mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-13 16:38:56 +02:00
v1.81.0.0 feat: Aside is the browser gstack drives first; every browsing skill, the PDF/diagram renderer, and web research; the bundled browser stays the automatic fallback (#2810)
* 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>
This commit is contained in:
Garry Tan
co-authored by
Claude Fable 5.1
Sina
Claude Fable 5.1
Sina
parent
c241216637
commit
0530392821
@@ -1,13 +1,14 @@
|
||||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||||
import { CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
|
||||
import { runSkillTest } from './helpers/session-runner';
|
||||
import { runSkillTest, type SkillTestResult } from './helpers/session-runner';
|
||||
import { callJudge } from './helpers/llm-judge';
|
||||
import {
|
||||
ROOT, browseBin, runId, evalsEnabled,
|
||||
ROOT, runId, evalsEnabled, selectedTests,
|
||||
describeIfSelected, testConcurrentIfSelected,
|
||||
copyDirSync, setupBrowseShims, logCost, recordE2E,
|
||||
copyDirSync, logCost, recordE2E,
|
||||
createEvalCollector, finalizeEvalCollector,
|
||||
} from './helpers/e2e-helpers';
|
||||
import { asideAvailable } from './helpers/aside-available';
|
||||
import { spawnSync } from 'child_process';
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
@@ -182,13 +183,29 @@ Write DESIGN.md and CLAUDE.md (or update it) in the working directory.`,
|
||||
}, CAPTURE_LONG_MS);
|
||||
|
||||
testConcurrentIfSelected('design-consultation-research', async () => {
|
||||
// Test WebSearch integration — research phase only, no DESIGN.md generation
|
||||
// Research phase only, no DESIGN.md generation. Web research runs in Aside
|
||||
// first, WebSearch second ({{ASIDE_RESEARCH}}, rendered into
|
||||
// design-consultation/SKILL.md). With Aside live the agent MUST search
|
||||
// through `aside exec` — a straight-to-WebSearch run is the ordering bug
|
||||
// this case pins. Without Aside (CI, or GSTACK_SKIP_ASIDE=1) it must use
|
||||
// the WebSearch tool, or say the fallback sentence when that is missing
|
||||
// too, and write the notes from in-distribution knowledge. Either way the
|
||||
// notes file must exist.
|
||||
const researchDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-research-'));
|
||||
|
||||
const result = await runSkillTest({
|
||||
prompt: `You have access to WebSearch. Research civic tech data platform designs.
|
||||
// Extract only the research contract (CLAUDE.md: extract, don't copy). The tree's
|
||||
// SKILL.md unless GSTACK_E2E_DOCS_ROOT points at a `gen:skill-docs --out-dir` render.
|
||||
const skill = fs.readFileSync(path.join(process.env.GSTACK_E2E_DOCS_ROOT || ROOT, 'design-consultation', 'SKILL.md'), 'utf-8');
|
||||
const sectionStart = skill.indexOf('## Web research runs in Aside');
|
||||
if (sectionStart < 0) throw new Error('design-consultation/SKILL.md has no "Web research runs in Aside" section — regenerate with: bun run gen:skill-docs');
|
||||
const sectionEnd = skill.indexOf('\n## ', sectionStart + 1);
|
||||
fs.writeFileSync(path.join(researchDir, 'research-contract.md'), skill.slice(sectionStart, sectionEnd > sectionStart ? sectionEnd : undefined));
|
||||
const live = asideAvailable();
|
||||
|
||||
Do exactly 2 WebSearch queries:
|
||||
const result = await runSkillTest({
|
||||
prompt: `Read ${researchDir}/research-contract.md first and follow it exactly: it says how web research runs in this project.
|
||||
|
||||
Research civic tech data platform designs. Run exactly 2 research queries:
|
||||
1. 'civic tech government data platform design 2025'
|
||||
2. 'open data portal UX best practices'
|
||||
|
||||
@@ -196,7 +213,8 @@ Summarize the key design patterns you found to ${researchDir}/research-notes.md.
|
||||
Include: color trends, typography patterns, and layout conventions you observed.
