mirror of
https://github.com/catlog22/Claude-Code-Workflow.git
synced 2026-02-05 01:50:27 +08:00
refactor: simplify lite-fix command modes and parameters
Reduced complexity from 3 modes to 2 modes with intelligent adaptation: Before (complex): - 3 modes: Regular, Critical, Hotfix - 3 parameters: --critical, --hotfix, --incident After (simplified): - 2 modes: Default (auto-adaptive), Hotfix - 1 parameter: --hotfix Key improvements: - Default mode intelligently adapts based on risk score (Phase 2) - Automatic workflow adjustment (diagnosis depth, test strategy, review) - Risk score thresholds determine process complexity automatically - Removed manual Critical mode selection (now auto-detected) - Removed --incident parameter (can include in bug description) Adaptive behavior: - risk_score <3.0: Full test suite, comprehensive diagnosis - 3.0-5.0: Focused integration tests, moderate diagnosis - 5.0-8.0: Smoke+critical tests, focused diagnosis - ≥8.0: Smoke tests only, minimal diagnosis Line count: 652 lines (reduced from 707) Matches lite-plan simplicity while maintaining full functionality
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
---
|
||||
name: lite-fix
|
||||
description: Lightweight bug diagnosis and fix workflow with fast-track verification and optional hotfix mode for production incidents
|
||||
argument-hint: "[--critical|--hotfix] [--incident ID] \"bug description or issue reference\""
|
||||
description: Lightweight bug diagnosis and fix workflow with intelligent severity assessment and optional hotfix mode for production incidents
|
||||
argument-hint: "[--hotfix] \"bug description or issue reference\""
|
||||
allowed-tools: TodoWrite(*), Task(*), SlashCommand(*), AskUserQuestion(*), Read(*), Bash(*)
|
||||
---
|
||||
|
||||
@@ -9,15 +9,15 @@ allowed-tools: TodoWrite(*), Task(*), SlashCommand(*), AskUserQuestion(*), Read(
|
||||
|
||||
## Overview
|
||||
|
||||
Fast-track bug fixing workflow optimized for quick diagnosis, targeted fixes, and streamlined verification. Supports both regular bug fixes and critical production hotfixes with appropriate process adaptations.
|
||||
Fast-track bug fixing workflow optimized for quick diagnosis, targeted fixes, and streamlined verification. Automatically adjusts process complexity based on impact assessment.
|
||||
|
||||
**Core capabilities:**
|
||||
- Rapid root cause diagnosis with intelligent code search
|
||||
- Impact scope assessment (affected users, data, systems)
|
||||
- Automatic severity assessment and adaptive workflow
|
||||
- Fix strategy selection (immediate patch vs comprehensive refactor)
|
||||
- Risk-aware verification (smoke tests for hotfix, full suite for regular)
|
||||
- Automatic hotfix branch management
|
||||
- Follow-up task generation for comprehensive fixes
|
||||
- Risk-aware verification (smoke tests to full suite)
|
||||
- Optional hotfix mode for production incidents with branch management
|
||||
- Automatic follow-up task generation for hotfixes
|
||||
|
||||
## Usage
|
||||
|
||||
@@ -26,33 +26,28 @@ Fast-track bug fixing workflow optimized for quick diagnosis, targeted fixes, an
|
||||
/workflow:lite-fix [FLAGS] <BUG_DESCRIPTION>
|
||||
|
||||
# Flags
|
||||
--critical, -c Critical bug requiring fast-track process
|
||||
--hotfix, -h Production hotfix mode (creates hotfix branch)
|
||||
--incident <ID> Associate with incident tracking ID
|
||||
--hotfix, -h Production hotfix mode (creates hotfix branch, auto follow-up)
|
||||
|
||||
# Arguments
|
||||
<bug-description> Bug description or issue reference (required)
|
||||
```
|
||||
|
||||
### Severity Modes
|
||||
### Modes
|
||||
|
||||
| Mode | Time Budget | Use Case | Workflow Characteristics |
|
||||
|------|-------------|----------|--------------------------|
|
||||
| **Regular** (default) | 2-4 hours | Non-blocking bugs, <20% user impact | Full diagnosis + comprehensive testing |
|
||||
| **Critical** (`--critical`) | 30-60 min | Core feature degraded, 20-50% user impact | Focused diagnosis + key scenario testing |
|
||||
| **Hotfix** (`--hotfix`) | 15-30 min | Production outage, 100% user impact | Minimal diagnosis + smoke testing + auto follow-up |
|
||||
| **Default** | Auto-adapt (15min-4h) | All standard bugs | Intelligent severity assessment + adaptive process |
|
||||
| **Hotfix** (`--hotfix`) | 15-30 min | Production outage | Minimal diagnosis + hotfix branch + auto follow-up |
|
||||
|
||||
### Examples
|
||||
|
||||
```bash
|
||||
# Regular mode: Standard bug fix
|
||||
# Default mode: Automatically adjusts based on impact
|
||||
/workflow:lite-fix "User avatar upload fails with 413 error"
