1.1 KiB
1.1 KiB
Step 1 — Implementation Detail
Dockerfile: the start command became the A2A server; the image setsA2A_HOST=0.0.0.0andA2A_PORT=8080; only port 8080 is exposed.- The health check reads
A2A_PORTand allows 60 seconds to start, because/healthanswers only after the provider bundle and MCP catalogs load. README.md: server section, start command, container example (now passingGOOGLE_GENAI_USE_VERTEXAI,GOOGLE_CLOUD_PROJECT,GOOGLE_CLOUD_LOCATION,A2A_PUBLIC_URL) and test calls.
Verified: built with podman and ran the image with MCP_ENABLED=false; /health and the agent card returned 200 and process 1 was the server.
Consequences for callers:
/card,/validateand/sessions/{session_id}are no longer served. The card is at/.well-known/agent-card.json./generatenow runs a full pre-approved Execution with real models, about 45 minutes in the evaluation runs.- Without
A2A_PUBLIC_URLthe card advertiseshttp://0.0.0.0:8080/a2a. - Podman's default image format ignores
HEALTHCHECK.
Not verified: a full Execution with real models and MCP servers inside the container.