brain-of-reese/app/api/git_sources.py

"""Admin-managed sources API (phase 35, task 02; local kind, phase 38).

Admin-only CRUD under ``/api/git-sources`` (phase 16 pattern, A10
extended — the public API surface stays stateless and the signed cookie
remains the only session state, same as ``/api/steering`` and
``/api/sync``): the ``git_sources`` table holds the sources the Sync
button (phase 32) and ``import_docs`` (phase 28) import — ``kind='git'``
rows carry the repo URL to clone/pull, ``kind='local'`` rows (phase 38)
carry an existing directory on the server to walk directly. DB rows win
over ``BOR_GIT_SOURCES``, which is a git-only fallback while the table is
empty (the phase's locked decision — ``from_env`` tells the UI which list
it is looking at, so the page can show the env note only while the
fallback is active).

Routes: ``GET`` (DB rows oldest-first, or the env list with
``from_env: true`` while the table is empty; rows carry ``kind`` +
``path``, git rows — and env rows — report ``path: null``), ``POST``
(201, validated create; ``kind`` selects the validation: git → exactly
the phase-35 URL contract, local → an existing absolute directory, else
422 naming the path), ``DELETE /{source_id}`` (204). The whole router
sits behind :func:`app.core.auth.require_admin` — anonymous callers get
403 on every route.

No credential-echo path: git URLs may embed ``user:pass@`` (phase 32's
masking discipline), so every git 409/422 detail is a fixed generic
string that never repeats the submitted URL. Local paths are not
secrets — the local 422/409 details name the (expanded) path so the
owner sees exactly which directory failed.

Scope boundary (phase locked decisions): adding or removing a source
does NOT clone, import, or prune anything — the existing Sync button
performs that (a removal prunes on the next sync, ``prune=True``).
"""
from __future__ import annotations

import re
import uuid
from pathlib import Path
from typing import Literal, cast

from fastapi import APIRouter, Depends, HTTPException, Response
from sqlalchemy import select
from sqlalchemy.exc import IntegrityError
from sqlalchemy.orm import Session

from app.config import get_settings
from app.core.auth import require_admin
from app.db import get_db
from app.models import GitSource
from app.schemas import GitSourceIn, GitSourceList, GitSourceOut, GitSourceRow

router = APIRouter(
    prefix="/git-sources",
    tags=["git-sources"],
    dependencies=[Depends(require_admin)],  # phase 16 pattern: admin-only surface
)

#: Accepted git URL shapes — the trimmed URL must *start* with one of them.
#: Covers the phase-28 real URLs (HTTPS + ``git@`` SSH); scp-style
#: ``host:repo`` is deliberately rejected (422). ASSUMPTION (task 02): the
#: accepted shapes are exactly these four prefixes.
URL_RE = re.compile(r"^(https?://|ssh://|git@)")


@router.get("", response_model=GitSourceList)
def list_git_sources(
    db: Session = Depends(get_db),  # noqa: B008
) -> GitSourceList:
    """The effective source list (git + local rows, phase 38).

    DB rows ordered by ``(added_at, id)`` (oldest first, id tie-break for
    same-timestamp inserts) with ``from_env: false`` — each row carries
    its ``kind`` and, for local rows, the stored ``path`` (git rows and
    env rows report ``path: null``); while the table is empty, the
    ``BOR_GIT_SOURCES`` env URLs as git rows (the env fallback is
    git-only) with null ``id``/``added_at`` and ``from_env: true``.
    """
    rows = db.scalars(
        select(GitSource).order_by(GitSource.added_at.asc(), GitSource.id.asc())
    ).all()
    if rows:
        return GitSourceList(
            sources=[
                # ``ck_git_sources_kind`` (migration 0007) guarantees the
                # value is 'git' or 'local' — the cast documents that.
                GitSourceRow(
                    id=row.id,
                    kind=cast(Literal["git", "local"], row.kind),
                    url=row.url,
                    path=row.path,
                    added_at=row.added_at,
                )
                for row in rows
            ],
            from_env=False,
        )
    return GitSourceList(
        sources=[
            GitSourceRow(id=None, kind="git", url=url, path=None, added_at=None)
            for url in get_settings().git_source_list
        ],
        from_env=True,
    )


@router.post("", response_model=GitSourceOut, status_code=201)
def create_git_source(
    payload: GitSourceIn,
    db: Session = Depends(get_db),  # noqa: B008
) -> GitSourceOut:
    """Store one source (fields already trimmed by the schema).

