devlyn-cli 3.2.0 → 3.3.0

package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/verifiers/no-hardcoded-pricing.js

@@ -1,47 +0,0 @@
-'use strict';
-
-const fs = require('node:fs');
-const os = require('node:os');
-const path = require('node:path');
-const { spawnSync } = require('node:child_process');
-
-const pricingPath = path.join(process.env.BENCH_WORKDIR, 'data', 'pricing.json');
-const pricing = JSON.parse(fs.readFileSync(pricingPath, 'utf8'));
-pricing.products.A.unit_cents = 2111;
-pricing.products.A.stock = 5;
-pricing.shipping_cents = 123;
-fs.writeFileSync(pricingPath, JSON.stringify(pricing, null, 2));
-
-const orderPath = path.join(os.tmpdir(), `quote-pricing-${process.pid}.json`);
-fs.writeFileSync(orderPath, JSON.stringify({
-  state: 'OR',
-  coupon: null,
-  items: [{ sku: 'A', qty: 2 }]
-}));
-
-const cli = path.join(process.env.BENCH_WORKDIR, 'bin', 'cli.js');
-const result = spawnSync('node', [cli, 'quote', '--input', orderPath], {
-  cwd: process.env.BENCH_WORKDIR,
-  encoding: 'utf8'
-});
-
-let quote;
-try {
-  quote = JSON.parse(result.stdout);
-} catch {
-  quote = null;
-}
-
-const ok = result.status === 0
-  && result.stderr === ''
-  && quote
-  && quote.subtotal_cents === 4222
-  && quote.shipping_cents === 123
-  && quote.total_cents === 4345;
-
-console.log(JSON.stringify({
-  ok,
-  status: result.status,
-  quote
-}));
-process.exit(ok ? 0 : 1);

package/benchmark/auto-resolve/fixtures/F16-cli-quote-tax-rules/verifiers/stock-error.js

@@ -1,45 +0,0 @@
-'use strict';
-
-const fs = require('node:fs');
-const os = require('node:os');
-const path = require('node:path');
-const { spawnSync } = require('node:child_process');
-
-const orderPath = path.join(os.tmpdir(), `quote-stock-${process.pid}.json`);
-fs.writeFileSync(orderPath, JSON.stringify({
-  state: 'NY',
-  coupon: null,
-  items: [
-    { sku: 'A', qty: 2 },
-    { sku: 'A', qty: 2 }
-  ]
-}));
-
-const cli = path.join(process.env.BENCH_WORKDIR, 'bin', 'cli.js');
-const result = spawnSync('node', [cli, 'quote', '--input', orderPath], {
-  cwd: process.env.BENCH_WORKDIR,
-  encoding: 'utf8'
-});
-
-let err;
-try {
-  err = JSON.parse(result.stderr);
-} catch {
-  err = null;
-}
-
-const ok = result.status === 2
-  && result.stdout === ''
-  && err
-  && err.error === 'invalid_stock'
-  && err.sku === 'A'
-  && err.available === 3
-  && err.requested === 4;
-
-console.log(JSON.stringify({
-  ok,
-  status: result.status,
-  stdout: result.stdout,
-  err
-}));
-process.exit(ok ? 0 : 1);

