Editor Extensions

Claude Code · VS Code

Pass the gateway and model to the extension through Claude user settings.

ConfigurableAnthropic MessagesDocs checked 2026-09-18

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

On this page

Before you begin

Install Anthropic’s official extension on a supported VS Code version. Its bundled CLI and the standalone terminal command are separate installs.

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 keys Browse models

Setup

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

01Install and open user configuration
Use the marketplace link on the official page. Back up ~/.claude/settings.json before editing.
Open official documentation
02Merge environment settings
The CLI and extension share these settings. Keep the key in user configuration, remove conflicting cloud-provider settings and reload the editor window.
~/.claude/settings.json
```
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://a2agent.me",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_A2AGENT_API_KEY",
    "ANTHROPIC_MODEL": "YOUR_MODEL_ID"
  }
}
```
03Check extension authentication
If sign-in is still shown, search VS Code settings for Claude Code login, check Disable Login Prompt, then start a new session.

Capabilities and limits

This does not establish access to cloud sessions, voice or other Claude-account features.
A remote window may read the remote home directory. Local terminal variables may not reach the extension process.

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/messages' \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_A2AGENT_API_KEY' \
  -H 'anthropic-version: 2023-06-01' \
  -d '{"model":"YOUR_MODEL_ID","max_tokens":128,"messages":[{"role":"user","content":"Reply with OK."}]}'

Troubleshooting

If the CLI works but the extension fails, check the settings.json and environment used by the window, then reload it.

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 three added env fields, restore authentication and Disable Login Prompt settings, then reload the window.

Sources and check date

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

Docs checked 2026-09-18