Files
openclaw/extensions/xai/stream.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

493 lines
14 KiB
TypeScript

import type { StreamFn } from "openclaw/plugin-sdk/agent-core";
import { streamSimple, type Api, type Context, type Model } from "openclaw/plugin-sdk/llm";
import { describe, expect, it } from "vitest";
import { applyXaiRuntimeModelCompat } from "./runtime-model-compat.js";
import {
createXaiFastModeWrapper,
createXaiToolPayloadCompatibilityWrapper,
wrapXaiProviderStream,
} from "./stream.js";
import {
createXaiPayloadCaptureStream,
expectXaiFastToolStreamShaping,
runXaiGrok4ResponseStream,
} from "./test-helpers.js";
type XaiStreamApi = Extract<Api, "openai-completions" | "openai-responses">;
type StreamEvent = Record<string, unknown> & { type?: string };
async function collectEvents(stream: ReturnType<StreamFn>): Promise<StreamEvent[]> {
const events: StreamEvent[] = [];
for await (const event of stream as AsyncIterable<StreamEvent>) {
events.push(event);
}
return events;
}
function buildEventStreamFn(events: unknown[]): StreamFn {
return (() =>
({
result: async () => {
const done = events.find((event) => {
const record = event && typeof event === "object" ? (event as { type?: unknown }) : {};
return record.type === "done";
}) as { message?: unknown } | undefined;
return (done?.message ?? { role: "assistant", content: [] }) as never;
},
async *[Symbol.asyncIterator]() {
for (const event of events) {
yield event as never;
}
},
}) as unknown as ReturnType<StreamFn>) as StreamFn;
}
function captureWrappedModelId(params: {
modelId: string;
fastMode: boolean;
api?: XaiStreamApi;
}): string {
let capturedModelId = "";
const baseStreamFn: StreamFn = (model) => {
capturedModelId = model.id;
return {} as ReturnType<StreamFn>;
};
const wrapped = createXaiFastModeWrapper(baseStreamFn, params.fastMode);
void wrapped(
{
api: params.api ?? "openai-responses",
provider: "xai",
id: params.modelId,
} as Model<Extract<Api, "openai-completions" | "openai-responses">>,
{ messages: [] } as Context,
{},
);
return capturedModelId;
}
function runXaiToolPayloadWrapper(params: {
payload: Record<string, unknown>;
api?: XaiStreamApi;
modelId?: string;
input?: string[];
}) {
const baseStreamFn: StreamFn = (_model, _context, options) => {
options?.onPayload?.(params.payload, {} as Model<XaiStreamApi>);
return {} as ReturnType<StreamFn>;
};
const wrapped = createXaiToolPayloadCompatibilityWrapper(baseStreamFn);
const api = params.api ?? "openai-responses";
void wrapped(
{
api,
provider: "xai",
id:
params.modelId ??
(api === "openai-completions" ? "grok-4-1-fast-reasoning" : "grok-4-fast"),
reasoning: params.modelId ? !params.modelId.includes("non-reasoning") : true,
...(params.input ? { input: params.input } : {}),
} as Model<XaiStreamApi>,
{ messages: [] } as Context,
{},
);
}
async function captureXaiResponsesPayloadWithThinking(): Promise<Record<string, unknown>> {
const model = applyXaiRuntimeModelCompat({
api: "openai-responses",
provider: "xai",
id: "grok-4.3",
baseUrl: "https://api.x.ai/v1",
reasoning: true,
input: ["text", "image"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 1_000_000,
maxTokens: 64_000,
} as Model<"openai-responses">);
const payloadPromise = new Promise<Record<string, unknown>>((resolve, reject) => {
const timeout = setTimeout(
() => reject(new Error("provider payload callback was not invoked")),
1_000,
);
const stream = streamSimple(
model,
{ messages: [{ role: "user", content: "hello", timestamp: 0 }] },
{
apiKey: "test-api-key",
cacheRetention: "none",
reasoning: "low",
onPayload: (payload) => {
clearTimeout(timeout);
resolve(structuredClone(payload as Record<string, unknown>));
throw new Error("stop after payload capture");
},
},
);
void stream.result();
});
return await payloadPromise;
}
describe("xai stream wrappers", () => {
it("rewrites supported Grok models to fast variants when fast mode is enabled", () => {
expect(captureWrappedModelId({ modelId: "grok-3", fastMode: true })).toBe("grok-3-fast");
