@@ -2,6 +2,15 @@
 
 <!-- version list -->
 
+## v8.11.0 (2026-10-02)
+
+### Features
+
+- **evaluators**: Send authenticated execution context to runners api
+  ([#278](https://github.com/agentcontrol/agent-control/pull/278),
+  [`60814a8`](https://github.com/agentcontrol/agent-control/commit/60814a8d839cb5c50262e87ff9196e41b6e7d69a))
+
+
 ## v8.10.0 (2026-10-01)
 
 ### Features
 
@@ -1,6 +1,6 @@
 [project]
 name = "agent-control-engine"
-version = "8.10.0"
+version = "8.11.0"
 description = "Control execution engine for Agent Control"
 requires-python = ">=3.12"
 dependencies = [
 
@@ -1,6 +1,6 @@
 [project]
 name = "agent-control-evaluators"
-version = "8.10.0"
+version = "8.11.0"
 description = "Builtin evaluators for agent-control"
 readme = "README.md"
 requires-python = ">=3.12"
 
@@ -1,6 +1,6 @@
 [project]
 name = "agent-control-evaluator-budget"
-version = "8.10.0"
+version = "8.11.0"
 description = "Budget evaluator for agent-control -- cumulative LLM cost and token tracking"
 readme = "README.md"
 requires-python = ">=3.12"
 
@@ -1,6 +1,6 @@
 [project]
 name = "agent-control-evaluator-cisco"
-version = "8.10.0"
+version = "8.11.0"
 description = "Cisco AI Defense evaluator for agent-control"
 readme = "README.md"
 requires-python = ">=3.12"
 
@@ -1,6 +1,6 @@
 [project]
 name = "agent-control-evaluator-defenseclaw"
-version = "8.10.0"
+version = "8.11.0"
 description = "DefenseClaw evaluators for agent-control"
 readme = "README.md"
 requires-python = ">=3.12"
 
@@ -1,6 +1,6 @@
 [project]
 name = "agent-control-evaluator-galileo"
-version = "8.10.0"
+version = "8.11.0"
 description = "Galileo evaluators (Luna, LLM-as-judge) for agent-control"
 readme = "README.md"
 requires-python = ">=3.12"
 
@@ -229,12 +229,12 @@ class ScorerInvokeRecord(BaseModel):
 
 
 class GalileoExecutionContext(BaseModel):
-    """Authenticated identity fields required by Galileo scorer invocation."""
+    """Authenticated organization and optional identity fields for Galileo scorer invocation."""
 
     organization_id: str = Field(min_length=1)
-    user_id: str = Field(min_length=1)
-    project_id: str = Field(min_length=1)
-    run_id: str = Field(min_length=1)
+    user_id: str | None = Field(default=None, min_length=1)
+    project_id: str | None = Field(default=None, min_length=1)
+    run_id: str | None = Field(default=None, min_length=1)
 
 
 class ScorerInvokeRequest(BaseModel):
@@ -266,7 +266,10 @@ def ensure_required_values(self) -> ScorerInvokeRequest:
 
     def to_dict(self) -> JSONObject:
         """Convert to the Luna scorer invoke request shape."""
-        return self.model_dump(mode="json", exclude_none=True)
+        request = self.model_dump(mode="json", exclude_none=True)
+        if self.execution_context is not None:
+            request["execution_context"] = self.execution_context.model_dump(mode="json")
+        return request
 
