使用 LangSmith Python 和 TypeScript SDK 管理 **代理代码库** 和 **技能代码库** 在 Context Hub programmatically. 推送 来自 CI 的新版本， 拉取 运行时拉取最新版本或固定提交以向代理注入上下文，并使用其他方法进行 检查存在性, 列出和搜索 代码库，并 删除 不再需要的内容。

设置

1. 安装包：

    pip install -U langsmith
    

    uv add langsmith
    

    yarn add langsmith
    

1. 配置环境变量。如果您已在环境中设置了 LANGSMITH_API_KEY ，请跳过此步骤。否则，请在 **设置 > API 密钥 > 创建 API 密钥** 在 LangSmith 中创建 API 密钥，然后将其设置为环境变量：

推送代理

创建新的代理代码库或提交现有代码库的新版本。如果 代码库尚不存在，则会使用您提供的元数据创建 (description, readme, tags, is_public）。如果已存在， 这些字段仅在显式传递时才会被修补。

该方法返回指向 LangSmith UI:

from langsmith import Client
from langsmith.schemas import FileEntry

client = Client()

url = client.push_agent(
    "email-assistant",
    files={
        "AGENTS.md": FileEntry(
            content="You are an email triage assistant.",
        ),
        "tools.json": FileEntry(content='{"tools": []}'),
    },
    description="Triages and drafts replies to incoming email.",
    tags=["email", "productivity"],
    is_public=False,
)
print(url)

const client = new Client();

const url = await client.pushAgent("email-assistant", {
  files: {
    "AGENTS.md": {
      type: "file",
      content: "You are an email triage assistant.",
    },
    "tools.json": { type: "file", content: '{"tools": []}' },
  },
  description: "Triages and drafts replies to incoming email.",
  tags: ["email", "productivity"],
  isPublic: false,
});
console.log(url);

中新建提交的 URL。推送技能

与 push_agent相同的接口，但提交到技能代码库。使用 来实现可重用的功能，其他代理可以依赖：

from langsmith import Client
from langsmith.schemas import FileEntry

client = Client()

url = client.push_skill(
    "deep-research",
    files={
        "SKILL.md": FileEntry(content="Conduct deep multi-step research."),
    },
    description="Multi-step web research with citations.",
    tags=["research"],
)
print(url)

const client = new Client();

const url = await client.pushSkill("deep-research", {
  files: {
    "SKILL.md": {
      type: "file",
      content: "Conduct deep multi-step research.",
    },
  },
  description: "Multi-step web research with citations.",
  tags: ["research"],
});
console.log(url);

链接到其他代码库

中的条目可以是指向另一个代理或技能代码库的链接，而不是内联文件内容，这样您可以在不重复的情况下组合上下文 files 中的条目可以是指向 另一个代理或技能代码库的链接，这样您可以在不重复内容的情况下组合上下文 跨代码库的内容。例如，委托给共享技能的代理。

如果您省略 commit_id, LangSmith会在您推送此提交时链接到该仓库的最新提交。如果链接的仓库之后有更新，LangSmith会将该更新传播到引用它的父仓库。

from langsmith import Client
from langsmith.schemas import AgentEntry, FileEntry, SkillEntry

client = Client()

url = client.push_agent(
    "email-assistant",
    files={
        "AGENTS.md": FileEntry(content="You are an email triage assistant."),
        # Link to the deep-research skill repo. Omit commit_id to always
        # resolve to the latest version, or pin it for reproducibility.
        "skills/research": SkillEntry(repo_handle="deep-research"),
        # Link to another agent repo.
        "agents/scheduler": AgentEntry(repo_handle="calendar-agent"),
    },
)
print(url)

const client = new Client();

const url = await client.pushAgent("email-assistant", {
  files: {
    "AGENTS.md": { type: "file", content: "You are an email triage assistant." },
    // Link to the deep-research skill repo. Omit commit_id to always
    // resolve to the latest version, or pin it for reproducibility.
    "skills/research": { type: "skill", repo_handle: "deep-research" },
    // Link to another agent repo.
    "agents/scheduler": { type: "agent", repo_handle: "calendar-agent" },
  },
});
console.log(url);

推送参数

两者 push_agent / pushAgent 和 push_skill / pushSkill 接受以下参数：

拉取智能体

拉取智能体仓库的快照。默认返回最新提交；通过以下方式传递提交哈希或标签 version （或将其嵌入标识符中为 owner/name:version）以拉取特定版本：

from langsmith import Client

client = Client()

agent = client.pull_agent("email-assistant")
print(agent.commit_hash)
print(list(agent.files))

# Pull a specific commit.
pinned = client.pull_agent("email-assistant", version="7ca95573")

# Pull a tagged commit (for example, the production tag).
prod = client.pull_agent("email-assistant:production")

const client = new Client();

const agent = await client.pullAgent("email-assistant");
console.log(agent.commit_hash);
console.log(Object.keys(agent.files));

// Pull a specific commit.
const pinned = await client.pullAgent("email-assistant", {
  version: "7ca95573",
});

// Pull a tagged commit.
const prod = await client.pullAgent("email-assistant:production");

拉取技能

拉取技能仓库的快照。功能与 pull_agent 相同，但返回 SkillContext:

from langsmith import Client

client = Client()

skill = client.pull_skill("deep-research")
print(skill.files["SKILL.md"].content)

const client = new Client();

const skill = await client.pullSkill("deep-research");
const skillFile = skill.files["SKILL.md"];
if (skillFile.type === "file") {
  console.log(skillFile.content);
}

拉取参数

两者 pull_agent / pullAgent 和 pull_skill / pullSkill 接受以下参数：

pull_agent 返回一个 AgentContext; pull_skill 返回一个 SkillContext.

检查仓库是否存在

使用这些方法检查您的工作区中是否存在智能体或技能仓库 ，然后再进行推送或拉取：

from langsmith import Client

client = Client()

if client.agent_exists("email-assistant"):
    print("agent already exists")

if not client.skill_exists("deep-research"):
    print("skill not found")

const client = new Client();

if (await client.agentExists("email-assistant")) {
  console.log("agent already exists");
}

if (!(await client.skillExists("deep-research"))) {
  console.log("skill not found");
}

列出智能体和技能

列出任一类型的仓库，可选择按可见性、存档状态和搜索查询进行过滤：

from langsmith import Client

client = Client()

# Python returns a paginated response.
result = client.list_agents(limit=20, query="email")
for repo in result.repos:
    print(repo.repo_handle)

skills = client.list_skills(is_public=True)

const client = new Client();

// TypeScript yields one repo at a time, auto-paginating.
for await (const repo of client.listAgents({ query: "email" })) {
  console.log(repo.repo_handle);
}

for await (const skill of client.listSkills({ isPublic: true })) {
  console.log(skill.repo_handle);
}

删除代理或技能

从您的工作区中删除代理或技能仓库：

from langsmith import Client

client = Client()

client.delete_agent("email-assistant")
client.delete_skill("deep-research")

const client = new Client();

await client.deleteAgent("email-assistant");
await client.deleteSkill("deep-research");