fix: force code review lanes to be additive only, not opt-in, and bump the verifier run cap

assets/agents/review-gauntlet/scripts/build_items.py

@@ -1,14 +1,20 @@
 #!/usr/bin/env python3
 """Deterministic lane builder for the review gauntlet.
 
-Selection = hard rules (the floor) ∪ LLM additions; forced lanes override
-everything exactly. Emits one 0-or-1-item list per lane: an empty list makes
-that lane's map node run zero branches (map-over-nothing), which IS the
-skip mechanism — no dynamic routing anywhere.
+Selection = hard rules (the floor) ∪ LLM additions ∪ caller-forced lanes.
+Forcing is ADDITIVE: it can only widen the computed selection — honoring a
+forced list as the exact set once dropped the always-on code-review lane in
+a live run. Emits one 0-or-1-item list per lane: an empty list makes that
+lane's map node run zero branches (map-over-nothing), which IS the skip
+mechanism — no dynamic routing anywhere.
 
 The LLM's add_* flags can only ADD lanes. A flag that is false never
 removes a lane the hard rules selected.
 
+Unavailable diff signals (malformed spec, git failure) mean the surface is
+UNKNOWN — selection degrades WIDER (security on; probe when a recipe
+exists), never narrower.
+
 A re-run pass (retry_gate emitted `retry_lanes`) skips selection: only the
 named lanes get an item, stamped with their attempt number, and every other
 lane maps over nothing — retry_gate restores their earlier reports.
@@ -101,56 +107,90 @@ def main():
         (forced.append(canon) if canon else unknown.append(str(lane)))
 
     reasons = []
-    if forced:
-        lanes = set(forced)
-        reasons.append(f"forced lanes honored exactly: {sorted(lanes)}")
-    else:
-        lanes = {"code-review"}
+    lanes = {"code-review"}
+    reasons.append(
+        "code-review: always on — the gauntlet is only spawned for non-trivial work"
+    )
+    if text("plan_context"):
+        lanes.add("adversary")
+        reasons.append("adversary: a spec/plan/acceptance-criteria context is present")
+    if (
+        state.get("touches_auth")
+        or state.get("touches_deps")
+        or state.get("touches_exec")
+        or state.get("security_posture") == "hardened"
+    ):
+        lanes.add("security")
         reasons.append(
-            "code-review: always on — the gauntlet is only spawned for non-trivial work"
+            "security: attack-surface signals (auth/deps/exec) or hardened posture"
         )
-        if text("plan_context"):
-            lanes.add("adversary")
-            reasons.append("adversary: a spec/plan/acceptance-criteria context is present")
-        if (
-            state.get("touches_auth")
-            or state.get("touches_deps")
-            or state.get("touches_exec")
-            or state.get("security_posture") == "hardened"
-        ):
+    if state.get("consumer_surface") and text("probe_context"):
+        lanes.add("probe")
+        reasons.append(
+            "probe: consumer-facing surface changed and a local-run recipe/suite pointer exists"
+        )
+
+    # Unavailable signals (malformed diff spec, git failure) = surface UNKNOWN.
+    # Degrade WIDER, never narrower — a run without signals once silently
+    # dropped the security and probe lanes.
+    if text("signals_summary") == "signals unavailable":
+        if "security" not in lanes:
             lanes.add("security")
             reasons.append(
-                "security: attack-surface signals (auth/deps/exec) or hardened posture"
+                "security: diff signals unavailable — surface unknown, degrading wider"
             )
-        if state.get("consumer_surface") and text("probe_context"):
+        if "probe" not in lanes and text("probe_context"):
             lanes.add("probe")
             reasons.append(
-                "probe: consumer-facing surface changed and a local-run recipe/suite pointer exists"
+                "probe: diff signals unavailable and a local-run recipe/suite pointer "
+                "exists — degrading wider"
             )
 
-        # LLM judgment is additive-only.
-        llm_why = text("lane_reasons")[:300]
-        for flag, lane in (
-            ("add_code_review", "code-review"),
-            ("add_adversary", "adversary"),
-            ("add_security", "security"),
-            ("add_probe", "probe"),
-        ):
-            if state.get(flag) and lane not in lanes:
-                if lane == "probe" and not text("probe_context"):
-                    reasons.append(
-                        "probe: requested by lane judgment but skipped — no local-run "
-                        "recipe/suite pointer (a probe without one is guaranteed INCONCLUSIVE)"
-                    )
-                    continue
-                if lane == "adversary" and not text("plan_context"):
-                    reasons.append(
-                        "adversary: requested by lane judgment but skipped — no spec/plan "
-                        "to check conformance against"
-                    )
-                    continue
-                lanes.add(lane)
-                reasons.append(f"{lane}: added by lane-selection judgment — {llm_why}")
+    # LLM judgment is additive-only.
+    llm_why = text("lane_reasons")[:300]
+    for flag, lane in (
+        ("add_code_review", "code-review"),
+        ("add_adversary", "adversary"),
+        ("add_security", "security"),
+        ("add_probe", "probe"),
+    ):
+        if state.get(flag) and lane not in lanes:
+            if lane == "probe" and not text("probe_context"):
+                reasons.append(
+                    "probe: requested by lane judgment but skipped — no local-run "
+                    "recipe/suite pointer (a probe without one is guaranteed INCONCLUSIVE)"
+                )
+                continue
+            if lane == "adversary" and not text("plan_context"):
+                reasons.append(
+                    "adversary: requested by lane judgment but skipped — no spec/plan "
+                    "to check conformance against"
+                )
+                continue
+            lanes.add(lane)
+            reasons.append(f"{lane}: added by lane-selection judgment — {llm_why}")
+
+    # Caller-forced lanes are ADDITIVE: they widen the computed selection,
+    # never replace it. (Honoring them as the exact set dropped code-review —
+    # documented as always-on — and adversary in a live run.) Forcing also
+    # bypasses the context guards above: the caller demanded the lane, so it
+    # runs, with the expectation named in the summary.
+    if forced:
+        newly = sorted(set(forced) - lanes)
+        lanes |= set(forced)
+        reasons.append(
+            f"forced lanes (additive): {sorted(set(forced))}"
+            + (f" — newly added: {newly}" if newly else " — all already selected")
+        )
+        if "probe" in forced and not text("probe_context"):
+            reasons.append(
+                "probe: forced without a local-run recipe/suite pointer — expect INCONCLUSIVE"
+            )
+        if "adversary" in forced and not text("plan_context"):
+            reasons.append(
+                "adversary: forced without spec/plan context — it fails closed "
+                "(DIVERGES) without extractable criteria"
+            )
 
