refactor(manifest): split schema boundaries

bot_bottle/manifest_extends.py

@@ -0,0 +1,141 @@
+"""Internal bottle `extends:` resolution for manifests."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from .manifest import Bottle, GitEntry
+
+
+def resolve_bottles(raws: dict[str, dict[str, object]]) -> dict[str, Bottle]:
+    """Apply `extends:` chains and return resolved Bottle objects."""
+    cache: dict[str, Bottle] = {}
+    for name in raws:
+        if name not in cache:
+            _resolve_one_bottle(name, raws, cache, ())
+    return cache
+
+
+def _resolve_one_bottle(
+    name: str,
+    raws: dict[str, dict[str, object]],
+    cache: dict[str, Bottle],
+    seen: tuple[str, ...],
+) -> Bottle:
+    from .manifest import Bottle, ManifestError
+
+    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 Bottle.from_dict so it
+    # is not accidentally treated as a real Bottle 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 = Bottle.from_dict(name, child_raw)
+        cache[name] = bottle
+        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, seen + (name,))
+    bottle = _merge_bottles(parent, child_raw, name)
+    cache[name] = bottle
+    return bottle
+
+
+def _merge_bottles(
+    parent: Bottle,
+    child_raw: dict[str, object],
+    name: str,
+) -> Bottle:
+    """Apply PRD 0025 merge rules."""
+    from .manifest import Bottle, GitUser, _validate_egress_routes
+
+    # Parse the child's declared fields into a Bottle (with the
+    # usual defaults for anything missing). Validation runs the same
+    # way it would for a leaf bottle: typos / wrong types die here.
+    child = Bottle.from_dict(name, child_raw)
+
+    # env: dict merge, child wins on collision.
+    merged_env = {**parent.env, **child.env}
+
+    # git.user: per-field overlay. Each non-empty field on child
+    # wins; empties fall through to parent. The default GitUser()
+    # is two empty strings, so a child that omits git.user
+    # inherits the parent's user verbatim.
+    merged_git_user = GitUser(
+        name=child.git_user.name or parent.git_user.name,
+        email=child.git_user.email or parent.git_user.email,
+    )
+
+    # git.remotes: missing means inherit; an explicit empty object
+    # clears; otherwise parent and child merge by UpstreamHost with
+    # child entries replacing duplicate hosts.
+    if _child_declares_git_remotes(child_raw):
+        merged_git = _merge_git_remotes(parent.git, child.git) if child.git else ()
+    else:
+        merged_git = parent.git
+
+    # Presence-driven full-replace for the remaining list-valued +
+    # scalar fields.
+    merged_egress = child.egress if "egress" in child_raw else parent.egress
+    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 Bottle(
+        env=merged_env,
+        agent_provider=merged_agent_provider,
+        git=merged_git,
+        git_user=merged_git_user,
+        egress=merged_egress,
+        supervise=merged_supervise,
+    )
+
+
+def _child_declares_git_remotes(child_raw: dict[str, object]) -> bool:
+    from .manifest import _as_json_object
+
+    git_raw = child_raw.get("git")
+    if git_raw is None:
+        return False
+    git_obj = _as_json_object(git_raw, "child git")
+    return "remotes" in git_obj
+
+
+def _merge_git_remotes(
+    parent: tuple[GitEntry, ...],
+    child: tuple[GitEntry, ...],
+) -> tuple[GitEntry, ...]:
+    by_host = {entry.UpstreamHost: entry for entry in parent}
+    for entry in child:
+        by_host[entry.UpstreamHost] = entry
+    return tuple(by_host.values())