devlyn-cli 3.2.0 → 3.3.0

package/benchmark/auto-resolve/fixtures/retired/F28-cli-return-authorization/verifiers/validation-boundary.js

@@ -1,116 +0,0 @@
-'use strict';
-
-const assert = require('node:assert');
-const { spawnSync } = require('node:child_process');
-const fs = require('node:fs');
-const os = require('node:os');
-const path = require('node:path');
-
-const work = process.env.BENCH_WORKDIR || process.cwd();
-const cli = path.join(work, 'bin', 'cli.js');
-
-function runCase(name, payload) {
-  const tmp = fs.mkdtempSync(path.join(os.tmpdir(), `f28-return-${name}-`));
-  const input = path.join(tmp, 'return.json');
-  fs.writeFileSync(input, JSON.stringify(payload, null, 2), 'utf8');
-  return spawnSync('node', [cli, 'authorize-return', '--input', input], {
-    cwd: work,
-    encoding: 'utf8'
-  });
-}
-
-function assertJsonError(result, label) {
-  assert.strictEqual(result.status, 2, `${label}: expected exit 2`);
-  assert.strictEqual(result.stdout, '', `${label}: expected empty stdout`);
-  const parsed = JSON.parse(result.stderr);
-  assert.strictEqual(typeof parsed.error, 'string', `${label}: error must be a string`);
-  assert.notStrictEqual(parsed.error.length, 0, `${label}: error must not be empty`);
-}
-
-function clone(value) {
-  return JSON.parse(JSON.stringify(value));
-}
-
-const boundary = runCase('boundary', {
-  today: '2026-05-20',
-  order: {
-    id: 'O-BORDER',
-    purchased_at: '2026-05-01',
-    items: [
-      { sku: 'MUG', qty: 1, unit_cents: 1000, return_window_days: 19, restocking_fee_percent: 25 }
-    ]
-  },
-  request: {
-    id: 'R-BORDER',
-    lines: [
-      { sku: 'MUG', qty: 1, reason: 'changed_mind', condition: 'sealed', resolution: 'refund' }
-    ]
-  }
-});
-
-assert.strictEqual(boundary.status, 0);
-assert.strictEqual(boundary.stderr, '');
-assert.deepStrictEqual(JSON.parse(boundary.stdout), {
-  request_id: 'R-BORDER',
-  order_id: 'O-BORDER',
-  approved: [
-    {
-      sku: 'MUG',
-      qty: 1,
-      resolution: 'refund',
-      gross_cents: 1000,
-      restocking_fee_cents: 0,
-      refund_cents: 1000,
-      exchange_credit_cents: 0
-    }
-  ],
-  rejected: [],
-  refund_cents: 1000,
-  exchange_credit_cents: 0,
-  restocking_fee_cents: 0
-});
-
-const validBase = {
-  today: '2026-05-20',
-  order: {
-    id: 'O-VALIDATE',
-    purchased_at: '2026-05-01',
-    items: [
-      { sku: 'COAT', qty: 1, unit_cents: 9900, return_window_days: 30, restocking_fee_percent: 12 }
-    ]
-  },
-  request: {
-    id: 'R-VALIDATE',
-    lines: [
-      { sku: 'COAT', qty: 1, reason: 'changed_mind', condition: 'opened', resolution: 'refund' }
-    ]
-  }
-};
-
-const duplicateSku = clone(validBase);
-duplicateSku.order.items.push({
-  sku: 'COAT',
-  qty: 1,
-  unit_cents: 9900,
-  return_window_days: 30,
-  restocking_fee_percent: 12
-});
-assertJsonError(runCase('duplicate-sku', duplicateSku), 'duplicate order SKU');
-
-const unknownSku = clone(validBase);
-unknownSku.request.lines[0].sku = 'SCARF';
-assertJsonError(runCase('unknown-sku', unknownSku), 'unknown requested SKU');
-
-const invalidDate = clone(validBase);
-invalidDate.today = '2026-02-30';
-assertJsonError(runCase('invalid-date', invalidDate), 'invalid calendar date');
-
-const invalidCondition = clone(validBase);
-invalidCondition.request.lines[0].condition = 'damaged_box';
-assertJsonError(runCase('invalid-condition', invalidCondition), 'invalid condition');
-
-const invalidResolution = clone(validBase);
-invalidResolution.request.lines[0].resolution = 'store_credit';
-assertJsonError(runCase('invalid-resolution', invalidResolution), 'invalid resolution');
-
-console.log(JSON.stringify({ ok: true }));

