Agent loop state machine refactor, unified LLM interface, and UI improvements

- Rewrite agent loop as Planning→Executing(N)→Completed state machine with
  per-step context isolation to prevent token explosion
- Split tools and prompts by phase (planning vs execution)
- Add advance_step/save_memo tools for step transitions and cross-step memory
- Unify LLM interface: remove duplicate types, single chat_with_tools path
- Add UTF-8 safe truncation (truncate_str) to prevent panics on Chinese text
- Extract CreateForm component, add auto-scroll to execution log
- Add report generation with app access URL, non-blocking title generation
- Add timer system, file serving, app proxy, exec module
- Update Dockerfile with uv, deployment config

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

deploy/deployment.yaml

@@ -3,19 +3,6 @@ kind: Namespace
 metadata:
   name: tori
 ---
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: tori-data
-  namespace: tori
-spec:
-  accessModes:
-    - ReadWriteOnce
-  storageClassName: local-path
-  resources:
-    requests:
-      storage: 1Gi
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -46,8 +33,9 @@ spec:
               value: "info"
       volumes:
         - name: data
-          persistentVolumeClaim:
-            claimName: tori-data
+          hostPath:
+            path: /data/tori
+            type: DirectoryOrCreate
 ---
 apiVersion: v1
 kind: Service