rrce-workflow 0.2.70 → 0.2.72

package/README.md

@@ -66,19 +66,23 @@ The easiest way to connect is via the TUI (`npx rrce-workflow mcp` -> **Install*
 
 #### OpenCode
 
-Add to `~/.config/opencode/opencode.json`:
-```json
-{
-  "$schema": "https://opencode.ai/config.json",
-  "mcp": {
-    "rrce": {
-      "type": "local",
-      "command": ["npx", "-y", "rrce-workflow", "mcp", "start"],
-      "enabled": true
+RRCE-Workflow integrates with OpenCode both as an MCP server and by providing **Custom Primary Agents**.
+
+1.  **Register MCP Server**: Add the following to `~/.config/opencode/opencode.json`:
+    ```json
+    {
+      "$schema": "https://opencode.ai/config.json",
+      "mcp": {
+        "rrce": {
+          "type": "local",
+          "command": ["npx", "-y", "rrce-workflow", "mcp", "start"],
+          "enabled": true
+        }
+      }
     }
-  }
-}
-```
+    ```
+
+2.  **Install Agents**: Run `npx rrce-workflow` and select **OpenCode** as a tool. This will generate specialized primary agents (Research, Planning, etc.) in `.opencode/agent/` that you can cycle through using the **Tab** key in the OpenCode TUI.
 
 #### VSCode (with MCP Extension)
 Add to `.vscode/mcp.json`:

package/agent-core/prompts/doctor.md

@@ -20,7 +20,7 @@ You are the Project Doctor for RRCE-Workflow. Perform a health check on the code
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 ## Pipeline Position
 - **Input**: Can be triggered at any time for project health analysis
@@ -142,7 +142,7 @@ Rank findings using this matrix:
 ### Step 6: Generate Output
 
 1. Create task directory: `{{RRCE_DATA}}/tasks/doctor-{{YYYYMMDD}}/`
-2. Write diagnosis using template: `{{RRCE_HOME}}/templates/doctor_output.md`
+2. Write diagnosis using template: `{{RRCE_DATA}}/templates/doctor_output.md`
 3. Save to: `{{RRCE_DATA}}/tasks/doctor-{{YYYYMMDD}}/diagnosis.md`
 
 **Output includes:**
@@ -176,7 +176,7 @@ Report:
 ## Deliverable
 
 - **File**: `{{RRCE_DATA}}/tasks/doctor-{{YYYYMMDD}}/diagnosis.md`
-- **Template**: `{{RRCE_HOME}}/templates/doctor_output.md`
+- **Template**: `{{RRCE_DATA}}/templates/doctor_output.md`
 - **Outcome**: Structured diagnosis with prioritized, actionable tasks
 
 ## Focus Area Deep Dive

package/agent-core/prompts/documentation.md

@@ -22,7 +22,7 @@ You are the Documentation Lead for the project. Operate like a senior engineerin
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 ## Supported DOC_TYPE Values
 
@@ -68,7 +68,7 @@ Workflow
    - If `TASK_SLUG` is provided, ensure `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/docs` exists and target `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/docs/{{TASK_SLUG}}-{{DOC_TYPE}}.md`.
    - Else if `TARGET_PATH` is provided, ensure its parent directory exists (must remain under `{{RRCE_DATA}}/`) and target `{{RRCE_DATA}}/{{TARGET_PATH}}`.
    - Otherwise, default to `{{RRCE_DATA}}/knowledge/{{DOC_TYPE}}.md` and ensure `{{RRCE_DATA}}/knowledge` exists.
-3. Select a template: prefer `{{RRCE_HOME}}/templates/docs/{{DOC_TYPE}}.md`; fallback to `{{RRCE_HOME}}/templates/documentation_output.md`.
+3. Select a template: prefer `{{RRCE_DATA}}/templates/docs/{{DOC_TYPE}}.md`; fallback to `{{RRCE_DATA}}/templates/documentation_output.md`.
 4. Populate contextual metadata (`AUTHOR`, `RELEASE_REF`, task references, dates) and render the document using the chosen template.
 5. If operating on a task slug, update `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` with documentation artifact paths, new references, final decisions, checklist completions, and remaining follow-ups.
 6. When broader knowledge changed, update the relevant `{{RRCE_DATA}}/knowledge/*.md` entries with `Updated: YYYY-MM-DD` markers, lean changelog bullets, and a small checklist of follow-ups.
@@ -76,5 +76,5 @@ Workflow
 
