multi-llm-consult

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Multi-LLM Consult

多LLM咨询

Overview

概述

Use a bundled script to query external LLM providers with a sanitized prompt and return a concise comparison.

使用内置脚本，通过经过清理的提示词查询外部LLM提供商，并返回简洁的对比结果。

Setup

配置步骤

Configure API keys in the TUI: open the Command Palette (Ctrl+P) and run Configure LLM Providers.
Keys are stored in
```
settings.json
```
under
```
llm_providers
```
.

在TUI中配置API密钥：打开命令面板（Ctrl+P）并运行Configure LLM Providers。
密钥将存储在
```
settings.json
```
的
```
llm_providers
```
字段下。

Workflow

工作流程

Identify the purpose (
```
second-opinion
```
,
```
plan
```
,
```
review
```
,
```
delegate
```
).
Summarize the task and sanitize sensitive data before sending it out.
Run the consult script with the chosen provider.
Compare responses and reconcile with your own plan before acting.

确定用途（
```
second-opinion
```
、
```
plan
```
、
```
review
```
、
```
delegate
```
）。
总结任务内容，并在发送前清理敏感数据。
使用选定的提供商运行咨询脚本。
对比返回结果，并在采取行动前与自身计划进行协调。

Consult Script

咨询脚本

Always run

--help

first:

bash

python scripts/consult_llm.py --help

Example: second opinion

bash

python scripts/consult_llm.py \
  --provider gemini \
  --purpose second-opinion \
  --prompt "We plan to refactor module X. What risks or gaps do you see?"

Example: delegate a review

bash

python scripts/consult_llm.py \
  --provider qwen \
  --purpose review \
  --prompt-file /tmp/review_request.md \
  --context-file /tmp/patch.diff

Example: plan check with Codex (OpenAI)

bash

python scripts/consult_llm.py \
  --provider codex \
  --purpose plan \
  --prompt "Draft a 5-step plan for implementing feature Y."

请先运行

--help

查看帮助：

bash

python scripts/consult_llm.py --help

示例：获取第二意见

bash

python scripts/consult_llm.py \
  --provider gemini \
  --purpose second-opinion \
  --prompt "We plan to refactor module X. What risks or gaps do you see?"

示例：委托评审

bash

python scripts/consult_llm.py \
  --provider qwen \
  --purpose review \
  --prompt-file /tmp/review_request.md \
  --context-file /tmp/patch.diff

示例：使用Codex（OpenAI）检查计划

bash

python scripts/consult_llm.py \
  --provider codex \
  --purpose plan \
  --prompt "Draft a 5-step plan for implementing feature Y."

Output Handling

结果处理

Treat responses as advisory; verify against repo constraints and current state.
Summarize the external response in 3-6 bullets before acting.
If responses conflict, call out the differences explicitly and choose a path.

将返回结果视为参考建议；需结合仓库约束和当前状态进行验证。
采取行动前，将外部返回结果总结为3-6条要点。
若结果存在冲突，需明确指出差异并选择合适的方案。

References

参考资料

Provider defaults and configuration:
```
references/providers.md
```

提供商默认设置与配置：
```
references/providers.md
```