bot-bottle/bot_bottle/manifest_extends.py

"""Internal bottle `extends:` resolution for manifests."""

from __future__ import annotations

from typing import TYPE_CHECKING

from .manifest_util import ManifestError

if TYPE_CHECKING:
    from .manifest import ManifestBottle
    from .manifest_egress import ManifestEgressConfig


def resolve_bottles(raws: dict[str, dict[str, object]]) -> dict[str, ManifestBottle]:
    """Apply `extends:` chains and return resolved ManifestBottle objects."""
    cache: dict[str, ManifestBottle] = {}
    # Per-bottle effective git-gate.repos, as raw dicts keyed by repo name.
    # Threaded alongside `cache` so a child can field-merge against its
    # parent's repos without reconstructing them from parsed entries.
    repos_cache: dict[str, dict[str, object]] = {}
    for name in raws:
        if name not in cache:
            _resolve_one_bottle(name, raws, cache, repos_cache, ())
    return cache


def resolve_bottles_partial(
    raws: dict[str, dict[str, object]],
) -> tuple[dict[str, ManifestBottle], dict[str, ManifestError]]:
    """Apply `extends:` chains and return `(good, broken)`.

    Bottles that fail validation (schema errors, bad extends, cycles) are
    collected in `broken` rather than raising, so unrelated bottles remain
    usable. Errors for parent bottles propagate to all children that extend
    them."""
    cache: dict[str, ManifestBottle] = {}
    broken: dict[str, ManifestError] = {}
    for name in raws:
        if name not in cache and name not in broken:
            _resolve_one_bottle_partial(name, raws, cache, broken, ())
    return cache, broken


def _resolve_one_bottle(
    name: str,
    raws: dict[str, dict[str, object]],
    cache: dict[str, ManifestBottle],
    repos_cache: dict[str, dict[str, object]],
    seen: tuple[str, ...],
) -> ManifestBottle:
    from .manifest import ManifestBottle

    if name in cache:
        return cache[name]
    if name in seen:
        chain = " -> ".join(seen + (name,))
        raise ManifestError(f"bottle '{name}' is in an extends cycle: {chain}")
    raw = raws[name]
    parent_name_raw = raw.get("extends")
    # Strip `extends:` before passing to ManifestBottle.from_dict so it
    # is not accidentally treated as a real ManifestBottle field by future
    # schema additions. It is only meaningful here.
    child_raw = {k: v for k, v in raw.items() if k != "extends"}

    if parent_name_raw is None:
        bottle = ManifestBottle.from_dict(name, child_raw)
        cache[name] = bottle
        repos_cache[name] = _resolve_repos_raw({}, child_raw)
        return bottle

    if not isinstance(parent_name_raw, str):
        raise ManifestError(
            f"bottle '{name}' extends must be a string "
            f"(was {type(parent_name_raw).__name__})"
        )
    parent_name: str = parent_name_raw
    if parent_name == name:
        raise ManifestError(
            f"bottle '{name}' extends itself; remove the "
            f"self-reference"
        )
    if parent_name not in raws:
        avail = ", ".join(sorted(raws.keys())) or "(none)"
        raise ManifestError(
            f"bottle '{name}' extends '{parent_name}' which is not "
            f"defined. Available bottles: {avail}"
        )
    parent = _resolve_one_bottle(
        parent_name, raws, cache, repos_cache, seen + (name,)
    )
    merged_repos_raw = _resolve_repos_raw(repos_cache[parent_name], child_raw)
    bottle = _merge_bottles(parent, child_raw, merged_repos_raw, name)
    cache[name] = bottle
    repos_cache[name] = merged_repos_raw
    return bottle


def _merge_bottles(
    parent: ManifestBottle,
    child_raw: dict[str, object],
    merged_repos_raw: dict[str, object],
    name: str,
) -> ManifestBottle:
    """Apply PRD 0025 merge rules."""
    from .manifest import ManifestBottle, ManifestGitUser
    from .manifest_egress import validate_egress_routes
    from .manifest_util import as_json_object

    # git-gate.repos: when the child declares repos, inject the already
    # name-merged repo set (computed by _resolve_repos_raw) so the child
    # parses with the full inherited+overridden list (issue #237).
    if _child_declares_git_gate_repos(child_raw):
        git_raw = as_json_object(child_raw.get("git-gate", {}), "child git-gate")
        child_raw = {**child_raw, "git-gate": {**git_raw, "repos": merged_repos_raw}}

    # Parse the child's declared fields into a ManifestBottle (with the
    # usual defaults for anything missing). Validation runs the same
    # way it would for a leaf bottle: typos / wrong types die here.
    child = ManifestBottle.from_dict(name, child_raw)

    # env: dict merge, child wins on collision.
    merged_env = {**parent.env, **child.env}

    # git-gate.user: per-field overlay. Each non-empty field on child
    # wins; empties fall through to parent. The default ManifestGitUser()
    # is two empty strings, so a child that omits git-gate.user
    # inherits the parent's user verbatim.
    merged_git_user = ManifestGitUser(
        name=child.git_user.name or parent.git_user.name,
        email=child.git_user.email or parent.git_user.email,
    )

