Guard protocol generation against context truncation

scripts/run_mvp_meeting.py

@@ -19,6 +19,7 @@ from src.meeting_lab.orchestration.mvp import (  # noqa: E402
     DEFAULT_DIARIZATION_MODEL,
     DEFAULT_MODEL,
     DEFAULT_OUTPUT_ROOT,
+    DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
     MvpMeetingConfig,
     create_unique_run_dir,
     run_mvp_meeting,
@@ -53,6 +54,12 @@ def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
     )
     parser.add_argument("--model", default=DEFAULT_MODEL)
     parser.add_argument("--ollama-endpoint", default=DEFAULT_ENDPOINT)
+    parser.add_argument(
+        "--protocol-safe-input-token-budget",
+        type=int,
+        default=DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
+        help="Conservative estimated prompt-token limit before any Ollama request.",
+    )
     parser.add_argument(
         "--diarization",
         choices=("auto", "gpu", "cpu", "off"),
@@ -91,6 +98,7 @@ def config_from_args(args: argparse.Namespace) -> MvpMeetingConfig:
         threads=args.threads,
         model=args.model,
         ollama_endpoint=args.ollama_endpoint,
+        protocol_safe_input_token_budget=args.protocol_safe_input_token_budget,
         diarization=args.diarization,
         diarization_runtime=args.diarization_runtime,
         diarization_container_image=args.diarization_container_image,