mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-09 14:38:59 +02:00
* feat(aside): browser-driver contract, cookbook, research and fallback resolvers
{{ASIDE_SETUP}} (readiness probe + ten rules for driving the user's real browser), {{ASIDE_COOKBOOK}} (script shapes verified live against Aside CLI 1.26: one flow per aside repl script, CDP console hook before navigation, evidence lines, session-directory artifact handoff, GSTACK_STEP_OK sentinel), {{ASIDE_RESEARCH}} (research through aside exec, WebSearch when Aside is absent, knowledge otherwise) and {{BROWSE_FALLBACK}} (the fifteen-row Aside-step to $B-command table plus the rules that differ, so every browsing skill keeps working on gstack's own headless browser). test/aside-driver.test.ts pins the sentences and asserts every browsing skill carries the Aside block followed by the fallback; test/helpers/aside-available.ts is the shared live-Aside probe.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* feat(render): Aside-first local-HTML renderer with the bundled browser as fallback
lib/aside-render.ts serves the HTML's directory on loopback (Aside refuses file:// URLs), opens it with waitUntil load, prints through CDP Page.printToPDF so tagged output, outlines, header/footer templates and page numbers survive, emulates device metrics for sized screenshots, and writes in-page evaluations to files; when Aside is absent it runs the same spec through the browse daemon (newtab, load, js, pdf, screenshot, closetab) and reports ENGINE=aside|browse. bin/gstack-render.ts is the CLI skill templates call. lib/claude-bin.ts and lib/error-handling.ts become the canonical copies (browse/src re-exports them).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(browse): /browse drives Aside first, with the $B reference behind the fallback
Contract, cookbook, mode choice (aside repl by default, aside exec for reading), report format, the fallback section, and the full command reference carved on demand.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(qa): /qa and /qa-only drive Aside, fall back to $B
QA_METHODOLOGY runs every phase as Aside scripts (orient, explore, document, re-test, mobile viewport via CDP emulation, links via HEAD fetch); the authenticate phase is 'you are already signed in'; a 13th rule requires consent before mutating actions on non-local targets; the fallback section translates each step onto $B. The qa E2E tests run on whichever engine is present.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(design): design-review, design-consultation, design-shotgun, plan-design-review, design-html drive Aside
Design-system extraction is one script printing FONTS/COLORS/HEADINGS/TOUCH_TARGETS/NAV; competitor research confirms the exact URLs before opening them in the real browser and runs on the bundled browser when Aside is absent; design-html's viewport screenshots, sketches and comparison boards render through gstack-render.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(deploy): benchmark, canary, land-and-deploy Step 7, devex-review drive Aside
One aside repl script per page prints NAV/PAINT/LCP/RESOURCES/SCRIPTS/CSS/SUMMARY (benchmark), CONSOLE_ERRORS/NAV/TEXT + screenshot (canary, re-run every 60s), and the post-deploy check reads responseStatus from the navigation entry; each carries the $B fallback.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* feat(third-party-actions): Aside is the recommended driver; gstack's visible browser stays the fallback
The readiness probe is lifted from {{ASIDE_SETUP}} at gen time (byte-identity pinned) and rule 3 points at browse/SKILL.md for how to drive; the consent question offers Aside first and gstack's own visible browser (handoff/resume for sign-in) as the fallback, as v1.72 framed it.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(scrape): /scrape reads pages through Aside; the browser-skills runtime rides the fallback
Look-then-extract scripts build the JSON inside the page and print it between JSON_START/JSON_END; aside exec for fuzzy intents; on the $B fallback the browser-skills match/prototype flow and /skillify apply as before.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(make-pdf): print through Aside first, the bundled browser otherwise
asideClient.ts replaces the direct $B client with one render() call per PDF (the exact option mapping the browse pdf command had: paper, margins, header/footer/page numbers, tagged, outline, printBackground, preferCSSPageSize, Paged.js wait); the diagram pre-pass, oversized-image downscale and DOCX rasters each run as one render script with per-fence try/catch; exit 4 now means no browser is available and names both remedies; $P setup reports which engine it found. The e2e gates run on whichever engine is present, so the Linux lane exercises the fallback.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* refactor(diagram): the triplet is one gstack-render call
