Files
openclaw/scripts/test-extension-batch.mjs
Peter Steinberger bb46b79d3c refactor: internalize OpenClaw agent runtime (#85341)
* refactor: extract agent core package

Introduce packages/agent-core as the OpenClaw-owned home for reusable agent loop, harness, session, prompt, and runtime dependency contracts.

* refactor: extract shared llm runtime

Move provider model registries, stream wrappers, OAuth helpers, and LLM utilities into src/llm with plugin-sdk barrels instead of depending on the old embedded runtime layout.

* refactor: remove pi runtime internals

Rename remaining Pi-shaped agent surfaces to OpenClaw agent runtime names, delete obsolete Pi docs and package graph checks, and add the third-party notice for incorporated code.

* refactor: tighten agent session runtime

Make agent-core/runtime dependencies explicit, consolidate compaction and session transcript helpers, and move model/session helpers behind OpenClaw-owned contracts.

* refactor: remove static model and pi auth paths

Drop static model catalogs and Pi auth bridges, move model/provider facts to manifest-owned runtime contracts, and harden internal embedded-agent utilities.

* refactor: remove legacy provider compat paths

* docs: remove agent parity notes

* fix: skip provider wildcard metadata parsing

* refactor: share session extension sdk loading

* refactor: inline acpx proxy error formatter

* refactor: fold edit recovery into edit tool

* fix: accept extension batch separator

* test: align startup provider plugin expectations

* fix: restore provider-scoped release discovery

* test: align static asset packaging expectations

* fix: run static provider catalogs during scoped discovery

* fix: add provider entry catalogs for scoped live discovery

* fix: load lightweight provider catalog entries

* fix: refresh provider-scoped plugin metadata

* fix: keep provider catalog entries on release live path

* fix: keep static manifest models in release live checks

* fix: harden release model discovery

* fix: reduce OpenAI live cache probe reasoning

* fix: disable OpenAI cache probe reasoning

* ci: extend OpenAI gateway live timeout

* fix: extend live gateway model budget

* fix: stabilize release validation regressions

* fix: honor provider aliases in model rows

* fix: stabilize release validation lanes

* fix: stabilize release memory qa

* ci: stabilize release validation lanes

* ci: prefer ipv4 for live docker node calls

* fix: restore shared tool-call stream wrapper

* ci: remove legacy pi test shard alias

* fix: clean up embedded agent test drift

* fix: stabilize runtime alias status

* fix: clean up embedded agent ci drift

* fix: restore release ci invariants

* fix: clean up post-rebase runtime drift

* fix: restore release ci checks

* fix: restore release ci after rebase

* fix: remove stale pi runtime path

* test: align compaction runtime expectations

* test: update plugin prerelease expectations

* fix: handle claude live tool approvals

* fix: stabilize release validation gates

* fix: finish agent runtime import

* test: finish post-rebase agent runtime mocks

* fix: keep codex compaction native

* fix: stabilize codex app-server hook tests

* test: isolate codex diagnostic active run

* test: remove codex diagnostic completion race

# Conflicts:
#	extensions/codex/src/app-server/run-attempt.test.ts

* ci: fix full release manifest performance run id

* refactor: narrow llm plugin sdk boundary

* chore: drop generated google boundary stamps

* fix: repair rebase fallout

* fix: clean up rebased runtime references

* fix: decode codex jwt payloads as base64url

* fix: preserve shipped pi runtime alias

* fix: add scoped sdk virtual modules

* fix: decode llm codex oauth jwt as base64url

* fix: avoid stale vertex adc negative cache

* fix: harden tool arg decoding and codeql path

* fix: keep vertex adc negative checks live

* refactor: consolidate codex jwt and edit helpers

* fix: await codex oauth node runtime imports

* fix: preserve sdk tool and notice contracts

* fix: preserve shipped compat config boundaries

* fix: align codex oauth callback host

* fix: terminate agent-core loop streams on failure

* fix: keep codex oauth callback alive during fallback

* ci: include session tools in critical codeql scans

* fix: keep Cloudflare Anthropic provider auth header

* docs: redirect legacy pi runtime pages

* fix: honor bundled web provider compat discovery

* fix: protect session output spill files

* fix: keep legacy agent dir env blocked

* fix: contain auto-discovered skill symlinks

* fix: harden agent core sdk proxy surfaces

* fix: restore approval reaction sdk compat

* fix: keep live docker runs bounded

* fix: keep codex oauth redirect host aligned

