refactor: remove verification field from responses and update related documentation

README.md

@@ -12,7 +12,6 @@ It lets an LLM use controlled local tools (screen, click, type, shell) to comple
 - Returns structured agent output as:
   - `return`: human-readable completion message
   - `data`: structured payload (for example command output)
-  - `verification`: final screen-capture metadata for completion accuracy checks
 
 ## Core Features
 
@@ -94,11 +93,7 @@ CLI JSON output includes both legacy and structured fields:
     "data": "file1.txt\nfile2.txt"
   },
   "return": "Task completed successfully",
-  "data": "file1.txt\nfile2.txt",
-  "verification": {
-    "ok": true,
-    "path": "C:/.../screens/screen_final_verification_step_003.png"
-  }
+  "data": "file1.txt\nfile2.txt"
 }
 ```
 
@@ -154,7 +149,6 @@ Each job payload includes:
 - `response.return`
 - `response.data`
 - top-level `return` and `data` aliases
-- `verification` (final screenshot path + metadata)
 
 ### Monitoring UI
 
@@ -174,7 +168,7 @@ Each job payload includes:
 - Use `click` offsets via `offset_up/down/left/right` and optional `sleep_after_seconds`.
 - When done, call:
   - `task_complete(return="...", data=...)`
-- A final verification screen capture is always taken automatically on completion.
+- Before `task_complete`, verify expected on-screen content with `see_screen` (and `enhance` if needed), and include an `observed_result` summary in `data`.
 
 `data` should contain useful structured output for the requester (text, object, list, etc.).