fix(semif): 0.1.4 — object states ending in ) ; } no longer 422 (INV-7)

SemIf's shared scorer trims one token at the state boundary. When an object
state's last value ends in ')', ';' or '}', the JSON that follows re-merges two
tokens back, so score_shared refused the request with 422. The engine now wraps
semif_phase1.shared._state_prefix to keep only the tokens the full prompts
share. Each row scores the same token sequence; only the prefill/suffix split
moves.

Startup proves the fix is in effect, not just installed (heid bug hunt SKAL,
folded). It checks that the hook is callable and is what score_shared resolves,
that an ordinary state keeps upstream's whole prefix, and that a merge-prone
state scores through the shared path.

Real tokenizer: 154 states, 23 refused before and 0 after, with no ordinary or
authored144 prefix changed. Acceptance: 144/144 parity. Shared vs direct 71/72;
the miss is a bf16 tie that flipped across a plain restart (see README).

services/semif-serve/tests/test_engine_load.py

@@ -6,6 +6,8 @@ import types
 
 import pytest
 
+from fake_tokenizer import MergeTokenizer, messages, upstream_prefix
+
 from semif_serve.config import Settings
 
 TOKEN = "t" * 40
@@ -24,6 +26,25 @@ class Model:
         yield Param(self._device)
 
 
+# The shape of SemIf's score_shared, compiled INTO the fake module so that, like the real one, it
+# resolves _state_prefix and direct_messages as module globals at call time and refuses (ValueError)
+# a prefix that is not a token-prefix of every row.
+SHARED_SRC = """
+def score_shared(model, tokenizer, rows, metadata, max_tokens=4096):
+    prefix = _state_prefix(tokenizer, rows[0]["state"])
+    for row in rows:
+        ids = tokenizer.encode(tokenizer.apply_chat_template(direct_messages(row), tokenize=False,
+                               add_generation_prompt=True, enable_thinking=False), add_special_tokens=False)
+        if not prefix or ids[:len(prefix)] != prefix:
+            raise ValueError("The fixed state prefix does not match every full prompt")
+    CALLS.append(("shared", rows[0]["state"]))
+    return [{"id": row["id"]} for row in rows], {}
+"""
+# A SemIf revision that binds the helper when score_shared is defined: the module global can be
+# replaced all day and scoring never sees it.
+SHARED_SRC_EARLY_BOUND = SHARED_SRC.replace("max_tokens=4096):", "max_tokens=4096, _state_prefix=_state_prefix):")
+
+
 @pytest.fixture
 def fakes(monkeypatch):
     calls = []
@@ -42,7 +63,7 @@ def fakes(monkeypatch):
 
     def load_causal_model(model, revision, device, dtype):
         calls.append(("load", model, revision, device, dtype))
-        return Model(state["device"]), object(), {"source": model}
+        return Model(state["device"]), MergeTokenizer(), {"source": model}
 
     def score(model, tok, row, meta, max_tokens):
         calls.append(("score", row["id"]))
@@ -52,10 +73,12 @@ def fakes(monkeypatch):
 
     core = types.ModuleType("semif_phase1.core")
     core.load_causal_model = load_causal_model
+    core.direct_messages = messages
     direct = types.ModuleType("semif_phase1.direct")
     direct.score = score
     shared = types.ModuleType("semif_phase1.shared")
-    shared.score_shared = lambda *a: ([], {})
+    shared._state_prefix, shared.direct_messages, shared.CALLS = upstream_prefix, messages, calls
+    exec(SHARED_SRC, shared.__dict__)
     pkg = types.ModuleType("semif_phase1")
     for name, mod in {"torch": torch, "semif_phase1": pkg, "semif_phase1.core": core,
                       "semif_phase1.direct": direct, "semif_phase1.shared": shared}.items():
@@ -67,7 +90,7 @@ def test_load_caps_before_the_weights_land_then_warms_up(fakes):
     from semif_serve.engine import TorchEngine
     _torch, calls, _ = fakes
     TorchEngine.load(Settings(api_token=TOKEN, vram_cap_gib=12.0))
-    assert [c[0] for c in calls] == ["cap", "load", "score"]
+    assert [c[0] for c in calls] == ["cap", "load", "score", "shared"]
     assert calls[0] == ("cap", round(12 / 96, 4))
     assert calls[2] == ("score", "semif-serve-warmup")
 
