perf: scope compile walks to applyTo roots

CHANGELOG.md

@@ -40,6 +40,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   every OS. Existing Windows lockfiles may retain the old CRLF-domain hash;
   keep the lockfile so its `resolved_commit` pins remain intact while the
   automatic one-time repair tracked in #2628 lands. (closes #2619)
+- `apm compile` now reduces matching work for literal scoped `applyTo` patterns
+  in large repositories while preserving historical placement. It shares a
+  source inventory across discovery and placement while preserving cleanup
+  behavior, and preserves commas in character classes. (#2595)
 - Hook commands such as `"${CLAUDE_PLUGIN_ROOT}"/hooks/probe.py` now rewrite to
   `"${CLAUDE_PLUGIN_ROOT}/hooks/probe.py"` and warn when a supported plugin-root
   placeholder remains unresolved instead of silently deploying a dead hook.

scripts/check_compile_inventory_authority.py

@@ -0,0 +1,75 @@
+"""Verify compile traversal is owned by the shared inventory."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).parents[1]
+INVENTORY = ROOT / "src/apm_cli/compilation/inventory.py"
+OPTIMIZER = ROOT / "src/apm_cli/compilation/context_optimizer.py"
+DISCOVERY = ROOT / "src/apm_cli/primitives/discovery.py"
+DISTRIBUTED = ROOT / "src/apm_cli/compilation/distributed_compiler.py"
+AGENTS = ROOT / "src/apm_cli/compilation/agents_compiler.py"
+
+
+def _has_all(source: str, required: tuple[str, ...]) -> bool:
+    """Return whether every required contract fragment appears in source."""
+    return all(fragment in source for fragment in required)
+
+
+def main() -> int:
+    """Return nonzero when compile traversal has a duplicate authority."""
+    inventory = INVENTORY.read_text(encoding="utf-8")
+    optimizer = OPTIMIZER.read_text(encoding="utf-8")
+    discovery = DISCOVERY.read_text(encoding="utf-8")
+    distributed = DISTRIBUTED.read_text(encoding="utf-8")
+    agents = AGENTS.read_text(encoding="utf-8")
+
+    valid = (
+        inventory.count("class CompileInventory") == 1
+        and inventory.count("os.walk(") == 1
+        and "os.walk(" not in optimizer
+        and "os.walk(" not in distributed
+        and _has_all(
+            optimizer,
+            (
+                "from .inventory import CompileInventory",
+                "inventory = self._inventory or CompileInventory.collect(self.base_dir)",
+                "inventory.files_under(self._scan_top_level_roots)",
+            ),
+        )
+        and _has_all(
+            discovery,
+            (
+                "inventory: CompileInventory | None = None",
+                "inventory.files_within(base_path)",
+            ),
+        )
+        and _has_all(
+            distributed,
+            (
+                "source_inventory: CompileInventory | None = None",
+                "deploy_inventory: CompileInventory | None = None",
+                "for directory_path, (relative_path, files) in sorted(cleanup_directories.items()):",
+            ),
+        )
+        and _has_all(
+            agents,
+            (
+                "self._source_inventory = CompileInventory.collect(",
+                "self.source_dir, exclude_patterns=config.exclude",
+                "source_inventory=self._source_inventory",
+                "deploy_inventory=self._deploy_inventory",
+            ),
+        )
+    )
+    if valid:
+        return 0
+
+    print("[x] Compile traversal must route through compilation/inventory.py")
+    return 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/lint-architecture-boundaries.sh

