mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-01 06:24:41 +01:00
feat(review): variant G parts 1 and 3: blocking floor in both prose voices, specialists at medium (GSTA-167)
Part 1: the native adversarial and outside-voice prompts end with the blocking
floor ("would fail a test, break production, or lose data or secrets") and ask
each finding for Severity and Blocks: yes|no. Additive rule: a finding is
CRITICAL when its label rule says so or it says Blocks: yes; Blocks: no never
lowers one (proseVoiceSeverity, BLOCKING_FLOOR in lib/review-scope.ts).
Part 3: ROLE_EFFORT puts specialists at medium; Red Team, native adversarial
and fix-check stay full; light's batched specialist (carries the Red Team
prompt) stays full; --no-tiers sends specialists to host.
Repinned reviewer briefs with no-loss replay G1 (live Arm G1, not yet run):
ship/sections/review-army.md, ship/sections/adversarial.md,
review/sections/adversarial.md, lib/review-depth.ts. Merge only on G1's pass.
Review-skill parity ratio 1.3136 -> 1.3180 and the gstack-review size pins
+537 for the approved +0.3k tokens per voice.
Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
garrytanandcapy-ai[bot] committed
1 parent
33d6029273
commit
9c1e0a089d
19 files changed
+178
-60
No files matched your search
@@ -44,7 +44,7 @@ const HELP = `gstack-review-plan — the review depth of the next /ship step (do
|
||||
--depth-floor standard|full raise the depth to at least this (never lowers it); /ship passes its prompt flag on every run
|
||||
--range-base <sha> the fix range's base (this pass's PASS_HEAD): after a fixed blocker on a diff below full depth, a
|
||||
committed range of at most ${SCOPED_RANGE_LINES} runtime lines plans a scoped pass; anything unread plans the full pass
|
||||
--no-tiers audits and watchers at the host's default effort too (as gstack-config review_effort_tiers off does)
|
||||
--no-tiers specialists, audits and watchers at the host's default effort too (as gstack-config review_effort_tiers off does)
|
||||
--json the plan as JSON (depth, runtime_lines, rules, errors with input and repair, gate_scan, per-dispatch exclude)
|
||||
--pass1-depth <d> pass 1's REVIEW_DEPTH depth: full, or absent, keeps pass 2 full
|
||||
--fix-check-prompt print the fix-check reviewer's prompt from --fix-list, --hunks, --tests and --callers files
|
||||
@@ -130,7 +130,7 @@ function main(): number {
|
||||
}
|
||||
}
|
||||
const plan = planReview({
|
||||
...collected, scope, gateTagged, numbers: scanNumbers(added), force, gated: list('--gated'), floor,
|
||||
...collected, scope, gateTagged, numbers: scanNumbers(added), force, gated: list('--gated'), floor, tiers: auditEffort !== 'host',
|
||||
criticalFound: has('--critical-found'), adversarialRan: has('--adversarial-ran'), reviewedNumbers: flag('--reviewed-numbers'),
|
||||
history: { fullPasses: pass, last, fixedBlocking: has('--fixed-blocking'), fixedBelow: has('--fixed-below') && last !== 'fix-check', blockingOpen: has('--blocking-open'), touchedGate: has('--touched-gate') || !!fixRange?.touched_gate, pass1Depth, rangeRuntimeLines: fixRange?.runtime_lines },
|
||||
});
|
||||
@@ -150,7 +150,7 @@ function main(): number {
|
||||
if (!d.exclude.length) out.push(`DIFF_EXCLUDE: ${key} none`);
|
||||
}
|
||||
for (const s of plan.skipped) out.push(`SKIP: ${s}`);
|
||||
out.push(`AUDIT_EFFORT: ${auditEffort} (coverage, plan-completion and docs audits, decision-trail reviewers, watchers; reviewers above stay full)`);
|
||||
out.push(`AUDIT_EFFORT: ${auditEffort} (coverage, plan-completion and docs audits, decision-trail reviewers, watchers; reviewers above run at their effort=)`);
|
||||
process.stdout.write(out.join('\n') + '\n');
|
||||
return EXIT.ok;
|
||||
}
|
||||
|
||||
@@ -46,7 +46,7 @@ Capy checklist for `/autoplan`: drive `gstack-autoplan`, never a hand adaptation
|
||||
|
||||
Token caps on /ship: pass a brief's cap as `--token-cap <n>`. /ship reads `cost.tokens` and `cost.credits` from `tools.thread.get({ thread_id: "<your own jam id>" })` (its own jam, subagents included; `"this"` names the root thread, so only a root run may pass it) inside the same execute program as the `gstack-ship-budget` command that takes them as `--reading <n> --credits <c>`, never in a call of its own. `ship/DRIVER.md` starts `--mode observe`: each program ends with `note`, and only a note past the cap stops (`docs/ship-budget.md`).
|
||||
|
||||
/ship on Capy is about a dozen calls, each one execute program (`ship/DRIVER.md`). A review pass, Step 11 and the Step 14.5 audit each run inside one program, in order: (1) `gstack-review-plan --base <base>` with the pass's flags (its `DISPATCH:` lines); (2) `gstack-review-log --start <skill>` once per row the step logs (under ship/SKILL.md's admission mode, add `--reservation <id>` from check's `RESERVATION_ID:` line); (3) `BEFORE`, the counter's tokens and credits; (4) `tools.subagent.create`, one reader each, `machine: "shared"`, its brief copied verbatim from the section that dispatches it; audit readers (Steps 7, 8, 9.2.1, 14.5) cannot block, so they add `model: { model_id: "anthropic/claude-sonnet-5-5", reasoning_mode: "low" }` (`anthropic/claude-haiku-5-5` also fits); (5) a poll of `tools.subagent.get` with `transcript: "none"` every ~20 s for at most 240 s, where a reader is settled only at status `done` or `failed` or with a `summary` (a just-created `idle` reader has not run); (6) `gstack-ship-budget note --step <n> --reading <AFTER> --credits <c> --dispatched-at <BEFORE> --dispatched-credits <c> --readers <n>`; (7) return only each reader's final output, or what still runs. The parent never walks the dispatch steps call by call. Waits: never let 5 minutes pass between calls. During tests, pregate, readers and CI, re-issue `wait` with `duration_seconds: 240` and the operation ids: a call after a longer gap bills the whole context fresh (about 40x a cached call), and a ping costs a few percent of that. A small waiting child saves nothing: the parent's cache expires during its wait too.
|
||||
/ship on Capy is about a dozen calls, each one execute program (`ship/DRIVER.md`). A review pass, Step 11 and the Step 14.5 audit each run inside one program, in order: (1) `gstack-review-plan --base <base>` with the pass's flags (its `DISPATCH:` lines); (2) `gstack-review-log --start <skill>` once per row the step logs (under ship/SKILL.md's admission mode, add `--reservation <id>` from check's `RESERVATION_ID:` line); (3) `BEFORE`, the counter's tokens and credits; (4) `tools.subagent.create`, one reader each, `machine: "shared"`, reasoning from its `effort=` (`full` the lane's, `medium` medium, `light` low), its brief copied verbatim from the section that dispatches it; audit readers (Steps 7, 8, 9.2.1, 14.5) cannot block, so they add `model: { model_id: "anthropic/claude-sonnet-5-5", reasoning_mode: "low" }` (`anthropic/claude-haiku-5-5` also fits); (5) a poll of `tools.subagent.get` with `transcript: "none"` every ~20 s for at most 240 s, where a reader is settled only at status `done` or `failed` or with a `summary` (a just-created `idle` reader has not run); (6) `gstack-ship-budget note --step <n> --reading <AFTER> --credits <c> --dispatched-at <BEFORE> --dispatched-credits <c> --readers <n>`; (7) return only each reader's final output, or what still runs. The parent never walks the dispatch steps call by call. Waits: never let 5 minutes pass between calls. During tests, pregate, readers and CI, re-issue `wait` with `duration_seconds: 240` and the operation ids: a call after a longer gap bills the whole context fresh (about 40x a cached call), and a ping costs a few percent of that. A small waiting child saves nothing: the parent's cache expires during its wait too.
|
||||
|
||||
## Plan, approve, ship
|
||||
|
||||
|
||||
@@ -206,18 +206,19 @@ set, because a higher effort would spend the time the gate is sized for.
