feat: add shared test acceptance and release 1.5.0

mcp_server/tools/task_manager.py

@@ -271,7 +271,9 @@ def mobile_manage_task(
       setups), `task_desc`, `model`, `elapsed_seconds`, a `test_summary` (when
       the run declared verification check items: machine-readable
       passed/failed/inconclusive/unchecked counts plus failed-item details —
-      no need to parse report prose), and `progress` (Flash:
+      no need to parse report prose), `test_result` (Flash and Pro: status
+      passed/failed/inconclusive/blocked, reason and evidence; completed only
+      means execution ended), and `progress` (Flash:
       current turn, latest thought/action — intervene if turns climb without
       progress or the thought indicates it is stuck; Pro: the active task plan
       — check it still aligns with your goal).
@@ -419,11 +421,23 @@ def mobile_manage_task(
                         "task_status": run_outcome.get("task_status"),
                         **tests,
                     }
+                    from artemis.runtime.case_result import resolve_case_result
+
+                    test_result = resolve_case_result(
+                        run_outcome, current_status, response.get("error") or ""
+                    )
+                    response["test_result"] = test_result.model_dump() if test_result else None
                 except (OSError, ValueError, TypeError):
                     # Unreadable or malformed run_outcome.json: omit the summary.
                     pass
                 break
 
+        if "test_result" not in response:
+            from artemis.runtime.case_result import resolve_case_result
+
+            test_result = resolve_case_result(None, current_status, response.get("error") or "")
+            response["test_result"] = test_result.model_dump() if test_result else None
+
         if current_status in ("running", "pending", "task_paused", "resuming") and is_alive:
             progress: dict[str, Any] = {}
 

mcp_server/tools/task_runner.py

@@ -279,7 +279,9 @@ def mobile_run_task(
       UI path. No step cap by default (history is compressed, and the agent
       can recall earlier steps and query the session recording), but no ADB
       shell, no pre-execution safety net, no persistent plan or notes, and
-      no verification or written report — unsuitable for exploration,
+      no midway checkpoints or persistent written notes. An exit-only read-only
+      Checker judges the prompt's expectations and returns test_result;
+      execution completion is separate from test pass. Unsuitable for exploration,
       multi-branch recovery, structured monitoring/polling, or tasks that
       must report back large amounts of detail.
     - **Pro**: complex, exploratory, or multi-branch tasks; continuous