OpenAI Assistants API v2 使用指南与迁移方案 - 2026年弃用前必看

openai-assistants by jezweb/claude-skills

313 周安装量

643 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/jezweb/claude-skills --skill openai-assistants

AI/机器学习 Node.js API

🇨🇳中文介绍

OpenAI Assistants API v2

状态：生产就绪（⚠️ 已弃用 - 将于 2026 年 8 月 26 日停止服务）包：openai@6.16.0 最后更新：2026-01-21 v1 弃用：2024 年 12 月 18 日 v2 停止服务：2026 年 8 月 26 日（请迁移至 Responses API）

⚠️ 弃用通知

OpenAI 正在弃用 Assistants API，转而支持 Responses API。

时间线：v1 于 2024 年 12 月 18 日弃用 | v2 将于 2026 年 8 月 26 日停止服务

在以下情况下使用此技能：维护遗留应用程序或迁移现有代码（12-18 个月的窗口期）不要在以下情况下使用：开始新项目（请改用 openai-responses 技能）

迁移：请参阅 references/migration-to-responses.md

快速开始

npm install openai@6.16.0



import OpenAI from 'openai';

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

// 1. 创建助手
const assistant = await openai.beta.assistants.create({
  name: "Math Tutor",
  instructions: "You are a math tutor. Use code interpreter for calculations.",
  tools: [{ type: "code_interpreter" }],
  model: "gpt-5",
});

// 2. 创建线程
const thread = await openai.beta.threads.create();

// 3. 添加消息
await openai.beta.threads.messages.create(thread.id, {
  role: "user",
  content: "Solve: 3x + 11 = 14",
});

// 4. 运行助手
const run = await openai.beta.threads.runs.create(thread.id, {
  assistant_id: assistant.id,
});

// 5. 轮询完成状态
let status = await openai.beta.threads.runs.retrieve(thread.id, run.id);
while (status.status !== 'completed') {
  await new Promise(r => setTimeout(r, 1000));
  status = await openai.beta.threads.runs.retrieve(thread.id, run.id);
}

// 6. 获取响应
const messages = await openai.beta.threads.messages.list(thread.id);
console.log(messages.data[0].content[0].text.value);

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

文件搜索（RAG）

使用向量存储进行语义搜索。最多 10,000 个文件（v2，v1 为 20）。定价：$0.10/GB/天（1GB 免费）。

// 创建向量存储
const vs = await openai.beta.vectorStores.create({ name: "Docs" });
await openai.beta.vectorStores.files.create(vs.id, { file_id: "file_123" });

// 等待索引完成
let store = await openai.beta.vectorStores.retrieve(vs.id);
while (store.status === 'in_progress') {
  await new Promise(r => setTimeout(r, 2000));
  store = await openai.beta.vectorStores.retrieve(vs.id);
}

// 在助手中使用
tool_resources: { file_search: { vector_store_ids: [vs.id] } }

⚠️ 使用前请等待 status: 'completed'

当 run.status === 'requires_action' 时提交工具输出：

if (run.status === 'requires_action') {
  const toolCalls = run.required_action.submit_tool_outputs.tool_calls;
  const outputs = toolCalls.map(tc => ({
    tool_call_id: tc.id,
    output: JSON.stringify(yourFunction(JSON.parse(tc.function.arguments))),
  }));

  run = await openai.beta.threads.runs.submitToolOutputs(thread.id, run.id, {
    tool_outputs: outputs,
  });
}

代码解释器：.c, .cpp, .csv, .docx, .html, .java, .json, .md, .pdf, .php, .pptx, .py, .rb, .tex, .txt, .css, .jpeg, .jpg, .js, .gif, .png, .tar, .ts, .xlsx, .xml, .zip（最大 512MB）

文件搜索：.c, .cpp, .docx, .html, .java, .json, .md, .pdf, .php, .pptx, .py, .rb, .tex, .txt, .css, .js, .ts, .go（最大 512MB）

1. 线程已有活动运行

Error: 400 Can't add messages to thread_xxx while a run run_xxx is active.