|
||||
|
||||
### Review effort tiers
|
||||
|
||||
Every reviewer that can block a ship runs at `full` effort on the lane's
|
||||
model: the core checklist, each specialist, the Red Team, the native
|
||||
adversarial pass and the fix-check. `gstack-review-plan` names each
|
||||
dispatch's effort, and `host` for the outside voice (its provider and
|
||||
The core checklist, the Red Team, the native adversarial pass and the
|
||||
fix-check run at `full` effort, the lane's reasoning. Specialists run at
|
||||
`medium`, reasoning medium on the same model (GSTA-167 part 3: the no-loss
|
||||
controls C and C2 ran them there); light's batched specialist carries the Red
|
||||
Team prompt and stays `full`. `gstack-review-plan` names each dispatch's effort, and `host` for the outside voice (its provider and
|
||||
`codex_effort` above). Only work that cannot block runs `light`, the same
|
||||
model at a medium or low setting and never a cheaper model family: the coverage,
|
||||
plan-completion and docs audits, decision-trail reviewers and watchers
|
||||
(`AUDIT_EFFORT:` in the plan's output). A paid replay showed why reviewers stay
|
||||
(`AUDIT_EFFORT:` in the plan's output). A paid replay showed why the fix-check stays
|
||||
at full: a medium-effort fix-check missed a fail-open in gate code that the same
|
||||
check at full effort caught. A host that cannot set a subagent's effort runs it
|
||||
at its default. `gstack-config set review_effort_tiers off` (default `on`)
|
||||
runs the audits and watchers at the host default too
|
||||
runs the specialists, audits and watchers at the host default too
|
||||
([review-policy.md](review-policy.md#review-depth)).
|
||||
|
||||
## Which workflows use the tiers?
|
||||
|
||||
@@ -242,15 +242,20 @@ passes `--adversarial-ran` so a repeat lists them no more. Later full passes rer
|
||||
specialists on the range only. Step 11.5 binds a planned skip through the Step 9
|
||||
record's `CURRENT` freshness instead of a native record.
|
||||
|
||||
**Effort.** Every reviewer that can block a ship (the core checklist,
|
||||
specialists, the Red Team, the native adversarial pass, fix-checks) runs at
|
||||
`full` effort. Work that cannot block (the Step 7 coverage audit, the Step 8
|
||||
**Effort.** The core checklist, the Red Team, the native adversarial pass and
|
||||
fix-checks run at `full` effort (the lane's reasoning); specialists run at
|
||||
`medium` (GSTA-167 part 3: the no-loss controls ran them there), except light's
|
||||
batched specialist, which carries the Red Team prompt and stays `full`. The
|
||||
outside voice and the native adversarial pass carry the floor sentence and end
|
||||
each finding with `Severity:` and `Blocks: yes|no`; a finding is CRITICAL when
|
||||
its label rule says so (native FIXABLE, outside Critical or High) or it says
|
||||
`Blocks: yes`, and `Blocks: no` never lowers one (`proseVoiceSeverity`). Work that cannot block (the Step 7 coverage audit, the Step 8
|
||||
plan-completion audit, the Step 14.5 docs audit, decision-trail reviewers,
|
||||
watchers) runs at `light`: the same model at a lower reasoning effort, never a
|
||||
cheaper model family. The outside voice keeps its own provider and effort
|
||||
(`codex_effort`). A host that cannot set a subagent's effort runs it at its
|
||||
default. `gstack-config set review_effort_tiers off` (or `--no-tiers`) runs
|
||||
the audits and watchers at the host default too
|
||||
the specialists, audits and watchers at the host default too
|
||||
([model-policy.md](model-policy.md#reasoning-effort)).
|
||||
|
||||
### Behavior changes
|
||||
|
||||
+15
-6
@@ -17,7 +17,7 @@ import { matchesAny } from './ship-policy';
|
||||
export type DiffClass = 'docs' | 'tests' | 'code' | 'gate';
|
||||
export type PathClass = 'docs' | 'tests' | 'code';
|
||||
export type Depth = 'light' | 'standard' | 'full';
|
||||
export type Effort = 'light' | 'full' | 'host';
|
||||
export type Effort = 'light' | 'medium' | 'full' | 'host';
|
||||
export type Role = 'specialist' | 'red-team' | 'adversarial-native' | 'outside-voice' | 'fix-check';
|
||||
export type Step = 'full' | 'scoped' | 'fix-check' | 'done' | 'stop';
|
||||
|
||||
@@ -31,6 +31,12 @@ export const LARGE_DIFF_LINES = 100;
|
||||
export const SCOPED_RANGE_LINES = 150;
|
||||
/** The checklists light's batched specialist always reads, whatever the scope. */
|
||||
export const LIGHT_FIXED: readonly Specialist[] = ['testing', 'maintainability', 'security'];
|
||||
/**
|
||||
* Each blocking role's effort (GSTA-167 part 3, CREW 30c): specialists at medium, which is how the no-loss controls ran
|
||||
* them; the Red Team, the native adversarial pass and the fix-check at full (the lane's reasoning); the outside voice at
|
||||
* its own provider's. Light's batched specialist carries the Red Team prompt, so it stays full.
|
||||
*/
|
||||
export const ROLE_EFFORT = { specialist: 'medium', 'red-team': 'full', 'adversarial-native': 'full', 'fix-check': 'full', 'outside-voice': 'host' } as const satisfies Record<Role, Effort>;
|
||||
/** Why light with runtime above 0 keeps the native adversarial pass as its own dispatch. */
|
||||
export const LIGHT_ADVERSARIAL_REASON = 'backtest inconclusive (GSTA-147 D5)';
|
||||
const CLASS_RANK: Record<DiffClass, number> = { docs: 0, tests: 1, code: 2, gate: 3 };
|
||||
@@ -58,7 +64,7 @@ const DATA_CONFIG = [
|
||||
|
||||
/** A hash of the constants and patterns that decide a depth, not of this file's bytes: a comment edit keeps it, a threshold edit changes it. */
|
||||
export const DEPTH_RULES = createHash('sha256').update(JSON.stringify({
|
||||
SMALL_DIFF_LINES, RED_TEAM_LINES, LARGE_DIFF_LINES, FULL_PASS_CAP, LIGHT_FIXED, SCOPED_RANGE_LINES,
|
||||
SMALL_DIFF_LINES, RED_TEAM_LINES, LARGE_DIFF_LINES, FULL_PASS_CAP, LIGHT_FIXED, SCOPED_RANGE_LINES, ROLE_EFFORT,
|
||||
patterns: Object.entries({ GATE_PATH, AGENT_PROSE, TEST_PATH, RELEASE_METADATA, DOC_PATH: [DOC_PATH], DATA_PATH: [DATA_PATH], DATA_CONFIG }).map(([k, v]) => [k, v.map(r => `/${r.source}/${r.flags}`)]),
|
||||
})).digest('hex').slice(0, 16);
|
||||
|
||||
@@ -281,6 +287,8 @@ export interface PlanInput extends ClassInput {
|
||||
reviewedNumbers?: string;
|
||||
/** --depth-floor: raises the depth, never lowers it. */
|
||||
floor?: Depth;
|
||||
/** false under --no-tiers or review_effort_tiers off: specialists run at the host's default effort. */
|
||||
tiers?: boolean;
|
||||
}
|
||||
/** One reviewer. `exclude` holds git pathspec argv items the reviewer's diff leaves out; `checklists` names what light's batched specialist reads. */
|
||||
export interface Dispatch { role: Role; name: string; effort: Effort; exclude: string[]; checklists?: string[]; reason?: string }
|
||||
@@ -350,15 +358,16 @@ export function planReview(i: PlanInput): ReviewPlan {
|
||||
const tests = i.paths.filter(p => pathClass(i, p) === 'tests' && !isOutput(i, p)).map(excludeSpec);
|
||||
const numbersChanged = i.numbers.publishes && i.reviewedNumbers !== undefined && i.reviewedNumbers !== i.numbers.fingerprint;
|
||||
const firstVoices = h.fullPasses === 0 || !i.adversarialRan;
|
||||
const specialist: Effort = i.tiers === false ? 'host' : ROLE_EFFORT.specialist;
|
||||
if (next.step === 'full' && stepDepth === 'light') {
|
||||
const forced = forcedBy(i);
|
||||
if (runtimeLines > 0) {
|
||||
const scoped = SPECIALISTS.filter(n => !LIGHT_FIXED.includes(n) && (forced(n) || (scopeWants[n]?.(i.scope ?? {}) && !(i.gated ?? []).includes(n))));
|
||||
add('specialist', 'batched', 'full', docsAndOutputs, { checklists: [...LIGHT_FIXED, ...scoped, 'red-team'] });
|
||||
add('specialist', 'batched', ROLE_EFFORT['red-team'], docsAndOutputs, { checklists: [...LIGHT_FIXED, ...scoped, 'red-team'] });
|
||||
skipped.push('red-team (light depth: the batched specialist carries the Red Team prompt)');
|
||||
if (firstVoices) add('adversarial-native', 'adversarial', 'full', [], { reason: LIGHT_ADVERSARIAL_REASON });
|
||||
} else {
|
||||
for (const n of SPECIALISTS.filter(forced)) add('specialist', n, 'full');
|
||||
for (const n of SPECIALISTS.filter(forced)) add('specialist', n, specialist);
|
||||
skipped.push('specialists, red-team and adversarial-native (light depth, runtime 0)');
|
||||
}
|
||||
if (h.fullPasses === 0 && i.numbers.publishes) add('outside-voice', 'outside-voice', 'host');
|
||||
@@ -369,7 +378,7 @@ export function planReview(i: PlanInput): ReviewPlan {
|
||||
const dcls: DiffClass = full ? 'gate' : cls;
|
||||
const raised = !full && runtimeLines <= SMALL_DIFF_LINES;
|
||||
const lines = full ? i.diffLines : Math.max(runtimeLines, raised ? SMALL_DIFF_LINES : 0);
