Agentica 代码排查

AI 智能社区

作者仓库星标 3,783
作者仓库 Continuous-Claude-v3

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

原文结构

Quick Reference：原文以此为独立章节。
11 Pattern Classes：Pattern · Purpose · Key Method Swarm · Parallel perspectives · .execute(query) Pipeline · Sequential stages · .run(initialstate)
Core Infrastructure：Component · File · Purpose CoordinationDB · coordination.py · SQLite tracking trackedspawn · trackedagent.py · Agent with tracking

适用与边界

When to Use：Building multi-agent workflows with Agentica patterns Need exact constructor signatures for pattern classes Want to understand coordination database schema
当前原文没有单列不适用场景或限制。

原文中的明确线索

要点：「Complete API specification for Agentica multi-agent coordination infrastructure.」
文件与命令：Swarm、.execute(query)、Pipeline、.run(initialstate)、Hierarchical、.execute(task)、Jury、.decide(returntype, question)

流狐整理：以上内容来自当前 SKILL.md 的章节与原词；未补写作者没有声明的工具、兼容性或能力。

Agentica Infrastructure Reference

Complete API specification for Agentica multi-agent coordination infrastructure.

When to Use

Building multi-agent workflows with Agentica patterns
Need exact constructor signatures for pattern classes
Want to understand coordination database schema
Implementing custom patterns using primitives
Debugging agent tracking or orphan detection

Quick Reference

11 Pattern Classes

Pattern	Purpose	Key Method
`Swarm`	Parallel perspectives	`.execute(query)`
`Pipeline`	Sequential stages	`.run(initial_state)`
`Hierarchical`	Coordinator + specialists	`.execute(task)`
`Jury`	Voting consensus	`.decide(return_type, question)`
`GeneratorCritic`	Iterative refinement	`.run(task)`
`CircuitBreaker`	Failure fallback	`.execute(query)`
`Adversarial`	Debate + judge	`.resolve(question)`
`ChainOfResponsibility`	Route to handler	`.process(query)`
`MapReduce`	Fan out + reduce	`.execute(query, chunks)`
`Blackboard`	Shared state	`.solve(query)`
`EventDriven`	Event bus	`.publish(event)`

Core Infrastructure

Component	File	Purpose
`CoordinationDB`	`coordination.py`	SQLite tracking
`tracked_spawn`	`tracked_agent.py`	Agent with tracking
`HandoffAtom`	`handoff_atom.py`	Universal handoff format
`BlackboardCache`	`blackboard.py`	Hot tier communication
`MemoryService`	`memory_service.py`	Core + Archival memory
`create_claude_scope`	`claude_scope.py`	Scope with file ops

Primitives

Primitive	Purpose
`Consensus`	Voting (MAJORITY, UNANIMOUS, THRESHOLD)
`Aggregator`	Combine results (MERGE, CONCAT, BEST)
`HandoffState`	Structured agent handoff
`build_premise`	Structured premise builder
`gather_fail_fast`	TaskGroup-based parallel execution

Full API Spec

See: API_SPEC.md in this skill directory

Usage Example

from scripts.agentica_patterns.patterns import Swarm, Jury
from scripts.agentica_patterns.primitives import ConsensusMode
from scripts.agentica_patterns.coordination import CoordinationDB
from scripts.agentica_patterns.tracked_agent import tracked_spawn

# Create tracking database
db = CoordinationDB(session_id="my-session")

# Swarm with tracking
swarm = Swarm(
    perspectives=["Security expert", "Performance expert"],
    db=db
)
result = await swarm.execute("Review this code")

# Jury with consensus
jury = Jury(
    num_jurors=3,
    consensus_mode=ConsensusMode.MAJORITY,
    premise="You evaluate code quality",
    db=db
)
verdict = await jury.decide(bool, "Is this code production ready?")