修复：首先取消活动运行：await openai.beta.threads.runs.cancel(threadId, runId)

2. 运行轮询超时 / 不完整状态

Error: OpenAIError: Final run has not been received

原因：长时间运行的任务可能超过轮询窗口或以 incomplete 状态结束预防：优雅处理不完整的运行

try {
  const stream = await openai.beta.threads.runs.stream(thread.id, { assistant_id });
  for await (const event of stream) {
    if (event.event === 'thread.message.delta') {
      process.stdout.write(event.data.delta.content?.[0]?.text?.value || '');
    }
  }
} catch (error) {
  if (error.message?.includes('Final run has not been received')) {
    // 运行以 'incomplete' 状态结束 - 线程可以继续
    const run = await openai.beta.threads.runs.retrieve(thread.id, runId);
    if (run.status === 'incomplete') {
      // 处理：提示用户继续，减少 max_completion_tokens 等
    }
  }
}

3. 向量存储未就绪 在索引完成前使用向量存储。修复：轮询 vectorStores.retrieve() 直到 status === 'completed'（参见文件搜索部分）

4. 文件上传格式问题 不支持的文件格式会导致静默失败。修复：上传前验证文件扩展名（参见文件格式部分）

5. 向量存储上传文档不正确

Error: No 'files' provided to process

原因：官方文档展示了 uploadAndPoll 的错误用法预防：将文件流包装在 { files: [...] } 对象中

// ✅ 正确
await openai.beta.vectorStores.fileBatches.uploadAndPoll(vectorStoreId, {
  files: fileStreams
});

// ❌ 错误（官方文档所示）
await openai.beta.vectorStores.fileBatches.uploadAndPoll(vectorStoreId, fileStreams);

6. 推理模型拒绝温度参数

Error: Unsupported parameter: 'temperature' is not supported with this model

原因：当将助手更新到 o3-mini/o1-preview/o1-mini 时，旧的温度设置会保留预防：显式将温度设置为 null

await openai.beta.assistants.update(assistantId, {
  model: 'o3-mini',
  reasoning_effort: 'medium',
  temperature: null,  // ✅ 必须显式清除
  top_p: null
});

7. uploadAndPoll 返回向量存储 ID 而非批次 ID

Error: Invalid 'batch_id': 'vs_...'. Expected an ID that begins with 'vsfb_'.

原因：uploadAndPoll 返回向量存储对象而非批次对象预防：使用替代方法获取批次 ID

// 选项 1：在单独上传后使用 createAndPoll
const batch = await openai.vectorStores.fileBatches.createAndPoll(
  vectorStoreId,
  { file_ids: uploadedFileIds }
);

// 选项 2：列出批次以找到正确的 ID
const batches = await openai.vectorStores.fileBatches.list(vectorStoreId);
const batchId = batches.data[0].id; // 以 'vsfb_' 开头

8. 向量存储文件删除影响所有存储 警告：从一个向量存储中删除文件会将其从所有向量存储中移除

// ❌ 这会从 VS_A、VS_B 和 VS_C 中删除文件
await openai.vectorStores.files.delete('VS_A', 'file-xxx');

原因：SDK 或 API 错误 - 删除操作具有全局影响预防：如果需要选择性删除，请避免在多个向量存储之间共享文件来源：GitHub Issue #1710

9. 大文件上传中的内存泄漏（社区提供） 来源：GitHub Issue #1052 | 状态：开放影响：在长时间运行的服务器中，每上传 22MB 文件约泄漏 44MB 内存原因：当使用 vectorStores.fileBatches.uploadAndPoll 从流（S3 等）上传大文件时，上传完成后内存可能不会被释放 已验证：维护者已确认，在 v4.58.1 中已减少但未消除 变通方案：在长期运行的服务器中监控内存使用情况；定期重启或使用单独的 worker 进程

