Files
myclaude/dev-workflow/README.md
swe-agent[bot] 19facf3385 feat(dev-workflow): Add intelligent backend selection based on task complexity
## Changes

### Core Improvements
1. **Flexible Task Count**: Remove 2-5 hard limit, use natural functional boundaries (typically 2-8)
2. **Complexity-Based Routing**: Tasks rated as simple/medium/complex based on functional requirements
3. **Intelligent Backend Selection**: Orchestrator auto-selects backend based on complexity
   - Simple/Medium → claude (fast, cost-effective)
   - Complex → codex (deep reasoning)
   - UI → gemini (enforced)

### Modified Files
- `dev-workflow/agents/dev-plan-generator.md`:
  - Add complexity field to task template
  - Add comprehensive complexity assessment guide
  - Update quality checks to include complexity validation
  - Remove artificial task count limits

- `dev-workflow/commands/dev.md`:
  - Add backend selection logic in Step 4
  - Update task breakdown to include complexity ratings
  - Add detailed examples for each backend type
  - Update quality standards

- `dev-workflow/README.md`:
  - Update documentation to reflect intelligent backend selection
  - Add complexity-based routing explanation
  - Update examples with complexity ratings

## Architecture
- No changes to codeagent-wrapper (all logic in orchestrator)
- Backward compatible (existing workflows continue to work)
- Complexity evaluation based on functional requirements, NOT code volume

## Benefits
- Better resource utilization (use claude for most tasks, codex for complex ones)
- Cost optimization (avoid using expensive codex for simple tasks)
- Flexibility (no artificial limits on task count)
- Clear complexity rationale for each task

Generated with swe-agent-bot

Co-Authored-By: swe-agent-bot <agent@swe-agent.ai>
2025-12-14 21:57:13 +08:00

5.3 KiB
Raw Blame History

/dev - Minimal Dev Workflow

Overview

A freshly designed lightweight development workflow with no legacy baggage, focused on delivering high-quality code fast.

Flow

/dev trigger
  ↓
AskUserQuestion (requirements clarification)
  ↓
codeagent analysis (plan mode + UI auto-detection)
  ↓
dev-plan-generator (create dev doc)
  ↓
codeagent concurrent development (intelligent backend selection)
  ↓
codeagent testing & verification (≥90% coverage)
  ↓
Done (generate summary)

The 6 Steps

1. Clarify Requirements

  • Use AskUserQuestion to ask the user directly
  • No scoring system, no complex logic
  • 23 rounds of Q&A until the requirement is clear

2. codeagent Analysis & UI Detection

  • Call codeagent to analyze the request in plan mode style
  • Extract: core functions, technical points, task list with complexity ratings
  • UI auto-detection: needs UI work when task involves style assets (.css, .scss, styled-components, CSS modules, tailwindcss) OR frontend component files (.tsx, .jsx, .vue); output yes/no plus evidence

3. Generate Dev Doc

  • Call the dev-plan-generator agent
  • Produce a single dev-plan.md
  • Append a dedicated UI task when Step 2 marks needs_ui: true
  • Include: task breakdown, file scope, dependencies, test commands

4. Concurrent Development

  • Work from the task list in dev-plan.md
  • Use codeagent per task with intelligent backend selection:
    • Simple/Medium tasks → --backend claude (fast, cost-effective)
    • Complex tasks → --backend codex (deep reasoning)
    • UI tasks → --backend gemini (enforced)
  • Backend selected automatically based on task complexity rating
  • Independent tasks → run in parallel
  • Conflicting tasks → run serially

5. Testing & Verification

  • Each codeagent task:
    • Implements the feature
    • Writes tests
    • Runs coverage
    • Reports results (≥90%)

6. Complete

  • Summarize task status
  • Record coverage

Usage

/dev "Implement user login with email + password"

No options, fixed workflow, works out of the box.

Output Structure

.claude/specs/{feature_name}/
└──  dev-plan.md      # Dev document generated by agent

Only one file—minimal and clear.

Core Components

Tools

  • AskUserQuestion: interactive requirement clarification
  • codeagent skill: analysis, development, testing; supports --backend for claude/codex/gemini
  • dev-plan-generator agent: generate dev doc with complexity ratings (subagent via Task tool, saves context)

Intelligent Backend Selection

  • Complexity-based routing: Tasks are rated as simple/medium/complex based on functional requirements (NOT code volume)
    • Simple: Follows existing patterns, deterministic logic → claude
    • Medium: Requires design decisions, multiple scenarios → claude
    • Complex: Architecture design, algorithms, deep domain knowledge → codex
    • UI: Style/component work → gemini (enforced)
  • Flow impact: Step 2 analyzes complexity; Step 3 includes complexity ratings in dev-plan.md; Step 4 auto-selects backend
  • Implementation: Orchestrator reads complexity field and invokes codeagent skill with appropriate backend parameter

Key Features

Fresh Design

  • No legacy project residue
  • No complex scoring logic
  • No extra abstraction layers

Minimal Orchestration

  • Orchestrator controls the flow directly
  • Only three tools/components
  • Steps are straightforward

Concurrency

  • Tasks split based on natural functional boundaries
  • Auto-detect dependencies and conflicts
  • codeagent executes independently with optimal backend

Quality Assurance

  • Enforces 90% coverage
  • codeagent tests and verifies its own work
  • Automatic retry on failure

Example

# Trigger
/dev "Add user login feature"

# Step 1: Clarify requirements
Q: What login methods are supported?
A: Email + password
Q: Should login be remembered?
A: Yes, use JWT token

# Step 2: codeagent analysis
Output:
- Core: email/password login + JWT auth
- Task 1: Backend API (complexity: medium)
- Task 2: Password hashing (complexity: simple)
- Task 3: Frontend form (complexity: simple)
UI detection: needs_ui = true (tailwindcss classes in frontend form)

# Step 3: Generate doc
dev-plan.md generated with complexity ratings ✓

# Step 4-5: Concurrent development (intelligent backend selection)
[task-1] Backend API (claude, medium) → tests → 92% ✓
[task-2] Password hashing (claude, simple) → tests → 95% ✓
[task-3] Frontend form (gemini, UI) → tests → 91% ✓

Directory Structure

dev-workflow/
├── README.md                          # This doc
├── commands/
│   └── dev.md                         # /dev workflow orchestrator definition
└── agents/
    └── dev-plan-generator.md          # Dev plan document generator agent

Minimal structure, only three files.

When to Use

Good for:

  • Any feature size
  • Fast iterations
  • High test coverage needs
  • Wanting concurrent speed-up

Design Principles

  1. KISS: keep it simple
  2. Disposable: no persistent config
  3. Quality first: enforce 90% coverage
  4. Concurrency first: leverage codeagent
  5. No legacy baggage: clean-slate design

Philosophy: zero tolerance for complexity—ship the smallest usable solution, like Linus would.