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

TODO.md

@@ -26,3 +26,8 @@
 - [x] Upgrade skill with verify-before-click rules, confidence thresholds, two-phase risky actions, and Spotify playbook
 - [x] Add top-level skill section for instance setup + mini API docs
 - [x] Clarify user-owned setup responsibilities vs agent responsibilities in skill docs
+
+## Deferred Backlog
+- [ ] Higher-level task macros composed from `see` + `interact` + `interact/verify` primitives
+- [ ] Additional verify primitives beyond `ocr_text_near_point` (image-diff region, window title/process state, color/pixel checks)
+- [ ] Broader API simplification pass to reduce payload overlap and consolidate shared OCR options

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).

examples/quickstart.py

@@ -35,6 +35,50 @@ def main():
     print("region:", payload["meta"]["region"])
     print("grid:", payload["meta"].get("grid", {}))
 
+    see_ocr = requests.post(
+        f"{BASE_URL}/see",
+        headers=headers,
+        json={"screen": SCREEN, "ocr": True, "with_grid": False, "ocr_min_confidence": 40},
+        timeout=30,
+    )
+    see_ocr.raise_for_status()
+    ocr_items = see_ocr.json()["data"]["meta"].get("ocr", [])
+    print("ocr_items:", len(ocr_items))
+
+    if ocr_items:
+        label = ocr_items[0]["text"]
+        click_text = requests.post(
+            f"{BASE_URL}/interact",
+            headers=headers,
+            json={
+                "screen": SCREEN,
+                "action": {"action": "click_text", "click_text": {"text": label, "match": "exact", "occurrence": "first"}},
+            },
+            timeout=30,
+        )
+        click_text.raise_for_status()
+        click_data = click_text.json()["data"]
+        target = click_data["resolved_target"]
+        verify = requests.post(
+            f"{BASE_URL}/interact/verify",
+            headers=headers,
+            json={
+                "action": {"screen": SCREEN, "action": {"action": "click", "target": {"mode": "pixel", "x": target["x"], "y": target["y"]}}},
+                "verify": {
+                    "type": "ocr_text_near_point",
+                    "text": label,
+                    "x": target["x"],
+                    "y": target["y"],
+                    "radius": 150,
+                    "screen": SCREEN,
+                },
+                "timeout_ms": 1500,
+            },
+            timeout=30,
+        )
+        verify.raise_for_status()
+        print("verify:", verify.json()["data"]["verified"])
+
 
 if __name__ == "__main__":
     main()

server/app.py

@@ -8,13 +8,15 @@ from fastapi.exceptions import RequestValidationError
 from fastapi.responses import JSONResponse
 
 from .config import SETTINGS
-from .models import ExecRequest, InteractRequest, LaunchRequest, SeeRequest, SeeZoomRequest, WindowActionRequest, WindowQuery
+from .models import ExecRequest, InteractRequest, InteractVerifyRequest, LaunchRequest, SeeRequest, SeeZoomRequest, WindowActionRequest, WindowQuery
 from .services import (
     apply_window_action,
     capture_region_image,
     capture_screen,
     draw_grid,
     encode_image,
+    execute_and_verify,
+    extract_ocr_items,
     exec_action,
     exec_command as run_exec_command,
     get_displays,
@@ -65,7 +67,8 @@ async def _http_exception_handler(_: Request, exc: HTTPException):
     detail = exc.detail
     if isinstance(detail, dict):
         message = str(detail.get("message", "request failed"))
-        return _err("http_error", message, exc.status_code, detail)
+        code = str(detail.get("code", "http_error"))
+        return _err(code, message, exc.status_code, detail.get("details"))
     return _err("http_error", str(detail), exc.status_code)
 
 
@@ -99,6 +102,8 @@ def see(req: SeeRequest, _: None = Depends(_auth)):
     if req.with_grid:
         out_img, grid_meta = draw_grid(image, region["x"], region["y"], req.grid_rows, req.grid_cols, req.include_labels)
         meta.update(grid_meta)
+    if req.ocr:
+        meta["ocr"] = extract_ocr_items(image, region["x"], region["y"], req.ocr_min_confidence, req.ocr_lang, req.ocr_psm)
     return _ok(
         {
             "image": {
@@ -154,6 +159,11 @@ def interact(req: InteractRequest, _: None = Depends(_auth)):
     return _ok(exec_action(req.action, req.screen))
 
