mandrel 2.98.0 → 2.101.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.agents/agents/story-worker.md +7 -1
- package/.agents/audit-checklists/quality.md +1 -0
- package/.agents/docs/agentrc-reference.json +3 -0
- package/.agents/docs/configuration.md +3 -0
- package/.agents/rules/api-conventions.md +4 -0
- package/.agents/rules/ci-remediation.md +8 -0
- package/.agents/rules/testing-standards.md +19 -1
- package/.agents/schemas/agentrc.schema.json +26 -0
- package/.agents/schemas/story-deliver-terminal.schema.json +17 -3
- package/.agents/schemas/validation-evidence.schema.json +10 -0
- package/.agents/scripts/lib/close-lock-events.js +18 -5
- package/.agents/scripts/lib/close-validation/gates.js +6 -1
- package/.agents/scripts/lib/close-validation/runner.js +10 -11
- package/.agents/scripts/lib/close-validation/test-delta.js +124 -0
- package/.agents/scripts/lib/config/pull-request.js +25 -0
- package/.agents/scripts/lib/config-settings-schema-delivery.js +22 -0
- package/.agents/scripts/lib/config-settings-schema.js +5 -0
- package/.agents/scripts/lib/coverage-capture-delta.js +2 -1
- package/.agents/scripts/lib/generated/agentrc-validator.js +2 -2
- package/.agents/scripts/lib/git/sync-from-base.js +4 -2
- package/.agents/scripts/lib/orchestration/ci-red-handling.js +4 -3
- package/.agents/scripts/lib/orchestration/ci-rerun-guard.js +81 -25
- package/.agents/scripts/lib/orchestration/handoff-state.js +41 -0
- package/.agents/scripts/lib/orchestration/review-providers/code-review.js +97 -28
- package/.agents/scripts/lib/orchestration/single-story-close/phases/base-sync.js +7 -0
- package/.agents/scripts/lib/orchestration/single-story-close/phases/close-validation.js +22 -4
- package/.agents/scripts/lib/orchestration/single-story-close/phases/confirm-merge.js +104 -57
- package/.agents/scripts/lib/orchestration/single-story-close/phases/merge-wait-recovery.js +16 -16
- package/.agents/scripts/lib/orchestration/single-story-close/phases/normalize-pr-title.js +28 -13
- package/.agents/scripts/lib/orchestration/single-story-close/phases/open-pr.js +1 -0
- package/.agents/scripts/lib/orchestration/single-story-close/phases/pr-body-trailers.js +38 -0
- package/.agents/scripts/lib/orchestration/single-story-close/phases/pre-push.js +24 -16
- package/.agents/scripts/lib/orchestration/single-story-close/phases/pull-request.js +18 -7
- package/.agents/scripts/lib/orchestration/single-story-close/runner.js +60 -34
- package/.agents/scripts/lib/orchestration/story-deliver-terminal.js +1 -1
- package/.agents/scripts/lib/orchestration/story-handoff.js +36 -9
- package/.agents/scripts/lib/test-run-credit.js +26 -0
- package/.agents/scripts/lib/test-tiers.js +14 -10
- package/.agents/scripts/lib/validation-evidence.js +6 -0
- package/.agents/scripts/run-tests.js +162 -92
- package/.agents/skills/core/code-review-and-quality/SKILL.md +1 -1
- package/.agents/workflows/audit-quality.md +7 -0
- package/.agents/workflows/helpers/code-review.md +10 -0
- package/.agents/workflows/helpers/deliver-reference.md +28 -1
- package/docs/CHANGELOG.md +33 -0
- package/package.json +1 -1
|
@@ -5,19 +5,20 @@
|
|
|
5
5
|
* Cross-platform driver for `npm test`. Cleanup runs in-process so reserved
|
|
6
6
|
* temp artefacts are removed even when tests fail (`posttest` would not run).
|
|
7
7
|
*
|
|
8
|
-
* The
|
|
8
|
+
* The tier runs through one in-process `node:test` `run()` call with process
|
|
9
|
+
* isolation: files reach each child one path at a time, so no command line
|
|
10
|
+
* ever carries the whole tier. Children inherit this process's env and cwd
|
|
11
|
+
* (Node 22's `run()` takes neither option), so both are swapped for the run.
