fix(skill): reconcile rebase with runner contracts

tests/unit_tests/agent/test_orchestrator_integration.py

@@ -1007,7 +1007,7 @@ class TestQueryEntrySessionQueryId:
 
     @pytest.mark.asyncio
     async def test_no_query_id_for_pure_event_first_flow(self, clean_agent_state):
-        """Pure event-first flow has query_id=None in session."""
+        """Pure event-first flow restores authorized Skill revisions without a Query."""
         from langbot.pkg.agent.runner.host_models import (
             AgentEventEnvelope,
             AgentBinding,
@@ -1018,6 +1018,8 @@ class TestQueryEntrySessionQueryId:
         )
         from langbot_plugin.api.entities.builtin.runner.input import AgentInput
         from langbot_plugin.api.entities.builtin.runner.delivery import DeliveryContext
+        from langbot.pkg.agent.runner.persistent_state_store import get_persistent_state_store
+        from langbot.pkg.provider.tools.loaders.skill import ACTIVATED_SKILL_NAMES_STATE_KEY, ACTIVATED_SKILLS_KEY
 
         db_engine = clean_agent_state
         descriptor = make_descriptor()
@@ -1030,6 +1032,10 @@ class TestQueryEntrySessionQueryId:
             ]
         )
         ap = FakeApplication(plugin_connector, db_engine)
+        revision = 'sha256:' + '1' * 64
+        ap.skill_repository = types.SimpleNamespace(
+            get_skill=AsyncMock(return_value={'name': 'demo', 'revision': revision})
+        )
 
         async def build_resource_context(execution_query):
             from langbot.pkg.provider.tools.loaders.mcp import (
@@ -1085,10 +1091,21 @@ class TestQueryEntrySessionQueryId:
                 'mcp-resource-agent-read-enabled': True,
             },
             resource_policy=ResourcePolicy(),
-            state_policy=StatePolicy(enable_state=False, state_scopes=[]),
+            state_policy=StatePolicy(enable_state=True, state_scopes=['conversation']),
             delivery_policy=DeliveryPolicy(enable_streaming=True, enable_reply=True),
         )
 
+        success, error = await get_persistent_state_store(db_engine).apply_update_from_event(
+            event.model_copy(update={'workspace_id': TEST_CONTEXT.workspace_uuid}),
+            binding,
+            descriptor,
+            'conversation',
+            ACTIVATED_SKILL_NAMES_STATE_KEY,
+            [{'name': 'demo', 'revision': revision}],
+            None,
+        )
+        assert success is True and error is None
+
         messages = [
             message
             async for message in orchestrator.run(
@@ -1114,6 +1131,7 @@ class TestQueryEntrySessionQueryId:
         assert execution_query.message_event.type == event.event_type
         assert '_host_box_scope' not in execution_query.variables
         assert execution_query.variables['_pipeline_bound_skills'] == ['demo', 'hidden']
+        assert execution_query.variables[ACTIVATED_SKILLS_KEY]['demo']['revision'] == revision
         assert execution_query.variables['_pipeline_mcp_resource_attachments'][0]['server_uuid'] == 'srv-1'
         assert execution_query.variables['_pipeline_mcp_resource_agent_read_enabled'] is True
         assert 'MCP resource context selected by LangBot host:' in plugin_connector.contexts[0]['input']['text']
@@ -1344,8 +1362,9 @@ class TestQueryEntryAdapterHostCapabilities:
         assert snapshot['conversation']['external.test_key'] == 'test_value'
 
     @pytest.mark.asyncio
-    async def test_run_from_query_restores_activated_skills_from_state(self, clean_agent_state):
-        """Persisted activated skill names are restored into the next Query run."""
+    @pytest.mark.parametrize('legacy_state', [False, True])
+    async def test_run_from_query_restores_activated_skills_from_state(self, clean_agent_state, legacy_state):
+        """Pinned revisions restore; old name-only state requires reactivation."""
         from langbot.pkg.agent.runner.persistent_state_store import get_persistent_state_store
         from langbot.pkg.provider.tools.loaders.skill import (
             ACTIVATED_SKILL_NAMES_STATE_KEY,
@@ -1363,6 +1382,10 @@ class TestQueryEntryAdapterHostCapabilities:
             ]
         )
         ap = FakeApplication(plugin_connector, db_engine)
+        revision = 'sha256:' + '1' * 64
+        ap.skill_repository = types.SimpleNamespace(
+            get_skill=AsyncMock(return_value={'name': 'demo', 'revision': revision})
+        )
         orchestrator = AgentRunOrchestrator(ap, FakeRegistry(descriptor))
         query = make_query()
 
