rrce-workflow 0.2.80 → 0.2.81

package/agent-core/prompts/doctor.md

@@ -2,7 +2,7 @@
 name: RRCE Doctor
 description: Analyze codebase health using semantic search; identify issues and recommend improvement tasks.
 argument-hint: "[PROJECT_NAME=<name>] [FOCUS_AREA=<area>]"
-tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'list_projects']
+tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'list_projects', 'create_task']
 required-args: []
 optional-args:
   - name: PROJECT_NAME
@@ -55,7 +55,7 @@ For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 ### Step 1: Load Project Context
 
 ```
-Tool: get_project_context
+Tool: rrce_get_project_context
 Args: { "project": "{{WORKSPACE_NAME}}" }
 ```
 
@@ -93,7 +93,7 @@ Use `search_knowledge` to efficiently find problem areas. Run queries based on F
 
 **Query Execution:**
 ```
-Tool: search_knowledge
+Tool: rrce_search_knowledge
 Args: { "query": "<query>", "project": "{{WORKSPACE_NAME}}" }
 ```
 

package/agent-core/prompts/documentation.md

@@ -2,7 +2,7 @@
 name: RRCE Documentation
 description: Produce project documentation aligned with the latest delivery.
 argument-hint: "DOC_TYPE=<type> [TASK_SLUG=<slug> | TARGET_PATH=<relative>] [RELEASE_REF=<tag/sha>]"
-tools: ['search_knowledge', 'get_project_context', 'list_projects', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
+tools: ['search_knowledge', 'get_project_context', 'list_projects', 'update_task', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args:
   - name: DOC_TYPE
     prompt: "Enter the documentation type (e.g., api, architecture, runbook, changelog)"
@@ -44,11 +44,16 @@ Pipeline Position
 1. **Path Resolution**: Always use the "System Resolved Paths" from the context preamble.
    - Use `{{RRCE_DATA}}` for all RRCE-specific storage.
    - Use `{{WORKSPACE_ROOT}}` for project source code.
-2. **File Writing**: When using the `write` tool:
+2. **Metadata Updates**: For `meta.json` changes, use the MCP tool:
+   ```
+   Tool: rrce_update_task
+   Args: { "project": "{{WORKSPACE_NAME}}", "task_slug": "{{TASK_SLUG}}", "updates": { ... } }
+   ```
+   This tool saves the file automatically. Do NOT use `write` for meta.json.
+3. **File Writing**: When using the `write` tool for other files:
    - The `content` parameter **MUST be a string**.
-   - If writing JSON (like `meta.json`), you **MUST stringify it** first.
-   - Example: `write(filePath, JSON.stringify(data, null, 2))`
-3. **Directory Safety**: Use `bash` with `mkdir -p` to ensure parent directories exist before writing files if they might be missing.
+   - For JSON in other files, stringify first: `JSON.stringify(data, null, 2)`
+4. **Directory Safety**: Use `bash` with `mkdir -p` to ensure parent directories exist before writing files if they might be missing.
 
 Prerequisites (RECOMMENDED)
 If a `TASK_SLUG` is provided:

package/agent-core/prompts/executor.md

@@ -2,7 +2,7 @@
 name: RRCE Executor
 description: Execute the planned tasks to deliver working code and tests. The ONLY agent authorized to modify source code.
 argument-hint: "TASK_SLUG=<slug> [BRANCH=<git ref>]"
-tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'terminalLastCommand', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
+tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'update_task', 'terminalLastCommand', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args:
   - name: TASK_SLUG
     prompt: "Enter the task slug to execute"
@@ -79,11 +79,16 @@ Before touching ANY code, verify ALL of the following in order:
 1. **Path Resolution**: Always use the "System Resolved Paths" from the context preamble.
    - Use `{{RRCE_DATA}}` for all RRCE-specific storage.
    - Use `{{WORKSPACE_ROOT}}` for project source code.
-2. **File Writing**: When using the `write` tool:
+2. **Metadata Updates**: For `meta.json` changes, use the MCP tool:
+   ```
+   Tool: rrce_update_task
+   Args: { "project": "{{WORKSPACE_NAME}}", "task_slug": "{{TASK_SLUG}}", "updates": { ... } }
+   ```
+   This tool saves the file automatically. Do NOT use `write` for meta.json.
+3. **File Writing**: When using the `write` tool for other files:
    - The `content` parameter **MUST be a string**.
-   - If writing JSON (like `meta.json`), you **MUST stringify it** first.
-   - Example: `write(filePath, JSON.stringify(data, null, 2))`
-3. **Directory Safety**: Use `bash` with `mkdir -p` to ensure parent directories exist before writing files if they might be missing.
+   - For JSON in other files, stringify first: `JSON.stringify(data, null, 2)`
+4. **Directory Safety**: Use `bash` with `mkdir -p` to ensure parent directories exist before writing files if they might be missing.
 
