#!/usr/bin/env python3
"""Generate crates/buzz-agent/src/databricks_model_names.rs from models.dev.

Usage:
    python3 scripts/generate-databricks-model-names.py \
        > crates/buzz-agent/src/databricks_model_names.rs

Fetches https://models.dev/api.json, extracts providers.databricks.models (the
authoritative curated name registry used by goose and others), and emits a
static Rust slice of (id, display_name) pairs sorted by ID.

Re-run whenever Databricks ships a new managed endpoint and commit the diff.
"""

import json
import subprocess
import sys


URL = "https://models.dev/api.json"


def fetch(url: str) -> bytes:
    # urllib blocks with HTTP 403 without a browser User-Agent; use curl when
    # available so the script works in hermit environments where curl is pinned.
    result = subprocess.run(
        ["curl", "-s", "-A", "Mozilla/5.0", url],
        capture_output=True,
        check=True,
    )
    return result.stdout


def rust_str(s: str) -> str:
    """Emit a Rust string literal with double quotes."""
    escaped = s.replace("\\", "\\\\").replace('"', '\\"')
    return f'"{escaped}"'


def main() -> None:
    raw = fetch(URL)
    data = json.loads(raw)
    models: dict = data["databricks"]["models"]
    entries = sorted(
        (k, v["name"] if isinstance(v, dict) else k) for k, v in models.items()
    )

    lines = [
        "// GENERATED by scripts/generate-databricks-model-names.py",
        "// Source:  https://models.dev/api.json -- providers.databricks.models",
        "// Refresh: python3 scripts/generate-databricks-model-names.py \\",
        "//              > crates/buzz-agent/src/databricks_model_names.rs",
        "//",
        "// Do not hand-edit -- rerun the script to update.",
        "",
        "/// Curated display names for known Databricks AI Gateway endpoints.",
        "///",
        "/// Keys are endpoint IDs returned verbatim by the discovery APIs.",
        "/// Values are human-readable display names sourced from models.dev.",
        "///",
        "/// Unknown endpoint IDs are displayed as their raw ID -- no guessing.",
        "pub(crate) static DATABRICKS_MODEL_NAMES: &[(&str, &str)] = &[",
    ]
    for id_, name in entries:
        lines.append(f"    ({rust_str(id_)}, {rust_str(name)}),")
    lines += ["];", ""]

    sys.stdout.write("\n".join(lines))


if __name__ == "__main__":
    main()