ktx/scripts/codex-backend-live-smoke.mjs

161 lines
5 KiB
JavaScript
Raw Permalink Normal View History

feat: add codex llm backend for ktx runtime work (#253) * feat: add codex sdk runner foundation * feat: parse codex runtime events * feat: expose codex runtime mcp tools * feat: add codex llm runtime * feat: wire codex llm backend * test: avoid Array.fromAsync in codex runner test * docs: document codex llm backend * fix: tighten codex runtime config ownership * fix: use codex sdk env and thread options * fix: parse codex sdk event shapes * test: add codex backend live smoke * docs: clarify codex backend isolation * fix: drive codex loop metrics from mcp events * fix: enforce codex local step budget * docs: disclose codex isolation limits * fix: count all codex agent steps and stream step callbacks live The agent-loop step budget only counted completed mcp_tool_call items, so built-in command_execution steps (which the public Codex SDK/CLI surface can still expose) never decremented the budget, letting ingest/reconciliation run past stepBudget until Codex stopped on its own. onStepFinish was also replayed only after the whole stream drained, so live work_unit_step / reconciliation progress appeared stuck until the Codex process exited. collectEvents is now the single live step accumulator: it counts every completed agent-action item via a shared isCompletedAgentStep predicate (command_execution, mcp_tool_call, file_change, web_search), fires onStepFinish as each step completes, and enforces the budget on that broader count. A no-tool turn still counts as one step. toolFailures stays MCP-specific, since a non-zero command exit is normal agent exploration, not a loop failure. * test: align ingest llm-guard assertions with codex backend The skip-llm ingest guard message now lists codex as a valid backend and mentions a Claude Code/Codex session plus a codex setup hint, but this slow suite test still asserted the pre-codex wording. Update it to match the production message (already covered by the local-bundle-runtime unit test) and add the codex setup-line assertion. * fix: treat codex error:null tool calls as success The Codex SDK serializes error: null on successful mcp_tool_call items, so the failure check (item.error !== undefined) flagged every successful tool call as failed with the empty-payload default "Codex turn failed". This killed every ingest work unit under the codex backend before it could produce a patch. Key on status === 'failed' (authoritative, always set) and only treat a populated error object as a failure. Add a regression test built from a verbatim real-SDK event capture. * fix: default codex backend to gpt-5.5 and report real probe errors The previous default gpt-5.3-codex is an API-key-only model that the OpenAI API rejects under ChatGPT-account (subscription) auth, so codex status/setup failed with a misleading "authentication is not usable" message even though auth was fine. - Default codex model is now gpt-5.5 (works on both subscription and API-key auth); the curated setup picker offers gpt-5.5 / gpt-5.4 / gpt-5.4-mini and keeps free-form entry for account-specific ids (e.g. gpt-5.3-codex-spark). - runCodexAuthProbe now distinguishes "model not available" from an auth failure and surfaces the real API error: collectEvents retains stream events when the SDK throws on a non-zero exit, and the API error JSON envelope is unwrapped to its human-readable message. - The Codex isolation warning now renders inside the clack setup frame. - Docs updated to gpt-5.5 with a note that *-codex ids require API-key auth. * fix: require llm.models.default in status and match codex probe remediation Status reported a project ready when a non-none LLM backend was configured without llm.models.default, but the runtime (resolveModelSlots) hard-requires it, so ingest/scan/memory threw after `ktx status` said the project was usable. buildLlmStatus now fails for any non-none backend missing models.default and no longer invents a fallback model for claude-code/codex. Codex probe failures now carry a category-matched fix: a model-access failure steers the user at llm.models.default instead of the auth/install remediation. runCodexAuthProbe returns the fix and status consumes it; the message stays self-sufficient so setup output is unchanged. Docs: README now lists the codex backend and local Codex auth; ktx-setup.mdx states --llm-model only accepts codex/default or gpt-*/codex-* ids. Repaired four doctor fixtures that configured a backend without models.default (the now-correctly-blocked config) and added coverage for the new behavior.
