Update marimo notebook docs with lessons from workflow debugging

- Add rules: all imports in setup cell, cell output at top level,
  async cells need async def, return classes from model cells,
  use python-dotenv for .env loading
- Add marimo check validation step to AGENTS.md and notebook-patterns.md
- Add "always create new workflow" rule to AGENTS.md
- Add new doc sections: Cell Output Must Be at the Top Level,
  Async Cells, Cells That Define Classes, Fixing _unparsable_cell,
  Checking Notebooks Before Running
- Update all code examples to follow new import/output rules
- Update workflows/lib/llm.py for mirascope v2 API

workflows/lib/llm.py

@@ -1,9 +1,9 @@
-"""Simple LLM helper for workbooks using Mirascope."""
+"""Simple LLM helper for workbooks using Mirascope v2."""
 
 import os
 from typing import TypeVar
 
-from mirascope.core import Messages, openai
+from mirascope import llm
 from pydantic import BaseModel
 
 T = TypeVar("T", bound=BaseModel)
@@ -13,11 +13,14 @@ _api_key = os.getenv("LLM_API_KEY", "")
 _base_url = os.getenv("LLM_API_URL", "https://litellm-notrack.app.monadical.io")
 _model = os.getenv("LLM_MODEL", "GLM-4.5-Air-FP8-dev")
 
-if _api_key:
-    os.environ["OPENAI_API_KEY"] = _api_key
-if _base_url:
-    base = _base_url.rstrip("/")
-    os.environ["OPENAI_BASE_URL"] = base if base.endswith("/v1") else f"{base}/v1"
+# Register our LiteLLM endpoint as an OpenAI-compatible provider
+_base = (_base_url or "").rstrip("/")
+llm.register_provider(
+    "openai",
+    scope="litellm/",
+    base_url=_base if _base.endswith("/v1") else f"{_base}/v1",
+    api_key=_api_key,
+)
 
 
 async def llm_call(
@@ -39,13 +42,9 @@ async def llm_call(
     """
     use_model = model or _model
 
-    @openai.call(model=use_model, response_model=response_model)
-    async def _call(sys: str, usr: str) -> openai.OpenAIDynamicConfig:
-        return {
-            "messages": [
-                Messages.System(sys),
-                Messages.User(usr),
-            ]
-        }
+    @llm.call(f"litellm/{use_model}", format=response_model)
+    async def _call() -> str:
+        return f"{system_prompt}\n\n{prompt}"
 
-    return await _call(system_prompt, prompt)
+    response = await _call()
+    return response.parse()