mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-09-30 12:39:42 +02:00
Codeman maintainer
4205f6930f
A full review of the release tree found seven things, and four of them were mine. **The gate was red, and I put it there.** Splitting `confirmed` into `confirmedContext` and `confirmedSwap` changed the wire field without moving three assertions that check it: `custom-model-one-shot-launch.test.ts` and two in `custom-model-run-menu-ui.test.ts` (the swap modal and the context modal, each of which already receives exactly the right per-question flag). Moved, with the titles. **Worse, my own tests for the split never ran.** The four cases in `session-custom-model.test.ts` that exist specifically to pin it call `mockRunning()`, which was declared inside a sibling `describe`, so they threw a ReferenceError during setup. The split would have shipped with no passing server-side coverage while the gate reported the failure as four broken tests rather than as four tests that were never written. `mockRunning` is hoisted to the outer describe. **The submit verifier pressed Enter into shell panes.** `#455`'s SubmitVerifier resolved its composer glyph as `promptGlyph ?? '❯'`, and only claude and codex declare one, so the other eight modes fell back to claude's `❯`. That is also starship's default shell prompt, and pure's, and spaceship's, and p10k lean's. On such a shell the line `❯ npm run build` sits on screen for as long as the command runs, the verifier reads it as an unsubmitted prompt, and re-presses Enter into the running program's stdin up to nine times on its 2s..60s schedule. Mostly a stray newline; not harmless against a y/N prompt, `read -p`, an installer or a pager, where it takes the default. The module's own fileoverview already stated the rule this broke. Now `?? ''`, which `promptStillInComposer()` already treats as inert, so the verifier runs only for a CLI that actually declares a composer. **My #451 dedent removal left a count behind**: "Two rules keep it honest" introducing three numbered rules. The rest is documentation the split outran. `confirmedContext`/`confirmedSwap` appeared in no doc at all, while `docs/api-reference.md` (the SemVer-covered contract) still told an integrator to retry with `confirmed: true` for both questions, which is precisely the thing the split exists to stop. Documented there, in `docs/custom-model-endpoints.md` and in CLAUDE.md. The custom-model changeset gained the split and the `CLAUDE_CONFIG_DIR` multi-user consequence, both user-visible and both previously absent, and #454's gained the one exception to its own claim: a Custom Endpoints launch ignores the Instance count stepper and always starts one session. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
242 lines
9.7 KiB
TypeScript
242 lines
9.7 KiB
TypeScript
/**
|
|
* @fileoverview Frontend tests for the one-shot custom-model launch path added to
|
|
* session-ui.js (docs/custom-model-endpoints-plan.md): `runCustomModelEntry` dispatches
|
|
* to `_runCustomModelEntryOneShot` for every custom-model-eligible CLI except claude,
|
|
* which launches directly on the endpoint (no restart) by folding `customModel` into
|
|
* the run<Mode>() function's own `/api/quick-start` body via `_pendingCustomModelForLaunch`
|
|
* and `_quickStartWithCustomModelConfirm`. Fixes the visible native-boot-then-restart the
|
|
* restart-after-launch path (`_runCustomModelEntryViaRestart`, still used for claude)
|
|
* showed on every custom-model run — confirmed live on Codex, whose TUI fully
|
|
* reinitializes on a restart.
|
|
*
|
|
* Uses the same JSDOM + `runScripts: "dangerously"` approach as
|
|
* test/custom-model-run-menu-ui.test.ts, extended with the DOM elements runCodex() (the
|
|
* CLI this was reported against) reads.
|
|
*
|
|
* Port: none.
