Kann ich AdaL vibecoden?

Build me a multi-model coding agent CLI to replace AdaL, in an empty folder.
Stack: Python 3.12, one file per module, no framework.

- Providers: Anthropic, OpenAI and Google, behind a single `chat(model, messages, tools)`
  function. Keys from .env via python-dotenv, never hardcoded. A `--model` flag
  switches families mid-session without restarting.
- Tools the agent can call: read_file, write_file, list_dir, run_shell, run_tests.
  run_shell prints the command and waits for y/n unless I pass --yolo.
- An orchestrator loop: a planner call splits my request into numbered steps, then
  each step runs as a fresh sub-agent with its own context window and only the tools
  it needs. Sub-agent results append to a shared markdown scratchpad on disk.
- Persist every session as JSONL under .agent/sessions/ so I can replay or resume.
  A `--resume <id>` flag reloads the scratchpad and continues.
- After any step that edits files, automatically run the test command from
  pyproject.toml and feed failures back to the same sub-agent for one retry.
- Print a running token and dollar total per provider at the end of every turn.
- Out of scope, deliberately: browser automation, a GUI, team accounts, and any
  hosted service. Those are the parts the subscription is actually selling.
- README: setup, the .env template, how to add a fourth provider, and one honest
  paragraph on where this loses to a tuned commercial harness on long tasks.

Antworte mir auf Deutsch. Oberfläche, Kommentare und README auf Deutsch, alle Bezeichner wie Tabellen, Spalten, Variablen, Routen und Dateinamen bleiben Englisch.