 
+@app.post("/interact/verify")
+def interact_verify(req: InteractVerifyRequest, _: None = Depends(_auth)):
+    return _ok(execute_and_verify(req))
+
+
 @app.get("/health")
 def health(_: None = Depends(_auth)):
     return _ok(

server/models.py

@@ -48,6 +48,7 @@ class ActionRequest(BaseModel):
         "scroll",
         "type",
         "hotkey",
+        "click_text",
     ]
     target: Optional[Target] = None
     duration_ms: int = Field(default=0, ge=0, le=20000)
@@ -58,6 +59,13 @@ class ActionRequest(BaseModel):
     keys: list[str] = Field(default_factory=list)
     interval_ms: int = Field(default=20, ge=0, le=5000)
     dry_run: bool = False
+    click_text: "ClickTextAction | None" = None
+
+    @model_validator(mode="after")
+    def _validate_click_text(self):
+        if self.action == "click_text" and self.click_text is None:
+            raise ValueError("click_text payload is required when action=click_text")
+        return self
 
 
 class ExecRequest(BaseModel):
@@ -103,6 +111,10 @@ class SeeRequest(BaseModel):
     include_labels: bool = True
     image_format: Literal["png", "jpeg"] = "png"
     jpeg_quality: int = Field(default=85, ge=1, le=100)
+    ocr: bool = False
+    ocr_min_confidence: float = Field(default=0.0, ge=0.0, le=100.0)
+    ocr_lang: str = Field(default="eng", min_length=1, max_length=64)
+    ocr_psm: int | None = Field(default=None, ge=0, le=13)
 
 
 class SeeZoomRequest(BaseModel):
@@ -122,3 +134,55 @@ class SeeZoomRequest(BaseModel):
 class InteractRequest(BaseModel):
     screen: int = 0
     action: ActionRequest
+
+
+class OCRRegion(BaseModel):
+    x: int = Field(ge=0)
+    y: int = Field(ge=0)
+    width: int = Field(gt=0)
+    height: int = Field(gt=0)
+
+
+class ClickTextAction(BaseModel):
+    text: str = Field(min_length=1, max_length=1000)
+    match: Literal["contains", "exact", "regex"] = "contains"
+    region: OCRRegion | None = None
+    screen: int | None = None
+    case_sensitive: bool = False
+    min_confidence: float = Field(default=0.0, ge=0.0, le=100.0)
+    occurrence: Literal["first", "best", "nth"] = "first"
+    nth: int | None = Field(default=None, ge=1, le=10000)
+    ocr_lang: str = Field(default="eng", min_length=1, max_length=64)
+    ocr_psm: int | None = Field(default=None, ge=0, le=13)
+
+    @model_validator(mode="after")
+    def _validate_nth(self):
+        if self.occurrence == "nth" and self.nth is None:
+            raise ValueError("nth is required when occurrence=nth")
+        if self.occurrence != "nth" and self.nth is not None:
+            raise ValueError("nth is only allowed when occurrence=nth")
+        return self
+
+
+class VerifyOCRTextNearPoint(BaseModel):
+    type: Literal["ocr_text_near_point"]
+    text: str = Field(min_length=1, max_length=1000)
+    x: int = Field(ge=0)
+    y: int = Field(ge=0)
+    radius: int = Field(default=80, ge=1, le=1000)
+    screen: int = 0
+    match: Literal["contains", "exact", "regex"] = "contains"
+    case_sensitive: bool = False
+    min_confidence: float = Field(default=0.0, ge=0.0, le=100.0)
+    ocr_lang: str = Field(default="eng", min_length=1, max_length=64)
+    ocr_psm: int | None = Field(default=None, ge=0, le=13)
+
+
+class InteractVerifyRequest(BaseModel):
+    action: InteractRequest
+    verify: VerifyOCRTextNearPoint
+    check_interval_ms: int = Field(default=250, ge=50, le=5000)
+    timeout_ms: int = Field(default=3000, ge=100, le=60000)
+
+
+ActionRequest.model_rebuild()

server/services.py

@@ -11,7 +11,22 @@ from fastapi import HTTPException
 from PIL import ImageChops, ImageStat
 
 from .config import SETTINGS
-from .models import ActionRequest, GridTarget, LaunchRequest, PixelTarget, Target, WindowActionRequest, WindowQuery
+from .models import (
+    ActionRequest,
+    ClickTextAction,
+    GridTarget,
+    InteractVerifyRequest,
+    LaunchRequest,
+    PixelTarget,
+    Target,
+    VerifyOCRTextNearPoint,
+    WindowActionRequest,
+    WindowQuery,
+)
+
+
+def api_error(status_code: int, code: str, message: str, details=None):
+    raise HTTPException(status_code=status_code, detail={"code": code, "message": message, "details": details})
 
 
 def import_capture_libs():
@@ -85,6 +100,50 @@ def capture_region_image(screen: int, region_x: int | None, region_y: int | None
     return crop, {"x": region_x, "y": region_y, "width": region_width, "height": region_height}, mon, displays, screen_selection
 