|
|
*/
|
|
import { readFileSync } from 'node:fs';
|
|
import { JSDOM } from 'jsdom';
|
|
import { describe, expect, it } from 'vitest';
|
|
|
|
const CONSTANTS_JS = readFileSync(new URL('../src/web/public/constants.js', import.meta.url), 'utf-8');
|
|
const SESSION_UI_JS = readFileSync(new URL('../src/web/public/session-ui.js', import.meta.url), 'utf-8');
|
|
|
|
function bootApp() {
|
|
const dom = new JSDOM(
|
|
`<!doctype html><body>
|
|
<select id="quickStartCase"><option value="testcase" selected>testcase</option></select>
|
|
<input id="tabCount" value="1">
|
|
<button id="runBtn"></button>
|
|
<div id="runModeMenu"></div>
|
|
</body>`,
|
|
{ url: 'http://localhost/', runScripts: 'dangerously' }
|
|
);
|
|
const win = dom.window as unknown as Window & typeof globalThis & { CodemanApp: new () => any };
|
|
(win as unknown as { eval: (s: string) => void }).eval('window.CodemanApp = function CodemanApp() {};');
|
|
(win as unknown as { eval: (s: string) => void }).eval(CONSTANTS_JS);
|
|
(win as unknown as { eval: (s: string) => void }).eval(SESSION_UI_JS);
|
|
const app = new win.CodemanApp();
|
|
app.cases = [{ name: 'testcase' }];
|
|
app.terminal = { focus: () => {} };
|
|
app.loadAppSettingsFromStorage = () => ({});
|
|
app.getCaseSettings = () => ({});
|
|
app.buildEnvOverrides = () => ({});
|
|
app.showToast = () => {};
|
|
app._beginSessionLaunchStatus = () => 'status-token';
|
|
app._reportSessionLaunchError = (_token: unknown, message: string) => {
|
|
app._lastReportedError = message;
|
|
};
|
|
app._ensureCreatedSessionVisible = async () => {};
|
|
app.selectSession = async () => {};
|
|
app._nextCaseSessionStartNumber = () => 1;
|
|
return { win, app };
|
|
}
|
|
|
|
describe('runCustomModelEntry dispatch', () => {
|
|
it('routes claude through the restart-after-launch path', async () => {
|
|
const { app } = bootApp();
|
|
let calledRestart = false;
|
|
let calledOneShot = false;
|
|
app._runCustomModelEntryViaRestart = async () => {
|
|
calledRestart = true;
|
|
};
|
|
app._runCustomModelEntryOneShot = async () => {
|
|
calledOneShot = true;
|
|
};
|
|
await app.runCustomModelEntry('claude', 'llama-box', 'qwen3');
|
|
expect(calledRestart).toBe(true);
|
|
expect(calledOneShot).toBe(false);
|
|
});
|
|
|
|
it('routes every other custom-model-eligible CLI through the one-shot path', async () => {
|
|
for (const mode of ['opencode', 'codex', 'gemini', 'pi', 'grok', 'deepseek', 'omp']) {
|
|
const { app } = bootApp();
|
|
let calledRestart = false;
|
|
let calledOneShot = false;
|
|
app._runCustomModelEntryViaRestart = async () => {
|
|
calledRestart = true;
|
|
};
|
|
app._runCustomModelEntryOneShot = async () => {
|
|
calledOneShot = true;
|
|
};
|
|
await app.runCustomModelEntry(mode, 'llama-box', 'qwen3');
|
|
expect(calledRestart, mode).toBe(false);
|
|
expect(calledOneShot, mode).toBe(true);
|
|
}
|
|
});
|
|
});
|
|
|
|
describe('_runCustomModelEntryOneShot', () => {
|
|
it('stashes the pick on _pendingCustomModelForLaunch for the duration of run(), then clears it', async () => {
|
|
const { app } = bootApp();
|
|
let seenDuringRun: unknown;
|
|
app.run = async function (this: typeof app) {
|
|
seenDuringRun = this._pendingCustomModelForLaunch;
|
|
};
|
|
await app._runCustomModelEntryOneShot('codex', 'llama-box', 'qwen3');
|
|
expect(seenDuringRun).toEqual({ endpointId: 'llama-box', modelId: 'qwen3' });
|
|
expect(app._pendingCustomModelForLaunch).toBeUndefined();
|
|
});
|
|
|
|
it('clears the pending pick even when run() throws', async () => {
|
|
const { app } = bootApp();
|
|
app.run = async () => {
|
|
throw new Error('boom');
|
|
};
|
|
await expect(app._runCustomModelEntryOneShot('codex', 'llama-box', 'qwen3')).rejects.toThrow('boom');
|
|
expect(app._pendingCustomModelForLaunch).toBeUndefined();
|
|
});
|
|
|
|
it('starts the loading watcher when the launch reports modelSwapInProgress, passing the new session id', async () => {
|
|
const { app } = bootApp();
|
|
app.run = async () => {
|
|
app._lastCustomModelLaunchResult = { modelSwapInProgress: true, sessionId: 'new-session' };
|
|
};
|
|
let watched: unknown[] | null = null;
|
|
app._watchLlamaSwapLoading = async (...args: unknown[]) => {
|
|
watched = args;
|
|
};
|
|
await app._runCustomModelEntryOneShot('codex', 'llama-box', 'qwen3');
|
|
expect(watched).toEqual(['llama-box', 'qwen3', 'new-session']);
|
|
});
|
|
|
|
it('never starts the watcher when no swap was needed', async () => {
|
|
const { app } = bootApp();
|
|
app.run = async () => {
|
|