|
||||
|
||||
# Critical mode: Urgent but not fatal
|
||||
/workflow:lite-fix --critical "Shopping cart randomly loses items at checkout"
|
||||
/workflow:lite-fix "Shopping cart randomly loses items at checkout"
|
||||
|
||||
# Hotfix mode: Production incident
|
||||
/workflow:lite-fix --hotfix --incident INC-2024-1015 "Payment gateway 5xx errors"
|
||||
/workflow:lite-fix --hotfix "Payment gateway 5xx errors"
|
||||
```
|
||||
|
||||
## Execution Process
|
||||
@@ -62,21 +57,21 @@ Fast-track bug fixing workflow optimized for quick diagnosis, targeted fixes, an
|
||||
```
|
||||
Bug Input → Diagnosis (Phase 1) → Impact Assessment (Phase 2)
|
||||
↓
|
||||
Fix Planning (Phase 3) → Verification Strategy (Phase 4)
|
||||
Severity Auto-Detection → Fix Planning (Phase 3)
|
||||
↓
|
||||
User Confirmation (Phase 5) → Execution (Phase 6)
|
||||
Verification Strategy (Phase 4) → User Confirmation (Phase 5) → Execution (Phase 6)
|
||||
```
|
||||
|
||||
### Phase Summary
|
||||
|
||||
| Phase | Regular | Critical | Hotfix |
|
||||
|-------|---------|----------|--------|
|
||||
| 1. Diagnosis | Full (cli-explore-agent) | Focused (direct grep) | Minimal (known issue) |
|
||||
| 2. Impact | Comprehensive | Targeted | Critical path only |
|
||||
| 3. Planning | Multiple strategies | Single best | Surgical fix |
|
||||
| 4. Verification | Full test suite | Key scenarios | Smoke tests |
|
||||
| 5. Confirmation | 4 dimensions | 3 dimensions | 2 dimensions |
|
||||
| 6. Execution | Via lite-execute | Via lite-execute | Via lite-execute + monitoring |
|
||||
| Phase | Default Mode | Hotfix Mode |
|
||||
|-------|--------------|-------------|
|
||||
| 1. Diagnosis | Adaptive search depth | Minimal (known issue) |
|
||||
| 2. Impact Assessment | Full risk scoring | Critical path only |
|
||||
| 3. Fix Planning | Strategy options based on complexity | Single surgical fix |
|
||||
| 4. Verification | Test level matches risk score | Smoke tests only |
|
||||
| 5. User Confirmation | 3 dimensions | 2 dimensions |
|
||||
| 6. Execution | Via lite-execute | Via lite-execute + monitoring |
|
||||
|
||||
---
|
||||
|
||||
@@ -86,39 +81,38 @@ Bug Input → Diagnosis (Phase 1) → Impact Assessment (Phase 2)
|
||||
|
||||
**Goal**: Identify root cause and affected code paths
|
||||
|
||||
**Execution Strategy by Mode**:
|
||||
**Execution Strategy**:
|
||||
|
||||
**Default Mode** - Adaptive search:
|
||||
- **High confidence keywords** (e.g., specific error messages): Direct grep search (5min)
|
||||
- **Medium confidence**: cli-explore-agent with focused search (10-15min)
|
||||
- **Low confidence** (vague symptoms): cli-explore-agent with broad search (20min)
|
||||
|
||||
**Regular Mode** - Comprehensive search:
|
||||
```javascript
|
||||
Task(
|
||||
subagent_type="cli-explore-agent",
|
||||
prompt=`
|
||||
Bug: ${bug_description}
|
||||
|
||||
Execute diagnostic search:
|
||||
1. Search error message: Grep "${error}" --output_mode content
|
||||
2. Find related code: Glob "**/affected-module/**/*.{ts,js}"
|
||||
3. Trace execution path
|
||||
4. Check recent changes: git log --since="1 week ago"
|
||||
|
||||
Return: Root cause hypothesis, affected paths, reproduction steps
|
||||
Time limit: 20 minutes
|
||||
`
|
||||
)
|
||||
// Confidence-based strategy selection
|
||||
if (has_specific_error_message || has_file_path_hint) {
|
||||
// Quick targeted search
|
||||
grep -r '${error_message}' src/ --include='*.ts' -n | head -10
|
||||
git log --oneline --since='1 week ago' -- '*affected*'
|
||||
} else {
|
||||
// Deep exploration
|
||||
Task(subagent_type="cli-explore-agent", prompt=`
|
||||
Bug: ${bug_description}
|
||||
Execute diagnostic search:
|
||||
1. Search error patterns and similar issues
|
||||
2. Trace execution path in affected modules
|
||||
3. Check recent changes
|
||||
Return: Root cause hypothesis, affected paths, reproduction steps
|
||||
`)
|
||||
}
|
||||
```
|
||||
|
||||
**Critical Mode** - Direct targeted search:
|
||||
**Hotfix Mode** - Minimal search:
|
||||
```bash
|
||||
grep -r '${error_message}' src/ --include='*.ts' -n | head -10
|
||||
git log --oneline --since='1 week ago' -- '*affected*' | head -5
|
||||
Read(suspected_file) # User typically knows the file
|
||||
git blame ${suspected_file}
|
||||
```
|
||||
|
||||
**Hotfix Mode** - Minimal search (assume known issue):
|
||||
```bash
|
||||
Read(suspected_file) # User provides file path
|
||||
```
|
||||
|
||||
**Output Structure**:
|
||||
```javascript
|
||||
{
|
||||
@@ -141,19 +135,30 @@ Read(suspected_file) # User provides file path
|
||||
|
||||
---
|
||||
|
||||