 
+def extract_ocr_items(image, origin_x: int, origin_y: int, min_confidence: float, lang: str, psm: int | None) -> list[dict]:
+    try:
+        import pytesseract
+    except Exception as exc:
+        api_error(503, "ocr_unavailable", f"pytesseract unavailable: {exc}")
+
+    config = ""
+    if psm is not None:
+        config = f"--psm {psm}"
+    try:
+        data = pytesseract.image_to_data(image, lang=lang, config=config, output_type=pytesseract.Output.DICT)
+    except Exception as exc:
+        api_error(503, "ocr_failed", f"ocr failed: {exc}")
+
+    out: list[dict] = []
+    n = len(data.get("text", []))
+    for i in range(n):
+        text = (data["text"][i] or "").strip()
+        if not text:
+            continue
+        try:
+            confidence = float(data["conf"][i])
+        except Exception:
+            continue
+        if confidence < min_confidence:
+            continue
+        left = int(data["left"][i])
+        top = int(data["top"][i])
+        width = int(data["width"][i])
+        height = int(data["height"][i])
+        bbox = {"x": origin_x + left, "y": origin_y + top, "width": width, "height": height}
+        center = {"x": bbox["x"] + (width // 2), "y": bbox["y"] + (height // 2)}
+        out.append(
+            {
+                "text": text,
+                "confidence": confidence,
+                "bbox": bbox,
+                "center": center,
+                "region_relative_bbox": {"x": left, "y": top, "width": width, "height": height},
+            }
+        )
+    return out
+
+
 def serialize_image(image, image_format: str, jpeg_quality: int) -> bytes:
     buf = io.BytesIO()
     if image_format == "jpeg":
@@ -164,6 +223,39 @@ def enforce_allowed_region(x: int, y: int):
         raise HTTPException(status_code=403, detail="point outside allowed region")
 
 
+def _text_matches(candidate: str, needle: str, mode: str, case_sensitive: bool) -> bool:
+    hay = candidate if case_sensitive else candidate.lower()
+    ndl = needle if case_sensitive else needle.lower()
+    if mode == "contains":
+        return ndl in hay
+    if mode == "exact":
+        return hay == ndl
+    flags = 0 if case_sensitive else re.IGNORECASE
+    return re.search(needle, candidate, flags=flags) is not None
+
+
+def _resolve_text_match(click_text: ClickTextAction, items: list[dict]) -> dict:
+    matches = [item for item in items if _text_matches(item["text"], click_text.text, click_text.match, click_text.case_sensitive)]
+    if not matches:
+        candidates = [item["text"] for item in sorted(items, key=lambda v: v["confidence"], reverse=True)[:8]]
+        api_error(404, "ocr_text_not_found", "no OCR text matched", {"query": click_text.text, "candidates": candidates})
+    if click_text.occurrence == "best":
+        return max(matches, key=lambda item: item["confidence"])
+    if click_text.occurrence == "nth":
+        idx = (click_text.nth or 1) - 1
+        if idx >= len(matches):
+            api_error(409, "ocr_nth_out_of_range", "requested nth match is out of range", {"match_count": len(matches), "nth": click_text.nth})
+        return matches[idx]
+    if len(matches) > 1 and click_text.match == "exact":
+        api_error(
+            409,
+            "ocr_text_ambiguous",
+            "multiple OCR entries matched",
+            {"match_count": len(matches), "candidates": [item["text"] for item in matches[:8]]},
+        )
+    return matches[0]
+
+
 def import_input_lib():
     try:
         import pyautogui
@@ -176,7 +268,10 @@ def import_input_lib():
 
 def exec_action(req: ActionRequest, screen: int = 0) -> dict:
     run_dry = SETTINGS["dry_run"] or req.dry_run
-    selected_display, _, screen_selection = select_display(screen)
+    action_screen = screen
+    if req.action == "click_text" and req.click_text and req.click_text.screen is not None:
+        action_screen = req.click_text.screen
+    selected_display, _, screen_selection = select_display(action_screen)
     pyautogui = None if run_dry else import_input_lib()
     resolved_target = None
 
