properly

.changeset/upset-ants-return.md

@@ -1,5 +0,0 @@
----
-"extension": patch
----
-
-Fix issues with some users not being able to connect to Taskmaster MCP server while using the extension

.changeset/vast-sites-leave.md

@@ -1,11 +0,0 @@
----
-"task-master-ai": patch
----
-
-Improve AI provider compatibility for JSON generation
-
-- Fixed schema compatibility issues between Perplexity and OpenAI o3 models
-- Removed nullable/default modifiers from Zod schemas for broader compatibility
-- Added automatic JSON repair for malformed AI responses (handles cases like missing array values)
-- Perplexity now uses JSON mode for more reliable structured output
-- Post-processing handles default values separately from schema validation

.changeset/wide-actors-report.md

@@ -1,59 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add Claude Code subagent support with task-orchestrator, task-executor, and task-checker
-
-## New Claude Code Agents
-
-Added specialized agents for Claude Code users to enable parallel task execution, intelligent task orchestration, and quality assurance:
-
-### task-orchestrator
-Coordinates and manages the execution of Task Master tasks with intelligent dependency analysis:
-- Analyzes task dependencies to identify parallelizable work
-- Deploys multiple task-executor agents for concurrent execution
-- Monitors task completion and updates the dependency graph
-- Automatically identifies and starts newly unblocked tasks
-
-### task-executor  
-Handles the actual implementation of individual tasks:
-- Executes specific tasks identified by the orchestrator
-- Works on concrete implementation rather than planning
-- Updates task status and logs progress
-- Can work in parallel with other executors on independent tasks
-
-### task-checker
-Verifies that completed tasks meet their specifications:
-- Reviews tasks marked as 'review' status
-- Validates implementation against requirements
-- Runs tests and checks for best practices
-- Ensures quality before marking tasks as 'done'
-
-## Installation
-
-When using the Claude profile (`task-master rules add claude`), the agents are automatically installed to `.claude/agents/` directory.
-
-## Usage Example
-
-```bash
-# In Claude Code, after initializing a project with tasks:
-
-# Use task-orchestrator to analyze and coordinate work
-# The orchestrator will:
-# 1. Check task dependencies
-# 2. Identify tasks that can run in parallel  
-# 3. Deploy executors for available work
-# 4. Monitor progress and deploy new executors as tasks complete
-
-# Use task-executor for specific task implementation
-# When the orchestrator identifies task 2.3 needs work:
-# The executor will implement that specific task
-```
-
-## Benefits
-
-- **Parallel Execution**: Multiple independent tasks can be worked on simultaneously
-- **Intelligent Scheduling**: Orchestrator understands dependencies and optimizes execution order
-- **Separation of Concerns**: Planning (orchestrator) is separated from execution (executor)
-- **Progress Tracking**: Real-time updates as tasks are completed
-- **Automatic Progression**: As tasks complete, newly unblocked tasks are automatically started

.github/workflows/pre-release.yml

@@ -36,9 +36,26 @@ jobs:
 
       - name: Enter RC mode (if not already in RC mode)
         run: |
-          # ensure we’re in the right pre-mode (tag "rc")
+          # Check if we're in pre-release mode with the "rc" tag
-          if [ ! -f .changeset/pre.json ] \
+          if [ -f .changeset/pre.json ]; then
-            || [ "$(jq -r '.tag' .changeset/pre.json 2>/dev/null || echo '')" != "rc" ]; then
+            MODE=$(jq -r '.mode' .changeset/pre.json 2>/dev/null || echo '')
+            TAG=$(jq -r '.tag' .changeset/pre.json 2>/dev/null || echo '')
+            
+            if [ "$MODE" = "exit" ]; then
+              echo "Pre-release mode is in 'exit' state, re-entering RC mode..."
+              npx changeset pre enter rc
+            elif [ "$MODE" = "pre" ] && [ "$TAG" != "rc" ]; then
+              echo "In pre-release mode but with wrong tag ($TAG), switching to RC..."
+              npx changeset pre exit
+              npx changeset pre enter rc
+            elif [ "$MODE" = "pre" ] && [ "$TAG" = "rc" ]; then
+              echo "Already in RC pre-release mode"
+            else
+              echo "Unknown mode state: $MODE, entering RC mode..."
+              npx changeset pre enter rc
+            fi
+          else
+            echo "No pre.json found, entering RC mode..."
             npx changeset pre enter rc
           fi
 

