Files
openclaw/src/plugin-sdk/provider-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

388 lines
14 KiB
TypeScript

import type { StreamFn } from "openclaw/plugin-sdk/agent-core";
import { describe, expect, it } from "vitest";
import { createAssistantMessageEventStream } from "../llm/utils/event-stream.js";
import { VERSION } from "../version.js";
import {
composeProviderStreamWrappers as composeProviderStreamWrappersShared,
createMoonshotThinkingWrapper as createMoonshotThinkingWrapperShared,
createPlainTextToolCallCompatWrapper as createPlainTextToolCallCompatWrapperShared,
createToolStreamWrapper as createToolStreamWrapperShared,
} from "./provider-stream-shared.js";
import {
buildProviderStreamFamilyHooks,
composeProviderStreamWrappers,
createMoonshotThinkingWrapper,
createPlainTextToolCallCompatWrapper,
createToolStreamWrapper,
GOOGLE_THINKING_STREAM_HOOKS,
KILOCODE_THINKING_STREAM_HOOKS,
MINIMAX_FAST_MODE_STREAM_HOOKS,
MOONSHOT_THINKING_STREAM_HOOKS,
OPENAI_RESPONSES_STREAM_HOOKS,
OPENROUTER_THINKING_STREAM_HOOKS,
TOOL_STREAM_DEFAULT_ON_HOOKS,
} from "./provider-stream.js";
function requireWrapStreamFn(
wrapStreamFn: ReturnType<typeof buildProviderStreamFamilyHooks>["wrapStreamFn"],
) {
expect(wrapStreamFn).toBeTypeOf("function");
if (!wrapStreamFn) {
throw new Error("expected wrapStreamFn to be defined");
}
return wrapStreamFn;
}
function requireStreamFn(streamFn: StreamFn | null | undefined) {
expect(streamFn).toBeTypeOf("function");
if (!streamFn) {
throw new Error("expected wrapped streamFn to be defined");
}
return streamFn;
}
function requireRecord(value: unknown, label: string): Record<string, unknown> {
if (!value || typeof value !== "object" || Array.isArray(value)) {
throw new Error(`expected ${label} to be an object`);
}
return value as Record<string, unknown>;
}
function requirePayload(payload: Record<string, unknown> | undefined): Record<string, unknown> {
if (!payload) {
throw new Error("expected captured payload");
}
return payload;
}
function expectDefaultThinkingBudget(payload: Record<string, unknown>) {
const config = requireRecord(payload.config, "payload.config");
const thinkingConfig = requireRecord(config.thinkingConfig, "payload.config.thinkingConfig");
expect(thinkingConfig.thinkingBudget).toBe(-1);
}
describe("composeProviderStreamWrappers", () => {
it("re-exports the shared wrapper composer", () => {
expect(composeProviderStreamWrappers).toBe(composeProviderStreamWrappersShared);
});
it("re-exports shared helper wrappers", () => {
expect(createMoonshotThinkingWrapper).toBe(createMoonshotThinkingWrapperShared);
expect(createPlainTextToolCallCompatWrapper).toBe(createPlainTextToolCallCompatWrapperShared);
expect(createToolStreamWrapper).toBe(createToolStreamWrapperShared);
});
it("applies wrappers left to right", () => {
const order: string[] = [];
const baseStreamFn: StreamFn = (_model, _context, _options) => {
order.push("base");
return {} as never;
};
const wrap =
(label: string) =>
(streamFn: StreamFn | undefined): StreamFn =>
(model, context, options) => {
order.push(`${label}:before`);
const result = (streamFn ?? baseStreamFn)(model, context, options);
order.push(`${label}:after`);
return result;
};
const composed = requireStreamFn(
composeProviderStreamWrappers(baseStreamFn, wrap("a"), undefined, wrap("b")),
);
void composed({} as never, {} as never, {});
expect(order).toEqual(["b:before", "a:before", "base", "a:after", "b:after"]);
});
it("returns the original stream when no wrappers are provided", () => {
const baseStreamFn: StreamFn = () => ({}) as never;
expect(composeProviderStreamWrappers(baseStreamFn)).toBe(baseStreamFn);
});
});
describe("buildProviderStreamFamilyHooks", () => {
it("covers the stream family matrix", async () => {
let capturedPayload: Record<string, unknown> | undefined;
let capturedModelId: string | undefined;
let capturedHeaders: Record<string, string> | undefined;
let payloadSeed: Record<string, unknown> | undefined;
const baseStreamFn: StreamFn = (model, _context, options) => {
capturedModelId = model.id;
const payload = {
model: model.id,
config: { thinkingConfig: { thinkingBudget: -1 } },
...payloadSeed,
} as Record<string, unknown>;
payloadSeed = undefined;
