fix(cli): review pass on the docsgpt command

- The image pins DOCSGPT_HOME=/app: it ships no checkout, so the data home
  no longer depends on the working directory.
- api, worker, beat and migrate print the data home and env file they
  resolved, so an API and a worker started from different directories show
  it.
- The worker passes -Q only when asked; a bare worker consumes every
  configured queue, which honours EMBEDDINGS_QUEUE and DOCUMENT_PARSE_QUEUE.
- The worker runs through celery.start and returns its exit code; click
  usage errors print usage and exit 2 instead of a traceback.
- Windows: solo pool and no embedded scheduler (celery rejects -B there),
  with a pointer to the new `docsgpt beat` command, which runs the
  scheduler on its own.
- prefetch_models and verify_offline parse their arguments, so --help is
  help rather than a model name.
- A DOCSGPT_ENV_FILE that is not a file raises instead of booting with
  defaults.

docsgpt/scripts/prefetch_models.py

@@ -97,11 +97,21 @@ def prefetch(names: Sequence[str], cache_dir: Optional[str] = None) -> List[str]
     return fetched
 
 
+def _parse(argv: Optional[Sequence[str]], prog: str, description: str) -> list[str]:
+    import argparse
+
+    parser = argparse.ArgumentParser(prog=prog, description=description)
+    parser.add_argument(
+        "models", nargs="*", help=f"embedding model names or aliases (default: {', '.join(DEFAULT_MODELS)})"
+    )
+    return parser.parse_args(argv).models or list(DEFAULT_MODELS)
+
+
 def main(argv: Optional[Sequence[str]] = None) -> int:
     logging.basicConfig(level=logging.INFO, format="%(levelname)s %(message)s")
     import os
 
-    names = list(argv) if argv else list(DEFAULT_MODELS)
+    names = _parse(argv, "prefetch-models", "Download the embedding models and the tiktoken encodings into the local caches.")
     fetched = prefetch(names, os.environ.get("EMBEDDINGS_CACHE_DIR"))
     logger.info("Cached %d model(s): %s", len(fetched), ", ".join(fetched))
     encodings = prefetch_tiktoken()