mandrel 2.70.0 → 2.71.0
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/README.md +8 -9
- package/.agents/agents/acceptance-critic.md +1 -0
- package/.agents/agents/auditor.md +1 -0
- package/.agents/agents/plan-critic.md +1 -0
- package/.agents/agents/story-worker.md +63 -64
- package/.agents/docs/agentrc-reference.json +2 -1
- package/.agents/docs/configuration.md +7 -8
- package/.agents/rules/git-conventions-reference.md +2 -2
- package/.agents/schemas/agentrc.schema.json +19 -2
- package/.agents/scripts/acceptance-eval.js +194 -15
- package/.agents/scripts/deliver-run.js +92 -43
- package/.agents/scripts/lib/audit-suite/index.js +1 -1
- package/.agents/scripts/lib/audit-suite/story-checklist.js +65 -0
- package/.agents/scripts/lib/audit-to-stories/audit-label-taxonomy.js +2 -2
- package/.agents/scripts/lib/bootstrap/issue-forms-template.js +1 -1
- package/.agents/scripts/lib/cli-args.js +22 -0
- package/.agents/scripts/lib/close-validation/gates.js +17 -3
- package/.agents/scripts/lib/config/agent-models.js +117 -0
- package/.agents/scripts/lib/config-settings-schema-delivery.js +13 -1
- package/.agents/scripts/lib/config-settings-schema-quality.js +1 -1
- package/.agents/scripts/lib/generated/agentrc-validator.js +1 -1
- package/.agents/scripts/lib/git/sync-from-base.js +89 -17
- package/.agents/scripts/lib/label-taxonomy.js +13 -3
- package/.agents/scripts/lib/notifications/notifier.js +11 -15
- package/.agents/scripts/lib/observability/close-telemetry.js +19 -3
- package/.agents/scripts/lib/observability/source-classifier.js +1 -0
- package/.agents/scripts/lib/orchestration/code-review.js +2 -2
- package/.agents/scripts/lib/orchestration/file-assumptions.js +45 -11
- package/.agents/scripts/lib/orchestration/plan-context.js +17 -10
- package/.agents/scripts/lib/orchestration/plan-persist/changes-repair.js +130 -24
- package/.agents/scripts/lib/orchestration/plan-persist/run-plan-persist.js +19 -16
- package/.agents/scripts/lib/orchestration/plan-persist/story-ops.js +1 -0
- package/.agents/scripts/lib/orchestration/plan-persist/summary.js +4 -3
- package/.agents/scripts/lib/orchestration/resolve-stories.js +10 -2
- package/.agents/scripts/lib/orchestration/review-providers/native.js +5 -165
- package/.agents/scripts/lib/orchestration/single-story-close/failed-terminal.js +14 -2
- package/.agents/scripts/lib/orchestration/single-story-close/phases/base-sync.js +151 -56
- package/.agents/scripts/lib/orchestration/single-story-close/phases/confirm-merge.js +4 -0
- package/.agents/scripts/lib/orchestration/single-story-close/phases/options.js +20 -4
- package/.agents/scripts/lib/orchestration/single-story-close/runner.js +26 -17
- package/.agents/scripts/lib/orchestration/story-handoff.js +849 -0
- package/.agents/scripts/lib/orchestration/story-init-result.js +83 -0
- package/.agents/scripts/lib/orchestration/task-body-validator.js +35 -5
- package/.agents/scripts/lib/orchestration/ticket-validator-sizing.js +1 -1
- package/.agents/scripts/lib/orchestration/ticket-validator.js +20 -2
- package/.agents/scripts/lib/single-story/confirm-merge.js +44 -7
- package/.agents/scripts/lib/story-body/story-body.js +40 -5
- package/.agents/scripts/lib/templates/decomposer-prompts.js +33 -36
- package/.agents/scripts/single-story-close.js +8 -0
- package/.agents/scripts/single-story-init.js +17 -32
- package/.agents/scripts/story-handoff.js +112 -0