 
 def _orbit_record_from_step(
 
@@ -236,38 +236,26 @@ def _execution_context_from_extensions(
         metadata = extensions.get("metadata")
         metadata_obj = metadata if isinstance(metadata, dict) else {}
         organization_id = extensions.get("namespace_key")
-        # Orbit's runtime-auth contract defines caller_id as the authenticated
-        # user ID for this flow. Keep that contract mapping inside Galileo.
+        # The runtime envelope's caller_id is supplied by the authenticated
+        # principal and is the caller identity Galileo associates with this run.
         user_id = extensions.get("caller_id")
         project_id = metadata_obj.get("project_id")
         target_type = extensions.get("target_type")
         target_id = extensions.get("target_id")
-        run_id = target_id if target_type == "log_stream" else None
-
-        missing = [
-            field
-            for field, value in (
-                ("organization_id", organization_id),
-                ("user_id", user_id),
-                ("project_id", project_id),
-                ("run_id", run_id),
-            )
-            if not isinstance(value, str) or not value
-        ]
-        if missing:
-            raise ValueError(
-                "Authenticated execution metadata is missing required fields: "
-                + ", ".join(missing)
-            )
+        run_id = (
+            target_id
+            if target_type in ("log_stream", "agent_stream")
+            and isinstance(target_id, str)
+            and target_id
+            else None
+        )
+        if not isinstance(organization_id, str) or not organization_id:
+            raise ValueError("Authenticated execution metadata is missing organization_id")
 
-        assert isinstance(organization_id, str)
-        assert isinstance(user_id, str)
-        assert isinstance(project_id, str)
-        assert isinstance(run_id, str)
         return GalileoExecutionContext(
             organization_id=organization_id,
-            user_id=user_id,
-            project_id=project_id,
+            user_id=user_id if isinstance(user_id, str) and user_id else None,
+            project_id=project_id if isinstance(project_id, str) and project_id else None,
             run_id=run_id,
         )
 
 
@@ -246,6 +246,23 @@ def test_scorer_invoke_request_serialization_keeps_legacy_record_shape(self) ->
             "config": {},
         }
 
+    def test_execution_context_serializes_missing_optional_claims_as_null(self) -> None:
+        from agent_control_evaluator_galileo.luna import ScorerInvokeInputs, ScorerInvokeRequest
+        from agent_control_evaluator_galileo.luna.client import GalileoExecutionContext
+
+        request = ScorerInvokeRequest(
+            scorer_id="scorer-123",
+            inputs=ScorerInvokeInputs(query="hello"),
+            execution_context=GalileoExecutionContext(organization_id="org-1"),
+        )
+
+        assert request.to_dict()["execution_context"] == {
+            "organization_id": "org-1",
+            "user_id": None,
+            "project_id": None,
+            "run_id": None,
+        }
+
     def test_scorer_invoke_request_rejects_unknown_config(self) -> None:
         from agent_control_evaluator_galileo.luna import (
             ScorerInvokeInputs,
@@ -1064,7 +1081,8 @@ async def test_evaluator_contextual_hook_forwards_complete_step(self) -> None:
 
     @patch.dict(os.environ, LUNA_ENV)
     @pytest.mark.asyncio
-    async def test_evaluator_consumes_verified_opaque_extensions(self) -> None:
+    @pytest.mark.parametrize("target_type", ["log_stream", "agent_stream"])
+    async def test_evaluator_consumes_verified_opaque_extensions(self, target_type: str) -> None:
         from agent_control_evaluator_galileo.luna import LunaEvaluator, ScorerInvokeResponse
         from agent_control_evaluator_galileo.luna.client import (
             GalileoExecutionContext,
@@ -1077,7 +1095,7 @@ async def test_evaluator_consumes_verified_opaque_extensions(self) -> None:
         extensions = {
             "namespace_key": "org-1",
             "caller_id": "verified-user-2",
-            "target_type": "log_stream",
+            "target_type": target_type,
             "target_id": "run-4",
             "metadata": {"project_id": "project-3"},
         }
@@ -1106,25 +1124,105 @@ async def test_evaluator_consumes_verified_opaque_extensions(self) -> None:
 