 ## Mission
 - Implement the scoped work as defined in the execution plan
@@ -96,7 +101,7 @@ Before touching ANY code, verify ALL of the following in order:
 
 Before implementing, search for relevant patterns:
 ```
-Tool: search_knowledge
+Tool: rrce_search_knowledge
 Args: { "query": "<component or pattern name>", "project": "{{WORKSPACE_NAME}}" }
 ```
 
@@ -262,7 +267,7 @@ After completing execution:
 
 If significant code was added or modified, suggest running:
 ```
-Tool: index_knowledge
+Tool: rrce_index_knowledge
 Args: { "project": "{{WORKSPACE_NAME}}" }
 ```
 

package/agent-core/prompts/init.md

@@ -132,7 +132,7 @@ Scan in this priority order. Stop early if sufficient information gathered:
 **Always run after generating/updating context:**
 
 ```
-Tool: index_knowledge
+Tool: rrce_index_knowledge
 Args: { "project": "{{WORKSPACE_NAME}}" }
 ```
 

package/agent-core/prompts/planning_discussion.md

@@ -2,7 +2,7 @@
 name: RRCE Planning
 description: Transform research findings into an actionable execution plan through interactive task breakdown.
 argument-hint: "TASK_SLUG=<slug>"
-tools: ['search_knowledge', 'get_project_context', 'list_projects', 'read', 'glob', 'grep', 'write', 'bash']
+tools: ['search_knowledge', 'get_project_context', 'list_projects', 'update_task', 'read', 'glob', 'grep', 'write', 'bash']
 required-args:
   - name: TASK_SLUG
     prompt: "Enter the task slug to create a plan for"
@@ -52,13 +52,18 @@ For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 1. **Path Resolution**: Always use the "System Resolved Paths" from the context preamble.
    - Use `{{RRCE_DATA}}` for all RRCE-specific storage.
    - Use `{{WORKSPACE_ROOT}}` for reading project source code (READ ONLY).
-2. **File Writing**: When using the `write` tool:
+2. **Metadata Updates**: For `meta.json` changes, use the MCP tool:
+   ```
+   Tool: rrce_update_task
+   Args: { "project": "{{WORKSPACE_NAME}}", "task_slug": "{{TASK_SLUG}}", "updates": { ... } }
+   ```
+   This tool saves the file automatically. Do NOT use `write` for meta.json.
+3. **File Writing**: When using the `write` tool for other files:
    - The `content` parameter **MUST be a string**.
-   - If writing JSON (like `meta.json`), you **MUST stringify it** first.
-   - Example: `write(filePath, JSON.stringify(data, null, 2))`
-3. **Write Permissions**: You may ONLY write to:
+   - For JSON in other files, stringify first: `JSON.stringify(data, null, 2)`
+4. **Write Permissions**: You may ONLY write to:
    - `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/planning/` (plan artifacts)
-   - `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` (metadata)
+   - `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` (metadata via rrce_update_task)
    - `{{RRCE_DATA}}/knowledge/` (new knowledge documents)
 
 ## Prerequisites (STRICT)
@@ -113,7 +118,7 @@ Extract and internalize:
 
 Search for related patterns and prior art:
 ```
-Tool: search_knowledge
+Tool: rrce_search_knowledge
 Args: { "query": "<task keywords>", "project": "{{WORKSPACE_NAME}}" }
 ```
 
@@ -273,7 +278,7 @@ After saving the plan and updating metadata:
 
