Guard protocol generation against context truncation

src/meeting_lab/orchestration/mvp.py

@@ -30,6 +30,7 @@ from src.meeting_lab.models.meeting_context import (
 from src.meeting_lab.progress import ProgressEvent, ProgressSink, ProgressStatus
 from src.meeting_lab.protocol.generate_direct_protocol import (
     DEFAULT_MODEL,
+    DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
     DirectProtocolResult,
     generate_direct_protocol,
     load_compact_transcript,
@@ -54,6 +55,7 @@ class MvpMeetingConfig:
     threads: str | int = "auto"
     model: str = DEFAULT_MODEL
     ollama_endpoint: str = DEFAULT_ENDPOINT
+    protocol_safe_input_token_budget: int = DEFAULT_SAFE_INPUT_TOKEN_BUDGET
     diarization: str = "off"
     diarization_runtime: str = "native"
     diarization_container_image: str | None = None
@@ -127,6 +129,8 @@ def _validate_inputs(
         and not config.diarization_container_image
     ):
         raise ValueError("A diarization container image is required.")
+    if config.protocol_safe_input_token_budget <= 0:
+        raise ValueError("Protocol safe input token budget must be positive.")
 
 
 def _emit(
@@ -154,6 +158,11 @@ def _persist_protocol(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
@@ -354,6 +363,7 @@ def run_mvp_meeting(
             preserved_context,
             model=config.model,
             endpoint=config.ollama_endpoint,
+            safe_input_token_budget=config.protocol_safe_input_token_budget,
         )
         stage_runtimes["protocol"] = round(time.perf_counter() - stage_started, 3)
         protocol_path = _persist_protocol(run_dir, result)