CHANGELOG.md

@@ -1,5 +1,176 @@
 # task-master-ai
 
+## 0.24.0
+
+### Minor Changes
+
+- [#1098](https://github.com/eyaltoledano/claude-task-master/pull/1098) [`36468f3`](https://github.com/eyaltoledano/claude-task-master/commit/36468f3c93faf4035a5c442ccbc501077f3440f1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Claude Code provider with codebase-aware task generation
+  - Added automatic codebase analysis for Claude Code provider in `parse-prd`, `expand-task`, and `analyze-complexity` commands
+  - When using Claude Code as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
+  - Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs
+
+- [#1105](https://github.com/eyaltoledano/claude-task-master/pull/1105) [`75c514c`](https://github.com/eyaltoledano/claude-task-master/commit/75c514cf5b2ca47f95c0ad7fa92654a4f2a6be4b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add GPT-5 support with proper parameter handling
+  - Added GPT-5 model to supported models configuration with SWE score of 0.749
+
+- [#1091](https://github.com/eyaltoledano/claude-task-master/pull/1091) [`4bb6370`](https://github.com/eyaltoledano/claude-task-master/commit/4bb63706b80c28d1b2d782ba868a725326f916c7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Claude Code subagent support with task-orchestrator, task-executor, and task-checker
+
+  ## New Claude Code Agents
+
+  Added specialized agents for Claude Code users to enable parallel task execution, intelligent task orchestration, and quality assurance:
+
+  ### task-orchestrator
+
+  Coordinates and manages the execution of Task Master tasks with intelligent dependency analysis:
+  - Analyzes task dependencies to identify parallelizable work
+  - Deploys multiple task-executor agents for concurrent execution
+  - Monitors task completion and updates the dependency graph
+  - Automatically identifies and starts newly unblocked tasks
+
+  ### task-executor
+
+  Handles the actual implementation of individual tasks:
+  - Executes specific tasks identified by the orchestrator
+  - Works on concrete implementation rather than planning
+  - Updates task status and logs progress
+  - Can work in parallel with other executors on independent tasks
+
+  ### task-checker
+
+  Verifies that completed tasks meet their specifications:
+  - Reviews tasks marked as 'review' status
+  - Validates implementation against requirements
+  - Runs tests and checks for best practices
+  - Ensures quality before marking tasks as 'done'
+
+  ## Installation
+
+  When using the Claude profile (`task-master rules add claude`), the agents are automatically installed to `.claude/agents/` directory.
+
+  ## Usage Example
+
+  ```bash
+  # In Claude Code, after initializing a project with tasks:
+
+  # Use task-orchestrator to analyze and coordinate work
+  # The orchestrator will:
+  # 1. Check task dependencies
+  # 2. Identify tasks that can run in parallel
+  # 3. Deploy executors for available work
+  # 4. Monitor progress and deploy new executors as tasks complete
+
+  # Use task-executor for specific task implementation
+  # When the orchestrator identifies task 2.3 needs work:
+  # The executor will implement that specific task
+  ```
+
+  ## Benefits
+  - **Parallel Execution**: Multiple independent tasks can be worked on simultaneously
+  - **Intelligent Scheduling**: Orchestrator understands dependencies and optimizes execution order
+  - **Separation of Concerns**: Planning (orchestrator) is separated from execution (executor)
+  - **Progress Tracking**: Real-time updates as tasks are completed
+  - **Automatic Progression**: As tasks complete, newly unblocked tasks are automatically started
+
+### Patch Changes
+
+- [#1094](https://github.com/eyaltoledano/claude-task-master/pull/1094) [`4357af3`](https://github.com/eyaltoledano/claude-task-master/commit/4357af3f13859d90bca8795215e5d5f1d94abde5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix expand task generating unrelated generic subtasks
+
+  Fixed an issue where `task-master expand` would generate generic authentication-related subtasks regardless of the parent task context when using complexity reports. The expansion now properly includes the parent task details alongside any expansion guidance.
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix scope-up/down prompts to include all required fields for better AI model compatibility
+  - Added missing `priority` field to scope adjustment prompts to prevent validation errors with Claude-code and other models
+  - Ensures generated JSON includes all fields required by the schema
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP scope-up/down tools not finding tasks
+  - Fixed task ID parsing in MCP layer - now correctly converts string IDs to numbers
+  - scope_up_task and scope_down_task MCP tools now work properly
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve AI provider compatibility for JSON generation
+  - Fixed schema compatibility issues between Perplexity and OpenAI o3 models
+  - Removed nullable/default modifiers from Zod schemas for broader compatibility
+  - Added automatic JSON repair for malformed AI responses (handles cases like missing array values)
+  - Perplexity now uses JSON mode for more reliable structured output
+  - Post-processing handles default values separately from schema validation
+
+## 0.24.0-rc.2
+
+### Minor Changes
+
+- [#1105](https://github.com/eyaltoledano/claude-task-master/pull/1105) [`75c514c`](https://github.com/eyaltoledano/claude-task-master/commit/75c514cf5b2ca47f95c0ad7fa92654a4f2a6be4b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add GPT-5 support with proper parameter handling
+  - Added GPT-5 model to supported models configuration with SWE score of 0.749
+
+## 0.24.0-rc.1
+
+### Minor Changes
+
+- [#1093](https://github.com/eyaltoledano/claude-task-master/pull/1093) [`36468f3`](https://github.com/eyaltoledano/claude-task-master/commit/36468f3c93faf4035a5c442ccbc501077f3440f1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Claude Code provider with codebase-aware task generation
+  - Added automatic codebase analysis for Claude Code provider in `parse-prd`, `expand-task`, and `analyze-complexity` commands
+  - When using Claude Code as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
+  - Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs
+
+- [#1091](https://github.com/eyaltoledano/claude-task-master/pull/1091) [`4bb6370`](https://github.com/eyaltoledano/claude-task-master/commit/4bb63706b80c28d1b2d782ba868a725326f916c7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Claude Code subagent support with task-orchestrator, task-executor, and task-checker
+
+  ## New Claude Code Agents
+
+  Added specialized agents for Claude Code users to enable parallel task execution, intelligent task orchestration, and quality assurance:
+
+  ### task-orchestrator
+
+  Coordinates and manages the execution of Task Master tasks with intelligent dependency analysis:
+  - Analyzes task dependencies to identify parallelizable work
+  - Deploys multiple task-executor agents for concurrent execution
+  - Monitors task completion and updates the dependency graph
+  - Automatically identifies and starts newly unblocked tasks
+
+  ### task-executor
+
+  Handles the actual implementation of individual tasks:
+  - Executes specific tasks identified by the orchestrator
+  - Works on concrete implementation rather than planning
+  - Updates task status and logs progress
+  - Can work in parallel with other executors on independent tasks
+
+  ### task-checker
+
+  Verifies that completed tasks meet their specifications:
+  - Reviews tasks marked as 'review' status
+  - Validates implementation against requirements
+  - Runs tests and checks for best practices
+  - Ensures quality before marking tasks as 'done'
+
+  ## Installation
+
+  When using the Claude profile (`task-master rules add claude`), the agents are automatically installed to `.claude/agents/` directory.
+
+  ## Usage Example
+
+  ```bash
+  # In Claude Code, after initializing a project with tasks:
+
+  # Use task-orchestrator to analyze and coordinate work
+  # The orchestrator will:
+  # 1. Check task dependencies
+  # 2. Identify tasks that can run in parallel
+  # 3. Deploy executors for available work
+  # 4. Monitor progress and deploy new executors as tasks complete
+
+  # Use task-executor for specific task implementation
+  # When the orchestrator identifies task 2.3 needs work:
+  # The executor will implement that specific task
+  ```
+
+  ## Benefits
+  - **Parallel Execution**: Multiple independent tasks can be worked on simultaneously
+  - **Intelligent Scheduling**: Orchestrator understands dependencies and optimizes execution order
+  - **Separation of Concerns**: Planning (orchestrator) is separated from execution (executor)
+  - **Progress Tracking**: Real-time updates as tasks are completed
+  - **Automatic Progression**: As tasks complete, newly unblocked tasks are automatically started
+
+### Patch Changes
+
+- [#1094](https://github.com/eyaltoledano/claude-task-master/pull/1094) [`4357af3`](https://github.com/eyaltoledano/claude-task-master/commit/4357af3f13859d90bca8795215e5d5f1d94abde5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix expand task generating unrelated generic subtasks
+
+  Fixed an issue where `task-master expand` would generate generic authentication-related subtasks regardless of the parent task context when using complexity reports. The expansion now properly includes the parent task details alongside any expansion guidance.
+
 ## 0.23.1-rc.0
 