|
||||
for (const n of specialistsFor(dcls, { ...i, diffLines: lines }, skipped)) add('specialist', n, 'full', full ? [] : n === 'testing' ? docsAndOutputs : [...docsAndOutputs, ...tests]);
|
||||
for (const n of specialistsFor(dcls, { ...i, diffLines: lines }, skipped)) add('specialist', n, specialist, full ? [] : n === 'testing' ? docsAndOutputs : [...docsAndOutputs, ...tests]);
|
||||
const redTeam = dcls === 'gate' || (dcls === 'code' && (lines > RED_TEAM_LINES || !!i.criticalFound || raised));
|
||||
if (redTeam) add('red-team', 'red-team', 'full');
|
||||
else skipped.push(`red-team (${dcls} class${dcls === 'code' ? `, ${lines} runtime lines, no critical` : ''})`);
|
||||
@@ -386,7 +395,7 @@ export function planReview(i: PlanInput): ReviewPlan {
|
||||
} else if (next.step === 'scoped') {
|
||||
add('fix-check', 'fix-check', 'full');
|
||||
const forced = SPECIALISTS.filter(forcedBy(i));
|
||||
for (const n of forced) add('specialist', n, 'full');
|
||||
for (const n of forced) add('specialist', n, specialist);
|
||||
skipped.push(forced.length ? 'specialists (scoped pass; forced ones dispatched)' : 'specialists (scoped pass)');
|
||||
add('red-team', 'red-team', 'full');
|
||||
const stepElevenPending = !i.adversarialRan && cls === 'code';
|
||||
|
||||
@@ -131,6 +131,20 @@ function fingerprintLine(fp: unknown): number | undefined {
|
||||
return Number.isInteger(n) && n > 0 ? n : undefined;
|
||||
}
|
||||
|
||||
/** The blocking floor in Garry's words (docs/review-policy.md, CREW rule 23); every reviewer prompt carries it verbatim. */
|
||||
export const BLOCKING_FLOOR = 'would fail a test, break production, or lose data or secrets';
|
||||
|
||||
/**
|
||||
* Normalizer v2 for the two prose voices (GSTA-167 part 1, additive): a finding is CRITICAL when the old label rule says
|
||||
* so (native FIXABLE; outside voice Critical or High, or P0/P1) or when it carries `Blocks: yes`. `Blocks: no` never
|
||||
* demotes a finding the label rule makes CRITICAL; everything else is INFORMATIONAL.
|
||||
*/
|
||||
export function proseVoiceSeverity(voice: 'adversarial-native' | 'outside-voice', f: { label?: string; severity?: string; blocks?: string }): 'CRITICAL' | 'INFORMATIONAL' {
|
||||
const label = String(voice === 'adversarial-native' ? f.label ?? '' : f.severity ?? '').trim().toUpperCase();
|
||||
const byLabel = voice === 'adversarial-native' ? label === 'FIXABLE' : ['CRITICAL', 'HIGH', 'P0', 'P1'].includes(label);
|
||||
return byLabel || /^yes\b/i.test(String(f.blocks ?? '').trim()) ? 'CRITICAL' : 'INFORMATIONAL';
|
||||
}
|
||||
|
||||
/** The categories a reviewer uses for a test finding; `testing` is what the Testing specialist's schema emits. */
|
||||
export const TEST_GAP_CATEGORIES: readonly string[] = ['testing', 'tests', 'test-gap', 'test-coverage', 'coverage', 'missing-test', 'untested'];
|
||||
|
||||
|
||||
@@ -96,9 +96,9 @@ Subagent prompt:
|
||||
|
||||
Read the diff for this branch. First list changed files: `DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff --name-status "$DIFF_BASE"`. For NON-fixture source code, read full content: `git diff "$DIFF_BASE" -- . ':(exclude)*test*' ':(exclude)*fixture*' ':(exclude)*.spec.*'`. For fixture/test files, review in SUMMARY mode only (`git diff --stat "$DIFF_BASE" -- '*test*' '*fixture*' '*.spec.*'`) — note that they changed and what they cover, but do not pull their raw payload bytes into adversarial reasoning. State explicitly in your output that fixtures were reviewed in summary mode so the coverage reduction is visible, not silent.
|
||||
|
||||
Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment). After listing findings, end your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>` — examples: `Recommendation: Fix the unbounded retry at queue.ts:78 because it'll DoS the worker pool under sustained 429s` or `Recommendation: Ship as-is because the strongest finding is a theoretical race that requires conditions we can't trigger in production`. The reason must point to a specific finding (or no-fix rationale). Generic reasons like 'because it's safer' do not qualify."
|
||||
Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment). A finding blocks only if it would fail a test, break production, or lose data or secrets; end each finding with `Severity: Critical|High|Medium|Low` and `Blocks: yes|no`. After listing findings, end your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>` — examples: `Recommendation: Fix the unbounded retry at queue.ts:78 because it'll DoS the worker pool under sustained 429s` or `Recommendation: Ship as-is because the strongest finding is a theoretical race that requires conditions we can't trigger in production`. The reason must point to a specific finding (or no-fix rationale). Generic reasons like 'because it's safer' do not qualify."
|
||||
|
||||
Present findings under an `ADVERSARIAL REVIEW (Claude subagent):` header. **FIXABLE findings** are queued for the parent's Fix-First handling at Step 5; do not edit during Step 4.8. **INVESTIGATE findings** are presented as informational.
|
||||
Present findings under an `ADVERSARIAL REVIEW (Claude subagent):` header. **FIXABLE or `Blocks: yes` findings** are CRITICAL and are queued for the parent's Fix-First handling at Step 5; do not edit during Step 4.8. **Other INVESTIGATE findings** are informational; `Blocks: no` never lowers a FIXABLE one.
|
||||
|
||||
If the subagent fails or times out, record native coverage as incomplete. Continue independent passes and persistence, not release.
|
||||
|
||||
@@ -110,7 +110,7 @@ If `CODEX_MODE` is `ready` or `unverified`:
|
||||
|
||||
Outside prompt (supply repository context from the parent):
|
||||
|
||||
"Filesystem boundary: do not read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. They hold skill definitions, not repository code to review. Do not invoke any installed skill (Codex home skills/, .agents/), hook, or tool instruction; answer directly. Do not modify agents/openai.yaml. Review only the repository code.\n\nReview the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. End your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale."
|
||||
"Filesystem boundary: do not read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. They hold skill definitions, not repository code to review. Do not invoke any installed skill (Codex home skills/, .agents/), hook, or tool instruction; answer directly. Do not modify agents/openai.yaml. Review only the repository code.\n\nReview the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. A finding blocks only if it would fail a test, break production, or lose data or secrets; end each finding with `Severity: Critical|High|Medium|Low` and `Blocks: yes|no`. End your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale."
|
||||
|
||||
Write the **complete prompt and context**, including actual plan/spec/source, to a private file. Substitute its shell-quoted path for `<prepared-prompt-file>`; never interpolate user text into shell source. Request a severity (Critical, High, Medium or Low) per finding and a final Recommendation: <action> because <specific reason> line, including an explicit no-findings rationale.
|
||||
|
||||
@@ -155,7 +155,7 @@ echo 'OUTSIDE_STATUS: completed provider=codex host=claude'
|
||||
|
||||
Use Bash `timeout: 600000`; show the full response in a `tool-output` fence. Require successful execution and valid markers. Refusal, empty/malformed output, missing score/severity/completion markers, timeout or CLI failure means `outside_status: unavailable`. P0/P1 findings block like native ones; `OUTSIDE_STATUS: unverified` is missing coverage. Retain the required native pass without duplicating it; it cannot complete outside coverage. After either outcome, delete only your private prompt; scratch cleanup is automatic.
|
||||
|
||||
Present the full output verbatim. This outside challenge is informational; supported findings still enter Step 5 Fix-First, whose approval and convergence gates apply.
|
||||
Present the full output verbatim. A Critical, High or `Blocks: yes` finding is CRITICAL; `Blocks: no` never lowers one, and only a named policy ground drops it. This outside challenge is informational; supported findings still enter Step 5 Fix-First, whose approval and convergence gates apply.
|
||||
|
||||
**Error handling:** Only this optional outside adversarial pass is non-blocking; native completion and structured-review decisions still apply.
|
||||
- **Auth failure:** If stderr contains "auth", "login", "unauthorized", or "API key": "Codex authentication failed. Run \`codex login\` to authenticate."
