undefined

**File Patterns:** `**/agents/*.py`, `**/schemas/*.py`, `**/models/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | All LLM outputs use Pydantic/dataclass schemas with validators |
| **Partial** | Some outputs typed, but dict returns or unvalidated strings exist |
| **Weak** | LLM returns raw strings parsed manually or with regex |

**Anti-patterns:**
- `json.loads(llm_response)` without schema validation
- `output.split()` or regex parsing of LLM responses
- `dict[str, Any]` return types from agents
- No validation between LLM output and handler execution

---

undefined

**File Patterns:** `**/prompts/**`, `**/templates/**`, `**/agents/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Prompts in separate files, templated (Jinja2), versioned |
| **Partial** | Prompts as module constants, some parameterization |
| **Weak** | Prompts hardcoded inline in functions, f-strings only |

**Anti-patterns:**
- `f"You are a {role}..."` inline in agent methods
- Prompts mixed with business logic
- No way to iterate on prompts without code changes
- No prompt versioning or A/B testing capability

---

undefined

**File Patterns:** `**/context/*.py`, `**/state/*.py`, `**/core/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Custom context format, token optimization, typed events, compaction |
| **Partial** | Basic message history with some structure |
| **Weak** | Raw message accumulation, standard OpenAI format only |

**Anti-patterns:**
- Unbounded message accumulation
- Large artifacts embedded inline (diffs, files)
- No agent-specific context filtering
- Same context for all agent types

---

undefined

**File Patterns:** `**/tools/*.py`, `**/handlers/*.py`, `**/agents/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | All tool outputs schema-validated, handlers type-safe |
| **Partial** | Most tools typed, some loose dict returns |
| **Weak** | Tools return arbitrary dicts, no validation layer |

**Anti-patterns:**
- Tool handlers that directly execute LLM output
- `eval()` or `exec()` on LLM-generated code
- No separation between decision (LLM) and execution (code)
- Magic method dispatch based on string matching

---

undefined

**File Patterns:** `**/state/*.py`, `**/models/*.py`, `**/database/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Single serializable state object with all execution metadata |
| **Partial** | State exists but split across systems (memory + DB) |
| **Weak** | Execution state scattered, requires multiple queries to reconstruct |

**Anti-patterns:**
- Retry count stored separately from task state
- Error history in logs but not in state
- LangGraph checkpoints + separate database storage
- No unified event thread

---

undefined

**File Patterns:** `**/routes/*.py`, `**/api/*.py`, `**/orchestrator/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | REST API + webhook resume, pause at any point including mid-tool |
| **Partial** | Launch/pause/resume exists but only at coarse-grained points |
| **Weak** | CLI-only launch, no pause/resume capability |

**Anti-patterns:**
- Blocking `input()` or `confirm()` calls
- No way to resume after process restart
- Approval only at plan level, not per-tool
- No webhook-based resume from external systems

---

undefined

**File Patterns:** `**/agents/*.py`, `**/tools/*.py`, `**/orchestrator/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | `request_human_input` tool with question/options/urgency/format |
| **Partial** | Approval gates exist but hardcoded in graph structure |
| **Weak** | Blocking CLI prompts, no tool-based human contact |

**Anti-patterns:**
- `typer.confirm()` in agent code
- Human contact hardcoded at specific graph nodes
- No way for agents to ask clarifying questions
- Single response format (yes/no only)

---

undefined

**File Patterns:** `**/orchestrator/*.py`, `**/graph/*.py`, `**/core/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Custom routing functions, conditional edges, execution mode control |
| **Partial** | Framework control flow with some customization |
| **Weak** | Default framework loop with no custom routing |

**Anti-patterns:**
- Single path through graph with no branching
- No distinction between tool types (all treated same)
- Framework-default error handling only
- No rate limiting or resource management

---

undefined

**File Patterns:** `**/agents/*.py`, `**/orchestrator/*.py`, `**/core/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Errors in context, retry with threshold, automatic escalation |
| **Partial** | Errors logged and returned, no automatic retry loop |
| **Weak** | Errors logged only, not fed back to LLM, task fails immediately |

**Anti-patterns:**
- `logger.error()` without adding to context
- No retry mechanism (fail immediately)
- No consecutive error tracking
- No escalation to humans after repeated failures

---

undefined

**File Patterns:** `**/agents/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | 3+ specialized agents, each with single responsibility, step limits |
| **Partial** | Multiple agents but some have broad scope |
| **Weak** | Single "god" agent that handles everything |

**Anti-patterns:**
- Single agent with 20+ tools
- Agent with unbounded step count
- Mixed responsibilities (planning + execution + review)
- No step or time limits on agent execution

---

undefined

**File Patterns:** `**/routes/*.py`, `**/cli/*.py`, `**/main.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | CLI + REST + WebSocket + webhooks + chat integrations |
| **Partial** | CLI + REST API available |
| **Weak** | CLI only, no programmatic access |

**Anti-patterns:**
- Only `if __name__ == "__main__"` entry point
- No REST API for external systems
- No event streaming for real-time updates
- Trigger logic tightly coupled to execution

---

undefined

**File Patterns:** `**/agents/*.py`, `**/nodes/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Immutable state updates, side effects isolated to tools/handlers |
| **Partial** | Mostly immutable, some in-place mutations |
| **Weak** | State mutated in place, side effects mixed with agent logic |

**Anti-patterns:**
- `state.field = new_value` (mutation)
- File writes inside agent methods
- HTTP calls inside agent decision logic
- Shared mutable state between agents

---

undefined

**File Patterns:** `**/context/*.py`, `**/retrieval/*.py`, `**/rag/*.py`

**Compliance Criteria:**

| Level | Criteria |
|-------|----------|
| **Strong** | Automatic pre-fetch of related tests, files, docs before planning |
| **Partial** | Manual context passing, design doc support |
| **Weak** | No pre-fetching, LLM must request all context via tools |

**Anti-patterns:**
- Architect starts with issue only, no codebase context
- No semantic search for similar past work
- Related tests/files discovered only during execution
- No RAG or document retrieval system

---

| Factor | Status | Notes |
|--------|--------|-------|
| 1. Natural Language -> Tool Calls | **Strong/Partial/Weak** | [Key finding] |
| 2. Own Your Prompts | **Strong/Partial/Weak** | [Key finding] |
| ... | ... | ... |
| 13. Pre-fetch Context | **Strong/Partial/Weak** | [Key finding] |

**Overall**: X Strong, Y Partial, Z Weak