feat: add post-diarization speaker mapping workflow

This commit is contained in:
2026-08-25 15:30:16 +02:00
parent df89a38829
commit 8a0f38fce4
6 changed files with 233 additions and 2 deletions
+58
View File
@@ -71,6 +71,64 @@ class MvpRunResult:
protocol_path: Path | None
def regenerate_mvp_protocol(
run_dir: Path,
*,
meeting_context: ContextInput,
model: str = DEFAULT_MODEL,
ollama_endpoint: str = DEFAULT_ENDPOINT,
protocol_num_ctx: int = DEFAULT_NUM_CTX,
protocol_safe_input_token_budget: int = DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
progress_sink: ProgressSink | None = None,
) -> MvpRunResult:
"""Regenerate only protocol artifacts from an existing completed run."""
started = time.perf_counter()
run_dir = Path(run_dir)
context = _effective_context(meeting_context)
if context is None:
raise ValueError("Meeting Context is required for protocol regeneration.")
if protocol_num_ctx <= 0:
raise ValueError("Protocol Ollama context size must be positive.")
if protocol_safe_input_token_budget <= 0:
raise ValueError("Protocol safe input token budget must be positive.")
diarized_transcript = run_dir / "diarization" / "transcript_diarized.json"
plain_transcript = run_dir / "transcript" / "transcript.json"
transcript_path = (
diarized_transcript if diarized_transcript.is_file() else plain_transcript
)
if not transcript_path.is_file():
raise FileNotFoundError(
f"Existing run has no protocol transcript artifact: {run_dir}"
)
context_path = run_dir / "context" / "meeting_context.yaml"
write_meeting_context(context, context_path)
_emit(progress_sink, "protocol_generation", "started", started)
try:
result = generate_direct_protocol(
transcript_path,
context_path,
model=model,
endpoint=ollama_endpoint,
num_ctx=protocol_num_ctx,
safe_input_token_budget=protocol_safe_input_token_budget,
)
protocol_path = _persist_protocol(run_dir, result)
except Exception as exc:
_emit(
progress_sink,
"failed",
"failed",
started,
message=f"protocol_generation: {type(exc).__name__}: {exc}",
)
raise
_emit(progress_sink, "protocol_generation", "completed", started)
_emit(progress_sink, "completed", "completed", started)
return MvpRunResult(0, run_dir, protocol_path)
def create_unique_run_dir(
output_root: Path,
meeting_name: str,