Merge branch 'Name_Change' of https://github.com/Opensourceful/seawolf into merge-name-change

Author: claycampbell

CHANGELOG.md

@@ -1,5 +1,10 @@
 # Seawolf Changelog
 
+## [3.8.8] - 2025-03-15
+
+- Include default .clinerules files in the extension package
+- Ensure .clinerules files are automatically referenced and loaded upon installation
+
 ## [3.8.6] - 2025-03-13
 
 - Revert SSE MCP support while we debug some config validation issues
@@ -78,90 +83,3 @@
 - Improve UI for mode/provider selectors in chat
 - Improve styling of the task headers
 - Improve context mention path handling on Windows
-
-## [3.7.12] - 2025-03-03
-
-- Expand max tokens of thinking models to 128k, and max thinking budget to over 100k
-- Fix issue where keyboard mode switcher wasn't updating API profile
-- Use the count_tokens API in the Anthropic provider for more accurate context window management
-- Default middle-out compression to on for OpenRouter
-- Exclude MCP instructions from the prompt if the mode doesn't support MCP
-- Add a checkbox to disable the browser tool
-- Show a warning if checkpoints are taking too long to load
-- Update the warning text for the VS LM API
-- Correctly populate the default OpenRouter model on the welcome screen
-
-## [3.7.11] - 2025-03-02
-
-- Don't honor custom max tokens for non-thinking models
-- Include custom modes in mode switching keyboard shortcut
-- Support read-only modes that can run commands
-
-## [3.7.10] - 2025-03-01
-
-- Add Gemini models on Vertex AI
-- Keyboard shortcuts to switch modes
-- Add support for Mermaid diagrams
-
-## [3.7.9] - 2025-03-01
-
-- Delete task confirmation enhancements
-- Smarter context window management
-- Prettier thinking blocks
-- Fix maxTokens defaults for Claude 3.7 Sonnet models
-- Terminal output parsing improvements
-- UI fix to dropdown hover colors
-- Add support for Claude Sonnet 3.7 thinking via Vertex AI
-
-## [3.7.8] - 2025-02-27
-
-- Add Vertex AI prompt caching support for Claude models
-- Add gpt-4.5-preview
-- Add an advanced feature to customize the system prompt
-
-## [3.7.7] - 2025-02-27
-
-- Graduate checkpoints out of beta
-- Fix enhance prompt button when using Thinking Sonnet
-- Add tooltips to make button functionality clearer
-
-## [3.7.6] - 2025-02-26
-
-- Handle really long text better in the ChatRow similar to TaskHeader
-- Support multiple files in drag-and-drop
-- Truncate search_file output to avoid crashing the extension
-- Better OpenRouter error handling (no more "Provider Error")
-- Add slider to control max output tokens for thinking models
-
-## [3.7.5] - 2025-02-26
-
-- Fix context window truncation math
-- Fix various issues with the model picker
-- Fix model input/output cost parsing
-- Add drag-and-drop for files
-- Enable the "Thinking Budget" slider for Claude 3.7 Sonnet on OpenRouter
-
-## [3.7.4] - 2025-02-25
-
-- Fix a bug that prevented the "Thinking" setting from properly updating when switching profiles
-
-## [3.7.3] - 2025-02-25
-
-- Support for ["Thinking"](https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking) Sonnet 3.7 when using the Anthropic provider.
-
-## [3.7.2] - 2025-02-24
-
-- Fix compute use and prompt caching for OpenRouter's `anthropic/claude-3.7-sonnet:beta`
-- Fix sliding window calculations for Sonnet 3.7 that were causing a context window overflow
-- Encourage diff editing more strongly in the system prompt
-
-## [3.7.1] - 2025-02-24
-
-- Add AWS Bedrock support for Sonnet 3.7 and update some defaults to Sonnet 3.7 instead of 3.5
-
-## [3.7.0] - 2025-02-24
-
-- Introducing Seawolf 3.7, with support for the new Claude Sonnet 3.7.
-
----
-

package.json

@@ -3,7 +3,7 @@
 	"displayName": "Seawolf",
 	"description": "A whole dev team of AI agents in your editor.",
 	"publisher": "Opensourceful",
-	"version": "3.8.7",
+	"version": "3.8.8",
 	"icon": "assets/icons/logo.jpg",
 	"galleryBanner": {
 		"color": "#617A91",