|
|
12
|
+
* The env unsets `NOTIFICATION_WEBHOOK_URL` so no test POSTs to a live
|
|
9
13
|
* webhook from `.env` (`MANDREL_ALLOW_TEST_WEBHOOKS=1` opts back in).
|
|
10
14
|
*
|
|
11
|
-
* Every tier enumerates explicit file targets (`node --test` has no negative
|
|
12
|
-
* pattern), which overflows the Windows ~32 767-char command line, so targets
|
|
13
|
-
* are chunked into one spawn per chunk.
|
|
14
|
-
*
|
|
15
15
|
* A green full-tier run in a `story-<id>` checkout deposits close's `test`
|
|
16
16
|
* gate evidence.
|
|
17
17
|
*/
|
|
18
18
|
|
|
19
|
-
import { spawnSync } from 'node:child_process';
|
|
20
19
|
import path from 'node:path';
|
|
20
|
+
import { run } from 'node:test';
|
|
21
|
+
import { spec, tap } from 'node:test/reporters';
|
|
21
22
|
import { fileURLToPath } from 'node:url';
|
|
22
23
|
import { assertNoReservedIdStreams } from './check-test-temp-hygiene.js';
|
|
23
24
|
import { cleanupRepoTestTempArtifacts } from './cleanup-repo-test-temp.js';
|
|
@@ -31,11 +32,21 @@ import {
|
|
|
31
32
|
TEST_CONCURRENCY_MIN,
|
|
32
33
|
TEST_RUNNER_FLAGS,
|
|
33
34
|
} from './lib/test-runner-contract.js';
|
|
34
|
-
import {
|
|
35
|
+
import {
|
|
36
|
+
listTestFilesForTier,
|
|
37
|
+
PASSTHROUGH_FLAGS,
|
|
38
|
+
parseTierArgv,
|
|
39
|
+
unrecognizedArgument,
|
|
40
|
+
} from './lib/test-tiers.js';
|
|
35
41
|
|
|
36
42
|
const __dirname = path.dirname(fileURLToPath(import.meta.url));
|
|
37
43
|
const ROOT = path.resolve(__dirname, '..', '..');
|
|
38
44
|
|
|
45
|
+
/** Child node flags, derived from the shared declaration (module mocks). */
|
|
46
|
+
const CHILD_EXEC_ARGV = TEST_RUNNER_FLAGS.filter((f) =>
|
|
47
|
+
f.startsWith('--experimental-'),
|
|
48
|
+
);
|
|
49
|
+
|
|
39
50
|
export {
|
|
40
51
|
resolveTestConcurrency,
|
|
41
52
|
TEST_CONCURRENCY_MAX,
|
|
@@ -43,52 +54,6 @@ export {
|
|
|
43
54
|
TEST_RUNNER_FLAGS,
|
|
44
55
|
};
|
|
45
56
|
|
|
46
|
-
/**
|
|
47
|
-
* Per-spawn budget for the joined targets. Windows: ~a quarter of the
|
|
48
|
-
* 32 767-char ceiling, leaving room for exe path and flags. POSIX `ARG_MAX` is
|
|
49
|
-
* far larger, so its budget keeps a tier in one spawn (each extra chunk pays a
|
|
50
|
-
* runner start-up and idles cores at its tail).
|
|
51
|
-
*/
|
|
52
|
-
export const MAX_TARGET_CHARS = 8000;
|
|
53
|
-
export const POSIX_MAX_TARGET_CHARS = 100_000;
|
|
54
|
-
|
|
55
|
-
/**
|
|
56
|
-
* @param {NodeJS.Platform} [platform]
|
|
57
|
-
* @returns {number}
|
|
58
|
-
*/
|
|
59
|
-
export function resolveMaxTargetChars(platform = process.platform) {
|
|
60
|
-
return platform === 'win32' ? MAX_TARGET_CHARS : POSIX_MAX_TARGET_CHARS;
|
|
61
|
-
}
|
|
62
|
-
|
|
63
|
-
/**
|
|
64
|
-
* Order-preserving chunks with joined length ≤ `maxChars`. An oversized
|
|
65
|
-
* target gets its own chunk; an empty list yields one empty chunk so the
|
|
66
|
-
* caller still spawns once.