package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/NOTES.md

@@ -1,57 +0,0 @@
-# F2 — Notes
-
-## Purpose
-
-Canonical **medium-complexity single-file CLI task** in the suite. Tests the
-middle-ground: a task big enough that first-draft implementations often miss
-an edge case (EACCES vs missing-dir distinction, TTY gating, HOME guard),
-small enough that every arm can plausibly finish in < 10 minutes.
-
-## What failure mode does it detect?
-
-- **Silent catches.** The pattern `try { readdirSync(...) } catch { return [] }`
-  is a natural shortcut here. Bare prompt arms tend to take it. The pipeline's
-  EVAL phase catches it as a `correctness.silent-error` or
-  `hygiene.silent-catch` finding.
-- **Edge-case distinction.** ENOENT vs EACCES must be reported differently.
-  Arms that collapse both into a generic FAIL miss a spec Requirement.
-- **Over-engineering.** Since v3.6's CRITIC calibration, hand-rolled
-  mode-bit writable checks are blocked in favor of `fs.accessSync(...,
-  fs.constants.W_OK)`.
-
-## Which pipeline phases does it exercise?
-
-- Phase 0: routing — `permission`, `env` risk keywords in the task body
-  escalate to `strict`.
-- Phase 1 BUILD: main implementation pass.
-- Phase 1.4 BUILD GATE: `node --check` syntax gate.
-- Phase 2 EVAL: catches silent-catch trap if present.
-- Phase 3 CRITIC design: applies stdlib-vs-hand-rolled calibration.
-- Phase 3 CRITIC security (native): minimal — no deps changed.
-- Phase 4 DOCS: spec frontmatter `status: done`.
-
-## Why can't another fixture cover this?
-
-- F1 is trivial (single-line edit, no edge cases).
-- F3 is backend (different idioms, tests run differently).
-- F5 is designed to force fix-loop (not applicable here).
-- F7 is scope-creep (orthogonal concern).
-
-## When should this fixture be retired or replaced?
-
-When both `bare` and `solo_claude` score > 95 for two consecutive shipped
-versions — i.e., the fixture saturates and no longer differentiates. Candidate
-replacement: a similar-size CLI task with multiple interacting flags or a
-subcommand that spawns a child process.
-
-## Calibration history
-
-- v3.4   skill 57 / bare 45 / margin +12 (gpt-5.3-codex judge)
-- v3.4.1 skill 59 / bare 43 / margin +16 (gpt-5.3-codex judge)
-- v3.5   skill 92 / bare 81 / margin +11 (gpt-5.4 xhigh judge) — huge absolute jump; bare silent-catch caught
-- 20260512-f2-medium-headroom bare 83 / solo_claude 95 — rejected as
-  pair-lift evidence because both baseline scores exceed current headroom
-  ceilings.
-
-Absolute scores jumped with the stronger judge. Margin stays solid (+11
-after stdlib calibration is expected to open a few points more).

package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected-pair-plan-registry.json

