Merge 4d48b0dbe1 into eb4325fab9

Custom modules with module.yaml configuration prompts were not being
collected during installation. Added customModulePaths option to
ConfigCollector to resolve custom module paths from selectedFiles
and cachedModules sources.

docs/ring-of-fire-sessions.md

@@ -0,0 +1,256 @@
+# BMad Method PR #1: Ring of Fire (ROF) Sessions
+
+**Feature Type**: Core workflow enhancement
+**Status**: Draft for community review
+**Origin**: tellingCube project (masemIT e.U.)
+**Author**: Mario Semper (@sempre)
+**Date**: 2025-11-23
+
+---
+
+## Summary
+
+**Ring of Fire (ROF) Sessions** enable multi-agent collaborative sessions that run in parallel to the user's main workflow, allowing users to delegate complex multi-perspective analysis while continuing other work.
+
+---
+
+## Problem Statement
+
+Current BMad Method requires **sequential agent interaction**. When users need multiple agents to collaborate on a complex topic, they must:
+- Manually orchestrate each agent conversation
+- Stay in the loop for every exchange
+- Wait for sequential responses before proceeding
+- Context-switch constantly between tasks
+
+This creates **bottlenecks** and prevents **parallel work streams**.
+
+---
+
+## Proposed Solution: Ring of Fire Sessions
+
+A new command pattern that enables **scoped multi-agent collaboration sessions** that run while the user continues other work.
+
+### Command Syntax
+
+```bash
+*rof "<topic>" --agents <agent-list> [--report brief|detailed|live]
+```
+
+### Example Usage
+
+```bash
+*rof "API Refactoring Strategy" --agents dev,architect,qa --report brief
+```
+
+**What happens**:
+1. Dev, Architect, and QA agents enter a collaborative session
+2. They analyze the topic together (code review, design discussion, testing concerns)
+3. When agents need tool access (read files, run commands), they request user approval
+4. User continues working on other tasks in parallel
+5. Session ends with consolidated report (brief: just recommendations, detailed: full transcript)
+
+---
+
+## Key Features
+
+### 1. User-Controlled Scope
+- **Small**: 2 agents, 5-minute quick discussion
+- **Large**: 10 agents, 2-hour deep analysis
+- User decides granularity based on complexity
+
+### 2. Approval-Gated Tool Access
+- Agents can **discuss** freely within the session
+- When agents need **tools** (read files, execute commands, make changes), they:
+  - Pause the session
+  - Request user approval
+  - Resume after user decision
+
+**Why**: Maintains user control, prevents runaway agent actions
+
+### 3. Flexible Reporting
+
+| Mode | Description | Use Case |
+|------|-------------|----------|
+| `brief` | Final recommendations only | "Just tell me what to do" |
+| `detailed` | Full transcript + recommendations | "Show me the reasoning" |
+| `live` | Real-time updates as agents discuss | "I want to observe" |
+
+**Default**: `brief` with Q&A available
+
+### 4. Parallel Workflows
+- User works on **Task A** while ROF session tackles **Task B**
+- No context-switching overhead
+- Efficient use of time
+
+---
+
+## Use Cases
+
+### 1. Architecture Reviews
+```bash
+*rof "Evaluate microservices vs monolith for new feature" --agents architect,dev,qa
+```
+**Agents collaborate on**: Design trade-offs, implementation complexity, testing implications
+
+### 2. Code Refactoring
+```bash
+*rof "Refactor authentication module" --agents dev,architect --report detailed
+```
+**Agents collaborate on**: Current code analysis, refactoring approach, migration strategy
+
+### 3. Feature Planning
+```bash
+*rof "Plan user notifications feature" --agents pm,ux,dev --report brief
+```
+**Agents collaborate on**: Requirements, UX flow, technical feasibility, timeline
+
+### 4. Quality Gates
+```bash
+*rof "Investigate test failures in CI/CD" --agents qa,dev --report live
+```
+**Agents collaborate on**: Root cause analysis, fix recommendations, regression prevention
+
+### 5. Documentation Sprints
+```bash
+*rof "Document API endpoints" --agents dev,pm,ux
+```
+**Agents collaborate on**: Technical accuracy, user-friendly examples, completeness
+
+---
+
+## User Experience Flow
+
+```mermaid
+sequenceDiagram
+    User->>River: *rof "Topic" --agents dev,architect
+    River->>Dev: Join ROF session
+    River->>Architect: Join ROF session
+    River->>User: Session started, continue your work
+
+    Dev->>Architect: Discuss approach
