GitNexus/gitnexus/test/unit/skill-evolution-workflow.test.ts
Gergő Magyar becac9a5d3
feat(eval): run the skill-evolution loop online (#2571)
* feat(eval): run the skill-evolution loop online

Add a scheduled + dispatch-gated workflow that runs the offline
propose -> benchmark -> gate loop (workflow_bench.evolve) in CI with the
pinned Claude canary runtime and bubblewrap containment, uploads the
benchmark evidence as an artifact, and on a gate-passed promotion opens
a human-reviewed PR via the release App token. The applied overlay is
bounded to the canonical skill tree and its shipped mirrors; any escape
fails the run instead of reaching a PR.

The scheduled lane ships disabled behind GITNEXUS_EVOLUTION_ENABLED and
requires the new GITNEXUS_BENCH_AUTH_TOKEN secret (benchmark sessions
bill real API usage), mirroring the review agent's staged rollout.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): restructure promotion-PR script so no lint suppression is needed

Replace the inline single-quoted credential helper with a GIT_ASKPASS
file written via a quoted heredoc (the App token still reaches git only
through step env at push time), and assemble the PR body from quoted
heredocs plus double-quoted printf instead of a backtick-laden
single-quoted template. Every run script in the workflow now passes
shellcheck with zero findings and zero disables; the body and askpass
rendering are smoke-tested.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): apply gate-passing overlays in the evolution loop

The loop invoked workflow_bench.evolve without --apply, so
apply_promoted_overlay (its only working-tree writer, gated by
`if args.apply:`) never ran. git status stayed clean, promoted=false was
emitted every run, and the App-token/PR-open steps were unreachable dead
code — a gate-passing run went green as "No promotion this run".

validate_promotion_for_apply already runs before the apply gate, so
adding --apply lets a passing candidate reach the tree without weakening
the deterministic gate; the boundary check then confirms it stayed in the
skill trees.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): provision ~/GitNexus so the benchmark repo resolves on CI

Every scenario in tasks.scenarios.yaml addresses the target repo as
~/GitNexus; runner_tasks.py resolves it with expanduser().resolve() then
`git -C <repo> rev-parse`, which raises when the path is missing. On a
hosted runner the checkout lands in $GITHUB_WORKSPACE and nothing created
~/GitNexus, so the first real run failed at task-binding.

Symlink ~/GitNexus -> $GITHUB_WORKSPACE before the loop. The checkout uses
fetch-depth: 0 (full history for the parentless clone), and the benchmark
only clones the repo copy-on-write and mounts deps read-only, so the
checkout is never mutated. GITNEXUS_BENCH_ORACLE_ROOT stays unset — it
defaults to the in-repo oracles dir and is staged by the harness.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): harden promotion summary output and PR branch recovery

Three fixes to the promotion-detection and PR-open steps:

- GITHUB_OUTPUT summary used a fixed `PROMOTION_EOF` heredoc delimiter; a
  value containing that marker on its own line could close the block early
  and inject output keys. Use a per-run random delimiter, matching the
  pattern already in tree-sitter-upgrade-readiness.yml.
- The summary concatenated every generation's promotion.json (including
  rejected ones), so the PR body could show a losing generation's
  decisions. The loop returns on the first promotion, so emit only the
  highest-numbered gen-N/bench/promotion.json — the decision that fired.
- The promotion branch name omitted the run attempt. GITHUB_RUN_ID is
  stable across re-runs, so a re-run after push-succeeds/PR-create-fails
  could never push. Include ${GITHUB_RUN_ATTEMPT} (the artifact name
  already does).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): least-privilege the promotion App token and gate on an Environment

The Mint-App-Token step passed only app-id + private-key, so the minted
token inherited every permission the Release App installation holds
(including Workflows: write) — far more than "push a branch, open a PR".
Switch to `client-id` (as publish.yml does) and request only
permission-contents: write + permission-pull-requests: write.

