@howlil/ez-agents 3.5.0 → 4.0.0

package/ez-agents/workflows/import-session.md

@@ -1,303 +0,0 @@
-# Workflow: import-session
-
-**Purpose:** Import session data from exported file
-
-**Related Commands:** `/ez:import-session`
-
----
-
-## Workflow Steps
-
-### 1. Parameters
-
-```
-file_path: string (required)
-source_model: string (optional) - For model-specific adapters
-```
-
-### 2. Validate Input
-
-```
-// Check file exists
-if (!fs.existsSync(file_path)) {
-  throw error(`File not found: ${file_path}`);
-}
-
-// Check file is .json
-if (!file_path.endsWith('.json')) {
-  throw error("Import file must be .json format");
-}
-
-// Try to parse JSON
-try {
-  content = fs.readFileSync(file_path, 'utf-8');
-  importedData = JSON.parse(content);
-} catch (err) {
-  throw error(`Invalid JSON: ${err.message}`);
-}
-```
-
-### 3. Import Session
-
-```
-SessionManager mgr = new SessionManager();
-SessionImport importer = new SessionImport(mgr);
-
-const options = {};
-if (source_model) {
-  options.sourceModel = source_model;
-}
-
-try {
-  result = importer.import(file_path, options);
-} catch (SessionImportError err) {
-  logger.error('Import failed', { file: file_path, error: err.message });
-  
-  // Display user-friendly error
-  output(`Import failed: ${err.message}`);
-  
-  if (err.validationErrors && err.validationErrors.length > 0) {
-    output("\nValidation errors:");
-    for (error of err.validationErrors) {
-      output(`  - ${error}`);
-    }
-  }
-  
-  output("\nSuggested fix:");
-  output("  Ensure the file is a valid session export from /ez:export-session");
-  
-  throw error;
-}
-```
-
-### 4. Validate Imported Session
-
-```
-// Check required fields
-session = importedData.session || importedData;
-
-requiredFields = ['metadata', 'context'];
-missingFields = [];
-
-for (field of requiredFields) {
-  if (!session[field]) {
-    missingFields.push(field);
-  }
-}
-
-if (missingFields.length > 0) {
-  warnings.push(`Missing optional fields: ${missingFields.join(', ')}`);
-}
-
-// Check session_chain integrity
-if (session.metadata?.session_chain) {
-  for (chainId of session.metadata.session_chain) {
-    linkedSession = mgr.loadSession(chainId);
-    if (!linkedSession) {
-      warnings.push(`Missing linked session: ${chainId}`);
-    }
-  }
-}
-```
-
-### 5. Create or Update Session
-
-```
-// Check if session_id already exists
-existingSession = mgr.loadSession(result.sessionId);
-
-if (existingSession) {
-  // Generate new session_id with timestamp suffix
-  timestamp = Date.now();
-  newSessionId = `${result.sessionId}-imported-${timestamp}`;
-  
-  // Create new session with modified ID
-  mgr.createSession({
-    model: session.metadata?.model,
-    phase: session.metadata?.phase,
-    plan: session.metadata?.plan
-  });
-  
-  // Update with imported data
-  mgr.updateSession(newSessionId, {
-    context: session.context,
-    state: session.state,
-    metadata: {
-      ...session.metadata,
-      session_id: newSessionId,
-      session_chain: [...(session.metadata?.session_chain || []), result.sessionId]
-    }
-  });
-  
-  result.sessionId = newSessionId;
-  logger.info('Session imported with new ID', { 
-    original: result.sessionId, 
-    new: newSessionId 
-  });
-} else {
-  // Update existing session created by importer
-  mgr.updateSession(result.sessionId, {
-    context: session.context,
-    state: session.state
-  });
-}
-```
-
-### 6. Log Success
-
-```
-logger.info('Session imported', { 
-  new_session_id: result.sessionId, 
-  source_file: file_path 
-});
-```
-
-### 7. Return Result
-
-```
-return {
-  success: true,
-  session_id: result.sessionId,
-  warnings: warnings || []
-};
-```
-
----
-
-## Import Confirmation Display
-
-```
-Session imported successfully!
-
-Session ID: {sessionId}
-Source: {file_path}
-Original model: {model}
-Original phase: {phase}
-Original plan: {plan}
-
-{warnings.length > 0 ? `Warnings:\n  - ${warnings.join('\n  - ')}` : ''}
-```
-
----
-
-## Session Summary Display
-
-```
-Session Summary:
-
-Tasks Completed: {completedTasks.length}
-Tasks Incomplete: {incompleteTasks.length}
-Key Decisions: {decisions.length}
-File Changes: {fileChanges.length}
-
-Incomplete Tasks:
-{incompleteTasks.map(t => `  - ${t}`).join('\n')}
-
-Recommended Next Action:
-  {nextAction}
-```
-
----
-
-## Follow-up Actions
-
-```
-What would you like to do?
-
-1. Resume this session
-2. View session chain
-3. Return to current session
-4. Export this session
-```
-
----
-
-## Error Handling
-
-### File Not Found
-```
-if (!fs.existsSync(file_path)) {
-  throw error(`File not found: ${file_path}`);
-}
-```
-
-### Invalid JSON
-```
-try {
-  importedData = JSON.parse(content);
-} catch (err) {
-  throw error(`Invalid JSON format: ${err.message}`);
-}
-```
-
-### Missing Required Fields
-```
-if (!session.metadata || !session.context) {
-  throw error("Invalid session format: Missing metadata or context");
-}
-```
-
-### Circular Chain Reference
-```
-if (session.metadata?.session_chain?.includes(session.metadata.session_id)) {
-  throw error("Invalid session chain: Circular reference detected");
-}
-```
-
----
-
-## Model-Specific Adapters
-
-### Claude Format
-```javascript
-_adaptClaudeFormat(data) {
-  // Claude may export with different structure
-  // Adapt to standard session format
-  return {
-    metadata: {
-      session_id: data.id || data.session_id,
-      model: 'claude',
-      ...data.metadata
-    },
-    context: data.context || data.conversation,
-    state: data.state || {}
-  };
-}
-```
-
-### Qwen Format
-```javascript
-_adaptQwenFormat(data) {
-  // Qwen standard format (already compatible)
-  return data;
-}
-```
-
-### OpenAI Format
-```javascript
-_adaptOpenAIFormat(data) {
-  // OpenAI may use different field names
-  return {
-    metadata: data.metadata || data.session_metadata,
-    context: data.context || data.messages,
-    state: data.state || {}
-  };
-}
-```
-
-### Kimi Format
-```javascript
-_adaptKimiFormat(data) {
-  // Kimi standard format (already compatible)
-  return data;
-}
-```
-
----
-
-## Related Files
-
-- `ez-agents/bin/lib/session-manager.cjs` - Session creation
-- `ez-agents/bin/lib/session-import.cjs` - Import logic
-- `ez-agents/bin/lib/session-errors.cjs` - Error classes
-- `.planning/sessions/` - Session storage directory