### Phase 2: Impact Assessment
|
||||
### Phase 2: Impact Assessment & Severity Auto-Detection
|
||||
|
||||
**Goal**: Quantify blast radius and risk level
|
||||
**Goal**: Quantify blast radius and auto-determine severity
|
||||
|
||||
**Risk Score Calculation**:
|
||||
```javascript
|
||||
risk_score = (user_impact × 0.4) + (system_risk × 0.3) + (business_impact × 0.3)
|
||||
|
||||
// Severity mapping
|
||||
// Auto-severity mapping
|
||||
if (risk_score >= 8.0) severity = "critical"
|
||||
else if (risk_score >= 5.0) severity = "high"
|
||||
else if (risk_score >= 3.0) severity = "medium"
|
||||
else severity = "low"
|
||||
|
||||
// Workflow adaptation
|
||||
if (severity >= "high") {
|
||||
diagnosis_depth = "focused"
|
||||
test_strategy = "smoke_and_critical"
|
||||
review_optional = true
|
||||
} else {
|
||||
diagnosis_depth = "comprehensive"
|
||||
test_strategy = "full_suite"
|
||||
review_optional = false
|
||||
}
|
||||
```
|
||||
|
||||
**Assessment Output**:
|
||||
@@ -161,8 +166,7 @@ else severity = "low"
|
||||
{
|
||||
affected_users: {
|
||||
count: "5000 active users (100%)",
|
||||
severity: "high",
|
||||
workaround: "Re-login required"
|
||||
severity: "high"
|
||||
},
|
||||
system_risk: {
|
||||
availability: "degraded_30%",
|
||||
@@ -174,15 +178,16 @@ else severity = "low"
|
||||
sla_breach: "yes"
|
||||
},
|
||||
risk_score: 7.1,
|
||||
severity: "high"
|
||||
severity: "high",
|
||||
workflow_adaptation: {
|
||||
test_strategy: "focused_integration",
|
||||
review_required: false,
|
||||
time_budget: "1_hour"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
**Auto-Severity Suggestion**:
|
||||
If `risk_score >= 8.0` and user didn't provide `--critical`, suggest:
|
||||
```
|
||||
💡 Suggestion: Consider using --critical flag (risk score: 8.2/10)
|
||||
```
|
||||
**Hotfix Mode**: Skip detailed assessment, assume critical
|
||||
|
||||
**TodoWrite**: Mark Phase 2 completed, Phase 3 in_progress
|
||||
|
||||
@@ -192,71 +197,61 @@ If `risk_score >= 8.0` and user didn't provide `--critical`, suggest:
|
||||
|
||||
**Goal**: Generate fix options with trade-off analysis
|
||||
|
||||
**Strategy Generation by Mode**:
|
||||
**Strategy Generation**:
|
||||
|
||||
**Default Mode** - Complexity-adaptive:
|
||||
- **Low risk score (<5.0)**: Generate 2-3 strategy options for user selection
|
||||
- **High risk score (≥5.0)**: Generate single best strategy for speed
|
||||
|
||||
**Regular Mode** - Multiple strategies (1-3 options):
|
||||
```javascript
|
||||
strategies = generateFixStrategies(root_cause, risk_score)
|
||||
|
||||
if (risk_score >= 5.0 || mode === "hotfix") {
|
||||
// Single best strategy
|
||||
return strategies[0] // Fastest viable fix
|
||||
} else {
|
||||
// Multiple options with trade-offs
|
||||
return strategies // Let user choose
|
||||
}
|
||||
```
|
||||
|
||||
**Example Strategies**:
|
||||
```javascript
|
||||
// Low risk: Multiple options
|
||||
[
|
||||
{
|
||||
strategy: "immediate_patch",
|
||||
description: "Fix comparison operator",
|
||||
files: ["src/auth/tokenValidator.ts:47"],
|
||||
estimated_time: "15 minutes",
|
||||
risk: "low",
|
||||
pros: ["Quick fix", "Minimal change"],
|
||||
cons: ["Doesn't address token refresh"]
|
||||
pros: ["Quick fix"],
|
||||
cons: ["Doesn't address underlying issue"]
|
||||
},
|
||||
{
|
||||
strategy: "comprehensive_refactor",
|
||||
description: "Refactor token validation with proper refresh",
|
||||
files: ["src/auth/tokenValidator.ts", "src/auth/refreshToken.ts"],
|
||||
strategy: "comprehensive_fix",
|
||||
description: "Refactor token validation logic",
|
||||
estimated_time: "2 hours",
|
||||
risk: "medium",
|
||||
pros: ["Addresses root cause"],
|
||||
cons: ["Longer implementation"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
**Critical/Hotfix Mode** - Single best strategy:
|
||||
```javascript
|
||||
// High risk or hotfix: Single option
|
||||
{
|
||||
strategy: "surgical_fix",
|
||||
description: "Minimal change to fix comparison",
|
||||
files: ["src/auth/tokenValidator.ts:47"],
|
||||
change: "currentTime > expiryTime → currentTime >= expiryTime",
|
||||
estimated_time: "5 minutes",
|
||||
risk: "minimal"
|
||||
}
|
||||
```
|
||||
|
||||
**Complexity Assessment & Planning**:
|
||||
**Complexity Assessment**:
|
||||
```javascript
|
||||
complexity = assessComplexity(fix_strategies)
|
||||
|
||||
if (complexity === "low" || mode === "hotfix") {
|
||||
plan = generateSimplePlan(selected_strategy) // Direct by Claude
|
||||
} else if (complexity === "medium") {
|
||||
plan = Task(subagent_type="cli-lite-planning-agent", ...)