|
|
67
|
-
*
|
|
68
|
-
* @param {string[]} targets
|
|
69
|
-
* @param {number} [maxChars]
|
|
70
|
-
* @returns {string[][]}
|
|
71
|
-
*/
|
|
72
|
-
export function chunkTestTargets(targets, maxChars = MAX_TARGET_CHARS) {
|
|
73
|
-
const chunks = [];
|
|
74
|
-
let current = [];
|
|
75
|
-
let currentLen = 0;
|
|
76
|
-
|
|
77
|
-
for (const target of targets) {
|
|
78
|
-
const addition = target.length + (current.length > 0 ? 1 : 0);
|
|
79
|
-
if (current.length > 0 && currentLen + addition > maxChars) {
|
|
80
|
-
chunks.push(current);
|
|
81
|
-
current = [];
|
|
82
|
-
currentLen = 0;
|
|
83
|
-
}
|
|
84
|
-
current.push(target);
|
|
85
|
-
currentLen += target.length + (current.length > 1 ? 1 : 0);
|
|
86
|
-
}
|
|
87
|
-
|
|
88
|
-
if (current.length > 0) chunks.push(current);
|
|
89
|
-
return chunks.length > 0 ? chunks : [[]];
|
|
90
|
-
}
|
|
91
|
-
|
|
92
57
|
/**
|
|
93
58
|
* Every flag must precede the targets: Node stops parsing options at the
|
|
94
59
|
* first positional and reads a later flag as a file pattern. Hence
|
|
@@ -116,61 +81,166 @@ export function buildNodeTestArgs({
|
|
|
116
81
|
];
|
|
117
82
|
}
|
|
118
83
|
|
|
119
|
-
|
|
84
|
+
const SHARD_RE = /^(\d+)\/(\d+)$/;
|
|
85
|
+
|
|
86
|
+
/** `i/n` with 1 ≤ i ≤ n, else null. */
|
|
87
|
+
function parseShardValue(raw) {
|
|
88
|
+
const match = SHARD_RE.exec(raw ?? '');
|
|
89
|
+
const index = Number(match?.[1]);
|
|
90
|
+
const total = Number(match?.[2]);
|
|
91
|
+
return index >= 1 && index <= total ? { index, total } : null;
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
/**
|
|
95
|
+
* Pull `--shard <i>/<n>` or `--shard=<i>/<n>` out of argv; a malformed or
|
|
96
|
+
* out-of-range value throws the unrecognized-argument error.
|
|
97
|
+
*/
|
|
98
|
+
export function extractShard(argv) {
|
|
99
|
+
const at = argv.findIndex((a) => a === '--shard' || a.startsWith('--shard='));
|
|
100
|
+
if (at === -1) return { shard: null, argv };
|
|
101
|
+
const span = argv[at] === '--shard' ? 2 : 1;
|
|
102
|
+
const flag = argv.slice(at, at + span).join(' ');
|
|
103
|
+
const shard = parseShardValue(flag.slice('--shard '.length));
|
|
104
|
+
if (!shard) throw unrecognizedArgument([flag]);
|
|
105
|
+
return { shard, argv: argv.filter((_, i) => i < at || i >= at + span) };
|
|
106
|
+
}
|
|
107
|
+
|
|
108
|
+
/**
|
|
109
|
+
* Shard `i` of `n` keeps every file whose index ≡ i-1 (mod n) — the rule
|
|
110
|
+
* `node --test --test-shard` applies — so shards partition the list.
|
|
111
|
+
*/
|
|
112
|
+
export function shardTestFiles(files, shard) {
|
|
113
|
+
if (!shard) return files;
|
|
114
|
+
return files.filter((_, i) => i % shard.total === shard.index - 1);
|
|
115
|
+
}
|
|
116
|
+
|
|
117
|
+
/**
|
|
118
|
+
* Map the pass-through argv onto `run()` options. A bare positional is an
|
|
119
|
+
* extra file, as it was on the old `node --test` command line.