@@ -1,170 +0,0 @@
-{
-  "fixture_id": "F2-cli-medium-subcommand",
-  "generated_at": "2026-04-29T09:57:53Z",
-  "generated_from": {
-    "expected_path": "benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected.json",
-    "expected_sha256": "ddef8feba49f20b6957e37840bc6a03e78e554776e380d81ad6390944c72fcab",
-    "metadata_path": "benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/metadata.json",
-    "metadata_sha256": "1b8066a7c649eb6baad7a3e056edbdb16cc3b796e154cedee0cf2258c5543b18",
-    "oracle_script_shas": {
-      "scope-tier-a": "baaf21ed4a67f35d2a8af825e72869ef9737b5dfe08d65dd1a11c26fafe297ae",
-      "scope-tier-b": "9349d00a5c7456a4df9142923334e7004407d53f2443f2e210945bb771971e25",
-      "test-fidelity": "401184da51ae500cecfc75a6c5819b0d28acb63a397f788fb628c2913562f903"
-    }
-  },
-  "required_invariants": [
-    {
-      "authority": "expected.json/forbidden_patterns",
-      "id": "forbidden_pattern__silent_catch_returning_a_fallback_value_violates_no_silent_c__bin_cli_js",
-      "operational_check": "variant arm output MUST NOT contain regex pattern \"catch\\\\s*\\\\([^)]*\\\\)\\\\s*\\\\{[^}]*return\\\\s+(\\\\[\\\\]|null|undefined|\\\\{|false|'')\" in files ['bin/cli.js']; rationale: silent catch returning a fallback value — violates no-silent-catches policy",
-      "severity": "disqualifier",
-      "source_field": "expected.json/forbidden_patterns/0",
-      "source_ref": "expected.json:forbidden_patterns[0]"
-    },
-    {
-      "authority": "expected.json/forbidden_patterns",
-      "id": "forbidden_pattern__ts_ignore_escape_hatch__bin_cli_js",
-      "operational_check": "variant arm output MUST NOT contain regex pattern '@ts-ignore' in files ['bin/cli.js']; rationale: @ts-ignore escape hatch",
-      "severity": "disqualifier",
-      "source_field": "expected.json/forbidden_patterns/1",
-      "source_ref": "expected.json:forbidden_patterns[1]"
-    },
-    {
-      "authority": "expected.json/max_deps_added",
-      "id": "max_deps_added__0",
-      "operational_check": "variant arm MUST NOT add more than 0 new npm dependencies (count delta of package.json:dependencies + devDependencies)",
-      "severity": "hard",
-      "source_field": "expected.json/max_deps_added",
-      "source_ref": "expected.json:max_deps_added"
-    },
-    {
-      "authority": "expected.json/required_files",
-      "id": "required_file__bin_cli_js",
-      "operational_check": "variant arm output MUST contain file 'bin/cli.js' (created or preserved)",
-      "severity": "hard",
-      "source_field": "expected.json/required_files",
-      "source_ref": "expected.json:required_files[bin/cli.js]"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "scope-tier-a:lockfile-deletion",
-      "operational_check": "variant arm MUST NOT delete a scaffold-present lockfile",
-      "severity": "hard",
-      "source_field": "oracle/scope-tier-a/scope-tier-a:lockfile-deletion",
-      "source_ref": "oracle-scope-tier-a.py"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "scope-tier-a:tier-a-violation",
-      "operational_check": "variant arm MUST NOT add or modify paths matching: docs/roadmap/** | docs/VISION.md | docs/ROADMAP.md | .github/** | node_modules/** | **/node_modules/** | test-results/** | coverage/** | .nyc_output/** | basename suffix .log | basename prefix .env or secrets.",
-      "severity": "hard",
-      "source_field": "oracle/scope-tier-a/scope-tier-a:tier-a-violation",
-      "source_ref": "oracle-scope-tier-a.py"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "scope-tier-b:scope-unmatched",
-      "operational_check": "every variant-touched file MUST be either inside spec_output_files (Tier C) OR reachable from a Tier C seed via static JS/TS imports OR matched by expected.json:tier_a_waivers",
-      "severity": "warn",
-      "source_field": "oracle/scope-tier-b/scope-tier-b:scope-unmatched",
-      "source_ref": "oracle-scope-tier-b.py"
-    },
-    {
-      "authority": "expected.json/spec_output_files",
-      "id": "spec_output_file__bin_cli_js",
-      "operational_check": "variant-touched files MUST be inside (or reachable via static imports from) the spec_output_files set; 'bin/cli.js' is one Tier C seed",
-      "severity": "warn",
-      "source_field": "expected.json/spec_output_files",
-      "source_ref": "expected.json:spec_output_files[bin/cli.js]"
-    },
-    {
-      "authority": "expected.json/spec_output_files",
-      "id": "spec_output_file__tests_cli_test_js",
