fix(browser): add full_page parameter to browser_vision for viewport-only screenshots

gateway/platforms/whatsapp.py

@@ -379,12 +379,15 @@ async def connect(self) -> bool:
             if not (bridge_dir / "node_modules").exists():
                 print(f"[{self.name}] Installing WhatsApp bridge dependencies...")
                 try:
+                    # Read timeout from environment variable, default to 300 seconds (5 minutes)
+                    # to accommodate slower systems like Unraid NAS
+                    npm_install_timeout = int(os.environ.get("WHATSAPP_NPM_INSTALL_TIMEOUT", "300"))
                     install_result = subprocess.run(
                         ["npm", "install", "--silent"],
                         cwd=str(bridge_dir),
                         capture_output=True,
                         text=True,
-                        timeout=60,
+                        timeout=npm_install_timeout,
                     )
                     if install_result.returncode != 0:
                         print(f"[{self.name}] npm install failed: {install_result.stderr}")

tests/tools/test_browser_console.py

@@ -195,6 +195,59 @@ def test_annotate_true_adds_flag(self):
                 assert "--annotate" in cmd_args
 
 
+
+class TestBrowserVisionFullPage:
+    """browser_vision supports full_page parameter."""
+
+    def test_schema_has_full_page_param(self):
+        from tools.browser_tool import BROWSER_TOOL_SCHEMAS
+
+        schema = next(s for s in BROWSER_TOOL_SCHEMAS if s["name"] == "browser_vision")
+        props = schema["parameters"]["properties"]
+        assert "full_page" in props
+        assert props["full_page"]["type"] == "boolean"
+        assert props["full_page"]["default"] is True
+
+    def test_full_page_default_includes_full_flag(self):
+        """Default (full_page=True) includes --full in screenshot args."""
+        from tools.browser_tool import browser_vision
+
+        with (
+            patch("tools.browser_tool._run_browser_command") as mock_cmd,
+            patch("tools.browser_tool.call_llm") as mock_call_llm,
+            patch("tools.browser_tool._get_vision_model", return_value="test-model"),
+        ):
+            mock_cmd.return_value = {"success": True, "data": {}}
+            try:
+                browser_vision("test", task_id="test")
+            except Exception:
+                pass
+
+            if mock_cmd.called:
+                args = mock_cmd.call_args[0]
+                cmd_args = args[2] if len(args) > 2 else []
+                assert "--full" in cmd_args
+
+    def test_full_page_false_omits_full_flag(self):
+        """With full_page=False, screenshot command has no --full flag."""
+        from tools.browser_tool import browser_vision
+
+        with (
+            patch("tools.browser_tool._run_browser_command") as mock_cmd,
+            patch("tools.browser_tool.call_llm") as mock_call_llm,
+            patch("tools.browser_tool._get_vision_model", return_value="test-model"),
+        ):
+            mock_cmd.return_value = {"success": True, "data": {}}
+            try:
+                browser_vision("test", full_page=False, task_id="test")
+            except Exception:
+                pass
+
+            if mock_cmd.called:
+                args = mock_cmd.call_args[0]
+                cmd_args = args[2] if len(args) > 2 else []
+                assert "--full" not in cmd_args
+
 class TestBrowserVisionConfig:
     def _setup_screenshot(self, tmp_path):
         shots_dir = tmp_path / "browser_screenshots"

tests/tools/test_file_tools.py

@@ -323,4 +323,41 @@ def test_truncated_hint_with_nonzero_offset(self, mock_get):
         assert "offset=100" in raw
 
 
+class TestPatchSchema:
+    """Tests for PATCH_SCHEMA to ensure required parameters are properly declared."""
+
+    def test_patch_schema_includes_all_required_params(self):
+        """PATCH_SCHEMA should include all parameters that are conditionally required."""
+        from tools.file_tools import PATCH_SCHEMA
+
+        # Verify schema structure
+        assert "parameters" in PATCH_SCHEMA
+        assert "required" in PATCH_SCHEMA["parameters"]
+
+        # All parameters that are mode-specific should be in required list
+        required = PATCH_SCHEMA["parameters"]["required"]
+        assert "mode" in required
+        assert "path" in required
+        assert "old_string" in required
+        assert "new_string" in required
+        assert "patch" in required
+
+        # replace_all is optional (has default), so it should NOT be in required
+        assert "replace_all" not in required
+
+    def test_patch_schema_description_mentions_mode_specific_requirements(self):
+        """PATCH_SCHEMA description should explain mode-specific requirements."""
+        from tools.file_tools import PATCH_SCHEMA
+
+        description = PATCH_SCHEMA.get("description", "")
+
+        # Description should mention mode-specific requirements
+        assert "mode-specific" in description.lower() or "IMPORTANT:" in description
+
+        # Should mention both modes
+        assert "mode='replace'" in description
+        assert "mode='patch'" in description
+
+
+
 

