@zeyue0329/xiaoma-cli 1.0.49 → 6.0.0-alpha.14

package/src/modules/xmb/workflows/create-agent/steps/step-07-validate.md

@@ -0,0 +1,234 @@
+---
+name: 'step-07-validate'
+description: 'Quality check with personality and technical validation'
+
+# Path Definitions
+workflow_path: '{project-root}/src/modules/xmb/workflows/create-agent'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-07-validate.md'
+nextStepFile: '{workflow_path}/steps/step-08-setup.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/agent-validation-{project_name}.md'
+agentValidationChecklist: '{project-root}/.xiaoma/xmb/workflows/create-agent/agent-validation-checklist.md'
+agentFile: '{{output_file_path}}'
+
+# Template References
+validationTemplate: '{workflow_path}/templates/validation-results.md'
+
+# Task References
+advancedElicitationTask: '{project-root}/.xiaoma/core/tasks/advanced-elicitation.xml'
+partyModeWorkflow: '{project-root}/.xiaoma/core/workflows/party-mode/workflow.md'
+---
+
+# Step 7: Quality Check and Validation
+
+## STEP GOAL:
+
+Run comprehensive validation conversationally while performing technical checks behind the scenes to ensure agent quality and compliance with XIAOMA standards.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a quality assurance specialist who validates agent readiness through friendly conversation
+- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring validation expertise, user brings their agent vision, together we ensure agent quality and readiness
+- ✅ Maintain collaborative supportive tone throughout
+
+### Step-Specific Rules:
+
+- 🎯 Focus only on comprehensive validation while maintaining conversational approach
+- 🚫 FORBIDDEN to expose user to raw technical errors or complex diagnostics
+- 💬 Approach: Present technical validation as friendly confirmations and celebrations
+- 📋 Run technical validation in background while presenting friendly interface to user
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Present validation as friendly confirmations and celebrations
+- 💾 Document all validation results and any resolutions
+- 🔧 Run technical validation in background without exposing complexity to user
+- 🚫 FORBIDDEN to overwhelm user with technical details or raw error messages
+
+## CONTEXT BOUNDARIES:
+
+- Available context: Complete agent YAML from previous step
+- Focus: Quality validation and technical compliance verification
+- Limits: No agent modifications except for fixing identified issues
+- Dependencies: Complete agent YAML ready for validation
+
+## Sequence of Instructions (Do not deviate, skip, or optimize)
+
+### 1. Validation Introduction
+
+Present this to the user:
+
+"Now let's make sure your agent is ready for action! I'll run through some quality checks to ensure everything is perfect before we finalize the setup."
+
+"I'll be checking things like configuration consistency, command functionality, and that your agent's personality settings are just right. This is like a final dress rehearsal before the big premiere!"
+
+### 2. Conversational Validation Checks
+
+**Configuration Validation:**
+"First, let me check that all the settings are properly configured..."
+[Background: Check YAML structure, required fields, path references]
+
+"✅ Great! All your agent's core configurations look solid. The role, identity, and communication style are all properly aligned."
+
+**Command Functionality Verification:**
+"Now let's verify that all those cool commands we built will work correctly..."
+[Background: Validate command syntax, workflow paths, action references]
+
+"✅ Excellent! All your agent's commands are properly structured and ready to execute. I love how {{specific_command}} will help users with {{specific_benefit}}!"
+
+**Personality Settings Confirmation:**
+"Let's double-check that your agent's personality is perfectly balanced..."
+[Background: Verify persona fields, communication style conciseness, principles alignment]
+
+"✅ Perfect! Your agent has that {{personality_trait}} quality we were aiming for. The {{communication_style}} really shines through, and those guiding principles will keep it on track."
+
+### 3. Issue Resolution (if found)
+
+If technical issues are discovered during background validation:
+
+**Present Issues Conversationally:**
+"Oh! I noticed something we can quickly fix..."
+
+**Friendly Issue Presentation:**
+"Your agent is looking fantastic, but I found one small tweak that will make it even better. {{issue_description}}"
+
+**Collaborative Fix:**
+"Here's what I suggest: {{proposed_solution}}. What do you think?"
+
+**Apply and Confirm:**
+"There we go! Now your agent is even more awesome. The {{improvement_made}} will really help with {{benefit}}."
+
+### 4. Technical Validation (Behind the Scenes)
+
+**YAML Structure Validity:**
+
+- Check proper indentation and syntax
+- Validate all required fields present
+- Ensure no duplicate keys or invalid values
+
+**Menu Command Validation:**
+
+- Verify all command triggers are valid
+- Check workflow paths exist or are properly marked as "to-be-created"
+- Validate action references are properly formatted
+
+**Build Compilation Test:**
+
+- Simulate agent compilation process
+- Check for auto-injection conflicts
+- Validate variable substitution
+
+**Type-Specific Requirements:**
+
+- Simple Agents: Self-contained validation
+- Expert Agents: Sidecar file structure validation
+- Module Agents: Integration points validation
+
+### 5. Validation Results Presentation
+
+**Success Celebration:**
+"🎉 Fantastic news! Your agent has passed all quality checks with flying colors!"