@@ -108,3 +131,77 @@ def test_the_entry_point_forces_offline_mode_before_the_engine_loads(fakes, monk
                         classmethod(lambda cls, s: seen.update(offline=os.environ.get("HF_HUB_OFFLINE")) or object()))
     main.app_from_env()
     assert seen["offline"] == "1"
+
+
+def test_load_wraps_the_upstream_state_prefix_once_even_across_reloads(fakes):
+    """INV-7: score_shared looks _state_prefix up as a module global, so the wrapper must replace
+    it there. A second load must wrap the ORIGINAL again, not stack wrapper on wrapper."""
+    import semif_phase1.shared as upstream
+    from semif_serve.engine import TorchEngine
+    for _ in range(2):
+        TorchEngine.load(Settings(api_token=TOKEN))
+        assert upstream._state_prefix is not upstream_prefix
+        assert upstream._state_prefix.semif_serve_wraps is upstream_prefix
+
+
+def test_load_fails_closed_when_the_pinned_semif_no_longer_has_the_prefix_hook(fakes, monkeypatch):
+    import semif_phase1.shared as upstream
+    from semif_serve.engine import TorchEngine
+    _torch, calls, _ = fakes
+    monkeypatch.delattr(upstream, "_state_prefix")
+    with pytest.raises(RuntimeError, match="_state_prefix"):
+        TorchEngine.load(Settings(api_token=TOKEN))
+    assert not any(c[0] == "load" for c in calls)
+
+
+def test_load_proves_the_hook_on_a_merge_prone_state_through_the_real_shared_path(fakes):
+    """Bug hunt SKAL (R2/H1, H2): existence is not effect. Startup scores one state that upstream
+    alone refuses, through score_shared itself."""
+    import semif_phase1.shared as upstream
+    from semif_serve.engine import BOUNDARY_ROW, TorchEngine
+    _torch, calls, _ = fakes
+    with pytest.raises(ValueError):                       # the probe really is merge-prone here
+        upstream.score_shared(None, MergeTokenizer(), [BOUNDARY_ROW], {})
+    TorchEngine.load(Settings(api_token=TOKEN))
+    assert ("shared", BOUNDARY_ROW["state"]) in calls
+
+
+def test_load_fails_closed_when_score_shared_binds_the_prefix_before_the_patch(fakes):
+    import semif_phase1.shared as upstream
+    from semif_serve.engine import TorchEngine
+    exec(SHARED_SRC_EARLY_BOUND, upstream.__dict__)
+    with pytest.raises(RuntimeError, match="INV-7"):
+        TorchEngine.load(Settings(api_token=TOKEN))
+
+
+def test_load_fails_closed_when_score_shared_resolves_its_globals_elsewhere(fakes):
+    import semif_phase1.shared as upstream
+    from semif_serve.engine import TorchEngine
+    _torch, calls, _ = fakes
+    elsewhere = {"_state_prefix": upstream_prefix, "direct_messages": messages, "CALLS": calls}
+    exec(SHARED_SRC, elsewhere)
+    upstream.score_shared = elsewhere["score_shared"]     # re-exported from another module
+    with pytest.raises(RuntimeError, match="INV-7"):
+        TorchEngine.load(Settings(api_token=TOKEN))
+    assert not any(c[0] == "load" for c in calls)
+
+
+def test_load_fails_closed_when_the_hook_is_not_callable(fakes, monkeypatch):
+    import semif_phase1.shared as upstream
+    from semif_serve.engine import TorchEngine
+    _torch, calls, _ = fakes
+    monkeypatch.setattr(upstream, "_state_prefix", "not a function")
+    with pytest.raises(RuntimeError, match="_state_prefix"):
+        TorchEngine.load(Settings(api_token=TOKEN))
+    assert not any(c[0] == "load" for c in calls)
+
+
+def test_load_fails_closed_when_the_wrapper_renders_the_wrong_prompt(fakes, monkeypatch):
+    """The SURVIVED row of bug hunt SKAL: a wrapper that renders nothing still yields a valid
+    (degenerate) prefix, so scoring stays correct and silently loses all sharing. Startup
+    requires the wrapper to keep upstream's whole prefix on an ordinary state."""
+    import semif_phase1.core as core
+    from semif_serve.engine import TorchEngine
+    monkeypatch.setattr(core, "direct_messages", lambda row: [])
+    with pytest.raises(RuntimeError, match="INV-7"):
+        TorchEngine.load(Settings(api_token=TOKEN))