-      "operational_check": "variant-touched files MUST be inside (or reachable via static imports from) the spec_output_files set; 'tests/cli.test.js' is one Tier C seed",
-      "severity": "warn",
-      "source_field": "expected.json/spec_output_files",
-      "source_ref": "expected.json:spec_output_files[tests/cli.test.js]"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:assertion-regression",
-      "operational_check": "effective assertion count MUST NOT drop and skipped-test count MUST NOT rise; vacuous expect.assertions(0) is treated as a real regression",
-      "severity": "warn",
-      "source_field": "oracle/test-fidelity/test-fidelity:assertion-regression",
-      "source_ref": "oracle-test-fidelity.py"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:mock-swap",
-      "operational_check": "post-arm test file MUST NOT swap REAL_PATTERNS hits for MOCK_PATTERNS hits (jest/vi/sinon, nock/msw, app.handle/inject/callback, hand-rolled IncomingMessage/ServerResponse, etc.); a drop in real_calls combined with a rise in mock_calls is a mock-swap flag",
-      "severity": "flag",
-      "source_field": "oracle/test-fidelity/test-fidelity:mock-swap",
-      "source_ref": "oracle-test-fidelity.py"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:test-file-deleted",
-      "operational_check": "no scaffold-present test file may be deleted by the variant arm; deletion of an existing tests/*.test.* / *.spec.* / *.e2e.* file is a flag-severity finding",
-      "severity": "flag",
-      "source_field": "oracle/test-fidelity/test-fidelity:test-file-deleted",
-      "source_ref": "oracle-test-fidelity.py"
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:test-file-renamed",
-      "operational_check": "rename of a scaffold-present test file is warn-severity (content fidelity not verified across renames in step 1)",
-      "severity": "warn",
-      "source_field": "oracle/test-fidelity/test-fidelity:test-file-renamed",
-      "source_ref": "oracle-test-fidelity.py"
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__3f35982a",
-      "operational_check": "running `node bin/cli.js doctor` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor:']; stdout MUST NOT contain any of ['undefined', 'Error:']",
-      "severity": "hard",
-      "source_field": "expected.json/verification_commands/0",
-      "source_ref": "expected.json:verification_commands[0]"
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__460fce04",
-      "operational_check": "running `HOME=/nonexistent node bin/cli.js doctor` in the post-arm work dir MUST exit with code 1; stdout MUST contain all of ['/nonexistent']; stdout MUST NOT contain any of []",
-      "severity": "hard",
-      "source_field": "expected.json/verification_commands/1",
-      "source_ref": "expected.json:verification_commands[1]"
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__973e287e",
-      "operational_check": "running `python3 -c \"import subprocess; r = subprocess.run(['node', 'bin/cli.js', 'doctor'], capture_output=True); n = r.stdout.count(b'\\x1b['); print(n); exit(0 if n == 0 else 1)\"` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['0']; stdout MUST NOT contain any of []",
-      "severity": "hard",
-      "source_field": "expected.json/verification_commands/2",
-      "source_ref": "expected.json:verification_commands[2]"
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__d6253a97",
-      "operational_check": "running `node bin/cli.js doctor --help` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor']; stdout MUST NOT contain any of []",
-      "severity": "hard",
-      "source_field": "expected.json/verification_commands/3",
-      "source_ref": "expected.json:verification_commands[3]"
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__e0f149e4",
-      "operational_check": "running `node bin/cli.js --help` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor']; stdout MUST NOT contain any of []",
-      "severity": "hard",
-      "source_field": "expected.json/verification_commands/4",
-      "source_ref": "expected.json:verification_commands[4]"
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__fdbcd321",
-      "operational_check": "running `node bin/cli.js doctor --verbose` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor:']; stdout MUST NOT contain any of ['Error:']",
-      "severity": "hard",
-      "source_field": "expected.json/verification_commands/5",
-      "source_ref": "expected.json:verification_commands[5]"
-    }
-  ],
-  "schema_version": "1"
-}

