feat(categorizer): implement subsystem/speed/batch_group inference

tests/categorizer.py

@@ -36,6 +36,38 @@ _FIXTURE_ARGS: dict[FixtureClass, frozenset[str]] = {
  FixtureClass.MOCK_APP: frozenset({"mock_app", "app_instance"}),
 }
 
+_SUBSYSTEM_PREFIXES: tuple[str, ...] = (
+ "ai", "api", "arch", "ast", "async", "auto", "beads", "bias", "cache",
+ "cli", "cmd", "comms", "conductor", "context", "cost", "dag", "deepseek",
+ "diff", "discussion", "event", "execution", "external", "ext", "fuzzy",
+ "gemini", "gui", "headless", "history", "hooks", "hot", "imgui", "layout",
+ "live", "log", "mcp", "markdown", "minimax", "mma", "model", "orchestrator",
+ "outline", "parallel", "patch", "perf", "persona", "phase", "pipeline",
+ "preset", "prior", "process", "project", "provider", "rag", "script",
+ "session", "shader", "sim", "skeleton", "slice", "spawn", "status",
+ "subagent", "summary", "symbol", "sync", "synthesis", "system", "takes",
+ "theme", "thinking", "ticket", "tier4", "tiered", "token", "tool", "track",
+ "tree", "ts", "undo", "usage", "user", "vendor", "view", "visual",
+ "vlogger", "websocket", "workflow", "workspace", "z",
+)
+
+_BATCH_GROUP_CLUSTERS: dict[str, tuple[str, ...]] = {
+ "core": (
+  "mcp", "ai", "context", "api", "dag", "path", "presets", "personas",
+  "history", "workspace", "rag", "beads", "model", "ast", "async", "cache",
+  "cli", "cmd", "fuzzy", "hooks", "log", "markdown", "orchestrator",
+  "outline", "pipeline", "project", "provider", "script", "session",
+  "skeleton", "slice", "spawn", "status", "subagent", "summary", "symbol",
+  "sync", "synthesis", "system", "takes", "thinking", "tier4", "tiered",
+  "tool", "track", "tree", "ts", "usage", "vendor", "vlogger", "websocket",
+  "workflow",
+ ),
+ "gui": ("gui", "theme", "imgui", "layout", "live", "prior", "visual", "view", "undo"),
+ "mma": ("mma", "conductor", "execution", "ext", "external", "auto", "manual", "tier", "arch", "phase", "process", "z"),
+ "comms": ("comms", "diff", "patch", "event", "hot", "process", "shader"),
+ "headless": ("headless",),
+}
+
 def _fixture_args_used(source: str) -> set[str]:
  try:
   tree = ast.parse(source)
@@ -64,14 +96,48 @@ def _classify_fixture_class(path: Path, source: str) -> FixtureClass:
    return FixtureClass.PERFORMANCE
  return FixtureClass.UNIT
 
+def _infer_subsystems(filename: str) -> list[str]:
+ stem = filename.removeprefix("test_").removesuffix(".py")
+ for prefix in sorted(_SUBSYSTEM_PREFIXES, key=len, reverse=True):
+  if stem.startswith(prefix + "_") or stem == prefix:
+   return [prefix]
+ return []
+
+def _infer_batch_group(subsystems: list[str]) -> str:
+ if not subsystems:
+  return "core"
+ first = subsystems[0]
+ for group, members in _BATCH_GROUP_CLUSTERS.items():
+  if first in members:
+   return group
+ return "core"
+
+def _infer_speed(filename: str, durations: dict[str, float] | None) -> Speed:
+ if not durations:
+  return Speed.MEDIUM
+ matching = [v for k, v in durations.items() if k.startswith(filename + "::")]
+ if not matching:
+  return Speed.MEDIUM
+ p95 = sorted(matching)[int(len(matching) * 0.95)]
+ if p95 < 1.0:
+  return Speed.FAST
+ if p95 < 5.0:
+  return Speed.MEDIUM
+ if p95 < 30.0:
+  return Speed.SLOW
+ return Speed.VERY_SLOW
+
 def auto_classify(path: Path, durations: dict[str, float] | None = None) -> CategoryRecord:
  source = path.read_text(encoding="utf-8", errors="replace")
  fixture_class = _classify_fixture_class(path, source)
+ subsystems = _infer_subsystems(path.name)
+ speed = _infer_speed(path.name, durations)
+ batch_group = _infer_batch_group(subsystems)
  return CategoryRecord(
   filename=path.name,
   fixture_class=fixture_class,
-  subsystems=[],
-  speed=Speed.MEDIUM,
-  batch_group="",
+  subsystems=subsystems,
+  speed=speed,
+  batch_group=batch_group,
   source="auto",
  )