reuse-surface/reuse_surface/maintain_llm.py

from __future__ import annotations

import json
import subprocess
import textwrap
from pathlib import Path
from typing import Any

import yaml
from jsonschema import Draft202012Validator

from reuse_surface.llm_bridge import execute_prompt, extract_json_object
from reuse_surface.registry import ROOT, load_index_at, parse_front_matter, registry_paths

PATCH_SCHEMA_PATH = ROOT / "schemas" / "registry-patch.schema.json"

MATURITY_SUMMARY = """
| Dimension | Levels | Question |
|---|---|---|
| discovery | D0–D7 | Planning/orientation reuse strength |
| availability | A0–A7 | Consumption mode and delivery artifacts |
| completeness | C0–C6 | Scope vs intent and expectations |
| reliability | R0–R6 | Consumer quality signals |

Promotion rules:
- Cite repo-relative evidence paths for every maturity_promote patch.
- Prefer single-step promotions (one level per dimension).
- Do not invent files; only cite paths visible in git diff or context.
"""


def load_patch_schema() -> dict[str, Any]:
    return json.loads(PATCH_SCHEMA_PATH.read_text(encoding="utf-8"))


def _git_diff(repo_root: Path, git_since: str | None) -> str:
    if not git_since:
        return ""
    proc = subprocess.run(
        [
            "git",
            "-C",
            str(repo_root),
            "diff",
            git_since,
            "HEAD",
            "--",
            "registry/",
            "reuse_surface/",
            "tests/",
            "docs/",
            ".gitea/",
            ".forgejo/",
            "pyproject.toml",
        ],
        capture_output=True,
        text=True,
        check=False,
    )
    return proc.stdout[:12000]


def build_maintain_prompt(
    repo_root: Path,
    capability_id: str,
    *,
    git_since: str | None = None,
    context_files: list[str] | None = None,
) -> str:
    paths = registry_paths(repo_root)
    index = load_index_at(paths["index"])
    row = next((item for item in index["capabilities"] if item["id"] == capability_id), None)
    if not row:
        raise ValueError(f"capability not in index: {capability_id}")
    entry = parse_front_matter(repo_root / row["path"])
    diff = _git_diff(repo_root, git_since)

    context_chunks: list[str] = []
    for rel in context_files or []:
        path = repo_root / rel
        if path.is_file():
            context_chunks.append(f"### {rel}\n{path.read_text(encoding='utf-8')[:4000]}")

    schema_hint = json.dumps(
        {
            "patches": [
                {
                    "capability_id": capability_id,
                    "kind": "maturity_promote",
                    "confidence": "medium",
                    "rationale": "CI gate added",
                    "dimension": "reliability",
                    "from_level": "R2",
                    "to_level": "R3",
                    "evidence_citations": ["tests/test_example.py"],
                    "promotion_history_entry": {
                        "date": "2026-06-16",
                        "dimension": "reliability",
                        "from": "R2",
                        "to": "R3",
                        "rationale": "pytest coverage for consumption path",
                    },
                }
            ],
            "notes": ["optional human review items"],
        },
        indent=2,
    )

    return textwrap.dedent(
        f"""
        Propose structured registry maintenance patches for `{capability_id}`.

        Return ONLY JSON matching this shape (no markdown fences):
        {schema_hint}

        Allowed patch kinds: vector_sync, evidence_append, artifact_append,
        maturity_promote, consumer_feedback, relation_add, index_row_add,
        index_updated_bump.

        Maturity reference:
        {MATURITY_SUMMARY}

        Current entry YAML:
        {yaml.safe_dump(entry, sort_keys=False)}

        Git diff since {git_since or 'N/A'}:
        {diff or '(none)'}

        Context files:
        {chr(10).join(context_chunks) if context_chunks else '(none)'}
        """
    ).strip()


def request_maintain_patches(
    repo_root: Path,
    capability_id: str,
    *,
    git_since: str | None = None,
    context_files: list[str] | None = None,
    llm_url: str | None = None,
) -> dict[str, Any]:
    prompt = build_maintain_prompt(
        repo_root,
        capability_id,
        git_since=git_since,
        context_files=context_files,
    )
    content = execute_prompt(
        prompt,
        base_url=llm_url,
        config={"temperature": 0.2, "max_tokens": 3000},
    )
    payload = extract_json_object(content)
    validator = Draft202012Validator(load_patch_schema())
    errors = sorted(validator.iter_errors(payload), key=lambda err: list(err.path))
    if errors:
        messages = "; ".join(error.message for error in errors[:3])
        raise ValueError(f"patch schema validation failed: {messages}")
    return payload