SVG, PNG and excalidraw from one invocation over the content-addressed bundle staged under /tmp/gstack-render; every diagram type gets an excalidraw export; gstack-render picks the engine and prints ENGINE=; the diagram E2E gates on either engine.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* feat(research): web research runs in Aside first, WebSearch second
The planning, review, design, security and investigate skills research through {{ASIDE_RESEARCH}}; WebSearch stays in allowed-tools as the fallback; testing.ts's bootstrap step follows; skeleton ceilings ratcheted for the research block.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* feat(setup,gen-skill-docs): prune renders of skills that no longer exist
setup gains _prune_stale_generated for every host tree and the doc generator removes gstack-* output dirs it did not write, so a skill removed from the source tree can never linger in an install.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* test: registries, budgets and suite reconciled for Aside-first with the $B fallback
Touchfiles + E2E tiers gain the Aside keys, coverage matrix and eval baselines updated, size budget re-baselined to parity-baseline-v1.80.0.0.json (the contract plus fallback ride in every browsing skill), parity ceilings ratcheted with measured values, LLM-judge prompts and the E2E fixtures speak Aside-first, browse-fallback.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* docs: Aside first, gstack browser fallback
README, BROWSER.md, docs/, CONTRIBUTING, CLAUDE.md, ARCHITECTURE, AGENTS.md, TODOS and the root router describe the one product story: Aside is the browser gstack drives first; the bundled headless browser is the automatic fallback (Linux, Windows, app closed) where cookie import, GStack Browser, pair-agent and browser-skills still apply.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* chore: regenerate SKILL.md docs, llms.txt, agents digest, ship goldens, context-budget fixture
bun run gen:skill-docs over the templates; goldens re-rendered; context-budget ceilings recaptured.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* v1.80.0.0: Aside is the browser gstack drives first; the bundled browser is the fallback
MINOR: new capability across ten skills, the renderer and research; nothing removed. CHANGELOG release summary + itemized changes; VERSION 1.80.0.0; package.json 1.80.0.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* docs(todos): file non-Claude host ownership-gate and version-heading pin follow-ups
Two follow-ups from the /plan-ceo-review + /plan-eng-review pass on merging
PR #2804 with main's v1.80.0.0 ownership gate: bring the Codex/Factory/
OpenCode/Cursor/Kiro copy loops and the stale-render prune under the
.gstack-owned marker rule, and a free test pinning that the CHANGELOG top
heading equals VERSION (the collision that git cannot see).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix: pre-landing review fixes for the Aside-first branch
Review army + adversarial passes (Claude and Codex) on the merged branch:
setup
- _prune_stale_generated scans the host dirs too (the generator already
removed the render before setup ran, so the host branch was dead), skips
symlinks in the render tree (rm -rf on a slash-terminated link empties its
target), removes a host symlink only when it resolves into gstack, cleans a
bannered real dir through _cleanup_weak_dir, recognizes frontmatter-renamed
skills, and logs through log. The always-run codex render passes every host
dir that may link to it.
- NEEDS_BUILD checks all three binaries (with $_EXE) and lib/ sources; the
browser hint and the bootstrap summary honor GSTACK_SKIP_ASIDE, treat a
requested skip as a request, and derive one skill list.
lib/aside-render.ts + bin/gstack-render.ts
- The loopback server carries a per-render secret path, checks containment on
the real path (symlink escapes are 403), and rejects malformed encoding.
- Inline eval results are one base64 line, so page text cannot forge
ASIDE_DIR= or the sentinel; the last ASIDE_DIR wins.
- runProc escalates SIGTERM to SIGKILL, bounds every wait, and clears every
timer (an uncleared one kept gstack-render alive after printing OK).
- renderTmpDir refuses a shared /tmp name owned by someone else; the work dir
and server are created inside try; goto's budget follows the render budget.