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/NOTES.md

@@ -1,35 +0,0 @@
-# F30 - Notes
-
-## Failure Mode
-
-This fixture detects payment-style implementations that pass simple happy-path
-tests while double-applying duplicate operations, letting rejected operations
-consume available credit, failing to release holds on capture/release, or
-mutating input files while computing settlement state.
-
-## Pipeline Phases
-
-It stresses IMPLEMENT and VERIFY. The visible spec names the state transition
-rules, idempotency output shape, and exact account summary; hidden verifiers
-combine those rules so a one-axis implementation is not enough.
-
-## Why Existing Fixtures Do Not Cover This
-
-F16 covers quote math, F23 covers warehouse allocation rollback, F25 covers cart
-promotions, and F28 return authorization was rejected after corrected scoring
-showed solo saturation. None focus on duplicate operation idempotency plus
-credit-hold mutation, capture/release transitions, and validation immutability.
-
-## Retirement Criteria
-
-Retire or rotate this fixture if both `solo_claude` and the selected pair arm
-score near the ceiling for two shipped versions, or if another fixture covers
-idempotent financial hold mutation with clearer pair headroom.
-
-## Headroom Status
-
-Retired after headroom run `20260511-f30-headroom-v1`: bare 33 /
-solo_claude 98, headroom FAIL because `solo_claude score 98 > 80`.
-
-Do not count F30 as pair-lift evidence. Rework the visible contract or hidden
-verifiers before spending pair arms on this idea again.

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/RETIRED.md

@@ -1,12 +0,0 @@
-# F30 retired
-
-Retired from the active golden suite after headroom run
-`20260511-f30-headroom-v1`.
-
-Reason: `solo_claude` scored 98, exceeding the headroom ceiling of 80, while
-bare scored 33. The fixture is useful as a record of an idempotent hold
-settlement candidate that proved too explicit for solo, but it is not
-pair-lift evidence.
-
-Future use: rework the visible contract or hidden verifiers so the task creates
-a fair pair-risk-probe gap without hiding requirements from the spec.

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/expected.json

@@ -1,58 +0,0 @@
-{
-  "verification_commands": [
-    {
-      "cmd": "node --test tests/cli.test.js",
-      "exit_code": 0,
-      "stdout_contains": [],
-      "stdout_not_contains": ["not ok "]
-    },
-    {
-      "cmd": "node \"$BENCH_FIXTURE_DIR/verifiers/mixed-idempotent-settlement.js\"",
-      "exit_code": 0,
-      "stdout_contains": ["\"ok\":true"],
-      "stdout_not_contains": [],
-      "contract_refs": [
-        "A failed authorization does not reserve credit and does not block a later valid authorization.",
-        "Capture removes the active hold and increases `balance_cents`.",
-        "Release removes the active hold without changing `balance_cents`.",
-        "Duplicate operation ids do not mutate state and report the original status."
-      ]
-    },
-    {
-      "cmd": "node \"$BENCH_FIXTURE_DIR/verifiers/rejection-boundaries.js\"",
-      "exit_code": 0,
-      "stdout_contains": ["\"ok\":true"],
-      "stdout_not_contains": [],
-      "contract_refs": [
-        "Reusing an active `hold_id` is rejected as `\"duplicate_hold\"`.",
-        "Capture or release with a wrong amount is rejected as `\"amount_mismatch\"` and does not mutate state.",
-        "Invalid unknown-account input exits `2`, prints one JSON error object to stderr, and prints no stdout.",
-        "The input file contents are unchanged after settlement."
-      ]
-    }
-  ],
-  "forbidden_patterns": [
-    {
-      "pattern": "catch\\s*\\([^)]*\\)\\s*\\{[^}]*return\\s+(null|undefined|''|\\{\\})",
-      "description": "silent catch returning fallback in credit hold settlement path",
-      "files": ["bin/cli.js"],
-      "severity": "disqualifier"
-    },
-    {
-      "pattern": "catch\\s*\\([^)]*\\)\\s*\\{\\s*\\}",
-      "description": "empty catch block",
-      "files": ["bin/cli.js"],
-      "severity": "disqualifier"
-    },
-    {
-      "pattern": "/\\*\\s*eslint-disable",
-      "description": "eslint-disable without scoped justification",
-      "files": ["bin/cli.js"],
-      "severity": "disqualifier"
-    }
-  ],
-  "required_files": ["bin/cli.js", "tests/cli.test.js"],
-  "forbidden_files": [],
-  "max_deps_added": 0,
-  "spec_output_files": ["bin/cli.js", "tests/cli.test.js"]
-}

