feat: Significant code review suite rewrite with improved graph agent features

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

@@ -0,0 +1,118 @@
+#!/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.
+
+The LLM's add_* flags can only ADD lanes. A flag that is false never
+removes a lane the hard rules selected.
+"""
+
+import json
+import os
+
+def load_state():
+    if path := os.environ.get("GRAPH_STATE_FILE"):
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+state = load_state()
+
+ALIASES = {
+    "code-review": "code-review",
+    "code_review": "code-review",
+    "code-reviewer": "code-review",
+    "adversary": "adversary",
+    "adversarial": "adversary",
+    "adversarial-review": "adversary",
+    "security": "security",
+    "security-review": "security",
+    "security-reviewer": "security",
+    "probe": "probe",
+    "usage": "probe",
+    "usage-pattern": "probe",
+    "usage-pattern-testing": "probe",
+}
+
+
+def text(key):
+    v = state.get(key)
+    return v.strip() if isinstance(v, str) else ""
+
+
+forced_raw = state.get("forced_lanes") or []
+forced, unknown = [], []
+for lane in forced_raw:
+    canon = ALIASES.get(str(lane).strip().lower())
+    (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"}
+    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(
+            "security: attack-surface signals (auth/deps/exec) or hardened posture"
+        )
+    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"
+        )
+
+    # 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}")
+
+if unknown:
+    reasons.append(f"ignored unknown forced lane name(s): {unknown}")
+
+print(
+    json.dumps(
+        {
+            "code_review_items": [{"lane": "code-review"}] if "code-review" in lanes else [],
+            "adversary_items": [{"lane": "adversary"}] if "adversary" in lanes else [],
+            "security_items": [{"lane": "security"}] if "security" in lanes else [],
+            "probe_items": [{"lane": "probe"}] if "probe" in lanes else [],
+            "lanes_summary": "\n".join(f"- {r}" for r in reasons),
+        }
+    )
+)

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

@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+"""Deterministic diff signals for the review gauntlet.
+
+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.
+"""
+
+import json
+import os
+import re
+import subprocess
+
+def load_state():
+    if path := os.environ.get("GRAPH_STATE_FILE"):
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+state = load_state()
+proj = state.get("project_dir") or "."
+spec = (state.get("diff_spec") or "worktree").strip()
+
+
+def git(*args):
+    r = subprocess.run(
+        ["git", "-C", proj, *args], capture_output=True, text=True, timeout=90
+    )
+    if r.returncode != 0:
+        raise RuntimeError((r.stderr or r.stdout).strip()[:400])
+    return r.stdout
+
+
+out = {}
+try:
+    if spec in ("", "worktree"):
+        names = git("diff", "--name-only", "HEAD")
+        difftext = git("diff", "HEAD")
+    else:
+        names = git("diff", "--name-only", spec)
+        difftext = git("diff", spec)
+    files = [f.strip() for f in names.splitlines() if f.strip()]
+    added = "\n".join(
+        l for l in difftext.splitlines() if l.startswith("+") and not l.startswith("+++")
+    )
+
+    def any_path(pattern):
+        return any(re.search(pattern, f, re.I) for f in files)
+
+    out.update(
+        {
+            "changed_files": files[:200],
+            "file_count": len(files),
+            "touches_proto": any_path(r"\.proto$|buf\.(yaml|gen\.yaml)$"),
+            "touches_migrations": any_path(r"migrations?/|\.sql$"),
+            # auth(?!or) admits auth/authn/authz/oauth but not "author".
+            # Over-firing here is the safe direction: it only ADDS a lane.
+            "touches_auth": any_path(
+                r"auth(?!or)|login|logout|token|session|permission|rbac|\bacl\b|credential|secret"
+            )
+            or bool(
+                re.search(
+                    r"auth(?!or)|password|token|secret|credential|jwt|session",
+                    added,
+                    re.I,
+                )
+            ),
+            "touches_deps": any_path(
+                r"go\.(mod|sum)$|package(-lock)?\.json$|yarn\.lock$|pnpm-lock\.yaml$"
+                r"|Cargo\.(toml|lock)$|requirements[^/]*\.txt$|pyproject\.toml$"
+                r"|Gemfile(\.lock)?$|pom\.xml$|build\.gradle|composer\.(json|lock)$"
+            ),
+            "touches_exec": bool(
+                re.search(
+                    r"exec\.Command|subprocess|os/exec|Runtime\.getRuntime"
+                    r"|shell_exec|\beval\(|\bsystem\(|child_process",
+                    added,
+                )
+            ),
+            "consumer_surface": any_path(
+                r"routes?|handlers?|\bapi\b|endpoints?|\bcmd/|\bcli\b|\.proto$"
+                r"|openapi|swagger|controllers?|graphql"
+            ),
+            "docs_only": bool(files)
+            and all(re.search(r"\.(md|rst|txt|adoc)$", f, re.I) for f in files),
+            "signals_summary": f"{len(files)} file(s) changed (diff: {spec})",
+        }
+    )
+except Exception as e:  # noqa: BLE001 — degraded signals must not sink the gauntlet
+    out["signals_error"] = (
+        f"NOTE: diff signals could not be computed ({e}); "
+        "lane selection falls back to caller context and forced lanes."
+    )
+    out["signals_summary"] = "signals unavailable"
+
+print(json.dumps(out))