expect(
captureWrappedModelId({
modelId: "grok-3",
fastMode: true,
api: "openai-completions",
}),
).toBe("grok-3-fast");
expect(captureWrappedModelId({ modelId: "grok-4", fastMode: true })).toBe("grok-4-fast");
expect(
captureWrappedModelId({
modelId: "grok-3",
fastMode: true,
api: "openai-responses",
}),
).toBe("grok-3-fast");
});
it("leaves unsupported or disabled models unchanged", () => {
expect(captureWrappedModelId({ modelId: "grok-3-fast", fastMode: true })).toBe("grok-3-fast");
expect(captureWrappedModelId({ modelId: "grok-3", fastMode: false })).toBe("grok-3");
});
it("composes the xai provider stream chain from extra params", () => {
const capture = createXaiPayloadCaptureStream();
const wrapped = wrapXaiProviderStream({
streamFn: capture.streamFn,
extraParams: { fastMode: true },
} as never);
runXaiGrok4ResponseStream(wrapped);
expectXaiFastToolStreamShaping(capture);
});
it("promotes standalone Grok-style tool text to a structured tool call", async () => {
const rawToolText = '[tool:read] {"path":"/app/skills/meme-maker/SKILL.md"}';
const baseStream = buildEventStreamFn([
{ type: "start", partial: { content: [] } },
{ type: "text_start", contentIndex: 0, partial: { content: [{ type: "text", text: "" }] } },
{ type: "text_delta", contentIndex: 0, delta: rawToolText },
{ type: "text_end", contentIndex: 0, content: rawToolText },
{
type: "done",
reason: "stop",
message: {
role: "assistant",
content: [{ type: "text", text: rawToolText }],
stopReason: "stop",
},
},
]);
const wrapped = wrapXaiProviderStream({
streamFn: baseStream,
extraParams: { tool_stream: false },
} as never);
const events = await collectEvents(
wrapped!(
{
api: "openai-responses",
provider: "xai",
id: "grok-4.3",
} as Model<"openai-responses">,
{
messages: [],
tools: [{ name: "read", description: "Read", parameters: { type: "object" } }],
} as unknown as Context,
{},
),
);
expect(events.map((event) => event.type)).toEqual([
"start",
"toolcall_start",
"toolcall_delta",
"done",
]);
const done = events.find((event) => event.type === "done") as {
message?: { content?: Array<Record<string, unknown>>; stopReason?: string };
reason?: string;
};
expect(done.reason).toBe("toolUse");
expect(done.message?.stopReason).toBe("toolUse");
expect(done.message?.content?.[0]).toMatchObject({
type: "toolCall",
name: "read",
arguments: { path: "/app/skills/meme-maker/SKILL.md" },
});
});
it("strips unsupported strict and reasoning controls from tool payloads", () => {
const payload = {
reasoning: "high",
reasoningEffort: "high",
reasoning_effort: "high",
tools: [
{
type: "function",
function: {
name: "write",
parameters: { type: "object", properties: {} },
strict: true,
},
},
],
};
runXaiToolPayloadWrapper({
payload,
api: "openai-completions",
modelId: "grok-4-fast-non-reasoning",
});
expect(payload).not.toHaveProperty("reasoning");
expect(payload).not.toHaveProperty("reasoningEffort");
expect(payload).not.toHaveProperty("reasoning_effort");
expect(payload.tools[0]?.function).not.toHaveProperty("strict");
});
it("strips unsupported reasoning controls from non-reasoning xai payloads", () => {
const payload: Record<string, unknown> = {
reasoning: { effort: "high" },
reasoningEffort: "high",
reasoning_effort: "high",
};
runXaiToolPayloadWrapper({ payload, modelId: "grok-4-fast-non-reasoning" });
expect(payload).not.toHaveProperty("reasoning");
expect(payload).not.toHaveProperty("reasoningEffort");
expect(payload).not.toHaveProperty("reasoning_effort");
});
it("passes reasoning controls through for reasoning-capable xai payloads", () => {
const payload: Record<string, unknown> = {
reasoning: { effort: "high" },
reasoningEffort: "high",
reasoning_effort: "high",
};
runXaiToolPayloadWrapper({ payload, modelId: "grok-4.3" });
expect(payload.reasoning).toEqual({ effort: "high" });
expect(payload.reasoningEffort).toBe("high");
expect(payload.reasoning_effort).toBe("high");
});
it("strips reasoning controls when compat disables reasoning effort", () => {
