{"id":"fbb790ca-f83a-4309-81fc-b2e900be4295","entityType":"agent","slug":"crewai-mrpetete-llm-se-agent","name":"llm-se-agent","canonicalUrl":"https://www.xpersona.co/agent/crewai-mrpetete-llm-se-agent","canonicalPath":"/agent/crewai-mrpetete-llm-se-agent","generatedAt":"2026-10-10T02:03:30.381Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T19:13:37.433Z","emptyReason":null},"description":"LLM-Based Software Engineering Agent — CrewAI multi-agent system llm-se-agent LLM-Based Software Engineering Agent — CrewAI multi-agent system 一个 AI 驱动的开发助手，接收自然语言需求，自动完成需求分析、代码生成、测试编写和错误调试——全流程端到端。 --- 项目简介 llm-se-agent 是基于 $1 构建、由通义千问（Qwen-Max，via DashScope）驱动的多智能体流水线。输入一句自然语言描述（如 *\"创建一个登录系统\"*），系统会按序调度三个专职 AI 智能体，自动生成经过测试和调试的完整代码，无需人工干预。 本项目为软件工程课程作业，由 7 人团队完成，旨在验证大语言模型自动化软件开发核心生命周期的可行性。 --- 工作原理 所有智能体间通信均通过经过校验的 JSON Schema 进行。编排器（M1）负责管理流水线、执行数据合约、处理 CrewAI 任务排序。 快速开始 **1. 克隆仓","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/MrPetete/llm-se-agent","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/MrPetete/llm-se-agent","kind":"source"}],"safetyScore":66,"overallRank":22.8,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"LLM-Based Software Engineering Agent — CrewAI multi-agent system llm-se-agent LLM-Based Software Engineering Agent — CrewAI multi-agent system 一个 AI 驱动的开发助手，接收自"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:13:37.433Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:13:37.433Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":1,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T19:13:37.425Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T19:13:37.433Z","lastCrawledAt":"2026-10-09T19:13:37.425Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T19:13:37.425Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-10T02:03:30.380Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-mrpetete-llm-se-agent/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T19:13:37.433Z","emptyReason":null},"readme":"# llm-se-agent\nLLM-Based Software Engineering Agent — CrewAI multi-agent system\n\n一个 AI 驱动的开发助手，接收自然语言需求，自动完成需求分析、代码生成、测试编写和错误调试——全流程端到端。\n\n---\n\n## 项目简介\n\n`llm-se-agent` 是基于 [CrewAI](https://github.com/joaomdmoura/crewAI) 构建、由通义千问（Qwen-Max，via DashScope）驱动的多智能体流水线。输入一句自然语言描述（如 *\"创建一个登录系统\"*），系统会按序调度三个专职 AI 智能体，自动生成经过测试和调试的完整代码，无需人工干预。\n\n本项目为软件工程课程作业，由 7 人团队完成，旨在验证大语言模型自动化软件开发核心生命周期的可行性。\n\n---\n\n## 工作原理\n\n```\n用户输入（自然语言需求）\n    │\n    ▼\n┌─────────────────────┐\n│  Agent A            │  需求分析师\n│  (M2)               │  → 生成 PRD、用户故事、架构概述\n└────────┬────────────┘\n         │  analysis_output.json\n         ▼\n┌─────────────────────┐\n│  Agent B            │  代码生成器\n│  (M3)               │  → 根据 PRD 生成实现代码\n└────────┬────────────┘\n         │  implementation_output.json\n         ▼\n┌─────────────────────┐\n│  Agent C            │  测试与调试器\n│  (M4)               │  → 编写 pytest 测试、在沙箱中执行、\n└────────┬────────────┘    分类并修复失败用例\n         │  test_output.json / debug_output.json\n         ▼\n    最终输出\n```\n\n所有智能体间通信均通过经过校验的 JSON Schema 进行。