 Deliverable
 - File: Resolved from `DOC_TYPE` plus either `TASK_SLUG`, `TARGET_PATH`, or default knowledge location.
-- Format: `{{RRCE_HOME}}/templates/docs/{{DOC_TYPE}}.md` when available; otherwise `{{RRCE_HOME}}/templates/documentation_output.md`.
+- Format: `{{RRCE_DATA}}/templates/docs/{{DOC_TYPE}}.md` when available; otherwise `{{RRCE_DATA}}/templates/documentation_output.md`.
 - Outcome: Documentation tailored to the requested type, summarizing scope, implementation, validations, decisions, references, and leftover work while keeping project knowledge synchronized.

package/agent-core/prompts/executor.md

@@ -18,7 +18,7 @@ You are the Executor for the project. Operate like a senior individual contribut
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 Pipeline Position
 - **Requires**: Planning phase must be complete before execution can begin.
@@ -85,7 +85,7 @@ Workflow
 2. Set `agents.executor.status` in `meta.json` to `in_progress` while working and `complete` after delivering.
 3. Maintain checklist entries with current progress markers and timestamps where helpful.
 4. Record checkpoints, blockers, and validation steps in `agents.executor.notes` and `references`.
-5. Capture your implementation log using `{{RRCE_HOME}}/templates/executor_output.md` and save it to `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/execution/{{TASK_SLUG}}-execution.md`, noting the provided `BRANCH` or current git ref.
+5. Capture your implementation log using `{{RRCE_DATA}}/templates/executor_output.md` and save it to `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/execution/{{TASK_SLUG}}-execution.md`, noting the provided `BRANCH` or current git ref.
 6. Summarize test evidence, code pointers, and outstanding follow-ups so documentation can build on it seamlessly.
 7. **Semantic Indexing**: If significant code was added or modified, suggest running `index_knowledge` to update the semantic search index:
    - Tool: `index_knowledge`
@@ -93,5 +93,5 @@ Workflow
 
 Deliverable
 - File: `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/execution/{{TASK_SLUG}}-execution.md`
-- Format: `{{RRCE_HOME}}/templates/executor_output.md`
+- Format: `{{RRCE_DATA}}/templates/executor_output.md`
 - Outcome: Implementation log covering what was built, how it was validated, and what remains, kept lean and actionable.

package/agent-core/prompts/init.md

@@ -17,7 +17,7 @@ You are the Project Initializer for RRCE-Workflow. Your mission: create a compre
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 ## Pipeline Position
 - **Entry Point**: Run before any other agent for new projects
@@ -122,7 +122,7 @@ Scan in this priority order. Stop early if sufficient information gathered:
 ### Step 3: Generate Project Context
 
 1. Ensure `{{RRCE_DATA}}/knowledge/` directory exists (create if absent)
-2. Compile findings using template: `{{RRCE_HOME}}/templates/init_output.md`
+2. Compile findings using template: `{{RRCE_DATA}}/templates/init_output.md`
 3. Save to: `{{RRCE_DATA}}/knowledge/project-context.md`
 4. Update `{{RRCE_DATA}}/workspace.json` with project metadata if it exists
 
@@ -160,7 +160,7 @@ Provide a brief summary:
 ## Deliverable
 
 - **File**: `{{RRCE_DATA}}/knowledge/project-context.md`
-- **Template**: `{{RRCE_HOME}}/templates/init_output.md`
+- **Template**: `{{RRCE_DATA}}/templates/init_output.md`
 - **Index**: `{{RRCE_DATA}}/knowledge/embeddings.json`
 - **Outcome**: Comprehensive project context + searchable semantic index
 

package/agent-core/prompts/planning_orchestrator.md

@@ -15,7 +15,7 @@ You are the Planning & Task Orchestrator for the project. Operate like an engine
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 Pipeline Position
 - **Requires**: Research phase must be complete before planning can begin.
@@ -58,12 +58,12 @@ Non-Negotiables
 
