Restore explicit integration workflow command

This commit is contained in:
hwhung
2026-05-06 21:28:56 +08:00
parent 369628345f
commit 41be842d9f
2 changed files with 10 additions and 21 deletions
+2 -2
View File
@@ -65,8 +65,8 @@ These can be overridden with CLI flags or environment variables:
- `--port` or `PORT` - `--port` or `PORT`
- `--proxy-api-key` or `PROXY_API_KEY` - `--proxy-api-key` or `PROXY_API_KEY`
For mass deployments, put the generated token directly in the Replit workflow run command with For mass deployments, put the generated token and Replit AI Integration variables directly in the
`--proxy-api-key`. The app will use that token as the required `Authorization: Bearer ...` value. Replit workflow run command with `--proxy-api-key`, `--openai-*`, and `--anthropic-*` flags.
## Verify ## Verify
+8 -19
View File
@@ -4,9 +4,6 @@ Goal: get the app running once, with Replit AI Integrations wired, on port 3000.
Bearer token for this deployment: DEPLOYMENT_GENERATED_PROXY_TOKEN 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: Do not:
- add it to a parent workspace - add it to a parent workspace
- move it into artifacts/ - move it into artifacts/
@@ -15,11 +12,10 @@ Do not:
- create config.json or /tmp config files - create config.json or /tmp config files
- inspect/free unrelated ports - inspect/free unrelated ports
- use nohup/setsid/background shell tricks - use nohup/setsid/background shell tricks
- search for or install integration skills/plugins/packages - invent, rotate, print, store, or replace the bearer token
- create provider API secrets manually - create provider API secrets manually
- use public OpenAI or Anthropic endpoints - use public OpenAI or Anthropic endpoints
- run a foreground server command directly in the shell - run a foreground server command directly in the shell
- set secrets or environment variables for the proxy token
- run verification commands - run verification commands
- run chat-completion smoke tests unless asked - run chat-completion smoke tests unless asked
@@ -27,27 +23,20 @@ Steps:
1. Clone into ./random-proxy-simple. 1. Clone into ./random-proxy-simple.
2. Use Replit's built-in AI Integrations feature only. Do not look for skills, plugins, 2. Provision/use Replit AI Integrations for:
packages, npm modules, or marketplace integrations.
Enable exactly these Replit AI Integration providers:
- OpenAI - OpenAI
- Anthropic - Anthropic
After provisioning, rely on Replit to inject these variables automatically: 3. From ./random-proxy-simple, run:
- AI_INTEGRATIONS_OPENAI_BASE_URL pnpm install --ignore-workspace
- 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 4. Create the smallest persistent workflow named "Random Proxy Simple" with this exact run command:
run command:
cd random-proxy-simple && pnpm dev -- --proxy-api-key DEPLOYMENT_GENERATED_PROXY_TOKEN cd random-proxy-simple && pnpm dev -- --host 0.0.0.0 --port 3000 --proxy-api-key DEPLOYMENT_GENERATED_PROXY_TOKEN --openai-base-url "$AI_INTEGRATIONS_OPENAI_BASE_URL" --openai-api-key "$AI_INTEGRATIONS_OPENAI_API_KEY" --anthropic-base-url "$AI_INTEGRATIONS_ANTHROPIC_BASE_URL" --anthropic-api-key "$AI_INTEGRATIONS_ANTHROPIC_API_KEY"
4. Start/restart that workflow once. 5. Start/restart that workflow once.
5. Do not run health, dashboard, model-list, or chat-completion verification commands. 6. Do not run health, dashboard, model-list, or chat-completion verification commands.
Report only: Report only:
- local URL - local URL