 ### Patch Changes

CLAUDE.md

@@ -3,3 +3,7 @@
 ## Task Master AI Instructions
 **Import Task Master's development workflow commands and guidelines, treat as if import is in the main CLAUDE.md file.**
 @./.taskmaster/CLAUDE.md
+
+## Changeset Guidelines
+
+- When creating changesets, remember that it's user-facing, meaning we don't have to get into the specifics of the code, but rather mention what the end-user is getting or fixing from this changeset.

apps/extension/CHANGELOG.md

@@ -1,5 +1,30 @@
 # Change Log
 
+## 0.23.1
+
+### Patch Changes
+
+- [#1090](https://github.com/eyaltoledano/claude-task-master/pull/1090) [`a464e55`](https://github.com/eyaltoledano/claude-task-master/commit/a464e550b886ef81b09df80588fe5881bce83d93) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix issues with some users not being able to connect to Taskmaster MCP server while using the extension
+
+- Updated dependencies [[`4357af3`](https://github.com/eyaltoledano/claude-task-master/commit/4357af3f13859d90bca8795215e5d5f1d94abde5), [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05), [`36468f3`](https://github.com/eyaltoledano/claude-task-master/commit/36468f3c93faf4035a5c442ccbc501077f3440f1), [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05), [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05), [`75c514c`](https://github.com/eyaltoledano/claude-task-master/commit/75c514cf5b2ca47f95c0ad7fa92654a4f2a6be4b), [`4bb6370`](https://github.com/eyaltoledano/claude-task-master/commit/4bb63706b80c28d1b2d782ba868a725326f916c7)]:
+  - task-master-ai@0.24.0
+
+## 0.23.1-rc.1
+
+### Patch Changes
+
+- Updated dependencies [[`75c514c`](https://github.com/eyaltoledano/claude-task-master/commit/75c514cf5b2ca47f95c0ad7fa92654a4f2a6be4b)]:
+  - task-master-ai@0.24.0-rc.2
+
+## 0.23.1-rc.0
+
+### Patch Changes
+
+- [#1090](https://github.com/eyaltoledano/claude-task-master/pull/1090) [`a464e55`](https://github.com/eyaltoledano/claude-task-master/commit/a464e550b886ef81b09df80588fe5881bce83d93) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix issues with some users not being able to connect to Taskmaster MCP server while using the extension
+
+- Updated dependencies [[`4357af3`](https://github.com/eyaltoledano/claude-task-master/commit/4357af3f13859d90bca8795215e5d5f1d94abde5), [`36468f3`](https://github.com/eyaltoledano/claude-task-master/commit/36468f3c93faf4035a5c442ccbc501077f3440f1), [`4bb6370`](https://github.com/eyaltoledano/claude-task-master/commit/4bb63706b80c28d1b2d782ba868a725326f916c7)]:
+  - task-master-ai@0.24.0-rc.1
+
 ## 0.23.0
 