 Workflow
 1. Confirm `TASK_SLUG` (prompt if missing) and ensure directories exist at `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/planning` and `{{RRCE_DATA}}/knowledge`, creating them automatically if absent.
-2. Update `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` (copy the template from `{{RRCE_HOME}}/templates/meta.template.json` if it is not already present):
+2. Update `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` (copy the template from `{{RRCE_DATA}}/templates/meta.template.json` if it is not already present):
    - Mark `agents.planning.status` as `in_progress` while drafting and `complete` upon handoff.
    - Link the plan artifact path in `agents.planning.artifact`.
    - Populate or refresh `summary`, `references`, `milestones`, `checklist`, and `open_questions`.
 3. Where new persistent knowledge is created (API notes, domain decisions, etc.), append or create records in `{{RRCE_DATA}}/knowledge/{{DOMAIN}}.md` and log the file path inside `meta.json.references`.
-4. Structure the plan using `{{RRCE_HOME}}/templates/planning_output.md` and store it at `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/planning/{{TASK_SLUG}}-plan.md`.
+4. Structure the plan using `{{RRCE_DATA}}/templates/planning_output.md` and store it at `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/planning/{{TASK_SLUG}}-plan.md`.
 5. Provide clear guidance on validation, testing strategy, rollout sequencing, and success criteria for the Executor.
 6. **Semantic Indexing**: If new knowledge files were created in `{{RRCE_DATA}}/knowledge/`, suggest running `index_knowledge` to update the semantic search index:
    - Tool: `index_knowledge`
@@ -71,5 +71,5 @@ Workflow
 
 Deliverable
 - File: `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/planning/{{TASK_SLUG}}-plan.md`
-- Format: `{{RRCE_HOME}}/templates/planning_output.md`
+- Format: `{{RRCE_DATA}}/templates/planning_output.md`
 - Outcome: Ordered, actionable roadmap with dependencies, acceptance criteria, context links, and knowledge updates ready for implementation.

package/agent-core/prompts/research_discussion.md

@@ -22,7 +22,7 @@ You are the Research & Discussion Lead for RRCE-Workflow. Your mission: refine i
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 ## Pipeline Position
 - **Entry Point**: First agent invoked for new tasks
@@ -83,7 +83,7 @@ Based on knowledge search, create a gap analysis:
 ### Step 3: Setup Task Structure
 
 1. Ensure directory exists: `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/research/`
-2. Copy meta template if new task: `{{RRCE_HOME}}/templates/meta.template.json` → `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json`
+2. Copy meta template if new task: `{{RRCE_DATA}}/templates/meta.template.json` → `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json`
 3. Populate initial metadata:
    - `task_id`: Generate UUID
    - `task_slug`: From argument
@@ -127,7 +127,7 @@ Document the decision in `meta.json.decisions`.
 
 ### Step 6: Generate Research Brief
 
-1. Compile findings using template: `{{RRCE_HOME}}/templates/research_output.md`
+1. Compile findings using template: `{{RRCE_DATA}}/templates/research_output.md`
 2. Save to: `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/research/{{TASK_SLUG}}-research.md`
 
 **Brief includes:**
@@ -188,7 +188,7 @@ Research is complete when:
 ## Deliverable
 
 - **File**: `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/research/{{TASK_SLUG}}-research.md`
-- **Template**: `{{RRCE_HOME}}/templates/research_output.md`
+- **Template**: `{{RRCE_DATA}}/templates/research_output.md`
 - **Metadata**: `{{RRCE_DATA}}/tasks/{{TASK_SLUG}}/meta.json` with status `complete`
 - **Outcome**: Planning agent can proceed without re-asking the same questions
 

package/agent-core/prompts/sync.md

@@ -16,7 +16,7 @@ You are the Knowledge Sync Lead. Act like a senior architect charged with keepin
 