- package/.agents/scripts/sync-claude-agents.js +58 -27
- package/.agents/workflows/helpers/acceptance-self-eval.md +24 -18
- package/.agents/workflows/helpers/code-review.md +3 -3
- package/.agents/workflows/helpers/deliver-digest.md +79 -80
- package/.agents/workflows/helpers/deliver-light.md +9 -7
- package/.agents/workflows/helpers/deliver-reference.md +38 -22
- package/.agents/workflows/helpers/deliver-story-reference.md +11 -9
- package/.agents/workflows/helpers/deliver-story.md +30 -23
- package/.agents/workflows/helpers/plan-reference.md +24 -9
- package/docs/CHANGELOG.md +19 -0
- package/lib/cli/registry.js +7 -0
- package/package.json +4 -3
- package/.agents/scripts/lib/orchestration/review-providers/scoped-lint.js +0 -272
|
@@ -13,6 +13,7 @@
|
|
|
13
13
|
|
|
14
14
|
import { existsSync } from 'node:fs';
|
|
15
15
|
import path from 'node:path';
|
|
16
|
+
import { buildStoryChecklist } from './lib/audit-suite/index.js';
|
|
16
17
|
import { parseSprintArgs } from './lib/cli-args.js';
|
|
17
18
|
import { runAsCli } from './lib/cli-utils.js';
|
|
18
19
|
import {
|
|
@@ -37,12 +38,12 @@ import {
|
|
|
37
38
|
planFastForward,
|
|
38
39
|
} from './lib/orchestration/git-cleanup/phases/fast-forward.js';
|
|
39
40
|
import { verifyRemote } from './lib/orchestration/remote-verifier.js';
|
|
40
|
-
import { pinRunScopedConfig } from './lib/orchestration/run-scoped-config.js';
|
|
41
41
|
import {
|
|
42
42
|
acquireStoryLease,
|
|
43
43
|
releaseStoryLease,
|
|
44
44
|
} from './lib/orchestration/single-story-lease-guard.js';
|
|
45
45
|
import { handleRemoteVerificationFailure } from './lib/orchestration/story-init-remote.js';
|
|
46
|
+
import { composeStoryInitResult } from './lib/orchestration/story-init-result.js';
|
|
46
47
|
import {
|
|
47
48
|
STATE_LABELS,
|
|
48
49
|
transitionTicketState,
|
|
@@ -564,6 +565,7 @@ export async function runSingleStoryInit({
|
|
|
564
565
|
injectedMaterialize = materializeBaseBranch,
|
|
565
566
|
injectedSeedBranch = seedStoryBranch,
|
|
566
567
|
injectedProvisionWorktree = provisionWorktree,
|
|
568
|
+
injectedBuildChecklist = buildStoryChecklist,
|
|
567
569
|
} = {}) {
|
|
568
570
|
const parsed =
|
|
569
571
|
storyIdParam !== undefined
|
|
@@ -688,35 +690,26 @@ export async function runSingleStoryInit({
|
|
|
688
690
|
}
|
|
689
691
|
}
|
|
690
692
|
|
|
691
|
-
|
|
692
|
-
|
|
693
|
-
|
|
694
|
-
|
|
695
|
-
|
|
696
|
-
|
|
697
|
-
|
|
698
|
-
const result = {
|
|
693
|
+
// Every path gets the checklist; `buildStoryChecklist` never throws.
|
|
694
|
+
const checklistPath = dryRun
|
|
695
|
+
? null
|
|
696
|
+
: injectedBuildChecklist({ storyId, body: story.body, config, progress })
|
|
697
|
+
.checklistPath;
|
|
698
|
+
const { result, summary } = composeStoryInitResult({
|
|
699
699
|
storyId,
|
|
700
|
-
epicId: null,
|
|
701
|
-
standalone: true,
|
|
702
700
|
storyBranch,
|
|
703
701
|
baseBranch,
|
|
704
|
-
|
|
705
|
-
|
|
706
|
-
|
|
707
|
-
worktreeEnabled: runtime.worktreeEnabled,
|
|
702
|
+
config,
|
|
703
|
+
story,
|
|
704
|
+
runtime,
|
|
708
705
|
workCwd,
|
|
709
706
|
worktreeCreated,
|
|
710
707
|
installStatus,
|
|
711
|
-
|
|
712
|
-
installFailed: installStatus.status === 'failed',
|
|
713
|
-
// Closed-Story worktree sweep outcome; a failure degrades here, never
|
|
714
|
-
// into an init failure. `null` under --dry-run.
