Tighten agent runbook
This commit is contained in:
@@ -1,77 +1,64 @@
|
|||||||
# Agent Instructions
|
# Agent Runbook
|
||||||
|
|
||||||
This repository is a standalone Express API server. It is not intended to be added to a parent workspace.
|
Run this repository as a standalone app. Do not add it to a parent workspace. Do not move it into `artifacts/`. Do not edit source files for setup.
|
||||||
|
|
||||||
## Run Exactly
|
## Setup
|
||||||
|
|
||||||
|
Run from this repository root:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
pnpm install --ignore-workspace
|
pnpm install --ignore-workspace
|
||||||
pnpm dev
|
pnpm dev
|
||||||
```
|
```
|
||||||
|
|
||||||
The server starts with built-in defaults even when `config.json` does not exist:
|
If plain `pnpm` is unavailable, use `corepack pnpm` for the same commands. Do not edit `package.json`.
|
||||||
|
|
||||||
|
The app runs without `config.json`:
|
||||||
|
|
||||||
- host: `0.0.0.0`
|
- host: `0.0.0.0`
|
||||||
- port: `8080`
|
- port: `8080`
|
||||||
- proxy bearer token: `dev-proxy-key`
|
- bearer token: `dev-proxy-key`
|
||||||
|
|
||||||
Do not create `config.json` unless internal provider endpoints are available.
|
## Optional Provider Config
|
||||||
|
|
||||||
## Fill Provider Config
|
Do not create `config.json` unless internal provider endpoints/tokens are available.
|
||||||
|
|
||||||
Only if internal provider endpoints are available:
|
If they are available, create `config.json` in one write with this shape:
|
||||||
|
|
||||||
```bash
|
|
||||||
cp config.example.json config.json
|
|
||||||
```
|
|
||||||
|
|
||||||
Then fill only these values:
|
|
||||||
|
|
||||||
```json
|
```json
|
||||||
{
|
{
|
||||||
|
"server": {
|
||||||
|
"host": "0.0.0.0",
|
||||||
|
"port": 8080
|
||||||
|
},
|
||||||
|
"proxy": {
|
||||||
|
"apiKey": "dev-proxy-key"
|
||||||
|
},
|
||||||
"providers": {
|
"providers": {
|
||||||
"openai": {
|
"openai": {
|
||||||
"apiKey": "internal-openai-token",
|
"apiKey": "",
|
||||||
"baseURL": "https://your-internal-openai-endpoint/v1"
|
"baseURL": ""
|
||||||
},
|
},
|
||||||
"anthropic": {
|
"anthropic": {
|
||||||
"apiKey": "internal-anthropic-token",
|
"apiKey": "",
|
||||||
"baseURL": "https://your-internal-anthropic-endpoint"
|
"baseURL": ""
|
||||||
}
|
}
|
||||||
|
},
|
||||||
|
"logging": {
|
||||||
|
"level": "info",
|
||||||
|
"pretty": true
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
```
|
```
|
||||||
|
|
||||||
Use internal endpoints supplied by the runtime/integration. Do not use public official provider endpoints.
|
Fill only `providers.openai.apiKey`, `providers.openai.baseURL`, `providers.anthropic.apiKey`, and `providers.anthropic.baseURL`. Use internal endpoints only. Never use public official provider endpoints.
|
||||||
|
|
||||||
If provider endpoints are not available, leave config absent. The dashboard, health check, and model list still work. Chat completion calls return `503` until the target provider has both `apiKey` and `baseURL`.
|
## Verify
|
||||||
|
|
||||||
## Routes
|
|
||||||
|
|
||||||
- `GET /` and `GET /dashboard` - static model dashboard
|
|
||||||
- `GET /api/healthz` - health check
|
|
||||||
- `GET /v1/models` - OpenAI-compatible model list
|
|
||||||
- `POST /v1/chat/completions` - OpenAI-compatible chat proxy
|
|
||||||
|
|
||||||
The `/v1/*` routes require:
|
|
||||||
|
|
||||||
```text
|
|
||||||
Authorization: Bearer <proxy.apiKey>
|
|
||||||
```
|
|
||||||
|
|
||||||
## Verification
|
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
curl -s http://localhost:8080/dashboard | head
|
|
||||||
curl -s http://localhost:8080/api/healthz
|
curl -s http://localhost:8080/api/healthz
|
||||||
|
curl -s http://localhost:8080/dashboard | head
|
||||||
curl -s -H "Authorization: Bearer dev-proxy-key" http://localhost:8080/v1/models
|
curl -s -H "Authorization: Bearer dev-proxy-key" http://localhost:8080/v1/models
|
||||||
```
|
```
|
||||||
|
|
||||||
Expected chat result without provider config: `503` with a message asking for `providers.<name>.apiKey` and `providers.<name>.baseURL`.
|
Expected without provider config: dashboard, health, and model list work; chat completions return `503`.
|
||||||
|
|
||||||
## Production
|
|
||||||
|
|
||||||
```bash
|
|
||||||
pnpm build
|
|
||||||
pnpm start
|
|
||||||
```
|
|
||||||
|
|||||||
Reference in New Issue
Block a user