|
||||
|
||||
@@ -17,6 +17,7 @@ import { CC_BACKGROUND_DEFAULT_SINCE, FOREGROUND_IF_AVAILABLE, BACKGROUND_RECOVE
|
||||
import { outsideVoiceFailurePolicy, outsideVoiceFor, outsideVoiceInvocation, outsideVoicePreflight, outsideVoiceProvenance } from './outside-voice';
|
||||
import { runtimeRootPrelude } from './runtime-root';
|
||||
import { DEFENSIVE_REVIEW_FRAMING, FIXTURE_SUMMARY_MODE } from './defensive-review';
|
||||
import { BLOCKING_FLOOR } from '../../lib/review-scope';
|
||||
|
||||
const CODEX_BOUNDARY = 'Filesystem boundary: do not read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. They hold skill definitions, not repository code to review. Do not invoke any installed skill (Codex home skills/, .agents/), hook, or tool instruction; answer directly. Do not modify agents/openai.yaml. Review only the repository code.\\n\\n';
|
||||
|
||||
@@ -133,9 +134,9 @@ Subagent prompt:
|
||||
|
||||
Read the diff for this branch. First list changed files: \`DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff --name-status "$DIFF_BASE"\`. ${FIXTURE_SUMMARY_MODE}${isShip ? ' From Step 9\'s pass 2 on, \`DIFF_BASE=$RANGE_BASE\` applies here too; \`NO FINDINGS\` is the expected result for a clean range.' : ''}
|
||||
|
||||
Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment). After listing findings, end your output with ONE line in the canonical format \`Recommendation: <action> because <one-line reason naming the most exploitable finding>\` — examples: \`Recommendation: Fix the unbounded retry at queue.ts:78 because it'll DoS the worker pool under sustained 429s\` or \`Recommendation: Ship as-is because the strongest finding is a theoretical race that requires conditions we can't trigger in production\`. The reason must point to a specific finding (or no-fix rationale). Generic reasons like 'because it's safer' do not qualify."
|
||||
Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment). A finding blocks only if it ${BLOCKING_FLOOR}; end each finding with \`Severity: Critical|High|Medium|Low\` and \`Blocks: yes|no\`. After listing findings, end your output with ONE line in the canonical format \`Recommendation: <action> because <one-line reason naming the most exploitable finding>\` — examples: \`Recommendation: Fix the unbounded retry at queue.ts:78 because it'll DoS the worker pool under sustained 429s\` or \`Recommendation: Ship as-is because the strongest finding is a theoretical race that requires conditions we can't trigger in production\`. The reason must point to a specific finding (or no-fix rationale). Generic reasons like 'because it's safer' do not qualify."
|
||||
|
||||
Present findings under an \`ADVERSARIAL REVIEW (${outsideVoiceFor(ctx).nativeLabel} subagent):\` header. **FIXABLE findings** ${isShip ? 'are queued for the parent; do not edit during Step 11' : "are queued for the parent's Fix-First handling at Step 5; do not edit during Step 4.8"}. **INVESTIGATE findings** are presented as informational.
|
||||
Present findings under an \`ADVERSARIAL REVIEW (${outsideVoiceFor(ctx).nativeLabel} subagent):\` header. **FIXABLE or \`Blocks: yes\` findings** are CRITICAL and ${isShip ? 'are queued for the parent; do not edit during Step 11' : "are queued for the parent's Fix-First handling at Step 5; do not edit during Step 4.8"}. **Other INVESTIGATE findings** are informational; \`Blocks: no\` never lowers a FIXABLE one.
|
||||
|
||||
If the subagent fails or times out, record native coverage as incomplete. Continue independent passes and persistence, not release.
|
||||
|
||||
@@ -149,11 +150,11 @@ If \`CODEX_MODE\` is \`ready\` or \`unverified\`:
|
||||
|
||||
Outside prompt (supply repository context from the parent):
|
||||
|
||||
"${CODEX_BOUNDARY}Review the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. End your output with ONE line in the canonical format \`Recommendation: <action> because <one-line reason naming the most exploitable finding>\`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale."
|
||||
"${CODEX_BOUNDARY}Review the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. A finding blocks only if it ${BLOCKING_FLOOR}; end each finding with \`Severity: Critical|High|Medium|Low\` and \`Blocks: yes|no\`. End your output with ONE line in the canonical format \`Recommendation: <action> because <one-line reason naming the most exploitable finding>\`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale."
|
||||
|
||||
${outsideVoiceInvocation(ctx, { timeoutMs: 540000, nativeAlreadyRequired: true, diffCommand: 'DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE"' })}
|
||||
|
||||
Present the full output verbatim. ${isShip ? 'An unavailable outside challenge does not block shipping by itself; supported findings still enter Step 11, and the structured P0/P1 and non-convergence gates still apply.' : 'This outside challenge is informational; supported findings still enter Step 5 Fix-First, whose approval and convergence gates apply.'}
|
||||
Present the full output verbatim. A Critical, High or \`Blocks: yes\` finding is CRITICAL; \`Blocks: no\` never lowers one, and only a named policy ground drops it. ${isShip ? 'An unavailable outside challenge does not block shipping by itself; supported findings still enter Step 11, and the structured P0/P1 and non-convergence gates still apply.' : 'This outside challenge is informational; supported findings still enter Step 5 Fix-First, whose approval and convergence gates apply.'}
|
||||
|
||||
**Error handling:** Only this optional outside adversarial pass is non-blocking; native completion and structured-review decisions still apply.
|
||||
${outsideVoiceFailurePolicy(ctx, { timeoutMinutes: 9, onTimeout: 'missing-coverage', stderrOnEmpty: true, fallback: 'none', escape: 1 })}
|
||||
|
||||
@@ -35,7 +35,7 @@ export interface Fixture { name: string; commit: string; paths: string[]; delete
|
||||
/** clean: pass 1 finds nothing; nits: pass 1 fixes below-floor findings; blocker: pass 1 fixes a blocker; adversarial-fix: Step 11 finds a should that is fixed; fix-regression: a pass-1 fix introduces a blocker the next step finds. */
|
||||
type Scenario = 'clean' | 'nits' | 'blocker' | 'adversarial-fix' | 'fix-regression';
|
||||
const SCENARIOS: Scenario[] = ['clean', 'nits', 'blocker', 'adversarial-fix', 'fix-regression'];
|
||||
interface Call { role: string; name?: string; effort: 'full' | 'light' | 'host'; diffBytes: number }
|
||||
interface Call { role: string; name?: string; effort: 'full' | 'medium' | 'light' | 'host'; diffBytes: number }
|
||||
|
||||
const fileBytes = (rel: string) => { try { return fs.statSync(path.join(ROOT, rel)).size; } catch { return 0; } };
|
||||
function promptBytes(role: string, name: string): number {
|
||||
|
||||
@@ -103,9 +103,9 @@ Subagent prompt:
|
||||
|
||||
Read the diff for this branch. First list changed files: `DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff --name-status "$DIFF_BASE"`. For NON-fixture source code, read full content: `git diff "$DIFF_BASE" -- . ':(exclude)*test*' ':(exclude)*fixture*' ':(exclude)*.spec.*'`. For fixture/test files, review in SUMMARY mode only (`git diff --stat "$DIFF_BASE" -- '*test*' '*fixture*' '*.spec.*'`) — note that they changed and what they cover, but do not pull their raw payload bytes into adversarial reasoning. State explicitly in your output that fixtures were reviewed in summary mode so the coverage reduction is visible, not silent. From Step 9's pass 2 on, `DIFF_BASE=$RANGE_BASE` applies here too; `NO FINDINGS` is the expected result for a clean range.
|
||||
|
||||
Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment). After listing findings, end your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>` — examples: `Recommendation: Fix the unbounded retry at queue.ts:78 because it'll DoS the worker pool under sustained 429s` or `Recommendation: Ship as-is because the strongest finding is a theoretical race that requires conditions we can't trigger in production`. The reason must point to a specific finding (or no-fix rationale). Generic reasons like 'because it's safer' do not qualify."
|
||||
Think like an attacker and a chaos engineer. Your job is to find ways this code will fail in production. Look for: edge cases, race conditions, security holes, resource leaks, failure modes, silent data corruption, logic errors that produce wrong results silently, error handling that swallows failures, and trust boundary violations. No compliments — just the problems. For each finding, classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment). A finding blocks only if it would fail a test, break production, or lose data or secrets; end each finding with `Severity: Critical|High|Medium|Low` and `Blocks: yes|no`. After listing findings, end your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>` — examples: `Recommendation: Fix the unbounded retry at queue.ts:78 because it'll DoS the worker pool under sustained 429s` or `Recommendation: Ship as-is because the strongest finding is a theoretical race that requires conditions we can't trigger in production`. The reason must point to a specific finding (or no-fix rationale). Generic reasons like 'because it's safer' do not qualify."
|
||||
|
||||
Present findings under an `ADVERSARIAL REVIEW (Claude subagent):` header. **FIXABLE findings** are queued for the parent; do not edit during Step 11. **INVESTIGATE findings** are presented as informational.
