diff --git a/CLAIMS.md b/CLAIMS.md
index c34774f9..7a831bf1 100644
--- a/CLAIMS.md
+++ b/CLAIMS.md
@@ -39,7 +39,7 @@ is a CI failure (`.github/workflows/lane-shas.yml`).
 | ADR-0095 | `miner_loop_closure` | Miner-sourced proposals route through single reviewed teaching path | `evals/miner_loop_closure/results/v1_dev.json` | `9f071733abe7dcacf759f928548ce738fb639af3fd6e4c621a651b306d7e77ce` |
 | ADR-0096 | `fabrication_control_summary` | Phantom endpoints / cross-pack non-bridges / sibling collapses refuse | `evals/fabrication_control/results/v1_summary.json` | `01e1b6b711141f2b4a14551d7df3ea482d8d6dd7b364a25c509f4f8d08cda8a8` |
 | ADR-0098 | `demo_composition` | Demos compose from shipped modules; no parallel mechanism | `evals/demo_composition/results/v1_dev.json` | `3a3d09f3a87462737e615c2dd3481b9e13e5ff8fadee0043c37873494ded556d` |
-| ADR-0099 | `public_demo` | Public showcase runs deterministically under 30s; all claims supported | `evals/public_demo/results/v1_dev.json` | `e323adb35ea17987991395424c603ff93bca08c11bc2713bd9f6338e86bb269f` |
+| ADR-0099 | `public_demo` | Public showcase runs deterministically under 30s; all claims supported | `evals/public_demo/results/v1_dev.json` | `2895df080b91618aefc2df407c637ff419fbb6dae33233c90262688c103411ea` |
 | ADR-0104 | `curriculum_loop_closure` | Curriculum-sourced proposals route through single reviewed teaching path | `evals/curriculum_loop_closure/results/v1_dev.json` | `b46d56b2d209172cc3ffaf3776dc8dcfe55093f13587c5cb67372be6dfa23e8d` |
 | ADR-0131 | `math_teaching_corpus_v1` | Math teaching corpus replays deterministically; all chains pass exit criterion (correct_rate=1.0, wrong=0) | `evals/math_teaching_corpus/v1/report.json` | `eaf160d145da29f9050ede8d58bf111b0f651dd40aeae9201857d0b97e014dd4` |
 | ADR-0206 | `deductive_logic_v1` | Propositional entailment scored against an independent truth-table oracle; dev+holdout+external 716/716 correct, wrong=0, refused=0 | `evals/deductive_logic/report.json` | `97a230949016e38d5e3f37a69e4245b320575ee70e5af92ff7607f7b05f74b5f` |
diff --git a/core/demos/showcase_adapters.py b/core/demos/showcase_adapters.py
index d0ae35b5..1726d3a9 100644
--- a/core/demos/showcase_adapters.py
+++ b/core/demos/showcase_adapters.py
@@ -164,7 +164,7 @@ class MultiHopTraceDemo:
             transitive_surface=True,
             composed_surface=True,
         )
-        runtime = ChatRuntime(config=config)
+        runtime = ChatRuntime(config=config, no_load_state=True)
         response = runtime.chat(self.prompt)
 
         surface = response.surface or ""
diff --git a/evals/learning_loop/run_demo.py b/evals/learning_loop/run_demo.py
index b1155b85..47eb4b57 100644
--- a/evals/learning_loop/run_demo.py
+++ b/evals/learning_loop/run_demo.py
@@ -387,7 +387,7 @@ def _scene5_replay_now_grounded(transient: Path) -> SceneResult:
         _tg._CORPUS_PATH = transient  # type: ignore[assignment]
         _tg.TEACHING_CORPORA = swapped_specs  # type: ignore[misc]
         _tg.clear_teaching_caches()
-        rt2 = ChatRuntime()
+        rt2 = ChatRuntime(no_load_state=True)
         response = rt2.chat(_DEMO_PROMPT)
     finally:
         _tg._CORPUS_PATH = real_path  # type: ignore[assignment]
@@ -440,7 +440,7 @@ def run_demo(*, emit_json: bool = False) -> dict[str, Any]:
     _VERBOSE = not emit_json
 