 ## Path Resolution
 Use the pre-resolved paths from the "System Resolved Paths" table in the context preamble.
-For details, see: `{{RRCE_HOME}}/docs/path-resolution.md`
+For details, see: `{{RRCE_DATA}}/docs/path-resolution.md`
 
 Pipeline Position
 - **Maintenance Agent**: Sync runs periodically or after significant codebase changes to keep knowledge current.

package/dist/index.js

@@ -1241,6 +1241,7 @@ var init_prompts = __esm({
 // src/commands/wizard/utils.ts
 import * as fs7 from "fs";
 import * as path8 from "path";
+import { stringify } from "yaml";
 function copyPromptsToDir(prompts, targetDir, extension) {
   for (const prompt of prompts) {
     const baseName = path8.basename(prompt.filePath, ".md");
@@ -1250,6 +1251,23 @@ function copyPromptsToDir(prompts, targetDir, extension) {
     fs7.writeFileSync(targetPath, content);
   }
 }
+function convertToOpenCodeAgent(prompt) {
+  const { frontmatter, content } = prompt;
+  const tools = {};
+  if (frontmatter.tools) {
+    for (const tool of frontmatter.tools) {
+      tools[`rrce_${tool}`] = true;
+    }
+  }
+  const opencodeFrontmatter = {
+    description: frontmatter.description,
+    mode: "primary",
+    tools: Object.keys(tools).length > 0 ? tools : void 0
+  };
+  return `---
+${stringify(opencodeFrontmatter)}---
+${content}`;
+}
 function copyDirRecursive(src, dest) {
   const entries = fs7.readdirSync(src, { withFileTypes: true });
   for (const entry of entries) {
@@ -1608,17 +1626,35 @@ function installAgentPrompts(config, workspacePath, dataPaths) {
   syncMetadataToAll(agentCoreDir, dataPaths);
   copyDirToAllStoragePaths(path11.join(agentCoreDir, "templates"), "templates", dataPaths);
   copyDirToAllStoragePaths(path11.join(agentCoreDir, "prompts"), "prompts", dataPaths);
-  if (config.storageMode === "workspace") {
+  copyDirToAllStoragePaths(path11.join(agentCoreDir, "docs"), "docs", dataPaths);
+  const rrceHome = config.globalPath || getDefaultRRCEHome2();
+  ensureDir(path11.join(rrceHome, "templates"));
+  ensureDir(path11.join(rrceHome, "docs"));
+  copyDirRecursive(path11.join(agentCoreDir, "templates"), path11.join(rrceHome, "templates"));
+  copyDirRecursive(path11.join(agentCoreDir, "docs"), path11.join(rrceHome, "docs"));
+  const needsIDEPrompts = config.storageMode === "workspace" && (config.tools.includes("copilot") || config.tools.includes("antigravity")) || config.tools.includes("opencode");
+  if (needsIDEPrompts) {
     const prompts = loadPromptsFromDir(getAgentCorePromptsDir());
-    if (config.tools.includes("copilot")) {
-      const copilotPath = getAgentPromptPath(workspacePath, "copilot");
-      ensureDir(copilotPath);
-      copyPromptsToDir(prompts, copilotPath, ".agent.md");
+    if (config.storageMode === "workspace") {
+      if (config.tools.includes("copilot")) {
+        const copilotPath = getAgentPromptPath(workspacePath, "copilot");
+        ensureDir(copilotPath);
+        copyPromptsToDir(prompts, copilotPath, ".agent.md");
+      }
+      if (config.tools.includes("antigravity")) {
+        const antigravityPath = getAgentPromptPath(workspacePath, "antigravity");
+        ensureDir(antigravityPath);
+        copyPromptsToDir(prompts, antigravityPath, ".md");
+      }
     }
-    if (config.tools.includes("antigravity")) {
-      const antigravityPath = getAgentPromptPath(workspacePath, "antigravity");
-      ensureDir(antigravityPath);
-      copyPromptsToDir(prompts, antigravityPath, ".md");
+    if (config.tools.includes("opencode")) {
+      const opencodePath = path11.join(workspacePath, ".opencode", "agent");
+      ensureDir(opencodePath);
+      for (const prompt of prompts) {
+        const baseName = path11.basename(prompt.filePath, ".md");
+        const content = convertToOpenCodeAgent(prompt);
+        fs10.writeFileSync(path11.join(opencodePath, `${baseName}.md`), content);
+      }
     }
   }
 }
@@ -2519,6 +2555,7 @@ var init_resources2 = __esm({
 });
 