|
||||
} else {
|
||||
if (complexity === "high" && risk_score < 5.0) {
|
||||
suggestCommand("/workflow:plan --mode bugfix")
|
||||
}
|
||||
```
|
||||
|
||||
**Plan Output**:
|
||||
```javascript
|
||||
{
|
||||
summary: "Fix timestamp comparison in token validation",
|
||||
approach: "Update comparison operator",
|
||||
tasks: [{
|
||||
title: "Fix token expiration comparison",
|
||||
file: "src/auth/tokenValidator.ts",
|
||||
action: "Update",
|
||||
implementation: ["Locate validateToken", "Update line 47", "Add comment"],
|
||||
verification: ["Manual test at boundary", "Run auth tests"]
|
||||
}],
|
||||
estimated_time: "30 minutes",
|
||||
recommended_execution: "Agent"
|
||||
return // Escalate to full planning
|
||||
}
|
||||
```
|
||||
|
||||
@@ -268,17 +263,19 @@ if (complexity === "low" || mode === "hotfix") {
|
||||
|
||||
**Goal**: Define testing approach based on severity
|
||||
|
||||
**Test Strategy Selection**:
|
||||
**Adaptive Test Strategy**:
|
||||
|
||||
| Mode | Test Scope | Duration | Automation |
|
||||
|------|------------|----------|------------|
|
||||
| **Regular** | Full test suite | 10-20 min | `npm test` |
|
||||
| **Critical** | Focused integration | 5-10 min | `npm test -- auth.test.ts` |
|
||||
| **Hotfix** | Smoke tests | 2-5 min | `npm test -- auth.smoke.test.ts` |
|
||||
| Risk Score | Test Scope | Duration | Automation |
|
||||
|------------|------------|----------|------------|
|
||||
| **< 3.0** (Low) | Full test suite | 15-20 min | `npm test` |
|
||||
| **3.0-5.0** (Medium) | Focused integration | 8-12 min | `npm test -- affected-module.test.ts` |
|
||||
| **5.0-8.0** (High) | Smoke + critical | 5-8 min | `npm test -- critical.smoke.test.ts` |
|
||||
| **≥ 8.0** (Critical) | Smoke only | 2-5 min | `npm test -- smoke.test.ts` |
|
||||
| **Hotfix** | Production smoke | 2-3 min | `npm test -- production.smoke.test.ts` |
|
||||
|
||||
**Branch Strategy**:
|
||||
|
||||
**Regular/Critical**:
|
||||
**Default Mode**:
|
||||
```javascript
|
||||
{
|
||||
type: "feature_branch",
|
||||
@@ -288,7 +285,7 @@ if (complexity === "low" || mode === "hotfix") {
|
||||
}
|
||||
```
|
||||
|
||||
**Hotfix**:
|
||||
**Hotfix Mode**:
|
||||
```javascript
|
||||
{
|
||||
type: "hotfix_branch",
|
||||
@@ -304,74 +301,48 @@ if (complexity === "low" || mode === "hotfix") {
|
||||
|
||||
### Phase 5: User Confirmation & Execution Selection
|
||||
|
||||
**Multi-Dimension Confirmation**:
|
||||
**Adaptive Confirmation Dimensions**:
|
||||
|
||||
**Default Mode** - 3 dimensions (adapted by risk score):
|
||||
|
||||
**Regular Mode** (4 dimensions):
|
||||
```javascript
|
||||
AskUserQuestion({
|
||||
questions: [
|
||||
{
|
||||
question: "Confirm fix approach?",
|
||||
header: "Fix Confirmation",
|
||||
options: [
|
||||
{ label: "Proceed", description: "Execute as planned" },
|
||||
{ label: "Modify", description: "Adjust strategy" },
|
||||
{ label: "Escalate", description: "Use /workflow:plan" }
|
||||
]
|
||||
},
|
||||
{
|
||||
question: "Execution method:",
|
||||
header: "Execution",
|
||||
options: [
|
||||
{ label: "Agent", description: "@code-developer" },
|
||||
{ label: "CLI Tool", description: "Codex/Gemini" },
|
||||
{ label: "Manual", description: "Provide plan only" }
|
||||
]
|
||||
},
|
||||
{
|
||||
question: "Verification level:",
|
||||
header: "Testing",
|
||||
options: [
|
||||
{ label: "Full Suite", description: "All tests" },
|
||||
{ label: "Focused", description: "Affected tests" },
|
||||
{ label: "Smoke Only", description: "Critical path" }
|
||||
]
|
||||
},
|
||||
{
|
||||
question: "Post-fix review:",
|
||||
header: "Code Review",
|
||||
options: [
|
||||
{ label: "Gemini", description: "AI review" },
|
||||
{ label: "Skip", description: "Trust tests" }
|
||||
]
|
||||
}
|
||||
]
|
||||
})
|
||||
dimensions = [
|
||||
{
|
||||
question: "Confirm fix approach?",
|
||||
options: ["Proceed", "Modify", "Escalate to /workflow:plan"]
|
||||
},
|
||||
{
|
||||
question: "Execution method:",
|
||||
options: ["Agent", "CLI Tool (Codex/Gemini)", "Manual (plan only)"]