|
|
715
|
-
worktreeSweep: worktreeSweep ?? null,
|
|
708
|
+
worktreeSweep,
|
|
716
709
|
dryRun,
|
|
717
|
-
|
|
718
|
-
|
|
719
|
-
};
|
|
710
|
+
remote,
|
|
711
|
+
checklistPath,
|
|
712
|
+
});
|
|
720
713
|
|
|
721
714
|
// The envelope (stdout + disk) is the only record; no ticket comment. Full
|
|
722
715
|
// result goes to a temp log, stdout gets the fields the caller acts on.
|
|
@@ -725,15 +718,7 @@ export async function runSingleStoryInit({
|
|
|
725
718
|
result,
|
|
726
719
|
scope: storyId,
|
|
727
720
|
config,
|
|
728
|
-
summary
|
|
729
|
-
storyId,
|
|
730
|
-
storyBranch,
|
|
731
|
-
workCwd,
|
|
732
|
-
worktreeCreated,
|
|
733
|
-
dependenciesInstalled,
|
|
734
|
-
remoteVerified: result.remoteVerified,
|
|
735
|
-
dryRun,
|
|
736
|
-
},
|
|
721
|
+
summary,
|
|
737
722
|
});
|
|
738
723
|
progress(
|
|
739
724
|
'DONE',
|
|
@@ -0,0 +1,112 @@
|
|
|
1
|
+
#!/usr/bin/env node
|
|
2
|
+
|
|
3
|
+
/**
|
|
4
|
+
* story-handoff.js — the story-worker's whole post-implementation tail in one
|
|
5
|
+
* command: preflight (lint + quality-preview + baselined ratchets) → merge
|
|
6
|
+
* origin/<base> → the one credited run → `--seat-missing` baseline seating →
|
|
7
|
+
* push + remote-ref check → held Story-scope review. Prints one JSON envelope on stdout.
|
|
8
|
+
*
|
|
9
|
+
* Exit 0 `ready` (hand off) · 2 `fix-required` (fix, commit, re-run; labels
|
|
10
|
+
* untouched) · 1 `blocked` (flips agent::blocked + posts friction) or a usage
|
|
11
|
+
* error. Idempotent: a re-run on an unchanged tree spawns no suite, seats
|
|
12
|
+
* nothing, pushes nothing and recomputes no review. Never runs close, opens a
|
|
13
|
+
* PR, or writes any other label.
|
|
14
|
+
*
|
|
15
|
+
* @see .agents/scripts/lib/orchestration/story-handoff.js
|
|
16
|
+
*/
|
|
17
|
+
|
|
18
|
+
import { parseArgs } from 'node:util';
|
|
19
|
+
|
|
20
|
+
import { runAsCli } from './lib/cli-utils.js';
|
|
21
|
+
import { resolveConfig } from './lib/config-resolver.js';
|
|
22
|
+
import { runStoryHandoff } from './lib/orchestration/story-handoff.js';
|
|
23
|
+
import { createProvider } from './lib/provider-factory.js';
|
|
24
|
+
import { computeStoryReviewDeposit } from './story-review-compute.js';
|
|
25
|
+
|
|
26
|
+
const USAGE = {
|
|
27
|
+
invocation:
|
|
28
|
+
'node .agents/scripts/story-handoff.js --story <id> [--cwd <workCwd>]',
|
|
29
|
+
summary:
|
|
30
|
+
"Run the story-worker's post-implementation tail — preflight, base merge, the one credited run, baseline seating, push and held review — and print one envelope: ready (exit 0), fix-required (exit 2) or blocked (exit 1).",
|
|
31
|
+
flags: [
|
|
32
|
+
['--story <id>', 'Story issue number; the branch is story-<id>.'],
|
|
33
|
+
['--cwd <path>', "The Story's worktree (default: the current directory)."],
|
|
34
|
+
],
|
|
35
|
+
notes: [
|
|
36
|
+
'Exit codes:\n 0 ready — hand off\n 2 fix-required — fix, commit, re-run (labels untouched)\n 1 blocked — agent::blocked + friction comment, or a usage error',