- probeAside classifies a present-but-failing CLI as ASIDE_NOT_RUNNING like
the skills' bash probe; render() retries on gstack's own browser when Aside
could not start or its private CDP bridge is gone (never on a page error
or a timeout of a running script); the CLI reports the engine that actually
rendered, exits 0 on --help, rejects non-numeric flags, documents
--wait-timeout, fences EVAL/PAGE_ERRORS as untrusted content, and names the
daemon's cookie-import JS lock remedy.
- The browse path passes --scale only when asked (a scale change rebuilds
the daemon context) and restores the viewport after a sized screenshot.
resolvers / templates
- The bash probe honors GSTACK_SKIP_ASIDE and has a perl deadline on stock
macOS; .local is no longer LOCAL (mDNS); same-origin filters compare parsed
origins; link status is HEAD-checked only on LOCAL targets; every
aside exec goes through the receipted _aside_exec prelude
({{ASIDE_EXEC_PRELUDE}}), including nine template blocks that called it
bare; the design sketch and diagram staging use private directories.
- The generator prunes only bannered renders and never a host whose
generation failed.
Docs, stale comments and dead code cleaned; goldens re-rendered; tests
updated and added for every behavior above.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* test: coverage for the render CLI, setup rebuild check, make-pdf exit codes, and prose $B spans
New free tests from the ship coverage audit: test/gstack-render-cli.test.ts
(argv guards, --help, output contract with a fake daemon, failure and
serve-root paths, no-browser case, prompt exit), test/setup-needs-build.test.ts
(every binary and source set flips NEEDS_BUILD, Windows suffixes),
make-pdf/test/cli-exit-codes.test.ts and setup-smoke.test.ts (error to exit
code mapping, runSetup stages, renderPdf's engine), and prose-span cases for
extractBrowseCommands in test/skill-parser.test.ts.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* docs: CHANGELOG and TODOS cover the review fixes (v1.81.0.0)
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* docs: sync project docs with the v1.81.0.0 review fixes
BROWSER.md, ARCHITECTURE.md, CONTRIBUTING.md, README.md, CLAUDE.md,
docs/TESTING_INTERNALS.md and docs/PROJECT_STRUCTURE.md now describe the
shipped renderer and setup: the loopback render server's per-render secret
path and real-path containment, ENGINE= naming the engine that actually
rendered (mid-run retry on gstack's own browser), EVAL/PAGE_ERRORS fenced as
untrusted content, --wait-timeout and the CLI's argv guards, the receipted
_aside_exec prelude ({{ASIDE_EXEC_PRELUDE}} in the placeholder table), the
LOCAL host rule without .local, LOCAL-only HEAD checks in the links script,
GSTACK_SKIP_ASIDE across probe/renderer/setup, the ownership-gated
retired-skill prune, the widened NEEDS_BUILD check, and the new free tests
(gstack-render-cli, setup-prune-stale-generated, setup-browser-hint,
setup-needs-build, make-pdf cli-exit-codes and setup-smoke).
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* docs: CHANGELOG states the precise mid-run retry rule
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(test): skill-e2e-bws slices the $B setup block from the Browser fallback section
browse/SKILL.md no longer has '## SETUP' / '## Core QA Patterns' (Aside is the
primary driver; the $B block moved under 'Browser fallback'), so the gate test
sliced an empty block and handed the agent nothing to run. Anchor on
'### Find the `$B` binary' up to the next heading. 7/7 pass.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(test): gate POSIX-only fixtures off Windows
windows-free-tests: the gstack-render CLI tests drive a shebang fake browse
that CreateProcess cannot exec, and two NEEDS_BUILD cases assert an execute
bit and a bare-name miss that MSYS bash does not have (test -x ignores mode
bits and resolves design -> design.exe). Those describes and cases now
self-skip on win32; argument guards, --help, the no-browser case, and every
other rebuild-check case still run there.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* fix(render): runProc waits for the exit code until the kill deadline; newtab retries once on a cold daemon
A process whose pipes have reached EOF is exiting, but runProc gave the exit
code only five seconds to arrive and then returned null, which run() reports
as a failed command. Under CI's six-shard load one such render failed with the
artifact already written. The SIGTERM/SIGKILL timers already bound the wait,
so the exit race now runs to the kill deadline.