|
||||
Present findings under an `ADVERSARIAL REVIEW (Claude subagent):` header. **FIXABLE or `Blocks: yes` findings** are CRITICAL and are queued for the parent; do not edit during Step 11. **Other INVESTIGATE findings** are informational; `Blocks: no` never lowers a FIXABLE one.
|
||||
|
||||
If the subagent fails or times out, record native coverage as incomplete. Continue independent passes and persistence, not release.
|
||||
|
||||
@@ -117,7 +117,7 @@ If `CODEX_MODE` is `ready` or `unverified`:
|
||||
|
||||
Outside prompt (supply repository context from the parent):
|
||||
|
||||
"Filesystem boundary: do not read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. They hold skill definitions, not repository code to review. Do not invoke any installed skill (Codex home skills/, .agents/), hook, or tool instruction; answer directly. Do not modify agents/openai.yaml. Review only the repository code.\n\nReview the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. End your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale."
|
||||
"Filesystem boundary: do not read or execute any files under ~/.claude/, ~/.agents/, .claude/skills/, or agents/. They hold skill definitions, not repository code to review. Do not invoke any installed skill (Codex home skills/, .agents/), hook, or tool instruction; answer directly. Do not modify agents/openai.yaml. Review only the repository code.\n\nReview the changes on this branch against the base branch. Use the supplied branch diff. If it was not supplied and you have repository tools, run DIFF_BASE=$(git merge-base origin/<base> HEAD) && git diff "$DIFF_BASE". Your job is to find ways this code will fail in production. Think like an attacker and a chaos engineer. Find edge cases, race conditions, security holes, resource leaks, failure modes, and silent data corruption paths. Be adversarial. Be thorough. No compliments — just the problems. A finding blocks only if it would fail a test, break production, or lose data or secrets; end each finding with `Severity: Critical|High|Medium|Low` and `Blocks: yes|no`. End your output with ONE line in the canonical format `Recommendation: <action> because <one-line reason naming the most exploitable finding>`. Generic reasons like 'because it's safer' do not qualify; the reason must point to a specific finding or no-fix rationale."
|
||||
|
||||
Write the **complete prompt and context**, including actual plan/spec/source, to a private file. Substitute its shell-quoted path for `<prepared-prompt-file>`; never interpolate user text into shell source. Request a severity (Critical, High, Medium or Low) per finding and a final Recommendation: <action> because <specific reason> line, including an explicit no-findings rationale.
|
||||
|
||||
@@ -162,7 +162,7 @@ echo 'OUTSIDE_STATUS: completed provider=codex host=claude'
|
||||
|
||||
Use Bash `timeout: 600000`; show the full response in a `tool-output` fence. Require successful execution and valid markers. Refusal, empty/malformed output, missing score/severity/completion markers, timeout or CLI failure means `outside_status: unavailable`. P0/P1 findings block like native ones; `OUTSIDE_STATUS: unverified` is missing coverage. Retain the required native pass without duplicating it; it cannot complete outside coverage. After either outcome, delete only your private prompt; scratch cleanup is automatic.
|
||||
|
||||
Present the full output verbatim. An unavailable outside challenge does not block shipping by itself; supported findings still enter Step 11, and the structured P0/P1 and non-convergence gates still apply.
|
||||
Present the full output verbatim. A Critical, High or `Blocks: yes` finding is CRITICAL; `Blocks: no` never lowers one, and only a named policy ground drops it. An unavailable outside challenge does not block shipping by itself; supported findings still enter Step 11, and the structured P0/P1 and non-convergence gates still apply.
|
||||
|
||||
**Error handling:** Only this optional outside adversarial pass is non-blocking; native completion and structured-review decisions still apply.
|
||||
- **Auth failure:** If stderr contains "auth", "login", "unauthorized", or "API key": "Codex authentication failed. Run \`codex login\` to authenticate."
|
||||
|
||||
@@ -21,7 +21,8 @@ reviewer and prompt with `git diff $RANGE_BASE` as the hunks, inside this pass.
|
||||
Save its `REVIEW_PLAN:` line and fingerprint, `REVIEW_DEPTH:` (depth,
|
||||
`runtime_lines`, `rules`) and `GATE_SCAN:`. Dispatch exactly its `DISPATCH:` lines
|
||||
(specialists, Red Team, Step 11's voices), each at its `effort=` on the same model
|
||||
family and reading its `DIFF_CMD:`, in place of 9.1's and 9.2's own selection rules;
|
||||
family (`full` is the lane's reasoning, `medium` reasoning medium, `light` low; a
|
||||
host that cannot set it runs its default) and reading its `DIFF_CMD:`, in place of 9.1's and 9.2's own selection rules;
|
||||
`specialist batched` (light depth) is one subagent reading every checklist its
|
||||
`checklists=` names, Red Team included, tagging each finding with its checklist.
|
||||
A `SKIP:` reviewer logs `{"dispatched":false,"reason":"scope"}`. Audits run at
|
||||
|
||||
@@ -19,7 +19,8 @@ reviewer and prompt with `git diff $RANGE_BASE` as the hunks, inside this pass.
|
||||
Save its `REVIEW_PLAN:` line and fingerprint, `REVIEW_DEPTH:` (depth,
|
||||
`runtime_lines`, `rules`) and `GATE_SCAN:`. Dispatch exactly its `DISPATCH:` lines
|
||||
(specialists, Red Team, Step 11's voices), each at its `effort=` on the same model
|
||||
family and reading its `DIFF_CMD:`, in place of 9.1's and 9.2's own selection rules;
|
||||
family (`full` is the lane's reasoning, `medium` reasoning medium, `light` low; a
|
||||
host that cannot set it runs its default) and reading its `DIFF_CMD:`, in place of 9.1's and 9.2's own selection rules;
|
||||
`specialist batched` (light depth) is one subagent reading every checklist its
|
||||
`checklists=` names, Red Team included, tagging each finding with its checklist.
|
||||
A `SKIP:` reviewer logs `{"dispatched":false,"reason":"scope"}`. Audits run at
|
||||
|
||||
+8
-8
@@ -6,29 +6,29 @@
|
||||
"agy/gstack-plan-design-review": 110044,
|
||||
"agy/gstack-plan-devex-review": 116496,
|
||||
"agy/gstack-plan-eng-review": 144907,
|
||||
"agy/gstack-review": 103743,
|
||||
"agy/gstack-review": 104280,
|
||||
"codex/gstack-autoplan": 108553,
|
||||
"codex/gstack-land-and-deploy": 100284,
|
||||
"codex/gstack-plan-design-review": 111116,
|
||||
"codex/gstack-plan-devex-review": 118004,
|
||||
"codex/gstack-plan-eng-review": 146072,
|
||||
"codex/gstack-review": 103266,
|
||||
"codex/gstack-review": 103803,
|
||||
"copilot/gstack-autoplan": 109253,
|
||||
"copilot/gstack-plan-design-review": 110355,
|
||||
"copilot/gstack-plan-devex-review": 115958,
|
||||
"copilot/gstack-plan-eng-review": 145072,
|
||||
"copilot/gstack-review": 103324,
|
||||
"copilot/gstack-review": 103861,
|
||||
"cursor/gstack-autoplan": 108485,
|
||||
"cursor/gstack-plan-design-review": 108900,
|
||||
"cursor/gstack-plan-devex-review": 115228,
|
||||
"cursor/gstack-plan-eng-review": 143662,
|
||||
"cursor/gstack-review": 121614,
|
||||
"cursor/gstack-review": 122151,
|
||||
"factory/gstack-autoplan": 110763,
|
||||
"factory/gstack-land-and-deploy": 100105,
|
||||
"factory/gstack-plan-design-review": 111675,
|
||||
"factory/gstack-plan-devex-review": 118591,
|
||||
"factory/gstack-plan-eng-review": 146770,
|
||||
"factory/gstack-review": 125387,
|
||||
"factory/gstack-review": 125924,
|
||||
"gbrain/gstack-autoplan": 108892,
|
||||
"gbrain/gstack-plan-eng-review": 126289,
|
||||
"hermes/gstack-autoplan": 108891,
|
||||
@@ -37,18 +37,18 @@
|
||||
"kiro/gstack-plan-design-review": 108752,
|
||||
"kiro/gstack-plan-devex-review": 115080,
|
||||
"kiro/gstack-plan-eng-review": 143524,
|
||||
"kiro/gstack-review": 121438,
|
||||
"kiro/gstack-review": 121975,
|
||||
"openclaw/gstack-autoplan": 108715,
|
||||
"openclaw/gstack-plan-eng-review": 124804,
|
||||
"opencode/gstack-autoplan": 109234,
|
||||
"opencode/gstack-plan-design-review": 110187,
|
||||
"opencode/gstack-plan-devex-review": 115836,
|
||||
"opencode/gstack-plan-eng-review": 144931,
|
||||
"opencode/gstack-review": 122236,
|
||||
"opencode/gstack-review": 122773,
|
||||
"slate/gstack-autoplan": 108372,
|
||||
"slate/gstack-plan-design-review": 108826,
|
||||
"slate/gstack-plan-devex-review": 115154,
|
||||
"slate/gstack-plan-eng-review": 143593,
|
||||
"slate/gstack-review": 121526
|
||||
"slate/gstack-review": 122063
|
||||
}
|
||||
}
|
||||
@@ -493,7 +493,7 @@ do not launch the downstream skill or open a browser.`,
|
||||
maxSkeletonBytes: 59_073, // GSTA-96 hoist (2026-10-26): lowered from 80_900 by the shared preamble that moved to sections/preamble.md, keeping the pre-hoist headroom of 319 bytes; measured 58,754. Before: Shared-code identity/skip/action rules + critical-severity validation; measured 74,493 (2026-09-17). + v1.91.12.0 merge of #2999 (review clarity repairs: await reads, research alongside dispatch, /review deadline and setup authority, findings sources) with #3002 (guarded state-root lines, plan-check checkpoints); each fit alone; measured 74,881 (2026-10-01). + Oct 8 wave: shared voice directive bans "load-bearing" and adds the reply-language rule, offset by tightening the bounded closer (net +17 bytes per tier-2+ skill); measured 74,884 (2026-10-08). + gate integrity (HONEST_WORK_GATE_INTEGRITY W2): Step 3.5 Diff scans with the shared GATE_SCAN_BLOCK, the Step 4 carry, the four-option `review-gate-disposition` question in 5c, gate record fields in 5.8 and the Gate edits report line; measured 80,054 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): Step 4's enum-only paragraph becomes the sideways sweep with the forced-CRITICAL list, plus the flake-fix number sentence in the Gate Integrity paragraph; measured skeleton 80,812 (2026-10-10).