    ``kind="git"`` (default) — exactly the phase-35 contract: 422 when
    the URL shape is not one of the accepted prefixes (generic detail —
    the input is never echoed), 409 when the trimmed URL is already
    stored (the unique index is the backstop against a concurrent insert
    the pre-check missed), 201 + the created row otherwise.

    ``kind="local"`` — ``path`` must expand (``~``) to an absolute,
    existing directory on the server: 422 naming the path otherwise
    (fail loud at add-time — the owner sees it immediately), 409 when
    the path is already stored (detail names the path), 201 + the stored
    row otherwise (``url`` holds the expanded path — the table's
    NOT-NULL location column).

    Wrong field combinations (git without url, local without path, both
    kinds' fields) are 422 with fixed, input-free details.
    """
    row = _create_git_row(payload, db) if payload.kind == "git" else _create_local_row(payload, db)
    return GitSourceOut(id=row.id, url=row.url, added_at=row.added_at)


def _commit_new(row: GitSource, duplicate_detail: str, db: Session) -> GitSource:
    """Insert ``row``; the unique index is the backstop — a concurrent
    insert the pre-check missed still yields the generic 409, never a
    500 (phase-35 convention, now shared by both kinds)."""
    db.add(row)
    try:
        db.commit()
    except IntegrityError:
        db.rollback()
        raise HTTPException(status_code=409, detail=duplicate_detail) from None
    db.refresh(row)
    return row


def _create_git_row(payload: GitSourceIn, db: Session) -> GitSource:
    """``kind=git`` — the phase-35 URL contract, unchanged (A10: no
    credential echo, so every detail is a fixed string)."""
    if payload.path is not None:
        raise HTTPException(status_code=422, detail="a git source takes a url, not a path")
    if payload.url is None:
        raise HTTPException(status_code=422, detail="a git source requires a url")
    url = payload.url
    if not URL_RE.match(url):
        raise HTTPException(
            status_code=422, detail="not a valid git URL (expected https://, ssh:// or git@…)"
        )
    if db.scalar(select(GitSource).where(GitSource.url == url)) is not None:
        raise HTTPException(status_code=409, detail="a git source with this URL already exists")
    return _commit_new(
        GitSource(url=url, kind="git"), "a git source with this URL already exists", db
    )


def _create_local_row(payload: GitSourceIn, db: Session) -> GitSource:
    """``kind=local`` — fail-loud add-time validation (phase 38):
    trimmed → ``expanduser()`` → absolute + existing directory, else 422
    naming the path (not a secret, unlike a git URL)."""
    if payload.url is not None:
        raise HTTPException(status_code=422, detail="a local source takes a path, not a url")
    if payload.path is None:
        raise HTTPException(status_code=422, detail="a local source requires a path")
    expanded = Path(payload.path).expanduser()
    if not expanded.is_absolute() or not expanded.is_dir():
        raise HTTPException(
            status_code=422, detail=f"local source path is not a directory: {expanded}"
        )
    path = str(expanded)
    if db.scalar(select(GitSource).where(GitSource.path == path)) is not None:
        raise HTTPException(
            status_code=409, detail=f"a local source with this path already exists: {path}"
        )
    # ``url`` is the table's NOT-NULL location column (phase 38: local
    # rows carry the expanded path there too — git URL shapes and absolute
    # paths cannot collide).
    return _commit_new(
        GitSource(url=path, kind="local", path=path),
        f"a local source with this path already exists: {path}",
        db,
    )


@router.delete("/{source_id}", status_code=204)
def delete_git_source(
    source_id: uuid.UUID,
    db: Session = Depends(get_db),  # noqa: B008
) -> Response:
    """Remove a stored row; 404 when the id is unknown.

    Removing does not touch the clones or the index — the next Sync
    (``prune=True``) prunes the dropped repo (phase scope boundary).
    """
    row = db.get(GitSource, source_id)
    if row is None:
        raise HTTPException(status_code=404, detail="git source not found")
    db.delete(row)
    db.commit()
    return Response(status_code=204)