docs: document llmman as a local model server

[ericcurtin]

Description

Documents llmman, a local model runner that serves the Ollama API on port 17434. any-agent has no Ollama-specific code (Ollama goes through any-llm's ollama/ provider), so llmman already works via api_base; this PR mirrors the existing Ollama docs touchpoints only:

• docs/agents/models.md: list llmman next to Ollama and add a short AgentConfig example with the api_base override.
• AgentConfig.api_base docstring (src/any_agent/config.py): add the llmman URL next to the Ollama one (rendered into the API docs).
• Local Agent cookbook (.md and .ipynb, kept in parallel): a two-line note under "Ollama setup"; the notebook change is a single markdown cell.
• Model ids keep the ollama/ prefix; a native llmman provider is proposed separately in any-llm.

Testing: ruff check/ruff format --check (v0.15.4) on config.py, py_compile, codespell on the four changed files, notebook re-parsed as JSON; mktestdocs.check_md_file("docs/agents/models.md") executes the new snippet. Not run against a live llmman server.

PR Type

• Documentation

Relevant issues

None.

Checklist

• I understand the code I am submitting.
• I have added unit tests that prove my fix/feature works (docs-only; the existing tests/docs mktestdocs check covers the new snippet)
• I have run this code locally and verified it fixes the issue.
• New and existing tests pass locally (full tests/docs suite could not be run locally for pre-existing dependency reasons; the relevant mktestdocs check passes)
• Documentation was updated where necessary
• I have read and followed the contribution guidelines
• AI Usage:
  • No AI was used.
  • AI was used for drafting/refactoring.
  • This is fully AI-generated.

AI Usage Information

• AI Model used: Claude

• AI Developer Tool used: OpenCode

• Any other info you'd like to share: Drafted with AI, reviewed and submitted by the author.

• I am an AI Agent filling out this form (check box if true)

AI-assisted, reviewed before submitting.