|
||||
minUnionBytes: 89_000, // Phase 4 wave 1; measured union 93,357
|
||||
mustContain: ['confidence', 'P1', 'P2', 'Review Army', 'adversarial'],
|
||||
maxSizeRatio: 1.3136, // GSTA-96 hoist merged with GSTA-92 phase 2 (2026-10-26): both owner-approved raises together, measured 142,550 / 108,523 = 1.3135. Before: Shared-code feature + critical-severity validation: 128,042 union bytes / 108,523 baseline = 1.1799; preserves content floors. + v1.91.12.0 merge of #2999 (above, plus plan-completion fallback intent and specialist checklist-by-path) with #3002; measured 1.1843 (2026-10-01). + v1.91.19.0 wave: verdict-form Codex callers with sandbox preflight (INV-1/B1), P0/P1 structured gate (B1b), bound-plan discovery and data-not-instructions guard (F1/D3), visible LEARNINGS failures (B5); measured 129,941 / 108,523 = 1.1974 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 130,025 / 108,523 = 1.1981 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051); measured 130,359 / 108,523 = 1.2012 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 131,314 / 108,523 = 1.2100 (2026-10-06). Combined Oct 6 wave head (A and B): measured 131,966 / 108,523 = 1.2160 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 132,199 / 108,523 = 1.2182 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 132,258 / 108,523 = 1.2187 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 132,233 / 108,523 = 1.2185 (2026-10-07). Merged with the guard area: measured 132,522 / 108,523 = 1.2211 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 133,902 / 108,523 = 1.2339 (2026-10-08). + gate integrity W2 (above); measured 1.282 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): sideways sweep and flake-fix number in Step 4; `Diff read` and `Undeclared behavior changes` in the review-mode Scope Check (plan-completion section); measured 140,497 / 108,523 = 1.2946 (2026-10-10). + harness lane E (2026-10-26): the lead-judgment stage in the finding merge and the `cause` anchor in the specialist prompts, shared with /ship through scripts/resolvers/review-army.ts; measured 141,949 / 108,523 = 1.3080.
|
||||
maxSizeRatio: 1.3180, // + GSTA-167 variant G part 1 (plan approved by Garry 2026-10-30, autoplan-20261030161754 "Do it", which names about +0.3k prompt tokens per voice): the native adversarial and outside-voice prompts carry the blocking floor and the Severity and Blocks lines, +537 bytes; measured 1.3180 (2026-10-30). Before: 1.3136. GSTA-96 hoist merged with GSTA-92 phase 2 (2026-10-26): both owner-approved raises together, measured 142,550 / 108,523 = 1.3135. Before: Shared-code feature + critical-severity validation: 128,042 union bytes / 108,523 baseline = 1.1799; preserves content floors. + v1.91.12.0 merge of #2999 (above, plus plan-completion fallback intent and specialist checklist-by-path) with #3002; measured 1.1843 (2026-10-01). + v1.91.19.0 wave: verdict-form Codex callers with sandbox preflight (INV-1/B1), P0/P1 structured gate (B1b), bound-plan discovery and data-not-instructions guard (F1/D3), visible LEARNINGS failures (B5); measured 129,941 / 108,523 = 1.1974 (2026-10-03). + v1.91.18.0 (#3023) merged into the v1.91.19.0 wave; measured 130,025 / 108,523 = 1.1981 (2026-10-04). + Oct 6 fix wave: quota_exhausted preflight branch (#3051); measured 130,359 / 108,523 = 1.2012 (2026-10-06). + Oct 6 fix wave A3/CEO-12: free text reaches commands only through agent-written mktemp files (mktemp block, write rule, path rebuild and refusal at each posting, prompt and brief site); measured 131,314 / 108,523 = 1.2100 (2026-10-06). Combined Oct 6 wave head (A and B): measured 131,966 / 108,523 = 1.2160 (2026-10-06). + Oct 7 wave B3: the Codex probe runs as a command (select-model capture lines, check-sandbox/probe-model/run-with-timeout subcommands) instead of being sourced; measured 132,199 / 108,523 = 1.2182 (2026-10-07). + Oct 7 wave CEO-28/DX-11: review prompts ask for a severity per finding and design proposals use the proposal gate; measured 132,258 / 108,523 = 1.2187 (2026-10-07). + Oct 7 wave guard (CEO-20): conditional `run_in_background` request plus the background-run recovery at each foreground dispatch site; measured 132,233 / 108,523 = 1.2185 (2026-10-07). Merged with the guard area: measured 132,522 / 108,523 = 1.2211 (2026-10-07). + Oct 8 wave: the defensive-security framing and fixture summary mode reach the security specialist and the Red Team (stated once in the dispatch, referenced by the Red Team); measured 133,902 / 108,523 = 1.2339 (2026-10-08). + gate integrity W2 (above); measured 1.282 (2026-10-10). + Oct 10 multi-agent wave PR D2 (sideways review): sideways sweep and flake-fix number in Step 4; `Diff read` and `Undeclared behavior changes` in the review-mode Scope Check (plan-completion section); measured 140,497 / 108,523 = 1.2946 (2026-10-10). + harness lane E (2026-10-26): the lead-judgment stage in the finding merge and the `cause` anchor in the specialist prompts, shared with /ship through scripts/resolvers/review-army.ts; measured 141,949 / 108,523 = 1.3080.
|
||||
},
|
||||
codex: {
|
||||
skill: 'codex',
|
||||
|
||||
@@ -0,0 +1,62 @@
|
||||
/**
|
||||
* GSTA-167 variant G part 1: both prose voices carry the blocking floor verbatim and end each
|
||||
* finding with Severity and Blocks, and the Step 11 rule is additive (normalizer v2): a finding is
|
||||
* CRITICAL when its label rule says so or it says Blocks: yes; Blocks: no never lowers one.
