Guard protocol generation against context truncation

scripts/run_direct_protocol.py

@@ -20,6 +20,7 @@ if str(REPO_ROOT) not in sys.path:
 from src.meeting_lab.llm.ollama import DEFAULT_ENDPOINT  # noqa: E402
 from src.meeting_lab.protocol.generate_direct_protocol import (  # noqa: E402
     DEFAULT_MODEL,
+    DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
     DirectProtocolResult,
     generate_direct_protocol,
 )
@@ -35,6 +36,11 @@ def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
     parser.add_argument("--output-root", type=Path, default=DEFAULT_OUTPUT_ROOT)
     parser.add_argument("--model", default=DEFAULT_MODEL)
     parser.add_argument("--ollama-endpoint", default=DEFAULT_ENDPOINT)
+    parser.add_argument(
+        "--safe-input-token-budget",
+        type=int,
+        default=DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
+    )
     return parser.parse_args(argv)
 
 
@@ -64,6 +70,11 @@ def persist_result(run_dir: Path, result: DirectProtocolResult) -> Path:
     (protocol_dir / "exact_prompt.txt").write_text(result.exact_prompt, encoding="utf-8")
     write_json(protocol_dir / "raw_response.json", result.raw_response)
     write_json(protocol_dir / "runtime_metadata.json", result.runtime_metadata)
+    transcript_input = getattr(result, "transcript_input", None)
+    if transcript_input is not None:
+        (protocol_dir / "transcript_input.txt").write_text(
+            transcript_input, encoding="utf-8"
+        )
     protocol_path = run_dir / "protocol.md"
     protocol_path.write_text(result.protocol_text, encoding="utf-8")
     return protocol_path
@@ -116,6 +127,7 @@ def run(args: argparse.Namespace) -> tuple[int, Path, Path | None]:
             preserved_context,
             model=args.model,
             endpoint=args.ollama_endpoint,
+            safe_input_token_budget=args.safe_input_token_budget,
         )
         protocol_path = persist_result(run_dir, result)
         metadata["status"] = "completed"

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,