feat: expose cleanup and reporting outcomes for gateway runs

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0726e-5232-73f2-aaca-2c05ceb62efb

src/glas_harness/contract.py

@@ -216,11 +216,14 @@ class ExecutionEvidence(ContractModel):
     tool_events_count: int = Field(default=0, ge=0)
     tool_events_completeness: Literal["complete", "partial", "unavailable"] = "unavailable"
     refs: dict[str, Any] = Field(default_factory=dict)
+    session_cleanup: Literal["unknown", "not_attempted", "succeeded", "failed"] = "unknown"
+    sandbox_destroy: Literal["unknown", "not_attempted", "succeeded", "failed"] = "unknown"
 
 
 class GatewayResult(ContractModel):
     ok: bool
     evidence: ExecutionEvidence
+    hub_report_status: Literal["unknown", "not_requested", "accepted", "failed"] = "unknown"
     # Direct caller output only. gateway.py deliberately excludes these fields
     # from State Hub detail because they can contain prompts/model responses.
     tool_output: str = ""

src/glas_harness/gateway.py

@@ -110,6 +110,8 @@ def run_execution(
 
     status = None
     session = None
+    session_cleanup = "not_attempted"
+    sandbox_destroy = "not_attempted"
     try:
         try:
             manager = manager if manager is not None else SandboxManager()
@@ -198,7 +200,9 @@ def run_execution(
         if session is not None:
             try:
                 selected_rein.cleanup_session(session)
+                session_cleanup = "succeeded"
             except Exception as exc:
+                session_cleanup = "failed"
                 if outcome == "succeeded" or not error:
                     outcome = "failed"
                     failure_stage = "teardown"
@@ -206,7 +210,9 @@ def run_execution(
         if status is not None:
             try:
                 manager.destroy(status.sandbox_id)
+                sandbox_destroy = "succeeded"
             except Exception as exc:
+                sandbox_destroy = "failed"
                 if outcome == "succeeded" or not error:
                     outcome = "failed"
                     failure_stage = "teardown"
@@ -226,6 +232,8 @@ def run_execution(
         tool_result=tool_result,
         summary=summary,
         refs=refs,
+        session_cleanup=session_cleanup,
+        sandbox_destroy=sandbox_destroy,
     )
     _report(request, result)
     return result
@@ -282,6 +290,8 @@ def _build_result(
     tool_result: ToolResult | None,
     summary: ExecutionSummary | None,
     refs: dict,
+    session_cleanup: str = "not_attempted",
+    sandbox_destroy: str = "not_attempted",
 ) -> GatewayResult:
     duration = max(0.0, time.monotonic() - started)
     resolved_model = (
@@ -331,6 +341,8 @@ def _build_result(
             tool_result.events_completeness if tool_result else "unavailable"
         ),
         refs=refs,
+        session_cleanup=session_cleanup,
+        sandbox_destroy=sandbox_destroy,
     )
     return GatewayResult(
         ok=outcome == "succeeded",
@@ -342,9 +354,10 @@ def _build_result(
 
 def _report(request: ExecutionRequest, result: GatewayResult) -> None:
     if not request.report_to_hub:
+        result.hub_report_status = "not_requested"
         return
     evidence = result.evidence.model_dump(mode="json", exclude_none=True)
-    hub.post_progress_event(
+    accepted = hub.post_progress_event(
         summary=(
             f"gateway run: {request.title} "
             f"({'ok' if result.ok else result.evidence.outcome})"
@@ -352,3 +365,4 @@ def _report(request: ExecutionRequest, result: GatewayResult) -> None:
         event_type="gateway_run",
         detail=evidence,
     )
+    result.hub_report_status = "accepted" if accepted else "failed"