mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-05 16:34:00 +01:00
* fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807) * ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997) * fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805) * fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847) * feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096) Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com> * fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851) * fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906) * test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910) * chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes * v1.91.14.0: release metadata * test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group * ci: Codex login steps run under bash (the CI container's default sh rejects pipefail) * fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt * fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts * test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call * fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier * test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers) * test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts) * test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep) * fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit * test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently * test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census * fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic * test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output * fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens * test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design) * test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept) * fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files --------- Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>
140 lines
4.4 KiB
TypeScript
140 lines
4.4 KiB
TypeScript
/**
|
|
* Shared helpers for daemon + daemon-client tests.
|
|
*
|
|
* Two test styles live here:
|
|
* - In-process: import fetchHandler from daemon.ts and call it with a
|
|
* synthesized Request. Fast, no spawn, no HTTP. Covers routing +
|
|
* handler semantics. Used by most of daemon.test.ts.
|
|
* - Out-of-process: spawn `bun run design/src/daemon.ts` with a tmp
|
|
* state file + env overrides, then HTTP against the bound port.
|
|
* Slow but only path that proves real spawn + state file + signal
|
|
* handling work. Used by daemon-discovery.test.ts.
|
|
*/
|
|
|
|
import { spawn, type ChildProcess } from "child_process";
|
|
import fs from "fs";
|
|
import os from "os";
|
|
import path from "path";
|
|
|
|
import { __testInternals__ } from "../src/daemon";
|
|
|
|
export const DAEMON_SCRIPT = path.join(import.meta.dir, "..", "src", "daemon.ts");
|
|
|
|
export function makeTmpDir(prefix = "design-daemon-test"): string {
|
|
return fs.mkdtempSync(path.join(os.tmpdir(), `${prefix}-`));
|
|
}
|
|
|
|
export function makeBoardHtml(tmpDir: string, body = "<p>Test board</p>"): string {
|
|
const p = path.join(tmpDir, "design-board.html");
|
|
fs.writeFileSync(
|
|
p,
|
|
`<!DOCTYPE html><html><head></head><body>${body}</body></html>`,
|
|
);
|
|
return p;
|
|
}
|
|
|
|
/** Reset the in-process daemon state between tests. */
|
|
export function resetDaemon(): void {
|
|
__testInternals__.resetForTest();
|
|
}
|
|
|
|
/** Build a Request for the in-process fetchHandler tests. */
|
|
export function req(method: string, urlPath: string, body?: unknown): Request {
|
|
const init: RequestInit = { method };
|
|
if (body !== undefined) {
|
|
init.body = typeof body === "string" ? body : JSON.stringify(body);
|
|
init.headers = { "Content-Type": "application/json" };
|
|
}
|
|
return new Request(`http://127.0.0.1:1234${urlPath}`, init);
|
|
}
|
|
|
|
export interface SpawnedDaemon {
|
|
proc: ChildProcess;
|
|
port: number;
|
|
stateFile: string;
|
|
stop: () => Promise<void>;
|
|
}
|
|
|
|
/**
|
|
* Spawn a real daemon process pointed at a per-test state file, with an
|
|
* aggressive idle window so idle-shutdown tests don't take 24h. Resolves
|
|
* when stdout emits `DAEMON_STARTED port=<N>`.
|
|
*/
|
|
export async function spawnDaemonForTest(
|
|
opts: { stateFile?: string; idleMs?: number; checkMs?: number; env?: Record<string, string> } = {},
|
|
): Promise<SpawnedDaemon> {
|
|
const stateFile = opts.stateFile ?? path.join(makeTmpDir("daemon-state"), "design.json");
|
|
const env: Record<string, string> = {
|
|
...(process.env as Record<string, string>),
|
|
// DESIGN_DAEMON_STATE_FILE points both daemon and any same-process
|
|
// discovery at this test's state file (overrides resolveStateFilePath).
|
|
DESIGN_DAEMON_STATE_FILE: stateFile,
|
|
DESIGN_DAEMON_IDLE_MS: String(opts.idleMs ?? 60_000),
|
|
DESIGN_DAEMON_CHECK_MS: String(opts.checkMs ?? 1000),
|
|
DESIGN_DAEMON_VERSION: "test-version",
|
|
GSTACK_HOME: path.join(path.dirname(stateFile), "gstack-home"),
|
|
...(opts.env ?? {}),
|
|
};
|
|
|
|
// Spawn with a marker in argv so cmdline-based identity verification
|
|
// exercises the real CMDLINE_MARKER ("gstack-design-daemon").
|
|
const proc = spawn(
|
|
"bun",
|
|
["run", DAEMON_SCRIPT, "--marker", "gstack-design-daemon"],
|
|
{
|
|
env,
|
|
stdio: ["ignore", "pipe", "pipe"],
|
|
cwd: path.dirname(stateFile),
|
|
},
|
|
);
|
|
|
|
const port = await new Promise<number>((resolve, reject) => {
|
|
const onTimeout = setTimeout(() => {
|
|
proc.kill("SIGKILL");
|
|
reject(new Error("Daemon failed to emit DAEMON_STARTED within 5s"));
|
|
}, 5000);
|
|
proc.stdout!.on("data", (chunk: Buffer) => {
|
|
const line = chunk.toString();
|
|
const m = line.match(/DAEMON_STARTED port=(\d+)/);
|
|
if (m) {
|
|
clearTimeout(onTimeout);
|
|
resolve(parseInt(m[1]!, 10));
|
|
}
|
|
});
|
|
proc.on("error", (e) => {
|
|
clearTimeout(onTimeout);
|
|
reject(e);
|
|
});
|
|
proc.on("exit", (code) => {
|
|
clearTimeout(onTimeout);
|
|
reject(new Error(`Daemon exited early with code ${code}`));
|
|
});
|
|
});
|
|
|
|
return {
|
|
proc,
|
|
port,
|
|
stateFile,
|
|
stop: async () => {
|
|
if (proc.exitCode !== null || proc.signalCode !== null) return;
|
|
await new Promise<void>((r) => {
|
|
const onExit = () => {
|
|
clearTimeout(t);
|
|
r();
|
|
};
|
|
const t = setTimeout(() => {
|
|
proc.removeListener("exit", onExit);
|
|
try {
|
|
proc.kill("SIGKILL");
|
|
} catch {
|
|
// gone
|
|
}
|
|
r();
|
|
}, 2000);
|
|
proc.once("exit", onExit);
|
|
proc.kill("SIGTERM");
|
|
});
|
|
},
|
|
};
|
|
}
|