coyote/assets/agents/review-gauntlet/graph.yaml

name: review-gauntlet
description: |
  Graph-based post-implementation review gate — "the done gate". Given a diff
  spec and the work's context (plan/acceptance criteria, rigor, security
  posture), it deterministically computes diff signals, selects the applicable
  independent review lanes — code-reviewer (always), adversary (when a
  spec/plan exists), security-reviewer (attack-surface signals), probe
  (consumer-facing surface with a local-run recipe) — runs the selected lanes
  IN PARALLEL as isolated sub-agents, and machine-parses their verdict
  sentinels into one deterministic verdict: GAUNTLET: PASS or
  GAUNTLET: BLOCKED. An orchestrator that must not claim "done" without green
  reviews spawns this once instead of judging trigger rules and parsing
  verdicts itself — the graph structure makes skipping a lane or misreading a
  verdict impossible. Invariants: lane selection can only be WIDENED by LLM
  judgment, never narrowed (deterministic rules are the floor); a missing
  verdict sentinel is a lane failure, never a pass; probe INCONCLUSIVE blocks
  with an environment note (it is never PASS or FAIL); reviewer lanes run
  verdict-independent — no cross-lane messaging.

version: '1.0'

# The limit is consulted by the SPAWNER against the child's absolute depth
# (root = 0). Deepest documented chain: architect(0) → sisyphus(1) →
# review-gauntlet(2) → code-reviewer(3) →
# {domain-reviewer(4) → file-reviewer(5) | finding-verifier(4)}.
# This agent spawns depth-3 children; 4 = one level of headroom.
max_agent_depth: 4
max_concurrent_agents: 12

variables:
  - name: project_dir
    description: Repository the change lives in; signals and every review lane run against it.
    default: '.'
  - name: verification_commands
    description: |
      JSON array of shell commands the CALLER declares for the deterministic
      run_checks stage — e.g. '["cargo test --all"]'. Never inferred from the
      prompt; empty array = none declared.
    default: '[]'

settings:
  max_loop_iterations: 10
  log_state_snapshots: true
  # A faulted lane can be re-run by retry_gate for up to 3 passes, and each
  # pass's agent node retries up to max_attempts = 2 with a fresh per-attempt
  # budget (src/graph/agent.rs retry_transient/bounded_attempt):
  # 3 passes × 2 attempts × 11400 (max lane timeout) = 68400, + 1200 margin
  # for the script stages (signals/select/build/retry gate/verdict gate)
  # = 69600; the parse and select_lanes llm nodes carry no `timeout:` and
  # are bounded by max_iterations.
  timeout: 69600

initial_state:
  diff_spec: worktree
  plan_context: ''
  rigor: production
  security_posture: standard
  probe_context: ''
  extra_context: ''
  forced_lanes: []
  changed_files: []
  file_count: 0
  signals_summary: ''
  signals_error: ''
  touches_auth: false
  touches_deps: false
  touches_exec: false
  touches_proto: false
  touches_migrations: false
  consumer_surface: false
  docs_only: false
  add_code_review: false
  add_adversary: false
  add_security: false
  add_probe: false
  lane_reasons: ''
  parse_failure: ''
  select_lanes_failure: ''
  lanes_degraded: ''
  code_review_items: []
  adversary_items: []
  security_items: []
  probe_items: []
  code_review_results: []
  adversary_results: []
  security_results: []
  probe_results: []
  lane_attempts: {}
  kept_results: {}
  retry_lanes: []
  review_incomplete: []
  gauntlet_started_at: 0
  lanes_summary: ''
  gauntlet_verdict: ''
  gauntlet_report: ''
  gauntlet_incomplete_line: ''

start: parse

nodes:
  parse:
    id: parse
    type: llm
    description: Extract the review request's facts from the spawn prompt. Extraction only — no judging, no lane selection.
    instructions: |
      You extract the facts of a review request into structured fields.
      EXTRACTION ONLY — do not decide which review lanes should run.