|
|
120
|
+
*
|
|
121
|
+
* @param {string[]} rest
|
|
122
|
+
* @returns {{ testNamePatterns?: string[], only: boolean, files: string[] }}
|
|
123
|
+
*/
|
|
124
|
+
export function toRunOptions(rest) {
|
|
125
|
+
const [namePattern, onlyFlag] = PASSTHROUGH_FLAGS;
|
|
126
|
+
const patterns = [];
|
|
127
|
+
const files = [];
|
|
128
|
+
let only = false;
|
|
129
|
+
for (let i = 0; i < rest.length; i += 1) {
|
|
130
|
+
const arg = rest[i];
|
|
131
|
+
if (arg === namePattern) {
|
|
132
|
+
i += 1;
|
|
133
|
+
patterns.push(rest[i]);
|
|
134
|
+
} else if (arg.startsWith(`${namePattern}=`)) {
|
|
135
|
+
patterns.push(arg.slice(namePattern.length + 1));
|
|
136
|
+
} else if (arg === onlyFlag) {
|
|
137
|
+
only = true;
|
|
138
|
+
} else {
|
|
139
|
+
files.push(arg);
|
|
140
|
+
}
|
|
141
|
+
}
|
|
142
|
+
return {
|
|
143
|
+
...(patterns.length > 0 ? { testNamePatterns: patterns } : {}),
|
|
144
|
+
only,
|
|
145
|
+
files,
|
|
146
|
+
};
|
|
147
|
+
}
|
|
148
|
+
|
|
149
|
+
function replaceProcessEnv(next) {
|
|
150
|
+
for (const key of Object.keys(process.env)) {
|
|
151
|
+
if (!Object.hasOwn(next, key)) delete process.env[key];
|
|
152
|
+
}
|
|
153
|
+
Object.assign(process.env, next);
|
|
154
|
+
}
|
|
155
|
+
|
|
156
|
+
/**
|
|
157
|
+
* The default runner: one `run()` over `files`, reported as TAP off a TTY
|
|
158
|
+
* (CI logs, `test-output.txt`) and spec on one. Resolves 1 when any non-todo
|
|
159
|
+
* test fails — a crashing file reports as a failed file-level test.
|
|
160
|
+
*/
|
|
161
|
+
export async function runNodeTests({
|
|
162
|
+
files,
|
|
163
|
+
cwd,
|
|
164
|
+
env,
|
|
165
|
+
testNamePatterns,
|
|
166
|
+
only = false,
|
|
167
|
+
stdout = process.stdout,
|
|
168
|
+
}) {
|
|
169
|
+
const savedEnv = { ...process.env };
|
|
170
|
+
const savedCwd = process.cwd();
|
|
171
|
+
replaceProcessEnv(env);
|
|
172
|
+
process.chdir(cwd);
|
|
173
|
+
let failed = false;
|
|
174
|
+
try {
|
|
175
|
+
const stream = run({
|
|
176
|
+
files,
|
|
177
|
+
isolation: 'process',
|
|
178
|
+
concurrency: resolveTestConcurrency(),
|
|
179
|
+
execArgv: CHILD_EXEC_ARGV,
|
|
180
|
+
testNamePatterns,
|
|
181
|
+
only,
|
|
182
|
+
});
|
|
183
|
+
stream.on('test:fail', (data) => {
|
|
184
|
+
if (!data.todo) failed = true;
|
|
185
|
+
});
|
|
186
|
+
for await (const chunk of stream.compose(stdout.isTTY ? new spec() : tap)) {
|
|
187
|
+
stdout.write(chunk);
|
|
188
|
+
}
|
|
189
|
+
} finally {
|
|
190
|
+
process.chdir(savedCwd);
|
|
191
|
+
replaceProcessEnv(savedEnv);
|
|
192
|
+
}
|
|
193
|
+
return failed ? 1 : 0;
|
|
194
|
+
}
|
|
195
|
+
|
|
196
|
+
export async function runTestSuite({
|
|
120
197
|
argv = process.argv.slice(2),
|
|
121
198
|
cwd = ROOT,
|
|
122
|
-
|
|
199
|
+
runTests = runNodeTests,
|
|
123
200
|
cleanup = cleanupRepoTestTempArtifacts,
|
|
124
201
|
listTargets = listTestFilesForTier,
|
|
125
|
-
maxTargetChars = resolveMaxTargetChars(),
|
|
126
202
|
fixtureStreamGuard = assertNoReservedIdStreams,
|
|
127
203
|
preflight = runTierPreflight,
|
|
128
204
|
depositCredit = reportTestRunCredit,
|
|
205
|
+
stdout = process.stdout,
|
|
129
206
|
} = {}) {
|
|
130
|
-
const {
|
|
207
|
+
const { shard, argv: unsharded } = extractShard(argv);
|
|
208
|
+
const { tier, rest } = parseTierArgv(unsharded);
|
|
131
209
|
|
|
132
210
|
// Nothing has been created yet, so a refusal needs no cleanup.