|
||||
Do NOT generate a full DESIGN.md — just research notes.`,
|
||||
workingDirectory: researchDir,
|
||||
maxTurns: 8,
|
||||
maxTurns: 10,
|
||||
allowedTools: ['Bash', 'Read', 'Write', 'WebSearch'],
|
||||
// 300s, not 90s: saturated-runner class (same as review-dashboard-via /
|
||||
// retro-base-branch). PR #2533 CI observed the sibling preview test at
|
||||
// 0 turns/$0.00 for 93s x3 attempts — session up, first completion
|
||||
@@ -214,19 +232,29 @@ Do NOT generate a full DESIGN.md — just research notes.`,
|
||||
const notesExist = fs.existsSync(notesPath);
|
||||
const notesContent = notesExist ? fs.readFileSync(notesPath, 'utf-8') : '';
|
||||
|
||||
// Check if WebSearch was used
|
||||
// Aside live: research went through `aside exec` in a Bash tool call (WebSearch
|
||||
// alone is the wrong order). Aside absent: WebSearch tool, or the fallback sentence.
|
||||
const asideExecCalls = result.toolCalls.filter(tc => tc.tool === 'Bash' && /\baside exec\b/.test(String(tc.input?.command ?? '')));
|
||||
const webSearchCalls = result.toolCalls.filter(tc => tc.tool === 'WebSearch');
|
||||
if (webSearchCalls.length > 0) {
|
||||
console.log(`WebSearch used ${webSearchCalls.length} times`);
|
||||
} else {
|
||||
console.warn('WebSearch not used — may be unavailable in test env');
|
||||
}
|
||||
const searched = asideExecCalls.length > 0 || webSearchCalls.length > 0;
|
||||
// Neither: the agent SAID the fallback. Assistant text blocks only — the
|
||||
// contract file the agent Reads contains the same sentence, so tool_result
|
||||
// content must not count.
|
||||
const assistantText = result.transcript
|
||||
.filter((e: any) => e?.type === 'assistant')
|
||||
.flatMap((e: any) => (e.message?.content ?? []).filter((c: any) => c?.type === 'text').map((c: any) => String(c.text)))
|
||||
.join('\n');
|
||||
const saidFallback = assistantText.includes('Search unavailable');
|
||||
const researchOk = live ? asideExecCalls.length > 0 : (searched || saidFallback);
|
||||
console.log(`aside exec issued ${asideExecCalls.length} times; WebSearch called ${webSearchCalls.length} times; Aside live: ${live}; fallback said: ${saidFallback}`);
|
||||
|
||||
recordE2E(evalCollector, '/design-consultation research', 'Design Consultation E2E', result, {
|
||||
passed: notesExist && notesContent.length > 200 && ['success', 'error_max_turns'].includes(result.exitReason),
|
||||
passed: researchOk && notesExist && notesContent.length > 200 && ['success', 'error_max_turns'].includes(result.exitReason),
|
||||
});
|
||||
|
||||
expect(['success', 'error_max_turns']).toContain(result.exitReason);
|
||||
if (live) expect(asideExecCalls.length).toBeGreaterThan(0);
|
||||
else expect(searched || saidFallback).toBe(true);
|
||||
expect(notesExist).toBe(true);
|
||||
if (notesExist) {
|
||||
expect(notesContent.length).toBeGreaterThan(200);
|
||||
@@ -502,13 +530,36 @@ IMPORTANT: Do NOT try to browse any URLs or use a browse binary. This is a plan
|
||||
|
||||
// --- Design Review E2E (live-site audit + fix) ---
|
||||
|
||||
/**
|
||||
* Concatenated tool_result text from the stream-json transcript. runSkillTest
|
||||
* leaves toolCalls[].output empty, and the agent's Bash INPUT also contains
|
||||
* the sentinel string — only the tool_result proves the script printed it.
|
||||
*/
|
||||
function toolOutput(result: SkillTestResult): string {
|
||||
const parts: string[] = [];
|
||||
for (const e of result.transcript) {
|
||||
if (e?.type !== 'user') continue;
|
||||
for (const item of e.message?.content ?? []) {
|
||||
if (item?.type !== 'tool_result') continue;
|
||||
parts.push(typeof item.content === 'string' ? item.content : JSON.stringify(item.content ?? ''));
|
||||
}
|
||||
}
|
||||
return parts.join('\n');
|
||||
}
|
||||
|
||||
// /design-review drives the Aside browser; without it the skill's BROWSER SETUP stops at
|
||||
// NEEDS_ASIDE, so the block self-skips (CI runners have no Aside).