 If new knowledge files were created in `{{RRCE_DATA}}/knowledge/`, suggest running:
 ```
-Tool: index_knowledge
+Tool: rrce_index_knowledge
 Args: { "project": "{{WORKSPACE_NAME}}" }
 ```
 

package/agent-core/prompts/research_discussion.md

@@ -2,7 +2,7 @@
 name: RRCE Research
 description: Interactive research and requirements clarification through constructive dialogue. Achieves 100% understanding before planning.
 argument-hint: REQUEST="<user prompt>" [TASK_SLUG=<slug>] [TITLE="<task title>"] [SOURCE=<url>]
-tools: ['search_knowledge', 'get_project_context', 'list_projects', 'read', 'glob', 'grep', 'write', 'bash']
+tools: ['search_knowledge', 'get_project_context', 'list_projects', 'create_task', 'update_task', 'read', 'glob', 'grep', 'write', 'bash']
 required-args:
   - name: TASK_SLUG
     prompt: "Enter a task slug (kebab-case identifier)"
@@ -57,13 +57,18 @@ For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 1. **Path Resolution**: Always use the "System Resolved Paths" from the context preamble.
    - Use `{{RRCE_DATA}}` for all RRCE-specific storage.
    - Use `{{WORKSPACE_ROOT}}` for reading project source code (READ ONLY).
-2. **File Writing**: When using the `write` tool:
+2. **Metadata Updates**: For `meta.json` changes, use the MCP tool:
+   ```
+   Tool: rrce_update_task
+   Args: { "project": "{{WORKSPACE_NAME}}", "task_slug": "{{TASK_SLUG}}", "updates": { ... } }
+   ```
+   This tool saves the file automatically. Do NOT use `write` for meta.json.
+3. **File Writing**: When using the `write` tool for other files:
    - The `content` parameter **MUST be a string**.
-   - If writing JSON (like `meta.json`), you **MUST stringify it** first.
-   - Example: `write(filePath, JSON.stringify(data, null, 2))`
-3. **Write Permissions**: You may ONLY write to:
+   - For JSON in other files, stringify first: `JSON.stringify(data, null, 2)`
+4. **Write Permissions**: You may ONLY write to:
    - `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/` (task artifacts)
-   - `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` (metadata)
+   - `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` (metadata via rrce_update_task)
 
 ## Mission
 - Challenge and refine the incoming request until intent, constraints, and success criteria are explicit
@@ -78,7 +83,7 @@ For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 **Search existing knowledge for relevant context:**
 
 ```
-Tool: search_knowledge
+Tool: rrce_search_knowledge
 Args: { "query": "<keywords from REQUEST>", "project": "{{WORKSPACE_NAME}}" }
 ```
 
@@ -91,7 +96,7 @@ Look for:
 **Get project context:**
 
 ```
-Tool: get_project_context
+Tool: rrce_get_project_context
 Args: { "project": "{{WORKSPACE_NAME}}" }
 ```
 

package/agent-core/prompts/sync.md

@@ -2,7 +2,7 @@
 name: RRCE Sync
 description: Reconcile project state with the RRCE knowledge base and update semantic index.
 argument-hint: "[SCOPE=<path|module>]"
-tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'list_projects', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
+tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'list_projects', 'update_task', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args: []
 optional-args:
   - name: SCOPE
@@ -27,11 +27,16 @@ Pipeline Position
 1. **Path Resolution**: Always use the "System Resolved Paths" from the context preamble.
    - Use `{{RRCE_DATA}}` for all RRCE-specific storage.
    - Use `{{WORKSPACE_ROOT}}` for project source code.
-2. **File Writing**: When using the `write` tool:
+2. **Metadata Updates**: For `meta.json` changes, use the MCP tool:
+   ```
+   Tool: rrce_update_task
+   Args: { "project": "{{WORKSPACE_NAME}}", "task_slug": "{{TASK_SLUG}}", "updates": { ... } }
+   ```
+   This tool saves the file automatically. Do NOT use `write` for meta.json.
+3. **File Writing**: When using the `write` tool for other files:
    - The `content` parameter **MUST be a string**.
-   - If writing JSON (like `meta.json`), you **MUST stringify it** first.
-   - Example: `write(filePath, JSON.stringify(data, null, 2))`
-3. **Directory Safety**: Use `bash` with `mkdir -p` to ensure parent directories exist before writing files if they might be missing.
+   - For JSON in other files, stringify first: `JSON.stringify(data, null, 2)`
+4. **Directory Safety**: Use `bash` with `mkdir -p` to ensure parent directories exist before writing files if they might be missing.
 