10. 线程已有活动运行 - 竞态条件（社区提供） 对问题 #1 的增强：当取消活动运行时，如果运行在取消前完成，可能会发生竞态条件

async function createRunSafely(threadId: string, assistantId: string) {
  // 首先检查活动运行
  const runs = await openai.beta.threads.runs.list(threadId, { limit: 1 });
  const activeRun = runs.data.find(r =>
    ['queued', 'in_progress', 'requires_action'].includes(r.status)
  );

  if (activeRun) {
    try {
      await openai.beta.threads.runs.cancel(threadId, activeRun.id);

      // 等待取消完成
      let run = await openai.beta.threads.runs.retrieve(threadId, activeRun.id);
      while (run.status === 'cancelling') {
        await new Promise(r => setTimeout(r, 500));
        run = await openai.beta.threads.runs.retrieve(threadId, activeRun.id);
      }
    } catch (error) {
      // 忽略“已完成”错误 - 运行自然结束
      if (!error.message?.includes('completed')) throw error;
    }
  }

  return openai.beta.threads.runs.create(threadId, { assistant_id: assistantId });
}

完整目录请参阅 references/top-errors.md。

与其他技能的关系

openai-api（聊天补全）：无状态，手动管理历史记录，直接响应。用于简单生成。

openai-responses（Responses API）：✅ 推荐用于新项目。更好的推理能力，现代化的 MCP 集成，积极开发中。

openai-assistants：⚠️ 将于 2026 年上半年弃用。仅用于遗留应用程序。迁移：references/migration-to-responses.md

v1 弃用：2024 年 12 月 18 日

关键变更：retrieval → file_search，向量存储（10k 文件 vs 20），256k 指令（vs 32k），消息级文件附件

请参阅 references/migration-from-v1.md

模板：templates/basic-assistant.ts, code-interpreter-assistant.ts, file-search-assistant.ts, function-calling-assistant.ts, streaming-assistant.ts

参考：references/top-errors.md, thread-lifecycle.md, vector-stores.md, migration-to-responses.md, migration-from-v1.md

相关技能：openai-responses（推荐）, openai-api

最后更新：2026-01-21 包：openai@6.16.0 状态：生产就绪（⚠️ 已弃用 - 将于 2026 年 8 月 26 日停止服务）变更：新增 6 个已知问题（向量存储上传错误、o3-mini 温度、内存泄漏），增强了流式错误处理

2026 年 1 月 20 日

🇺🇸English

OpenAI Assistants API v2

Status : Production Ready (⚠️ Deprecated - Sunset August 26, 2026) Package : openai@6.16.0 Last Updated : 2026-01-21 v1 Deprecated : December 18, 2024 v2 Sunset : August 26, 2026 (migrate to Responses API)

⚠️ Deprecation Notice

OpenAI is deprecating Assistants API in favor ofResponses API.

Timeline : v1 deprecated Dec 18, 2024 | v2 sunset August 26, 2026

Use this skill if : Maintaining legacy apps or migrating existing code (12-18 month window) Don't use if : Starting new projects (use openai-responses skill instead)

Migration : See references/migration-to-responses.md

Quick Start

npm install openai@6.16.0



import OpenAI from 'openai';

const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

// 1. Create assistant
const assistant = await openai.beta.assistants.create({
  name: "Math Tutor",
  instructions: "You are a math tutor. Use code interpreter for calculations.",
  tools: [{ type: "code_interpreter" }],
  model: "gpt-5",
});

// 2. Create thread
const thread = await openai.beta.threads.create();

// 3. Add message
await openai.beta.threads.messages.create(thread.id, {
  role: "user",
  content: "Solve: 3x + 11 = 14",
});

// 4. Run assistant
const run = await openai.beta.threads.runs.create(thread.id, {
  assistant_id: assistant.id,
});

// 5. Poll for completion
let status = await openai.beta.threads.runs.retrieve(thread.id, run.id);
while (status.status !== 'completed') {
  await new Promise(r => setTimeout(r, 1000));
  status = await openai.beta.threads.runs.retrieve(thread.id, run.id);
}

// 6. Get response
const messages = await openai.beta.threads.messages.list(thread.id);
console.log(messages.data[0].content[0].text.value);