编排器（`M1`）负责管理流水线、执行数据合约、处理 CrewAI 任务排序。\n\n## 快速开始\n\n**1. 克隆仓库并检查环境**\n\n```bash\ngit clone https://github.com/<your-org>/llm-se-agent.git\ncd llm-se-agent\npip install -r requirements.txt\npython scripts/doctor.py\n```\n\n**2. 配置 API 密钥**\n\n```bash\ncp .env.example .env\n# 编辑 .env 文件，填写以下内容：\n# LLM_PROVIDER=qwen\n# DASHSCOPE_API_KEY=your_key_here\n```\n\n**3. 运行流水线**\n\n```bash\npython run.py build \"创建一个待办事项的 REST API\"\n```\n\n**4. 其他 CLI 命令**\n\n```bash\npython run.py doctor   # 重新运行环境检查\npython run.py stats    # 查看 logs/ 中的 LLM 调用统计\n```\n\n**输出**保存在 `outputs/<时间戳>/` 目录下，包含 `analysis_output.json`、`implementation_output.json`、`test_output.json`、`debug_output.json` 及所有生成的代码文件。\n\n---\n\n## 智能体介绍\n\n### Agent A — 需求分析师\n基于 CrewAI 实现。接收自然语言 prompt，依次执行三个任务：PRD 生成、用户故事扩展、架构概述。采用少样本提示（2 个示例），输出结构化 JSON，经 `schemas/analysis_output.json` 校验。\n\n### Agent B — 代码生成器\n接收 Agent A 的结构化 PRD，通过 Qwen 生成可运行的 Python 实现代码。内置 `ast.parse` 语法校验，失败时进行一次 Qwen 修复尝试，并提供确定性模拟回退机制。通过 `retry_used` / `retry_reason` 字段将重试状态暴露给编排器。\n\n### Agent C — 测试与调试器\n读取 Agent B 的代码输出，通过 Qwen 生成 pytest 测试套件，并在子进程沙箱中执行。测试失败时，将回溯信息分类至 9 个类别（TypeError、ImportError、AttributeError、AssertionError 等），生成针对性修复方案并重新运行测试进行验证。输出 `debug_output.json`，包含修复前后的完整计数与已应用的修复内容。\n\n---\n\n## 团队成员\n\n| 成员 | 角色 | 职责 |\n|------|------|------|\n| M1 | 组长 & 编排器 | 系统架构、JSON Schema、CrewAI 流水线、集成 |\n| M2 | Agent A — 需求分析师 | PRD 生成、用户故事、架构概述 |\n| M3 | Agent B — 代码生成器 | 代码生成、语法验证、修复循环 |\n| M4 | Agent C — 测试与调试器 | 测试生成、沙箱执行、Bug 分类与修复 |\n| M5 | DevOps & LLM 基础设施 | LLM 封装器、CI/CD、Docker、CLI、配置、doctor.py |\n| M6 | 文档 & 集成支持 | 技术报告、集成参考文档、风格指南、使用指南 |\n| M7 | QA & 评估 | 8 个测试场景（TC-01–TC-08）、KPI 指标、评估报告 |\n\n---\n\n## 测试场景\n\nM7 设计了覆盖三个难度层级的 8 个评估场景：\n\n| 编号 | 名称 | 难度 |\n|------|------|------|\n| TC-01 | 问候应用 | 简单 |\n| TC-02 | 基础计算器 | 简单 |\n| TC-03 | CSV 汇总工具 | 简单 |\n| TC-04 | 带数据库的待办清单 | 中等 |\n| TC-05 | 网页爬虫 | 中等 |\n| TC-06 | 天气 API 客户端 | 中等 |\n| TC-07 | FastAPI CRUD 接口 | 困难 |\n| TC-08 | 多模块项目 | 中等 |\n\n**每个场景追踪的 KPI：** 代码行数（LOC）、Pylint 评分（0–10）、执行时间、峰值内存占用、通过/失败正确性。\n\n---\n\n## 技术栈\n\n- **LLM 框架：** [CrewAI](https://github.com/joaomdmoura/crewAI)\n- **LLM 提供商：** 通义千问（Qwen-Max via [DashScope](https://dashscope.aliyun.com/)）（可插拔：支持 OpenAI / Anthropic）\n- **语言：** Python 3.10+\n- **测试：** pytest + pytest-json-report\n- **CI：** GitHub Actions（flake8 + pytest，拦截过时的 `gpt-4` 字符串）\n- **容器化：** Docker + docker-compose\n- **配置管理：** pydantic-settings\n\n---\n\n## 文档\n\n## 开发规范\n\n**分支策略：**\n- `main` — 仅用于稳定发布\n- `dev` — 集成分支，所有 PR 合并至此\n- `feature/<名称>` — 各智能体/功能开发分支\n\n禁止直接推送至 `dev` 或 `main`，所有变更须通过 Pull Request 并由 M1 审核后合并。