|
|
37
|
+
],
|
|
38
|
+
};
|
|
39
|
+
|
|
40
|
+
/**
|
|
41
|
+
* @param {string[]} argv
|
|
42
|
+
* @returns {{ storyId: number|null, cwd: string|null }}
|
|
43
|
+
*/
|
|
44
|
+
function parseArgv(argv) {
|
|
45
|
+
const { values } = parseArgs({
|
|
46
|
+
args: argv,
|
|
47
|
+
options: {
|
|
48
|
+
story: { type: 'string' },
|
|
49
|
+
cwd: { type: 'string' },
|
|
50
|
+
},
|
|
51
|
+
strict: false,
|
|
52
|
+
});
|
|
53
|
+
const storyId = Number.parseInt(values.story ?? '', 10);
|
|
54
|
+
return {
|
|
55
|
+
storyId: Number.isInteger(storyId) && storyId > 0 ? storyId : null,
|
|
56
|
+
cwd: values.cwd ?? null,
|
|
57
|
+
};
|
|
58
|
+
}
|
|
59
|
+
|
|
60
|
+
/**
|
|
61
|
+
* @param {string[]} [argv]
|
|
62
|
+
* @param {{
|
|
63
|
+
* resolveConfigImpl?: typeof resolveConfig,
|
|
64
|
+
* runHandoffImpl?: typeof runStoryHandoff,
|
|
65
|
+
* stdout?: { write: (s: string) => void },
|
|
66
|
+
* stderr?: { write: (s: string) => void },
|
|
67
|
+
* cwd?: string,
|
|
68
|
+
* }} [deps]
|
|
69
|
+
* @returns {Promise<{ envelope: object, exitCode: number }>}
|
|
70
|
+
*/
|
|
71
|
+
export async function runStoryHandoffCli(
|
|
72
|
+
argv = process.argv.slice(2),
|
|
73
|
+
deps = {},
|
|
74
|
+
) {
|
|
75
|
+
const {
|
|
76
|
+
resolveConfigImpl = resolveConfig,
|
|
77
|
+
runHandoffImpl = runStoryHandoff,
|
|
78
|
+
stdout = process.stdout,
|
|
79
|
+
stderr = process.stderr,
|
|
80
|
+
cwd: defaultCwd = process.cwd(),
|
|
81
|
+
} = deps;
|
|
82
|
+
const { storyId, cwd } = parseArgv(argv);
|
|
83
|
+
if (!storyId) {
|
|
84
|
+
throw new Error(
|
|
85
|
+
'story-handoff: --story <id> is required (a positive integer).',
|
|
86
|
+
);
|
|
87
|
+
}
|
|
88
|
+
const workCwd = cwd ?? defaultCwd;
|
|
89
|
+
const config = resolveConfigImpl({ cwd: workCwd });
|
|
90
|
+
const outcome = await runHandoffImpl(
|
|
91
|
+
{ storyId, cwd: workCwd, config },
|
|
92
|
+
{
|
|
93
|
+
computeReview: computeStoryReviewDeposit,
|
|
94
|
+
createProviderFn: createProvider,
|
|
95
|
+
progress: (tag, msg) => stderr.write(`[story-handoff] [${tag}] ${msg}\n`),
|
|
96
|
+
},
|
|
97
|
+
);
|
|
98
|
+
stdout.write(`${JSON.stringify(outcome.envelope, null, 2)}\n`);
|
|
99
|
+
return outcome;
|
|
100
|
+
}
|
|
101
|
+
|
|
102
|
+
async function main() {
|
|
103
|
+
const { exitCode } = await runStoryHandoffCli();
|
|
104
|
+
return exitCode;
|
|
105
|
+
}
|
|
106
|
+
|
|
107
|
+
runAsCli(import.meta.url, main, {
|
|
108
|
+
source: 'story-handoff',
|
|
109
|
+
propagateExitCode: true,
|
|
110
|
+
errorPrefix: '[story-handoff] ❌ Fatal error',
|
|
111
|
+
usage: USAGE,
|
|
112
|
+
});
|
|
@@ -5,6 +5,7 @@
|
|
|
5
5
|
* `.claude/agents/` tree — the sibling of `sync-claude-commands.js`, with the
|
|
6
6
|
* same payload-wins shadowing and orphan-reap. A role agent runs on its own
|
|
7
7
|
* system prompt (no entry-doc `@`-import closure), which is the point of routing to it.