|
||||
},
|
||||
{
|
||||
question: "Verification level:",
|
||||
options: adaptedByRiskScore() // Auto-suggest based on Phase 2
|
||||
}
|
||||
]
|
||||
|
||||
// If risk_score >= 5.0, auto-skip code review dimension
|
||||
// If risk_score < 5.0, add optional code review dimension
|
||||
if (risk_score < 5.0) {
|
||||
dimensions.push({
|
||||
question: "Post-fix review:",
|
||||
options: ["Gemini", "Skip"]
|
||||
})
|
||||
}
|
||||
```
|
||||
|
||||
**Critical Mode** (3 dimensions - skip code review)
|
||||
|
||||
**Hotfix Mode** (2 dimensions - minimal confirmation):
|
||||
**Hotfix Mode** - 2 dimensions (minimal):
|
||||
```javascript
|
||||
AskUserQuestion({
|
||||
questions: [
|
||||
{
|
||||
question: "Confirm hotfix deployment:",
|
||||
options: [
|
||||
{ label: "Deploy", description: "Apply to production" },
|
||||
{ label: "Stage First", description: "Test in staging" },
|
||||
{ label: "Abort", description: "Cancel" }
|
||||
]
|
||||
},
|
||||
{
|
||||
question: "Post-deployment monitoring:",
|
||||
options: [
|
||||
{ label: "Real-time", description: "Monitor 15 minutes" },
|
||||
{ label: "Passive", description: "Rely on alerts" }
|
||||
]
|
||||
}
|
||||
]
|
||||
})
|
||||
[
|
||||
{
|
||||
question: "Confirm hotfix deployment:",
|
||||
options: ["Deploy", "Stage First", "Abort"]
|
||||
},
|
||||
{
|
||||
question: "Post-deployment monitoring:",
|
||||
options: ["Real-time (15 min)", "Passive (alerts only)"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
**TodoWrite**: Mark Phase 5 completed, Phase 6 in_progress
|
||||
@@ -380,25 +351,24 @@ AskUserQuestion({
|
||||
|
||||
### Phase 6: Execution Dispatch & Follow-up
|
||||
|
||||
**Step 6.1: Dispatch to lite-execute**
|
||||
**Dispatch to lite-execute**:
|
||||
|
||||
```javascript
|
||||
executionContext = {
|
||||
mode: "bugfix",
|
||||
severity: mode, // "regular" | "critical" | "hotfix"
|
||||
severity: auto_detected_severity, // From Phase 2
|
||||
planObject: plan,
|
||||
diagnosisContext: diagnosis,
|
||||
impactContext: impact_assessment,
|
||||
verificationStrategy: test_strategy,
|
||||
branchStrategy: branch_strategy,
|
||||
executionMethod: user_selection.execution_method,
|
||||
monitoringLevel: user_selection.monitoring
|
||||
executionMethod: user_selection.execution_method
|
||||
}
|
||||
|
||||
SlashCommand("/workflow:lite-execute --in-memory --mode bugfix")
|
||||
```
|
||||
|
||||
**Step 6.2: Hotfix Follow-up Tasks** (auto-generated if hotfix mode)
|
||||
**Hotfix Auto Follow-up**:
|
||||
|
||||
```javascript
|
||||
if (mode === "hotfix") {
|
||||
@@ -407,33 +377,24 @@ if (mode === "hotfix") {
|
||||
id: `FOLLOWUP-${taskId}-comprehensive`,
|
||||
title: "Replace hotfix with comprehensive fix",
|
||||
priority: "high",
|
||||
due_date: "within_3_days"
|
||||
due_date: "within_3_days",
|
||||
description: "Refactor quick hotfix into proper solution with full test coverage"
|
||||
},
|
||||
{
|
||||
id: `FOLLOWUP-${taskId}-postmortem`,
|
||||
title: "Incident postmortem",
|
||||
priority: "medium",
|
||||
due_date: "within_1_week"
|
||||
due_date: "within_1_week",
|
||||
sections: ["Timeline", "Root cause", "Prevention measures"]
|
||||
}
|
||||
]
|
||||
|
||||
Write(`.workflow/lite-fixes/${taskId}-followup.json`, follow_up_tasks)
|
||||
}
|
||||
```
|
||||
|
||||
**Step 6.3: Real-time Monitoring** (if selected)
|
||||
|
||||
```javascript
|
||||
if (user_selection.monitoring === "real-time") {
|
||||
console.log(`
|
||||
📊 Real-time Monitoring Active (15 minutes)
|
||||
|
||||
Metrics:
|
||||
- Error rate: <5%
|
||||
- Login success: >95%
|
||||
- Auth latency: <500ms
|
||||
|
||||
Auto-rollback: Enabled
|
||||
⚠️ Hotfix follow-up tasks generated:
|
||||
- Comprehensive fix: ${follow_up_tasks[0].id} (due in 3 days)
|
||||
- Postmortem: ${follow_up_tasks[1].id} (due in 1 week)
|
||||
`)
|
||||
}
|
||||
```
|
||||
@@ -450,6 +411,7 @@ if (user_selection.monitoring === "real-time") {
|
||||
symptom: string,
|
||||
error_message: string | null,
|
||||
keywords: string[],