2026-06-02 13:57:11 +02:00
import { execFile } from 'node:child_process';
import { mkdtemp, rm } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { dirname, join, resolve } from 'node:path';
import { fileURLToPath, pathToFileURL } from 'node:url';
import { promisify } from 'node:util';
const execFileAsync = promisify(execFile);
const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url));
const ROOT_DIR = resolve(SCRIPT_DIR, '..');
const OPT_IN_MESSAGE =
'Set KTX_RUN_CODEX_BACKEND_SMOKE=1 or pass --force to run the Codex backend live smoke.';
export function codexBackendSmokeOptIn(env = process.env, args = process.argv.slice(2)) {
if (env.KTX_RUN_CODEX_BACKEND_SMOKE === '1' || args.includes('--force')) {
return { run: true };
}
return { run: false, message: OPT_IN_MESSAGE };
}
async function run(command, args, options = {}) {
process.stdout.write(`$ ${command} ${args.join(' ')}\n`);
try {
const result = await execFileAsync(command, args, {
cwd: options.cwd ?? ROOT_DIR,
env: { ...process.env, ...(options.env ?? {}) },
encoding: 'utf8',
maxBuffer: 1024 * 1024 * 20,
timeout: options.timeoutMs ?? 300_000,
});
if (result.stdout) {
process.stdout.write(result.stdout);
}
if (result.stderr) {
process.stderr.write(result.stderr);
}
return { code: 0, stdout: result.stdout, stderr: result.stderr };
} catch (error) {
const stdout = typeof error.stdout === 'string' ? error.stdout : '';
const stderr = typeof error.stderr === 'string' ? error.stderr : error.message;
if (stdout) {
process.stdout.write(stdout);
}
if (stderr) {
process.stderr.write(stderr);
}
return {
code: typeof error.code === 'number' ? error.code : 1,
stdout,
stderr,
};
}
}
function requireSuccess(label, result) {
if (result.code !== 0) {
throw new Error(`${label} failed with code ${result.code}\nstdout:\n${result.stdout}\nstderr:\n${result.stderr}`);
}
}
async function runSetupSmoke(projectDir) {
const result = await run(
'node',
[
join(ROOT_DIR, 'packages/cli/dist/bin.js'),
'setup',
'--project-dir',
projectDir,
'--llm-backend',
'codex',
'--llm-model',
'gpt-5.3-codex',
'--no-input',
'--yes',
'--skip-databases',
'--skip-sources',
'--skip-agents',
],
{ timeoutMs: 600_000 },
);
requireSuccess('ktx setup codex backend', result);
if (!result.stdout.includes('LLM ready: yes (codex, gpt-5.3-codex)')) {
throw new Error(`setup did not report Codex LLM readiness\nstdout:\n${result.stdout}`);
}
}
async function runRuntimeSmoke(projectDir) {
const runtimeUrl = pathToFileURL(join(ROOT_DIR, 'packages/cli/dist/context/llm/codex-runtime.js')).href;
const zodUrl = pathToFileURL(join(ROOT_DIR, 'packages/cli/node_modules/zod/index.js')).href;
const { CodexKtxLlmRuntime } = await import(runtimeUrl);
const { z } = await import(zodUrl);
const runtime = new CodexKtxLlmRuntime({
projectDir,
modelSlots: { default: 'gpt-5.3-codex' },
});
const text = await runtime.generateText({
role: 'default',
prompt: 'Reply with exactly: ktx_codex_text_ok',
});
if (text.trim() !== 'ktx_codex_text_ok') {
throw new Error(`Codex text smoke returned unexpected text: ${text}`);
}
let toolCalls = 0;
const loop = await runtime.runAgentLoop({
modelRole: 'default',
systemPrompt: 'You must use available tools when the user asks for a tool result.',
userPrompt:
'Call the echo_value tool with {"value":"ktx_codex_tool_ok"}, then finish after the tool returns.',
toolSet: {
echo_value: {
name: 'echo_value',
description: 'Return the provided value as markdown.',
inputSchema: z.object({ value: z.string() }),
execute: async (input) => {
toolCalls += 1;
return { markdown: `echo:${input.value}` };
},
},
},
stepBudget: 4,
telemetryTags: {},
});
if (loop.stopReason !== 'natural') {
throw new Error(`Codex tool smoke stopped with ${loop.stopReason}: ${loop.error?.message ?? 'no error'}`);
}
if (toolCalls !== 1) {
throw new Error(`Expected Codex to call echo_value exactly once, got ${toolCalls}`);
}
}
export async function runCodexBackendLiveSmoke() {
const projectDir = await mkdtemp(join(tmpdir(), 'ktx-codex-backend-smoke-'));
try {
requireSuccess(
'ktx build',
await run('pnpm', ['--filter', '@kaelio/ktx', 'run', 'build'], { timeoutMs: 600_000 }),
);
await runSetupSmoke(projectDir);
await runRuntimeSmoke(projectDir);
process.stdout.write(`Codex backend live smoke passed in ${projectDir}\n`);
} finally {
await rm(projectDir, { recursive: true, force: true });
}
}
async function main() {
const optIn = codexBackendSmokeOptIn();
if (!optIn.run) {
process.stdout.write(`${optIn.message}\n`);
return;
}
await runCodexBackendLiveSmoke();
}
if (import.meta.url === pathToFileURL(process.argv[1] ?? '').href) {
await main();
}