A2Agent
Login
All integrations

CLI Tools

Crush

Register an OpenAI-compatible provider in crushrc.

ConfigurableOpenAI Chat CompletionsDocs checked

The vendor documents custom endpoints. Check model capabilities and verify the connection.

On this page

Before you begin

Install a current Crush release with crushrc support. Windows uses the same configuration syntax through Crush’s interpreter.

Have an A2Agent API key ready and copy an accessible model ID from the catalog. Replace every placeholder, back up existing settings and keep keys out of repositories.

Manage API keysBrowse models

Setup

File contents are usually shared; switching OS changes commands and paths. For WSL on Windows, select macOS / Linux.

  1. 01Install and back up configuration

    Choose the package or binary for your OS from the official repository, then run crush --version.

    Open official documentation

  2. 02Register the provider and model

    Put this in crushrc; do not execute it directly in a terminal. Adjust context and output budgets to your model.

    ~/.config/crush/crushrc
    provider add a2agent --type openai-compat --base-url "https://a2agent.me/v1" --api-key "$A2AGENT_API_KEY"
model add a2agent/YOUR_MODEL_ID --name "A2Agent" --context-window 32768 --default-max-tokens 4096

  3. 03Pass the key

    After launching, open the model picker with Ctrl+L and select A2Agent.

    Shell
    export A2AGENT_API_KEY='YOUR_A2AGENT_API_KEY'
crush

Capabilities and limits

  • Use openai-compat for a custom compatible provider. Legacy JSON configuration is deprecated; check official migration instructions when updating.
  • Project crushrc takes precedence over global configuration.

Verify the connection

Replace every placeholder and run locally. Expect JSON containing OK. Then start a new client conversation, test one read-only tool call separately, and confirm the requests in A2Agent usage records. This test incurs a small amount of model usage.

Shell
curl --fail-with-body --silent --show-error --max-time 60 'https://a2agent.me/v1/chat/completions' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_A2AGENT_API_KEY' \
  -d '{"model":"YOUR_MODEL_ID","max_tokens":128,"messages":[{"role":"user","content":"Reply with OK."}]}'

Troubleshooting

If the model does not load, check project overrides, the environment variable and the provider prefix in model add.

401 / 403: authentication or access denied

Use a key issued by A2Agent, without extra spaces, and check that it is active and unexpired. Confirm the group permits the model and protocol. A vendor subscription credential cannot replace an A2Agent key.

404 / model not found: endpoint or model mismatch

Check the root URL, /v1 prefix and full request path against this guide; avoid duplicated paths. Model IDs are case-sensitive and must be accessible to the current key.

429: quota or rate limit

Check your balance, key limits, concurrent usage and service status. Wait before retrying and reduce simultaneous agents; repeated retries do not remove a quota limit.

Chat works, but tools fail or streaming stops

Test a short text request, then a single read-file tool call. Check tool support, output budget, proxy timeouts and client version. Inspect the diff before resuming a long task to avoid repeating actions.

Restore previous settings

Remove the two added configuration lines, select the previous model, and close the terminal holding the key.

Sources and check date

Status is based on official configuration docs, not end-to-end client testing with A2Agent.

Docs checked 2026-09-18