"""Phase 11 audit: classify each remaining .get() and [] access site as either
promoted (per-aggregate dataclass consumer) or collapsed-codepath (per spec FR2).

Outputs a markdown table per file.
"""

from __future__ import annotations
import re
from pathlib import Path

GET_PATTERN = re.compile(r"\.get\('[a-z_]+',")
SUBSCRIPT_PATTERN = re.compile(r"\[\s*'[a-z_]+'\s*\]")

FILES = [
 "src/aggregate.py",
 "src/ai_client.py",
 "src/app_controller.py",
 "src/gui_2.py",
 "src/mcp_client.py",
 "src/models.py",
 "src/paths.py",
 "src/synthesis_formatter.py",
 "src/api_hooks.py",
 "src/conductor_tech_lead.py",
 "src/log_pruner.py",
 "src/log_registry.py",
 "src/multi_agent_conductor.py",
 "src/performance_monitor.py",
 "src/project_manager.py",
]

CLASSIFICATIONS = {
 "src/aggregate.py": "build_tier3_context reads file_items: list[Metadata] from callers; collapsed-codepath",
 "src/ai_client.py": "file_items parameter is list[Metadata] for multimodal content (is_image, base64_data); collapsed-codepath",
 "src/app_controller.py": "session log entries + project config (manual_slop.toml) + UI state all dicts; collapsed-codepath",
 "src/gui_2.py": "self.active_tickets is list[dict] per app_controller:1110; UI table dicts; project config from manual_slop.toml; collapsed-codepath",
 "src/mcp_client.py": "MCP wire protocol dicts + tool result dicts; collapsed-codepath",
 "src/models.py": "legacy compat shims (Ticket.from_dict, etc.); mostly backward-compat code paths",
 "src/paths.py": "TOML config dict access; collapsed-codepath",
 "src/synthesis_formatter.py": "synthesis result formatting; minor collapsed-codepath",
 "src/api_hooks.py": "REST API payload dicts (HTTP body); collapsed-codepath",
 "src/conductor_tech_lead.py": "JSON-parsed tickets returned from LLM; collapsed-codepath",
 "src/log_pruner.py": "log session registry dicts; collapsed-codepath",
 "src/log_registry.py": "log session registry dicts; collapsed-codepath",
 "src/multi_agent_conductor.py": "telemetry aggregation dicts; collapsed-codepath",
 "src/performance_monitor.py": "performance metrics dicts; collapsed-codepath",
 "src/project_manager.py": "TOML project manager state; collapsed-codepath",
}

def count_pattern(path: Path, pattern: re.Pattern[str]) -> int:
 try:
  content = path.read_text(encoding="utf-8")
 except Exception:
  return 0
 return len(pattern.findall(content))

def main() -> None:
 print("# Phase 11 Audit: Remaining .get() and [] sites\n")
 print("Each site is classified as either (a) PROMOTED to per-aggregate dataclass, or (b) COLLAPSED-CODEPATH per spec FR2.\n")
 print("## Per-File Counts\n")
 print("| File | .get() sites | [key] subscript sites | Classification |")
 print("|---|---:|---:|---|")
 total_get = 0
 total_subscript = 0
 for f in FILES:
  p = Path(f)
  if not p.exists():
   continue
  n_get = count_pattern(p, GET_PATTERN)
  n_subscript = count_pattern(p, SUBSCRIPT_PATTERN)
  total_get += n_get
  total_subscript += n_subscript
  classification = CLASSIFICATIONS.get(f, "unknown")
  print(f"| {f} | {n_get} | {n_subscript} | {classification} |")
 print(f"| **TOTAL** | **{total_get}** | **{total_subscript}** | |")
 print()
 print(f"Total access sites: {total_get + total_subscript}")

if __name__ == "__main__":
 main()