Location

API spec: .claude/skills/agentica-infrastructure/API_SPEC.md Source: scripts/agentica_patterns/

流狐档案作者与许可取自来源；运行、权限和网络为流狐检测或估算

流狐分类: AI 智能
作者声明 Agent: 未找到明确声明；不据此推断已兼容或已测试
静态检查: 88 / 100 · 启发式扫描，不代表运行安全
作者 / 版本 / 许可: @parcadei · 未声明 license
流狐 Token 估算: 低消耗
流狐接入估算: 需简单配置
是否需要外部 API Key: 未发现要求
检测到的系统要求: 未声明
底层运行要求: Python
检测到的文件与系统行为: 只读
允许写入 / 修改
Shell 执行
检测到的网络行为: 仅限本地
安装命令数: 无（仅作为资料）

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 agentica-infrastructure.preview

# Usage Example

from scripts.agentica_patterns.patterns import Swarm, Jury
from scripts.agentica_patterns.primitives import ConsensusMode
from scripts.agentica_patterns.coordination import CoordinationDB
from scripts.agentica_patterns.tracked_agent import tracked_spawn

# Create tracking database
db = CoordinationDB(session_id="my-session")

# Swarm with tracking
swarm = Swarm(
    perspectives=["Security expert", "Performance expert"],
    db=db
)
result = await swarm.execute("Review this code")

# Jury with consensus
jury = Jury(
    num_jurors=3,
    consensus_mode=ConsensusMode.MAJORITY,
    premise="You evaluate code quality",
    db=db
)
verdict = await jury.decide(bool, "Is this code production ready?")

SKILL.md SKILL.md

# Agentica Infrastructure Reference

Complete API specification for Agentica multi-agent coordination infrastructure.

## When to Use

- Building multi-agent workflows with Agentica patterns
- Need exact constructor signatures for pattern classes
- Want to understand coordination database schema
- Implementing custom patterns using primitives
- Debugging agent tracking or orphan detection

## Quick Reference

### 11 Pattern Classes

| Pattern | Purpose | Key Method |
|---------|---------|------------|
| `Swarm` | Parallel perspectives | `.execute(query)` |
| `Pipeline` | Sequential stages | `.run(initial_state)` |
| `Hierarchical` | Coordinator + specialists | `.execute(task)` |
| `Jury` | Voting consensus | `.decide(return_type, question)` |
| `GeneratorCritic` | Iterative refinement | `.run(task)` |
| `CircuitBreaker` | Failure fallback | `.execute(query)` |
| `Adversarial` | Debate + judge | `.resolve(question)` |
| `ChainOfResponsibility` | Route to handler | `.process(query)` |
| `MapReduce` | Fan out + reduce | `.execute(query, chunks)` |
| `Blackboard` | Shared state | `.solve(query)` |
| `EventDriven` | Event bus | `.publish(event)` |

### Core Infrastructure

| Component | File | Purpose |
|-----------|------|---------|
| `CoordinationDB` | `coordination.py` | SQLite tracking |
| `tracked_spawn` | `tracked_agent.py` | Agent with tracking |
| `HandoffAtom` | `handoff_atom.py` | Universal handoff format |
| `BlackboardCache` | `blackboard.py` | Hot tier communication |
| `MemoryService` | `memory_service.py` | Core + Archival memory |
| `create_claude_scope` | `claude_scope.py` | Scope with file ops |

### Primitives

| Primitive | Purpose |
|-----------|---------|
| `Consensus` | Voting (MAJORITY, UNANIMOUS, THRESHOLD) |

…

证据边界与执行链路

作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。

章节    -> When to Use → Quick Reference → 11 Pattern Classes → Core Infrastructure → Primitives → Full API Spec
要点    -> Complete API specification for Agentica multi-agent coordination infrastructure.
文件/命令 -> Swarm · .execute(query) · Pipeline · .run(initialstate) · Hierarchical · .execute(task) · Jury · .decide(returntype, question)
内容 SHA-256 -> 87fef76567df