feat(ai-tools): omp shared + OpenCode/omp sessions, tokens, subagents; Grok hooks; resume by id

- omp-usage.js / opencode-usage.js: poll each CLI's own session store into
  sessions (tool omp/opencode), token_usage per model and subagent agents;
  transcript routes read them (omp journals, OpenCode's opencode.db).
- Grok runs the Claude hooks in ~/.claude/settings.json: its hooks are now
  recognised (hookEventName + workspaceRoot), tagged tool=grok, and their
  transcript_path dropped instead of being parsed as a Claude transcript.
- Catalog `resumeById`: omp/Grok/Cursor `--resume <id>`, OpenCode
  `--session <id>`; session ids may carry `_`. The client offers Resume for
  any tool that resumes by id.
- Kimi Code and GitHub Copilot leave the catalog (their session stores could
  not be verified).

server/index.js

@@ -766,6 +766,18 @@ function startBackgroundServices() {
   } catch (err) {
     console.warn("cursor usage poll failed to start:", err.message);
   }
+  // Oh My Pi and OpenCode sessions, subagents and token usage, from each CLI's
+  // own session store (omp-usage.js, opencode-usage.js).
+  for (const [name, mod, start] of [
+    ["omp", "./lib/omp-usage", "startOmpUsagePoll"],
+    ["opencode", "./lib/opencode-usage", "startOpencodeUsagePoll"],
+  ]) {
+    try {
+      require(mod)[start](broadcast);
+    } catch (err) {
+      console.warn(`${name} usage poll failed to start:`, err.message);
+    }
+  }
   // Codex/Antigravity hooks the user installed forward through a script whose
   // content names this build; point it here (the command in the tool's
   // hooks.json, which Codex trusts, stays the same).