The first CLI call auto-starts the browse daemon; on a cold start it can
answer 'Unable to connect' once while the server is still coming up. That
single case is retried after 1.5s; every other newtab failure is not.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* test(aside-render): warm the daemon before live fallback cases; failures name the render error
- Live fallback cases run 'goto about:blank' up to twice before asserting and
skip (never fail) when the daemon cannot come up.
- expectOk() puts r.error and the browse transcript into the assertion so a
failed render is diagnosable from the CI log.
- The argv-contract cases dump the fake's log on a miss.
- File default timeout is 30s: the subject is the CLI contract, not latency.
- Two cases pin the cold-daemon newtab retry and that other errors are not
retried.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
* docs: CHANGELOG notes the cold-start tolerance of the bundled-browser renderer
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---------
Co-authored-by: Sina <sdroid674+github@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
189 lines
8.8 KiB
TypeScript
189 lines
8.8 KiB
TypeScript
/**
|
|
* /diagram skill E2E (paid, claude -p).
|
|
*
|
|
* gstack renders local HTML through `bin/gstack-render.ts`: the Aside browser
|
|
* when it is running, otherwise gstack's own browse daemon. The /diagram skill
|
|
* runs ONE gstack-render call per triplet (staged bundle, three --eval/--out
|
|
* pairs) and never picks the engine itself — so the test needs SOME browser:
|
|
* Aside on a Mac, or a browse binary (evals.yml's `bun run build` compiles one
|
|
* and PLAYWRIGHT_BROWSERS_PATH survives the hermetic env). With neither, the
|
|
* whole file self-skips — never fails.
|
|
*
|
|
* Two tests with deliberately different tiers (eng-review D5, CLAUDE.md rules):
|
|
*
|
|
* diagram-triplet (gate) — deterministic functional contract: from an
|
|
* English ask, the agent following the skill emits a parseable triplet
|
|
* (.mmd source, .excalidraw scene with elements, SVG markup, PNG bytes) and
|
|
* did it through gstack-render (a Bash tool call names it). No quality
|
|
* judgment; either the artifacts exist and parse or they don't.
|
|
*
|
|
* diagram-authoring-quality (periodic) — LLM-judged benchmark of the
|
|
* authored mermaid itself (faithfulness to the ask, label quality, readable
|
|
* size). Non-deterministic by nature → never blocks merge.
|
|
*
|
|
* Per the extract-don't-copy fixture rule, the prompt embeds only the skill's
|
|
* working section (from "# /diagram" onward), not the full generated SKILL.md
|
|
* with its preamble.
|
|
*/
|
|
import { expect } from 'bun:test';
|
|
import { CAPTURE_MS } from './helpers/eval-budgets';
|
|
import * as fs from 'node:fs';
|
|
import * as path from 'node:path';
|
|
import * as os from 'node:os';
|
|
|
|
import { runSkillTest, type SkillTestResult } from './helpers/session-runner';
|
|
import {
|
|
ROOT, runId,
|
|
describeIfSelected, testConcurrentIfSelected,
|
|
logCost,
|
|
} from './helpers/e2e-helpers';
|
|
import { asideAvailable } from './helpers/aside-available';
|
|
import { resolveBrowseBin } from '../lib/aside-render';
|
|
import { callJudge } from './helpers/llm-judge';
|
|
|
|
// --- Whole-file gate: a browser gstack-render can drive. Skip, never fail. ---
|
|
|
|
const browserOk = asideAvailable() || resolveBrowseBin() !== null;
|
|
if (process.env.EVALS && !browserOk) {
|
|
process.stderr.write('\nskill-e2e-diagram: SKIPPED — no browser: Aside is not running and no browse binary resolves (bun run build)\n');