|
||||
confidence_level: "high" | "medium" | "low", // Search confidence
|
||||
root_cause: {
|
||||
file: string,
|
||||
line_range: string,
|
||||
@@ -468,7 +430,13 @@ if (user_selection.monitoring === "real-time") {
|
||||
system_risk: { availability: string, cascading_failures: string },
|
||||
business_impact: { revenue: string, reputation: string, sla_breach: string },
|
||||
risk_score: number, // 0-10
|
||||
severity: "low" | "medium" | "high" | "critical"
|
||||
severity: "low" | "medium" | "high" | "critical",
|
||||
workflow_adaptation: {
|
||||
diagnosis_depth: string,
|
||||
test_strategy: string,
|
||||
review_optional: boolean,
|
||||
time_budget: string
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
@@ -477,7 +445,6 @@ if (user_selection.monitoring === "real-time") {
|
||||
{
|
||||
strategy: string,
|
||||
summary: string,
|
||||
approach: string,
|
||||
tasks: [{
|
||||
title: string,
|
||||
file: string,
|
||||
@@ -490,85 +457,72 @@ if (user_selection.monitoring === "real-time") {
|
||||
}
|
||||
```
|
||||
|
||||
### executionContext (passed to lite-execute)
|
||||
```javascript
|
||||
{
|
||||
mode: "bugfix",
|
||||
severity: "regular" | "critical" | "hotfix",
|
||||
planObject: fixPlan,
|
||||
diagnosisContext: diagnosisContext,
|
||||
impactContext: impactContext,
|
||||
verificationStrategy: {...},
|
||||
branchStrategy: {...},
|
||||
executionMethod: string,
|
||||
monitoringLevel: string
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Best Practices
|
||||
|
||||
### Severity Selection Guide
|
||||
### When to Use Default Mode
|
||||
|
||||
**Use Regular Mode when:**
|
||||
- Bug is not blocking critical functionality
|
||||
- Have time for comprehensive testing (2-4 hours)
|
||||
- Want to explore multiple fix strategies
|
||||
- Can afford full test suite run
|
||||
**Use for all standard bugs:**
|
||||
- Automatically adapts to severity (no manual mode selection needed)
|
||||
- Risk score determines workflow complexity
|
||||
- Handles 90% of bug fixing scenarios
|
||||
|
||||
**Use Critical Mode when:**
|
||||
- Bug affects significant user base (>20%)
|
||||
- Features degraded but not completely broken
|
||||
- Need fix within 1 hour
|
||||
- Have clear reproduction steps
|
||||
**Typical scenarios:**
|
||||
- UI bugs, logic errors, edge cases
|
||||
- Performance issues (non-critical)
|
||||
- Integration failures
|
||||
- Data validation bugs
|
||||
|
||||
**Use Hotfix Mode when:**
|
||||
### When to Use Hotfix Mode
|
||||
|
||||
**Only use for production incidents:**
|
||||
- Production is down or critically degraded
|
||||
- Revenue/reputation at immediate risk
|
||||
- SLA breach occurring
|
||||
- Need fix within 30 minutes
|
||||
- Issue is well-understood
|
||||
- Issue is well-understood (minimal diagnosis needed)
|
||||
|
||||
### Branching Best Practices
|
||||
**Hotfix characteristics:**
|
||||
- Creates hotfix branch from production tag
|
||||
- Minimal diagnosis (assumes known issue)
|
||||
- Smoke tests only
|
||||
- Auto-generates follow-up tasks
|
||||
- Requires incident tracking
|
||||
|
||||
**Hotfix Branching**:
|
||||
### Branching Strategy
|
||||
|
||||
**Default Mode (feature branch)**:
|
||||
```bash
|
||||
# Standard feature branch workflow
|
||||
git checkout -b fix/issue-description main
|
||||
# ... implement fix
|
||||
git checkout main && git merge fix/issue-description
|
||||
```
|
||||
|
||||
**Hotfix Mode (dual merge)**:
|
||||
```bash
|
||||
# ✅ Correct: Branch from production tag
|
||||
git checkout -b hotfix/fix-name v2.3.1
|
||||
|
||||
# ❌ Wrong: Branch from main (unreleased code)
|
||||
git checkout -b hotfix/fix-name main
|
||||
```
|
||||
|
||||
**Merge Strategy**:
|
||||
```bash
|
||||
# Hotfix merges to both targets
|
||||
# Merge to both targets
|
||||
git checkout main && git merge hotfix/fix-name
|
||||
git checkout production && git merge hotfix/fix-name
|
||||
git tag v2.3.2
|
||||
|
||||
# ❌ Wrong: Branch from main
|
||||
git checkout -b hotfix/fix-name main # Contains unreleased code!