|
|
8
|
+
* A `delivery.routing.agentModels` entry overrides the role's `model:` default.
|
|
8
9
|
*/
|
|
9
10
|
|
|
10
11
|
// cli-opt-out: top-level-await script with no main() function — runAsCli wraps an async main, which doesn't apply here.
|
|
@@ -12,6 +13,8 @@ import fs from 'node:fs';
|
|
|
12
13
|
import path from 'node:path';
|
|
13
14
|
|
|
14
15
|
import { applyHeader } from './lib/command-header.js';
|
|
16
|
+
import { applyAgentModel, getAgentModels } from './lib/config/agent-models.js';
|
|
17
|
+
import { resolveConfig } from './lib/config-resolver.js';
|
|
15
18
|
import { Logger } from './lib/Logger.js';
|
|
16
19
|
|
|
17
20
|
// cwd, never `__dirname/../..`, which lands inside node_modules when installed.
|
|
@@ -52,13 +55,23 @@ const isTopLevelAgent = (entry) => entry.isFile() && entry.name.endsWith('.md');
|
|
|
52
55
|
// Payload first, so it wins a collision.
|
|
53
56
|
const SRC_DIRS = [PAYLOAD_SRC, LOCAL_SRC].filter(dirExists);
|
|
54
57
|
|
|
55
|
-
/**
|
|
56
|
-
|
|
57
|
-
|
|
58
|
+
/**
|
|
59
|
+
* Named, not inline: an anonymous callback in this spawned-only script has no
|
|
60
|
+
* coverage coordinates for the CRAP seat to resolve.
|
|
61
|
+
*
|
|
62
|
+
* @param {string} dir
|
|
63
|
+
* @returns {Array<{dir: string, name: string}>}
|
|
64
|
+
*/
|
|
65
|
+
function agentEntriesIn(dir) {
|
|
66
|
+
return fs
|
|
58
67
|
.readdirSync(dir, { withFileTypes: true })
|
|
59
68
|
.filter(isTopLevelAgent)
|
|
60
|
-
.map((e)
|
|
61
|
-
|
|
69
|
+
.map(function toAgentEntry(e) {
|
|
70
|
+
return { dir, name: e.name };
|
|
71
|
+
});
|
|
72
|
+
}
|
|
73
|
+
|
|
74
|
+
const entries = SRC_DIRS.flatMap(agentEntriesIn);
|
|
62
75
|
|
|
63
76
|
const byName = new Map();
|
|
64
77
|
for (const e of entries) {
|
|
@@ -90,29 +103,47 @@ for (const name of listExistingAgents()) {
|
|
|
90
103
|
}
|
|
91
104
|
}
|
|
92
105
|
|
|
93
|
-
//
|
|
106
|
+
// Resolved once: an invalid override (an unknown role) fails the sync here.
|
|
107
|
+
const agentModels = getAgentModels(resolveConfig({ cwd: PROJECT_ROOT }));
|
|
108
|
+
|
|
109
|
+
/**
|
|
110
|
+
* @param {string} name
|
|
111
|
+
* @param {string} content
|
|
112
|
+
* @returns {string}
|
|
113
|
+
*/
|
|
114
|
+
function withModelOverride(name, content) {
|
|
115
|
+
const model = agentModels[name.replace(/\.md$/, '')];
|
|
116
|
+
return model ? applyAgentModel(content, model) : content;
|
|
117
|
+
}
|
|
118
|
+
|
|
94
119
|
let synced = 0;
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
}
|
|
115
|
-
|
|
120
|
+
|
|
121
|
+
/**
|
|
122
|
+
* The header goes after any frontmatter, so `---` stays on line 1.