|
|
133
211
|
const preflightStatus = preflight({ tier, repoRoot: cwd });
|
|
134
212
|
if (preflightStatus !== 0) return preflightStatus;
|
|
135
213
|
|
|
136
|
-
const
|
|
137
|
-
const
|
|
214
|
+
const { files: extraFiles, ...options } = toRunOptions(rest);
|
|
215
|
+
const files = shardTestFiles(
|
|
216
|
+
[...new Set([...listTargets(tier, cwd), ...extraFiles])],
|
|
217
|
+
shard,
|
|
218
|
+
);
|
|
138
219
|
|
|
139
|
-
const env = buildWebhookSafeTestEnv(process.env);
|
|
140
220
|
const startedAt = Date.now();
|
|
141
|
-
let status =
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
|
|
150
|
-
|
|
151
|
-
|
|
152
|
-
spawnError = testRun.error;
|
|
153
|
-
break;
|
|
154
|
-
}
|
|
155
|
-
const chunkStatus = testRun.status ?? 1;
|
|
156
|
-
// First non-zero wins; later chunks still run to report every failure.
|
|
157
|
-
if (chunkStatus !== 0 && status === 0) status = chunkStatus;
|
|
221
|
+
let status = 1;
|
|
222
|
+
try {
|
|
223
|
+
status = await runTests({
|
|
224
|
+
...options,
|
|
225
|
+
files,
|
|
226
|
+
cwd,
|
|
227
|
+
env: buildWebhookSafeTestEnv(process.env),
|
|
228
|
+
stdout,
|
|
229
|
+
});
|
|
230
|
+
} finally {
|
|
231
|
+
cleanup({ repoRoot: cwd });
|
|
158
232
|
}
|
|
159
233
|
|
|
160
|
-
cleanup({ repoRoot: cwd });
|
|
161
|
-
|
|
162
234
|
// Fail a run whose fixture telemetry leaked into the live signals tree,
|
|
163
235
|
// where the retro graduator would count it as real evidence.
|
|
164
236
|
const polluted = fixtureStreamGuard({ cwd });
|
|
165
237
|
if (polluted !== 0 && status === 0) status = polluted;
|
|
166
238
|
|
|
167
|
-
|
|
168
|
-
|
|
239
|
+
// Best-effort; never affects the exit code. A shard is not a full run.
|
|
240
|
+
if (!shard) {
|
|
241
|
+
depositCredit({ cwd, tier, status, durationMs: Date.now() - startedAt });
|
|
169
242
|
}
|
|
170
243
|
|
|
171
|
-
// Best-effort; never affects the exit code.
|
|
172
|
-
depositCredit({ cwd, tier, status, durationMs: Date.now() - startedAt });
|
|
173
|
-
|
|
174
244
|
return status;
|
|
175
245
|
}
|
|
176
246
|
|
|
@@ -188,16 +258,16 @@ Flags:
|
|
|
188
258
|
Tier to run. Default: full — every test file except
|
|
189
259
|
\`tests/e2e/**\`, which only \`--tier e2e\` runs.
|
|
190
260
|
--test-name-pattern <re>, --test-only
|
|
191
|
-
The documented \`node --test\` pass-throughs,
|
|
192
|
-
|
|
193
|
-
Any other \`--flag\` is rejected rather than forwarded
|
|
194
|
-
|
|
195
|
-
|
|
196
|
-
|
|
261
|
+
The documented \`node --test\` pass-throughs, mapped
|
|
262
|
+
onto the \`run()\` options \`testNamePatterns\` / \`only\`.
|
|
263
|
+
Any other \`--flag\` is rejected rather than forwarded,
|
|
264
|
+
so a typo never runs nothing and still exits 0.
|
|
265
|
+
--shard <i>/<n> Run shard i of n (1 ≤ i ≤ n) of the tier's sorted
|
|
266
|
+
file list; the n shards partition it.
|
|
197
267
|
--help Show this message.
|
|
198
268
|
|
|
199
|
-
Exits
|
|
200
|
-
|
|
269
|
+
Exits 1 when any non-todo test fails, or 2 when the tier preflight refuses
|
|
270
|
+
to start the suite.
|
|
201
271
|
`;
|
|
202
272
|
|
|
203
273
|
runAsCli(import.meta.url, async () => runTestSuite(), {
|
|
@@ -16,7 +16,7 @@ description:
|
|
|
16
16
|
- Apply the **five-axis review** to every change: **Correctness, Readability & Simplicity, Architecture, Security, Performance**.