Core Concepts

Four Main Objects:

Assistants : Configured AI with instructions (max 256k chars in v2, was 32k in v1), model, tools, metadata
Threads : Conversation containers with persistent message history (max 100k messages)
Messages : User/assistant messages with optional file attachments
Runs : Async execution with states (queued, in_progress, requires_action, completed, failed, expired)

Key API Patterns

Assistants

const assistant = await openai.beta.assistants.create({
  model: "gpt-5",
  instructions: "System prompt (max 256k chars in v2)",
  tools: [{ type: "code_interpreter" }, { type: "file_search" }],
  tool_resources: { file_search: { vector_store_ids: ["vs_123"] } },
});

Key Limits : 256k instruction chars (v2), 128 tools max, 16 metadata pairs

Threads & Messages

// Create thread with messages
const thread = await openai.beta.threads.create({
  messages: [{ role: "user", content: "Hello" }],
});

// Add message with attachments
await openai.beta.threads.messages.create(thread.id, {
  role: "user",
  content: "Analyze this",
  attachments: [{ file_id: "file_123", tools: [{ type: "code_interpreter" }] }],
});

// List messages
const msgs = await openai.beta.threads.messages.list(thread.id);

Key Limits : 100k messages per thread

Runs

// Create run with optional overrides
const run = await openai.beta.threads.runs.create(thread.id, {
  assistant_id: "asst_123",
  additional_messages: [{ role: "user", content: "Question" }],
  max_prompt_tokens: 1000,
  max_completion_tokens: 500,
});

// Poll until complete
let status = await openai.beta.threads.runs.retrieve(thread.id, run.id);
while (['queued', 'in_progress'].includes(status.status)) {
  await new Promise(r => setTimeout(r, 1000));
  status = await openai.beta.threads.runs.retrieve(thread.id, run.id);
}

Run States : queued → in_progress → requires_action (function calling) / completed / failed / cancelled / expired (10 min max)

Streaming

const stream = await openai.beta.threads.runs.stream(thread.id, { assistant_id });

for await (const event of stream) {
  if (event.event === 'thread.message.delta') {
    process.stdout.write(event.data.delta.content?.[0]?.text?.value || '');
  }
}

Key Events : thread.run.created, thread.message.delta (streaming content), thread.run.step.delta (tool progress), thread.run.completed, thread.run.requires_action (function calling)

Tools

Code Interpreter

Runs Python code in sandbox. Generates charts, processes files (CSV, JSON, PDF, images). Max 512MB per file.

// Attach file to message
attachments: [{ file_id: "file_123", tools: [{ type: "code_interpreter" }] }]

// Access generated files
for (const content of message.content) {
  if (content.type === 'image_file') {
    const fileContent = await openai.files.content(content.image_file.file_id);
  }
}

File Search (RAG)

Semantic search with vector stores. 10,000 files max (v2, was 20 in v1). Pricing : $0.10/GB/day (1GB free).

// Create vector store
const vs = await openai.beta.vectorStores.create({ name: "Docs" });
await openai.beta.vectorStores.files.create(vs.id, { file_id: "file_123" });

// Wait for indexing
let store = await openai.beta.vectorStores.retrieve(vs.id);
while (store.status === 'in_progress') {
  await new Promise(r => setTimeout(r, 2000));
  store = await openai.beta.vectorStores.retrieve(vs.id);
}

// Use in assistant
tool_resources: { file_search: { vector_store_ids: [vs.id] } }

⚠️ Wait forstatus: 'completed' before using

Function Calling

Submit tool outputs when run.status === 'requires_action':

if (run.status === 'requires_action') {
  const toolCalls = run.required_action.submit_tool_outputs.tool_calls;
  const outputs = toolCalls.map(tc => ({
    tool_call_id: tc.id,
    output: JSON.stringify(yourFunction(JSON.parse(tc.function.arguments))),
  }));

  run = await openai.beta.threads.runs.submitToolOutputs(thread.id, run.id, {
    tool_outputs: outputs,
  });
}