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/metadata.json

@@ -1,10 +0,0 @@
-{
-  "id": "F30-cli-credit-hold-settlement",
-  "category": "high-risk",
-  "difficulty": "high",
-  "timeout_seconds": 1500,
-  "required_tools": ["node"],
-  "browser": false,
-  "deps_change_expected": false,
-  "intent": "Add a bench-cli settle-holds command that reads account credit holds and operations, applies authorization/capture/release with idempotency and rollback, and emits exact cents-based settlement state without mutating input."
-}

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/setup.sh

@@ -1,2 +0,0 @@
-#!/usr/bin/env bash
-set -e

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/spec.md

@@ -1,73 +0,0 @@
----
-id: "F30-cli-credit-hold-settlement"
-title: "Credit hold settlement"
-status: planned
-complexity: high
-depends-on: []
----
-
-# F30 Credit hold settlement
-
-## Context
-
-`bench-cli` currently has greeting and version commands only. The task:
-add a `settle-holds` command that reads account credit holds and operations,
-applies authorization/capture/release with idempotency and rollback, and emits
-exact cents-based settlement state without mutating input.
-
-Credit holds feed payment and ledger workflows, so duplicate operations,
-failed operations, and available-credit calculations must be deterministic.
-
-## Requirements
-
-- [ ] `bench-cli settle-holds --input <path>` reads JSON shaped as `{ "accounts": Array<Account>, "operations": Array<Operation> }`.
-- [ ] Each account has `{ "id": string, "balance_cents": number, "credit_limit_cents": number }`.
-- [ ] Each operation has `{ "id": string, "account_id": string, "type": "authorize" | "capture" | "release", "hold_id": string, "amount_cents": number }`.
-- [ ] Validate before settlement: ids and hold ids must be non-empty strings, account ids must be unique, balances and credit limits must be non-negative integers, amount cents must be positive integers, operation types must be one of the allowed strings, and every operation account must exist.
-- [ ] Invalid input exits `2`, writes exactly one JSON error object to stderr, and writes nothing to stdout.
-- [ ] Business rejections do not exit non-zero and do not mutate settlement state.
-- [ ] Process operations in input order.
-- [ ] An `authorize` operation creates one active hold when `credit_limit_cents - balance_cents - active_hold_cents >= amount_cents`; otherwise it is rejected with reason `"insufficient_credit"`.
-- [ ] An `authorize` operation for a `hold_id` that is already active is rejected with reason `"duplicate_hold"`.
-- [ ] A `capture` operation requires an active hold for the same account and exactly the requested amount available on that hold; otherwise it is rejected with reason `"unknown_hold"` or `"amount_mismatch"`.
-- [ ] An approved `capture` increases `balance_cents` by `amount_cents` and removes the active hold.
-- [ ] A `release` operation requires an active hold for the same account and exactly the requested amount available on that hold; otherwise it is rejected with reason `"unknown_hold"` or `"amount_mismatch"`.
-- [ ] An approved `release` removes the active hold without changing `balance_cents`.
-- [ ] Duplicate operation ids are idempotent: the first occurrence is processed normally; each later operation with the same `id` must not mutate state and emits `{ "id": string, "status": "duplicate", "original_status": "approved" | "rejected" }`.
-- [ ] Approved rows have keys `id`, `status`, `type`, `account_id`, `hold_id`, `amount_cents`.
-- [ ] Rejected rows have keys `id`, `status`, `reason`.
-- [ ] Duplicate rows have keys `id`, `status`, `original_status`.
-- [ ] On success, write exactly one JSON object to stdout and no stderr. Keys: `results`, `accounts`.
-- [ ] `results` is ordered by input operation order.
-- [ ] `accounts` is sorted by account id. Each account row has keys `id`, `balance_cents`, `active_hold_cents`, `available_cents`.
-- [ ] The command must not modify the input file.
-- [ ] `tests/cli.test.js` is updated. Existing tests still pass AND at least two new tests cover one mixed approved/rejected/duplicate settlement and one validation failure.
-
-## Constraints
-
-- **No new npm dependencies.**
-- **No floating-money output.** All public amounts are integer cents.
-- **No silent catches.** Invalid input and file-read failures must surface as JSON errors with exit `2`.
-- **No extra stdout/stderr text** on the success path; downstream tooling parses stdout as JSON.
-- **Touch only `bin/cli.js` and `tests/cli.test.js`.**
-
-## Out of Scope
-
-- Payment processor calls.
-- Persistence beyond stdout.
-- Partial captures or partial releases.
-- Currencies, interest, fees, or statement generation.
-- Touching `server/`, `web/`, or `tests/server.test.js`.
-
-## Verification
-
-- `node --test tests/cli.test.js` exits 0.
-- A failed authorization does not reserve credit and does not block a later valid authorization.
-- Capture removes the active hold and increases `balance_cents`.
-- Release removes the active hold without changing `balance_cents`.
-- Duplicate operation ids do not mutate state and report the original status.
-- Reusing an active `hold_id` is rejected as `"duplicate_hold"`.
-- Capture or release with a wrong amount is rejected as `"amount_mismatch"` and does not mutate state.
-- Invalid unknown-account input exits `2`, prints one JSON error object to stderr, and prints no stdout.
-- The input file contents are unchanged after settlement.
-- `git diff --stat` shows only `bin/cli.js` and `tests/cli.test.js` touched.