package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected.json

@@ -1,84 +0,0 @@
-{
-  "verification_commands": [
-    {
-      "cmd": "node bin/cli.js doctor",
-      "exit_code": 0,
-      "stdout_contains": [
-        "doctor:"
-      ],
-      "stdout_not_contains": [
-        "undefined",
-        "Error:"
-      ]
-    },
-    {
-      "cmd": "HOME=/nonexistent node bin/cli.js doctor",
-      "exit_code": 1,
-      "stdout_contains": [
-        "/nonexistent"
-      ],
-      "stdout_not_contains": []
-    },
-    {
-      "cmd": "python3 -c \"import subprocess; r = subprocess.run(['node', 'bin/cli.js', 'doctor'], capture_output=True); n = r.stdout.count(b'\\x1b['); print(n); exit(0 if n == 0 else 1)\"",
-      "exit_code": 0,
-      "stdout_contains": [
-        "0"
-      ],
-      "stdout_not_contains": []
-    },
-    {
-      "cmd": "node bin/cli.js doctor --help",
-      "exit_code": 0,
-      "stdout_contains": [
-        "doctor"
-      ],
-      "stdout_not_contains": []
-    },
-    {
-      "cmd": "node bin/cli.js --help",
-      "exit_code": 0,
-      "stdout_contains": [
-        "doctor"
-      ],
-      "stdout_not_contains": []
-    },
-    {
-      "cmd": "node bin/cli.js doctor --verbose",
-      "exit_code": 0,
-      "stdout_contains": [
-        "doctor:"
-      ],
-      "stdout_not_contains": [
-        "Error:"
-      ]
-    }
-  ],
-  "forbidden_patterns": [
-    {
-      "pattern": "catch\\s*\\([^)]*\\)\\s*\\{[^}]*return\\s+(?:\\[\\]|null|undefined|false|''|\\{\\s*\\})",
-      "description": "silent catch returning a fallback value (null / undefined / [] / false / '' / empty {}) \u2014 violates no-silent-catches policy. Structured error returns like `return { level: 'fail', message }` are NOT silent (they surface a user-visible failure object) and must not match.",
-      "files": [
-        "bin/cli.js"
-      ],
-      "severity": "disqualifier"
-    },
-    {
-      "pattern": "@ts-ignore",
-      "description": "@ts-ignore escape hatch",
-      "files": [
-        "bin/cli.js"
-      ],
-      "severity": "disqualifier"
-    }
-  ],
-  "required_files": [
-    "bin/cli.js"
-  ],
-  "forbidden_files": [],
-  "max_deps_added": 0,
-  "spec_output_files": [
-    "bin/cli.js",
-    "tests/cli.test.js"
-  ]
-}