|
|
}
|
|
|
|
/** describeIfSelected, forced to describe.skip when no browser is available. */
|
|
const describeDiagram = (name: string, keys: string[], fn: () => void) =>
|
|
describeIfSelected(name, keys, fn, browserOk ? undefined : []);
|
|
|
|
const BUNDLE = path.join(ROOT, 'lib', 'diagram-render', 'dist', 'diagram-render.html');
|
|
const RENDER = path.join(ROOT, 'bin', 'gstack-render.ts');
|
|
|
|
/** Extract the working section of the generated skill doc (post-preamble). */
|
|
function skillExtract(): string {
|
|
const full = fs.readFileSync(path.join(ROOT, 'diagram', 'SKILL.md'), 'utf-8');
|
|
const start = full.indexOf('# /diagram');
|
|
if (start < 0) throw new Error('diagram/SKILL.md missing "# /diagram" section — regenerate skill docs');
|
|
if (!full.includes('gstack-render')) throw new Error('diagram/SKILL.md does not render through gstack-render (stale generated doc) — run `bun run gen:skill-docs`');
|
|
return full.slice(start);
|
|
}
|
|
|
|
function setupDir(prefix: string): string {
|
|
const dir = fs.mkdtempSync(path.join(os.tmpdir(), prefix));
|
|
fs.writeFileSync(path.join(dir, 'diagram-skill.md'), skillExtract());
|
|
// Pre-stage the bundle so the test is hermetic (no global install needed);
|
|
// gstack-render serves this directory on loopback for the render.
|
|
fs.copyFileSync(BUNDLE, path.join(dir, 'diagram-render.html'));
|
|
fs.mkdirSync(path.join(dir, 'out'));
|
|
return dir;
|
|
}
|
|
|
|
function basePrompt(dir: string, ask: string): string {
|
|
return `You have the /diagram skill instructions at ./diagram-skill.md — read them and follow Steps 1-4.
|
|
|
|
Environment notes (already set up — skip Step 2's bundle discovery and staging):
|
|
- gstack-render picks the browser itself (its first output line is ENGINE=aside or ENGINE=browse); either is fine. Do not probe for or start a browser yourself.
|
|
- The render bundle is ALREADY staged at ${dir}/diagram-render.html — use that path wherever the skill says <staged>.
|
|
- gstack-render lives at ${RENDER}; run it as \`bun run ${RENDER}\` instead of the ~/.claude/skills/gstack/bin/gstack-render.ts path the skill shows.
|
|
- Write all four artifacts into ./out/ with the slug "flow" (out/flow.mmd, out/flow.excalidraw, out/flow.svg, out/flow.png).
|
|
- Do not open any other applications. Do not use the Read tool on the PNG (no inline display needed here).
|
|
|
|
The diagram to create: ${ask}`;
|
|
}
|
|
|
|
/** The skill's render contract: at least one Bash tool call ran gstack-render. */
|
|
function expectRenderedViaGstackRender(result: SkillTestResult): void {
|
|
const ran = result.toolCalls.some((c) => c.tool === 'Bash' && JSON.stringify(c.input ?? {}).includes('gstack-render'));
|
|
expect(ran).toBe(true);
|
|
}
|
|
|
|
describeDiagram('/diagram skill E2E', ['diagram-triplet', 'diagram-authoring-quality'], () => {
|
|
testConcurrentIfSelected('diagram-triplet', async () => {
|
|
const dir = setupDir('diagram-triplet-');
|
|
try {
|
|
const result = await runSkillTest({
|
|
prompt: basePrompt(
|
|
dir,
|
|
'a flowchart (graph LR) of a 4-stage pipeline: markdown → prepass → browser render → PDF.',
|
|
),
|
|
workingDirectory: dir,
|
|
maxTurns: 25,
|
|
allowedTools: ['Bash', 'Read', 'Write'],
|
|
timeout: CAPTURE_MS,
|
|
testName: 'diagram-triplet',
|
|
runId,
|
|
});
|
|
logCost('diagram triplet', result);
|
|
expect(result.exitReason).toBe('success');
|
|
expectRenderedViaGstackRender(result);
|
|
|
|
// The deterministic contract: all four artifacts exist and parse.
