test: add indexer unit tests + integration marker; make indexer importable without env

- pytest.ini: 'integration' marker, deselected by default; the integration
  suite requires a live Qdrant and will only run in the nightly CI job.
- src/indexer.py: move env validation from import time into _validate_config()
  called by main() — the module can now be imported without MAILDIR_PATH /
  QDRANT_URL / COLLECTION_NAME set, enabling unit tests.
- tests/test_indexer.py: 27 new unit tests, no network and no model:
  decode_mime_words (encoded-words utf-8/iso-8859-1, mixed), extract_text_from_html
  (tags, scripts), normalize_email_address, parse_email_message with real
  EmailMessage objects (plain bodies, attachments detected and excluded from
  body, HTML alternative, unknown charset fallback via raw bytes message,
  encoded attachment filename), get_recent_keys against a real tmp_path
  Maildir (fresh mtime selected, old mtime excluded, colon-suffix keys).
  mailbox.Maildir(create=True) does not create cur/new/tmp on Python 3.11 —
  the test helper pre-creates them.

src/indexer.py

@@ -22,26 +22,27 @@ from bs4 import BeautifulSoup
 # Load .env config
 load_dotenv()
 
-# Configuration
+# Configuration (validated lazily in main() so the module can be imported
+# and unit-tested without environment variables)
 MAILDIR_PATH = os.environ.get("MAILDIR_PATH", "")
 MAILDIR_FOLDERS = os.environ.get("MAILDIR_FOLDERS", "")
 QDRANT_URL = os.environ.get("QDRANT_URL", "")
 COLLECTION_NAME = os.environ.get("COLLECTION_NAME", "")
 
-if not MAILDIR_PATH:
-    raise ValueError("MAILDIR_PATH environment variable is required.")
-if not QDRANT_URL:
-    raise ValueError("QDRANT_URL environment variable is required.")
-if not COLLECTION_NAME:
-    raise ValueError("COLLECTION_NAME environment variable is required.")
-
-EMBEDDING_MODEL_NAME = os.environ.get("EMBEDDING_MODEL_NAME", "BAAI/bge-small-en-v1.5")
-BATCH_SIZE = int(os.environ.get("BATCH_SIZE", "100"))
-EMBEDDING_BATCH_SIZE = int(os.environ.get("EMBEDDING_BATCH_SIZE", "64"))
 METADATA_COLLECTION = "mcp_indexer_metadata"
 INCREMENTAL_DAYS = int(os.environ.get("INCREMENTAL_DAYS", "7"))
 FORCE_REINDEX = os.environ.get("FORCE_REINDEX", "").lower() in ("1", "true", "yes")
 
+
+def _validate_config():
+    """Raises if required environment variables are missing. Called from main()."""
+    if not MAILDIR_PATH:
+        raise ValueError("MAILDIR_PATH environment variable is required.")
+    if not QDRANT_URL:
+        raise ValueError("QDRANT_URL environment variable is required.")
+    if not COLLECTION_NAME:
+        raise ValueError("COLLECTION_NAME environment variable is required.")
+
 def decode_mime_words(s: str) -> str:
     """Decodes MIME encoded strings (e.g. subjects, filenames)."""
     if not s:
@@ -251,6 +252,8 @@ def main():
     Main ingestion function.
     Reads Maildir, extracts text, generates local embeddings, and pushes to Qdrant.
     """
+    _validate_config()
+
     print(f"Indexing emails from {MAILDIR_PATH} into {QDRANT_URL}...")
 
     if not os.path.exists(MAILDIR_PATH):