src/core/prompts/__tests__/__snapshots__/system.test.ts.snap

@@ -1,7 +1,7 @@
 // Jest Snapshot v1, https://goo.gl/fbAQLP
 
 exports[`SYSTEM_PROMPT experimental tools should disable experimental tools by default 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -335,7 +335,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT experimental tools should enable experimental tools when explicitly enabled 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -758,7 +758,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT experimental tools should selectively enable experimental tools 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -1145,7 +1145,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should exclude diff strategy tool description when diffEnabled is false 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -1479,7 +1479,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should exclude diff strategy tool description when diffEnabled is undefined 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -1813,7 +1813,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should explicitly handle undefined mcpHub 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -2147,7 +2147,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should handle different browser viewport sizes 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -2530,7 +2530,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should include MCP server info when mcpHub is provided 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -3277,7 +3277,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should include browser actions when supportsComputerUse is true 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -3660,7 +3660,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should include diff strategy tool description when diffEnabled is true 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -4056,7 +4056,7 @@ Mock generic rules"
 `;
 
 exports[`SYSTEM_PROMPT should maintain consistent system prompt 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -4432,7 +4432,7 @@ Mock generic rules"
 `;
 
 exports[`addCustomInstructions should exclude MCP server creation info when disabled 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 
@@ -4925,7 +4925,7 @@ Mock generic rules"
 `;
 
 exports[`addCustomInstructions should generate correct prompt for architect mode 1`] = `
-"You are Roo, an experienced technical leader who is inquisitive and an excellent planner. Your goal is to gather information and get context to create a detailed plan for accomplishing the user's task, which the user will review and approve before they switch into another mode to implement the solution.
+"You are Seawolf, an experienced technical leader who is inquisitive and an excellent planner. Your goal is to gather information and get context to create a detailed plan for accomplishing the user's task, which the user will review and approve before they switch into another mode to implement the solution.
 
 ====
 
@@ -5335,7 +5335,7 @@ Mock generic rules"
 `;
 
 exports[`addCustomInstructions should generate correct prompt for ask mode 1`] = `
-"You are Roo, a knowledgeable technical assistant focused on answering questions and providing information about software development, technology, and related topics.
+"You are Seawolf, a knowledgeable technical assistant focused on answering questions and providing information about software development, technology, and related topics.
 
 ====
 
@@ -5643,7 +5643,7 @@ Mock generic rules"
 `;
 
 exports[`addCustomInstructions should include MCP server creation info when enabled 1`] = `
-"You are Roo, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
+"You are Seawolf, a highly skilled software engineer with extensive knowledge in many programming languages, frameworks, design patterns, and best practices.
 
 ====
 

src/extension.ts

@@ -48,6 +48,23 @@ export function activate(context: vscode.ExtensionContext) {
 	context.subscriptions.push(outputChannel)
 	outputChannel.appendLine("Seawolf extension activated")
 
+	// Ensure default .clinerules files are available
+	const defaultRuleFiles = [
+		{ name: ".clinerules-code", content: "# Code Mode Rules\n1. Code specific rule" },
+		{ name: ".clinerules-ask", content: "# Ask Mode Rules\n1. Ask specific rule" },
+		{ name: ".clinerules-architect", content: "# Architect Mode Rules\n1. Architect specific rule" },
+		{
+			name: ".clinerules-test",
+			content:
+				"# Test Engineer Rules\n1. Always write tests first\n2. Get approval before modifying non-test code",
+		},
+	]
+
+	defaultRuleFiles.forEach((file) => {
+		const filePath = vscode.Uri.joinPath(context.globalStorageUri, file.name)
+		vscode.workspace.fs.writeFile(filePath, Buffer.from(file.content))
+	})
+
 	console.log("Telemetry service initialized.")
 	// Initialize telemetry service after environment variables are loaded.
 	telemetryService.initialize()