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

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""Deterministic verdict gate for the review gauntlet.
+
+Parses each configured lane's verdict SENTINEL with a regex — no LLM
+re-reads, no judgment. The gate's hard rules:
+
+  - a missing sentinel is a LANE FAILURE and blocks — never a pass;
+  - any 🔴 finding in the code-review report blocks regardless of the
+    lane's own verdict line;
+  - NEEDS-HUMAN without 🔴 passes but is surfaced as attention required;
+  - probe INCONCLUSIVE blocks with an ENVIRONMENT note — it is never
+    treated as PASS or FAIL (fix the environment per the plan's local-run
+    recipe, then re-run);
+  - the gate itself must never crash into a silent pass: any internal
+    error emits GAUNTLET: BLOCKED naming the error.
+"""
+
+import json
+import os
+import re
+
+def load_state():
+    if path := os.environ.get("GRAPH_STATE_FILE"):
+        with open(path) as f:
+            return json.load(f)
+    return json.loads(os.environ.get("GRAPH_STATE", "{}"))
+
+
+def main():
+    state = load_state()
+    blockers, attention, lane_lines, reports = [], [], [], []
+
+    def lane_report(key):
+        arr = state.get(key) or []
+        if not arr:
+            return None
+        item = arr[0]
+        return item if isinstance(item, str) else json.dumps(item)
+
+    def record(lane, status, detail=""):
+        lane_lines.append(f"| {lane} | {status} | {detail} |")
+
+    # --- code-review ------------------------------------------------------
+    cr = lane_report("code_review_results")
+    if cr is None:
+        record("code-review", "SKIPPED", "not selected")
+    else:
+        reports.append(("code-review", cr))
+        m = re.search(r"Verdict:\**\s*\**\s*(MERGE-READY|NEEDS-HUMAN)", cr)
+        reds = cr.count("🔴")
+        if reds:
+            blockers.append(
+                f"code-review: {reds} 🔴 CRITICAL finding(s) — fix before claiming done"
+            )
+            record("code-review", "BLOCKED", f"{reds} 🔴 finding(s)")
+        elif m and m.group(1) == "MERGE-READY":
+            record("code-review", "GREEN", "MERGE-READY")
+        elif m:
+            attention.append(
+                "code-review: NEEDS-HUMAN — see the lane report's "
+                "'Human attention required' section"
+            )
+            record("code-review", "GREEN (attention)", "NEEDS-HUMAN, no 🔴")
+        else:
+            blockers.append(
+                "code-review: no Review Verdict sentinel found — the lane failed; "
+                "a missing verdict is never a pass"
+            )
+            record("code-review", "BLOCKED", "missing verdict sentinel")
+
+    # --- adversary --------------------------------------------------------
+    adv = lane_report("adversary_results")
+    if adv is None:
+        record("adversary", "SKIPPED", "not selected")
+    else:
+        reports.append(("adversary", adv))
+        m = re.search(r"ADVERSARIAL_REVIEW:\s*(CONFORMS|DIVERGES)", adv)
+        if m and m.group(1) == "CONFORMS":
+            record("adversary", "GREEN", "CONFORMS")
+        elif m:
+            blockers.append(
+                "adversary: DIVERGES — the implementation does not conform to the plan"
+            )
+            record("adversary", "BLOCKED", "DIVERGES")