    # git-gate.repos: when declared, child.git already holds the merged
    # set (an explicit empty dict clears parent, leaving child.git empty).
    # When omitted, the parent's entries are inherited verbatim.
    if _child_declares_git_gate_repos(child_raw):
        merged_git = child.git
    else:
        merged_git = parent.git

    # egress.routes: missing means inherit; otherwise parent and child
    # route lists concatenate. Other egress scalar fields remain
    # presence-driven overlays.
    merged_egress = (
        _merge_egress(parent.egress, child.egress, child_raw)
        if "egress" in child_raw
        else parent.egress
    )

    # Presence-driven full-replace for the remaining scalar fields.
    merged_agent_provider = (
        child.agent_provider
        if "agent_provider" in child_raw
        else parent.agent_provider
    )
    merged_supervise = (
        child.supervise if "supervise" in child_raw else parent.supervise
    )
    validate_egress_routes(name, merged_egress.routes)

    return ManifestBottle(
        env=merged_env,
        agent_provider=merged_agent_provider,
        git=merged_git,
        git_user=merged_git_user,
        egress=merged_egress,
        supervise=merged_supervise,
    )


def _resolve_repos_raw(
    parent_repos: dict[str, object],
    child_raw: dict[str, object],
) -> dict[str, object]:
    """Compute a bottle's effective git-gate.repos as raw dicts.

    Repos are keyed by name. When the child omits git-gate.repos it
    inherits the parent's set verbatim; an explicit empty dict clears it.
    Otherwise parent and child unite by name, with same-name entries
    field-merged (parent fields are defaults, child fields win)."""
    from .manifest_util import as_json_object

    if not _child_declares_git_gate_repos(child_raw):
        return parent_repos
    child_repos = _declared_repos_raw(child_raw)
    if not child_repos:
        return {}
    # Parent entries keep their order; child-only names are appended.
    names = list(parent_repos) + [n for n in child_repos if n not in parent_repos]
    return {
        name: {
            **as_json_object(parent_repos.get(name, {}), "parent git-gate repo"),
            **as_json_object(child_repos.get(name, {}), "child git-gate repo"),
        }
        for name in names
    }


def _declared_repos_raw(child_raw: dict[str, object]) -> dict[str, object]:
    """Return the child's explicitly declared git-gate.repos as raw dicts,
    or an empty dict when none are declared."""
    from .manifest_util import as_json_object

    if not _child_declares_git_gate_repos(child_raw):
        return {}
    git_raw = as_json_object(child_raw.get("git-gate", {}), "child git-gate")
    return as_json_object(git_raw.get("repos", {}), "child git-gate.repos")


def _child_declares_git_gate_repos(child_raw: dict[str, object]) -> bool:
    from .manifest_util import as_json_object

    git_raw = child_raw.get("git-gate")
    if git_raw is None:
        return False
    git_obj = as_json_object(git_raw, "child git-gate")
    return "repos" in git_obj


def _merge_egress(
    parent: ManifestEgressConfig,
    child: ManifestEgressConfig,
    child_raw: dict[str, object],
) -> ManifestEgressConfig:
    from .manifest_egress import ManifestEgressConfig
    from .manifest_util import as_json_object

    child_egress_raw = as_json_object(child_raw.get("egress"), "child egress")
    routes = parent.routes + child.routes
    log = child.Log if "log" in child_egress_raw else parent.Log
    return ManifestEgressConfig(routes=routes, Log=log)


def _resolve_one_bottle_partial(
    name: str,
    raws: dict[str, dict[str, object]],
    cache: dict[str, ManifestBottle],
    broken: dict[str, ManifestError],
    seen: tuple[str, ...],
) -> None:
    """Error-tolerant variant: on failure, adds to `broken` instead of raising."""
    from .manifest import ManifestBottle

    if name in cache or name in broken:
        return
    if name in seen:
        chain = " -> ".join(seen + (name,))
        broken[name] = ManifestError(
            f"bottle '{name}' is in an extends cycle: {chain}"
        )
        return

    raw = raws[name]
    parent_name_raw = raw.get("extends")
    child_raw = {k: v for k, v in raw.items() if k != "extends"}

    try:
        if parent_name_raw is None:
            cache[name] = ManifestBottle.from_dict(name, child_raw)
            return

        if not isinstance(parent_name_raw, str):
            broken[name] = ManifestError(
                f"bottle '{name}' extends must be a string "
                f"(was {type(parent_name_raw).__name__})"
            )
            return

        parent_name: str = parent_name_raw
        if parent_name == name:
            broken[name] = ManifestError(
                f"bottle '{name}' extends itself; remove the self-reference"
            )
            return

        if parent_name not in raws:
            avail = ", ".join(sorted(raws.keys())) or "(none)"
            broken[name] = ManifestError(
                f"bottle '{name}' extends '{parent_name}' which is not "
                f"defined. Available bottles: {avail}"
            )
            return

        _resolve_one_bottle_partial(parent_name, raws, cache, broken, seen + (name,))
        if parent_name in broken:
            broken[name] = ManifestError(
                f"bottle '{name}' extends '{parent_name}' which failed to load: "
                f"{broken[parent_name]}"
            )
            return

        parent = cache[parent_name]
        cache[name] = _merge_bottles(parent, child_raw, name)
    except ManifestError as exc:
        broken[name] = exc