What this error means
ANTHROPIC_API_KEY is not set — web container missing environment variable in Docker Compose is a Docker failure pattern reported for developers trying to fix anthropic_api_key not set error in docker compose web container. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
PR #199 (May 2026) fixes a Docker Compose issue where the web service's environment block didn't forward ANTHROPIC_API_KEY from the host. The web container had no Anthropic key, causing all LLM calls to fail with 'ANTHROPIC_API_KEY is not set'. Surfaced during May 11 smoke test.
Common causes
- Developers running LLM-integrated applications in Docker Compose find that the web container fails with 'ANTHROPIC_API_KEY is not set' even though the host has the variable configured. The docker-compose.yml environment block doesn't forward ANTHROPIC_API_KEY from the host, causing all LLM calls (prep brief, clinical analysis, protocol generation) to fail silently.
- PR #199 (May 2026) fixes a Docker Compose issue where the web service's environment block didn't forward ANTHROPIC_API_KEY from the host. The web container had no Anthropic key, causing all LLM calls to fail with 'ANTHROPIC_API_KEY is not set'. Surfaced during May 11 smoke test.
Quick fixes
- Confirm the exact error signature matches
ANTHROPIC_API_KEY is not set — web container missing environment variable in Docker Compose. - Check the Docker account, local tool state, and provider configuration involved in the failing workflow.
- Compare the failing environment with a known working setup, then change one configuration value at a time.
Platform/tool-specific checks
- Verify the command, editor, extension, or API client that produced the error.
- Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
- Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- Keep the working fix documented for the team or deployment environment.
How to prevent it
- Keep provider/tool configuration documented.
- Record non-secret diagnostics such as tool version, provider name, model name, and command path.
- Add a lightweight check before CI or production workflows depend on the tool.