claude-use-gemini-acp

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Claude → Gemini via ACP

通过ACP从Claude调用Gemini

Spawn a Gemini CLI subprocess in ACP mode, send a prompt, stream the response to stdout, and terminate cleanly. No persistent session — one prompt, one response.

以ACP模式启动Gemini CLI子进程，发送提示，将响应流式传输到标准输出，并干净地终止进程。无持久会话——一个提示对应一个响应。

When to use

使用场景

The task requires more context than fits in Claude's window
You want real-time Google Search grounding
You want a second opinion from a different model
The user says "ask Gemini", "use Gemini for this", etc.

任务所需上下文超出Claude的窗口容量
你需要实时基于谷歌搜索的支持
你希望从不同模型获取第二意见
用户要求“询问Gemini”“用Gemini处理这个”等

Setup (first use only)

首次使用设置

bash

cd ~/.claude/skills/claude-use-gemini-acp/scripts
pnpm install

This installs

@agentclientprotocol/sdk

into the local

node_modules/

. Subsequent runs skip this step — pnpm caches the result.

bash

cd ~/.claude/skills/claude-use-gemini-acp/scripts
pnpm install

这会将

@agentclientprotocol/sdk

安装到本地

node_modules/

目录。后续运行可跳过此步骤——pnpm会缓存结果。

Usage

使用方法

bash

GEMINI_MODEL=gemini-2.5-pro \
TARGET_CWD=/path/to/project \
node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs \
  "Summarize the architecture in ARCHITECTURE.md and list the top 3 risks"

The response streams to stdout as Gemini generates it. Capture it for use in your response:

bash

response=$(node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs "your prompt")

bash

GEMINI_MODEL=gemini-2.5-pro \
TARGET_CWD=/path/to/project \
node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs \
  "总结ARCHITECTURE.md中的架构并列出前3个风险"

Gemini生成响应时会将其流式传输到标准输出。你可以捕获响应用于后续处理：

bash

response=$(node ~/.claude/skills/claude-use-gemini-acp/scripts/gemini-delegate.mjs "你的提示内容")

Environment variables

环境变量

Variable	Default	Description
`GEMINI_MODEL`	`gemini-2.5-pro`	Model to use
`GEMINI_CLI_VERSION`	`nightly`	gemini-cli package version ( `nightly` or a specific semver)
`TARGET_CWD`	current working dir	Working directory passed to the Gemini session

变量名	默认值	描述
`GEMINI_MODEL`	`gemini-2.5-pro`	使用的模型
`GEMINI_CLI_VERSION`	`nightly`	gemini-cli包版本（ `nightly` 或特定语义化版本）
`TARGET_CWD`	当前工作目录	传递给Gemini会话的工作目录

How it works

工作原理

Spawns

pnpm dlx @google/gemini-cli@<version> --acp --yolo --model <model>

Connects via

@agentclientprotocol/sdk

ClientSideConnection

ndJsonStream

Sends
```
initialize
```
→
```
newSession
```
→
```
prompt
```
over the ACP session
Streams
```
agent_message_chunk
```
deltas to stdout as they arrive
Terminates the subprocess once the prompt response completes

The

--yolo

flag (

-y

) auto-approves all tool calls inside Gemini's session.

启动

pnpm dlx @google/gemini-cli@<version> --acp --yolo --model <model>

子进程

通过

@agentclientprotocol/sdk

的

ClientSideConnection

ndJsonStream

建立连接

在ACP会话上依次发送
```
initialize
```
→
```
newSession
```
→
```
prompt
```
指令
当
```
agent_message_chunk
```
增量到达时，将其流式传输到标准输出
提示响应完成后终止子进程

--yolo

标志（

-y

）会自动批准Gemini会话内的所有工具调用。

Prompt construction tips

提示构建技巧

Include all relevant context in the prompt string — this is a fresh session with no prior history
Reference files by absolute path if you want Gemini to read them (it can use its filesystem tools)
Keep prompts focused: one clear task per invocation
For multi-step work, do multiple sequential invocations rather than one sprawling prompt

在提示字符串中包含所有相关上下文——这是一个无历史记录的全新会话
如果希望Gemini读取文件，请使用绝对路径引用（它可以使用文件系统工具）
提示要聚焦：每次调用对应一个明确任务
对于多步骤工作，多次连续调用而非使用一个冗长的提示

Error handling

错误处理

If the script exits non-zero, check stderr for:

```
pnpm dlx
```
download failures (network, auth)
Gemini auth errors (
```
gemini auth login
```
may be needed)
ACP initialization failures (version mismatch)

The script does not retry — if something fails, surface the error to the user and suggest re-running after fixing the root cause.

如果脚本非零退出，请检查标准错误输出以排查：

```
pnpm dlx
```
下载失败（网络、权限问题）
Gemini认证错误（可能需要执行
```
gemini auth login
```
）
ACP初始化失败（版本不匹配）

脚本不会重试——如果出现故障，请向用户显示错误并建议修复根本原因后重新运行。