|
|
const mmd = fs.readFileSync(path.join(dir, 'out', 'flow.mmd'), 'utf-8');
|
|
expect(mmd).toMatch(/graph\s+(LR|TD)/);
|
|
|
|
const scene = JSON.parse(fs.readFileSync(path.join(dir, 'out', 'flow.excalidraw'), 'utf-8'));
|
|
expect(scene.type).toBe('excalidraw');
|
|
expect(Array.isArray(scene.elements)).toBe(true);
|
|
expect(scene.elements.length).toBeGreaterThan(3);
|
|
|
|
const svg = fs.readFileSync(path.join(dir, 'out', 'flow.svg'), 'utf-8');
|
|
expect(svg).toMatch(/<svg/i);
|
|
|
|
const png = fs.readFileSync(path.join(dir, 'out', 'flow.png'));
|
|
expect(png.subarray(0, 4)).toEqual(Buffer.from([0x89, 0x50, 0x4e, 0x47]));
|
|
expect(png.length).toBeGreaterThan(5_000);
|
|
} finally {
|
|
try { fs.rmSync(dir, { recursive: true, force: true }); } catch { /* ignore */ }
|
|
}
|
|
}, CAPTURE_MS);
|
|
|
|
testConcurrentIfSelected('diagram-authoring-quality', async () => {
|
|
const dir = setupDir('diagram-quality-');
|
|
try {
|
|
const result = await runSkillTest({
|
|
prompt: basePrompt(
|
|
dir,
|
|
'how gstack renders diagrams in PDFs: markdown containing mermaid fences goes through a pre-pass that extracts the fences, renders them in a browser (Aside, or gstack\'s own headless fallback) using an offline bundle, substitutes the SVG back in, inlines local images, and prints the PDF through the same browser. Failures become visible diagnostic blocks.',
|
|
),
|
|
workingDirectory: dir,
|
|
maxTurns: 25,
|
|
allowedTools: ['Bash', 'Read', 'Write'],
|
|
timeout: CAPTURE_MS,
|
|
testName: 'diagram-authoring-quality',
|
|
runId,
|
|
});
|
|
logCost('diagram authoring quality', result);
|
|
expect(result.exitReason).toBe('success');
|
|
expectRenderedViaGstackRender(result);
|
|
|
|
const mmd = fs.readFileSync(path.join(dir, 'out', 'flow.mmd'), 'utf-8');
|
|
const svg = fs.readFileSync(path.join(dir, 'out', 'flow.svg'), 'utf-8');
|
|
expect(svg).toMatch(/<svg/i);
|
|
|
|
const verdict = await callJudge<{ score: number; reasoning: string }>(
|
|
`You are judging the quality of an agent-authored mermaid diagram.
|
|
|
|
THE ASK: a diagram of gstack's PDF diagram-rendering flow — mermaid fences are
|
|
extracted by a pre-pass, rendered in a browser (Aside, or gstack's own headless
|
|
fallback) via an offline bundle, substituted back as SVG, images inlined,
|
|
printed to PDF through the same browser, with render failures becoming visible
|
|
diagnostic blocks.
|
|
|
|
THE AUTHORED MERMAID:
|
|
\`\`\`mermaid
|
|
${mmd}
|
|
\`\`\`
|
|
|
|
Score 1-10 on: faithfulness to the ask (are the named stages present and
|
|
correctly ordered?), label quality (short node labels, detail on edges),
|
|
and readable size (5-15 nodes, not a wall). A diagram that misses the
|
|
failure/diagnostic path entirely caps at 5 — that path is an explicitly
|
|
named requirement, so omitting it must fail the run.
|
|
|
|
Respond with JSON: {"score": N, "reasoning": "..."}`,
|
|
);
|
|
// eslint-disable-next-line no-console
|
|
console.log(`[diagram-quality] score=${verdict.score} — ${verdict.reasoning}`);
|
|
expect(verdict.score).toBeGreaterThanOrEqual(6);
|
|
} finally {
|
|
try { fs.rmSync(dir, { recursive: true, force: true }); } catch { /* ignore */ }
|
|
}
|
|
}, CAPTURE_MS);
|
|
});
|