-
Check whether VSR is already installed with command -v vllm-sr.
-
If VSR is missing, run the supported installer in agent-safe mode:
curl -fsSL https://vllm-sr.ai/install.sh | bash -s -- --mode cli --runtime skip --no-launch
-
Locate the OpenClaw config in this order unless the user already gave you a path:
$OPENCLAW_CONFIG_PATH
./openclaw.json
~/.openclaw/openclaw.json
-
Import the OpenClaw model providers into canonical VSR config:
vllm-sr config import --from openclaw --source <openclaw.json> --target config.yaml
-
Do not pass --force unless the user explicitly approves overwriting existing backup files.
-
After a successful import, report:
- the imported logical model names
- the canonical target config path
- the rewritten OpenClaw config path
- the rewritten OpenClaw base URL
- the backup file paths, if any
-
Suggest the next validation commands:
vllm-sr validate config.yaml
vllm-sr config router --config config.yaml
-
If the user wants runtime verification after validation, suggest:
vllm-sr serve --config config.yaml
curl http://127.0.0.1:8899/v1/models