rrce-workflow 0.2.73 → 0.2.74

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']
+tools: ['search_knowledge', 'get_project_context', 'list_projects', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args:
   - name: DOC_TYPE
     prompt: "Enter the documentation type (e.g., api, architecture, runbook, changelog)"
@@ -40,6 +40,16 @@ Pipeline Position
 - **Best After**: Executor phase complete (if documenting a specific task).
 - **Standalone**: Can also run independently to document general knowledge, architecture, or runbooks.
 
+## Technical Protocol (STRICT)
+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:
+   - 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.
+
 Prerequisites (RECOMMENDED)
 If a `TASK_SLUG` is provided:
 1. **Execution Complete** (recommended): Check `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` for `agents.executor.status === 'complete'`.

package/agent-core/prompts/executor.md

@@ -2,7 +2,7 @@
 name: RRCE Executor
 description: Execute the planned tasks to deliver working code and tests.
 argument-hint: "TASK_SLUG=<slug> [BRANCH=<git ref>]"
-tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'terminalLastCommand']
+tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'terminalLastCommand', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args:
   - name: TASK_SLUG
     prompt: "Enter the task slug to execute"
@@ -24,6 +24,16 @@ Pipeline Position
 - **Requires**: Planning phase must be complete before execution can begin.
 - **Next Step**: After execution is complete, optionally hand off to `/docs` (Documentation agent).
 
+## Technical Protocol (STRICT)
+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:
+   - 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.
+
 Prerequisites (STRICT)
 Before proceeding, verify ALL of the following:
 

package/agent-core/prompts/planning_orchestrator.md

@@ -2,7 +2,7 @@
 name: RRCE Planning
 description: Transform clarified requirements into an actionable execution plan.
 argument-hint: "TASK_SLUG=<slug>"
-tools: ['search_knowledge', 'get_project_context', 'list_projects']
+tools: ['search_knowledge', 'get_project_context', 'list_projects', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args:
   - name: TASK_SLUG
     prompt: "Enter the task slug to create a plan for"
@@ -22,6 +22,16 @@ Pipeline Position
 - **Correlation**: Planning works with Init to maintain project context. If planning reveals significant architectural changes, recommend running `/init` to update project context.
 - **Next Step**: After planning is complete, hand off to `/execute` (Executor agent).
 
+## Technical Protocol (STRICT)
+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:
+   - 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.
+
 Prerequisites (STRICT)
 Before proceeding, verify ALL of the following:
 

package/agent-core/prompts/research_discussion.md

@@ -2,7 +2,7 @@
 name: RRCE Research
 description: Research and clarify requirements by leveraging existing project knowledge before asking for clarification.
 argument-hint: REQUEST="<user prompt>" [TASK_SLUG=<slug>] [TITLE="<task title>"] [SOURCE=<url>]
-tools: ['search_knowledge', 'get_project_context', 'list_projects']
+tools: ['search_knowledge', 'get_project_context', 'list_projects', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args:
   - name: TASK_SLUG
     prompt: "Enter a task slug (kebab-case identifier)"
@@ -30,6 +30,16 @@ For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 - **Recommendation**: If `project-context.md` doesn't exist, suggest `/init` first for best results
 - **Next Step**: After research is complete, hand off to `/plan TASK_SLUG={{TASK_SLUG}}`
 
+## Technical Protocol (STRICT)
+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:
+   - 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.
+
 ## Mission
 - Challenge and refine the incoming request until intent, constraints, and success criteria are explicit
 - Leverage existing project knowledge BEFORE asking the user for clarification

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']
+tools: ['search_knowledge', 'get_project_context', 'index_knowledge', 'list_projects', 'read', 'write', 'edit', 'bash', 'glob', 'grep']
 required-args: []
 optional-args:
   - name: SCOPE
@@ -23,6 +23,16 @@ Pipeline Position
 - **Requires**: Init must have been run at least once (project-context.md must exist).
 - **Triggers Init**: If sync detects major structural changes, recommend running `/init` to update project context.
 
+## Technical Protocol (STRICT)
+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:
+   - 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.
+
 Prerequisites (STRICT)
 1. **Project Context Exists**: Check `{{RRCE_DATA}}/knowledge/project-context.md` exists.
    - If missing, **STOP** and prompt user:

package/dist/index.js

@@ -393,9 +393,17 @@ function parseWorkspaceConfig(configPath) {
   }
 }
 function findClosestProject(projects, cwd = process.cwd()) {
-  const matches = projects.filter((p) => cwd.startsWith(p.path));
-  matches.sort((a, b) => b.path.length - a.path.length);
-  return matches[0];
+  const matches = projects.map((p) => {
+    let matchPath = "";
+    if (cwd.startsWith(p.path)) {
+      matchPath = p.path;
+    } else if (p.sourcePath && cwd.startsWith(p.sourcePath)) {
+      matchPath = p.sourcePath;
+    }
+    return { project: p, matchPath };
+  }).filter((m) => m.matchPath !== "");
+  matches.sort((a, b) => b.matchPath.length - a.matchPath.length);
+  return matches[0]?.project;
 }
 var SKIP_DIRECTORIES;
 var init_detection = __esm({
@@ -1253,7 +1261,16 @@ function copyPromptsToDir(prompts, targetDir, extension) {
 }
 function convertToOpenCodeAgent(prompt) {
   const { frontmatter, content } = prompt;
-  const tools = {};
+  const tools = {
+    // Enable standard host tools by default
+    "read": true,
+    "write": true,
+    "edit": true,
+    "bash": true,
+    "grep": true,
+    "glob": true,
+    "webfetch": true
+  };
   if (frontmatter.tools) {
     for (const tool of frontmatter.tools) {
       tools[`rrce_${tool}`] = true;
@@ -1262,7 +1279,7 @@ function convertToOpenCodeAgent(prompt) {
   const opencodeFrontmatter = {
     description: frontmatter.description,
     mode: "primary",
-    tools: Object.keys(tools).length > 0 ? tools : void 0
+    tools
   };
   return `---
 ${stringify(opencodeFrontmatter)}---
@@ -1676,12 +1693,15 @@ function installAgentPrompts(config, workspacePath, dataPaths) {
       }
     }
     if (config.tools.includes("opencode")) {
-      const opencodePath = path12.join(workspacePath, ".opencode", "agent");
-      ensureDir(opencodePath);
-      for (const prompt of prompts) {
-        const baseName = path12.basename(prompt.filePath, ".md");
-        const content = convertToOpenCodeAgent(prompt);
-        fs10.writeFileSync(path12.join(opencodePath, `${baseName}.md`), content);
+      const primaryDataPath = dataPaths[0];
+      if (primaryDataPath) {
+        const opencodePath = path12.join(primaryDataPath, ".opencode", "agent");
+        ensureDir(opencodePath);
+        for (const prompt of prompts) {
+          const baseName = path12.basename(prompt.filePath, ".md");
+          const content = convertToOpenCodeAgent(prompt);
+          fs10.writeFileSync(path12.join(opencodePath, `${baseName}.md`), content);
+        }
       }
     }
   }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rrce-workflow",
-  "version": "0.2.73",
+  "version": "0.2.74",
   "description": "RRCE-Workflow TUI - Agentic code workflow generator for AI-assisted development",
   "author": "RRCE Team",
   "license": "MIT",