 // src/mcp/prompts.ts
+import * as path16 from "path";
 function getAllPrompts() {
   const prompts = loadPromptsFromDir(getAgentCorePromptsDir());
   return prompts.map((p) => {
@@ -2555,6 +2592,40 @@ function getPromptDef(name) {
     (p) => p.name === name || p.id === name || p.name.toLowerCase() === search || p.id.toLowerCase() === search
   );
 }
+function renderPromptWithContext(content, args) {
+  const renderArgs = { ...args };
+  const activeProject = detectActiveProject();
+  const DEFAULT_RRCE_HOME = getEffectiveGlobalPath();
+  let resolvedRrceData = ".rrce-workflow/";
+  let resolvedRrceHome = DEFAULT_RRCE_HOME;
+  let resolvedWorkspaceRoot = process.cwd();
+  let resolvedWorkspaceName = "current-project";
+  if (activeProject) {
+    resolvedRrceData = activeProject.dataPath;
+    if (!resolvedRrceData.endsWith("/") && !resolvedRrceData.endsWith("\\")) {
+      resolvedRrceData += "/";
+    }
+    resolvedWorkspaceRoot = activeProject.sourcePath || activeProject.path || activeProject.dataPath;
+    resolvedWorkspaceName = activeProject.name;
+    if (activeProject.source === "global") {
+      const workspacesDir = path16.dirname(activeProject.dataPath);
+      resolvedRrceHome = path16.dirname(workspacesDir);
+    }
+  }
+  if (!renderArgs["RRCE_DATA"]) renderArgs["RRCE_DATA"] = resolvedRrceData;
+  if (!renderArgs["RRCE_HOME"]) renderArgs["RRCE_HOME"] = resolvedRrceHome;
+  if (!renderArgs["WORKSPACE_ROOT"]) renderArgs["WORKSPACE_ROOT"] = resolvedWorkspaceRoot;
+  if (!renderArgs["WORKSPACE_NAME"]) renderArgs["WORKSPACE_NAME"] = resolvedWorkspaceName;
+  return {
+    rendered: renderPrompt(content, renderArgs),
+    context: {
+      RRCE_DATA: resolvedRrceData,
+      RRCE_HOME: resolvedRrceHome,
+      WORKSPACE_ROOT: resolvedWorkspaceRoot,
+      WORKSPACE_NAME: resolvedWorkspaceName
+    }
+  };
+}
 function renderPrompt(content, args) {
   let rendered = content;
   for (const [key, val] of Object.entries(args)) {
@@ -2566,6 +2637,8 @@ var init_prompts2 = __esm({
   "src/mcp/prompts.ts"() {
     "use strict";
     init_prompts();
+    init_resources();
+    init_paths();
   }
 });
 