Bind the job to a protected Environment (gitnexus-evolution) so promotion
runs can be gated server-side. workflow_dispatch runs the workflow and
in-tree evolve.py from the *dispatched ref*, so a code-side ref guard is
removable by the dispatched branch itself; an Environment deployment-branch
rule (main only) is the boundary that holds. The admin steps to create it
and scope the secrets are documented in the activation checklist.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(ci): correct upload-artifact pin comment and add shell strict-mode

- The upload-artifact SHA 043fb46d… is v7.0.1 (labeled so in the sibling
  workflows that pin it); the comment mislabeled it # v6.0.0. Correct the
  comment; the pin is unchanged.
- Add `set -euo pipefail` to the two build steps that lacked it, matching
  every other run block in the file (GitHub's default shell already sets
  -eo pipefail; this adds -u and consistency).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* docs(ci): complete the skill-evolution activation checklist

- Add RELEASE_APP_ID / RELEASE_APP_PRIVATE_KEY to the required-secrets
  checklist (the Mint step hard-fails without them on a promotion) and the
  App-install-scope verification.
- Document the protected Environment admin step and why it is the real
  boundary for the workflow_dispatch ref-secret exposure.
- Note that workflow_dispatch runs the billing loop regardless of
  GITNEXUS_EVOLUTION_ENABLED.
- Justify the weekly cron against the README's ~90-day guidance and note the
  355-minute timeout ceiling.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* fix(eval): redact API tokens from diagnostic fields before artifact upload

results.jsonl (runner.py) and proposer-session.json (evolve.py) serialize
session records whose error_detail can carry a stderr_tail that echoed the
API key. Transcripts are redacted before persistence, but these two sinks
were not, and both land in the 14-day evolution artifact.

Run each record's serialized JSON through the existing redact_text with the
run's auth token before writing. Scoped to these diagnostic sinks only: the
promoted overlay and proposal.md are left untouched (the overlay is the
applied artifact and must stay byte-identical for apply and the
shipped-skills-sync guard).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* test(ci): add a contract test for the skill-evolution workflow

No test exercised this workflow's path, which is why both P1 blockers
(missing --apply, unresolvable ~/GitNexus task repo) reached production.
Parse the workflow YAML and assert the structural contract: --apply is
passed, the task repo is provisioned, the promotion branch carries the run
attempt, the App token is permission-scoped and the job is Environment-
gated, the output summary uses a random delimiter and a single generation,
the artifact pin is labelled correctly, and every multi-line shell step
sets strict mode. Follows the review-agent-workflow.test.ts precedent.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

* feat(ci): run the proposer on its own (stronger) model

One `model` input drove both the benchmark arms and the proposer/diagnosis
session. Split them: `model` stays the benchmark arms (match the model your
skill users run, so a promotion is valid for them and the tasks aren't
ceiling-saturated), and a new `proposer_model` input runs the proposer —
the harder meta-reasoning task that writes the candidate skill, and only one
session per generation, so a stronger model is cheap here. evolve.py already
supports --proposer-model; the workflow just didn't expose it.

Defaults: arms = claude-sonnet-5, proposer = claude-opus-4-8 (both
overridable via workflow_dispatch). The weekly cadence bounds the added
spend. Contract test asserts the split stays wired.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Va5uu9Ar3e45QZ5xFsG4AZ

