Files
openclaw/extensions/xai/index.test.ts
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

280 lines
9.4 KiB
TypeScript

import type { OpenClawPluginApi } from "openclaw/plugin-sdk/plugin-entry";
import { createTestPluginApi } from "openclaw/plugin-sdk/plugin-test-api";
import {
registerProviderPlugin,
registerSingleProviderPlugin,
} from "openclaw/plugin-sdk/plugin-test-runtime";
import { describe, expect, it } from "vitest";
import plugin from "./index.js";
import setupPlugin from "./setup-api.js";
import {
createXaiPayloadCaptureStream,
expectXaiFastToolStreamShaping,
runXaiGrok4ResponseStream,
} from "./test-helpers.js";
function createProviderModel(overrides: {
id: string;
api?: string;
baseUrl?: string;
provider?: string;
}) {
return {
id: overrides.id,
name: overrides.id,
api: overrides.api ?? "openai-completions",
provider: overrides.provider ?? "xai",
baseUrl: overrides.baseUrl ?? "https://api.x.ai/v1",
reasoning: true,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 200_000,
maxTokens: 8_192,
};
}
type XaiAutoEnableProbe = Parameters<OpenClawPluginApi["registerAutoEnableProbe"]>[0];
function registerXaiAutoEnableProbe(): XaiAutoEnableProbe {
const probes: XaiAutoEnableProbe[] = [];
setupPlugin.register(
createTestPluginApi({
registerAutoEnableProbe(probe) {
probes.push(probe);
},
}),
);
const probe = probes[0];
if (!probe) {
throw new Error("expected xAI setup plugin to register an auto-enable probe");
}
return probe;
}
function requireEntry<T extends { id?: string }>(entries: T[], id: string): T {
const entry = entries.find((candidate) => candidate.id === id);
if (!entry) {
throw new Error(`Expected entry ${id}`);
}
return entry;
}
describe("xai provider plugin", () => {
it("exposes OAuth and device-code auth choices", async () => {
const provider = await registerSingleProviderPlugin(plugin);
expect(provider.auth?.map((method) => method.id)).toEqual(["api-key", "oauth", "device-code"]);
const deviceCode = provider.auth?.find((method) => method.id === "device-code");
expect(deviceCode?.kind).toBe("device_code");
expect(deviceCode?.wizard?.choiceId).toBe("xai-device-code");
});
it("classifies Grok usage and spending limit errors", async () => {
const provider = await registerSingleProviderPlugin(plugin);
expect(
provider.classifyFailoverReason?.({
errorMessage:
'403 {"code":"The caller does not have permission to execute the specified operation","error":"Your team team-redacted has either used all available credits or reached its monthly spending limit. To continue making API requests, please purchase more credits or raise your spending limit."}',
}),
).toBe("billing");
expect(
provider.classifyFailoverReason?.({
errorMessage:
'429 {"code":"Some resource has been exhausted","error":"Your team team-redacted has either used all available credits or reached its monthly spending limit. To continue making API requests, please purchase more credits or raise your spending limit."}',
}),
).toBe("billing");
expect(
provider.classifyFailoverReason?.({
errorMessage:
'429 {"code":"Some resource has been exhausted","error":"Rate limit exceeded"}',
}),
).toBe("rate_limit");
expect(
provider.classifyFailoverReason?.({
errorMessage:
'400 {"code":"Client specified an invalid argument","error":"Incorrect API key provided: xa***en. You can obtain an API key from https://console.x.ai."}',
}),
).toBeUndefined();
});
it("registers xAI speech providers for batch and streaming STT", async () => {
const { mediaProviders, realtimeTranscriptionProviders } = await registerProviderPlugin({
plugin,
id: "xai",
name: "xAI Provider",
});
const mediaProvider = requireEntry(mediaProviders, "xai");
expect(mediaProvider.capabilities).toEqual(["audio"]);
expect(mediaProvider.defaultModels).toEqual({ audio: "grok-stt" });
const realtimeProvider = requireEntry(realtimeTranscriptionProviders, "xai");
expect(realtimeProvider.label).toBe("xAI Realtime Transcription");
expect(realtimeProvider.aliases).toContain("xai-realtime");
});
it("declares setup auto-enable reasons for plugin-owned tool config", () => {
const probe = registerXaiAutoEnableProbe();
expect(
probe({
config: { plugins: { entries: { xai: { config: { xSearch: { enabled: true } } } } } },
env: {},
}),
).toBe("xai tool configured");
expect(
probe({
config: {