 Prerequisites (STRICT)
 1. **Project Context Exists**: Check `{{RRCE_DATA}}/knowledge/project-context.md` exists.
@@ -62,7 +67,7 @@ Workflow
 5. Summarize any unresolved questions or future sync needs at the bottom of the modified file(s) under a `Checklist` heading.
 6. **Semantic Indexing (MANDATORY)**: After updating any knowledge files, run the indexer to keep search current:
    ```
-   Tool: index_knowledge
+   Tool: rrce_index_knowledge
    Args: { "project": "{{WORKSPACE_NAME}}" }
    ```
 

package/dist/index.js

@@ -2821,7 +2821,7 @@ function registerToolHandlers(server) {
   server.setRequestHandler(ListToolsRequestSchema, async () => {
     const tools = [
       {
-        name: "search_knowledge",
+        name: "rrce_search_knowledge",
         description: "Search across all exposed project knowledge bases",
         inputSchema: {
           type: "object",
@@ -2833,7 +2833,7 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "index_knowledge",
+        name: "rrce_index_knowledge",
         description: "Update the semantic search index for a specific project",
         inputSchema: {
           type: "object",
@@ -2845,12 +2845,12 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "list_projects",
+        name: "rrce_list_projects",
         description: "List all projects exposed via MCP. Use these names for project-specific tools.",
         inputSchema: { type: "object", properties: {} }
       },
       {
-        name: "get_project_context",
+        name: "rrce_get_project_context",
         description: "Get the project context/architecture for a specific project",
         inputSchema: {
           type: "object",
@@ -2859,12 +2859,12 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "list_agents",
+        name: "rrce_list_agents",
         description: "List available agents (e.g. init, plan) and their arguments. Use this to discover which agent to call.",
         inputSchema: { type: "object", properties: {} }
       },
       {
-        name: "get_agent_prompt",
+        name: "rrce_get_agent_prompt",
         description: 'Get the system prompt for a specific agent. Accepts agent Name (e.g. "RRCE Init") or ID (e.g. "init").',
         inputSchema: {
           type: "object",
@@ -2876,7 +2876,7 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "list_tasks",
+        name: "rrce_list_tasks",
         description: "List all tasks for a project",
         inputSchema: {
           type: "object",
@@ -2885,7 +2885,7 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "get_task",
+        name: "rrce_get_task",
         description: "Get details of a specific task",
         inputSchema: {
           type: "object",
@@ -2897,7 +2897,7 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "create_task",
+        name: "rrce_create_task",
         description: "Create a new task in the project",
         inputSchema: {
           type: "object",
@@ -2911,7 +2911,7 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "update_task",
+        name: "rrce_update_task",
         description: "Update an existing task",
         inputSchema: {
           type: "object",
@@ -2924,7 +2924,7 @@ function registerToolHandlers(server) {
         }
       },
       {
-        name: "delete_task",
+        name: "rrce_delete_task",
         description: "Delete a task from the project",
         inputSchema: {
           type: "object",
@@ -2939,7 +2939,7 @@ function registerToolHandlers(server) {
     const projects = getExposedProjects();
     if (projects.length === 0) {
       tools.push({
-        name: "help_setup",
+        name: "rrce_help_setup",
         description: "Get help on how to configure projects for the RRCE MCP Server",
         inputSchema: { type: "object", properties: {} }
       });
@@ -2951,27 +2951,27 @@ function registerToolHandlers(server) {
     logger.info(`Calling tool: ${name}`, args);
     try {
       switch (name) {
-        case "search_knowledge": {
+        case "rrce_search_knowledge": {
           const params = args;
           const results = await searchKnowledge(params.query, params.project);
           return { content: [{ type: "text", text: JSON.stringify(results, null, 2) }] };
         }
-        case "index_knowledge": {
+        case "rrce_index_knowledge": {
           const params = args;
           const result = await indexKnowledge(params.project, params.force);
           return { content: [{ type: "text", text: JSON.stringify(result, null, 2) }] };
         }
-        case "list_projects": {
+        case "rrce_list_projects": {
           const projects = getExposedProjects();
           const list = projects.map((p) => ({ name: p.name, source: p.source, path: p.path }));
           return {
             content: [{