File Formats

Code Interpreter : .c, .cpp, .csv, .docx, .html, .java, .json, .md, .pdf, .php, .pptx, .py, .rb, .tex, .txt, .css, .jpeg, .jpg, .js, .gif, .png, .tar, .ts, .xlsx, .xml, .zip (512MB max)

File Search : .c, .cpp, .docx, .html, .java, .json, .md, .pdf, .php, .pptx, .py, .rb, .tex, .txt, .css, .js, .ts, .go (512MB max)

Known Issues

1. Thread Already Has Active Run

Error: 400 Can't add messages to thread_xxx while a run run_xxx is active.

Fix : Cancel active run first: await openai.beta.threads.runs.cancel(threadId, runId)

2. Run Polling Timeout / Incomplete Status

Error: OpenAIError: Final run has not been received

Why It Happens : Long-running tasks may exceed polling windows or finish with incomplete status Prevention : Handle incomplete runs gracefully

try {
  const stream = await openai.beta.threads.runs.stream(thread.id, { assistant_id });
  for await (const event of stream) {
    if (event.event === 'thread.message.delta') {
      process.stdout.write(event.data.delta.content?.[0]?.text?.value || '');
    }
  }
} catch (error) {
  if (error.message?.includes('Final run has not been received')) {
    // Run ended with 'incomplete' status - thread can continue
    const run = await openai.beta.threads.runs.retrieve(thread.id, runId);
    if (run.status === 'incomplete') {
      // Handle: prompt user to continue, reduce max_completion_tokens, etc.
    }
  }
}

Source : GitHub Issues #945, #1306, #1439

3. Vector Store Not Ready Using vector store before indexing completes. Fix : Poll vectorStores.retrieve() until status === 'completed' (see File Search section)

4. File Upload Format Issues Unsupported file formats cause silent failures. Fix : Validate file extensions before upload (see File Formats section)

5. Vector Store Upload Documentation Incorrect

Error: No 'files' provided to process

Why It Happens : Official documentation shows incorrect usage of uploadAndPoll Prevention : Wrap file streams in { files: [...] } object

// ✅ Correct
await openai.beta.vectorStores.fileBatches.uploadAndPoll(vectorStoreId, {
  files: fileStreams
});

// ❌ Wrong (shown in official docs)
await openai.beta.vectorStores.fileBatches.uploadAndPoll(vectorStoreId, fileStreams);

Source : GitHub Issue #1337

6. Reasoning Models Reject Temperature Parameter

Error: Unsupported parameter: 'temperature' is not supported with this model

Why It Happens : When updating assistant to o3-mini/o1-preview/o1-mini, old temperature settings persist Prevention : Explicitly set temperature to null

await openai.beta.assistants.update(assistantId, {
  model: 'o3-mini',
  reasoning_effort: 'medium',
  temperature: null,  // ✅ Must explicitly clear
  top_p: null
});

Source : GitHub Issue #1318

7. uploadAndPoll Returns Vector Store ID Instead of Batch ID

Error: Invalid 'batch_id': 'vs_...'. Expected an ID that begins with 'vsfb_'.

Why It Happens : uploadAndPoll returns vector store object instead of batch object Prevention : Use alternative methods to get batch ID

// Option 1: Use createAndPoll after separate upload
const batch = await openai.vectorStores.fileBatches.createAndPoll(
  vectorStoreId,
  { file_ids: uploadedFileIds }
);

// Option 2: List batches to find correct ID
const batches = await openai.vectorStores.fileBatches.list(vectorStoreId);
const batchId = batches.data[0].id; // starts with 'vsfb_'

Source : GitHub Issue #1700

8. Vector Store File Delete Affects All Stores Warning : Deleting a file from one vector store removes it from ALL vector stores

// ❌ This deletes file from VS_A, VS_B, AND VS_C
await openai.vectorStores.files.delete('VS_A', 'file-xxx');