|
||||
*/
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import * as fs from 'node:fs';
|
||||
import * as path from 'node:path';
|
||||
import { BLOCKING_FLOOR, proseVoiceSeverity } from '../lib/review-scope';
|
||||
import { generateAdversarialStep } from '../scripts/resolvers/outside-voice-steps';
|
||||
import { HOST_PATHS } from '../scripts/resolvers/types';
|
||||
|
||||
const ROOT = path.join(import.meta.dir, '..');
|
||||
const render = (skillName: 'ship' | 'review', host: 'claude' | 'codex') => generateAdversarialStep({ skillName, tmplPath: '', host, paths: HOST_PATHS[host] } as any);
|
||||
const prompt = (text: string, opener: string) => {
|
||||
const start = text.indexOf(opener);
|
||||
expect(start).toBeGreaterThan(-1);
|
||||
return text.slice(start, text.indexOf('"\n', start));
|
||||
};
|
||||
const BLOCKS = `A finding blocks only if it ${BLOCKING_FLOOR}; end each finding with \`Severity: Critical|High|Medium|Low\` and \`Blocks: yes|no\`.`;
|
||||
|
||||
describe('prose voices carry the blocking floor (GSTA-167 part 1)', () => {
|
||||
// Value: protects=the outside voice and the native adversarial pass rate against the floor the policy states, so a real
|
||||
// blocker labeled Medium or INVESTIGATE can still say Blocks: yes; fails_when=either prompt loses the floor sentence or the
|
||||
// Blocks line on any host or skill; seam=generateAdversarialStep
|
||||
for (const skill of ['ship', 'review'] as const) for (const host of ['claude', 'codex'] as const) {
|
||||
test(`${skill} on ${host}: both prompts end with the floor, Severity and Blocks; the structured review prompt is unchanged`, () => {
|
||||
const text = render(skill, host);
|
||||
const native = prompt(text, 'Think like an attacker and a chaos engineer. Your job');
|
||||
const outside = prompt(text, 'Review the changes on this branch against the base branch.');
|
||||
for (const p of [native, outside]) expect(p).toContain(BLOCKS);
|
||||
expect(native).toContain('classify as FIXABLE (you know how to fix it) or INVESTIGATE (needs human judgment).');
|
||||
expect(text).toContain('Prepare a structured review prompt requesting severity-tagged findings ([P0]-[P3]) or an explicit NO_FINDINGS conclusion.');
|
||||
expect(text).toContain('**FIXABLE or `Blocks: yes` findings** are CRITICAL');
|
||||
expect(text).toContain('A Critical, High or `Blocks: yes` finding is CRITICAL; `Blocks: no` never lowers one');
|
||||
});
|
||||
}
|
||||
|
||||
// Value: protects=F10, every prose copy of the floor stays the same words (wrapped copies compared with whitespace
|
||||
// collapsed); fails_when=a copy drifts from BLOCKING_FLOOR; seam=none
|
||||
test('every prose copy of the floor matches BLOCKING_FLOOR once whitespace is collapsed', () => {
|
||||
const files = ['scripts/resolvers/fix-check.ts', 'review/SKILL.md.tmpl', 'ship/SKILL.md.tmpl', 'capy/skill/gstack/factory.md', 'capy/README.md', 'docs/review-policy.md'];
|
||||
const drift = files.filter(f => !fs.readFileSync(path.join(ROOT, f), 'utf8').replace(/\s+/g, ' ').includes(BLOCKING_FLOOR));
|
||||
expect(drift).toEqual([]);
|
||||
});
|
||||
});
|
||||
|
||||
describe('normalizer v2: CRITICAL is the label rule or Blocks: yes', () => {
|
||||
test.each([
|
||||
['adversarial-native', { label: 'FIXABLE', blocks: 'no' }, 'CRITICAL'],
|
||||
['adversarial-native', { label: 'INVESTIGATE', blocks: 'yes' }, 'CRITICAL'],
|
||||
['adversarial-native', { label: 'INVESTIGATE', blocks: 'no' }, 'INFORMATIONAL'],
|
||||
['adversarial-native', { label: 'INVESTIGATE' }, 'INFORMATIONAL'],
|
||||
['outside-voice', { severity: 'Critical', blocks: 'no' }, 'CRITICAL'],
|
||||
['outside-voice', { severity: 'High' }, 'CRITICAL'],
|
||||
['outside-voice', { severity: 'P1' }, 'CRITICAL'],
|
||||
['outside-voice', { severity: 'Medium', blocks: 'yes' }, 'CRITICAL'],
|
||||
['outside-voice', { severity: 'Low', blocks: 'Yes, it loses the row' }, 'CRITICAL'],
|
||||
['outside-voice', { severity: 'Medium', blocks: 'no' }, 'INFORMATIONAL'],
|
||||
['outside-voice', { severity: 'Low' }, 'INFORMATIONAL'],
|
||||
] as const)('%s %j -> %s', (voice, f, want) => expect(proseVoiceSeverity(voice, f)).toBe(want));
|
||||
});
|
||||
@@ -82,17 +82,17 @@ describe('planReview', () => {
|
||||
expect(p.depth).toBe('light');
|
||||
expect(roles(p)).toEqual([]);
|
||||
});
|
||||
test('code class pass 1: every reviewer at full effort, the outside voice at its own', () => {
|
||||
test('code class pass 1: specialists at medium, the native adversarial at full, the outside voice at its own', () => {
|
||||
const p = planReview(base({}));
|
||||
expect(roles(p)).toEqual(['specialist:testing:full', 'specialist:maintainability:full', 'specialist:security:full', 'specialist:performance:full', 'specialist:simplification:full', 'adversarial-native:adversarial:full', 'outside-voice:outside-voice:host']);
|
||||
expect(roles(p)).toEqual(['specialist:testing:medium', 'specialist:maintainability:medium', 'specialist:security:medium', 'specialist:performance:medium', 'specialist:simplification:medium', 'adversarial-native:adversarial:full', 'outside-voice:outside-voice:host']);
|
||||
});
|
||||
test('gate class forces red team and ignores hit-rate gating', () => {
|
||||
const p = planReview(base({ gateTagged: 1, gated: ['security'] }));
|
||||
expect(roles(p)).toContain('red-team:red-team:full');
|
||||
expect(roles(p)).toContain('specialist:security:full');
|
||||
expect(roles(p)).toContain('specialist:security:medium');
|
||||
});
|
||||
test('code class honours hit-rate gating and small-diff skip', () => {
|
||||
expect(roles(planReview(base({ gated: ['simplification'] })))).not.toContain('specialist:simplification:full');
|
||||
expect(roles(planReview(base({ gated: ['simplification'] })))).not.toContain('specialist:simplification:medium');
|
||||
expect(planReview(base({ diffLines: 20 })).dispatches.filter(d => d.role === 'specialist').map(d => d.name)).toEqual(['batched']);
|
||||
});
|
||||
test('pass 2 reruns the army on the range but not the adversarial or outside voice once Step 11 ran', () => {
|
||||
@@ -113,9 +113,21 @@ describe('planReview', () => {
|
||||
const p = planReview(base({ numbers, reviewedNumbers: 'old', history: { fullPasses: 1, last: 'full', fixedBelow: true } }));
|
||||
expect(roles(p)).toEqual(['fix-check:fix-check:full', 'outside-voice:outside-voice (numbers changed):host']);
|
||||
});
|
||||
test('no reviewer runs below full effort (GSTA-131 eval: a light fix-check missed a fail-open a full one caught)', () => {
|
||||
for (const h of [{ fullPasses: 0, last: 'none' }, { fullPasses: 1, last: 'full', fixedBelow: true }, { fullPasses: 1, last: 'full', fixedBlocking: true }] as const)
|
||||
expect(planReview(base({ gateTagged: 1, history: h })).dispatches.filter(d => d.role !== 'outside-voice').every(d => d.effort === 'full')).toBe(true);
|
||||
// Value: protects=GSTA-167 part 3 (specialists at medium, CREW 30c) without moving the GSTA-131 lesson (a light fix-check missed
|
||||
// a fail-open a full one caught): Red Team, native adversarial and fix-check stay full; fails_when=any of those drops below
|
||||
// full, a specialist leaves medium, or --no-tiers leaves a specialist off the host default; seam=planReview
|
||||
test('specialists run at medium; the Red Team, native adversarial and fix-check stay full; --no-tiers sends specialists to host', () => {
|
||||
for (const h of [{ fullPasses: 0, last: 'none' }, { fullPasses: 1, last: 'full', fixedBelow: true }, { fullPasses: 1, last: 'full', fixedBlocking: true }] as const) {
|
||||
const d = planReview(base({ gateTagged: 1, history: h })).dispatches;
|
||||
expect(d.filter(x => x.role === 'specialist').every(x => x.effort === 'medium')).toBe(true);
|
||||
expect(d.filter(x => ['red-team', 'adversarial-native', 'fix-check'].includes(x.role)).every(x => x.effort === 'full')).toBe(true);
|
||||
expect(d.filter(x => x.role === 'outside-voice').every(x => x.effort === 'host')).toBe(true);
|
||||
}
|
||||
const gate = planReview(base({ gateTagged: 1 })).dispatches;
|
||||