+    Architect->>Dev: Suggest alternatives
+
+    Dev->>User: Need to read auth.ts - approve?
+    User->>Dev: Approved
+    Dev->>Architect: After reading file...
+
+    Architect->>Dev: Recommendation
+    Dev->>River: Session complete
+    River->>User: Brief report: [Recommendations]
+```
+
+---
+
+## Implementation Considerations
+
+### Technical Requirements
+- **Session state management**: Track active ROF sessions, participating agents
+- **Agent context sharing**: Agents share knowledge within session scope
+- **User approval workflow**: Clear prompt for tool requests
+- **Report generation**: Brief/detailed/live output formatting
+- **Workflow integration**: Link ROF findings to existing workflow plans/todos
+
+### Open Questions for Community
+
+1. **Integration**: Core BMad feature or plugin/extension?
+2. **Concurrency**: How to handle file conflicts if multiple agents want to edit?
+3. **Cost Model**: Guidance for LLM call budgeting with multiple agents?
+4. **Session Limits**: Recommended max agents/duration?
+5. **Agent Communication**: Free-form discussion or structured turn-taking?
+
+---
+
+## Real-World Validation
+
+**Origin Project**: tellingCube (BI dashboard, masemIT e.U.)
+
+**Validation Scenario**:
+- **Topic**: "Next steps for tellingCube after validation test"
+- **Agents**: River (orchestrator), Mary (analyst), Winston (architect)
+- **Report Mode**: Brief
+- **Outcome**: Successfully analyzed post-validation roadmap with 3 scenarios (GO/CHANGE/NO-GO), delivered consolidated recommendations in 5 minutes
+
+**User Feedback (Mario Semper)**:
+> "This is exactly what I needed - I wanted multiple perspectives without having to orchestrate every conversation. The brief report gave me actionable next steps immediately."
+
+**Documentation**: `docs/_masemIT/readme.md` in tellingCube repository
+
+---
+
+## Proposed Documentation Structure
+
+```
+.bmad-core/
+  features/
+    ring-of-fire.md              # Feature specification
+
+docs/
+  guides/
+    using-rof-sessions.md        # User guide with examples
+
+  architecture/
+    agent-collaboration.md       # Technical design
+    rof-session-management.md    # State handling approach
+```
+
+---
+
+## Benefits
+
+✅ **Unlocks parallel workflows** - User productivity gains
+✅ **Reduces context-switching** - Cognitive load reduction
+✅ **Enables complex analysis** - Multi-perspective insights
+✅ **Maintains user control** - Approval gates for tools
+✅ **Scales flexibly** - From quick checks to deep dives
+
+---
+
+## Comparison to Existing Patterns
+
+| Feature | Standard Agent Use | ROF Session |
+|---------|-------------------|-------------|
+| Agent collaboration | Sequential (one at a time) | Parallel (multiple simultaneously) |
+| User involvement | Required for every exchange | Only for approvals |
+| Parallel work | No (user waits) | Yes (user continues tasks) |
+| Output | Chat transcript | Consolidated report |
+| Use case | Single-perspective tasks | Multi-perspective analysis |
+
+---
+
+## Next Steps
+
+1. **Community feedback** on approach and open questions
+2. **Technical design** refinement (state management, agent communication)
+3. **Prototype implementation** in BMad core or as extension
+4. **Beta testing** with real projects (beyond tellingCube)
+5. **Documentation** completion with examples
+
+---
+
+## Alternatives Considered
+
+### Alt 1: "Breakout Session"
+- **Pros**: Clear meeting metaphor
+- **Cons**: Less evocative, doesn't convey "continuous collaborative space"
+
+### Alt 2: "Agent Huddle"
+- **Pros**: Short, casual
+- **Cons**: Implies quick/informal only
+
+### Alt 3: "Lagerfeuer" (original German name)
+- **Pros**: Warm, campfire metaphor
+- **Cons**: Poor i18n, hard to pronounce/remember for non-German speakers
+
+**Chosen**: **Ring of Fire** - evokes continuous collaboration circle, internationally understood, memorable, shortcut "ROF" works well
+
+---
+
+## References
+
+- **Source Project**: tellingCube (https://github.com/masemIT/telling-cube) [if public]
+- **Documentation**: `docs/_masemIT/readme.md`
+- **Discussion**: [Link to BMad community discussion if applicable]
+
+---
+
+**Contribution ready for review.** Feedback welcome! 🔥

src/modules/bmm/docs/README.md

@@ -139,9 +139,6 @@ Comprehensive documentation for all BMM workflows organized by phase:
   - Complete story lifecycle
   - One-story-at-a-time discipline
 