      - `diff_spec`: the git diff specification the caller named — a ref
        range ("main...HEAD", "HEAD~3..HEAD"), a single ref, or the literal
        "worktree" for uncommitted changes against HEAD. When the caller
        did not name one, use "worktree".
      - `project_dir_in`: the repository directory the caller named as holding
        the change (absolute path preferred); empty string when the caller
        named none.
      - `plan_context`: the plan / spec / acceptance-criteria text the
        implementation must satisfy, verbatim (or a file path the caller
        pointed at). Empty string when the caller supplied none.
      - `rigor`: poc | prototype | production. Default "production" when
        not stated.
      - `security_posture`: prototype | standard | hardened. Default
        "standard" when not stated.
      - `probe_context`: the local-run recipe and/or existing usage-suite
        pointers for black-box probing (how to boot the service, where the
        suites live). Empty string when the caller supplied none.
      - `forced_lanes`: lanes the caller explicitly demanded (verbatim
        names). Empty array = automatic selection.
      - `extra_context`: any remaining caller context reviewers should see,
        condensed.
    prompt: |
      Extract the review-request facts from this request:

      {{initial_prompt}}
    tools: []
    output_schema:
      type: object
      properties:
        diff_spec:
          type: string
        plan_context:
          type: string
        rigor:
          type: string
        security_posture:
          type: string
        probe_context:
          type: string
        forced_lanes:
          type: array
          items:
            type: string
        extra_context:
          type: string
        project_dir_in:
          type: string
      required: [diff_spec, plan_context, rigor, security_posture, probe_context, forced_lanes, extra_context, project_dir_in]
    max_iterations: 3
    max_attempts: 2
    state_updates:
      parse_failure: '{{output}}'
    fallback: parse_fault
    next: signals

  parse_fault:
    id: parse_fault
    type: script
    description: Fail-closed marker for a dead parse stage (reached only via parse's fallback) — records a PIPELINE-FAULT in signals_error and jumps straight to the verdict gate, which blocks on it. Lane item lists stay their initial [] so every lane records SKIPPED.
    script: scripts/parse_fault.py
    timeout: 30
    next: verdict_gate

  signals:
    id: signals
    type: script
    description: Deterministic diff signals — file list, attack-surface and consumer-surface indicators. Pure git; no LLM judgment.
    script: scripts/signals.py
    timeout: 120
    next: select_lanes

  select_lanes:
    id: select_lanes
    type: llm
    description: Additive-only lane judgment on top of the deterministic rules. It can WIDEN the gauntlet, never narrow it.
    instructions: |
      You look at a change's deterministic diff signals and decide whether any
      review lane the hard rules might have missed should ALSO run. You can
      only ADD lanes — the deterministic floor (enforced downstream, not by
      you) is: code-review always runs; adversary runs when a plan/spec is
      present; security runs on attack-surface signals or hardened posture;
      probe runs when consumer-facing surface changed and a local-run recipe
      exists. Setting a flag to false NEVER removes a lane the rules selected.

      Reasons to add:
      - `add_security`: the diff handles external/untrusted input, touches
        crypto/secrets handling, or changes trust boundaries in ways the
        path-based signals missed.
      - `add_adversary`: the request references behavior it must preserve or
        criteria scattered in prose that amount to a spec, even without a
        formal plan.
      - `add_probe`: the change alters observable API/CLI behavior even
        though the path signals missed it (only useful when a local-run
        recipe exists — the builder skips it otherwise, noting why).
      - `add_code_review`: always selected by the rules; flag exists only
        for forced-lane configurations.