     if unknown:
         reasons.append(f"ignored unknown forced lane name(s): {unknown}")

assets/agents/review-gauntlet/scripts/default_lanes.py

@@ -8,8 +8,10 @@ AND a local-run recipe exists (build_items gates probe the same way — a
 probe without a recipe is INCONCLUSIVE by construction),
 plus security when the attack-surface signals (auth/deps/exec) or a hardened
 posture demand it, unioned with any lanes the caller forced (canonicalized
-with the same aliases build_items uses) — which build_items honors exactly,
-so selection degrades WIDER, never narrower. The degradation note goes into
+with the same aliases build_items uses) — which build_items honors
+ADDITIVELY, so selection degrades WIDER, never narrower. Unavailable diff
+signals also widen: unknown surface adds security (and probe when a
+local-run recipe exists). The degradation note goes into
 `lanes_degraded`; build_items folds it into lanes_summary so the final
 report names the degradation.
 
@@ -72,6 +74,11 @@ def main():
         or state.get("security_posture") == "hardened"
     ):
         lanes.add("security")
+    # Unavailable signals = surface UNKNOWN → widen (mirrors build_items).
+    if (state.get("signals_summary") or "") == "signals unavailable":
+        lanes.add("security")
+        if isinstance(probe_context, str) and probe_context.strip():
+            lanes.add("probe")
     # Caller-forced lanes survive degradation — union, never overwrite.
     for lane in state.get("forced_lanes") or []:
         if canon := ALIASES.get(str(lane).strip().lower()):

assets/agents/review-gauntlet/scripts/signals.py

@@ -3,9 +3,10 @@
 
 Pure git — no LLM judgment. Every signal is computed from the changed-file
 list and the added lines of the diff. Failures never sink the gauntlet:
-on any error the script reports `signals_error` and leaves the defaults
-(false/empty) in place, which biases lane selection toward the caller's
-context and forced lanes.
+on any error the script reports `signals_error` and marks the signals
+unavailable — downstream (build_items / default_lanes) treats that as
+UNKNOWN surface and degrades WIDER (security on; probe when a recipe
+exists), on top of caller context and forced lanes.
 """
 
 import json
@@ -26,6 +27,19 @@ proj = os.path.expanduser(
     (state.get("project_dir_in") or "").strip() or state.get("project_dir") or "."
 )
 spec = (state.get("diff_spec") or "worktree").strip()
+spec_raw = spec
+# The parse stage should emit a bare revision token, but callers write prose
+# and extraction drifts ("run get_diff --base origin/main" once reached
+# `git diff` verbatim, killing the signals — and with them the security and
+# probe lanes). Deterministically recover a usable spec before giving up.
+_TOKEN = r"[\w./~^@{}-]+"
+if spec not in ("", "worktree") and not re.fullmatch(
+    rf"{_TOKEN}(\.\.\.?{_TOKEN})?", spec
+):
+    if m := re.search(rf"({_TOKEN}\.\.\.?{_TOKEN})", spec):
+        spec = m.group(1)  # a revision range buried in prose
+    elif m := re.search(rf"--base[= ]({_TOKEN})", spec):
+        spec = f"{m.group(1)}...HEAD"  # the get_diff idiom
 
 
 def git(*args):
@@ -112,13 +126,18 @@ try:
             ),
             "docs_only": bool(files)
             and all(re.search(r"\.(md|rst|txt|adoc)$", f, re.I) for f in files),
-            "signals_summary": f"{len(files)} file(s) changed (diff: {spec})",
+            "signals_summary": f"{len(files)} file(s) changed (diff: {spec})"
+            + (f" — spec normalized from {spec_raw!r}" if spec != spec_raw else ""),
         }
     )
 except Exception as e:  # noqa: BLE001 — degraded signals must not sink the gauntlet
+    what = f"diff spec {spec!r}" + (
+        f", normalized from {spec_raw!r}" if spec != spec_raw else ""
+    )
     out["signals_error"] = (
-        f"NOTE: diff signals could not be computed ({e}); "
-        "lane selection falls back to caller context and forced lanes."
+        f"NOTE: diff signals could not be computed ({what}: {e}); surface UNKNOWN — "
+        "lane selection degrades WIDER (security lane added; probe eligible when a "
+        "local-run recipe exists), plus caller context and forced lanes."
     )
     out["signals_summary"] = "signals unavailable"