* fix: resolve post-rebase agent runtime drift

* fix: redact anthropic oauth parse failures

* fix: preserve responses strict tool shaping

* fix: repair agent runtime rebase cleanup

* docs: redirect retired parity pages

* fix: bound auto-discovered resources to roots

* fix: repair post-rebase agent test drift

* fix: preserve bundled provider allowlist migration

* fix: preserve manifest-owned provider aliases

* fix: declare photon image dependency

* fix: keep provider headers out of proxy body

* fix: preserve shipped env aliases

* fix: refresh control ui i18n generated state

* fix: quote read fallback paths

* fix: preview edits through configured backend

* test: satisfy core test typecheck

* fix: preserve ZAI usage auth fallback

* test: repair codex diagnostic test

* fix: repair agent runtime rebase drift

* test: finish embedded runner import rename

* fix: repair agent runtime rebase integrations

* test: align compaction oauth fallback expectations

* fix: allow sdk-auth session models

* fix: update doctor tool schema import

* fix: preserve bedrock plugin region

* fix: stream harmony-like prose immediately

* ci: include session runtime in codeql shards

* fix: repair latest rebase integrations

* fix: honor explicit codex websocket transport

* fix: keep openai-compatible credentials provider-scoped

* fix: refresh sdk api baseline after rebase

* fix: route cli runtime aliases through openclaw harness

* test: rename stale harness mock expectation

* test: rename embedded agent overflow calls

* test: clean embedded auth test wording

* test: use openclaw stream types in deepinfra cache test

* fix: refresh sdk api baseline on latest main

* fix: honor bundled discovery compat allowlists

* fix: refresh sdk api baseline after latest rebase

* fix: remove stale rebase imports

* test: rename stale model catalog mock

* test: mock renamed doctor runtime modules

* fix: map canonical kimi env auth

* fix: use internal model registry in bench script

* fix: migrate deepinfra provider catalog entry

* fix: enforce builtin tool suppression

* fix: route compaction auth and proxy payloads safely

* refactor: prune unused llm registry leftovers

* test: update codex hooks session import

* test: fix model picker ci coverage

* test: align model picker auth mock types
2026-05-27 19:24:04 +01:00

262 lines
7.7 KiB
JavaScript

#!/usr/bin/env node
import path from "node:path";
import {
listTrackedTestFilesForRoots,
resolveExtensionBatchPlan,
} from "./lib/extension-test-plan.mjs";
import { isDirectScriptRun, runVitestBatch } from "./lib/vitest-batch-runner.mjs";
const FS_MODULE_CACHE_PATH_ENV_KEY = "OPENCLAW_VITEST_FS_MODULE_CACHE_PATH";
const PARALLEL_ENV_KEY = "OPENCLAW_EXTENSION_BATCH_PARALLEL";
const ALLOW_NO_TESTS_FLAG = "--allow-no-tests";
const ALLOW_EMPTY_AFTER_EXCLUDE_FLAG = "--allow-empty-after-exclude";
function printUsage() {
console.error(
`Usage: pnpm test:extensions:batch <extension[,extension...]> [${ALLOW_NO_TESTS_FLAG}] [${ALLOW_EMPTY_AFTER_EXCLUDE_FLAG}] [vitest args...]`,
);
console.error(
` node scripts/test-extension-batch.mjs <extension[,extension...]> [${ALLOW_NO_TESTS_FLAG}] [${ALLOW_EMPTY_AFTER_EXCLUDE_FLAG}] [vitest args...]`,
);
}
export function parseExtensionIds(rawArgs) {
const normalizedArgs = rawArgs[0] === "--" ? rawArgs.slice(1) : rawArgs;
const separatorIndex = normalizedArgs.indexOf("--");
const args = separatorIndex >= 0 ? normalizedArgs.slice(0, separatorIndex) : [...normalizedArgs];
const separatorPassthroughArgs =
separatorIndex >= 0 ? normalizedArgs.slice(separatorIndex + 1) : [];
const extensionIds = [];
while (args[0] && !args[0].startsWith("-")) {
extensionIds.push(
...args
.shift()
.split(",")
.map((value) => value.trim())
.filter(Boolean),
);
}
return {
extensionIds,
passthroughArgs: separatorIndex >= 0 ? [...args, ...separatorPassthroughArgs] : args,
};
}
function parsePositiveInt(value) {
const parsed = Number.parseInt(value ?? "", 10);
return Number.isFinite(parsed) && parsed > 0 ? parsed : null;
}
export function resolveExtensionBatchParallelism(groupCount, env = process.env) {
const override = parsePositiveInt(env[PARALLEL_ENV_KEY]);
return Math.min(Math.max(1, override ?? 1), Math.max(1, groupCount));
}
function sanitizeCacheSegment(value) {
return (
value
.replace(/[^a-zA-Z0-9._-]+/gu, "-")
.replace(/^-+|-+$/gu, "")
.slice(0, 180) || "default"
);
}
function createGroupEnv({ baseEnv, group, groupIndex, useDedicatedCache }) {
if (!useDedicatedCache || baseEnv[FS_MODULE_CACHE_PATH_ENV_KEY]?.trim()) {
return baseEnv;
}
return {
...baseEnv,
[FS_MODULE_CACHE_PATH_ENV_KEY]: path.join(
process.cwd(),
"node_modules",
".experimental-vitest-cache",
"extension-batch",
sanitizeCacheSegment(`${groupIndex}-${group.config}`),