      Put one line per added lane into `lane_reasons`. When nothing needs
      adding, all flags false and empty reasons is the correct answer.
    prompt: |
      Change signals (deterministic):
      - diff spec: {{diff_spec}}
      - files changed: {{file_count}}
      - changed files (first 200): {{changed_files}}
      - touches auth paths/content: {{touches_auth}}
      - touches dependency manifests: {{touches_deps}}
      - adds exec/shell/subprocess calls: {{touches_exec}}
      - touches protobuf/contracts: {{touches_proto}}
      - touches migrations: {{touches_migrations}}
      - consumer-facing surface paths: {{consumer_surface}}
      - docs-only diff: {{docs_only}}
      - {{signals_summary}}
      {{signals_error}}

      Caller context:
      - rigor: {{rigor}}; security posture: {{security_posture}}
      - plan/spec present: {{plan_context}}
      - probe recipe present: {{probe_context}}
      - extra: {{extra_context}}
    tools: []
    output_schema:
      type: object
      properties:
        add_code_review:
          type: boolean
        add_adversary:
          type: boolean
        add_security:
          type: boolean
        add_probe:
          type: boolean
        lane_reasons:
          type: string
      required: [add_code_review, add_adversary, add_security, add_probe, lane_reasons]
    max_iterations: 3
    max_attempts: 2
    state_updates:
      select_lanes_failure: '{{output}}'
    fallback: default_lanes
    next: build_items

  default_lanes:
    id: default_lanes
    type: script
    description: Deterministic lane-selection fallback (reached only via select_lanes' fallback) — when the additive LLM judgment dies, forces code-review + adversary, plus probe when consumer_surface AND a probe_context (local-run recipe) is present, plus security on attack-surface signals (auth/deps/exec) or hardened posture, unioned with any caller-forced lanes. Selection degrades WIDER, never narrower; the degradation note flows into lanes_summary via build_items.
    script: scripts/default_lanes.py
    timeout: 30
    next: build_items

  build_items:
    id: build_items
    type: script
    description: Deterministic lane builder — hard rules are the floor, LLM flags may only add, forced lanes override exactly. Emits one 0-or-1-item list per lane; an empty list skips that lane's map. On a re-run pass (retry_lanes non-empty) it skips selection and emits items only for those lanes, each carrying its attempt number.
    script: scripts/build_items.py
    timeout: 30
    next: [map_code_review, map_adversary, map_security, map_probe]

  map_code_review:
    id: map_code_review
    type: map
    over: '{{code_review_items}}'
    as: lane_ctx
    branch: run_code_review
    output_key: lane_out
    collect_into: code_review_results
    max_concurrency: 1
    next: retry_gate

  map_adversary:
    id: map_adversary
    type: map
    over: '{{adversary_items}}'
    as: lane_ctx
    branch: run_adversary
    output_key: lane_out
    collect_into: adversary_results
    max_concurrency: 1
    next: retry_gate

  map_security:
    id: map_security
    type: map
    over: '{{security_items}}'
    as: lane_ctx
    branch: run_security
    output_key: lane_out
    collect_into: security_results
    max_concurrency: 1
    next: retry_gate

  map_probe:
    id: map_probe
    type: map
    over: '{{probe_items}}'
    as: lane_ctx
    branch: run_probe
    output_key: lane_out
    collect_into: probe_results
    max_concurrency: 1
    next: retry_gate

  run_code_review:
    id: run_code_review
    type: agent
    description: Independent code-quality review lane.
    agent: code-reviewer
    # Exceeds the code-reviewer graph's own settings.timeout (10800) by 600 so
    # the child's graph timeout, not this lane timeout, is the binding bound.
    # NOTE: the child's own internal retry envelope (its nodes' max_attempts ×
    # timeouts) is not derived here — deliberately out of scope for this
    # change; tracked as a follow-up.
    timeout: 11400
    prompt: |
      Review the code changes in {{project_dir}} (diff: {{diff_spec}}) as an
      independent post-implementation review.

      Quality bar: rigor={{rigor}}.

