Add pytesseract OCR, click_text interact action, and interact verify endpoint

docs/API.md

@@ -8,9 +8,10 @@ Auth header when enabled:
 x-clickthrough-token: <token>
 ```
 
-This API is intended for AI computer control through 3 methods only:
+This API is intended for AI computer control through these methods:
 - `see`
 - `interact`
+- `interact/verify`
 - `exec`
 
 All responses use one envelope.
@@ -62,7 +63,11 @@ Capture a full screen or a region. Optional grid overlay returns coordinate meta
   "grid_cols": 12,
   "include_labels": true,
   "image_format": "png",
-  "jpeg_quality": 85
+  "jpeg_quality": 85,
+  "ocr": false,
+  "ocr_min_confidence": 0,
+  "ocr_lang": "eng",
+  "ocr_psm": null
 }
 ```
 
@@ -70,6 +75,14 @@ Returns:
 - `data.image.base64`
 - `data.meta.region` (global desktop coords)
 - `data.meta.grid` (rows/cols/cell size + formula)
+- `data.meta.ocr` (when `ocr=true`)
+
+OCR item shape:
+- `text`
+- `confidence`
+- `bbox` (global coords)
+- `center`
+- `region_relative_bbox`
 
 ### `POST /see/zoom`
 Capture a tighter crop around a global point and draw another grid over that crop.
@@ -126,12 +139,83 @@ Supported actions:
 - `scroll` (`scroll_amount`)
 - `type` (`text`, `interval_ms`)
 - `hotkey` (`keys`)
+- `click_text` (OCR-driven text click with optional region)
 
 Target modes:
 - `pixel`: absolute global `x,y`
 - `grid`: grid cell from a `see`/`see/zoom` response
 
-## 3) Exec
+### `click_text` example (full screen OCR)
+```json
+{
+  "screen": 0,
+  "action": {
+    "action": "click_text",
+    "click_text": {
+      "text": "Sign in",
+      "match": "contains",
+      "case_sensitive": false,
+      "min_confidence": 45,
+      "occurrence": "best"
+    }
+  }
+}
+```
+
+### `click_text` example (region OCR)
+```json
+{
+  "screen": 0,
+  "action": {
+    "action": "click_text",
+    "click_text": {
+      "text": "Continue",
+      "match": "exact",
+      "region": { "x": 940, "y": 520, "width": 400, "height": 260 },
+      "occurrence": "first"
+    }
+  }
+}
+```
+
+## 3) Interact Verify
+
+### `POST /interact/verify`
+Execute one interact action, then poll quick OCR verification checks until success or timeout.
+
+```json
+{
+  "action": {
+    "screen": 0,
+    "action": {
+      "action": "click_text",
+      "click_text": {
+        "text": "Apply",
+        "match": "contains"
+      }
+    }
+  },
+  "verify": {
+    "type": "ocr_text_near_point",
+    "text": "Applied",
+    "x": 1180,
+    "y": 640,
+    "radius": 120,
+    "screen": 0,
+    "match": "contains"
+  },
+  "check_interval_ms": 250,
+  "timeout_ms": 3000
+}
+```
+
+Response includes:
+- `action_result`
+- `verified`
+- `attempts`
+- `last_check`
+- `duration_ms`
+## 4) Exec
 
 ### `POST /exec`
 Run host shell commands (PowerShell/Bash/CMD).