feat: initialize agents from a2a template
All checks were successful
build / build (push) Successful in 2s
All checks were successful
build / build (push) Successful in 2s
This commit is contained in:
@@ -84,6 +84,11 @@ when you deploy through the control plane).
|
||||
|
||||
Your tools:
|
||||
|
||||
- init_agent_template(name, description)
|
||||
— initialize agents/<name>/ from the
|
||||
installed a2a-pack `a2a init` template.
|
||||
Use this FIRST for a new project, then
|
||||
edit the generated files.
|
||||
- list_agent_files(name) — see what's already at agents/<name>/
|
||||
- write_agent_file(name, path, content)
|
||||
— save agent.py / a2a.yaml / requirements.txt
|
||||
@@ -116,8 +121,10 @@ Discipline:
|
||||
|
||||
- Pick a kebab-case slug for ``name`` (e.g. ``research-agent``,
|
||||
``csv-sanitizer``). Class name is PascalCase from the slug.
|
||||
- Write ALL THREE files (agent.py, a2a.yaml, requirements.txt) before
|
||||
testing — partial scaffolds break ``a2a card``.
|
||||
- For a new project, call init_agent_template first. Then read/edit the
|
||||
generated files instead of inventing boilerplate from memory.
|
||||
- Ensure all three core files (agent.py, a2a.yaml, requirements.txt)
|
||||
exist before testing — partial scaffolds break ``a2a card``.
|
||||
- Always run test_agent_in_sandbox before deploying. If exit_code != 0,
|
||||
read stderr, edit the offending file, retest. Do NOT deploy a broken
|
||||
scaffold.
|
||||
|
||||
Reference in New Issue
Block a user