The `agents plan apply --format json` command was returning a raw
plan dictionary instead of the spec-required JSON envelope. This fix
introduces a dedicated `_apply_output_dict()` helper that wraps the
non-rich format output in the proper envelope structure with
`command`, `status`, `exit_code`, `data`, `timing`, and `messages`
fields.

The `data` field contains structured information about artifacts,
changes, project, applied_at, validation (test/lint/type_check),
sandbox_cleanup, and lifecycle metrics. Other commands (plan status,
plan cancel, plan use) remain unaffected — they continue using
`_plan_spec_dict`.

Tests: 16 Behave scenarios + 15 Robot Framework integration tests
added covering envelope structure, field presence, sandbox cleanup
state derivation from actual plan state, legacy fallback, cost
metadata, and command isolation.

ISSUES CLOSED: #9449

@@ -0,0 +3,4 @@
+from __future__ import annotations
+
+import json
+import sys

@@ -0,0 +10,4 @@
+Envelope Has All Required Top-Level Fields
+    [Documentation]    Verify that the plan apply JSON envelope contains all required top-level keys.
+    ${result}=    Run Plan Apply Json Envelope Test    verify_top_level_fields
+    Should Be Equal As Integers    ${result.rc}    0