@@ -191,6 +286,36 @@ def exec_action(req: ActionRequest, screen: int = 0) -> dict:
     if req.action == "scroll" and resolved_target is None:
         raise HTTPException(status_code=400, detail="target is required for scroll")
 
+    click_text_match = None
+    if req.action == "click_text":
+        if req.click_text is None:
+            api_error(400, "click_text_payload_required", "click_text payload is required")
+        region = req.click_text.region
+        img, captured_region, _, _, _ = capture_region_image(
+            action_screen,
+            None if region is None else region.x,
+            None if region is None else region.y,
+            None if region is None else region.width,
+            None if region is None else region.height,
+        )
+        items = extract_ocr_items(
+            img,
+            captured_region["x"],
+            captured_region["y"],
+            req.click_text.min_confidence,
+            req.click_text.ocr_lang,
+            req.click_text.ocr_psm,
+        )
+        matched = _resolve_text_match(req.click_text, items)
+        enforce_allowed_region(matched["center"]["x"], matched["center"]["y"])
+        click_text_match = {
+            "query": req.click_text.model_dump(),
+            "matched": matched,
+            "capture_region": captured_region,
+            "screen": screen_selection,
+        }
+        resolved_target = {"x": matched["center"]["x"], "y": matched["center"]["y"], "target_info": {"mode": "ocr_text"}}
+
     if not run_dry:
         if req.action == "move":
             pyautogui.moveTo(resolved_target["x"], resolved_target["y"], duration=duration_sec)
@@ -211,8 +336,71 @@ def exec_action(req: ActionRequest, screen: int = 0) -> dict:
             if len(req.keys) < 1:
                 raise HTTPException(status_code=400, detail="keys is required for hotkey")
             pyautogui.hotkey(*req.keys)
+        elif req.action == "click_text":
+            pyautogui.click(
+                x=resolved_target["x"],
+                y=resolved_target["y"],
+                clicks=req.clicks,
+                interval=req.interval_ms / 1000.0,
+                button=req.button,
+                duration=duration_sec,
+            )
 
-    return {"action": req.action, "executed": not run_dry, "dry_run": run_dry, "screen": screen_selection, "display": selected_display, "resolved_target": resolved_target}
+    return {
+        "action": req.action,
+        "executed": not run_dry,
+        "dry_run": run_dry,
+        "screen": screen_selection,
+        "display": selected_display,
+        "resolved_target": resolved_target,
+        "click_text_match": click_text_match,
+    }
+
+
+def _verify_ocr_text_near_point(spec: VerifyOCRTextNearPoint) -> dict:
+    radius = spec.radius
+    display, _, _ = select_display(spec.screen)
+    region_x = max(display["x"], spec.x - radius)
+    region_y = max(display["y"], spec.y - radius)
+    max_right = display["x"] + display["width"]
+    max_bottom = display["y"] + display["height"]
+    region_right = min(max_right, spec.x + radius)
+    region_bottom = min(max_bottom, spec.y + radius)
+    region_w = max(1, region_right - region_x)
+    region_h = max(1, region_bottom - region_y)
+    img, region, _, _, screen_selection = capture_region_image(spec.screen, region_x, region_y, region_w, region_h)
+    items = extract_ocr_items(img, region["x"], region["y"], spec.min_confidence, spec.ocr_lang, spec.ocr_psm)
+    matches = [item for item in items if _text_matches(item["text"], spec.text, spec.match, spec.case_sensitive)]
+    return {"ok": len(matches) > 0, "matches": matches[:8], "items_count": len(items), "screen": screen_selection, "region": region}
+
+
+def execute_and_verify(req: InteractVerifyRequest) -> dict:
+    started = time.time()
+    action_result = exec_action(req.action.action, req.action.screen)
+    attempts = 0
+    last_check = None
+    deadline = started + (req.timeout_ms / 1000.0)
+    while True:
+        attempts += 1
+        check = _verify_ocr_text_near_point(req.verify)
+        last_check = check
+        if check["ok"]:
+            return {
+                "action_result": action_result,
+                "verified": True,
+                "attempts": attempts,
+                "last_check": last_check,
+                "duration_ms": int((time.time() - started) * 1000),
+            }
+        if time.time() >= deadline:
+            return {
+                "action_result": action_result,
+                "verified": False,
+                "attempts": attempts,
+                "last_check": last_check,
+                "duration_ms": int((time.time() - started) * 1000),
+            }
+        time.sleep(req.check_interval_ms / 1000.0)
 
 
 def windows_only(feature: str):

skill/SKILL.md

@@ -5,21 +5,24 @@ description: Use 3 methods to control a computer: see (screenshot+grid), interac
 