),
};
}
function orderPlanGroups(planGroups, parallelism) {
if (parallelism <= 1) {
return planGroups;
}
return [...planGroups].toSorted((left, right) => {
if (left.estimatedCost !== right.estimatedCost) {
return right.estimatedCost - left.estimatedCost;
}
if (left.testFileCount !== right.testFileCount) {
return right.testFileCount - left.testFileCount;
}
return left.config.localeCompare(right.config);
});
}
function normalizeRelativePath(inputPath) {
return path
.relative(process.cwd(), path.resolve(process.cwd(), inputPath))
.split(path.sep)
.join("/");
}
function isExactExcludePath(inputPath) {
return !/[*!?[\]{}]/u.test(inputPath);
}
export function parseExactVitestExcludePaths(vitestArgs) {
const excludePaths = new Set();
for (let index = 0; index < vitestArgs.length; index += 1) {
const arg = vitestArgs[index];
if (arg === "--exclude") {
const value = vitestArgs[index + 1];
if (value && isExactExcludePath(value)) {
excludePaths.add(normalizeRelativePath(value));
}
index += 1;
continue;
}
const prefix = "--exclude=";
if (arg.startsWith(prefix)) {
const value = arg.slice(prefix.length);
if (value && isExactExcludePath(value)) {
excludePaths.add(normalizeRelativePath(value));
}
}
}
return excludePaths;
}
function resolveGroupTargets(group, exactExcludePaths) {
if (exactExcludePaths.size === 0) {
return group.roots;
}
const testFiles = listTrackedTestFilesForRoots(group.roots);
if (!testFiles) {
return group.roots;
}
return testFiles.filter((file) => !exactExcludePaths.has(file));
}
async function runPlanGroup(group, params) {
const targets = resolveGroupTargets(group, params.exactExcludePaths);
if (targets.length === 0) {
console.error(`[test-extension-batch] ${group.config}: no test files remain after excludes`);
return params.allowEmptyAfterExclude ? 0 : 1;
}
console.log(
`[test-extension-batch] ${group.config}: ${group.extensionIds.join(", ")} (${targets.length} targets)`,
);
return await params.runGroup({
args: params.vitestArgs,
config: group.config,
env: createGroupEnv({
baseEnv: params.env,
group,
groupIndex: params.groupIndex,
useDedicatedCache: params.useDedicatedCache,
}),
targets,
});
}
export async function runExtensionBatchPlan(batchPlan, params = {}) {
const env = params.env ?? process.env;
const vitestArgs = params.vitestArgs ?? [];
const exactExcludePaths = parseExactVitestExcludePaths(vitestArgs);
const runGroup = params.runGroup ?? runVitestBatch;
const parallelism = resolveExtensionBatchParallelism(batchPlan.planGroups.length, env);
const orderedGroups = orderPlanGroups(batchPlan.planGroups, parallelism);
const useDedicatedCache = parallelism > 1;
const allowEmptyAfterExclude = params.allowEmptyAfterExclude ?? false;
if (parallelism > 1) {
console.log(`[test-extension-batch] Running up to ${parallelism} config groups in parallel`);
}
let nextGroupIndex = 0;
let exitCode = 0;
async function worker() {
while (exitCode === 0) {
const groupIndex = nextGroupIndex;
nextGroupIndex += 1;
const group = orderedGroups[groupIndex];
if (!group) {
return;
}
const groupExitCode = await runPlanGroup(group, {
env,
groupIndex,
runGroup,
exactExcludePaths,
allowEmptyAfterExclude,
useDedicatedCache,
vitestArgs,
});
if (groupExitCode !== 0) {
exitCode = groupExitCode;
return;
}
}
}
await Promise.all(Array.from({ length: parallelism }, () => worker()));
return exitCode;
}
async function run() {
const rawArgs = process.argv.slice(2);
if (rawArgs.includes("--help") || rawArgs.includes("-h")) {
printUsage();
return;
}
const allowNoTests = rawArgs.includes(ALLOW_NO_TESTS_FLAG);
const allowEmptyAfterExclude = rawArgs.includes(ALLOW_EMPTY_AFTER_EXCLUDE_FLAG);
const controlArgs = new Set([ALLOW_NO_TESTS_FLAG, ALLOW_EMPTY_AFTER_EXCLUDE_FLAG]);
const args = rawArgs.filter((arg) => !controlArgs.has(arg));
const { extensionIds, passthroughArgs: vitestArgs } = parseExtensionIds(args);
if (extensionIds.length === 0) {
printUsage();
process.exit(1);
}
const batchPlan = resolveExtensionBatchPlan({ cwd: process.cwd(), extensionIds });
if (batchPlan.noTestExtensionIds.length > 0 && !allowNoTests) {
console.error(
`[test-extension-batch] No tests found for requested extension(s): ${batchPlan.noTestExtensionIds.join(", ")}`,
);
process.exit(1);
}
if (!batchPlan.hasTests) {
console.error("[test-extension-batch] No tests found for the requested extensions.");
if (!allowNoTests) {
process.exit(1);
}
return;
}
console.log(
`[test-extension-batch] Running ${batchPlan.testFileCount} test files across ${batchPlan.extensionCount} extensions`,
);
const exitCode = await runExtensionBatchPlan(batchPlan, {
allowEmptyAfterExclude,
env: process.env,
vitestArgs,
});
if (exitCode !== 0) {
process.exit(exitCode);
}
}
if (isDirectScriptRun(import.meta.url)) {
await run();
}