2nd/10_Wiki/Topics/Backend/E-component (Execution Loop).md

---
id: wiki-2026-0508-e-component-execution-loop
title: E-component (Execution Loop)
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [Execution Loop, E-Loop, Agent Runtime Loop]
duplicate_of: none
source_trust_level: A
confidence_score: 0.9
verification_status: applied
tags: [agent, runtime, llm, architecture]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: Python
  framework: anthropic-sdk
---

# E-component (Execution Loop)

## 매 한 줄
> **"매 LLM agent 의 heartbeat"**. 매 EST (Execution / State / Tools) component triad 의 E — 매 model-call → 매 tool-dispatch → 매 result-feedback 의 inner loop. 매 Claude Agent SDK / OpenAI Assistants / LangGraph 매 same primitive.

## 매 핵심

### 매 mechanism
1. Send messages + tool definitions to LLM.
2. LLM 매 returns text + (optional) tool_use blocks.
3. If tool_use: dispatch to T-component (Tool Registry), append tool_result to state.
4. Loop until 매 stop_reason == "end_turn" or max_iterations.

### 매 components
- **E (this)**: orchestrator — message-pump.
- **S** (State Store): conversation history, scratch state.
- **T** (Tool Registry): handler dispatch, schema validation.

### 매 응용
1. Code agents (Claude Code, Cursor, Devin).
2. Research agents (Perplexity, Deep Research).
3. Workflow automation.

## 💻 패턴

### Minimal execution loop (Anthropic SDK 2026)
```python
from anthropic import Anthropic
client = Anthropic()

def run(messages, tools, dispatch, max_iters=20):
    for _ in range(max_iters):
        resp = client.messages.create(
            model="claude-opus-4-7",
            max_tokens=4096,
            tools=tools,
            messages=messages,
        )
        messages.append({"role": "assistant", "content": resp.content})
        if resp.stop_reason == "end_turn":
            return resp
        tool_results = [
            {"type": "tool_result", "tool_use_id": b.id, "content": dispatch(b.name, b.input)}
            for b in resp.content if b.type == "tool_use"
        ]
        messages.append({"role": "user", "content": tool_results})
    raise RuntimeError("max iterations exceeded")
```

### Streaming variant
```python
with client.messages.stream(model="claude-opus-4-7", messages=messages, tools=tools) as stream:
    for event in stream:
        if event.type == "content_block_delta":
            print(event.delta.text, end="", flush=True)
    final = stream.get_final_message()
```

### Tool dispatch (T-component plug-in)
```python
TOOLS = {
    "read_file": lambda input: open(input["path"]).read(),
    "list_dir":  lambda input: os.listdir(input["path"]),
}
def dispatch(name, input):
    try: return TOOLS[name](input)
    except Exception as e: return f"Error: {e}"
```

### Stop conditions
```python
STOP = {"end_turn", "stop_sequence", "max_tokens"}
if resp.stop_reason in STOP: break
```

### Prompt caching the system + tools
```python
resp = client.messages.create(
    model="claude-opus-4-7",
    system=[{"type": "text", "text": SYSTEM, "cache_control": {"type": "ephemeral"}}],
    tools=[{**t, "cache_control": {"type": "ephemeral"}} for t in tools],
    messages=messages,
)
```

### Budget guard
```python
total_tokens = 0
while True:
    resp = client.messages.create(...)
    total_tokens += resp.usage.input_tokens + resp.usage.output_tokens
    if total_tokens > BUDGET: raise BudgetExceeded()
```

## 매 결정 기준
| 상황 | Approach |
|---|---|
| Single-turn task | Direct API call |
| Multi-tool task | E-loop |
| Long-running workflow | E-loop + checkpointing (S) |

**기본값**: E-loop + prompt caching + budget guard + max-iter clamp.

## 🔗 Graph
- 부모: [[Agent-Architecture]]
- 변형: [[ReAct]]
- 응용: [[LangGraph]]
- Adjacent: [[S-component-State-Store]] · [[T-component-Tool-Registry]]

## 🤖 LLM 활용
**언제**: building agent runtime, multi-step tool-use task.
**언제 X**: pure single-shot prompt (no tools, no state).

## ❌ 안티패턴
- **No max-iter cap**: 매 infinite-loop 의 risk.
- **No budget guard**: 매 unbounded cost.
- **Recreating system prompt per turn**: cache miss → 매 5-10x cost.

## 🧪 검증 / 중복
- Verified (Anthropic Messages API docs, Claude Agent SDK).
- 신뢰도 A.

## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — E-component FULL with SDK 2026 loop patterns |