 # Clickthrough Computer Control
 
-Use exactly 3 methods:
+Use these methods:
 - `see`
 - `interact`
+- `interact/verify`
 - `exec`
 
 ## Method 1: See
 
 Use `POST /see` to capture full screen or a region with a grid overlay.
 Use `POST /see/zoom` to capture a tighter crop with a denser grid.
+Use `POST /see` with `ocr=true` when text localization is needed.
 
 Rules:
 - Start with coarse grid (`12x12`).
 - For precision, zoom and use denser grid (`20x20` or higher).
 - Always use returned `meta.region` and `meta.grid` when computing click targets.
 - Coordinates are global desktop coordinates.
+- OCR results are in `data.meta.ocr` and include confidence, bbox, and center.
 
 ## Method 2: Interact
 
@@ -27,15 +30,26 @@ Use `POST /interact` for one action at a time.
 
 Mouse actions:
 - `move`, `click`, `right_click`, `double_click`, `middle_click`, `scroll`
+- `click_text` (OCR-driven click; optionally scope with `click_text.region`)
 
 Keyboard actions:
 - `type`, `hotkey`
 
 Rules:
 - Prefer `grid` targets derived from fresh `see`/`see/zoom` captures.
+- For text buttons/labels, prefer `click_text` and bound OCR with a region when possible.
 - Use `pixel` only when you already have reliable coordinates.
 - After each important action, call `see` again before continuing.
 
+## Method 2.5: Action Verify
+
+Use `POST /interact/verify` to execute one action and immediately validate nearby OCR text state.
+
+Rules:
+- Keep verification narrow: use `ocr_text_near_point` with a focused radius.
+- Use short intervals/timeouts for speed (`check_interval_ms` ~250, `timeout_ms` 1000-3000).
+- Prefer this over manual re-check loops when immediate confirmation is required.
+
 ## Method 3: Exec
 
 Use `POST /exec` only for shell/system tasks.
@@ -49,8 +63,8 @@ Rules:
 
 1. `see` capture.
 2. If needed, `see/zoom` refine.
-3. `interact` one step.
+3. `interact` one step (`click_text` for text UI targets).
-4. `see` verify.
+4. `interact/verify` for action->state confirmation, or `see` verify.
 5. Repeat.
 
