uv run massgen --automation --config massgen/configs/basic/multi/two_agents_gemini.yaml "What is 2+2?"

LOG_DIR: .massgen/massgen_logs/log_20251120_143022_123456
STATUS: .massgen/massgen_logs/log_20251120_143022_123456/status.json

🤖 Multi-Agent Mode
Agents: gemini-2.5-pro1, gemini-2.5-pro2
Question: What is 2+2?

============================================================
QUESTION: What is 2+2?
[Coordination in progress - monitor status.json for real-time updates]

WINNER: gemini-2.5-pro1
DURATION: 33.4s
ANSWER_PREVIEW: The answer is 4.

COMPLETED: 2 agents, 35.2s total

cat .massgen/massgen_logs/log_20251120_143022_123456/status.json

{
  "coordination": {
    "completion_percentage": 65,
    "phase": "enforcement"
  },
  "results": {
    "winner": null  // null = running, "agent_id" = done
  },
  "agents": {
    "agent_a": {
      "status": "streaming",
      "error": null
    }
  }
}

# Read final answer
cat [log_dir]/final/[winner]/answer.txt

import json, time, sys
from pathlib import Path

log_dir = Path(sys.argv[1])  # Pass LOG_DIR as argument
while True:
    if (log_dir / "status.json").exists():
        with open(log_dir / "status.json") as f:
            data = json.load(f)
        with open("token_monitor.log", "a") as log:
            log.write(f"=== {time.strftime('%H:%M:%S')} ===\n")
            log.write(f"Tokens: {data.get('total_tokens_used', 0)}\n")
            log.write(f"Cost: ${data.get('total_cost', 0):.4f}\n\n")
    time.sleep(5)

import time, sys
from pathlib import Path

log_dir = Path(sys.argv[1])
while True:
    if log_dir.exists():
        with open("error_monitor.log", "a") as log:
            log.write(f"=== {time.strftime('%H:%M:%S')} ===\n")
            errors = []
            for logfile in log_dir.glob("*.log"):
                with open(logfile) as f:
                    for line in f:
                        if any(x in line.lower() for x in ['error', 'warning', 'failed']):
                            errors.append(line.strip())
            log.write('\n'.join(errors[-5:]) if errors else "No errors\n")
            log.write("\n")
    time.sleep(5)

import json, time, sys
from pathlib import Path

log_dir = Path(sys.argv[1])
while True:
    if (log_dir / "status.json").exists():
        with open(log_dir / "status.json") as f:
            data = json.load(f)
        with open("progress_monitor.log", "a") as log:
            log.write(f"=== {time.strftime('%H:%M:%S')} ===\n")
            progress = data.get('completion_percentage', 0)
            active = sum(1 for a in data.get('agents', {}).values()
                        if a.get('status') == 'active')
            log.write(f"Progress: {progress}% Active agents: {active}\n\n")
    time.sleep(5)

import json, time, sys
from pathlib import Path

log_dir = Path(sys.argv[1])
while True:
    if (log_dir / "status.json").exists():
        with open(log_dir / "status.json") as f:
            data = json.load(f)
        coord = data.get('coordination', {})
        with open("coordination_monitor.log", "a") as log:
            log.write(f"=== {time.strftime('%H:%M:%S')} ===\n")
            log.write(f"Phase: {coord.get('phase', 'unknown')}\n")
            log.write(f"Round: {coord.get('round', 0)}\n")
            log.write(f"Total answers: {coord.get('total_answers', 0)}\n\n")
    time.sleep(5)

# Start with --automation to verify everything works
uv run massgen --automation --config [config_path] "[question]"

from custom_tools._multimodal_tools.run_massgen_with_recording import run_massgen_with_recording

result = await run_massgen_with_recording(
    config_path="massgen/configs/basic/multi/two_agents_gemini.yaml",
    question="What is 2+2?",
    output_format="mp4",  # ALWAYS use mp4 for maximum compatibility
    timeout_seconds=120,
    width=1920,
    height=1080
)

from custom_tools._multimodal_tools.understand_video import understand_video

# Overall UX evaluation
ux_eval = await understand_video(
    video_path=result["video_path"],  # The MP4 file from Step 1
    prompt="Evaluate the overall terminal display quality, clarity, and usability",
    num_frames=12
)

# Focused on coordination
coordination_eval = await understand_video(
    video_path=result["video_path"],
    prompt="How clearly does the display show agent coordination phases and voting?",
    num_frames=8
)

# Status indicators
status_eval = await understand_video(
    video_path=result["video_path"],
    prompt="Are status indicators (streaming, answered, voted) clear and visually distinct?",
    num_frames=8
)

# Check Gemini models and their release dates
grep -A 5 "model.*2\." massgen/backend/gemini.py

# Check OpenAI models and their release dates
grep -A 5 "model.*gpt" massgen/backend/openai.py

# Check Claude models and their release dates
grep -A 5 "model.*claude" massgen/backend/claude.py

cat docs/source/reference/token_budget.rst | grep -A 3 "gemini\|gpt\|claude"

# WORKFLOW:
# 1. Read backend file to find recent mid-tier models
# 2. Verify release date (< 12 months old)
# 3. Check pricing tier (mid-range)
# 4. Use model in --config-model flag

# Example: Generate 2-agent config
massgen --generate-config ./test_config.yaml \
  --config-backend gemini \
  --config-model gemini-2.5-pro \  # (example - always verify this is current!)
  --config-agents 2 \
  --config-docker

# With context path
massgen --generate-config ./test_config.yaml \
  --config-backend openai \
  --config-model gpt-5-mini \  # (example - always verify this is current!)
  --config-context-path /path/to/project

agents:
  - backend:
      enable_mcp_command_line: true
      command_line_execution_mode: "docker"

agents:
  - backend:
      enable_code_based_tools: true
      auto_discover_custom_tools: true

agents:
  - backend: {type: "gemini", model: "gemini-2.5-pro"}
  - backend: {type: "openai", model: "gpt-5-mini"}