Introduce AutoMetabuilder core components and workflow packages:

- Implement core components: CLI argument parsing, environment loading, GitHub service creation, and logging configuration.
- Add support for OpenAI client setup and model resolution.
- Develop SDLC context loader from GitHub and repository files.
- Implement workflow context and engine builders.
- Introduce major workflow packages: `game_tick_loop` and `contextual_iterative_loop`.
- Update localization files with new package descriptions and labels.
- Streamline web navigation by loading items from a dedicated JSON file.

backend/autometabuilder/web/routes/run.py

@@ -0,0 +1,19 @@
+"""Run route for triggering the bot."""
+from __future__ import annotations
+
+from flask import Blueprint, request
+
+from ..run_state import start_bot
+
+run_bp = Blueprint("run", __name__)
+
+
+@run_bp.route("/api/run", methods=["POST"])
+def api_run() -> tuple[dict[str, object], int]:
+    payload = request.get_json(silent=True) or {}
+    mode = payload.get("mode", "once")
+    iterations = int(payload.get("iterations", 1))
+    yolo = bool(payload.get("yolo", True))
+    stop_at_mvp = bool(payload.get("stop_at_mvp", False))
+    started = start_bot(mode, iterations, yolo, stop_at_mvp)
+    return {"started": started}, 202 if started else 409