feat(vom): update vom algorithm, fix overlay problem with background state machine

crates/bsk-protocol/schema/tool_observe_params.json

@@ -0,0 +1,40 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "ObserveParams",
+  "description": "Parameters for `tool.observe` — produce a semantic VOM observation for one tab plus a fresh `@e<N>` ref-store on the extension side.\n\nUnlike `tool.snapshot`, this path may run bounded perception probes such as hover-surface discovery. It must not submit input, click, navigate, or otherwise commit page state.",
+  "type": "object",
+  "required": [
+    "session_id"
+  ],
+  "properties": {
+    "max_depth": {
+      "description": "Cap the depth of the rendered VOM tree.",
+      "type": [
+        "integer",
+        "null"
+      ],
+      "format": "uint32",
+      "minimum": 0.0
+    },
+    "max_tokens": {
+      "description": "Soft cap on rendered tokens (approximate; extension uses a best-effort heuristic based on character count).",
+      "type": [
+        "integer",
+        "null"
+      ],
+      "format": "uint32",
+      "minimum": 0.0
+    },
+    "session_id": {
+      "type": "string"
+    },
+    "tab_id": {
+      "description": "Optional target tab. Defaults to the Agent Window's currently active tab.",
+      "type": [
+        "integer",
+        "null"
+      ],
+      "format": "int64"
+    }
+  }
+}

crates/bsk-protocol/schema/tool_observe_result.json

@@ -0,0 +1,108 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "title": "ObserveResult",
+  "type": "object",
+  "required": [
+    "ref_count",
+    "tab_id",
+    "text"
+  ],
+  "properties": {
+    "dialogs": {
+      "type": "array",
+      "items": {
+        "$ref": "#/definitions/JavaScriptDialogInfo"
+      }
+    },
+    "ref_count": {
+      "description": "Number of `@e<N>` refs registered for this session by this observation. Equivalent to the size of the new ref-store map.",
+      "type": "integer",
+      "format": "uint32",
+      "minimum": 0.0
+    },
+    "tab_id": {
+      "description": "Tab the observation was computed for.",
+      "type": "integer",
+      "format": "int64"
+    },
+    "text": {
+      "description": "Semantic VOM observation text. Refs are rendered as `@e<N>` so the agent can copy them into subsequent interaction tools.",
+      "type": "string"
+    },
+    "truncated": {
+      "description": "Whether the rendered tree was truncated because of `max_depth` / `max_tokens`. Agents may re-run with looser caps.",
+      "default": false,
+      "type": "boolean"
+    }
+  },
+  "definitions": {
+    "JavaScriptDialogHandledAction": {
+      "description": "How the extension resolved the dialog so CDP could continue.",
+      "type": "string",
+      "enum": [
+        "accepted",
+        "dismissed"
+      ]
+    },
+    "JavaScriptDialogInfo": {
+      "description": "One observed + handled JavaScript dialog during a tool call.",
+      "type": "object",
+      "required": [
+        "handled",
+        "message",
+        "sequence",
+        "tab_id",
+        "type"
+      ],
+      "properties": {
+        "default_prompt": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "handled": {
+          "$ref": "#/definitions/JavaScriptDialogHandledAction"
+        },
+        "has_browser_handler": {
+          "type": [
+            "boolean",
+            "null"
+          ]
+        },
+        "message": {
+          "type": "string"
+        },
+        "sequence": {
+          "description": "Monotonic per-tab sequence for ordering within a session.",
+          "type": "integer",
+          "format": "uint64",
+          "minimum": 0.0
+        },
+        "tab_id": {
+          "type": "integer",
+          "format": "int64"
+        },
+        "type": {
+          "$ref": "#/definitions/JavaScriptDialogType"
+        },
+        "url": {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      }
+    },
+    "JavaScriptDialogType": {
+      "description": "Native JS dialog kind reported by CDP.",
+      "type": "string",
+      "enum": [
+        "alert",
+        "confirm",
+        "prompt",
+        "beforeunload"
+      ]
+    }
+  }
+}