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/task.txt

@@ -1,17 +0,0 @@
-Add a bench-cli settle-holds command that reads account credit holds and
-operations, applies authorization/capture/release with idempotency and rollback,
-and emits exact cents-based settlement state without mutating input.
-
-The command should read `--input <path>` JSON with accounts and operations.
-Validate the input before settlement. Use integer cents only, write exactly one
-JSON object to stdout on success, and write exactly one JSON error object to
-stderr with exit code 2 for invalid input. Do not add npm dependencies.
-
-Business rejections should stay on exit code 0. Process operations in input
-order. Authorizations create active holds only when available credit is enough.
-Captures and releases require an active hold for the same account and exact
-amount. Failed operations must not mutate state. Duplicate operation ids are
-idempotent: only the first occurrence mutates state, and later duplicates report
-the original approved/rejected status.
-
-Update the CLI tests. Touch only `bin/cli.js` and `tests/cli.test.js`.

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/verifiers/mixed-idempotent-settlement.js

@@ -1,53 +0,0 @@
-'use strict';
-
-const assert = require('node:assert');
-const { execFileSync } = require('node:child_process');
-const fs = require('node:fs');
-const os = require('node:os');
-const path = require('node:path');
-
-const work = process.env.BENCH_WORKDIR || process.cwd();
-const cli = path.join(work, 'bin', 'cli.js');
-const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'f30-mixed-'));
-const input = path.join(tmp, 'holds.json');
-
-fs.writeFileSync(input, JSON.stringify({
-  accounts: [
-    { id: 'acct-a', balance_cents: 2000, credit_limit_cents: 10000 },
-    { id: 'acct-b', balance_cents: 0, credit_limit_cents: 5000 }
-  ],
-  operations: [
-    { id: 'op-auth-1', account_id: 'acct-a', type: 'authorize', hold_id: 'h-1', amount_cents: 5000 },
-    { id: 'op-too-large', account_id: 'acct-a', type: 'authorize', hold_id: 'h-2', amount_cents: 4000 },
-    { id: 'op-release', account_id: 'acct-a', type: 'release', hold_id: 'h-1', amount_cents: 5000 },
-    { id: 'op-auth-3', account_id: 'acct-a', type: 'authorize', hold_id: 'h-3', amount_cents: 3000 },
-    { id: 'op-capture', account_id: 'acct-a', type: 'capture', hold_id: 'h-3', amount_cents: 3000 },
-    { id: 'op-capture', account_id: 'acct-a', type: 'capture', hold_id: 'h-3', amount_cents: 3000 },
-    { id: 'op-auth-b', account_id: 'acct-b', type: 'authorize', hold_id: 'h-b', amount_cents: 5000 }
-  ]
-}), 'utf8');
-
-const stdout = execFileSync('node', [cli, 'settle-holds', '--input', input], {
-  cwd: work,
-  encoding: 'utf8',
-  stdio: ['ignore', 'pipe', 'pipe']
-});
-const parsed = JSON.parse(stdout);
-
-assert.deepStrictEqual(parsed, {
-  results: [
-    { id: 'op-auth-1', status: 'approved', type: 'authorize', account_id: 'acct-a', hold_id: 'h-1', amount_cents: 5000 },
-    { id: 'op-too-large', status: 'rejected', reason: 'insufficient_credit' },
-    { id: 'op-release', status: 'approved', type: 'release', account_id: 'acct-a', hold_id: 'h-1', amount_cents: 5000 },
-    { id: 'op-auth-3', status: 'approved', type: 'authorize', account_id: 'acct-a', hold_id: 'h-3', amount_cents: 3000 },
-    { id: 'op-capture', status: 'approved', type: 'capture', account_id: 'acct-a', hold_id: 'h-3', amount_cents: 3000 },
-    { id: 'op-capture', status: 'duplicate', original_status: 'approved' },
-    { id: 'op-auth-b', status: 'approved', type: 'authorize', account_id: 'acct-b', hold_id: 'h-b', amount_cents: 5000 }
-  ],
-  accounts: [
-    { id: 'acct-a', balance_cents: 5000, active_hold_cents: 0, available_cents: 5000 },
-    { id: 'acct-b', balance_cents: 0, active_hold_cents: 5000, available_cents: 0 }
-  ]
-});
-
-console.log(JSON.stringify({ ok: true }));

