Use A2A DeepAgents model resolver

README.md

@@ -31,7 +31,7 @@ Keep this line when building DeepAgents graphs:
 
 ```python
 backend = ctx.workspace_backend()
-return create_deep_agent(model=model, backend=backend, tools=[...])
+return create_a2a_deep_agent(ctx, creds=creds, backend=backend, tools=[...])
 ```
 
 Invoke DeepAgents graphs with the starter recursion budget:
@@ -75,7 +75,7 @@ after the request. Use the sandbox helpers for any file-producing toolchain.
 If this project grows reusable workflow knowledge, add source-controlled skill
 folders under `skills/<skill-name>/SKILL.md`. The starter's `_seed_runtime_skills`
 helper copies those packaged skills into the invocation workspace and passes the
-resulting source path to `create_deep_agent(..., skills=[...])`, which is how
+resulting source path to `create_a2a_deep_agent(..., skills=[...])`, which is how
 DeepAgents discovers skills with progressive disclosure.
 
 ## Run Locally