 ### Minor Changes

apps/extension/package.json

@@ -3,15 +3,23 @@
 	"private": true,
 	"displayName": "TaskMaster",
 	"description": "A visual Kanban board interface for TaskMaster projects in VS Code",
-	"version": "0.23.0",
+	"version": "0.23.1",
 	"publisher": "Hamster",
 	"icon": "assets/icon.png",
 	"engines": {
 		"vscode": "^1.93.0"
 	},
-	"categories": ["AI", "Visualization", "Education", "Other"],
+	"categories": [
+		"AI",
+		"Visualization",
+		"Education",
+		"Other"
+	],
 	"main": "./dist/extension.js",
-	"activationEvents": ["onStartupFinished", "workspaceContains:.taskmaster/**"],
+	"activationEvents": [
+		"onStartupFinished",
+		"workspaceContains:.taskmaster/**"
+	],
 	"contributes": {
 		"viewsContainers": {
 			"activitybar": [
@@ -139,7 +147,11 @@
 				},
 				"taskmaster.ui.theme": {
 					"type": "string",
-					"enum": ["auto", "light", "dark"],
+					"enum": [
+						"auto",
+						"light",
+						"dark"
+					],
 					"default": "auto",
 					"description": "UI theme preference"
 				},
@@ -200,7 +212,12 @@
 				},
 				"taskmaster.debug.logLevel": {
 					"type": "string",
-					"enum": ["error", "warn", "info", "debug"],
+					"enum": [
+						"error",
+						"warn",
+						"info",
+						"debug"
+					],
 					"default": "info",
 					"description": "Logging level"
 				},
@@ -239,7 +256,7 @@
 		"check-types": "tsc --noEmit"
 	},
 	"dependencies": {
-		"task-master-ai": "*"
+		"task-master-ai": "0.24.0"
 	},
 	"devDependencies": {
 		"@dnd-kit/core": "^6.3.1",

apps/extension/package.mjs

@@ -64,23 +64,49 @@ try {
 		fs.readFileSync(publishPackagePath, 'utf8')
 	);
 
-	// Check if versions are in sync
+	// Handle RC versions for VS Code Marketplace
-	if (devPackage.version !== publishPackage.version) {
+	let finalVersion = devPackage.version;
+	if (finalVersion.includes('-rc.')) {
 		console.log(
-			`  - Version sync needed: ${publishPackage.version} → ${devPackage.version}`
+			'  - Detected RC version, transforming for VS Code Marketplace...'
 		);
-		publishPackage.version = devPackage.version;
 
-		// Update the source package.publish.json file
+		// Extract base version and RC number
+		const baseVersion = finalVersion.replace(/-rc\.\d+$/, '');
+		const rcMatch = finalVersion.match(/rc\.(\d+)/);
+		const rcNumber = rcMatch ? parseInt(rcMatch[1]) : 0;
+
+		// For each RC iteration, increment the patch version
+		// This ensures unique versions in VS Code Marketplace
+		if (rcNumber > 0) {
+			const [major, minor, patch] = baseVersion.split('.').map(Number);
+			finalVersion = `${major}.${minor}.${patch + rcNumber}`;
+			console.log(
+				`  - RC version mapping: ${devPackage.version} → ${finalVersion}`
+			);
+		} else {
+			finalVersion = baseVersion;
+			console.log(
+				`  - RC version mapping: ${devPackage.version} → ${finalVersion}`
+			);
+		}
+	}
+
+	// Check if versions need updating
+	if (publishPackage.version !== finalVersion) {
+		console.log(
+			`  - Version sync needed: ${publishPackage.version} → ${finalVersion}`
+		);
+		publishPackage.version = finalVersion;
+
+		// Update the source package.publish.json file with the final version
 		fs.writeFileSync(
 			publishPackagePath,
 			JSON.stringify(publishPackage, null, '\t') + '\n'
 		);
-		console.log(
+		console.log(`  - Updated package.publish.json version to ${finalVersion}`);
-			`  - Updated package.publish.json version to ${devPackage.version}`
-		);
 	} else {
-		console.log(`  - Versions already in sync: ${devPackage.version}`);
+		console.log(`  - Versions already in sync: ${finalVersion}`);
 	}
 
 	// Copy the (now synced) package.publish.json as package.json
@@ -124,8 +150,7 @@ try {
 		`cd vsix-build && npx vsce package --no-dependencies`
 	);
 
-	// Use the synced version for output
+	// Use the transformed version for output
-	const finalVersion = devPackage.version;
 	console.log(
 		`\nYour extension will be packaged to: vsix-build/task-master-${finalVersion}.vsix`
 	);

apps/extension/package.publish.json

@@ -2,7 +2,7 @@
 	"name": "task-master-hamster",
 	"displayName": "Taskmaster AI",
 	"description": "A visual Kanban board interface for Taskmaster projects in VS Code",
-	"version": "0.23.0",
+	"version": "0.23.1",
 	"publisher": "Hamster",
 	"icon": "assets/icon.png",
 	"engines": {