package/benchmark/auto-resolve/fixtures/retired/F30-cli-credit-hold-settlement/verifiers/rejection-boundaries.js

@@ -1,74 +0,0 @@
-'use strict';
-
-const assert = require('node:assert');
-const { spawnSync } = require('node:child_process');
-const fs = require('node:fs');
-const os = require('node:os');
-const path = require('node:path');
-
-const work = process.env.BENCH_WORKDIR || process.cwd();
-const cli = path.join(work, 'bin', 'cli.js');
-
-function runPayload(label, payload) {
-  const tmp = fs.mkdtempSync(path.join(os.tmpdir(), `f30-${label}-`));
-  const input = path.join(tmp, 'holds.json');
-  const original = JSON.stringify(payload, null, 2);
-  fs.writeFileSync(input, original, 'utf8');
-  const result = spawnSync('node', [cli, 'settle-holds', '--input', input], {
-    cwd: work,
-    encoding: 'utf8'
-  });
-  assert.strictEqual(fs.readFileSync(input, 'utf8'), original, `${label}: input mutated`);
-  return result;
-}
-
-const boundary = runPayload('boundary', {
-  accounts: [
-    { id: 'acct-a', balance_cents: 1000, credit_limit_cents: 7000 }
-  ],
-  operations: [
-    { id: 'op-auth', account_id: 'acct-a', type: 'authorize', hold_id: 'h-1', amount_cents: 3000 },
-    { id: 'op-dupe-hold', account_id: 'acct-a', type: 'authorize', hold_id: 'h-1', amount_cents: 1000 },
-    { id: 'op-bad-capture', account_id: 'acct-a', type: 'capture', hold_id: 'h-1', amount_cents: 2000 },
-    { id: 'op-release', account_id: 'acct-a', type: 'release', hold_id: 'h-1', amount_cents: 3000 },
-    { id: 'op-bad-release', account_id: 'acct-a', type: 'release', hold_id: 'h-1', amount_cents: 3000 },
-    { id: 'op-after', account_id: 'acct-a', type: 'authorize', hold_id: 'h-2', amount_cents: 6000 },
-    { id: 'op-dupe-reject', account_id: 'acct-a', type: 'authorize', hold_id: 'h-3', amount_cents: 1 },
-    { id: 'op-dupe-reject', account_id: 'acct-a', type: 'authorize', hold_id: 'h-4', amount_cents: 1 }
-  ]
-});
-
-assert.strictEqual(boundary.status, 0);
-assert.strictEqual(boundary.stderr, '');
-assert.deepStrictEqual(JSON.parse(boundary.stdout), {
-  results: [
-    { id: 'op-auth', status: 'approved', type: 'authorize', account_id: 'acct-a', hold_id: 'h-1', amount_cents: 3000 },
-    { id: 'op-dupe-hold', status: 'rejected', reason: 'duplicate_hold' },
-    { id: 'op-bad-capture', status: 'rejected', reason: 'amount_mismatch' },
-    { id: 'op-release', status: 'approved', type: 'release', account_id: 'acct-a', hold_id: 'h-1', amount_cents: 3000 },
-    { id: 'op-bad-release', status: 'rejected', reason: 'unknown_hold' },
-    { id: 'op-after', status: 'approved', type: 'authorize', account_id: 'acct-a', hold_id: 'h-2', amount_cents: 6000 },
-    { id: 'op-dupe-reject', status: 'rejected', reason: 'insufficient_credit' },
-    { id: 'op-dupe-reject', status: 'duplicate', original_status: 'rejected' }
-  ],
-  accounts: [
-    { id: 'acct-a', balance_cents: 1000, active_hold_cents: 6000, available_cents: 0 }
-  ]
-});
-
-const invalid = runPayload('invalid', {
-  accounts: [
-    { id: 'acct-a', balance_cents: 0, credit_limit_cents: 1000 }
-  ],
-  operations: [
-    { id: 'op-missing-account', account_id: 'acct-missing', type: 'authorize', hold_id: 'h-1', amount_cents: 100 }
-  ]
-});
-
-assert.strictEqual(invalid.status, 2);
-assert.strictEqual(invalid.stdout, '');
-const err = JSON.parse(invalid.stderr);
-assert.strictEqual(typeof err.error, 'string');
-assert.notStrictEqual(err.error.length, 0);
-
-console.log(JSON.stringify({ ok: true }));

