docs: plan explicit execution cleanup and reporting outcomes

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

workplans/GLAS-WP-0013-execution-outcome-evidence.md

@@ -0,0 +1,58 @@
+---
+id: GLAS-WP-0013
+type: workplan
+title: "Expose cleanup and reporting outcomes to execution consumers"
+domain: infotech
+repo: glas-harness
+status: active
+owner: codex
+topic_slug: execution-outcome-evidence
+created: "2026-09-06"
+updated: "2026-09-06"
+---
+
+# Execution outcome evidence
+
+## Priority and boundary
+
+The first real local profile remains the highest priority in GLAS-WP-0012,
+with owner activation/runtime work already registered. This plan closes the
+independent observability gaps identified in the September scope assessment.
+A failed execution can currently mask cleanup/destruction failures, while the
+caller cannot distinguish accepted, failed or disabled Hub reporting.
+
+Use additive, defaulted outcome fields on existing result models. Preserve the
+original execution failure and report secondary teardown outcomes separately.
+Expose reporting acceptance to the direct caller without recursive reporting,
+raw exception disclosure to Hub, automatic execution retries or a durable queue.
+Memory, channels, subagents and aggregate budget enforcement remain design gaps,
+not work authorized by this bounded plan. No profile readiness changes.
+
+## Record cleanup and destruction independently
+
+```task
+id: GLAS-WP-0013-T01
+status: progress
+priority: high
+```
+
+Evidence reports cleanup and sandbox destruction as not attempted, succeeded
+or failed. Preserve the original failure stage if execution already failed,
+but always expose secondary failure outcomes. Destroy is attempted even if
+cleanup raises. Successful execution becomes failed when teardown fails.
+Test normal, pre-creation refusal, startup failure and combined failure paths.
+
+## Return State Hub reporting outcome
+
+```task
+id: GLAS-WP-0013-T02
+status: todo
+priority: high
+```
+
+GatewayResult reports not requested, accepted or failed. Reporting is attempted
+once after evidence is final; no-Hub makes no request. Hub failure must not
+rerun the task or change its execution outcome. Test successful reporting,
+HTTP refusal/unavailability, disabled reporting and failure evidence redaction.
+Document that acceptance is an HTTP result, not durable audit delivery or an
+exactly-once guarantee. Run full tests and catalog validation; update SCOPE.