expect(gate.map(x => x.role)).toEqual(expect.arrayContaining(['specialist', 'red-team', 'adversarial-native']));
|
||||
const host = planReview(base({ gateTagged: 1, tiers: false })).dispatches;
|
||||
expect(host.filter(x => x.role === 'specialist').every(x => x.effort === 'host')).toBe(true);
|
||||
expect(host.filter(x => x.role === 'red-team' || x.role === 'adversarial-native').every(x => x.effort === 'full')).toBe(true);
|
||||
});
|
||||
test('done dispatches nothing', () => expect(planReview(base({ history: { fullPasses: 1, last: 'full' } })).dispatches).toEqual([]));
|
||||
});
|
||||
@@ -195,7 +207,7 @@ describe('review depth: the matrix', () => {
|
||||
test('runtime 51 is standard: thresholds read runtime lines, reviewers read their own hunks', () => {
|
||||
const p = planReview(mixed({ perPath: per({ 'src/app.ts': 51, 'test/a.test.ts': 400, 'README.md': 3 }), diffLines: 454 }));
|
||||
expect([p.depth, p.runtimeLines]).toEqual(['standard', 51]);
|
||||
expect(roles(p)).toEqual(['specialist:testing:full', 'specialist:maintainability:full', 'specialist:performance:full', 'adversarial-native:adversarial:full', 'outside-voice:outside-voice:host']);
|
||||
expect(roles(p)).toEqual(['specialist:testing:medium', 'specialist:maintainability:medium', 'specialist:performance:medium', 'adversarial-native:adversarial:full', 'outside-voice:outside-voice:host']);
|
||||
const ex = Object.fromEntries(p.dispatches.map(d => [d.name, d.exclude]));
|
||||
expect(ex.testing).toEqual([':(exclude)README.md']);
|
||||
expect(ex.maintainability).toEqual([':(exclude)README.md', ':(exclude)test/a.test.ts']);
|
||||
@@ -245,7 +257,7 @@ describe('review depth: the matrix', () => {
|
||||
test('a fixed blocker in light raises the next full step to the standard set, Red Team included', () => {
|
||||
const p = planReview(mixed({ perPath: per({ 'src/app.ts': 30 }), history: { fullPasses: 1, last: 'full', fixedBlocking: true } }));
|
||||
expect([p.depth, p.stepDepth]).toEqual(['light', 'standard']);
|
||||
expect(roles(p)).toEqual(['specialist:testing:full', 'specialist:maintainability:full', 'specialist:performance:full', 'red-team:red-team:full', 'adversarial-native:adversarial:full', 'outside-voice:outside-voice:host']);
|
||||
expect(roles(p)).toEqual(['specialist:testing:medium', 'specialist:maintainability:medium', 'specialist:performance:medium', 'red-team:red-team:full', 'adversarial-native:adversarial:full', 'outside-voice:outside-voice:host']);
|
||||
});
|
||||
test('--depth-floor raises and never lowers', () => {
|
||||
expect(depthFor({ cls: 'code', runtimeLines: 10, errors: [], floor: 'full' })).toBe('full');
|
||||
|
||||
@@ -53,13 +53,14 @@ describe('reviewer packets stay reverted (GSTA-167)', () => {
|
||||
const NO_LOSS_REPLAYS = {
|
||||
'#3638': 'no-loss round 3: main restored the pre-#3621 reviewers (v1.91.331.0)',
|
||||
'PR-a': "GSTA-167 variant G Arm 4: structural plan identity at the 14 cohort heads and the free exact re-score of saved C, D and A' findings (parts 4a and 4b)",
|
||||
'G1': "GSTA-167 variant G Arm G1: live no-loss replay of both prose voices with part 1's prompts, 2 passes, normalizer v2, paired rule against pooled C' (parts 1 and 3; specialists at medium as in C and C2)",
|
||||
} as const;
|
||||
type Replay = keyof typeof NO_LOSS_REPLAYS;
|
||||
const REVIEWER_BRIEFS: Record<string, { sha: string; replay: Replay }> = {
|
||||
'ship/sections/review-army.md': { sha: '8cb848bf22f4decd1b88f18b0a3359af81fc4e45ff81abf626ebf0a1557f8668', replay: 'PR-a' },
|
||||
'ship/sections/adversarial.md': { sha: '3f361c1f42605c8329048c81162216e7bf9902bdbb2327811c39ee4e201bb95d', replay: '#3638' },
|
||||
'ship/sections/review-army.md': { sha: '7ee6cfac4432a83a8a91d77c6adb3574c23a762c7f8b4fb379d5b8a8d7398730', replay: 'G1' },
|
||||
'ship/sections/adversarial.md': { sha: 'c48aa7717c7438941fa23418367e19a62e07edda7445d0d5a55924e172dd5d33', replay: 'G1' },
|
||||
'review/sections/review-army.md': { sha: '78329b64640260cd8831ca81a9189f3f8dcade9c406431631d3f2cd798cd3967', replay: '#3638' },
|
||||
'review/sections/adversarial.md': { sha: 'a402018055670f50b75322ab92a0b03d740c481cc5ef2f2ac72b281dae29ec7b', replay: '#3638' },
|
||||
'review/sections/adversarial.md': { sha: 'e6962fa25b78f362654f2954f79683e524d2ebd452d1494f8a2b099888e8e255', replay: 'G1' },
|
||||
'review/checklist.md': { sha: '607788afeb2c83f2dff1dccd58d212616ec72393d28cda2fa18690c1a83df699', replay: '#3638' },
|
||||
'review/design-checklist.md': { sha: 'b9205f88313cc64902c0b13e9685722ab8138d3dcc58916154f47274abda7d83', replay: '#3638' },
|
||||
'review/gate-integrity.md': { sha: 'f570db344c9a01df633bcaa281d6017f4f12420fd3e0aa3078c1ce06e0df8332', replay: '#3638' },
|
||||
@@ -73,7 +74,7 @@ const REVIEWER_BRIEFS: Record<string, { sha: string; replay: Replay }> = {
|
||||
'review/specialists/state-machines.md': { sha: '597215e4438d85d9cc71b48097c61eef7cba4f4b09dc14c92b4b94893b3d3ea2', replay: '#3638' },
|
||||
'review/specialists/testing.md': { sha: 'd6cc2bef7be562387d0c0a22fefe646dff9c295f1d34d8453a6cb496584150e4', replay: '#3638' },
|
||||
'scripts/resolvers/fix-check.ts': { sha: '712bf5b0c439e96bac32f19cbe25394dabb4c94aa66600100bfde9b100e15a08', replay: '#3638' },
|
||||
'lib/review-depth.ts': { sha: '49a32aa4e94df58d9aebc34ed46bfff7153cc2202ad43692d07390560e617372', replay: 'PR-a' },
|
||||
'lib/review-depth.ts': { sha: 'f5599365da06fe6d9829701c3d7e7f716703d87b9b577835e2dc5c938a8f6e6b', replay: 'G1' },
|
||||
};
|
||||
|
||||
describe('reviewer briefs stay at their no-loss-tested bytes (GSTA-167)', () => {
|
||||
|
||||
@@ -33,13 +33,20 @@ describe('gstack-review-plan', () => {
|
||||
const r = run(repo({ 'docs/bench.md': 'Median latency fell 42% to 180 ms.\n' }), []);
|
||||
expect(r.stdout).toContain('DISPATCH: outside-voice outside-voice effort=host');
|
||||
});
|
||||
test('--json carries the class, the next step, every dispatch with its effort and the audit effort; --no-tiers renders audits at host effort', () => {
|
||||
test('--json carries the class, the next step, every dispatch with its effort and the audit effort; --no-tiers renders specialists and audits at host effort', () => {
|
||||
const r = repo({ 'src/a.ts': Array.from({ length: 80 }, (_, i) => `export const v${i} = ${i};`).join('\n') + '\n' });
|
||||
const plan = JSON.parse(run(r, ['--json']).stdout);
|
||||
expect(plan).toMatchObject({ class: 'code', next: { step: 'full' }, pass: 0 });
|
||||
expect(plan.dispatches.find((d: any) => d.role === 'specialist').effort).toBe('full');
|
||||
expect(plan.dispatches.filter((d: any) => d.role === 'specialist').map((d: any) => d.effort)).toEqual(expect.arrayContaining(['medium']));
|
||||
expect(plan.dispatches.filter((d: any) => d.role === 'specialist').every((d: any) => d.effort === 'medium')).toBe(true);
|
||||
expect(plan.dispatches.find((d: any) => d.role === 'adversarial-native').effort).toBe('full');
|
||||
expect(plan.audit_effort).toBe('light');
|
||||
expect(JSON.parse(run(r, ['--json', '--no-tiers']).stdout).audit_effort).toBe('host');
|
||||
expect(run(r, []).stdout).toContain('DISPATCH: specialist testing effort=medium');
|
||||
const host = JSON.parse(run(r, ['--json', '--no-tiers']).stdout);
|
||||
expect(host.audit_effort).toBe('host');
|
||||
expect(host.dispatches.filter((d: any) => d.role === 'specialist').every((d: any) => d.effort === 'host')).toBe(true);
|
||||
expect(host.dispatches.find((d: any) => d.role === 'adversarial-native').effort).toBe('full');
|
||||
expect(run(r, ['--no-tiers']).stdout).toContain('DISPATCH: specialist testing effort=host');
|
||||
});
|
||||
test('a below-floor fix after pass 1 plans one fix-check', () => {
|
||||
const r = run(repo({ 'src/a.ts': 'export const a = 1;\n' }), ['--pass', '1', '--last', 'full', '--fixed-below']);
|
||||
|
||||
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"bytes": 654,
|
||||
"why": "GSTA-167 variant G parts 1 and 3: both prose voices carry the blocking floor and end each finding with Severity and Blocks; specialists at effort medium"
|
||||
}
|
||||
Reference in new issue
Block a user