      Plan / acceptance-criteria context (may be empty):
      {{plan_context}}

      {{extra_context}}

      Close your report with your Review Verdict line.
    max_attempts: 2
    state_updates:
      lane_out: '{{output}}'
    fallback: lane_fault

  run_adversary:
    id: run_adversary
    type: agent
    description: Plan-conformance review lane.
    agent: adversary
    # Exceeds the adversary graph's own settings.timeout (9000) by 600 so the
    # child's graph timeout, not this lane timeout, is the binding bound.
    # NOTE: the child's own internal retry envelope (its nodes' max_attempts ×
    # timeouts) is not derived here — deliberately out of scope for this
    # change; tracked as a follow-up.
    timeout: 9600
    inputs:
      verification_commands: '{{verification_commands}}'
    prompt: |
      Adversarial plan-conformance review in {{project_dir}}.

      The implementation to check: diff {{diff_spec}}.

      The spec / plan / acceptance criteria it must satisfy:
      {{plan_context}}

      Verification commands arrive as a structured input (the verification_commands variable), not in this prompt.

      {{extra_context}}

      Return your ADVERSARIAL_REVIEW verdict.
    max_attempts: 2
    state_updates:
      lane_out: '{{output}}'
    fallback: lane_fault

  run_security:
    id: run_security
    type: agent
    description: Security review lane.
    agent: security-reviewer
    timeout: 7200
    prompt: |
      Security review of the code changes in {{project_dir}} (diff: {{diff_spec}}).

      Security posture: {{security_posture}}.

      {{extra_context}}

      Return your SECURITY_REVIEW verdict.
    max_attempts: 2
    state_updates:
      lane_out: '{{output}}'
    fallback: lane_fault

  run_probe:
    id: run_probe
    type: agent
    description: Black-box usage-pattern verification lane.
    agent: probe
    timeout: 7200
    prompt: |
      Usage-pattern verification (black-box probe) of the changes in
      {{project_dir}} (diff: {{diff_spec}}).

      Local-run recipe / existing usage suites:
      {{probe_context}}

      Plan / acceptance-criteria context:
      {{plan_context}}

      The workspace may contain test files from an aborted earlier attempt of
      this lane; reconcile rather than duplicate.

      Derive expected behaviors from the plan/contract BEFORE reading
      implementation code, run existing suites first, then author spec-first
      tests for the uncovered delta. Return your USAGE_PROBE verdict.
    max_attempts: 2
    state_updates:
      lane_out: '{{output}}'
    fallback: lane_fault

  lane_fault:
    id: lane_fault
    type: script
    description: Fail-closed lane fault marker (reached only via the run_* lanes' fallback routes; shared across the four map branches). Normalizes the engine's "Agent node failed" text in lane_out into a PIPELINE-FAULT lane result the map collects; verdict_gate turns it into BLOCKED — a degraded lane is never a pass.
    script: scripts/lane_fault.py
    timeout: 30

  retry_gate:
    id: retry_gate
    type: script
    description: Deterministic fault-only re-run gate. Stashes every lane report that ran this pass, restores reports a re-run pass overwrote with [] (a lane not being re-run maps over nothing), classifies each lane that ran as completed / faulted / skipped, counts attempts, and routes back into build_items for faulted lanes that still have attempts left inside the wall-clock budget; otherwise it records them in review_incomplete and falls through to verdict_gate. A real verdict is never re-run, and a gate crash never retries — it records a PIPELINE-FAULT and falls through.
    script: scripts/retry_gate.py
    timeout: 30
    next: verdict_gate

  verdict_gate:
    id: verdict_gate
    type: script
    description: Deterministic sentinel parser and gate. A missing sentinel is a lane failure, never a pass; probe INCONCLUSIVE blocks with an environment note; the code-review critical count is read from render.py's summary line (raw 🔴 count if absent) and blocks regardless of the lane's own verdict line; a code-review verdict line that records the nested graph's own pipeline fault blocks as a degraded lane. Lanes retry_gate gave up on, and any pipeline-level fault, are named on a GAUNTLET_REVIEW_INCOMPLETE machine line so a caller can tell an incomplete review from a failed one.
    script: scripts/verdict_gate.py
    timeout: 60
    next: done

  done:
    id: done
    type: end
    output: |
      GAUNTLET: {{gauntlet_verdict}}{{gauntlet_incomplete_line}}

      {{gauntlet_report}}