|
|
17
17
|
- Flag dead code artifacts (`_unused` vars, backwards-compat shims, `// removed` comments) and require their removal before merge.
|
|
18
18
|
- Defer to `.agents/rules/security-baseline.md` and the `security-and-hardening` skill for security review; explicit checks include input validation, no hardcoded secrets, parameterized queries, encoded output, authn+authz, and treating external data as untrusted.
|
|
19
|
-
- Bug-fix reviews cover **both** the fix and the regression test; a fix without a failing-then-passing test is not approvable.
|
|
19
|
+
- Bug-fix reviews cover **both** the fix and the regression test; a fix without a failing-then-passing test is not approvable, and neither is one whose commit body states no `Behaviour delta:` or whose diff changes behaviour outside it (`rules/testing-standards.md` § Applying the Standards).
|
|
20
20
|
- **Refactoring is post-green and behaviour-preserving.** Run the refactor pass only when the suite is already green and gates pass; inputs, outputs, side effects, error semantics, and ordering MUST be identical before and after, and existing tests MUST keep passing **without modification** (if a test had to change, behaviour changed — revert).
|
|
21
21
|
- **Lower CRAP by lowering complexity, and remove duplication at the root.** Target the highest-CRAP well-covered functions and the largest verbatim duplications by measurement (`check-baselines.js`), not by smell; extract one well-named helper rather than leaving near-copies. CRAP must not rise and maintainability must not fall on any touched file, and no gate, floor, or threshold may be retuned to make the pass "succeed".
|
|
22
22
|
|
|
@@ -187,6 +187,13 @@ Evaluate the gathered context against the following test quality dimensions:
|
|
|
187
187
|
- Category: file under `Coverage`. A property test whose seed is
|
|
188
188
|
neither pinned nor printed on failure goes under `Flakiness`: a red that
|
|
189
189
|
cannot be reproduced breaks the reproducibility the rubric demands.
|
|
190
|
+
- **Vacuous property tests.** An existing property test is itself a
|
|
191
|
+
finding when its generator cannot reach the inputs the stated
|
|
192
|
+
invariant constrains (a domain that excludes the edge, a filter that
|
|
193
|
+
discards it), or when its assertion would hold for any implementation.
|
|
194
|
+
File it under `Coverage` at **Medium**, or **High** under the High
|
|
195
|
+
conditions above. Name the unreachable input or the trivially true
|
|
196
|
+
assertion.
|
|
190
197
|
- **Name the property.** Each finding states the invariant as a testable
|
|
191
198
|
property (e.g. `decode(encode(x)) === x`; "no transition leaves a
|
|
192
199
|
terminal state") plus its generator shape (the input domain to draw
|
|
@@ -229,6 +229,16 @@ spec decision, a swallowed error on a real failure path) is a 🔴.
|
|
|
229
229
|
disabled-code block removed to make a diff look clean, or a lint-suppression
|
|
230
230
|
comment (`biome-ignore`, `eslint-disable`, `@ts-expect-error`) added to mute
|
|
231
231
|
a real diagnostic instead of fixing it.
|
|
232
|
+
- **Over-broad fixes** — a bug fix that reaches green by changing more than
|
|
233
|
+
the bug: the fix commit's body carries no `Behaviour delta:` line, or the
|
|
234
|
+
diff changes behaviour for inputs outside the stated delta (a widened
|
|
235
|
+
guard, a new early return, a catch-all branch, a default that now applies
|
|
236
|
+
everywhere), or the regression test asserts no input just outside the
|
|
237
|
+
delta unchanged.
|
|
238
|
+
- **Vacuous properties** — a new property test that constrains nothing: no
|
|
239
|
+
`Failure witness:` line records a mutant it was seen to fail against, its
|
|
240
|
+
generator cannot reach the inputs the stated invariant constrains, or its
|
|
241
|
+
assertion would hold for any implementation.
|
|
232
242
|
|
|
233
243
|
For every hit, name the file and line, the taxonomy category, and *why the
|
|
234
244
|
code — not the check — should have changed*. A finding here is legitimate only
|
|
@@ -485,8 +485,35 @@ full-suite lock wait expired) logs a deferred line and the close settles
|
|
|
485
485
|
line naming host contention — neither is reported as failing tests.