     active_bytes_before = _active_bytes()
-    rt = ChatRuntime()
+    rt = ChatRuntime(no_load_state=True)
     sink = _BufferSink()
     rt.attach_discovery_sink(sink)
     rt.attach_contemplation(enabled=True)
diff --git a/evals/public_demo/results/v1_dev.json b/evals/public_demo/results/v1_dev.json
index 9a3509da..9208969c 100644
--- a/evals/public_demo/results/v1_dev.json
+++ b/evals/public_demo/results/v1_dev.json
@@ -13,7 +13,7 @@
     {
       "case_id": "determinism_run_to_run_byte_equality",
       "details": {
-        "sha256": "a78769179151c9825e7989c51ae21df0172a8e2d5e8a146e766ba1f60250bb21"
+        "sha256": "86db25b63152567cd5ff685be5f0a6c90d10f423ea69f210ef9b47e36d20ceba"
       },
       "divergence": null,
       "passed": true
diff --git a/evals/public_demo/runner.py b/evals/public_demo/runner.py
index b525e42b..d3a15ccf 100644
--- a/evals/public_demo/runner.py
+++ b/evals/public_demo/runner.py
@@ -180,8 +180,16 @@ def _fail(case_id: str, divergence: str) -> dict[str, Any]:
 
 
 def run() -> dict[str, Any]:
+    import os
+
     from core.demos.showcase import run_showcase
 
+    # Hermetic lane: demos must not load the developer's lived engine_state/.
+    os.environ.setdefault(
+        "CORE_ENGINE_STATE_DIR",
+        tempfile.mkdtemp(prefix="public_demo_engine_state_"),
+    )
+
     tmp_root = Path(tempfile.mkdtemp(prefix="public_demo_lane_"))
     try:
         run_a = run_showcase(output_dir=tmp_root / "run_a")
diff --git a/evals/register_tour/run_tour.py b/evals/register_tour/run_tour.py
index f6044bfb..5c1198cf 100644
--- a/evals/register_tour/run_tour.py
+++ b/evals/register_tour/run_tour.py
@@ -92,7 +92,10 @@ def _print_header() -> None:
 
 def _run_one_register(register_id: str) -> list[dict[str, Any]]:
     """Run the prompt sequence under ``register_id`` and return per-cell records."""
-    runtime = ChatRuntime(config=RuntimeConfig(register_pack_id=register_id))
+    runtime = ChatRuntime(
+        config=RuntimeConfig(register_pack_id=register_id),
+        no_load_state=True,
+    )
     pipeline = CognitiveTurnPipeline(runtime=runtime)
     cells: list[dict[str, Any]] = []
     for prompt in _PROMPTS:
diff --git a/scripts/verify_lane_shas.py b/scripts/verify_lane_shas.py
index 5ffe78b7..81794e61 100644
--- a/scripts/verify_lane_shas.py
+++ b/scripts/verify_lane_shas.py
@@ -39,7 +39,7 @@ PINNED_SHAS: dict[str, str] = {
     "domain_contract_validation": "98ace04e3f02bbc5a8ad655bb6593c3f1ee64cb67014f1122fe6c3c85f48d22f",
     "fabrication_control_summary": "01e1b6b711141f2b4a14551d7df3ea482d8d6dd7b364a25c509f4f8d08cda8a8",
     "demo_composition": "3a3d09f3a87462737e615c2dd3481b9e13e5ff8fadee0043c37873494ded556d",
-    "public_demo": "e323adb35ea17987991395424c603ff93bca08c11bc2713bd9f6338e86bb269f",
+    "public_demo": "2895df080b91618aefc2df407c637ff419fbb6dae33233c90262688c103411ea",
     "math_teaching_corpus_v1": "eaf160d145da29f9050ede8d58bf111b0f651dd40aeae9201857d0b97e014dd4",
     "deductive_logic_v1": "97a230949016e38d5e3f37a69e4245b320575ee70e5af92ff7607f7b05f74b5f",
 }