\n\n**LLM 调用**记录至 `logs/llm_calls.jsonl`（包含时间戳、智能体、提供商、模型、Token 数、延迟）。运行 `python run.py stats` 查看汇总统计。\n","readmeExcerpt":"llm-se-agent LLM-Based Software Engineering Agent — CrewAI multi-agent system 一个 AI 驱动的开发助手，接收自然语言需求，自动完成需求分析、代码生成、测试编写和错误调试——全流程端到端。 --- 项目简介 llm-se-agent 是基于 $1 构建、由通义千问（Qwen-Max，via DashScope）驱动的多智能体流水线。输入一句自然语言描述（如 *\"创建一个登录系统\"*），系统会按序调度三个专职 AI 智能体，自动生成经过测试和调试的完整代码，无需人工干预。 本项目为软件工程课程作业，由 7 人团队完成，旨在验证大语言模型自动化软件开发核心生命周期的可行性。 --- 工作原理 所有智能体间通信均通过经过校验的 JSON Schema 进行。编排器（M1）负责管理流水线、执行数据合约、处理 CrewAI 任务排序。 快速开始 **1. 克隆仓","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"用户输入（自然语言需求）\n    │\n    ▼\n┌─────────────────────┐\n│  Agent A            │  需求分析师\n│  (M2)               │  → 生成 PRD、用户故事、架构概述\n└────────┬────────────┘\n         │  analysis_output.json\n         ▼\n┌─────────────────────┐\n│  Agent B            │  代码生成器\n│  (M3)               │  → 根据 PRD 生成实现代码\n└────────┬────────────┘\n         │  implementation_output.json\n         ▼\n┌─────────────────────┐\n│  Agent C            │  测试与调试器\n│  (M4)               │  → 编写 pytest 测试、在沙箱中执行、\n└────────┬────────────┘    分类并修复失败用例\n         │  test_output.json / debug_output.json\n         ▼\n    最终输出"},{"language":"bash","snippet":"git clone https://github.com/<your-org>/llm-se-agent.git\ncd llm-se-agent\npip install -r requirements.txt\npython scripts/doctor.py"},{"language":"bash","snippet":"cp .env.example .env\n# 编辑 .env 文件，填写以下内容：\n# LLM_PROVIDER=qwen\n# DASHSCOPE_API_KEY=your_key_here"},{"language":"bash","snippet":"python run.py build \"创建一个待办事项的 REST API\""},{"language":"bash","snippet":"python run.py doctor   # 重新运行环境检查\npython run.py stats    # 查看 logs/ 中的 LLM 调用统计"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"LLM-Based Software Engineering Agent — CrewAI multi-agent system llm-se-agent LLM-Based Software Engineering Agent — CrewAI multi-agent system 一个 AI 驱动的开发助手，接收自然语言需求，自动完成需求分析、代码生成、测试编写和错误调试——全流程端到端。 --- 项目简介 llm-se-agent 是基于 $1 构建、由通义千问（Qwen-Max，via DashScope）驱动的多智能体流水线。输入一句自然语言描述（如 *\"创建一个登录系统\"*），系统会按序调度三个专职 AI 智能体，自动生成经过测试和调试的完整代码，无需人工干预。 本项目为软件工程课程作业，由 7 人团队完成，旨在验证大语言模型自动化软件开发核心生命周期的可行性。 --- 工作原理 所有智能体间通信均通过经过校验的 JSON Schema 进行。编排器（M1）负责管理流水线、执行数据合约、处理 CrewAI 任务排序。 快速开始 **1. 克隆仓","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":348,"uniquenessScore":63,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:13:37.433Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T19:13:37.433Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T02:03:30.381Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}