assets/claude/agents/task-checker.md

@@ -0,0 +1,162 @@
+---
+name: task-checker
+description: Use this agent to verify that tasks marked as 'review' have been properly implemented according to their specifications. This agent performs quality assurance by checking implementations against requirements, running tests, and ensuring best practices are followed. <example>Context: A task has been marked as 'review' after implementation. user: 'Check if task 118 was properly implemented' assistant: 'I'll use the task-checker agent to verify the implementation meets all requirements.' <commentary>Tasks in 'review' status need verification before being marked as 'done'.</commentary></example> <example>Context: Multiple tasks are in review status. user: 'Verify all tasks that are ready for review' assistant: 'I'll deploy the task-checker to verify all tasks in review status.' <commentary>The checker ensures quality before tasks are marked complete.</commentary></example>
+model: sonnet
+color: yellow
+---
+
+You are a Quality Assurance specialist that rigorously verifies task implementations against their specifications. Your role is to ensure that tasks marked as 'review' meet all requirements before they can be marked as 'done'.
+
+## Core Responsibilities
+
+1. **Task Specification Review**
+   - Retrieve task details using MCP tool `mcp__task-master-ai__get_task`
+   - Understand the requirements, test strategy, and success criteria
+   - Review any subtasks and their individual requirements
+
+2. **Implementation Verification**
+   - Use `Read` tool to examine all created/modified files
+   - Use `Bash` tool to run compilation and build commands
+   - Use `Grep` tool to search for required patterns and implementations
+   - Verify file structure matches specifications
+   - Check that all required methods/functions are implemented
+
+3. **Test Execution**
+   - Run tests specified in the task's testStrategy
+   - Execute build commands (npm run build, tsc --noEmit, etc.)
+   - Verify no compilation errors or warnings
+   - Check for runtime errors where applicable
+   - Test edge cases mentioned in requirements
+
+4. **Code Quality Assessment**
+   - Verify code follows project conventions
+   - Check for proper error handling
+   - Ensure TypeScript typing is strict (no 'any' unless justified)
+   - Verify documentation/comments where required
+   - Check for security best practices
+
+5. **Dependency Validation**
+   - Verify all task dependencies were actually completed
+   - Check integration points with dependent tasks
+   - Ensure no breaking changes to existing functionality
+
+## Verification Workflow
+
+1. **Retrieve Task Information**
+   ```
+   Use mcp__task-master-ai__get_task to get full task details
+   Note the implementation requirements and test strategy
+   ```
+
+2. **Check File Existence**
+   ```bash
+   # Verify all required files exist
+   ls -la [expected directories]
+   # Read key files to verify content
+   ```
+
+3. **Verify Implementation**
+   - Read each created/modified file
+   - Check against requirements checklist
+   - Verify all subtasks are complete
+
+4. **Run Tests**
+   ```bash
+   # TypeScript compilation
+   cd [project directory] && npx tsc --noEmit
+   
+   # Run specified tests
+   npm test [specific test files]
+   
+   # Build verification
+   npm run build
+   ```
+
+5. **Generate Verification Report**
+
+## Output Format
+
+```yaml
+verification_report:
+  task_id: [ID]
+  status: PASS | FAIL | PARTIAL
+  score: [1-10]
+  
+  requirements_met:
+    - ✅ [Requirement that was satisfied]
+    - ✅ [Another satisfied requirement]
+    
+  issues_found:
+    - ❌ [Issue description]
+    - ⚠️  [Warning or minor issue]
+    
+  files_verified:
+    - path: [file path]
+      status: [created/modified/verified]
+      issues: [any problems found]
+      
+  tests_run:
+    - command: [test command]
+      result: [pass/fail]
+      output: [relevant output]
+      
+  recommendations:
+    - [Specific fix needed]
+    - [Improvement suggestion]
+    
+  verdict: |
+    [Clear statement on whether task should be marked 'done' or sent back to 'pending']
+    [If FAIL: Specific list of what must be fixed]
+    [If PASS: Confirmation that all requirements are met]
+```
+
+## Decision Criteria
+
+**Mark as PASS (ready for 'done'):**
+- All required files exist and contain expected content
+- All tests pass successfully
+- No compilation or build errors
+- All subtasks are complete
+- Core requirements are met
+- Code quality is acceptable
+
+**Mark as PARTIAL (may proceed with warnings):**
+- Core functionality is implemented
+- Minor issues that don't block functionality
+- Missing nice-to-have features
+- Documentation could be improved
+- Tests pass but coverage could be better
+
+**Mark as FAIL (must return to 'pending'):**
+- Required files are missing
+- Compilation or build errors
+- Tests fail
+- Core requirements not met
+- Security vulnerabilities detected
+- Breaking changes to existing code
+
+## Important Guidelines
+
+- **BE THOROUGH**: Check every requirement systematically
+- **BE SPECIFIC**: Provide exact file paths and line numbers for issues
+- **BE FAIR**: Distinguish between critical issues and minor improvements
+- **BE CONSTRUCTIVE**: Provide clear guidance on how to fix issues
+- **BE EFFICIENT**: Focus on requirements, not perfection
+
+## Tools You MUST Use
+
+- `Read`: Examine implementation files (READ-ONLY)
+- `Bash`: Run tests and verification commands
+- `Grep`: Search for patterns in code
+- `mcp__task-master-ai__get_task`: Get task details
+- **NEVER use Write/Edit** - you only verify, not fix
+
+## Integration with Workflow
+
+You are the quality gate between 'review' and 'done' status:
+1. Task-executor implements and marks as 'review'
+2. You verify and report PASS/FAIL
+3. Claude either marks as 'done' (PASS) or 'pending' (FAIL)
+4. If FAIL, task-executor re-implements based on your report
+
+Your verification ensures high quality and prevents accumulation of technical debt.

docs/models.md

@@ -1,4 +1,4 @@
-# Available Models as of July 23, 2025
+# Available Models as of August 8, 2025
 