|
||||
describeIfSelected('Design Review E2E', ['design-review-fix'], () => {
|
||||
// bun runs describe.skip callbacks too — probe only when this block is actually selected,
|
||||
// so an unrelated eval run never pays the up-to-30s `aside repl` probe.
|
||||
const selected = evalsEnabled && (selectedTests === null || selectedTests.includes('design-review-fix'));
|
||||
if (selected && !asideAvailable()) { test.skip('needs Aside', () => {}); return; }
|
||||
|
||||
let qaDesignDir: string;
|
||||
let qaDesignServer: ReturnType<typeof Bun.serve> | null = null;
|
||||
|
||||
beforeAll(() => {
|
||||
qaDesignDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-qa-design-'));
|
||||
setupBrowseShims(qaDesignDir);
|
||||
|
||||
const run = (cmd: string, args: string[]) =>
|
||||
spawnSync(cmd, args, { cwd: qaDesignDir, stdio: 'pipe', timeout: 5000 });
|
||||
@@ -594,11 +645,7 @@ describeIfSelected('Design Review E2E', ['design-review-fix'], () => {
|
||||
const serverUrl = `http://localhost:${(qaDesignServer as any)?.port}`;
|
||||
|
||||
const result = await runSkillTest({
|
||||
prompt: `IMPORTANT: The browse binary is already assigned below as B. Do NOT search for it or run the SKILL.md setup block — just use $B directly.
|
||||
|
||||
B="${browseBin}"
|
||||
|
||||
Read design-review/SKILL.md for the design review + fix workflow.
|
||||
prompt: `The Aside browser is installed and running. Read design-review/SKILL.md for the design review + fix workflow and follow its BROWSER SETUP section: drive the browser with \`aside repl\` scripts shaped exactly like its cookbook. Do not look for any other browser binary.
|
||||
|
||||
Review the site at ${serverUrl}. Use --quick mode. Skip any AskUserQuestion calls — this is non-interactive. Fix up to 3 issues max. Write your report to ./design-audit.md.`,
|
||||
workingDirectory: qaDesignDir,
|
||||
@@ -620,12 +667,24 @@ Review the site at ${serverUrl}. Use --quick mode. Skip any AskUserQuestion call
|
||||
const commits = gitLog.stdout.toString().trim().split('\n');
|
||||
const designFixCommits = commits.filter((c: string) => c.includes('style(design)'));
|
||||
|
||||
// The agent must actually drive Aside: an `aside repl` Bash call, a printed sentinel
|
||||
// (from a tool_result, never the input), and no reach for the retired browse binary.
|
||||
const bashCommands = result.toolCalls
|
||||
.filter(t => t.tool === 'Bash')
|
||||
.map(t => String(t.input?.command ?? ''));
|
||||
const droveAside = bashCommands.some(c => /aside repl/.test(c));
|
||||
const sentinelPrinted = /GSTACK_STEP_OK/.test(toolOutput(result));
|
||||
const usedBrowseBin = bashCommands.some(c => /browse\/dist\/browse|\$B /.test(c));
|
||||
|
||||
recordE2E(evalCollector, '/design-review fix', 'Design Review E2E', result, {
|
||||
passed: ['success', 'error_max_turns'].includes(result.exitReason),
|
||||
passed: ['success', 'error_max_turns'].includes(result.exitReason) && droveAside && sentinelPrinted && !usedBrowseBin,
|
||||
});
|
||||
|
||||
// Accept error_max_turns — the fix loop is complex
|
||||
expect(['success', 'error_max_turns']).toContain(result.exitReason);
|
||||
expect(droveAside).toBe(true);
|
||||
expect(sentinelPrinted).toBe(true);
|
||||
expect(usedBrowseBin).toBe(false);
|
||||
|
||||
// Report and commits are best-effort — log what happened
|
||||
if (reportExists) {
|
||||
|
||||
Reference in New Issue
Block a user