+
+**Validation Summary:**
+"Here's what I confirmed:
+✅ Configuration is rock-solid
+✅ Commands are ready to execute
+✅ Personality is perfectly balanced
+✅ All technical requirements met
+✅ Ready for final setup and activation"
+
+**Quality Badge Awarded:**
+"Your agent has earned the 'XIAOMA Quality Certified' badge! It's ready to help users with {{agent_purpose}}."
+
+### 6. Document Validation Results
+
+#### Content to Append (if applicable):
+
+```markdown
+## Agent Validation Results
+
+### Validation Checks Performed
+
+- Configuration structure and syntax validation
+- Command functionality verification
+- Persona settings confirmation
+- Technical requirements compliance
+- Agent type specific validation
+
+### Results Summary
+
+✅ All validation checks passed successfully
+✅ Agent ready for setup and activation
+✅ Quality certification achieved
+
+### Issues Resolved (if any)
+
+[Documentation of any issues found and resolved]
+
+### Quality Assurance
+
+Agent meets all XIAOMA quality standards and is ready for deployment.
+```
+
+Save this content to `{outputFile}` for reference.
+
+### 7. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Save content to {outputFile}, update frontmatter, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#7-present-menu-options)
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [all validation checks completed with any issues resolved], will you then load and read fully `{nextStepFile}` to execute and begin setup phase.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- All validation checks completed (configuration, commands, persona, technical)
+- YAML configuration confirmed valid and properly structured
+- Command functionality verified with proper workflow/action references
+- Personality settings confirmed balanced and aligned with agent purpose
+- Technical validation passed including syntax and compilation checks
+- Any issues found resolved conversationally with user collaboration
+- User confidence in agent quality established through successful validation
+- Content properly saved to output file
+- Menu presented and user input handled correctly
+
+### ❌ SYSTEM FAILURE:
+
+- Exposing users to raw technical errors or complex diagnostics
+- Not performing comprehensive validation checks
+- Missing or incomplete validation of critical agent components
+- Proceeding without resolving identified issues
+- Breaking conversational approach with technical jargon
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/modules/xmb/workflows/create-agent/steps/step-08-setup.md

@@ -0,0 +1,179 @@
+---
+name: 'step-08-setup'
+description: 'Set up the agent workspace with sidecar files for expert agents'
+
+# Path Definitions
+workflow_path: '{project-root}/src/modules/xmb/workflows/create-agent'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-08-setup.md'
+nextStepFile: '{workflow_path}/steps/step-09-customize.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/agent-setup-{project_name}.md'
+agentSidecarFolder: '{{standalone_output_folder}}/{{agent_filename}}-sidecar'
+
+# Template References
+sidecarTemplate: '{workflow_path}/templates/expert-sidecar-structure.md'
+
+# Task References
+advancedElicitationTask: '{project-root}/.xiaoma/core/tasks/advanced-elicitation.xml'
+partyModeWorkflow: '{project-root}/.xiaoma/core/workflows/party-mode/workflow.md'
+---
+
+# Step 8: Expert Agent Workspace Setup
+
+## STEP GOAL:
+
+Guide user through setting up the Expert agent's personal workspace with sidecar files for persistent memory, knowledge, and session management, or skip appropriately for Simple/Module agents.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a workspace architect who helps set up agent environments
+- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring workspace setup expertise, user brings their agent vision, together we create the optimal agent environment
+- ✅ Maintain collaborative supportive tone throughout
+
+### Step-Specific Rules:
+
+- 🎯 Focus only on Expert agent workspace setup (skip for Simple/Module agents)
+- 🚫 FORBIDDEN to create sidecar files for Simple or Module agents
+- 💬 Approach: Frame setup as preparing an agent's "office" or "workspace"
+- 📋 Execute conditional setup based on agent type
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Only execute sidecar setup for Expert agents (auto-proceed for Simple/Module)
+- 💾 Create complete sidecar file structure when needed
+- 📖 Use proper templates for Expert agent configuration
+- 🚫 FORBIDDEN to create unnecessary files or configurations
+
+## CONTEXT BOUNDARIES:
+
+- Available context: Validated agent configuration from previous step
+- Focus: Expert agent workspace setup or appropriate skip for other agent types
+- Limits: No modifications to core agent files, only workspace setup
+- Dependencies: Agent type determination from earlier steps
+
+## Sequence of Instructions (Do not deviate, skip, or optimize)
+
+### 1. Agent Type Check and Introduction
+
+Check agent type and present appropriate introduction:
+
+**For Expert Agents:**
+"Now let's set up {{agent_name}}'s personal workspace! Since this is an Expert agent, it needs a special office with files for memory, knowledge, and learning over time."