|
|
123
|
+
*
|
|
124
|
+
* @param {{ dir: string, name: string }} entry
|
|
125
|
+
* @returns {Promise<void>}
|
|
126
|
+
*/
|
|
127
|
+
async function syncEntry({ dir, name }) {
|
|
128
|
+
const isLocal = dir === LOCAL_SRC;
|
|
129
|
+
const header = isLocal ? LOCAL_HEADER : HEADER;
|
|
130
|
+
const content = await fs.promises.readFile(path.join(dir, name), 'utf8');
|
|
131
|
+
const dest = path.join(DEST_DIR, name);
|
|
132
|
+
const target = applyHeader(withModelOverride(name, content), header);
|
|
133
|
+
|
|
134
|
+
try {
|
|
135
|
+
const existingContent = await fs.promises.readFile(dest, 'utf8');
|
|
136
|
+
if (existingContent === target) return;
|
|
137
|
+
} catch (err) {
|
|
138
|
+
if (err.code !== 'ENOENT') throw err;
|
|
139
|
+
}
|
|
140
|
+
|
|
141
|
+
await fs.promises.writeFile(dest, target, 'utf8');
|
|
142
|
+
synced++;
|
|
143
|
+
Logger.info(` synced ${name}`);
|
|
144
|
+
}
|
|
145
|
+
|
|
146
|
+
await Promise.all(Array.from(byName.values()).map(syncEntry));
|
|
116
147
|
|
|
117
148
|
Logger.info(
|
|
118
149
|
`\n✔ ${synced} file(s) synced, ${sourceSet.size} total agents in .claude/agents/`,
|
|
@@ -36,15 +36,20 @@ per-criterion, mid-delivery, and evaluates the actual work product.
|
|
|
36
36
|
alone**:
|
|
37
37
|
|
|
38
38
|
> ```bash
|
|
39
|
-
> node <main-repo>/.agents/scripts/
|
|
39
|
+
> node <main-repo>/.agents/scripts/acceptance-eval.js --story <storyId> --init --cwd <workCwd>
|
|
40
40
|
> ```
|
|
41
41
|
>
|
|
42
|
-
> One call
|
|
43
|
-
>
|
|
44
|
-
> `
|
|
45
|
-
>
|
|
46
|
-
>
|
|
47
|
-
>
|
|
42
|
+
> One call writes the verdict **skeleton** — one record per
|
|
43
|
+
> `acceptance[]` item, in order, `index` and `criterion` filled, `verdict`
|
|
44
|
+
> and `evidence` empty, plus `storyId`, `schemaVersion`, the next `round`
|
|
45
|
+
> and HEAD — under `temp/scratch/story-<id>/`, and prints its path, the
|
|
46
|
+
> change set computed once (`files`) and the `verdictOwner`, derived by the
|
|
47
|
+
> same function `ceremony-derive.js` uses: **`minimal` / `standard` →
|
|
48
|
+
> `inline`** (the default — you fill the skeleton yourself), **`strict` →
|
|
49
|
+
> `fresh`** (dispatch the maker-blind critic with that `files` list).
|
|
50
|
+
> `ceremony-derive.js` stays for close and for a critic hand-off outside
|
|
51
|
+
> this loop; the level it derives feeds `review-depth.js`, not this
|
|
52
|
+
> decision.
|
|
48
53
|
|
|
49
54
|
**Never run both**, and never run a preliminary self-assessment before
|
|
50
55
|
dispatching a fresh critic — the redundant pre-pass buys no measurable
|
|
@@ -95,13 +100,11 @@ per-criterion, mid-delivery, and evaluates the actual work product.
|
|
|
95
100
|
without being respawned; a stale or absent stamp reports `spawn: true` and
|
|
96
101
|
the command runs for real. The credited run itself is stated once, in
|
|
97
102
|
[`deliver-digest.md`](deliver-digest.md) § 5.
|
|
98
|
-
+
|
|
103
|
+
+ **Fills the skeleton** into **one** verdict file conforming to
|
|
99
104
|
[`acceptance-eval-verdict.schema.json`](../../schemas/acceptance-eval-verdict.schema.json):
|
|
100
|
-
|
|
101
|
-
verifyEvidence[] }` record
|
|
102
|
-
|
|
103
|
-
`commitSha`. A fresh critic **returns that path to you** rather than
|
|
104
|
-
calling the gate itself.