options?.onPayload?.(payload as never, model as never);
capturedPayload = payload;
capturedHeaders = options?.headers;
return {} as never;
};
const googleHooks = GOOGLE_THINKING_STREAM_HOOKS;
const googleStream = requireStreamFn(
requireWrapStreamFn(googleHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "high",
} as never),
);
await googleStream(
{ api: "google-generative-ai", id: "gemini-3.1-pro-preview" } as never,
{} as never,
{},
);
const googlePayload = requirePayload(capturedPayload);
const googleConfig = requireRecord(googlePayload.config, "google payload config");
const googleThinkingConfig = requireRecord(
googleConfig.thinkingConfig,
"google thinking config",
);
expect(googleThinkingConfig.thinkingLevel).toBe("HIGH");
expect(googleThinkingConfig).not.toHaveProperty("thinkingBudget");
const minimaxHooks = MINIMAX_FAST_MODE_STREAM_HOOKS;
const minimaxStream = requireStreamFn(
requireWrapStreamFn(minimaxHooks.wrapStreamFn)({
streamFn: baseStreamFn,
extraParams: { fastMode: true },
} as never),
);
await minimaxStream(
{
api: "anthropic-messages",
provider: "minimax",
id: "MiniMax-M2.7",
} as never,
{} as never,
{},
);
expect(capturedModelId).toBe("MiniMax-M2.7-highspeed");
const kilocodeHooks = KILOCODE_THINKING_STREAM_HOOKS;
void requireStreamFn(
requireWrapStreamFn(kilocodeHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "high",
modelId: "openai/gpt-5.4",
} as never),
)({ provider: "kilocode", id: "openai/gpt-5.4" } as never, {} as never, {});
const kilocodeOpenAiPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(kilocodeOpenAiPayload);
expect(requireRecord(kilocodeOpenAiPayload.reasoning, "kilocode reasoning").effort).toBe(
"high",
);
void requireStreamFn(
requireWrapStreamFn(kilocodeHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "high",
modelId: "kilo/auto",
} as never),
)({ provider: "kilocode", id: "kilo/auto" } as never, {} as never, {});
const kilocodeAutoPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(kilocodeAutoPayload);
expect(kilocodeAutoPayload).not.toHaveProperty("reasoning");
const moonshotHooks = MOONSHOT_THINKING_STREAM_HOOKS;
const moonshotStream = requireStreamFn(
requireWrapStreamFn(moonshotHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "off",
} as never),
);
await moonshotStream({ api: "openai-completions", id: "kimi-k2.5" } as never, {} as never, {});
const moonshotDisabledPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(moonshotDisabledPayload);
expect(requireRecord(moonshotDisabledPayload.thinking, "moonshot thinking").type).toBe(
"disabled",
);
const moonshotKeepStream = requireStreamFn(
requireWrapStreamFn(moonshotHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "low",
extraParams: { thinking: { type: "enabled", keep: "all" } },
} as never),
);
await moonshotKeepStream(
{ api: "openai-completions", id: "kimi-k2.6" } as never,
{} as never,
{},
);
const moonshotKeepPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(moonshotKeepPayload);
const moonshotKeepThinking = requireRecord(
moonshotKeepPayload.thinking,
"moonshot keep thinking",
);
expect(moonshotKeepThinking.type).toBe("enabled");
expect(moonshotKeepThinking.keep).toBe("all");
await moonshotKeepStream(
{ api: "openai-completions", id: "kimi-k2.5" } as never,
{} as never,
{},
);
const moonshotStrippedPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(moonshotStrippedPayload);
const moonshotStrippedThinking = requireRecord(
moonshotStrippedPayload.thinking,
"moonshot stripped thinking",
);
expect(moonshotStrippedThinking.type).toBe("enabled");
expect(moonshotStrippedThinking).not.toHaveProperty("keep");
payloadSeed = { tool_choice: { type: "tool", name: "read" } };
await moonshotKeepStream(
{ api: "openai-completions", id: "kimi-k2.6" } as never,
{} as never,
{},
);
const moonshotToolChoicePayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(moonshotToolChoicePayload);
expect(requireRecord(moonshotToolChoicePayload.tool_choice, "tool choice")).toEqual({
type: "tool",
name: "read",
});
const moonshotToolChoiceThinking = requireRecord(
moonshotToolChoicePayload.thinking,
"moonshot tool-choice thinking",
);
expect(moonshotToolChoiceThinking.type).toBe("disabled");
expect(moonshotToolChoiceThinking).not.toHaveProperty("keep");