Why It Happens : SDK or API bug - delete operation has global effect Prevention : Avoid sharing files across multiple vector stores if selective deletion is needed Source : GitHub Issue #1710

9. Memory Leak in Large File Uploads (Community-sourced) Source : GitHub Issue #1052 | Status : OPEN Impact : ~44MB leaked per 22MB file upload in long-running servers Why It Happens : When uploading large files from streams (S3, etc.) using vectorStores.fileBatches.uploadAndPoll, memory may not be released after upload completes Verified : Maintainer acknowledged, reduced in v4.58.1 but not eliminated Workaround : Monitor memory usage in long-lived servers; restart periodically or use separate worker processes

10. Thread Already Has Active Run - Race Condition (Community-sourced) Enhancement to Issue #1 : When canceling an active run, race conditions may occur if the run completes before cancellation

async function createRunSafely(threadId: string, assistantId: string) {
  // Check for active runs first
  const runs = await openai.beta.threads.runs.list(threadId, { limit: 1 });
  const activeRun = runs.data.find(r =>
    ['queued', 'in_progress', 'requires_action'].includes(r.status)
  );

  if (activeRun) {
    try {
      await openai.beta.threads.runs.cancel(threadId, activeRun.id);

      // Wait for cancellation to complete
      let run = await openai.beta.threads.runs.retrieve(threadId, activeRun.id);
      while (run.status === 'cancelling') {
        await new Promise(r => setTimeout(r, 500));
        run = await openai.beta.threads.runs.retrieve(threadId, activeRun.id);
      }
    } catch (error) {
      // Ignore "already completed" errors - run finished naturally
      if (!error.message?.includes('completed')) throw error;
    }
  }

  return openai.beta.threads.runs.create(threadId, { assistant_id: assistantId });
}

Source : OpenAI Community Forum

See references/top-errors.md for complete catalog.

Relationship to Other Skills

openai-api (Chat Completions): Stateless, manual history, direct responses. Use for simple generation.

openai-responses (Responses API): ✅ Recommended for new projects. Better reasoning, modern MCP integration, active development.

openai-assistants : ⚠️ Deprecated H1 2026. Use for legacy apps only. Migration: references/migration-to-responses.md

v1 to v2 Migration

v1 deprecated : Dec 18, 2024

Key Changes : retrieval → file_search, vector stores (10k files vs 20), 256k instructions (vs 32k), message-level file attachments

See references/migration-from-v1.md

Templates : templates/basic-assistant.ts, code-interpreter-assistant.ts, file-search-assistant.ts, function-calling-assistant.ts, streaming-assistant.ts

References : references/top-errors.md, thread-lifecycle.md, vector-stores.md, migration-to-responses.md, migration-from-v1.md

Related Skills : openai-responses (recommended), openai-api

Last Updated : 2026-01-21 Package : openai@6.16.0 Status : Production Ready (⚠️ Deprecated - Sunset August 26, 2026) Changes : Added 6 new known issues (vector store upload bugs, o3-mini temperature, memory leak), enhanced streaming error handling

Weekly Installs

313

Repository

jezweb/claude-skills

GitHub Stars

643

First Seen

Jan 20, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

claude-code260

gemini-cli207

opencode205

cursor198

antigravity191

codex177

AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具

42,300 周安装

OpenAI Assistants API v2 使用指南与迁移方案 - 2026年弃用前必看

🇨🇳中文介绍

OpenAI Assistants API v2

⚠️ 弃用通知

快速开始

相关 Skills

核心概念

关键 API 模式

助手

线程与消息

运行

流式传输

工具

代码解释器

文件搜索（RAG）

函数调用

文件格式

已知问题

与其他技能的关系

v1 到 v2 迁移

🇺🇸English

OpenAI Assistants API v2

⚠️ Deprecation Notice

Quick Start

Core Concepts

Key API Patterns

Assistants

Threads & Messages

Runs

Streaming

Tools

Code Interpreter

File Search (RAG)

Function Calling

File Formats

Known Issues

Relationship to Other Skills

v1 to v2 Migration

最新 Skills