Implement refinement hardening workplan

tests/fixtures/evaluation-scenarios.json

@@ -0,0 +1,170 @@
+{
+  "schema_version": "phase_memory.evaluation_scenarios.v1",
+  "scenarios": [
+    {
+      "id": "policy-denied-activation",
+      "profile": {
+        "schema_version": "markitect.memory.profile.v1",
+        "id": "eval-policy-profile",
+        "memory_kinds": ["knowledge", "decision"],
+        "activation": {"max_items": 4, "max_tokens": 60},
+        "policy": {"mode": "allow-all", "trust_zone_labels": ["local"]},
+        "observability": {"audit_sink": "recording"}
+      },
+      "graph": {
+        "schema_version": "markitect.memory.graph.v1",
+        "id": "eval-policy-graph",
+        "nodes": [
+          {
+            "id": "policy.public",
+            "kind": "knowledge",
+            "text": "Public operating constraint that can be activated for local planning.",
+            "phase": "stabilized",
+            "policy": {"labels": ["public"], "trust_zone": "local"},
+            "source_spans": [{"path": "policy.md", "line_start": 1}],
+            "metadata": {"graph_id": "eval-policy-graph"}
+          },
+          {
+            "id": "policy.secret",
+            "kind": "knowledge",
+            "text": "Sensitive credential note that must not enter restart context.",
+            "phase": "stabilized",
+            "policy": {"labels": ["restricted"], "trust_zone": "local", "secret": true},
+            "metadata": {"graph_id": "eval-policy-graph"}
+          }
+        ],
+        "edges": [
+          {
+            "id": "edge.policy",
+            "kind": "references",
+            "source": "policy.public",
+            "target": "policy.secret"
+          }
+        ],
+        "events": []
+      },
+      "expect": {"denied_node_ids": ["policy.secret"]}
+    },
+    {
+      "id": "profile-lifecycle-rules",
+      "profile": {
+        "schema_version": "markitect.memory.profile.v1",
+        "id": "eval-lifecycle-profile",
+        "memory_kinds": ["episode", "decision"],
+        "retention": {
+          "episode": {"stale_after_days": 7},
+          "decision": {"delete_after_days": 365}
+        },
+        "refresh": {"mode": "enabled"},
+        "compaction": {"node_ids": ["life.old-episode"]},
+        "metadata": {
+          "phase_transitions": [
+            {
+              "node_kind": "decision",
+              "from_phase": "fluid",
+              "to_phase": "stabilized",
+              "min_age_days": 2,
+              "reason": "decision has stabilized"
+            }
+          ]
+        }
+      },
+      "graph": {
+        "schema_version": "markitect.memory.graph.v1",
+        "id": "eval-lifecycle-graph",
+        "nodes": [
+          {
+            "id": "life.old-episode",
+            "kind": "episode",
+            "text": "An old episode ready to become stale and compacted.",
+            "phase": "fluid",
+            "freshness": {"updated_at": "2026-04-01T00:00:00+00:00", "source_digest": "old"},
+            "metadata": {"graph_id": "eval-lifecycle-graph"}
+          },
+          {
+            "id": "life.decision",
+            "kind": "decision",
+            "text": "A decision that should transition to stabilized after review.",
+            "phase": "fluid",
+            "freshness": {"updated_at": "2026-05-01T00:00:00+00:00", "source_digest": "decision-old"},
+            "metadata": {"graph_id": "eval-lifecycle-graph"}
+          }
+        ],
+        "edges": [],
+        "events": []
+      },
+      "expect": {
+        "actions": [
+          ["life.old-episode", "mark_stale"],
+          ["life.decision", "transition_phase"],
+          ["life.decision", "refresh"]
+        ],
+        "compact_source": "life.old-episode"
+      }
+    },
+    {
+      "id": "budget-path-and-semantic-hints",
+      "profile": {
+        "schema_version": "markitect.memory.profile.v1",
+        "id": "eval-budget-profile",
+        "memory_kinds": ["decision", "knowledge", "episode"],
+        "activation": {"max_items": 2, "max_tokens": 16, "semantic_index": "memory"}
+      },
+      "graph": {
+        "schema_version": "markitect.memory.graph.v1",
+        "id": "eval-budget-graph",
+        "nodes": [
+          {
+            "id": "budget.anchor",
+            "kind": "decision",
+            "text": "Restart anchor with source.",
+            "phase": "stabilized",
+            "source_spans": [{"path": "restart.md", "line_start": 3}],
+            "metadata": {"graph_id": "eval-budget-graph"}
+          },
+          {
+            "id": "budget.semantic",
+            "kind": "knowledge",
+            "text": "Semantic index hint for restart package selection.",
+            "phase": "stabilized",
+            "source_spans": [{"path": "retrieval.md", "line_start": 7}],
+            "metadata": {"graph_id": "eval-budget-graph"}
+          },
+          {
+            "id": "budget.long",
+            "kind": "episode",
+            "text": "This verbose episode is intentionally long enough to lose against the strict activation token budget pressure.",
+            "phase": "fluid",
+            "metadata": {"graph_id": "eval-budget-graph"}
+          }
+        ],
+        "edges": [
+          {
+            "id": "edge.budget",
+            "kind": "supports",
+            "source": "budget.anchor",
+            "target": "budget.semantic"
+          }
+        ],
+        "events": [
+          {
+            "id": "budget.path-event",
+            "kind": "activated",
+            "timestamp": "2026-05-18T00:00:00+00:00",
+            "activation_refs": ["activation.budget"]
+          }
+        ]
+      },
+      "path": {
+        "id": "path.budget",
+        "event_ids": ["budget.path-event"]
+      },
+      "expect": {
+        "selected_node_ids": ["budget.anchor", "budget.semantic"],
+        "omitted_node_ids": ["budget.long"],
+        "semantic_top_id": "budget.semantic",
+        "event_ids": ["budget.path-event"]
+      }
+    }
+  ]
+}