package/ez-agents/workflows/research-phase.md

@@ -1,74 +0,0 @@
-<purpose>
-Research how to implement a phase. Spawns ez-phase-researcher with phase context.
-
-Standalone research command. For most workflows, use `/ez:plan-phase` which integrates research automatically.
-</purpose>
-
-<process>
-
-## Step 0: Resolve Model Profile
-
-@~/.claude/ez-agents/references/model-profile-resolution.md
-
-Resolve model for:
-- `ez-phase-researcher`
-
-## Step 1: Normalize and Validate Phase
-
-@~/.claude/ez-agents/references/phase-argument-parsing.md
-
-```bash
-PHASE_INFO=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" roadmap get-phase "${PHASE}")
-```
-
-If `found` is false: Error and exit.
-
-## Step 2: Check Existing Research
-
-```bash
-ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
-```
-
-If exists: Offer update/view/skip options.
-
-## Step 3: Gather Phase Context
-
-```bash
-INIT=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" init phase-op "${PHASE}")
-if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
-# Extract: phase_dir, padded_phase, phase_number, state_path, requirements_path, context_path
-```
-
-## Step 4: Spawn Researcher
-
-```
-Task(
-  prompt="<objective>
-Research implementation approach for Phase {phase}: {name}
-</objective>
-
-<files_to_read>
-- {context_path} (USER DECISIONS from /ez:discuss-phase)
-- {requirements_path} (Project requirements)
-- {state_path} (Project decisions and history)
-</files_to_read>
-
-<additional_context>
-Phase description: {description}
-</additional_context>
-
-<output>
-Write to: .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
-</output>",
-  subagent_type="ez-phase-researcher",
-  model="{researcher_model}"
-)
-```
-
-## Step 5: Handle Return
-
-- `## RESEARCH COMPLETE` — Display summary, offer: Plan/Dig deeper/Review/Done
-- `## CHECKPOINT REACHED` — Present to user, spawn continuation
-- `## RESEARCH INCONCLUSIVE` — Show attempts, offer: Add context/Try different mode/Manual
-
-</process>

package/ez-agents/workflows/standup.md

@@ -1,64 +0,0 @@
-<purpose>
-Generate a sprint standup report. Analyzes recent SUMMARY.md files, STATE.md decisions/blockers, and phase progress to produce yesterday/today/blockers/velocity/health score.
-</purpose>
-
-<process>
-
-## 1. Initialize
-
-```bash
-INIT=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" init progress)
-if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
-```
-
-Parse optional phase from $ARGUMENTS.
-
-## 2. Gather Data
-
-```bash
-STATE=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" state-snapshot)
-ROADMAP=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" roadmap analyze)
-PROGRESS_BAR=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" progress bar --raw)
-```
-
-Find 3-5 most recent SUMMARY.md files (last 2 sessions worth of work).
-
-## 3. Calculate Sprint Health
-
-Score 0-100 based on:
-- Plans completed vs planned (velocity): 30pts
-- Active blockers (0=30pts, 1=15pts, 2+=0pts): 30pts
-- Requirements coverage from ROADMAP: 20pts
-- Deviation rate from STATE.md: 20pts
-
-## 4. Generate Standup Report
-
-```
-## Daily Standup — {date}
-
-### Yesterday
-{recent SUMMARY.md one-liners}
-
-### Today (Planned)
-{next phase/plans from ROADMAP}
-
-### Blockers
-{from STATE.md blockers[] or "None"}
-
-### Velocity Trend
-{calculated from plan completion rate}
-
-Sprint Health: {score}/100 — {status}
-{one-line recommendation}
-```
-
-Status thresholds: 80-100=HEALTHY, 60-79=SOME FRICTION, 40-59=STRUGGLING, <40=AT RISK.
-
-</process>
-
-<success_criteria>
-- [ ] Recent work summarized
-- [ ] Next steps identified
-- [ ] Blockers surfaced
-- [ ] Sprint health score calculated
-</success_criteria>