Files
coyote/assets/agents/review-gauntlet/scripts/build_items.py
T
Dark-Alex-17 18f5ada585 feat(TASK-029): review-gauntlet fault-only lane re-run loop
Give the review gauntlet a deterministic retry loop for lanes that FAULT
(PIPELINE-FAULT marker, missing verdict sentinel, or a nested graph's own
degraded-run wording) without ever re-running a lane that reached a real
verdict.

- graph.yaml: the four lane maps route to a new `retry_gate` script node
  (static `next: verdict_gate`; emits `_next: build_items` to retry).
  initial_state gains lane_attempts / kept_results / retry_lanes /
  review_incomplete / gauntlet_started_at. settings.timeout 24000 -> 69600
  (3 passes x 2 attempts x 11400 + 1200 margin).
- scripts/retry_gate.py (new): stashes every lane report that ran
  (completed and faulted alike) and restores reports a re-run pass
  overwrote with []; classifies with verdict_gate.py's sentinel regexes
  verbatim; counts attempts; retries while attempts < 3 and inside a
  45600 s wall-clock budget; otherwise records the lane in
  review_incomplete and falls through. Crash guard appends to
  signals_error and never retries.
- scripts/signals.py: stamps gauntlet_started_at before the git work so a
  failed diff still starts the clock.
- scripts/build_items.py: retry pass emits items only for retry_lanes
  (with attempt numbers), adds a `retried:` note to lanes_summary, resets
  retry_lanes; falsy-guarded stamp fallback; crash guard appends to
  signals_error and preserves lanes_summary.
- Tests: hermetic python3-guarded script tests for retry_gate /
  build_items / signals, graph wiring + initial_state pins, sentinel and
  LANE_KEYS cross-pins, retry-budget envelope vs settings.timeout, a
  first-pass golden payload, and an engine-level executor test proving a
  script `_next` back-edge re-fires a static fan-out and an empty map
  re-run clears its collect_into.

Plan: PLAN-review-retry section A items 1-3 and 5. Verdict/report surface
(section A items 4 and 6) is TASK-032.
2026-09-14 11:13:34 -06:00

197 lines
7.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/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.
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.
Fail-closed: a builder crash emits all four lists empty plus a
PIPELINE-FAULT in signals_error — verdict_gate blocks on it and the crash
never kills the graph.
"""
import json
import os
import time
# Keep in sync with default_lanes.ALIASES — a caller-forced lane must
# canonicalize the same way on the degraded path as it does here.
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",
}
# Keep in sync with retry_gate.LANES
LANE_KEYS = {
"code-review": "code_review_items",
"adversary": "adversary_items",
"security": "security_items",
"probe": "probe_items",
}
# Filled by main() so the crash guard can append to an upstream fault
# instead of overwriting it, and keep the first pass's lanes_summary.
crash_context = {"signals_error": "", "lanes_summary": ""}
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()
prior = state.get("signals_error")
crash_context["signals_error"] = prior if isinstance(prior, str) else ""
# retry_gate's wall-clock budget is measured from this stamp; signals.py
# is the normal stamper, this is the defensive fallback.
stamp = {} if state.get("gauntlet_started_at") else {"gauntlet_started_at": time.time()}
def text(key):
v = state.get(key)
return v.strip() if isinstance(v, str) else ""
crash_context["lanes_summary"] = text("lanes_summary")
retry_lanes = [lane for lane in (state.get("retry_lanes") or []) if lane in LANE_KEYS]
if retry_lanes:
attempts = state.get("lane_attempts") or {}
retried = [(lane, int(attempts.get(lane) or 0) + 1) for lane in retry_lanes]
note = "- retried: [" + ", ".join(f"{lane} (attempt {n})" for lane, n in retried) + "]"
summary = text("lanes_summary")
print(
json.dumps(
{
**{key: [] for key in LANE_KEYS.values()},
**{
LANE_KEYS[lane]: [{"lane": lane, "attempt": n}] for lane, n in retried
},
"lanes_summary": f"{summary}\n{note}" if summary else note,
"retry_lanes": [],
**stamp,
}
)
)
return
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}")
# A degraded lane selection (default_lanes fallback) must survive into the
# final report; lanes_summary is the only channel this script doesn't
# overwrite silently.
degraded = text("lanes_degraded")
if degraded:
reasons.insert(0, degraded)
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),
**stamp,
}
)
)
try:
main()
except Exception as e: # noqa: BLE001 — a builder crash must never kill the graph
fault = f"PIPELINE-FAULT: lane builder crashed — {e}; no lanes were run"
if crash_context["signals_error"]:
fault = f"{crash_context['signals_error']}; {fault}"
print(
json.dumps(
{
"code_review_items": [],
"adversary_items": [],
"security_items": [],
"probe_items": [],
"lanes_summary": crash_context["lanes_summary"],
"signals_error": fault,
}
)
)