package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/NOTES.md

@@ -1,28 +0,0 @@
-# F34 CLI settle in-flight
-
-## Failure mode
-
-Detects implementations that couple authorization completion order to
-settlement order. The two cheap-but-wrong shapes: (a) sequential
-await-per-transfer — correct ledger, fails the visible overlap requirement
-(`high_water >= 3`); (b) apply-as-authorizations-resolve — meets overlap,
-corrupts file-order settlement (flips `t-60` accept and `t-40` reject in the
-verifier input). The correct shape starts authorizations concurrently and
-settles strictly in file order afterward — the decoupling is the measured
-skill (Tier-1 "H1" from memory `project_pair_fixture_tier1_2026_05_05`;
-keyword-hidden: spec never says race/lock/mutex/concurrency primitive).
-
-## Fairness
-
-Every verifier assertion quotes a visible spec bullet via `contract_refs`
-(lint-fixtures enforced). Gateway latency is deterministic (trailing digits
-of the id = ms), high-water threshold is stated in the spec with the exact
-sample size, and the flip case is derivable from the visible settlement rule
-alone. No hidden shape or tie-break exists outside spec.md.
-
-## Headroom prediction (pre-registered, unmeasured)
-
-bare ≤ 60 (expected to fail ordering-vs-completion or overlap), solo ≤ 80
-(hypothesis: misses the decoupling — settles in completion order). To be
-measured with `headroom-gate.py` before any pair-evidence claims; this
-fixture carries no measurement claim until then.

package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/RETIRED.md

@@ -1,15 +0,0 @@
-# F34 retired
-
-Retired from the active golden suite after headroom run
-`iter-0039-headroom-f34-f35`.
-
-Reason: bare scored 92, exceeding the headroom ceiling of 60, and
-`solo_claude` scored 88, exceeding the headroom ceiling of 80. Both arms
-solved the settle-inflight task competently (judge: bare 92 vs solo_claude 88,
-margin -4) and share the same minor scope slip (touching
-`data/gateway-stats.json` outside the expected diff); neither arm hit a hard
-disqualifier. The task was not hard enough for bare, let alone solo — there is
-no pair-lift headroom to measure.
-
-Future use: rework the visible contract or hidden verifiers so the task
-creates a fair pair-risk-probe gap without hiding requirements from the spec.

