feat: configure 32k context for protocol generation

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_NUM_CTX,
     DEFAULT_SAFE_INPUT_TOKEN_BUDGET,
     DirectProtocolResult,
     generate_direct_protocol,
@@ -55,6 +56,7 @@ class MvpMeetingConfig:
     threads: str | int = "auto"
     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
     diarization: str = "off"
     diarization_runtime: str = "native"
@@ -131,6 +133,8 @@ def _validate_inputs(
         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.")
+    if config.protocol_num_ctx <= 0:
+        raise ValueError("Protocol Ollama context size must be positive.")
 
 
 def _emit(
@@ -363,6 +367,7 @@ def run_mvp_meeting(
             preserved_context,
             model=config.model,
             endpoint=config.ollama_endpoint,
+            num_ctx=config.protocol_num_ctx,
             safe_input_token_budget=config.protocol_safe_input_token_budget,
         )
         stage_runtimes["protocol"] = round(time.perf_counter() - stage_started, 3)

src/meeting_lab/protocol/generate_direct_protocol.py

@@ -33,7 +33,7 @@ DEFAULT_MODEL = "qwen3.6:35B-A3B"
 DEFAULT_NUM_CTX = 32768
 DEFAULT_NUM_PREDICT = 8192
 DEFAULT_TIMEOUT = 1800
-DEFAULT_SAFE_INPUT_TOKEN_BUDGET = 16_200
+DEFAULT_SAFE_INPUT_TOKEN_BUDGET = 29_000
 ESTIMATED_UTF8_BYTES_PER_TOKEN = 4.4