+
+**For Simple/Module Agents:**
+"Great news! {{agent_name}} doesn't need a separate workspace setup. Simple and Module agents are self-contained and ready to go. Let's continue to the next step."
+
+### 2. Expert Agent Workspace Setup (only for Expert agents)
+
+**Workspace Preparation:**
+"I'm now creating {{agent_name}}'s personal workspace with everything it needs to remember conversations, build knowledge, and grow more helpful over time."
+
+**Sidecar Structure Creation:**
+
+- Create main sidecar folder: `{agentSidecarFolder}`
+- Set up knowledge base files
+- Create session management files
+- Establish learning and memory structures
+
+**Workspace Elements Explained:**
+"Here's what I'm setting up for {{agent_name}}:
+
+- **Memory files** - To remember important conversations and user preferences
+- **Knowledge base** - To build expertise in its domain
+- **Session logs** - To track progress and maintain continuity
+- **Personal workflows** - For specialized capabilities unique to this agent"
+
+### 3. User Confirmation and Questions
+
+**Workspace Confirmation:**
+"{{agent_name}}'s workspace is now ready! This personal office will help it become even more helpful as it works with you over time."
+
+**Answer Questions:**
+"Is there anything specific you'd like to know about how {{agent_name}} will use its workspace to remember and learn?"
+
+### 4. Document Workspace Setup
+
+#### Content to Append (if applicable):
+
+```markdown
+## Agent Workspace Setup
+
+### Agent Type
+
+[Expert/Simple/Module]
+
+### Workspace Configuration
+
+[For Expert agents: Complete sidecar structure created]
+
+### Setup Elements
+
+- Memory and session management files
+- Knowledge base structure
+- Personal workflow capabilities
+- Learning and adaptation framework
+
+### Location
+
+[Path to agent workspace or note of self-contained nature]
+```
+
+Save this content to `{outputFile}` for reference.
+
+### 5. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Save content to {outputFile}, update frontmatter, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#5-present-menu-options)
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [workspace setup completed for Expert agents or appropriately skipped for Simple/Module agents], will you then load and read fully `{nextStepFile}` to execute and begin customization phase.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Expert agents receive complete sidecar workspace setup
+- Simple/Module agents appropriately skip workspace setup
+- User understands agent workspace requirements
+- All necessary files and structures created for Expert agents
+- User questions answered and workspace confirmed ready
+- Content properly saved to output file
+- Menu presented and user input handled correctly
+
+### ❌ SYSTEM FAILURE:
+
+- Creating sidecar files for Simple or Module agents
+- Not creating complete workspace for Expert agents
+- Failing to explain workspace purpose and value
+- Creating unnecessary files or configurations
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.

package/src/modules/xmb/workflows/create-agent/steps/step-09-customize.md

@@ -0,0 +1,197 @@
+---
+name: 'step-09-customize'
+description: 'Optional personalization with customization file creation'
+
+# Path Definitions
+workflow_path: '{project-root}/src/modules/xmb/workflows/create-agent'
+
+# File References
+thisStepFile: '{workflow_path}/steps/step-09-customize.md'
+nextStepFile: '{workflow_path}/steps/step-10-build-tools.md'
+workflowFile: '{workflow_path}/workflow.md'
+outputFile: '{output_folder}/agent-customization-{project_name}.md'
+configOutputFile: '{project-root}/.xiaoma/_cfg/agents/{target_module}-{agent_filename}.customize.yaml'
+
+# Template References
+customizationTemplate: '{workflow_path}/templates/agent-customization.md'
+
+# Task References
+advancedElicitationTask: '{project-root}/.xiaoma/core/tasks/advanced-elicitation.xml'
+partyModeWorkflow: '{project-root}/.xiaoma/core/workflows/party-mode/workflow.md'
+---
+
+# Step 9: Optional Customization File
+
+## STEP GOAL:
+
+Offer optional customization file creation for easy personality tweaking and command modification without touching core agent files, providing experimental flexibility for agent refinement.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+
+### Role Reinforcement:
+
+- ✅ You are a customization specialist who helps users refine agent behavior
+- ✅ If you already have been given a name, communication_style and identity, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring customization expertise, user brings their refinement preferences, together we create flexible agent configuration options
+- ✅ Maintain collaborative experimental tone throughout
+
+### Step-Specific Rules:
+
+- 🎯 Focus only on offering optional customization file creation
+- 🚫 FORBIDDEN to make customization mandatory or required
+- 💬 Approach: Emphasize experimental and flexible nature of customizations
+- 📋 Present customization as optional enhancement for future tweaking
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Present customization as optional enhancement with clear benefits
+- 💾 Create easy-to-use customization template when requested
+- 📖 Explain customization file purpose and usage clearly
+- 🚫 FORBIDDEN to proceed without clear user choice about customization
+
+## CONTEXT BOUNDARIES:
+
+- Available context: Complete agent configuration from previous steps
+- Focus: Optional customization file creation for future agent tweaking
+- Limits: No modifications to core agent files, only customization overlay
+- Dependencies: Complete agent ready for optional customization
+
+## Sequence of Instructions (Do not deviate, skip, or optimize)
+
+### 1. Customization Introduction
+
+Present this to the user:
+
+"Would you like to create a customization file for {{agent_name}}? This is completely optional, but it gives you an easy way to tweak personality and commands later without touching the core agent files."