               type: "text",
-              text: JSON.stringify(list, null, 2) + "\n\nTip: Use these project names for tools like `get_project_context` or `index_knowledge`."
+              text: JSON.stringify(list, null, 2) + "\n\nTip: Use these project names for tools like `rrce_get_project_context` or `rrce_index_knowledge`."
             }]
           };
         }
-        case "get_project_context": {
+        case "rrce_get_project_context": {
           const context = getProjectContext(args.project);
           if (!context) {
             const projects = getExposedProjects().map((p) => p.name).join(", ");
@@ -2982,7 +2982,7 @@ Available projects: ${projects}`;
           }
           return { content: [{ type: "text", text: context }] };
         }
-        case "list_agents": {
+        case "rrce_list_agents": {
           const prompts = getAllPrompts();
           return {
             content: [{
@@ -2992,11 +2992,11 @@ Available projects: ${projects}`;
                 id: p.id,
                 description: p.description,
                 arguments: p.arguments
-              })), null, 2) + "\n\nTip: Retrieve the prompt for an agent using `get_agent_prompt` with its name or ID."
+              })), null, 2) + "\n\nTip: Retrieve the prompt for an agent using `rrce_get_agent_prompt` with its name or ID."
             }]
           };
         }
-        case "get_agent_prompt": {
+        case "rrce_get_agent_prompt": {
           const params = args;
           const agentName = params.agent;
           const promptDef = getPromptDef(agentName);
@@ -3021,12 +3021,12 @@ The system has pre-resolved the configuration for this project. Use these values
 `;
           return { content: [{ type: "text", text: contextPreamble + rendered }] };
         }
-        case "list_tasks": {
+        case "rrce_list_tasks": {
           const params = args;
           const tasks = getProjectTasks(params.project);
           return { content: [{ type: "text", text: JSON.stringify(tasks, null, 2) }] };
         }
-        case "get_task": {
+        case "rrce_get_task": {
           const params = args;
           const task = getTask(params.project, params.task_slug);
           if (!task) {
@@ -3034,26 +3034,28 @@ The system has pre-resolved the configuration for this project. Use these values
           }
           return { content: [{ type: "text", text: JSON.stringify(task, null, 2) }] };
         }
-        case "create_task": {
+        case "rrce_create_task": {
           const params = args;
           const taskData = {
             title: params.title || params.task_slug,
             summary: params.summary || ""
           };
           const task = await createTask(params.project, params.task_slug, taskData);
-          return { content: [{ type: "text", text: JSON.stringify(task, null, 2) }] };
+          return { content: [{ type: "text", text: `\u2713 Task '${params.task_slug}' created. meta.json saved.
+${JSON.stringify(task, null, 2)}` }] };
         }
-        case "update_task": {
+        case "rrce_update_task": {
           const params = args;
           const task = await updateTask(params.project, params.task_slug, params.updates);
-          return { content: [{ type: "text", text: JSON.stringify(task, null, 2) }] };
+          return { content: [{ type: "text", text: `\u2713 Task '${params.task_slug}' updated. meta.json saved.
+${JSON.stringify(task, null, 2)}` }] };
         }
-        case "delete_task": {
+        case "rrce_delete_task": {
           const params = args;
           const success = deleteTask(params.project, params.task_slug);
-          return { content: [{ type: "text", text: success ? `Task '${params.task_slug}' deleted.` : `Failed to delete task '${params.task_slug}'.` }] };
+          return { content: [{ type: "text", text: success ? `\u2713 Task '${params.task_slug}' deleted.` : `\u2717 Failed to delete '${params.task_slug}'.` }] };
         }
-        case "help_setup": {
+        case "rrce_help_setup": {
           const msg = `
 RRCE MCP Server is running, but no projects are configured/exposed.
 
@@ -3291,7 +3293,7 @@ async function handleConfigure() {
     enableSemanticSearch = shouldEnable;
     if (enableSemanticSearch) {
       note3(
-        `This enables "search_knowledge" tool for agents.
+        `This enables "rrce_search_knowledge" tool for agents.
 First use will download a ~100MB embedding model (all-MiniLM-L6-v2)
 to your local device (one-time).`,
         "Semantic Search Enabled"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rrce-workflow",
-  "version": "0.2.80",
+  "version": "0.2.81",
   "description": "RRCE-Workflow TUI - Agentic code workflow generator for AI-assisted development",
   "author": "RRCE Team",
   "license": "MIT",