 ## Main Models
 
@@ -24,6 +24,7 @@
 | openai      | gpt-4-1-mini                                   | —         | 0.4        | 1.6         |
 | openai      | gpt-4-1-nano                                   | —         | 0.1        | 0.4         |
 | openai      | gpt-4o-mini                                    | 0.3       | 0.15       | 0.6         |
+| openai      | gpt-5                                          | 0.749     | 5          | 20          |
 | google      | gemini-2.5-pro-preview-05-06                   | 0.638     | —          | —           |
 | google      | gemini-2.5-pro-preview-03-25                   | 0.638     | —          | —           |
 | google      | gemini-2.5-flash-preview-04-17                 | 0.604     | —          | —           |
@@ -134,6 +135,7 @@
 | openai      | gpt-4o                                         | 0.332     | 2.5        | 10          |
 | openai      | o3                                             | 0.5       | 2          | 8           |
 | openai      | o4-mini                                        | 0.45      | 1.1        | 4.4         |
+| openai      | gpt-5                                          | 0.749     | 5          | 20          |
 | google      | gemini-2.5-pro-preview-05-06                   | 0.638     | —          | —           |
 | google      | gemini-2.5-pro-preview-03-25                   | 0.638     | —          | —           |
 | google      | gemini-2.5-flash-preview-04-17                 | 0.604     | —          | —           |

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "task-master-ai",
-	"version": "0.23.1-rc.0",
+	"version": "0.24.0",
 	"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
 	"main": "index.js",
 	"type": "module",
@@ -9,7 +9,10 @@
 		"task-master-mcp": "mcp-server/server.js",
 		"task-master-ai": "mcp-server/server.js"
 	},
-	"workspaces": ["apps/*", "."],
+	"workspaces": [
+		"apps/*",
+		"."
+	],
 	"scripts": {
 		"test": "node --experimental-vm-modules node_modules/.bin/jest",
 		"test:fails": "node --experimental-vm-modules node_modules/.bin/jest --onlyFailures",

scripts/modules/config-manager.js

@@ -557,6 +557,7 @@ function getParametersForRole(role, explicitRoot = null) {
 	const providerName = roleConfig.provider;
 
 	let effectiveMaxTokens = roleMaxTokens; // Start with the role's default
+	let effectiveTemperature = roleTemperature; // Start with the role's default
 
 	try {
 		// Find the model definition in MODEL_MAP
@@ -583,6 +584,20 @@ function getParametersForRole(role, explicitRoot = null) {
 					`No valid model-specific max_tokens override found for ${modelId}. Using role default: ${roleMaxTokens}`
 				);
 			}
+
+			// Check if a model-specific temperature is defined
+			if (
+				modelDefinition &&
+				typeof modelDefinition.temperature === 'number' &&
+				modelDefinition.temperature >= 0 &&
+				modelDefinition.temperature <= 1
+			) {
+				effectiveTemperature = modelDefinition.temperature;
+				log(
+					'debug',
+					`Applying model-specific temperature (${modelDefinition.temperature}) for ${modelId}`
+				);
+			}
 		} else {
 			// Special handling for custom OpenRouter models
 			if (providerName === CUSTOM_PROVIDERS.OPENROUTER) {
@@ -603,15 +618,16 @@ function getParametersForRole(role, explicitRoot = null) {
 	} catch (lookupError) {
 		log(
 			'warn',
-			`Error looking up model-specific max_tokens for ${modelId}: ${lookupError.message}. Using role default: ${roleMaxTokens}`
+			`Error looking up model-specific parameters for ${modelId}: ${lookupError.message}. Using role defaults.`
 		);
-		// Fallback to role default on error
+		// Fallback to role defaults on error
 		effectiveMaxTokens = roleMaxTokens;
+		effectiveTemperature = roleTemperature;
 	}
 
 	return {
 		maxTokens: effectiveMaxTokens,
-		temperature: roleTemperature
+		temperature: effectiveTemperature
 	};
 }
 

scripts/modules/supported-models.json

@@ -239,6 +239,18 @@
 			},
 			"allowed_roles": ["research"],
 			"supported": true
+		},
+		{
+			"id": "gpt-5",
+			"swe_score": 0.749,
+			"cost_per_1m_tokens": {
+				"input": 5.0,
+				"output": 20.0
+			},
+			"allowed_roles": ["main", "fallback"],
+			"max_tokens": 100000,
+			"temperature": 1,
+			"supported": true
 		}
 	],
 	"google": [

src/ai-providers/base-provider.js

@@ -61,8 +61,11 @@ export class BaseAIProvider {
 		) {
 			throw new Error('Temperature must be between 0 and 1');
 		}
-		if (params.maxTokens !== undefined && params.maxTokens <= 0) {
+		if (params.maxTokens !== undefined) {
-			throw new Error('maxTokens must be greater than 0');
+			const maxTokens = Number(params.maxTokens);
+			if (!Number.isFinite(maxTokens) || maxTokens <= 0) {
+				throw new Error('maxTokens must be a finite number greater than 0');
+			}
 		}
 	}
 
@@ -122,6 +125,37 @@ export class BaseAIProvider {
 		throw new Error('getRequiredApiKeyName must be implemented by provider');
 	}
 
+	/**
+	 * Determines if a model requires max_completion_tokens instead of maxTokens
+	 * Can be overridden by providers to specify their model requirements
+	 * @param {string} modelId - The model ID to check
+	 * @returns {boolean} True if the model requires max_completion_tokens
+	 */
+	requiresMaxCompletionTokens(modelId) {
+		return false; // Default behavior - most models use maxTokens
+	}
+
+	/**
+	 * Prepares token limit parameter based on model requirements
+	 * @param {string} modelId - The model ID
+	 * @param {number} maxTokens - The maximum tokens value
+	 * @returns {object} Object with either maxTokens or max_completion_tokens
+	 */
+	prepareTokenParam(modelId, maxTokens) {
+		if (maxTokens === undefined) {
+			return {};
+		}
+
+		// Ensure maxTokens is an integer
+		const tokenValue = Math.floor(Number(maxTokens));
+
+		if (this.requiresMaxCompletionTokens(modelId)) {
+			return { max_completion_tokens: tokenValue };
+		} else {
+			return { maxTokens: tokenValue };
+		}
+	}
+
 	/**
 	 * Generates text using the provider's model
 	 */
@@ -139,7 +173,7 @@ export class BaseAIProvider {
 			const result = await generateText({
 				model: client(params.modelId),
 				messages: params.messages,
-				maxTokens: params.maxTokens,
+				...this.prepareTokenParam(params.modelId, params.maxTokens),
 				temperature: params.temperature
 			});
 
