Files
random-proxy-simple/setup.md
T
2026-05-06 21:25:27 +08:00

56 lines
1.8 KiB
Markdown

Clone and run https://git.komnenos.me/springfw/random-proxy-simple in ./random-proxy-simple.
Goal: get the app running once, with Replit AI Integrations wired, on port 3000.
Bearer token for this deployment: DEPLOYMENT_GENERATED_PROXY_TOKEN
Use that exact token as the proxy bearer token in the run command. Do not invent, rotate, print,
or replace it. Do not ask for another token.
Do not:
- add it to a parent workspace
- move it into artifacts/
- modify source files
- edit package.json
- create config.json or /tmp config files
- inspect/free unrelated ports
- use nohup/setsid/background shell tricks
- search for or install integration skills/plugins/packages
- create provider API secrets manually
- use public OpenAI or Anthropic endpoints
- run a foreground server command directly in the shell
- set secrets or environment variables for the proxy token
- run verification commands
- run chat-completion smoke tests unless asked
Steps:
1. Clone into ./random-proxy-simple.
2. Use Replit's built-in AI Integrations feature only. Do not look for skills, plugins,
packages, npm modules, or marketplace integrations.
Enable exactly these Replit AI Integration providers:
- OpenAI
- Anthropic
After provisioning, rely on Replit to inject these variables automatically:
- AI_INTEGRATIONS_OPENAI_BASE_URL
- AI_INTEGRATIONS_OPENAI_API_KEY
- AI_INTEGRATIONS_ANTHROPIC_BASE_URL
- AI_INTEGRATIONS_ANTHROPIC_API_KEY
3. Create or update one persistent Replit workflow named "Random Proxy Simple" with this exact
run command:
cd random-proxy-simple && pnpm dev -- --proxy-api-key DEPLOYMENT_GENERATED_PROXY_TOKEN
4. Start/restart that workflow once.
5. Do not run health, dashboard, model-list, or chat-completion verification commands.
Report only:
- local URL
- whether OpenAI and Anthropic AI Integrations were wired
- that no verification commands were run