fix: require current a2a init scaffold

agent_builder/builder.py

@@ -30,37 +30,19 @@ Given a user description, you write a complete agent project under the
 user's workspace at ``agents/<name>/`` and then deploy it through the
 control plane.
 
-What an a2a-pack agent looks like:
+The default starter is the current a2a-pack DeepAgents scaffold. It declares
+``LLMProvisioning.CALLER_PROVIDED``, reads caller LLM credentials from
+``ctx.llm``, builds a ``ChatOpenAI`` model from those credentials, and wires a
+small tool-calling DeepAgent with ``create_deep_agent`` plus
+``wrap_model_call`` middleware. Do not recreate this from memory: call
+``init_agent_template`` first and modify the generated files.
 
-```python
-from pydantic import BaseModel
-from a2a_pack import A2AAgent, NoAuth, RunContext, skill
-
-
-class <Name>Config(BaseModel):
-    pass
-
-
-class <Name>(A2AAgent[<Name>Config, NoAuth]):
-    name = "<slug>"
-    description = "..."
-    version = "0.1.0"
-    config_model = <Name>Config
-    auth_model = NoAuth
-
-    @skill(description="...", tags=["..."])
-    async def <skill>(self, ctx: RunContext[NoAuth], ...) -> dict:
-        await ctx.emit_progress("...")
-        return {"ok": True, "...": "..."}
-```
-
-You ALSO need an ``a2a.yaml`` like:
+The generated ``a2a.yaml`` looks like:
 
 ```yaml
 name: <slug>
 version: 0.1.0
 entrypoint: agent:<Name>
-description: <one line>
 expose:
   public: true
 ```