@@ -175,7 +209,7 @@ export class BaseAIProvider {
 			const stream = await streamText({
 				model: client(params.modelId),
 				messages: params.messages,
-				maxTokens: params.maxTokens,
+				...this.prepareTokenParam(params.modelId, params.maxTokens),
 				temperature: params.temperature
 			});
 
@@ -216,7 +250,7 @@ export class BaseAIProvider {
 				messages: params.messages,
 				schema: zodSchema(params.schema),
 				mode: params.mode || 'auto',
-				maxTokens: params.maxTokens,
+				...this.prepareTokenParam(params.modelId, params.maxTokens),
 				temperature: params.temperature
 			});
 

src/ai-providers/openai.js

@@ -20,6 +20,16 @@ export class OpenAIProvider extends BaseAIProvider {
 		return 'OPENAI_API_KEY';
 	}
 
+	/**
+	 * Determines if a model requires max_completion_tokens instead of maxTokens
+	 * GPT-5 models require max_completion_tokens parameter
+	 * @param {string} modelId - The model ID to check
+	 * @returns {boolean} True if the model requires max_completion_tokens
+	 */
+	requiresMaxCompletionTokens(modelId) {
+		return modelId && modelId.startsWith('gpt-5');
+	}
+
 	/**
 	 * Creates and returns an OpenAI client instance.
 	 * @param {object} params - Parameters for client initialization