plugins: { entries: { xai: { config: { codeExecution: { enabled: true } } } } },
},
env: {},
}),
).toBe("xai tool configured");
expect(probe({ config: {}, env: {} })).toBeNull();
});
it("owns replay policy for xAI OpenAI-compatible transports", async () => {
const provider = await registerSingleProviderPlugin(plugin);
const completionsPolicy = provider.buildReplayPolicy?.({
provider: "xai",
modelApi: "openai-completions",
modelId: "grok-3",
} as never);
expect(completionsPolicy?.sanitizeToolCallIds).toBe(true);
expect(completionsPolicy?.toolCallIdMode).toBe("strict");
expect(completionsPolicy?.applyAssistantFirstOrderingFix).toBe(true);
expect(completionsPolicy?.validateGeminiTurns).toBe(true);
expect(completionsPolicy?.validateAnthropicTurns).toBe(true);
const responsesPolicy = provider.buildReplayPolicy?.({
provider: "xai",
modelApi: "openai-responses",
modelId: "grok-4-fast",
} as never);
expect(responsesPolicy?.sanitizeToolCallIds).toBe(true);
expect(responsesPolicy?.toolCallIdMode).toBe("strict");
expect(responsesPolicy?.applyAssistantFirstOrderingFix).toBe(false);
expect(responsesPolicy?.validateGeminiTurns).toBe(false);
expect(responsesPolicy?.validateAnthropicTurns).toBe(false);
});
it("wires provider stream shaping for fast mode and tool-stream defaults", async () => {
const provider = await registerSingleProviderPlugin(plugin);
const capture = createXaiPayloadCaptureStream();
const wrapped = provider.wrapStreamFn?.({
provider: "xai",
modelId: "grok-4",
extraParams: { fastMode: true },
streamFn: capture.streamFn,
} as never);
runXaiGrok4ResponseStream(wrapped);
expectXaiFastToolStreamShaping(capture);
});
it("defaults tool_stream extra params but preserves explicit values", async () => {
const provider = await registerSingleProviderPlugin(plugin);
expect(
provider.prepareExtraParams?.({
provider: "xai",
modelId: "grok-4",
extraParams: { fastMode: true },
} as never),
).toEqual({
fastMode: true,
tool_stream: true,
});
const explicit = { fastMode: true, tool_stream: false };
expect(
provider.prepareExtraParams?.({
provider: "xai",
modelId: "grok-4",
extraParams: explicit,
} as never),
).toBe(explicit);
});
it("owns forward-compatible Grok model resolution", async () => {
const provider = await registerSingleProviderPlugin(plugin);
const resolved = provider.resolveDynamicModel?.({
provider: "xai",
modelId: "grok-4.3",
modelRegistry: { find: () => null } as never,
providerConfig: {
api: "openai-completions",
baseUrl: "https://api.x.ai/v1",
},
} as never);
expect(resolved?.id).toBe("grok-4.3");
expect(resolved?.provider).toBe("xai");
expect(resolved?.api).toBe("openai-completions");
expect(resolved?.baseUrl).toBe("https://api.x.ai/v1");
expect(resolved?.reasoning).toBe(true);
expect(resolved?.input).toEqual(["text", "image"]);
expect(resolved?.contextWindow).toBe(1_000_000);
});
it("marks modern Grok refs without accepting multi-agent ids", async () => {
const provider = await registerSingleProviderPlugin(plugin);
expect(
provider.isModernModelRef?.({
provider: "xai",
modelId: "grok-4.3",
} as never),
).toBe(true);
expect(
provider.isModernModelRef?.({
provider: "xai",
modelId: "grok-4.20-multi-agent-experimental-beta-0304",
} as never),
).toBe(false);
});
it("owns xai compat flags for direct and downstream routed models", async () => {
const provider = await registerSingleProviderPlugin(plugin);
const normalized = provider.normalizeResolvedModel?.({
provider: "xai",
modelId: "grok-4.3",
model: createProviderModel({ id: "grok-4.3" }),
} as never);
expect(normalized?.thinkingLevelMap).toEqual({
off: null,
minimal: "low",
low: "low",
medium: "medium",
high: "high",
xhigh: "high",
});
const olderReasoningModel = provider.normalizeResolvedModel?.({
provider: "xai",
modelId: "grok-4-1-fast",
model: createProviderModel({ id: "grok-4-1-fast" }),
} as never);
expect(olderReasoningModel?.thinkingLevelMap).toEqual({
off: null,
minimal: null,
low: null,
medium: null,
high: null,
xhigh: null,
});
const normalizedCompat = normalized?.compat as
| {
toolSchemaProfile?: string;
nativeWebSearchTool?: boolean;
toolCallArgumentsEncoding?: string;
}
| undefined;
expect(normalizedCompat?.toolSchemaProfile).toBe("xai");
expect(normalizedCompat?.nativeWebSearchTool).toBe(true);
expect(normalizedCompat?.toolCallArgumentsEncoding).toBe("html-entities");
});
});