@@ -1376,7 +1399,7 @@ class TestQueryEntryAdapterHostCapabilities:
             descriptor,
             'conversation',
             ACTIVATED_SKILL_NAMES_STATE_KEY,
-            ['demo'],
+            ['demo'] if legacy_state else [{'name': 'demo', 'revision': revision}],
             None,
         )
         assert success is True
@@ -1385,7 +1408,16 @@ class TestQueryEntryAdapterHostCapabilities:
         messages = [message async for message in orchestrator.run_from_query(query)]
 
         assert len(messages) == 1
-        assert query.variables[ACTIVATED_SKILLS_KEY]['demo']['name'] == 'demo'
+        if legacy_state:
+            assert ACTIVATED_SKILLS_KEY not in query.variables
+            assert ap.skill_repository.get_skill.await_count == 0
+            assert (
+                len([warning for warning in ap.logger.warnings if 'Legacy name-only activated Skill state' in warning])
+                == 1
+            )
+        else:
+            assert query.variables[ACTIVATED_SKILLS_KEY]['demo']['name'] == 'demo'
+            assert query.variables[ACTIVATED_SKILLS_KEY]['demo']['revision'] == revision
 
     @pytest.mark.asyncio
     async def test_event_log_and_transcript_written(self, clean_agent_state):

tests/unit_tests/api/service/test_maintenance_service.py

@@ -383,6 +383,7 @@ class TestMaintenanceServiceGetStorageAnalysis:
                 handler=plugin_handler,
             ),
             box_service=box_service,
+            skill_repository=SimpleNamespace(storage_root=Mock(return_value='/core/skills/tenants/test')),
         )
         service = MaintenanceService(ap)
         service._path_size = Mock(return_value=10)
@@ -394,12 +395,17 @@ class TestMaintenanceServiceGetStorageAnalysis:
 
         result = await service.get_storage_analysis(TEST_CONTEXT)
 
-        assert result['total_size_bytes'] == 115
+        assert result['total_size_bytes'] == 125
+        assert (
+            next(section for section in result['sections'] if section['key'] == 'skills')['path']
+            == '/core/skills/tenants/test'
+        )
         assert result['processes'][1]['directories'][0]['key'] == 'artifacts'
         assert result['processes'][2]['directories'][1]['key'] == 'mcp'
         assert result['processes'][2]['managed_processes'] == 2
         plugin_handler.get_storage_analysis.assert_awaited_once_with()
         box_service.get_storage_analysis.assert_awaited_once_with(TEST_CONTEXT)
+        ap.skill_repository.storage_root.assert_called_once_with(TEST_CONTEXT)
 
     async def test_get_storage_analysis_postgresql(self):
         """Handles PostgreSQL database type."""

tests/unit_tests/box/test_box_service.py

@@ -585,7 +585,6 @@ async def test_box_service_reconnect_restores_workspace_and_runs_cleanup(
     connector.reconnect.assert_awaited_once()
     service._ensure_default_workspace.assert_called_once()
     service._purge_attachment_dirs.assert_awaited_once()
-    app.skill_mgr.reload_skills.assert_not_awaited()
     assert service.available is True
 
 

tests/unit_tests/box/test_runner_box.py

@@ -24,7 +24,6 @@ def service():
         require_workspace_sandbox=AsyncMock(side_effect=lambda context: context),
         _action_context=lambda context: context,
         client=SimpleNamespace(get_sessions=AsyncMock(side_effect=lambda **kw: list(sessions.values()))),
-        build_skill_extra_mounts=lambda query: [],
     )
     return RunnerBoxService(box)
 

tests/unit_tests/provider/test_skill_tools.py

@@ -261,6 +261,33 @@ class TestSkillToolLoader:
     handled by SkillService via the HTTP API / web UI instead.
     """
 
+    @pytest.mark.asyncio
+    async def test_frozen_skill_source_runs_activation_without_box(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import SkillToolLoader
+        from langbot.pkg.provider.tools.toolmgr import ToolManager
+
+        skill = _make_skill_data(name='demo', instructions='Read this first')
+        ap = _make_ap()
+        ap.skill_mgr = _make_skill_manager({'demo': skill})
+        ap.skill_repository = SimpleNamespace(get_skill=AsyncMock(return_value=skill))
+        ap.box_service = SimpleNamespace(is_workspace_sandbox_available=AsyncMock(return_value=False))
+        manager = ToolManager(ap)
+        manager.skill_tool_loader = SkillToolLoader(ap)
+        query = _make_query(_execution_context=_CONTEXT)
+        source_ref = {'source': 'skill', 'source_id': None}
+
+        result = await manager.execute_func_call('activate', {'skill_name': 'demo'}, query, source_ref)
+
+        assert result['activated'] is True
+        assert result['revision'] == skill['revision']
+        assert result['capabilities']['execution_available'] is False
+        assert query.variables['_skill_execution_available'] is False
+        assert await manager.get_tool_by_source(_CONTEXT, 'activate', source_ref) is not None
+        assert await manager.get_tool_by_source(_CONTEXT, 'register_skill', source_ref) is None
+
+        ap.box_service.is_workspace_sandbox_available.return_value = True
+        assert await manager.get_tool_by_source(_CONTEXT, 'register_skill', source_ref) is not None
+
     @pytest.mark.asyncio
     async def test_activate_returns_instructions_and_registers_skill(self):
         from langbot.pkg.provider.tools.loaders.skill_authoring import (