|
||||
```
|
||||
|
||||
### Follow-up Task Management
|
||||
|
||||
**Always create follow-up for hotfixes**:
|
||||
- ✅ Comprehensive fix (within 3 days)
|
||||
- ✅ Test coverage improvement
|
||||
- ✅ Monitoring/alerting enhancements
|
||||
- ✅ Documentation updates
|
||||
- ✅ Postmortem (if critical)
|
||||
|
||||
---
|
||||
|
||||
## Error Handling
|
||||
|
||||
| Error | Cause | Resolution |
|
||||
|-------|-------|------------|
|
||||
| Root cause not found | Insufficient search | Expand search or escalate to /workflow:plan |
|
||||
| Reproduction fails | Stale bug or env issue | Verify environment, request updated steps |
|
||||
| Multiple causes | Complex interaction | Use /cli:discuss-plan for analysis |
|
||||
| Fix too complex | High-risk refactor | Suggest /workflow:plan --mode refactor |
|
||||
| Verification fails | Insufficient tests | Add test cases or adjust mode |
|
||||
| Root cause unclear | Vague symptoms | Extend diagnosis time or use /cli:mode:bug-diagnosis |
|
||||
| Multiple potential causes | Complex interaction | Use /cli:discuss-plan for analysis |
|
||||
| Fix too complex | High-risk refactor | Escalate to /workflow:plan --mode bugfix |
|
||||
| High risk score but unsure | Uncertain severity | Default mode will adapt, proceed normally |
|
||||
|
||||
---
|
||||
|
||||
@@ -577,10 +531,10 @@ git tag v2.3.2
|
||||
**Lite-fix directory**:
|
||||
```
|
||||
.workflow/lite-fixes/
|
||||
├── BUGFIX-2024-10-20T14-30-00.json # Bug fix task JSON
|
||||
├── BUGFIX-2024-10-20T14-30-00-followup.json # Follow-up tasks (hotfix)
|
||||
└── diagnosis-cache/ # Cached diagnosis
|
||||
└── auth-token-hash.json
|
||||
├── BUGFIX-2024-10-20T14-30-00.json # Task JSON
|
||||
├── BUGFIX-2024-10-20T14-30-00-followup.json # Follow-up (hotfix only)
|
||||
└── diagnosis-cache/ # Cached diagnoses
|
||||
└── ${bug_hash}.json
|
||||
```
|
||||
|
||||
**Session-based** (if active session):
|
||||
@@ -597,39 +551,36 @@ git tag v2.3.2
|
||||
|
||||
## Advanced Features
|
||||
|
||||
### 1. Diagnosis Caching
|
||||
### 1. Intelligent Diagnosis Caching
|
||||
|
||||
Speed up similar issues:
|
||||
Reuse diagnosis for similar bugs:
|
||||
```javascript
|
||||
cache_key = hash(bug_keywords + recent_changes_hash)
|
||||
cache_path = `.workflow/lite-fixes/diagnosis-cache/${cache_key}.json`
|
||||
|
||||
if (cache_exists && cache_age < 1_week) {
|
||||
if (cache_exists && cache_age < 7_days && similarity > 0.8) {
|
||||
diagnosis = load_from_cache()
|
||||
console.log("Using cached diagnosis (similar issue found)")
|
||||
}
|
||||
```
|
||||
|
||||
### 2. Auto-Severity Detection
|
||||
### 2. Auto-Severity Suggestion
|
||||
|
||||
Detect urgency from keywords:
|
||||
```javascript
|
||||
if (bug_description.includes("production|down|critical|outage")) {
|
||||
suggested_flag = "--critical"
|
||||
} else if (bug_description.includes("hotfix|urgent|incident")) {
|
||||
suggested_flag = "--hotfix"
|
||||
urgency_keywords = ["production", "down", "outage", "critical", "urgent"]
|
||||
if (bug_description.includes(urgency_keywords) && !mode_specified) {
|
||||
console.log("💡 Tip: Consider --hotfix flag for production issues")
|
||||
}
|
||||
```
|
||||
|
||||
### 3. Rollback Plan (Hotfix)
|
||||
### 3. Adaptive Workflow Intelligence
|
||||
|
||||
Real-time workflow adjustment:
|
||||
```javascript
|
||||
rollback_plan = {
|
||||
method: "git_revert",
|
||||
commands: [
|
||||
"git revert ${commit_sha}",
|
||||
"git push origin hotfix/${branch}",
|
||||
"# Re-deploy v2.3.1"
|
||||
],
|
||||
estimated_time: "5 minutes"
|
||||
// During Phase 2, if risk score suddenly increases
|
||||
if (new_risk_score > initial_estimate * 1.5) {
|
||||
console.log("⚠️ Severity increased, adjusting workflow...")
