feat: usage tracking + knowledge import script

- usage_tracker.py: daily token/call buckets per user (home/{user}/usage.json)
- Hook into local backend (OpenAI usage field) and Gemini API (usage_metadata)
- Claude/Gemini CLI backends produce no structured token data and are not tracked
- Fix CLAUDE.md stale tool count (27 → 39) and refresh tool list
- scripts/import_knowledge.py: walk markdown dirs, chunk by H2, call local LLM
  for summaries, create AE journal entries with path-derived tags; resumable via
  state file; --dry-run and --limit flags for safe testing

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

CLAUDE.md

@@ -226,10 +226,13 @@ Cortex is running and stable. All channels are live:
 
 Active users: scott (inara, developer), holly (tina), brian (wintermute)
 
-**27 orchestrator tools:** web_search, file_read, shell_exec, claude_allow_dir,
+**39 orchestrator tools:** web_search, http_fetch,
+file_read/list/write, shell_exec, claude_allow_dir,
+cortex_restart/logs/status/update,
 task_list/create/update/complete, cron_list/add/remove/toggle,
-reminders_add/list/clear, scratch_read/write/append/clear,
-ae_journal_list/search/entry_create/entry_update/entry_disable/entry_append/entry_prepend,
+reminders_add/list/remove/clear, scratch_read/write/append/clear,
+email_send, nc_talk_send,
+ae_journal_list/search/entries_list/entry_read/entry_create/entry_update/entry_disable/entry_append/entry_prepend,
 ae_task_list.
 
 See `documentation/TODO__Agents.md` for the active task list.