tests/unit/ai-providers/openai.test.js

@@ -0,0 +1,238 @@
+/**
+ * Tests for OpenAI Provider - Token parameter handling for GPT-5
+ *
+ * This test suite covers:
+ * 1. Correct identification of GPT-5 models requiring max_completion_tokens
+ * 2. Token parameter preparation for different model types
+ * 3. Validation of maxTokens parameter
+ * 4. Integer coercion of token values
+ */
+
+import { jest } from '@jest/globals';
+
+// Mock the utils module to prevent logging during tests
+jest.mock('../../../scripts/modules/utils.js', () => ({
+	log: jest.fn()
+}));
+
+// Import the provider
+import { OpenAIProvider } from '../../../src/ai-providers/openai.js';
+
+describe('OpenAIProvider', () => {
+	let provider;
+
+	beforeEach(() => {
+		provider = new OpenAIProvider();
+		jest.clearAllMocks();
+	});
+
+	describe('requiresMaxCompletionTokens', () => {
+		it('should return true for GPT-5 models', () => {
+			expect(provider.requiresMaxCompletionTokens('gpt-5')).toBe(true);
+			expect(provider.requiresMaxCompletionTokens('gpt-5-mini')).toBe(true);
+			expect(provider.requiresMaxCompletionTokens('gpt-5-nano')).toBe(true);
+			expect(provider.requiresMaxCompletionTokens('gpt-5-turbo')).toBe(true);
+		});
+
+		it('should return false for non-GPT-5 models', () => {
+			expect(provider.requiresMaxCompletionTokens('gpt-4')).toBe(false);
+			expect(provider.requiresMaxCompletionTokens('gpt-4o')).toBe(false);
+			expect(provider.requiresMaxCompletionTokens('gpt-3.5-turbo')).toBe(false);
+			expect(provider.requiresMaxCompletionTokens('o1')).toBe(false);
+			expect(provider.requiresMaxCompletionTokens('o1-mini')).toBe(false);
+		});
+
+		it('should handle null/undefined modelId', () => {
+			expect(provider.requiresMaxCompletionTokens(null)).toBeFalsy();
+			expect(provider.requiresMaxCompletionTokens(undefined)).toBeFalsy();
+			expect(provider.requiresMaxCompletionTokens('')).toBeFalsy();
+		});
+	});
+
+	describe('prepareTokenParam', () => {
+		it('should return max_completion_tokens for GPT-5 models', () => {
+			const result = provider.prepareTokenParam('gpt-5', 1000);
+			expect(result).toEqual({ max_completion_tokens: 1000 });
+		});
+
+		it('should return maxTokens for non-GPT-5 models', () => {
+			const result = provider.prepareTokenParam('gpt-4', 1000);
+			expect(result).toEqual({ maxTokens: 1000 });
+		});
+
+		it('should coerce token value to integer', () => {
+			// Float values
+			const result1 = provider.prepareTokenParam('gpt-5', 1000.7);
+			expect(result1).toEqual({ max_completion_tokens: 1000 });
+
+			const result2 = provider.prepareTokenParam('gpt-4', 1000.7);
+			expect(result2).toEqual({ maxTokens: 1000 });
+
+			// String float
+			const result3 = provider.prepareTokenParam('gpt-5', '1000.7');
+			expect(result3).toEqual({ max_completion_tokens: 1000 });
+
+			// String integers (common CLI input path)
+			expect(provider.prepareTokenParam('gpt-5', '1000')).toEqual({
+				max_completion_tokens: 1000
+			});
+			expect(provider.prepareTokenParam('gpt-4', '1000')).toEqual({
+				maxTokens: 1000
+			});
+		});
+
+		it('should return empty object for undefined maxTokens', () => {
+			const result = provider.prepareTokenParam('gpt-5', undefined);
+			expect(result).toEqual({});
+		});
+
+		it('should handle edge cases', () => {
+			// Test with 0 (should still pass through as 0)
+			const result1 = provider.prepareTokenParam('gpt-5', 0);
+			expect(result1).toEqual({ max_completion_tokens: 0 });
+
+			// Test with string number
+			const result2 = provider.prepareTokenParam('gpt-5', '100');
+			expect(result2).toEqual({ max_completion_tokens: 100 });
+
+			// Test with negative number (will be floored, validation happens elsewhere)
+			const result3 = provider.prepareTokenParam('gpt-4', -10.5);
+			expect(result3).toEqual({ maxTokens: -11 });
+		});
+	});
+
+	describe('validateOptionalParams', () => {
+		it('should accept valid maxTokens values', () => {
+			expect(() =>
+				provider.validateOptionalParams({ maxTokens: 1000 })
+			).not.toThrow();
+			expect(() =>
+				provider.validateOptionalParams({ maxTokens: 1 })
+			).not.toThrow();
+			expect(() =>
+				provider.validateOptionalParams({ maxTokens: '1000' })
+			).not.toThrow();
+		});
+
+		it('should reject invalid maxTokens values', () => {
+			expect(() => provider.validateOptionalParams({ maxTokens: 0 })).toThrow(
+				Error
+			);
+			expect(() => provider.validateOptionalParams({ maxTokens: -1 })).toThrow(
+				Error
+			);
+			expect(() => provider.validateOptionalParams({ maxTokens: NaN })).toThrow(
+				Error
+			);
+			expect(() =>
+				provider.validateOptionalParams({ maxTokens: Infinity })
+			).toThrow(Error);
+			expect(() =>
+				provider.validateOptionalParams({ maxTokens: 'invalid' })
+			).toThrow(Error);
+		});
+
+		it('should accept valid temperature values', () => {
+			expect(() =>
+				provider.validateOptionalParams({ temperature: 0 })
+			).not.toThrow();
+			expect(() =>
+				provider.validateOptionalParams({ temperature: 0.5 })
+			).not.toThrow();
+			expect(() =>
+				provider.validateOptionalParams({ temperature: 1 })
+			).not.toThrow();
+		});
+
+		it('should reject invalid temperature values', () => {
+			expect(() =>
+				provider.validateOptionalParams({ temperature: -0.1 })
+			).toThrow(Error);
+			expect(() =>
+				provider.validateOptionalParams({ temperature: 1.1 })
+			).toThrow(Error);
+		});
+	});
+
+	describe('getRequiredApiKeyName', () => {
+		it('should return OPENAI_API_KEY', () => {
+			expect(provider.getRequiredApiKeyName()).toBe('OPENAI_API_KEY');
+		});
+	});
+
+	describe('getClient', () => {
+		it('should throw error if API key is missing', () => {
+			expect(() => provider.getClient({})).toThrow(Error);
+		});
+
+		it('should create client with apiKey only', () => {
+			const params = {
+				apiKey: 'sk-test-123'
+			};
+
+			// The getClient method should return a function
+			const client = provider.getClient(params);
+			expect(typeof client).toBe('function');
+
+			// The client function should be callable and return a model object
+			const model = client('gpt-4');
+			expect(model).toBeDefined();
+			expect(model.modelId).toBe('gpt-4');
+		});
+
+		it('should create client with apiKey and baseURL', () => {
+			const params = {
+				apiKey: 'sk-test-456',
+				baseURL: 'https://api.openai.example'
+			};
+
+			// Should not throw when baseURL is provided
+			const client = provider.getClient(params);
+			expect(typeof client).toBe('function');
+
+			// The client function should be callable and return a model object
+			const model = client('gpt-5');
+			expect(model).toBeDefined();
+			expect(model.modelId).toBe('gpt-5');
+		});
+
+		it('should return the same client instance for the same parameters', () => {
+			const params = {
+				apiKey: 'sk-test-789'
+			};
+
+			// Multiple calls with same params should work
+			const client1 = provider.getClient(params);
+			const client2 = provider.getClient(params);
+
+			expect(typeof client1).toBe('function');
+			expect(typeof client2).toBe('function');
+
+			// Both clients should be able to create models
+			const model1 = client1('gpt-4');
+			const model2 = client2('gpt-4');
+			expect(model1.modelId).toBe('gpt-4');
+			expect(model2.modelId).toBe('gpt-4');
+		});
+
+		it('should handle different model IDs correctly', () => {
+			const client = provider.getClient({ apiKey: 'sk-test-models' });
+
+			// Test with different models
+			const gpt4 = client('gpt-4');
+			expect(gpt4.modelId).toBe('gpt-4');
+
+			const gpt5 = client('gpt-5');
+			expect(gpt5.modelId).toBe('gpt-5');
+
+			const gpt35 = client('gpt-3.5-turbo');
+			expect(gpt35.modelId).toBe('gpt-3.5-turbo');
+		});
+	});
+
+	describe('name property', () => {
+		it('should have OpenAI as the provider name', () => {
+			expect(provider.name).toBe('OpenAI');
+		});
+	});
+});