const payload: Record<string, unknown> = {
reasoning: { effort: "high" },
reasoningEffort: "high",
reasoning_effort: "high",
};
const baseStreamFn: StreamFn = (model, _context, options) => {
options?.onPayload?.(payload, model);
return {} as ReturnType<StreamFn>;
};
const wrapped = createXaiToolPayloadCompatibilityWrapper(baseStreamFn);
void wrapped(
{
api: "openai-responses",
provider: "xai",
id: "grok-4.20-beta-latest-reasoning",
reasoning: true,
compat: { supportsReasoningEffort: false },
} as unknown as Model<"openai-responses">,
{ messages: [] } as Context,
{},
);
expect(payload).not.toHaveProperty("reasoning");
expect(payload).not.toHaveProperty("reasoningEffort");
expect(payload).not.toHaveProperty("reasoning_effort");
});
it("keeps native xAI Responses thinking efforts before the shared runtime dispatches payloads", async () => {
const payload = await captureXaiResponsesPayloadWithThinking();
expect(payload.reasoning).toEqual({ effort: "low", summary: "auto" });
expect(payload.include).toEqual(["reasoning.encrypted_content"]);
});
it("moves image-bearing tool results out of function_call_output payloads", () => {
const payload: Record<string, unknown> = {
input: [
{
type: "function_call_output",
call_id: "call_1",
output: [
{ type: "input_text", text: "Read image" },
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QUJDRA==",
},
],
},
],
};
runXaiToolPayloadWrapper({ payload, input: ["text", "image"] });
expect(payload.input).toEqual([
{
type: "function_call_output",
call_id: "call_1",
output: "Read image",
},
{
type: "message",
role: "user",
content: [
{ type: "input_text", text: "Attached image(s) from tool result:" },
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QUJDRA==",
},
],
},
]);
});
it("replays source-based input_image parts from tool results", () => {
const payload: Record<string, unknown> = {
input: [
{
type: "function_call_output",
call_id: "call_1",
output: [
{ type: "input_text", text: "Read image" },
{
type: "input_image",
source: {
type: "base64",
media_type: "image/png",
data: "QUJDRA==",
},
},
],
},
],
};
runXaiToolPayloadWrapper({ payload, input: ["text", "image"] });
expect(payload.input).toEqual([
{
type: "function_call_output",
call_id: "call_1",
output: "Read image",
},
{
type: "message",
role: "user",
content: [
{ type: "input_text", text: "Attached image(s) from tool result:" },
{
type: "input_image",
source: {
type: "base64",
media_type: "image/png",
data: "QUJDRA==",
},
},
],
},
]);
});
it("keeps multiple tool outputs contiguous before replaying collected images", () => {
const payload: Record<string, unknown> = {
input: [
{
type: "function_call_output",
call_id: "call_1",
output: [
{ type: "input_text", text: "first" },
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QUFBQQ==",
},
],
},
{
type: "function_call_output",
call_id: "call_2",
output: [
{ type: "input_text", text: "second" },
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QkJCQg==",
},
],
},
],
};
runXaiToolPayloadWrapper({ payload, input: ["text", "image"] });
expect(payload.input).toEqual([
{
type: "function_call_output",
call_id: "call_1",
output: "first",
},
{
type: "function_call_output",
call_id: "call_2",
output: "second",
},
{
type: "message",
role: "user",
content: [
{ type: "input_text", text: "Attached image(s) from tool result:" },
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QUFBQQ==",
},
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QkJCQg==",
},
],
},
]);
});
it("drops image blocks and uses fallback text for models without image input", () => {
const payload: Record<string, unknown> = {
input: [
{
type: "function_call_output",
call_id: "call_1",
output: [
{
type: "input_image",
detail: "auto",
image_url: "data:image/png;base64,QUJDRA==",
},
],
},
],
};
runXaiToolPayloadWrapper({ payload, input: ["text"] });
expect(payload.input).toEqual([
{
type: "function_call_output",
call_id: "call_1",
output: "(see attached image)",
},
]);
});
});