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-20 05:37:07 +01:00

113 lines
4.6 KiB
TypeScript

import { readFileSync } from 'node:fs';
import path from 'node:path';
import { load } from 'js-yaml';
import { describe, expect, it } from 'vitest';
// Contract guard for the online skill-evolution workflow. Both P1 blockers
// fixed here (a gate-passing run never applied its overlay; the benchmark
// could not resolve its task repo on a hosted runner) reached production
// because nothing exercised this workflow's path. Assert the structural
// contract so a regression fails loudly in CI instead of on the first real run.
const WORKFLOW_PATH = path.resolve(
__dirname,
'../../../.github/workflows/gitnexus-skill-evolution.yml',
);
const workflow = readFileSync(WORKFLOW_PATH, 'utf8');
const workflowDocument = load(workflow) as {
jobs?: Record<
string,
{
environment?: unknown;
steps?: Array<{
name?: string;
run?: unknown;
uses?: string;
with?: Record<string, unknown>;
}>;
}
>;
};
const evolveJob = workflowDocument.jobs?.evolve;
function stepRun(stepName: string): string {
const step = evolveJob?.steps?.find(({ name }) => name === stepName);
return typeof step?.run === 'string' ? step.run : '';
}
describe('gitnexus skill-evolution workflow contract', () => {
it('applies gate-passing overlays so the promotion-PR path is reachable', () => {
const loop = stepRun('Run the propose → benchmark → gate loop');
expect(loop).toContain('python -m workflow_bench.evolve');
// Without --apply the overlay is never written, git status stays clean,
// promoted=false is emitted, and the App-token/PR steps are dead code.
expect(loop).toContain('--apply');
});
it('runs the proposer on its own model, separate from the benchmark arms', () => {
const loop = stepRun('Run the propose → benchmark → gate loop');
// The benchmark arms match the production model; the proposer/diagnosis
// session gets its own (stronger) model — one session per generation.
expect(loop).toContain('--model "${MODEL}"');
expect(loop).toContain('--proposer-model "${PROPOSER_MODEL}"');
});
it('provisions the benchmark task repo at ~/GitNexus before the loop', () => {
const provision = stepRun('Point the benchmark task repo at the checkout');
expect(provision).toContain('ln -sfn');
expect(provision).toContain('${GITHUB_WORKSPACE}');
expect(provision).toContain('${HOME}/GitNexus');
});
it('names the promotion branch with the run attempt for re-run recovery', () => {
const openPr = stepRun('Open the promotion PR');
expect(openPr).toContain('${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}');
});
it('emits only the promoted generation with a per-run random output delimiter', () => {
const detect = stepRun('Detect and bound the applied promotion');
// Random per-run delimiter, not a fixed heredoc marker that a summary
// value could close early.
expect(detect).toContain('openssl rand -hex');
expect(detect).not.toContain("echo 'summary<<PROMOTION_EOF'");
// Single promoted generation (highest-numbered gen-N), not a blind
// concatenation of every generation's promotion.json.
expect(detect).toContain('sort -V');
expect(detect).not.toContain('xargs -0 -r cat');
});
it('least-privileges the App token and gates the job on a protected Environment', () => {
expect(evolveJob?.environment).toBe('gitnexus-evolution');
const mint = evolveJob?.steps?.find(({ name }) => name === 'Mint GitHub App token');
expect(mint?.with).toMatchObject({
'client-id': expect.any(String),
'permission-contents': 'write',
'permission-pull-requests': 'write',
});
expect(mint?.with).not.toHaveProperty('app-id');
});
it('labels the upload-artifact pin with its real version', () => {
expect(workflow).toContain(
'actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1',
);
expect(workflow).not.toContain('# v6.0.0');
});
it('runs every multi-line shell step under strict mode', () => {
const runSteps = (evolveJob?.steps ?? []).filter(
(step): step is { name?: string; run: string } =>
typeof step.run === 'string' && step.run.includes('\n'),
);
expect(runSteps.length).toBeGreaterThan(0);
for (const step of runSteps) {
expect(step.run, `${step.name} must set -euo pipefail`).toContain('set -euo pipefail');
}
});
it('documents the App secrets and protected Environment on the activation checklist', () => {
expect(workflow).toContain('RELEASE_APP_ID');
expect(workflow).toContain('RELEASE_APP_PRIVATE_KEY');
expect(workflow).toContain('gitnexus-evolution');
});
});