     @patch.dict(os.environ, LUNA_ENV)
     @pytest.mark.asyncio
-    async def test_evaluator_requires_authenticated_caller_id(self) -> None:
-        from agent_control_evaluator_galileo.luna import LunaEvaluator
-        from agent_control_evaluator_galileo.luna.client import GalileoLunaClient
+    async def test_evaluator_allows_missing_caller_id(self) -> None:
+        from agent_control_evaluator_galileo.luna import LunaEvaluator, ScorerInvokeResponse
+        from agent_control_evaluator_galileo.luna.client import (
+            GalileoExecutionContext,
+            GalileoLunaClient,
+        )
 
         evaluator = LunaEvaluator.from_dict({"scorer_id": "scorer-123"})
         extensions = {
             "namespace_key": "org-1",
             "target_type": "log_stream",
             "target_id": "run-4",
+            "metadata": {},
+        }
+
+        with patch.object(GalileoLunaClient, "invoke", new_callable=AsyncMock) as mock_invoke:
+            mock_invoke.return_value = ScorerInvokeResponse(score=0.8, status="success")
+            result = await evaluator.evaluate_with_extensions(
+                "selected input", Step(type="llm", name="answer", input="prompt"), extensions
+            )
+
+        assert result.error is None
+        mock_invoke.assert_awaited_once_with(
+            scorer_id="scorer-123",
+            step=Step(type="llm", name="answer", input="prompt"),
+            execution_context=GalileoExecutionContext(
+                organization_id="org-1",
+                user_id=None,
+                project_id=None,
+                run_id="run-4",
+            ),
+            input="selected input",
+            output=None,
+            config=None,
+            timeout=10.0,
+        )
+
+    @patch.dict(os.environ, LUNA_ENV)
+    @pytest.mark.asyncio
+    async def test_evaluator_omits_run_id_for_unsupported_target_type(self) -> None:
+        from agent_control_evaluator_galileo.luna import LunaEvaluator, ScorerInvokeResponse
+        from agent_control_evaluator_galileo.luna.client import (
+            GalileoExecutionContext,
+            GalileoLunaClient,
+        )
+
+        evaluator = LunaEvaluator.from_dict({"scorer_id": "scorer-123"})
+        extensions = {
+            "namespace_key": "org-1",
+            "caller_id": "verified-user-2",
+            "target_type": "environment",
+            "target_id": "prod",
             "metadata": {"project_id": "project-3"},
         }
 
         with patch.object(GalileoLunaClient, "invoke", new_callable=AsyncMock) as mock_invoke:
+            mock_invoke.return_value = ScorerInvokeResponse(score=0.8, status="success")
             result = await evaluator.evaluate_with_extensions(
                 "selected input", Step(type="llm", name="answer", input="prompt"), extensions
             )
 
+        assert result.error is None
+        mock_invoke.assert_awaited_once_with(
+            scorer_id="scorer-123",
+            step=Step(type="llm", name="answer", input="prompt"),
+            execution_context=GalileoExecutionContext(
+                organization_id="org-1",
+                user_id="verified-user-2",
+                project_id="project-3",
+                run_id=None,
+            ),
+            input="selected input",
+            output=None,
+            config=None,
+            timeout=10.0,
+        )
+
+    @patch.dict(os.environ, LUNA_ENV)
+    @pytest.mark.asyncio
+    async def test_evaluator_rejects_missing_organization_id(self) -> None:
+        from agent_control_evaluator_galileo.luna import LunaEvaluator
+        from agent_control_evaluator_galileo.luna.client import GalileoLunaClient
+
+        evaluator = LunaEvaluator.from_dict({"scorer_id": "scorer-123"})
+        extensions = {
+            "target_type": "log_stream",
+            "target_id": "run-4",
+            "metadata": {"project_id": "project-3"},
+        }
+
+        with patch.object(GalileoLunaClient, "invoke", new_callable=AsyncMock) as mock_invoke:
+            result = await evaluator.evaluate_with_extensions(
+                "selected input",
+                Step(type="llm", name="answer", input="prompt"),
+                extensions,
+            )
+
         assert result.error is not None
-        assert "user_id" in result.error
+        assert "organization_id" in result.error
         mock_invoke.assert_not_called()
 
     @patch.dict(os.environ, LUNA_ENV)