tools/browser_tool.py

@@ -954,6 +954,11 @@ def _update_session_activity(task_id: str):
                     "type": "boolean",
                     "default": False,
                     "description": "If true, overlay numbered [N] labels on interactive elements. Each [N] maps to ref @eN for subsequent browser commands. Useful for QA and spatial reasoning about page layout."
+                },
+                "full_page": {
+                    "type": "boolean",
+                    "default": True,
+                    "description": "If true (default), capture the entire scrollable page. Set to false to capture only the current viewport — useful for long pages where full-page screenshots produce unreadable downscaled images."
                 }
             },
             "required": ["question"]
@@ -2121,7 +2126,7 @@ def browser_get_images(task_id: Optional[str] = None) -> str:
         }, ensure_ascii=False)
 
 
-def browser_vision(question: str, annotate: bool = False, task_id: Optional[str] = None) -> str:
+def browser_vision(question: str, annotate: bool = False, full_page: bool = True, task_id: Optional[str] = None) -> str:
     """
     Take a screenshot of the current page and analyze it with vision AI.
 
@@ -2136,6 +2141,7 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
     Args:
         question: What you want to know about the page visually
         annotate: If True, overlay numbered [N] labels on interactive elements
+        full_page: If True (default), capture the full scrollable page. If False, capture only the current viewport.
         task_id: Task identifier for session isolation
 
     Returns:
@@ -2164,7 +2170,8 @@ def browser_vision(question: str, annotate: bool = False, task_id: Optional[str]
         screenshot_args = []
         if annotate:
             screenshot_args.append("--annotate")
-        screenshot_args.append("--full")
+        if full_page:
+            screenshot_args.append("--full")
         screenshot_args.append(str(screenshot_path))
         result = _run_browser_command(
             effective_task_id, 
@@ -2623,7 +2630,7 @@ def check_browser_requirements() -> bool:
     name="browser_vision",
     toolset="browser",
     schema=_BROWSER_SCHEMA_MAP["browser_vision"],
-    handler=lambda args, **kw: browser_vision(question=args.get("question", ""), annotate=args.get("annotate", False), task_id=kw.get("task_id")),
+    handler=lambda args, **kw: browser_vision(question=args.get("question", ""), annotate=args.get("annotate", False), full_page=args.get("full_page", True), task_id=kw.get("task_id")),
     check_fn=check_browser_requirements,
     emoji="👁️",
 )

tools/file_tools.py

@@ -908,18 +908,18 @@ def _check_file_reqs():
 
 PATCH_SCHEMA = {
     "name": "patch",
-    "description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nReplace mode (default): find a unique string and replace it.\nPatch mode: apply V4A multi-file patches for bulk changes.",
+    "description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nIMPORTANT: Parameters are mode-specific:\n- For mode='replace': provide path, old_string, new_string (optionally replace_all)\n- For mode='patch': provide patch content",
     "parameters": {
         "type": "object",
         "properties": {
             "mode": {"type": "string", "enum": ["replace", "patch"], "description": "Edit mode: 'replace' for targeted find-and-replace, 'patch' for V4A multi-file patches", "default": "replace"},
-            "path": {"type": "string", "description": "File path to edit (required for 'replace' mode)"},
-            "old_string": {"type": "string", "description": "Text to find in the file (required for 'replace' mode). Must be unique in the file unless replace_all=true. Include enough surrounding context to ensure uniqueness."},
-            "new_string": {"type": "string", "description": "Replacement text (required for 'replace' mode). Can be empty string to delete the matched text."},
+            "path": {"type": "string", "description": "File path to edit (required when mode='replace')"},
+            "old_string": {"type": "string", "description": "Text to find in file (required when mode='replace'). Must be unique in file unless replace_all=true. Include enough surrounding context to ensure uniqueness."},
+            "new_string": {"type": "string", "description": "Replacement text (required when mode='replace'). Can be empty string to delete the matched text."},
             "replace_all": {"type": "boolean", "description": "Replace all occurrences instead of requiring a unique match (default: false)", "default": False},
-            "patch": {"type": "string", "description": "V4A format patch content (required for 'patch' mode). Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"}
+            "patch": {"type": "string", "description": "V4A format patch content (required when mode='patch'). Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"}
         },
-        "required": ["mode"]
+        "required": ["mode", "path", "old_string", "new_string", "patch"]
     }
 }