const openAiHooks = OPENAI_RESPONSES_STREAM_HOOKS;
void requireStreamFn(
requireWrapStreamFn(openAiHooks.wrapStreamFn)({
streamFn: baseStreamFn,
extraParams: { serviceTier: "flex" },
config: {},
agentDir: "/tmp/provider-stream-test",
} as never),
)(
{
api: "openai-responses",
provider: "openai",
baseUrl: "https://api.openai.com/v1",
id: "gpt-5.4",
} as never,
{} as never,
{},
);
const openAiPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(openAiPayload);
expect(openAiPayload.service_tier).toBe("flex");
expect(capturedHeaders).toEqual({
"User-Agent": `openclaw/${VERSION}`,
originator: "openclaw",
version: VERSION,
});
const openRouterHooks = OPENROUTER_THINKING_STREAM_HOOKS;
void requireStreamFn(
requireWrapStreamFn(openRouterHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "high",
modelId: "openai/gpt-5.4",
} as never),
)({ provider: "openrouter", id: "openai/gpt-5.4" } as never, {} as never, {});
const openRouterOpenAiPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(openRouterOpenAiPayload);
expect(requireRecord(openRouterOpenAiPayload.reasoning, "openrouter reasoning").effort).toBe(
"high",
);
void requireStreamFn(
requireWrapStreamFn(openRouterHooks.wrapStreamFn)({
streamFn: baseStreamFn,
thinkingLevel: "high",
modelId: "x-ai/grok-3",
} as never),
)({ provider: "openrouter", id: "x-ai/grok-3" } as never, {} as never, {});
const openRouterGrokPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(openRouterGrokPayload);
expect(openRouterGrokPayload).not.toHaveProperty("reasoning");
const toolStreamHooks = TOOL_STREAM_DEFAULT_ON_HOOKS;
const toolStreamDefault = requireStreamFn(
requireWrapStreamFn(toolStreamHooks.wrapStreamFn)({
streamFn: baseStreamFn,
extraParams: {},
} as never),
);
await toolStreamDefault({ id: "glm-4.7" } as never, {} as never, {});
const toolStreamDefaultPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(toolStreamDefaultPayload);
expect(toolStreamDefaultPayload.tool_stream).toBe(true);
const toolStreamDisabled = requireStreamFn(
requireWrapStreamFn(toolStreamHooks.wrapStreamFn)({
streamFn: baseStreamFn,
extraParams: { tool_stream: false },
} as never),
);
await toolStreamDisabled({ id: "glm-4.7" } as never, {} as never, {});
const toolStreamDisabledPayload = requirePayload(capturedPayload);
expectDefaultThinkingBudget(toolStreamDisabledPayload);
expect(toolStreamDisabledPayload).not.toHaveProperty("tool_stream");
});
it("exposes canonical stream hook constants for reused families", () => {
expect(GOOGLE_THINKING_STREAM_HOOKS.wrapStreamFn).toBeTypeOf("function");
expect(KILOCODE_THINKING_STREAM_HOOKS.wrapStreamFn).toBeTypeOf("function");
expect(MINIMAX_FAST_MODE_STREAM_HOOKS.wrapStreamFn).toBeTypeOf("function");
expect(MOONSHOT_THINKING_STREAM_HOOKS.wrapStreamFn).toBeTypeOf("function");
expect(OPENAI_RESPONSES_STREAM_HOOKS.wrapStreamFn).toBeTypeOf("function");
expect(OPENROUTER_THINKING_STREAM_HOOKS.wrapStreamFn).toBeTypeOf("function");
expect(TOOL_STREAM_DEFAULT_ON_HOOKS.wrapStreamFn).toBeTypeOf("function");
});
});
describe("createPlainTextToolCallCompatWrapper", () => {
it("streams normal prose that starts with a Harmony channel word", async () => {
let pushSourceEvent: ((event: never) => void) | undefined;
const baseStreamFn: StreamFn = () => {
const stream = createAssistantMessageEventStream();
pushSourceEvent = (event) => stream.push(event);
return stream;
};
const wrapped = requireStreamFn(createPlainTextToolCallCompatWrapper(baseStreamFn));
const output = wrapped(
{} as never,
{ tools: [{ name: "read" }] } as never,
{},
) as AsyncIterable<unknown>;
const iterator = output[Symbol.asyncIterator]();
const first = iterator.next();
pushSourceEvent?.({
type: "text_delta",
contentIndex: 0,
delta: "final answer starts here",
partial: { role: "assistant", content: "final answer starts here" },
} as never);
const firstResult = await Promise.race([
first,
new Promise<"timeout">((resolve) => setTimeout(() => resolve("timeout"), 20)),
]);
expect(firstResult).not.toBe("timeout");
expect(firstResult).toMatchObject({
done: false,
value: { type: "text_delta", delta: "final answer starts here" },
});
pushSourceEvent?.({
type: "done",
message: { role: "assistant", content: "final answer starts here" },
} as never);
await iterator.next();
});
});