 ## Quick Safety Rules

tests/test_ocr_and_interact.py

@@ -0,0 +1,139 @@
+import sys
+
+from PIL import Image
+from fastapi.testclient import TestClient
+
+from server import services
+from server.app import app
+from server.models import ClickTextAction
+
+
+def test_extract_ocr_items_normalization(monkeypatch):
+    class FakeOutput:
+        DICT = "DICT"
+
+    class FakeTesseract:
+        Output = FakeOutput
+
+        @staticmethod
+        def image_to_data(_image, lang, config, output_type):
+            assert lang == "eng"
+            assert output_type == "DICT"
+            return {
+                "text": ["hello", " ", "world"],
+                "conf": ["95.0", "-1", "62.5"],
+                "left": [10, 12, 40],
+                "top": [20, 25, 60],
+                "width": [30, 10, 50],
+                "height": [10, 10, 12],
+            }
+
+    monkeypatch.setitem(sys.modules, "pytesseract", FakeTesseract)
+    items = services.extract_ocr_items(Image.new("RGB", (100, 100)), origin_x=100, origin_y=200, min_confidence=60, lang="eng", psm=None)
+    assert len(items) == 2
+    assert items[0]["text"] == "hello"
+    assert items[0]["bbox"]["x"] == 110
+    assert items[0]["center"]["y"] == 225
+    assert items[1]["text"] == "world"
+
+
+def test_resolve_text_match_contains_exact_regex_and_nth():
+    items = [
+        {"text": "Save", "confidence": 70},
+        {"text": "Save as", "confidence": 96},
+        {"text": "SAVE", "confidence": 88},
+    ]
+    contains = services._resolve_text_match(ClickTextAction(text="save", match="contains", occurrence="first"), items)
+    assert contains["text"] == "Save"
+    best = services._resolve_text_match(ClickTextAction(text="save", match="contains", occurrence="best"), items)
+    assert best["text"] == "Save as"
+    exact_case = services._resolve_text_match(
+        ClickTextAction(text="SAVE", match="exact", case_sensitive=True, occurrence="first"),
+        items,
+    )
+    assert exact_case["text"] == "SAVE"
+    regex_nth = services._resolve_text_match(ClickTextAction(text="^Save", match="regex", occurrence="nth", nth=2), items)
+    assert regex_nth["text"] == "Save as"
+
+
+def test_interact_click_text_region_optional(monkeypatch):
+    monkeypatch.setattr(services, "select_display", lambda screen: ({"screen": screen}, [], {"requested": screen, "selected": screen, "fallback": False}))
+    monkeypatch.setattr(
+        services,
+        "capture_region_image",
+        lambda screen, x, y, w, h: (Image.new("RGB", (20, 20)), {"x": x or 0, "y": y or 0, "width": w or 20, "height": h or 20}, {}, [], {}),
+    )
+    monkeypatch.setattr(
+        services,
+        "extract_ocr_items",
+        lambda *args, **kwargs: [
+            {
+                "text": "Apply",
+                "confidence": 93.0,
+                "bbox": {"x": 10, "y": 20, "width": 20, "height": 10},
+                "center": {"x": 20, "y": 25},
+                "region_relative_bbox": {"x": 10, "y": 20, "width": 20, "height": 10},
+            }
+        ],
+    )
+
+    client = TestClient(app)
+    response = client.post(
+        "/interact",
+        json={"screen": 0, "action": {"action": "click_text", "dry_run": True, "click_text": {"text": "Apply", "match": "contains"}}},
+    )
+    assert response.status_code == 200
+    body = response.json()["data"]
+    assert body["resolved_target"]["x"] == 20
+    assert body["click_text_match"]["matched"]["text"] == "Apply"
+
+
+def test_see_ocr_off_on_contract(monkeypatch):
+    monkeypatch.setattr(
+        "server.app.capture_region_image",
+        lambda *args, **kwargs: (Image.new("RGB", (10, 10)), {"x": 0, "y": 0, "width": 10, "height": 10}, {"screen": 0}, [], {}),
+    )
+    monkeypatch.setattr("server.app.encode_image", lambda *args, **kwargs: "abc")
+    monkeypatch.setattr("server.app.extract_ocr_items", lambda *args, **kwargs: [{"text": "x"}])
+
+    client = TestClient(app)
+    off = client.post("/see", json={"ocr": False, "with_grid": False})
+    assert off.status_code == 200
+    assert "ocr" not in off.json()["data"]["meta"]
+    on = client.post("/see", json={"ocr": True, "with_grid": False})
+    assert on.status_code == 200
+    assert on.json()["data"]["meta"]["ocr"][0]["text"] == "x"
+
+
+def test_interact_verify_success_and_timeout(monkeypatch):
+    calls = {"n": 0}
+    monkeypatch.setattr(services, "exec_action", lambda action, screen=0: {"action": action.action, "executed": True})
+
+    def fake_verify(_spec):
+        calls["n"] += 1
+        return {"ok": calls["n"] >= 2, "matches": [], "items_count": 1, "screen": {"selected": 0}, "region": {"x": 0, "y": 0, "width": 1, "height": 1}}
+
+    monkeypatch.setattr(services, "_verify_ocr_text_near_point", fake_verify)
+    client = TestClient(app)
+    payload = {
+        "action": {"screen": 0, "action": {"action": "type", "text": "hello"}},
+        "verify": {"type": "ocr_text_near_point", "text": "hello", "x": 100, "y": 100},
+        "check_interval_ms": 10,
+        "timeout_ms": 500,
+    }
+    ok_resp = client.post("/interact/verify", json=payload)
+    assert ok_resp.status_code == 200
+    ok_data = ok_resp.json()["data"]
+    assert ok_data["verified"] is True
+    assert ok_data["attempts"] == 2
+
+    monkeypatch.setattr(
+        services,
+        "_verify_ocr_text_near_point",
+        lambda _spec: {"ok": False, "matches": [], "items_count": 0, "screen": {"selected": 0}, "region": {"x": 0, "y": 0, "width": 1, "height": 1}},
+    )
+    timeout_resp = client.post("/interact/verify", json=payload)
+    assert timeout_resp.status_code == 200
+    timeout_data = timeout_resp.json()["data"]
+    assert timeout_data["verified"] is False
+    assert timeout_data["attempts"] >= 1