-<<<<<<< Updated upstream
-<<<<<<< Updated upstream
-
 - **[Testing & QA Workflows](./test-architecture.md)** - Comprehensive quality assurance (1,420 lines)
   - Test strategy, automation, quality gates
   - TEA agent and test healing
@@ -149,14 +146,6 @@ Comprehensive documentation for all BMM workflows organized by phase:
 
 **Total: 34 workflows documented across all phases**
 
-=======
-
-> > > > > > > Stashed changes
-
-=======
-
-> > > > > > > Stashed changes
-
 ### Advanced Workflow References
 
 For detailed technical documentation on specific complex workflows:
@@ -181,23 +170,9 @@ Quality assurance guidance:
 
 <!-- Test Architect documentation to be added -->
 
-<<<<<<< Updated upstream
-
-<<<<<<< Updated upstream
-
 - Test design workflows
 - Quality gates
 - Risk assessment
-- # NFR validation
-  =======
-  > > > > > > > Stashed changes
-  - Test design workflows
-  - Quality gates
-  - Risk assessment
-  - NFR validation
-    > > > > > > > Stashed changes
-
----
 
 ## 🏗️ Module Structure
 

src/modules/bmm/docs/workflows-implementation.md

@@ -133,7 +133,6 @@ The `sprint-status.yaml` file is the single source of truth for all implementati
 ### (BMad Method / Enterprise)
 
 ```
-<<<<<<< Updated upstream
 PRD (PM) → Architecture (Architect)
   → create-epics-and-stories (PM)  ← V6: After architecture!
   → implementation-readiness (Architect)
@@ -142,7 +141,6 @@ PRD (PM) → Architecture (Architect)
       → story loop (SM/DEV)
       → retrospective (SM)
   → [Next Epic]
-=======
 Current Phase: 4 (Implementation)
 Current Epic: Epic 1 (Authentication)
 Current Sprint: Sprint 1
@@ -190,108 +188,12 @@ See: [workflow-status instructions](../workflows/workflow-status/instructions.md
 
 See: [document-project reference](./workflow-document-project-reference.md)
 
----
-
-## Story Lifecycle Visualization
-
-```
-┌─────────────────────────────────────────────────────────────┐
-│ PHASE 4: IMPLEMENTATION (Iterative Story Lifecycle)        │
-└─────────────────────────────────────────────────────────────┘
-
-┌─────────────────┐
-│ Sprint Planning │  → Creates sprint-status.yaml
-└────────┬────────┘     Defines story queue
-         │
-         ├──────────────────────────────────────────┐
-         │                                          │
-         ▼                                          │
-┌─────────────────────┐                            │
-│ Epic Tech Context   │  → Optional per epic       │
-│ (Once per epic)     │     Provides technical     │
-└─────────────────────┘     guidance              │
-         │                                          │
-         ▼                                          │
-┌─────────────────────────────────────────────────┤
-│ FOR EACH STORY IN QUEUE:                        │
-├─────────────────────────────────────────────────┤
-         │                                          │
-         ▼                                          │
-┌─────────────────┐                                │
-│ Create Story    │  → Generates story file        │
-│ (TODO → IN PROGRESS)                            │
-└────────┬────────┘                                │
-         │                                          │
-         ▼                                          │
-┌─────────────────┐                                │
-│ Story Context   │  → Assembles focused context   │
-└────────┬────────┘                                │
-         │                                          │
-         ▼                                          │
-┌─────────────────┐                                │
-│ Dev Story       │  → Implements + tests           │
-│ (IN PROGRESS)   │                                │
-└────────┬────────┘                                │
-         │                                          │
-         ▼                                          │
-┌─────────────────┐                                │
-│ Code Review     │  → Senior dev review            │
-│ (IN PROGRESS →  │                                │
-│  READY FOR REVIEW)                               │
-└────────┬────────┘                                │
-         │                                          │
-    ┌────┴────┐                                    │
-    │ Result? │                                    │
-    └────┬────┘                                    │
-         │                                          │
-    ┌────┼────────────────────┐                   │