|
||||
test_strategy = "more_comprehensive"
|
||||
review_required = true
|
||||
}
|
||||
```
|
||||
|
||||
@@ -638,47 +589,40 @@ rollback_plan = {
|
||||
## Related Commands
|
||||
|
||||
**Diagnostic Commands**:
|
||||
- `/cli:mode:bug-diagnosis` - Root cause analysis only
|
||||
- `/cli:mode:code-analysis` - Execution path tracing
|
||||
- `/cli:mode:bug-diagnosis` - Detailed root cause analysis (use before lite-fix if unclear)
|
||||
|
||||
**Fix Execution**:
|
||||
- `/workflow:lite-execute --in-memory` - Execute fix plan (called by lite-fix)
|
||||
- `/cli:execute` - Direct implementation
|
||||
- `/cli:codex-execute` - Multi-stage fix
|
||||
- `/workflow:lite-execute --in-memory` - Execute fix plan (automatically called)
|
||||
|
||||
**Planning Commands**:
|
||||
- `/workflow:plan --mode bugfix` - Complex bug requiring comprehensive planning
|
||||
- `/cli:discuss-plan` - Multi-model collaborative analysis
|
||||
- `/workflow:plan --mode bugfix` - Complex bugs requiring comprehensive planning
|
||||
|
||||
**Review Commands**:
|
||||
- `/workflow:review --type quality` - Post-fix code review
|
||||
- `/workflow:review --type security` - Security validation
|
||||
- `/workflow:review --type quality` - Post-fix quality review
|
||||
|
||||
---
|
||||
|
||||
## Comparison with Other Commands
|
||||
|
||||
| Command | Use Case | Time | Output |
|
||||
|---------|----------|------|--------|
|
||||
| `/workflow:lite-fix` | Bug fixes (regular to critical) | 15min-4h | In-memory + JSON |
|
||||
| `/workflow:lite-plan` | New features | 1-6h | In-memory + JSON |
|
||||
| `/workflow:plan` | Complex features | 1-5 days | Persistent session |
|
||||
| `/cli:mode:bug-diagnosis` | Analysis only | 10-30min | Diagnostic report |
|
||||
| Command | Use Case | Modes | Adaptation | Output |
|
||||
|---------|----------|-------|------------|--------|
|
||||
| `/workflow:lite-fix` | Bug fixes | 2 (default + hotfix) | Auto-adaptive | In-memory + JSON |
|
||||
| `/workflow:lite-plan` | New features | 1 + explore flag | Manual | In-memory + JSON |
|
||||
| `/workflow:plan` | Complex features | Multiple | Manual | Persistent session |
|
||||
| `/cli:mode:bug-diagnosis` | Analysis only | 1 | N/A | Report only |
|
||||
|
||||
---
|
||||
|
||||
## Quality Gates
|
||||
|
||||
**Before execution**:
|
||||
- [ ] Root cause identified (>80% confidence)
|
||||
- [ ] Impact scope clearly defined
|
||||
- [ ] Fix strategy reviewed and approved
|
||||
**Before execution** (auto-checked):
|
||||
- [ ] Root cause identified (>70% confidence for default, >90% for hotfix)
|
||||
- [ ] Impact scope defined
|
||||
- [ ] Fix strategy reviewed
|
||||
- [ ] Verification plan matches risk level
|
||||
- [ ] Branch strategy appropriate
|
||||
|
||||
**Hotfix-specific**:
|
||||
- [ ] Incident ticket linked
|
||||
- [ ] Incident commander approval
|
||||
- [ ] Production tag identified
|
||||
- [ ] Rollback plan documented
|
||||
- [ ] Follow-up tasks generated
|
||||
- [ ] Monitoring configured
|
||||
@@ -687,21 +631,22 @@ rollback_plan = {
|
||||
|
||||
## When to Use lite-fix
|
||||
|
||||
✅ **Good fit**:
|
||||
- Clear bug symptom with reproduction steps
|
||||
- Localized fix (1-3 files)
|
||||
- Time-sensitive but not catastrophic
|
||||
✅ **Perfect for:**
|
||||
- Any bug with clear symptoms
|
||||
- Localized fixes (1-5 files)
|
||||
- Known technology stack
|
||||
- Time-sensitive but not catastrophic (default mode adapts)
|
||||
- Production incidents (use --hotfix)
|
||||
|
||||
❌ **Poor fit**:
|
||||
- Root cause unclear → use `/cli:mode:bug-diagnosis` first
|
||||
❌ **Not suitable for:**
|
||||
- Root cause completely unclear → use `/cli:mode:bug-diagnosis` first
|
||||
- Requires architectural changes → use `/workflow:plan`
|
||||
- Complex legacy code → use `/workflow:plan --legacy-refactor`
|
||||
- Performance investigation → use `/workflow:plan --performance-optimization`
|
||||
- Data migration needed → use `/workflow:plan --data-migration`
|
||||
- Complex legacy code without tests → use `/workflow:plan --legacy-refactor`
|
||||
- Performance deep-dive → use `/workflow:plan --performance-optimization`
|
||||
- Data migration → use `/workflow:plan --data-migration`
|
||||
|
||||
---
|
||||
|
||||
**Last Updated**: 2025-11-20
|
||||
**Version**: 1.0.0
|
||||
**Status**: Design Document
|
||||
**Version**: 2.0.0
|
||||
**Status**: Design Document (Simplified)
|
||||
|
||||
Reference in New Issue
Block a user