@@ -2707,9 +2780,17 @@ Available projects: ${projects}`;
           for (const [key, val] of Object.entries(renderArgs)) {
             stringArgs[key] = String(val);
           }
-          const content = renderPrompt(promptDef.content, stringArgs);
-          const contextPreamble = getContextPreamble();
-          return { content: [{ type: "text", text: contextPreamble + content }] };
+          const { rendered, context } = renderPromptWithContext(promptDef.content, stringArgs);
+          let contextPreamble = getContextPreamble();
+          contextPreamble += `
+### System Resolved Paths (OVERRIDE)
+The system has pre-resolved the configuration for this project. Use these values instead of manual resolution:
+- **RRCE_DATA**: \`${context.RRCE_DATA}\` (Stores knowledge, tasks, refs)
+- **WORKSPACE_ROOT**: \`${context.WORKSPACE_ROOT}\` (Source code location)
+- **RRCE_HOME**: \`${context.RRCE_HOME}\`
+- **Current Project**: ${context.WORKSPACE_NAME}
+`;
+          return { content: [{ type: "text", text: contextPreamble + rendered }] };
         }
         case "help_setup": {
           const msg = `
@@ -2747,7 +2828,6 @@ import {
   ListPromptsRequestSchema,
   GetPromptRequestSchema
 } from "@modelcontextprotocol/sdk/types.js";
-import * as path16 from "path";
 function registerPromptHandlers(server) {
   server.setRequestHandler(ListPromptsRequestSchema, async () => {
     logger.debug("Listing prompts");
@@ -2782,34 +2862,15 @@ function registerPromptHandlers(server) {
       for (const [key, val] of Object.entries(providedArgs)) {
         renderArgs[key] = String(val);
       }
-      const activeProject = detectActiveProject();
-      const DEFAULT_RRCE_HOME = getEffectiveGlobalPath();
-      let resolvedRrceData = ".rrce-workflow/";
-      let resolvedRrceHome = DEFAULT_RRCE_HOME;
-      let resolvedWorkspaceRoot = process.cwd();
-      let resolvedWorkspaceName = "current-project";
-      if (activeProject) {
-        resolvedRrceData = activeProject.dataPath + "/";
-        resolvedWorkspaceRoot = activeProject.sourcePath || activeProject.path || activeProject.dataPath;
-        resolvedWorkspaceName = activeProject.name;
-        if (activeProject.source === "global") {
-          const workspacesDir = path16.dirname(activeProject.dataPath);
-          resolvedRrceHome = path16.dirname(workspacesDir);
-        }
-      }
-      if (!renderArgs["RRCE_DATA"]) renderArgs["RRCE_DATA"] = resolvedRrceData;
-      if (!renderArgs["RRCE_HOME"]) renderArgs["RRCE_HOME"] = resolvedRrceHome;
-      if (!renderArgs["WORKSPACE_ROOT"]) renderArgs["WORKSPACE_ROOT"] = resolvedWorkspaceRoot;
-      if (!renderArgs["WORKSPACE_NAME"]) renderArgs["WORKSPACE_NAME"] = resolvedWorkspaceName;
-      const content = renderPrompt(promptDef.content, renderArgs);
+      const { rendered, context } = renderPromptWithContext(promptDef.content, renderArgs);
       let contextPreamble = getContextPreamble();
       contextPreamble += `
 ### System Resolved Paths (OVERRIDE)
 The system has pre-resolved the configuration for this project. Use these values instead of manual resolution:
-- **RRCE_DATA**: \`${resolvedRrceData}\` (Stores knowledge, tasks, refs)
-- **WORKSPACE_ROOT**: \`${resolvedWorkspaceRoot}\` (Source code location)
-- **RRCE_HOME**: \`${resolvedRrceHome}\`
-- **Current Project**: ${resolvedWorkspaceName}
+- **RRCE_DATA**: \`${context.RRCE_DATA}\` (Stores knowledge, tasks, refs)
+- **WORKSPACE_ROOT**: \`${context.WORKSPACE_ROOT}\` (Source code location)
+- **RRCE_HOME**: \`${context.RRCE_HOME}\`
+- **Current Project**: ${context.WORKSPACE_NAME}
 `;
       return {
         messages: [
@@ -2817,7 +2878,7 @@ The system has pre-resolved the configuration for this project. Use these values
             role: "user",
             content: {
               type: "text",
-              text: contextPreamble + content
+              text: contextPreamble + rendered
             }
           }
         ]

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rrce-workflow",
-  "version": "0.2.70",
+  "version": "0.2.72",
   "description": "RRCE-Workflow TUI - Agentic code workflow generator for AI-assisted development",
   "author": "RRCE Team",
   "license": "MIT",