-    │    │                    │                   │
-    ▼    ▼                    ▼                   │
-APPROVED  APPROVED           REQUEST              │
-          WITH COMMENTS      CHANGES              │
-    │         │                   │                │
-    └─────────┴───────────────────┘               │
-              │                                    │
-              ▼                                    │
-    ┌─────────────────┐                           │
-    │ Story Done      │  → READY FOR REVIEW → DONE│
-    └────────┬────────┘                           │
-             │                                     │
-             ├─────────────────────────────────────┘
-             │ More stories?
-             │
-             ▼
-    ┌────────────────┐
-    │ Epic Complete? │
-    └────────┬───────┘
-             │
-        ┌────┼────┐
-        │         │
-       Yes       No
-        │         └──> Continue to next story
-        │
-        ▼
-┌─────────────────┐
-│ Retrospective   │  → Review epic, lessons learned
-└─────────────────┘
-        │
-        ▼
-    All epics done?
-        │
-       Yes → PROJECT COMPLETE
->>>>>>> Stashed changes
-```
-
----
-
 ## Related Documentation
 
 - [Phase 1: Analysis Workflows](./workflows-analysis.md)
 - [Phase 2: Planning Workflows](./workflows-planning.md)
 - [Phase 3: Solutioning Workflows](./workflows-solutioning.md)
 
----
-
 ## Troubleshooting
 
 **Q: Which workflow should I run next?**
@@ -306,6 +208,4 @@ A: Not recommended. Complete one story's full lifecycle before starting the next
 **Q: What if code review finds issues?**
 A: DEV runs `dev-story` to make fixes, re-runs tests, then runs `code-review` again until it passes.
 
----
-
 _Phase 4 Implementation - One story at a time, done right._

src/modules/bmm/module.yaml

@@ -2,7 +2,7 @@
 
 code: bmm
 name: "BMM: BMad Method Agile-AI Driven-Development"
-default_selected: false # This module will be selected by default for new installations
+default_selected: true # This module will be selected by default for new installations
 
 header: "BMad Method™: Breakthrough Method of Agile-Ai Driven-Dev"
 subheader: "Agent and Workflow Configuration for this module"

tools/cli/installers/lib/core/config-collector.js

@@ -132,8 +132,12 @@ class ConfigCollector {
    * Collect configuration for all modules
    * @param {Array} modules - List of modules to configure (including 'core')
    * @param {string} projectDir - Target project directory
+   * @param {Object} options - Additional options
+   * @param {Map} options.customModulePaths - Map of module ID to source path for custom modules
    */
-  async collectAllConfigurations(modules, projectDir) {
+  async collectAllConfigurations(modules, projectDir, options = {}) {
+    // Store custom module paths for use in collectModuleConfig
+    this.customModulePaths = options.customModulePaths || new Map();
     await this.loadExistingConfig(projectDir);
 
     // Check if core was already collected (e.g., in early collection phase)
@@ -451,11 +455,21 @@ class ConfigCollector {
       this.allAnswers = {};
     }
     // Load module's config
-    // First, try the standard src/modules location
-    let installerConfigPath = path.join(getModulePath(moduleName), '_module-installer', 'module.yaml');
-    let moduleConfigPath = path.join(getModulePath(moduleName), 'module.yaml');
+    // First, check if we have a custom module path for this module
+    let installerConfigPath = null;
+    let moduleConfigPath = null;
 
-    // If not found in src/modules, we need to find it by searching the project
+    if (this.customModulePaths && this.customModulePaths.has(moduleName)) {
+      const customPath = this.customModulePaths.get(moduleName);
+      installerConfigPath = path.join(customPath, '_module-installer', 'module.yaml');
+      moduleConfigPath = path.join(customPath, 'module.yaml');
+    } else {
+      // Try the standard src/modules location
+      installerConfigPath = path.join(getModulePath(moduleName), '_module-installer', 'module.yaml');
+      moduleConfigPath = path.join(getModulePath(moduleName), 'module.yaml');
+    }
+
+    // If not found in src/modules or custom paths, search the project
     if (!(await fs.pathExists(installerConfigPath)) && !(await fs.pathExists(moduleConfigPath))) {
       // Use the module manager to find the module source
       const { ModuleManager } = require('../modules/manager');

