Claude Code engine, image viewer, colour tags, checks per turn and more

- Claude Code as an engine: chats on a "claude-code/<alias>" model run through
  the claude CLI (stream-json); tool approvals go through our permission
  system. Sign in from the web UI (URL + pasted code), CLI version and update
  from Settings; the Docker image contains the CLI.
- Small models (8k context) for side tasks: input is cut to the model's
  context window; one-line chat status, "What does this do?" on approvals,
  "Plan as automation" (job draft from a chat).
- Mobile: top bar no longer widens the page, image viewer (zoom, swipe, mark
  up, use in message), jump to previous own message, message menu, time under
  every message.
- Approvals: push actions (allow/reject), "always allow in this project"
  (never for dangerous commands) with revoke.
- Per turn: changed files with diffs and rollback; project check command with
  a green/red badge and "let the agent fix it".
- Colour tags for chats in the colours of the active theme.
- Project defaults for new chats, project page (timeline), offline queue.

Tested in a throwaway container with a mock model (8k small model): 26 API
checks passed (permissions, diffs, checks, defaults, job draft, side-task
budget, Claude Code status/login URL, unsigned-in chat).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

server/src/jobs.rs

@@ -321,6 +321,8 @@ pub async fn run_with(app: &Arc<App>, job: &Job, trigger: &str, payload: Option<
         instructions: String::new(),
         // New chats keep their approvals and questions out of Telegram (⋯ menu turns it on).
         telegram_quiet: true,
+        summary: String::new(),
+        color: None,
     };
     let session = app.save_session(session)?;
     app.store.job_started(&job.id, &session.id, now)?;