+        else:
+            blockers.append(
+                "adversary: no ADVERSARIAL_REVIEW sentinel found — lane failed; never a pass"
+            )
+            record("adversary", "BLOCKED", "missing verdict sentinel")
+
+    # --- security ---------------------------------------------------------
+    sec = lane_report("security_results")
+    if sec is None:
+        record("security", "SKIPPED", "not selected")
+    else:
+        reports.append(("security", sec))
+        m = re.search(r"SECURITY_REVIEW:\s*(PASS|FAIL)", sec)
+        if m and m.group(1) == "PASS":
+            record("security", "GREEN", "PASS")
+        elif m:
+            blockers.append("security: SECURITY_REVIEW: FAIL — exploitable finding(s)")
+            record("security", "BLOCKED", "FAIL")
+        else:
+            blockers.append(
+                "security: no SECURITY_REVIEW sentinel found — lane failed; never a pass"
+            )
+            record("security", "BLOCKED", "missing verdict sentinel")
+
+    # --- probe ------------------------------------------------------------
+    pb = lane_report("probe_results")
+    if pb is None:
+        record("probe", "SKIPPED", "not selected")
+    else:
+        reports.append(("probe", pb))
+        m = re.search(r"USAGE_PROBE:\s*(PASS|FAIL|INCONCLUSIVE)", pb)
+        if m and m.group(1) == "PASS":
+            record("probe", "GREEN", "PASS")
+        elif m and m.group(1) == "FAIL":
+            blockers.append("probe: USAGE_PROBE: FAIL — observed behavior contradicts the contract")
+            record("probe", "BLOCKED", "FAIL")
+        elif m:
+            blockers.append(
+                "probe: INCONCLUSIVE — the ENVIRONMENT could not be established; this is "
+                "not a code verdict. Follow the plan's local-run recipe to fix the "
+                "environment and re-run. INCONCLUSIVE is never treated as PASS or FAIL."
+            )
+            record("probe", "BLOCKED", "INCONCLUSIVE (environment)")
+        else:
+            blockers.append(
+                "probe: no USAGE_PROBE sentinel found — lane failed; never a pass"
+            )
+            record("probe", "BLOCKED", "missing verdict sentinel")
+
+    verdict = "BLOCKED" if blockers else "PASS"
+
+    md = "\n".join(
+        ["| lane | status | detail |", "|------|--------|--------|"] + lane_lines
+    )
+    md += "\n\n## Lane selection\n" + (state.get("lanes_summary") or "(none recorded)")
+    if blockers:
+        md += "\n\n## Blockers\n" + "\n".join(f"- {b}" for b in blockers)
+    if attention:
+        md += "\n\n## Human attention required\n" + "\n".join(f"- {a}" for a in attention)
+    if state.get("signals_error"):
+        md += f"\n\n> {state['signals_error']}"
+    md += "\n\n## Full lane reports\n"
+    for lane, rep in reports:
+        md += f"\n<details><summary>{lane}</summary>\n\n{rep}\n\n</details>\n"
+
+    print(json.dumps({"gauntlet_verdict": verdict, "gauntlet_report": md}))
+
+
+try:
+    main()
+except Exception as e:  # noqa: BLE001 — the gate must never crash into a silent pass
+    print(
+        json.dumps(
+            {
+                "gauntlet_verdict": "BLOCKED",
+                "gauntlet_report": f"verdict gate error: {e} — treat as a failed gate, not a pass.",
+            }
+        )
+    )