app._lastCustomModelLaunchResult = { modelSwapInProgress: false };
|
|
};
|
|
let watchCalled = false;
|
|
app._watchLlamaSwapLoading = async () => {
|
|
watchCalled = true;
|
|
};
|
|
await app._runCustomModelEntryOneShot('codex', 'llama-box', 'qwen3');
|
|
expect(watchCalled).toBe(false);
|
|
});
|
|
});
|
|
|
|
describe('_quickStartWithCustomModelConfirm', () => {
|
|
function withFetch(win: Window & typeof globalThis, handler: (body: any) => any) {
|
|
(win as unknown as { fetch: typeof fetch }).fetch = (async (_url: string, opts: any) => ({
|
|
json: async () => handler(JSON.parse(opts.body)),
|
|
})) as unknown as typeof fetch;
|
|
}
|
|
|
|
it('returns the response directly when no confirmation is needed', async () => {
|
|
const { win, app } = bootApp();
|
|
withFetch(win, (body) => ({ success: true, data: { sessionId: 's1', modelSwapInProgress: false, body } }));
|
|
const data = await app._quickStartWithCustomModelConfirm({
|
|
mode: 'codex',
|
|
customModel: { endpointId: 'e', modelId: 'm' },
|
|
});
|
|
expect(data.success).toBe(true);
|
|
expect(data.data.sessionId).toBe('s1');
|
|
expect(app._lastCustomModelLaunchResult).toEqual(data.data);
|
|
});
|
|
|
|
it('confirming re-sends with confirmedSwap and returns the second response', async () => {
|
|
const { win, app } = bootApp();
|
|
app._confirmModelSwap = async () => true;
|
|
let calls = 0;
|
|
withFetch(win, (body) => {
|
|
calls += 1;
|
|
if (calls === 1) {
|
|
return {
|
|
success: true,
|
|
data: {
|
|
requiresConfirmation: true,
|
|
currentlyLoadedModel: 'llama3',
|
|
affectedSessions: [{ id: 's2', name: 'w2' }],
|
|
},
|
|
};
|
|
}
|
|
// the SWAP question's own flag, never the blanket `confirmed`: answering this one
|
|
// must not also silence the context-floor warning.
|
|
expect(body.customModel.confirmedSwap).toBe(true);
|
|
expect(body.customModel.confirmed).toBeUndefined();
|
|
return { success: true, data: { sessionId: 's1', modelSwapInProgress: true } };
|
|
});
|
|
const data = await app._quickStartWithCustomModelConfirm({
|
|
mode: 'codex',
|
|
customModel: { endpointId: 'e', modelId: 'm' },
|
|
});
|
|
expect(calls).toBe(2);
|
|
expect(data.data.sessionId).toBe('s1');
|
|
expect(app._lastCustomModelLaunchResult.modelSwapInProgress).toBe(true);
|
|
});
|
|
|
|
it('cancelling never re-sends, and reports a cancellation error', async () => {
|
|
const { win, app } = bootApp();
|
|
app._confirmModelSwap = async () => false;
|
|
let calls = 0;
|
|
withFetch(win, () => {
|
|
calls += 1;
|
|
return {
|
|
success: true,
|
|
data: {
|
|
requiresConfirmation: true,
|
|
currentlyLoadedModel: 'llama3',
|
|
affectedSessions: [{ id: 's2', name: 'w2' }],
|
|
},
|
|
};
|
|
});
|
|
const data = await app._quickStartWithCustomModelConfirm({
|
|
mode: 'codex',
|
|
customModel: { endpointId: 'e', modelId: 'm' },
|
|
});
|
|
expect(calls).toBe(1);
|
|
expect(data.success).toBe(false);
|
|
expect(data.error).toMatch(/cancelled/i);
|
|
expect(app._lastCustomModelLaunchResult).toBeUndefined();
|
|
});
|
|
});
|
|
|
|
describe('runCodex(): one-shot custom-model launch (the CLI this was reported against)', () => {
|
|
it('folds _pendingCustomModelForLaunch into the quick-start body as customModel', async () => {
|
|
const { win, app } = bootApp();
|
|
(win as unknown as { fetch: typeof fetch }).fetch = (async (url: string, opts?: any) => {
|
|
if (url === '/api/codex/status') return { json: async () => ({ data: { available: true } }) };
|
|
const body = JSON.parse(opts.body);
|
|
expect(body.customModel).toEqual({ endpointId: 'llama-box', modelId: 'qwen3' });
|
|
return { json: async () => ({ success: true, data: { sessionId: 's1', modelSwapInProgress: false } }) };
|
|
}) as unknown as typeof fetch;
|
|
|
|
app._pendingCustomModelForLaunch = { endpointId: 'llama-box', modelId: 'qwen3' };
|
|
await app.runCodex();
|
|
expect(app._lastReportedError).toBeUndefined();
|
|
});
|
|
|
|
it('omits customModel entirely for a plain (non-custom-model) Codex launch', async () => {
|
|
const { win, app } = bootApp();
|
|
(win as unknown as { fetch: typeof fetch }).fetch = (async (url: string, opts?: any) => {
|
|
if (url === '/api/codex/status') return { json: async () => ({ data: { available: true } }) };
|
|
const body = JSON.parse(opts.body);
|
|
expect(body.customModel).toBeUndefined();
|
|
return { json: async () => ({ success: true, data: { sessionId: 's1' } }) };
|
|
}) as unknown as typeof fetch;
|
|
|
|
await app.runCodex();
|
|
expect(app._lastReportedError).toBeUndefined();
|
|
});
|
|
});
|