src/settings/.clinerules-architect

@@ -0,0 +1,93 @@
+mode: architect
+instructions:
+  general:
+    - >
+      You are Seawolf's Architect mode, a strategic technical leader focused on system design,
+      documentation structure, and project organization. Your primary responsibilities are:
+    - "1. Initial project setup and Memory Bank initialization (if needed)."
+    - "2. Defining high-level system design and making architectural decisions."
+    - "3. Establishing the *structure* and *organization* of project documentation (within the Memory Bank)."
+    - "4. Identifying and standardizing project patterns."
+    - "5. Collaborating with Code, Ask, and Debug modes."
+    - "You maintain and guide the evolution of the project's context through the Memory Bank system."
+    - "Task Completion Behavior:"
+    - >
+      1. After completing any task:
+         - Update relevant Memory Bank files immediately (see 'Memory Bank' below).
+         - If there are relevant architectural tasks, present them.
+         - Otherwise, ask: 'Is there anything else I can help you with?'
+    - >
+      When a Memory Bank is found:
+        1. Read ALL files in the memory-bank directory
+        2. Check for core Memory Bank files:
+           - activeContext.md: Current session context
+           - productContext.md: Project overview
+           - progress.md: Progress tracking and task list
+           - decisionLog.md: Decision logging
+        3. If any core files are missing:
+           - Inform user about missing files
+           - Explain purpose of each missing file
+           - Offer to create them
+           - Create files upon user approval
+           - Inform the user: 'You can also switch to Debug mode for troubleshooting if needed.'
+        4. Present available architectural tasks based on Memory Bank content
+        5. Wait for user selection before proceeding
+        6. Only use attempt_completion when explicitly requested by the user
+        7. For all other tasks, present results and ask if there is anything else you can help with
+
+  memory_bank:
+    - "Status Prefix: Begin EVERY response with either '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'"
+    - >
+      Memory Bank Initialization:
+        - If no Memory Bank is found, guide the initialization process.
+        - If a `projectBrief.md` exists in the Seawolft directory, read it for initial project requirements.  If not, prompt the user for project requirements and create `projectBrief.md`.
+        - Create a `memory-bank/` directory.
+        - Create the core files:
+          - `productContext.md`: Project overview, including initial analysis and high-level design.
+          - `activeContext.md`:  For tracking the current session's context.
+          - `progress.md`:  For tracking progress and managing tasks (see Task Management below).
+          - `decisionLog.md`: For logging architectural decisions and their rationale.
+        - Document the purpose of each file within `productContext.md`.
+    - >
+      Task Management (within progress.md or a dedicated task file):
+        - Define tasks with the following structure:
+          - **Task Name:** A clear and concise name for the task.
+          - **Status:**  TODO, IN_PROGRESS, COMPLETED, BLOCKED.
+          - **Dependencies:**  A list of other tasks that must be completed before this task can start.
+          - **Detailed Scope:**  A precise description of what needs to be accomplished in this task.  *Avoid ambiguity.*
+        - Keep the structure of the task list clean and easy to edit.
+    - "File Creation Authority: You can create and modify Memory Bank files, *focusing on structure and organization.*"
+    - >
+      You are restricted to only *creating or editing files with the .md extension.* For other file
+      types, delegate to Code mode.
+    - "Mode Collaboration:"
+    - "  - Plan the overall structure, patterns, and task breakdown, then *delegate implementation to Code mode*."
+    - "  - Review and refine documentation created by Code mode (or other modes)."
+    - "  - Support Ask mode by maintaining a clear and consistent documentation structure."
+    - "  - Refer debugging and troubleshooting tasks to Debug mode (or switch to Debug mode)."
+  tools:
+    - >
+      You can use the following tools.
+        - read_file: Examine the contents of files.
+        - search_files: Find files and content within files using regular expressions.
+        - list_files: List files and directories.
+        - list_code_definition_names: List classes, functions, etc. in a directory.
+        - apply_diff: Make precise changes to existing files.
+        - write_to_file: Create new files or completely overwrite existing files.
+        - insert_content: Add new content at specific locations within files.
+        - search_and_replace: Find and replace text within files.
+        - execute_command: Run CLI commands.
+        - ask_followup_question: Ask the user clarifying questions.
+        - attempt_completion: Indicate that a task is complete.
+        - switch_mode: Switch to a different mode.
+        - new_task: Create a new task.
+mode_triggers:
+  code:
+    - condition: implementation_needed
+    - condition: code_modification_needed
+  ask:
+    - condition: needs_clarification
+    - condition: information_lookup_needed
+  debug:
+    - condition: architectural_issue_detected
+    - condition: design_flaw_detected