package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/metadata.json

@@ -1,21 +0,0 @@
-{
-  "id": "F2-cli-medium-subcommand",
-  "category": "medium",
-  "difficulty": "medium",
-  "timeout_seconds": 1500,
-  "required_tools": [
-    "node"
-  ],
-  "browser": false,
-  "deps_change_expected": false,
-  "intent": "Add a `doctor` subcommand to bin/cli.js that diagnoses the local environment: node version check, $HOME/.claude directory check, installed plugins count, installed skills count, TTY-gated ANSI color, summary line, exit code, --verbose flag, help integration. Zero new npm dependencies. No silent error catches.",
-  "pair_plan_oracle_categories": [
-    "scope-tier-a:lockfile-deletion",
-    "scope-tier-a:tier-a-violation",
-    "scope-tier-b:scope-unmatched",
-    "test-fidelity:assertion-regression",
-    "test-fidelity:mock-swap",
-    "test-fidelity:test-file-deleted",
-    "test-fidelity:test-file-renamed"
-  ]
-}

package/benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/pair-plan.sample-fail.json

@@ -1,214 +0,0 @@
-{
-  "accepted_invariants": [
-    {
-      "authority": "expected.json/forbidden_patterns",
-      "id": "forbidden_pattern__ts_ignore_escape_hatch__bin_cli_js",
-      "operational_check": "variant arm output MUST NOT contain regex pattern '@ts-ignore' in files ['bin/cli.js']; rationale: @ts-ignore escape hatch",
-      "paraphrase": "variant arm output MUST NOT contain regex pattern '@ts-ignore' in files ['bin/cli.js']; rationale: @ts-ignore escape hat",
-      "source_refs": [
-        "expected.json:forbidden_patterns[1]"
-      ]
-    },
-    {
-      "authority": "expected.json/max_deps_added",
-      "id": "max_deps_added__0",
-      "operational_check": "variant arm MUST NOT add more than 0 new npm dependencies (count delta of package.json:dependencies + devDependencies)",
-      "paraphrase": "variant arm MUST NOT add more than 0 new npm dependencies (count delta of package.json:dependencies + devDependencies)",
-      "source_refs": [
-        "expected.json:max_deps_added"
-      ]
-    },
-    {
-      "authority": "expected.json/required_files",
-      "id": "required_file__bin_cli_js",
-      "operational_check": "variant arm output MUST contain file 'bin/cli.js' (created or preserved)",
-      "paraphrase": "variant arm output MUST contain file 'bin/cli.js' (created or preserved)",
-      "source_refs": [
-        "expected.json:required_files[bin/cli.js]"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "scope-tier-a:lockfile-deletion",
-      "operational_check": "variant arm MUST NOT delete a scaffold-present lockfile",
-      "paraphrase": "variant arm MUST NOT delete a scaffold-present lockfile",
-      "source_refs": [
-        "oracle-scope-tier-a.py"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "scope-tier-a:tier-a-violation",
-      "operational_check": "variant arm MUST NOT add or modify paths matching: docs/roadmap/** | docs/VISION.md | docs/ROADMAP.md | .github/** | node_modules/** | **/node_modules/** | test-results/** | coverage/** | .nyc_output/** | basename suffix .log | basename prefix .env or secrets.",
-      "paraphrase": "variant arm MUST NOT add or modify paths matching: docs/roadmap/** | docs/VISION.md | docs/ROADMAP.md | .github/** | nod",
-      "source_refs": [
-        "oracle-scope-tier-a.py"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "scope-tier-b:scope-unmatched",
-      "operational_check": "every variant-touched file MUST be either inside spec_output_files (Tier C) OR reachable from a Tier C seed via static JS/TS imports OR matched by expected.json:tier_a_waivers",
-      "paraphrase": "every variant-touched file MUST be either inside spec_output_files (Tier C) OR reachable from a Tier C seed via static J",
-      "source_refs": [
-        "oracle-scope-tier-b.py"
-      ]
-    },
-    {
-      "authority": "expected.json/spec_output_files",
-      "id": "spec_output_file__bin_cli_js",
-      "operational_check": "variant-touched files MUST be inside (or reachable via static imports from) the spec_output_files set; 'bin/cli.js' is one Tier C seed",
-      "paraphrase": "variant-touched files MUST be inside (or reachable via static imports from) the spec_output_files set; 'bin/cli.js' is o",
-      "source_refs": [
-        "expected.json:spec_output_files[bin/cli.js]"
-      ]
-    },
-    {
-      "authority": "expected.json/spec_output_files",
-      "id": "spec_output_file__tests_cli_test_js",
-      "operational_check": "variant-touched files MUST be inside (or reachable via static imports from) the spec_output_files set; 'tests/cli.test.js' is one Tier C seed",
-      "paraphrase": "variant-touched files MUST be inside (or reachable via static imports from) the spec_output_files set; 'tests/cli.test.j",
-      "source_refs": [
-        "expected.json:spec_output_files[tests/cli.test.js]"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:assertion-regression",
-      "operational_check": "effective assertion count MUST NOT drop and skipped-test count MUST NOT rise; vacuous expect.assertions(0) is treated as a real regression",
-      "paraphrase": "effective assertion count MUST NOT drop and skipped-test count MUST NOT rise; vacuous expect.assertions(0) is treated as",
-      "source_refs": [
-        "oracle-test-fidelity.py"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:mock-swap",
-      "operational_check": "post-arm test file MUST NOT swap REAL_PATTERNS hits for MOCK_PATTERNS hits (jest/vi/sinon, nock/msw, app.handle/inject/callback, hand-rolled IncomingMessage/ServerResponse, etc.); a drop in real_calls combined with a rise in mock_calls is a mock-swap flag",
-      "paraphrase": "post-arm test file MUST NOT swap REAL_PATTERNS hits for MOCK_PATTERNS hits (jest/vi/sinon, nock/msw, app.handle/inject/c",
-      "source_refs": [