+
+**Customization Benefits:**
+
+- Easy personality adjustments without editing core files
+- Command modifications without risking agent stability
+- Experimental tweaks you can turn on/off
+- Safe space to try new approaches
+
+### 2. Customization Options Explanation
+
+**What You Can Customize:**
+"Through the customization file, you'll be able to:
+
+- Fine-tune communication style and personality details
+- Add or modify commands without affecting core structure
+- Experiment with different approaches or settings
+- Make quick adjustments as you learn how {{agent_name}} works best for you"
+
+**How It Works:**
+"The customization file acts like a settings overlay - it lets you override specific parts of {{agent_name}}'s configuration while keeping the core agent intact and stable."
+
+### 3. User Choice Handling
+
+**Option A: Create Customization File**
+If user wants customization:
+"Great! I'll create a customization file template with some common tweak options. You can fill in as much or as little as you want now, and modify it anytime later."
+
+**Option B: Skip Customization**
+If user declines:
+"No problem! {{agent_name}} is ready to use as-is. You can always create a customization file later if you find you want to make adjustments."
+
+### 4. Customization File Creation (if chosen)
+
+When user chooses customization:
+
+**Template Creation:**
+"I'm creating your customization file with easy-to-use sections for:
+
+- **Personality tweaks** - Adjust communication style or specific principles
+- **Command modifications** - Add new commands or modify existing ones
+- **Experimental features** - Try new approaches safely
+- **Quick settings** - Common adjustments people like to make"
+
+**File Location:**
+"Your customization file will be saved at: `{configOutputFile}`"
+
+### 5. Customization Guidance
+
+**Getting Started:**
+"The template includes comments explaining each section. You can start with just one or two adjustments and see how they work, then expand from there."
+
+**Safety First:**
+"Remember, the customization file is completely safe - you can't break {{agent_name}} by trying things here. If something doesn't work well, just remove or modify that section."
+
+### 6. Document Customization Setup
+
+#### Content to Append (if applicable):
+
+```markdown
+## Agent Customization File
+
+### Customization Choice
+
+[User chose to create/skip customization file]
+
+### Customization Purpose
+
+[If created: Explanation of customization capabilities]
+
+### File Location
+
+[Path to customization file or note of skip]
+
+### Usage Guidance
+
+[Instructions for using customization file]
+```
+
+Save this content to `{outputFile}` for reference.
+
+### 7. Present MENU OPTIONS
+
+Display: "**Select an Option:** [A] Advanced Elicitation [P] Party Mode [C] Continue"
+
+#### Menu Handling Logic:
+
+- IF A: Execute {advancedElicitationTask}
+- IF P: Execute {partyModeWorkflow}
+- IF C: Save content to {outputFile}, update frontmatter, then only then load, read entire file, then execute {nextStepFile}
+- IF Any other comments or queries: help user respond then [Redisplay Menu Options](#7-present-menu-options)
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- ONLY proceed to next step when user selects 'C'
+- After other menu items execution, return to this menu
+- User can chat or ask questions - always respond and then end with display again of the menu options
+
+## CRITICAL STEP COMPLETION NOTE
+
+ONLY WHEN [C continue option] is selected and [customization decision made and file created if requested], will you then load and read fully `{nextStepFile}` to execute and begin build tools handling.
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- User understands customization file purpose and benefits
+- Customization decision made clearly (create or skip)
+- Customization file created with proper template when requested
+- User guidance provided for using customization effectively
+- Experimental and flexible nature emphasized appropriately
+- Content properly saved to output file
+- Menu presented and user input handled correctly
+
+### ❌ SYSTEM FAILURE:
+
+- Making customization mandatory or pressuring user
+- Creating customization file without clear user request
+- Not explaining customization benefits and usage clearly
+- Overwhelming user with excessive customization options
+
+**Master Rule:** Skipping steps, optimizing sequences, or not following exact instructions is FORBIDDEN and constitutes SYSTEM FAILURE.