|
|
486
486
|
|
|
487
487
|
Every full-suite run ends on `⏲ suite timings: lockWaitMs=… hostWaitMs=…
|
|
488
|
-
testRunMs
|
|
488
|
+
testRunMs=…`. The handoff envelope carries its credited run's figures as
|
|
489
|
+
top-level `lockWait` / `suiteTimings` (null when the depositor ran no suite).
|
|
490
|
+
The close terminal's `suiteTimings` names its `source`: `close` when close
|
|
491
|
+
spawned the suite, `credited-run` when it honoured the handoff's credit;
|
|
492
|
+
`spawns[]` lists every spawn of that run. A `lockWaitMs` large next to
|
|
493
|
+
`testRunMs` is serialization behind sibling suites, not a slow suite — the
|
|
494
|
+
cue for `delivery.execution.workloads`. The
|
|
489
495
|
`coverage.timeoutMs` clock starts at spawn, never in the lock queue; a suite
|
|
490
496
|
that writes `$MANDREL_SUITE_READY_FILE` when its tests start (after a
|
|
491
497
|
consumer load gate) gets a fresh bound for them, so worst-case wall is lock
|
|
492
498
|
wait + 2 × `timeoutMs`.
|
|
499
|
+
|
|
500
|
+
**Delta re-credit after a base move.** When close's base sync merged
|
|
501
|
+
incoming paths (`BASE MOVED`), the `test` gate is the suite gate, the
|
|
502
|
+
pre-sync head holds `test` credit and `project.commands.testChanged` is set,
|
|
503
|
+
close runs that command instead of the full suite, with the pre-sync head in
|
|
504
|
+
`MANDREL_CHANGED_SINCE`, under the full-suite lock. Its log and progress line
|
|
505
|
+
read `test (delta since <sha12>, <n> incoming path(s))`; a green run deposits
|
|
506
|
+
`test` evidence for the merged tree (`scope: delta`, `since: <sha>`) under
|
|
507
|
+
the full-suite identity, so a re-close is credited, and a red one fails the
|
|
508
|
+
close like a red full run. An incoming coverage-config file or Story file,
|
|
509
|
+
no credit, no command, or coverage-capture running the suite logs
|
|
510
|
+
`test delta re-credit not eligible (<reason>)` and runs the full suite — the
|
|
511
|
+
same delta rules as the coverage capture's own delta refresh.
|
|
512
|
+
|
|
513
|
+
**PR-body trailers.** Close appends each git trailer named in
|
|
514
|
+
`delivery.pullRequest.bodyTrailers` (last branch commit carrying it wins) to
|
|
515
|
+
the PR body it opens; workers record one with `git commit --trailer`.
|
|
516
|
+
|
|
517
|
+
**Early merged-PR probe.** Before any sync or gate, close reads the head's
|
|
518
|
+
pull requests; a merged one whose head every surviving branch tip equals
|
|
519
|
+
short-circuits to the land tail instead of re-validating landed work.
|
package/docs/CHANGELOG.md
CHANGED
|
@@ -15,6 +15,39 @@ All notable changes to this project will be documented in this file.
|
|
|
15
15
|
-->
|
|
16
16
|
<!-- markdownlint-disable-file MD004 MD012 MD037 -->
|
|
17
17
|
|
|
18
|
+
## [2.101.0](https://github.com/dsj1984/mandrel/compare/mandrel-v2.100.0...mandrel-v2.101.0) (2026-10-23)
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
### Added
|
|
22
|
+
|
|
23
|
+
* close lifts consumer-declared git trailers from the branch commits into the pull-request body ([#5875](https://github.com/dsj1984/mandrel/issues/5875)) ([#5885](https://github.com/dsj1984/mandrel/issues/5885)) ([443ee08](https://github.com/dsj1984/mandrel/commit/443ee08ace3ba785a34577b5b6a4822eeb238c61))
|
|
24
|
+
* confirm-merge re-arms auto-merge once the advisory check that disarmed it reports green on the same head, and the block names that check ([#5876](https://github.com/dsj1984/mandrel/issues/5876)) ([#5886](https://github.com/dsj1984/mandrel/issues/5886)) ([85a8aac](https://github.com/dsj1984/mandrel/commit/85a8aacfc6e4525d4b3d10aae859ac9dffd55c31))