tools/cli/installers/lib/core/installer.js

@@ -435,8 +435,53 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
       // Quick update already collected all configs, use them directly
       moduleConfigs = this.configCollector.collectedConfig;
     } else {
+      // Build custom module paths map from customContent
+      const customModulePaths = new Map();
+
+      // Handle selectedFiles (from existing install path or manual directory input)
+      if (config.customContent && config.customContent.selected && config.customContent.selectedFiles) {
+        const { CustomHandler } = require('../custom/handler');
+        const customHandler = new CustomHandler();
+        for (const customFile of config.customContent.selectedFiles) {
+          const customInfo = await customHandler.getCustomInfo(customFile, path.resolve(config.directory));
+          if (customInfo && customInfo.id) {
+            customModulePaths.set(customInfo.id, customInfo.path);
+          }
+        }
+      }
+
+      // Handle cachedModules (from new install path where modules are cached)
+      // Only include modules that were actually selected for installation
+      if (config.customContent && config.customContent.cachedModules) {
+        // Get selected cached module IDs (if available)
+        const selectedCachedIds = config.customContent.selectedCachedModules || [];
+        // If no selection info, include all cached modules (for backward compatibility)
+        const shouldIncludeAll = selectedCachedIds.length === 0 && config.customContent.selected;
+
+        for (const cachedModule of config.customContent.cachedModules) {
+          // For cached modules, the path is the cachePath which contains the module.yaml
+          if (
+            cachedModule.id &&
+            cachedModule.cachePath && // Include if selected or if we should include all
+            (shouldIncludeAll || selectedCachedIds.includes(cachedModule.id))
+          ) {
+            customModulePaths.set(cachedModule.id, cachedModule.cachePath);
+          }
+        }
+      }
+
+      // Get list of all modules including custom modules
+      const allModulesForConfig = [...(config.modules || [])];
+      for (const [moduleId] of customModulePaths) {
+        if (!allModulesForConfig.includes(moduleId)) {
+          allModulesForConfig.push(moduleId);
+        }
+      }
+
       // Regular install - collect configurations (core was already collected in UI.promptInstall if interactive)
-      moduleConfigs = await this.configCollector.collectAllConfigurations(config.modules || [], path.resolve(config.directory));
+      moduleConfigs = await this.configCollector.collectAllConfigurations(allModulesForConfig, path.resolve(config.directory), {
+        customModulePaths,
+      });
     }
 
     // Get bmad_folder from config (default to 'bmad' for backwards compatibility)
@@ -905,10 +950,13 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
             const moduleTargetPath = path.join(bmadDir, moduleName);
             await fs.ensureDir(moduleTargetPath);
 
+            // Get collected config for this custom module (from module.yaml prompts)
+            const collectedModuleConfig = moduleConfigs[moduleName] || {};
+
             const result = await customHandler.install(
               customInfo.path,
               path.join(bmadDir, 'temp-custom'),
-              { ...config.coreConfig, ...customInfo.config, _bmadDir: bmadDir },
+              { ...config.coreConfig, ...customInfo.config, ...collectedModuleConfig, _bmadDir: bmadDir },
               (filePath) => {
                 // Track installed files with correct path
                 const relativePath = path.relative(path.join(bmadDir, 'temp-custom'), filePath);
@@ -939,8 +987,10 @@ If AgentVibes party mode is enabled, immediately trigger TTS with agent's voice:
               await fs.remove(tempCustomPath);
             }
 
-            // Create module config
-            await this.generateModuleConfigs(bmadDir, { [moduleName]: { ...config.coreConfig, ...customInfo.config } });
+            // Create module config (include collected config from module.yaml prompts)
+            await this.generateModuleConfigs(bmadDir, {
+              [moduleName]: { ...config.coreConfig, ...customInfo.config, ...collectedModuleConfig },
+            });
 
             // Store custom module info for later manifest update
             if (!config._customModulesToTrack) {