pathfinderの最適化プロセス：モデル選定・精度調整・履歴相関の検証

  # .gitignore の内容に基づき自動的に無視対象を決定
# 例：
__pycache__
node_modules
dist
build
target
.git
  

  TopK = ceil(total_files * ratio)  # ratio: 0.05 や 0.1 など
  

  // 起動時に定数パスで事前に再ランキングを実行
let _ = rerank("alpha_path", "beta_path", &embedder)?;
  

  /models/*       # models配下はすべて無視
!mxbai-colbert  # ただしこのディレクトリは含める
  

  sampling/
├── cmd/
│   ├── server/
│   │   └── main.go
├── internal/
│   ├── domain/
│   │   ├── knowledge/
│   │   ├── llm/
│   │   └── pipeline/
│   ├── infra/
│   │   ├── llamacpp/
│   │   ├── lmstudio/
│   │   ├── nats/
│   │   ├── openaihttp/
│   │   ├── postgres/
│   │   ├── reranker/
│   │   └── vllm/
├── devstack/
│   ├── dagster/
│   └── trino/
└── packages/
    └── resolver-go/
  

  モデル候補：
├── mxbai-edge-colbert-v0-32m (公式)
│   ├── onnx/model_int8.onnx    ← 高速，精度？
│   ├── onnx/model_fp16.onnx    ← 中速，中精度
│   └── onnx/model_fp32.onnx    ← 低速，高精度
├── lightonai-mxbai-edge       ← オルタナティブ
└── ort-comm-colbert-sm-v1     ← 軽量版
  

  let scores_m1 = rerank_with_model(query, candidates, &model1)?;
let scores_m2 = rerank_with_model(query, candidates, &model2)?;
let final_scores = (scores_m1 + scores_m2) / 2.0;
  

  struct QueryHistory {
    queries: Vec<QueryRecord>,
}

struct QueryRecord {
    query: String,
    parent_dir: String,
    timestamp: u64,
}
  

  // candidate_dir が最近のクエリ親と同じ → スコア +20
// 似た構造（depth, name_pattern が近い） → スコア +10

fn compute_history_affinity(
    candidate_dir: &str,
    history: &QueryHistory,
) -> f32 {
    // 過去5件の parent_dir との一致度
    ...
}
  

  score >= 50.0 → 確信度高い，即座に返す
30.0 < score < 50.0 → marginal，再ランキング検討
score <= 30.0 → 低信頼度，常に再ランキング
  

  [email protected] ~/Development/loftllc-web % pathfinder-mcp -h
pathfinder-mcp — deterministic path resolution MCP server

USAGE
    pathfinder [OPTIONS]

OPTIONS
    --root <PATH>     Add a project root directory to watch and index.
                      May be specified multiple times.  Defaults to $PWD.
    -h, --help        Print this help message and exit.

DESCRIPTION
    An MCP (Model Context Protocol) server that resolves ENOENT / NotFound
    path errors for AI coding agents.  It builds an in-memory path index of
    configured root directories and uses fuzzy matching combined with ColBERT
    MaxSim re-ranking (when an ONNX model is available) to resolve incorrect
    paths to their most likely existing counterparts.

    Communication is via JSON-RPC over stdin/stdout.  Evaluation metrics are
    written to stderr as JSON lines (redirect with 2>metrics.jsonl).

    The server runs a stdin reader thread with periodic orphan detection and
    exits automatically when the parent MCP client process disappears.

ENVIRONMENT VARIABLES
    RESOLVE_MODEL_PRECISION  Model precision: "int8" (default), "fp16", or "fp32".
    RESOLVE_MODEL_DIR        Model directory containing model_*.onnx + tokenizer.json.
    RESOLVE_TOPK             Minimum topk value (default 10).
    INCLUDE_DIRS             Comma-separated directory names to force-include.

MCP TOOLS
    path_resolve             Resolve a failed file path to the best match.
    tool_retry_with_resolve  Resolve and automatically retry the operation.
    roots_list               Return configured root directories.
    reindex_paths            Force a full rebuild of the path index.

MCP CLIENT CONFIGURATION (Claude Code)
    "pathfinder-mcp": {
      "command": "pathfinder",
      "args": ["--root", "${workspaceFolder}"]
    }