package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/expected.json

@@ -1,57 +0,0 @@
-{
-  "verification_commands": [
-    {
-      "cmd": "node --test tests/cli.test.js",
-      "exit_code": 0,
-      "stdout_contains": [],
-      "stdout_not_contains": ["not ok "]
-    },
-    {
-      "cmd": "node \"$BENCH_FIXTURE_DIR/verifiers/ordered-settlement.js\"",
-      "exit_code": 0,
-      "stdout_contains": ["\"ok\":true"],
-      "stdout_not_contains": [],
-      "contract_refs": [
-        "Every transfer is authorized by calling `authorize(transfer)` from `lib/gateway.js` exactly once per transfer.",
-        "Regardless of the order in which authorizations complete, transfers settle in file order, each exactly once.",
-        "Each rejected transfer produces exact row shape `{ \"id\": string, \"error\": \"insufficient_funds\", \"available\": number, \"requested\": number }`, where `available` is the sender's balance at that transfer's turn in file order.",
-        "The seeded gateway records the maximum number of authorizations in flight at once in `data/gateway-stats.json`; settling the six-transfer sample in `## Verification` must record `high_water` of at least `3`.",
-        "The command must not modify `data/accounts.json`."
-      ]
-    },
-    {
-      "cmd": "node \"$BENCH_FIXTURE_DIR/verifiers/reject-invalid.js\"",
-      "exit_code": 0,
-      "stdout_contains": ["\"ok\":true"],
-      "stdout_not_contains": [],
-      "contract_refs": [
-        "Validation happens before any authorization starts.",
-        "unknown account, or non-positive or non-integer `amount` exits `2` and writes exactly one JSON error object to stderr with shape `{ \"error\": \"invalid_input\", \"reason\": string }`, printing nothing to stdout."
-      ]
-    }
-  ],
-  "forbidden_patterns": [
-    {
-      "pattern": "catch\\s*\\([^)]*\\)\\s*\\{[^}]*return\\s+(null|undefined|''|\\{\\})",
-      "description": "silent catch returning fallback in settle path",
-      "files": ["bin/cli.js"],
-      "severity": "disqualifier"
-    },
-    {
-      "pattern": "catch\\s*\\([^)]*\\)\\s*\\{\\s*\\}",
-      "description": "empty catch block",
-      "files": ["bin/cli.js"],
-      "severity": "disqualifier"
-    },
-    {
-      "pattern": "/\\*\\s*eslint-disable",
-      "description": "eslint-disable without scoped justification",
-      "files": ["bin/cli.js"],
-      "severity": "disqualifier"
-    }
-  ],
-  "required_files": ["bin/cli.js", "tests/cli.test.js", "data/accounts.json", "lib/gateway.js"],
-  "forbidden_files": [],
-  "max_deps_added": 0,
-  "spec_output_files": ["bin/cli.js", "tests/cli.test.js"]
-}

package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/metadata.json

@@ -1,10 +0,0 @@
-{
-  "id": "F34-cli-settle-inflight",
-  "category": "high-risk",
-  "difficulty": "high",
-  "timeout_seconds": 1500,
-  "required_tools": ["node"],
-  "browser": false,
-  "deps_change_expected": false,
-  "intent": "Add a bench-cli settle command that authorizes transfers through a seeded async gateway with overlapping in-flight authorizations while settling balances strictly in file order, with exact accepted/rejected/balances JSON output and validation before any authorization."
-}

package/benchmark/auto-resolve/fixtures/retired/F34-cli-settle-inflight/setup.sh

@@ -1,50 +0,0 @@
-#!/usr/bin/env bash
-# F34 setup — seed accounts and the concurrency-tracking gateway.
-set -e
-
-mkdir -p data lib
-
-cat > data/accounts.json <<'JSON'
-{
-  "acct-a": 100,
-  "acct-b": 0,
-  "acct-c": 50,
-  "acct-d": 10
-}
-JSON
-
-cat > lib/gateway.js <<'JS'
-'use strict';
-// Seeded authorization gateway. DO NOT MODIFY (fixture contract).
-// Latency is deterministic per transfer id (trailing digits = milliseconds),
-// so authorization completion order can differ from file order. Tracks how
-// many authorizations are in flight at once and how many calls were made.
-const fs = require('fs');
-const path = require('path');
-
-const STATS_PATH = path.join(__dirname, '..', 'data', 'gateway-stats.json');
-let inFlight = 0;
-let highWater = 0;
-let calls = 0;
-
-function writeStats() {
-  fs.writeFileSync(STATS_PATH, JSON.stringify({ calls, high_water: highWater }) + '\n');
-}
-
-async function authorize(transfer) {
-  calls += 1;
-  inFlight += 1;
-  if (inFlight > highWater) highWater = inFlight;
-  writeStats();
-  const digits = String(transfer && transfer.id ? transfer.id : '').replace(/\D/g, '');
-  const ms = digits ? (Number(digits) % 100) || 5 : 5;
-  await new Promise((resolve) => setTimeout(resolve, ms));
-  inFlight -= 1;
-  writeStats();
-  return { authorized: true };
-}
-
-module.exports = { authorize };
-JS
-
-exit 0