よく使う言語だけ AST ベースでコードベース解析器を自作した: ctree の設計と pathfinder/Serena 連携

  $ ctree --help
Generate annotated tree + symbols + compact ctx

Usage: ctree [OPTIONS] [COMMAND]

Commands:
  init
  reset
  check
  clean
  help   Print this message or the help of the given subcommand(s)

Options:
      --mcp                    Run as MCP stdio server
      --config <CONFIG>        Config file path (default: .ctree.toml if exists)
      --root <ROOT>            Scan root path [default: .]
      --syntax <SYNTAX>        [possible values: go, rust, python, typescript,
                                csharp, dart, lua, awk, shell, kotlin, swift,
                                markdown, html]
      --include <INCLUDE>      Include globs
      --exclude <EXCLUDE>      Exclude globs [default: **/tmp/**,**/testdata/**,
                                **/.git/**,**/vendor/**]
      --strong <STRONG>        Strong scope globs
      --weak <WEAK>            Weak scope globs
      --sw <SW>                Max annotation words per strong file line [default: 12]
      --ww <WW>                Max annotation words per weak/symbol-only file line [default: 3]
      --reasoning <REASONING>  Reasoning level [possible values: high, medium, low]
      --template <TEMPLATE>    Output template [possible values: plain, hugo, jinja]
  -h, --help                   Print help
  

  [ctree]
watch = "rust"
root = "."
include = ["src/**/*.rs", "tests/**/*.rs"]
exclude = ["**/tmp/**", "**/testdata/**", "**/.git/**", "**/vendor/**", "**/target/**"]
strong = ["src/**"]
weak = ["tests/**"]
sw = 24
ww = 5
reasoning = "medium"
  

  .ctree/
  rust/
    e83adb52/          ← スコープ設定のハッシュ
      snapshots/
        .baseline.txt
        rev/
          0001.txt
          0002.txt
  

  $ ctree check --syntax rust
frequency=always
action=generate
latest_before=0001
latest_after=0001
(no new rev)
  

  $ ctree check --syntax rust
frequency=always
action=generate
latest_before=
latest_after=0001
rev_file=.ctree/rust/{scope_hash}/snapshots/rev/0001.txt
hashes={hash1},{hash2},{hash3},...

{hash1}
source=symbol kind=module name=... scope=strong path=src/.../main.rs line=2
mod ...;
--{hash1}
{hash2}
source=symbol kind=function name=... scope=strong path=src/.../mcp.rs line=164
fn ...(args: ...) -> Result<...> {
--{hash2}
  

  path_resolve:
  check_path: "content/ja/docs/tech/infrastrcture/podman-quadlet-systemd-ubuntu.md"
                                      ^^^^^^^^^^^ typo
  →  resolved: "content/ja/docs/tech/infrastructure/podman-quadlet-systemd-ubuntu.md"
  

  $ pathfinder --help
pathfinder — semantic path finder & MCP resolution server

USAGE
    pathfinder [OPTIONS]          Interactive semantic directory finder (default).
    pathfinder --mcp [OPTIONS]    Start as an MCP server.

FINDER OPTIONS
    --include-builds    Include build/artifact dirs (target, dist, …).

MCP OPTIONS
    --root <PATH>       Add a project root directory to watch and index.

GENERAL OPTIONS
    -h, --help          Print this help message and exit.
    -V, --version       Print version, model, and PCA config.

MCP TOOLS
  1. path_resolve        Resolve a failed file path to the best match.
  2. tool_retry_with_resolve  Resolve + retry the operation in one call.
  3. roots_list          Return configured root directories.
  4. reindex_paths       Force a full index rebuild.

ENVIRONMENT VARIABLES
    PF_MCP_INFERENCE    Inference mode: "general" (default) or "code".
    Models (both INT8 quantized):
      general → mxbai-edge-colbert (17M, 48-dim)
      code    → lateon-code-edge (17M, 48-dim)
  

  1. pathfinder  → LLM のパス typo を解決（ENOENT → tool_retry_with_resolve）
2. ctree check → スナップショット更新、変更されたシンボルのハッシュを取得
3. get_baseline → コードベースの浅い俯瞰を得る
4. 関心のあるシンボルを特定 → Serena の find_symbol で定義・参照を深掘り
5. get_revs + get_text → 変更されたシンボルの詳細を取得