|
|
25
|
+
* handoff and close envelopes carry the credited run's lock wait and suite timings, so the serialization cost of a delivery is visible per run ([#5879](https://github.com/dsj1984/mandrel/issues/5879)) ([#5888](https://github.com/dsj1984/mandrel/issues/5888)) ([68e9683](https://github.com/dsj1984/mandrel/commit/68e9683ccc2c41b16ecaf0b71485ae951d4b5ec1))
|
|
26
|
+
* the code-review provider reviews a large diff file by file within the prompt cap instead of truncating it ([#5878](https://github.com/dsj1984/mandrel/issues/5878)) ([#5882](https://github.com/dsj1984/mandrel/issues/5882)) ([e64a84e](https://github.com/dsj1984/mandrel/commit/e64a84e780c6546723466d9c4df1d46cbfb3ee46))
|
|
27
|
+
* the lint driver names every task that failed, with its exit code, and flags a crash exit ([#5889](https://github.com/dsj1984/mandrel/issues/5889)) ([#5891](https://github.com/dsj1984/mandrel/issues/5891)) ([7db5a92](https://github.com/dsj1984/mandrel/commit/7db5a923679fbe8158c4eb1541ed4cc7cc51447e))
|
|
28
|
+
* when the base moves between handoff and close, the `test` gate re-credits by running only the tests the incoming commits affect ([#5880](https://github.com/dsj1984/mandrel/issues/5880)) ([#5890](https://github.com/dsj1984/mandrel/issues/5890)) ([66423e3](https://github.com/dsj1984/mandrel/commit/66423e36c06dcfdb44564516c74d1cc829bc932d))
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
### Fixed
|
|
32
|
+
|
|
33
|
+
* close probes the head's pull request before validation and short-circuits to the land tail when it already merged ([#5877](https://github.com/dsj1984/mandrel/issues/5877)) ([#5887](https://github.com/dsj1984/mandrel/issues/5887)) ([ddc1b52](https://github.com/dsj1984/mandrel/commit/ddc1b52c2f081928c6eff297803c5e60a34ece9c))
|
|
34
|
+
* **deps:** drop the braces audit exception now that GHSA-vfj7-8cjw-p6xm is withdrawn ([#5883](https://github.com/dsj1984/mandrel/issues/5883)) ([364f547](https://github.com/dsj1984/mandrel/commit/364f54705372e26d1b5d1c8d628fc9628940efbf))
|
|
35
|
+
|
|
36
|
+
## [2.100.0](https://github.com/dsj1984/mandrel/compare/mandrel-v2.99.0...mandrel-v2.100.0) (2026-10-23)
|
|
37
|
+
|
|
38
|
+
|
|
39
|
+
### Fixed
|
|
40
|
+
|
|
41
|
+
* **ci:** guard fromJSON on the release PR output so a release merge can publish (refs [#5872](https://github.com/dsj1984/mandrel/issues/5872)) ([#5873](https://github.com/dsj1984/mandrel/issues/5873)) ([bcf11b9](https://github.com/dsj1984/mandrel/commit/bcf11b9722fe47f42a832218909bdb3cc5495a45))
|
|
42
|
+
|
|
43
|
+
## [2.99.0](https://github.com/dsj1984/mandrel/compare/mandrel-v2.98.0...mandrel-v2.99.0) (2026-10-23)
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
### Added
|
|
47
|
+
|
|
48
|
+
* adopt verification-discipline rules: bug-fix behaviour delta, write-time property tests with failure witnesses, caller obligations ([#5863](https://github.com/dsj1984/mandrel/issues/5863)) ([#5864](https://github.com/dsj1984/mandrel/issues/5864)) ([d746c14](https://github.com/dsj1984/mandrel/commit/d746c1442808f3c4d7f39996027e0d57df500b94))
|
|
49
|
+
* cut the required-CI critical path: one-pass node:test orchestrator, sharded Windows Smoke, leaner validate job, ruleset drift guard ([#5866](https://github.com/dsj1984/mandrel/issues/5866)) ([#5871](https://github.com/dsj1984/mandrel/issues/5871)) ([64f01a1](https://github.com/dsj1984/mandrel/commit/64f01a1c6b730c22e48a8fc004490dd613c700e2))
|
|
50
|
+
|
|
18
51
|
## [2.98.0](https://github.com/dsj1984/mandrel/compare/mandrel-v2.97.0...mandrel-v2.98.0) (2026-10-22)
|
|
19
52
|
|
|
20
53
|
|
package/package.json
CHANGED