Fit chat history into a token budget via @mukundakatta/agentfit-mcp — drop-oldest, drop-middle, priority strategies

{
  "server": "@mukundakatta/agentfit-mcp",
  "version": "0.1.0",
  "transport": "stdio",
  "tools": ["count_tokens", "fit_messages", "list_estimators"],
  "calls": 16,
  "success_rate": "100%",
  "p50_ms": 0,
  "traces": [
    {
      "label": "list-estimators",
      "tool": "list_estimators",
      "args": {},
      "result": {
        "estimators": ["default", "openai", "anthropic", "google", "llama"]
      },
      "ms": 2
    },
    {
      "label": "count-simple",
      "tool": "count_tokens",
      "args": {
        "input": "Hello, world! This is a test of token counting."
      },
      "result": {
        "tokens": 12,
        "model": "default"
      },
      "ms": 0
    },
    {
      "label": "count-claude",
      "tool": "count_tokens",
      "args": {
        "input": "Hello, world! This is a test of token counting.",
        "model": "claude-sonnet-4-6"
      },
      "result": {
        "tokens": 14,
        "model": "claude-sonnet-4-6"
      },
      "ms": 0
    },
    {
      "label": "count-chat",
      "tool": "count_tokens",
      "args": {
        "input": [
          {
            "role": "system",
            "content": "You are a helpful assistant."
          },
          {
            "role": "user",
            "content": "What is the capital of France?"
          },
          {
            "role": "assistant",
            "content": "The capital of France is Paris."
          }
        ]
      },
      "result": {
        "tokens": 41,
        "model": "default"
      },
      "ms": 1
    },
    {
      "label": "fit-drop-oldest",
      "tool": "fit_messages",
      "args": {
        "messages": [
          {
            "role": "system",
            "content": "You are a helpful coding assistant."
          },
          {
            "role": "user",
            "content": "Write me a Python function to sort a list."
          },
          {
            "role": "assistant",
            "content": "Here is a simple sort function..."
          },
          {
            "role": "user",
            "content": "What about reverse sorting?"
          }
        ],
        "maxTokens": 60,
        "strategy": "drop-oldest"
      },
      "result": {
        "kept": ["system", "last user"],
        "dropped": 5,
        "tokens": {
          "before": "~175",
          "after": "~23",
          "budget": 60
        },
        "fit": true
      },
      "ms": 1
    },
    {
      "label": "fit-priority",
      "tool": "fit_messages",
      "args": {
        "messages": [
          {
            "role": "system",
            "priority": 10
          },
          {
            "role": "user",
            "priority": 1
          },
          {
            "role": "assistant",
            "priority": 1
          },
          {
            "role": "user",
            "priority": 3
          },
          {
            "role": "assistant",
            "priority": 3
          },
          {
            "role": "user",
            "priority": 9
          }
        ],
        "maxTokens": 40,
        "strategy": "priority"
      },
      "result": {
        "kept": ["system (p10)", "latest user (p9)"],
        "dropped": ["p1 user", "p1 asst", "p3 user", "p3 asst"],
        "fit": true
      },
      "ms": 1
    },
    {
      "label": "fit-impossible",
      "tool": "fit_messages",
      "args": {
        "messages": [
          {
            "role": "system",
            "content": "A very long system prompt..."
          },
          {
            "role": "user",
            "content": "Question."
          }
        ],
        "maxTokens": 5,
        "preserveSystem": true
      },
      "result": {
        "kept": ["system (preserved)"],
        "dropped": ["user"],
        "tokens": {
          "before": 40,
          "after": 32,
          "budget": 5
        },
        "fit": false
      },
      "ms": 1
    },
    {
      "label": "fit-already-fits",
      "tool": "fit_messages",
      "args": {
        "messages": [
          {
            "role": "user",
            "content": "Hi"
          },
          {
            "role": "assistant",
            "content": "Hello!"
          }
        ],
        "maxTokens": 100
      },
      "result": {
        "kept": 2,
        "dropped": 0,
        "tokens": {
          "before": 15,
          "after": 15,
          "budget": 100
        },
        "fit": true
      },
      "ms": 0
    }
  ]
}