@@ -195,20 +195,8 @@ if [ -n "$compiled_write_hits" ]; then
     violations=$((violations + 1))
 fi
 distributed_compiler="src/apm_cli/compilation/distributed_compiler.py"
-nested_worktree_walk_count=$(grep -Fc \
-    'for directory, child_dirs, files in os.walk(self.base_dir, followlinks=False):' \
-    "$distributed_compiler" || true)
-nested_worktree_boundary_count=$(grep -Fc \
-    '(directory_path / ".git").is_file()' \
-    "$distributed_compiler" || true)
-nested_worktree_prune_count=$(grep -Fc 'child_dirs.clear()' "$distributed_compiler" || true)
-nested_worktree_rglob_hits=$(grep -En 'rglob\("AGENTS\.md"\)' "$distributed_compiler" || true)
-if [ "$nested_worktree_walk_count" -ne 1 ] \
-    || [ "$nested_worktree_boundary_count" -ne 1 ] \
-    || [ "$nested_worktree_prune_count" -ne 1 ] \
-    || [ -n "$nested_worktree_rglob_hits" ]; then
-    echo "[x] Nested worktree cleanup must prune .git-file roots"
-    [ -n "$nested_worktree_rglob_hits" ] && echo "$nested_worktree_rglob_hits"
+if ! python3 scripts/check_compile_inventory_authority.py; then
+    echo "[x] Compile traversal must use the shared inventory"
     violations=$((violations + 1))
 fi
 agents_source_attribution_output=$(python3 scripts/check_agents_source_attribution_owner.py \
@@ -1678,20 +1666,27 @@ apply_to_owner="src/apm_cli/utils/patterns.py"
 apply_to_normalizer_defs=$(grep -rEc --include='*.py' \
     '^def _?normalize_apply_to\(' src/apm_cli \
     | awk -F: '{sum += $2} END {print sum + 0}')
+apply_to_prefix_defs=$(grep -rEc --include='*.py' \
+    '^def literal_apply_to_top_level_roots\(' src/apm_cli \
+    | awk -F: '{sum += $2} END {print sum + 0}')
 apply_to_parser="src/apm_cli/primitives/parser.py"
 hidden_tool_placement_owner="src/apm_cli/compilation/context_optimizer.py"
 hidden_tool_tree_defs=$(grep -rEc --include='*.py' \
     '^PLACEMENT_HIDDEN_TOOL_TREES[[:space:]]*=' src/apm_cli \
     | awk -F: '{sum += $2} END {print sum + 0}')
 if [ "$apply_to_normalizer_defs" -ne 1 ] \
     || ! grep -q '^def normalize_apply_to(' "$apply_to_owner" \
+    || [ "$apply_to_prefix_defs" -ne 1 ] \
+    || ! grep -q '^def literal_apply_to_top_level_roots(' "$apply_to_owner" \
     || ! grep -q 'from apm_cli.utils.patterns import normalize_apply_to' "$apply_to_parser" \
     || grep -Eq '^def _?normalize_apply_to\(' "$apply_to_parser" \
     || ! grep -q 'normalize_apply_to(metadata.get("applyTo"), default="")' "$apply_to_parser" \
     || [ "$hidden_tool_tree_defs" -ne 1 ] \
     || ! grep -q '^PLACEMENT_HIDDEN_TOOL_TREES = frozenset(' "$hidden_tool_placement_owner" \
+    || ! grep -q 'literal_apply_to_top_level_roots(' "$hidden_tool_placement_owner" \
+    || grep -q '^    def _targeted_top_level_roots(' "$hidden_tool_placement_owner" \
     || ! grep -q 'not self._is_supported_hidden_tool_root(path)' "$hidden_tool_placement_owner"; then
-    echo "[x] applyTo normalization must use utils/patterns.py and hidden placement ContextOptimizer"
+    echo "[x] applyTo parsing must use utils/patterns.py and hidden placement ContextOptimizer"
     violations=$((violations + 1))
 fi
 

src/apm_cli/compilation/agents_compiler.py

@@ -23,10 +23,11 @@
 from ..primitives.discovery import discover_primitives
 from ..primitives.models import Instruction, PrimitiveCollection
 from ..utils.path_security import PathTraversalError, ensure_path_within
-from ..utils.paths import portable_relpath
+from ..utils.paths import portable_relpath, resolve_base_and_source_dirs
 from ..version import get_version
 from .claude_formatter import CLAUDE_HEADER, ClaudeFormatter
 from .constants import BUILD_ID_PLACEHOLDER
+from .inventory import CompileInventory
 from .link_resolver import resolve_markdown_links, validate_link_targets
 from .template_builder import (
     TemplateData,
@@ -336,13 +337,14 @@ def __init__(self, base_dir: str = ".", source_dir: str | None = None):
                 compile --root`` redirects writes but sources remain in
                 ``$PWD``.
         """
-        self.base_dir = Path(base_dir)
-        self.source_dir = Path(source_dir) if source_dir else self.base_dir
+        self.base_dir, self.source_dir = resolve_base_and_source_dirs(base_dir, source_dir)
         self.warnings: list[str] = []
         self.errors: list[str] = []
         self._logger = None
         self._distributed_placement: dict[Path, tuple[Instruction, ...]] | None = None
         self._distributed_context_optimizer: ContextOptimizer | None = None
+        self._source_inventory: CompileInventory | None = None
+        self._deploy_inventory: CompileInventory | None = None
 
     def _log(self, method: str, message: str, **kwargs):
         """Delegate to logger if available, else no-op."""
@@ -403,6 +405,14 @@ def compile(
         # Placement is valid only for this invocation's primitive snapshot.
         self._distributed_placement = None
         self._distributed_context_optimizer = None
+        self._source_inventory = CompileInventory.collect(
+            self.source_dir, exclude_patterns=config.exclude
+        )
+        self._deploy_inventory = (
+            self._source_inventory
+            if self.source_dir == self.base_dir and not config.exclude
+            else CompileInventory.collect(self.base_dir)
+        )
 
         try:
             # Use provided primitives or discover them (with dependency support)
@@ -412,6 +422,7 @@ def compile(
                     primitives = discover_primitives(
                         str(self.source_dir),
                         exclude_patterns=config.exclude,
+                        inventory=self._source_inventory,
                     )
                 else:
                     # Use enhanced discovery with dependencies (Task 4 integration)
@@ -420,6 +431,7 @@ def compile(
                     primitives = discover_primitives_with_dependencies(
                         str(self.source_dir),
                         exclude_patterns=config.exclude,
+                        inventory=self._source_inventory,
                     )
 
             # Route to targets based on config.target.
@@ -555,6 +567,8 @@ def _compile_distributed(
             str(self.base_dir),
             exclude_patterns=config.exclude,
             source_dir=str(self.source_dir),
+            source_inventory=self._source_inventory,
+            deploy_inventory=self._deploy_inventory,
         )
 
         # Skip instructions in AGENTS.md when they are already deployed to the
@@ -865,6 +879,8 @@ def _compile_claude_md(
                 str(self.base_dir),
                 exclude_patterns=config.exclude,
                 source_dir=str(self.source_dir),
+                source_inventory=self._source_inventory,
+                deploy_inventory=self._deploy_inventory,
             )
             placement_map = self._get_distributed_placement(
                 config,