|
|
105
|
+
every `{ index, criterion, verdict: met|partial|unmet, evidence,
|
|
106
|
+
verifyEvidence[] }` record, in acceptance-array order. A fresh critic
|
|
107
|
+
**returns that path to you** rather than calling the gate itself.
|
|
105
108
|
2. **Decide — exactly one gate call per round.** Run the gate against that one
|
|
106
109
|
verdict file (the caller's Step 1a names the exact invocation — omit
|
|
107
110
|
`--epic`). The gate **scores the verdict the round produced** — schema
|
|
@@ -115,8 +118,10 @@ per-criterion, mid-delivery, and evaluates the actual work product.
|
|
|
115
118
|
The gate reads the Story's `acceptance[]` count itself (Story #5313): a
|
|
116
119
|
verdict whose `criteria[]` length differs — one covering only part of the
|
|
117
120
|
Story — is rejected **before scoring**, with an error naming the count and
|
|
118
|
-
consuming **no round**.
|
|
119
|
-
|
|
121
|
+
consuming **no round**. A skeleton record left unfilled (empty `verdict`
|
|
122
|
+
or `evidence`) is likewise rejected before scoring, naming the unfilled
|
|
123
|
+
indices, with no round consumed. `--expected-criteria` is still accepted
|
|
124
|
+
but redundant; when passed it must agree with that count.
|
|
120
125
|
|
|
121
126
|
> **Why one call per round and not several.** The round counter is
|
|
122
127
|
> **Story-scoped** — derived by counting `acceptance-eval` signals in the
|
|
@@ -127,11 +132,12 @@ per-criterion, mid-delivery, and evaluates the actual work product.
|
|
|
127
132
|
The gate validates the verdict against the schema, applies the round cap,
|
|
128
133
|
emits the per-criterion `acceptance-eval` signal into the retro / feedback
|
|
129
134
|
substrate, prints a JSON envelope, and exits with one of three decisions:
|
|
130
|
-
+ **`decision: "proceed"`** (every criterion `met`) → exit 0.
|
|
131
|
-
|
|
135
|
+
+ **`decision: "proceed"`** (every criterion `met`) → exit 0. Run the one
|
|
136
|
+
tail command, `story-handoff.js` ([`deliver-digest.md`](deliver-digest.md)
|
|
137
|
+
§ 5).
|
|
132
138
|
+ **`decision: "redraft"`** (some `partial`/`unmet`, rounds remaining) →
|
|
133
139
|
exit 0. Redraft the flagged criteria (named in `unmetCriteria[]`), commit
|
|
134
|
-
the fix,
|
|
140
|
+
the fix, re-run `--init` for the next round's skeleton, and score again.
|
|
135
141
|
+ **`decision: "block"`** (round cap reached, criteria still unmet) → exit
|
|
136
142
|
non-zero. **Do not proceed to close.** Take the caller's blocked path
|
|
137
143
|
(transition to `agent::blocked`) and post a `friction` comment naming the
|
|
@@ -79,7 +79,7 @@ How each tier changes the review protocol:
|
|
|
79
79
|
The LLM-backed review providers (code-review, codex, security-review,
|
|
80
80
|
ultrareview) render the resolved `depth` into the prompt/instructions they emit so the underlying
|
|
81
81
|
model actually changes thoroughness. The native provider deliberately ignores
|
|
82
|
-
`depth` — its mechanical
|
|
82
|
+
`depth` — its mechanical maintainability sweep already scales with diff
|
|
83
83
|
size, and there is no "review harder" knob a deterministic scorer can turn (its
|
|
84
84
|
module JSDoc documents this). When you (the host LLM) perform the Step 2 pillar
|
|
85
85
|
review yourself, honor the `depth` semantics above directly.
|
|
@@ -108,8 +108,8 @@ diff `baseRef..headRef`, with the LLM-backed providers honoring `depth`
|
|
|
108
108
|
The pipeline will:
|
|
109
109
|
|
|
110
110
|
- Generate a `git diff baseRef..headRef`.
|
|
111
|
-
- Calculate maintainability scores for all new/modified files
|
|
112
|
-
-
|
|
111
|
+
- Calculate maintainability scores for all new/modified files (lint is a
|
|
112
|
+
close-validation gate, so the review does not re-run it).
|
|
113
113
|
- Post a structured summary report to the `[TICKET_ID]` issue.
|
|
114
114
|
|
|
115
115
|
### Story scope runs no lens pass
|