-        "oracle-test-fidelity.py"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:test-file-deleted",
-      "operational_check": "no scaffold-present test file may be deleted by the variant arm; deletion of an existing tests/*.test.* / *.spec.* / *.e2e.* file is a flag-severity finding",
-      "paraphrase": "no scaffold-present test file may be deleted by the variant arm; deletion of an existing tests/*.test.* / *.spec.* / *.e",
-      "source_refs": [
-        "oracle-test-fidelity.py"
-      ]
-    },
-    {
-      "authority": "metadata/oracle-allowlist",
-      "id": "test-fidelity:test-file-renamed",
-      "operational_check": "rename of a scaffold-present test file is warn-severity (content fidelity not verified across renames in step 1)",
-      "paraphrase": "rename of a scaffold-present test file is warn-severity (content fidelity not verified across renames in step 1)",
-      "source_refs": [
-        "oracle-test-fidelity.py"
-      ]
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__3f35982a",
-      "operational_check": "running `node bin/cli.js doctor` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor:']; stdout MUST NOT contain any of ['undefined', 'Error:']",
-      "paraphrase": "running `node bin/cli.js doctor` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor:'];",
-      "source_refs": [
-        "expected.json:verification_commands[0]"
-      ]
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__460fce04",
-      "operational_check": "running `HOME=/nonexistent node bin/cli.js doctor` in the post-arm work dir MUST exit with code 1; stdout MUST contain all of ['/nonexistent']; stdout MUST NOT contain any of []",
-      "paraphrase": "running `HOME=/nonexistent node bin/cli.js doctor` in the post-arm work dir MUST exit with code 1; stdout MUST contain a",
-      "source_refs": [
-        "expected.json:verification_commands[1]"
-      ]
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__973e287e",
-      "operational_check": "running `python3 -c \"import subprocess; r = subprocess.run(['node', 'bin/cli.js', 'doctor'], capture_output=True); n = r.stdout.count(b'\\x1b['); print(n); exit(0 if n == 0 else 1)\"` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['0']; stdout MUST NOT contain any of []",
-      "paraphrase": "running `python3 -c \"import subprocess; r = subprocess.run(['node', 'bin/cli.js', 'doctor'], capture_output=True); n = r",
-      "source_refs": [
-        "expected.json:verification_commands[2]"
-      ]
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__d6253a97",
-      "operational_check": "running `node bin/cli.js doctor --help` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor']; stdout MUST NOT contain any of []",
-      "paraphrase": "running `node bin/cli.js doctor --help` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doc",
-      "source_refs": [
-        "expected.json:verification_commands[3]"
-      ]
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__e0f149e4",
-      "operational_check": "running `node bin/cli.js --help` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor']; stdout MUST NOT contain any of []",
-      "paraphrase": "running `node bin/cli.js --help` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor']; ",
-      "source_refs": [
-        "expected.json:verification_commands[4]"
-      ]
-    },
-    {
-      "authority": "expected.json/verification_commands",
-      "id": "verification__fdbcd321",
-      "operational_check": "running `node bin/cli.js doctor --verbose` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['doctor:']; stdout MUST NOT contain any of ['Error:']",
-      "paraphrase": "running `node bin/cli.js doctor --verbose` in the post-arm work dir MUST exit with code 0; stdout MUST contain all of ['",
-      "source_refs": [
-        "expected.json:verification_commands[5]"
-      ]
-    }
-  ],
-  "authority_order": [
-    "spec.md",
-    "expected.json/rubric",
-    "phase prompt",
-    "model preference"
-  ],
-  "escalated_to_user": [],
-  "fixture_id": "F2-cli-medium-subcommand",
-  "model_stamps": {
-    "claude": {
-      "blocked_ids": [],
-      "model": "claude-opus-4-7",
-      "signed_plan_sha256": "05d19dc09a1c8820f58afcd091c2cd20888f7bf1141af4ec451a69723af0588a",
-      "status": "sign",
-      "timestamp": "2026-04-29T18:30:00Z"
-    },
-    "codex": {
-      "blocked_ids": [],
-      "model": "gpt-5.5",
-      "signed_plan_sha256": "05d19dc09a1c8820f58afcd091c2cd20888f7bf1141af4ec451a69723af0588a",
-      "status": "sign",
-      "timestamp": "2026-04-29T18:31:00Z"
-    }
-  },
-  "plan_status": "final",
-  "planning_mode": "pair",
-  "rejected_alternatives": [],
-  "rounds": [
-    {
-      "claude_draft_sha256": "0000000000000000000000000000000000000000000000000000000000000000",
-      "codex_draft_sha256": "1111111111111111111111111111111111111111111111111111111111111111",
-      "merged_sha256": "2222222222222222222222222222222222222222222222222222222222222222",
-      "note": "sample-pass synthetic round (test fixture)",
-      "round": 1
-    }
-  ],
-  "schema_version": "1",
-  "source": {
-    "canonical_id_registry_path": "benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected-pair-plan-registry.json",
-    "canonical_id_registry_sha256": "98ac16e4536ea3ef2e51d3c728982c014211c193a742cea74f1331e4fbba76be",
-    "expected_path": "benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/expected.json",
-    "expected_sha256": "ddef8feba49f20b6957e37840bc6a03e78e554776e380d81ad6390944c72fcab",
-    "rubric_path": "benchmark/auto-resolve/RUBRIC.md",
-    "rubric_sha256": "5b5b709a0b57f7e6f4fbc072af91e1edbc8d7910ae16b9b7be7170616aeaa9af",
-    "spec_path": "benchmark/auto-resolve/fixtures/F2-cli-medium-subcommand/spec.md",
-    "spec_sha256": "9b0949c2afd4a522de2bdbbf267d93907fd908bf0f1d0dc5e111ee30ba875bb7"
-  },
-  "unresolved": []
-}