mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-29 23:48:47 +00:00
* 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
324 lines
11 KiB
TypeScript
324 lines
11 KiB
TypeScript
import { createAssistantMessageEventStream, type Model } from "openclaw/plugin-sdk/llm";
|
|
import { beforeAll, describe, expect, it, vi } from "vitest";
|
|
import type { AnthropicVertexStreamDeps } from "./stream-runtime.js";
|
|
|
|
const SYSTEM_PROMPT_CACHE_BOUNDARY = "\n<!-- OPENCLAW_CACHE_BOUNDARY -->\n";
|
|
|
|
function createStreamDeps(): {
|
|
deps: AnthropicVertexStreamDeps;
|
|
streamAnthropicMock: ReturnType<typeof vi.fn>;
|
|
anthropicVertexCtorMock: ReturnType<typeof vi.fn>;
|
|
} {
|
|
const streamAnthropicMock = vi.fn(
|
|
(..._args: Parameters<AnthropicVertexStreamDeps["streamAnthropic"]>) =>
|
|
createAssistantMessageEventStream(),
|
|
);
|
|
const anthropicVertexCtorMock = vi.fn();
|
|
const MockAnthropicVertex = function MockAnthropicVertex(options: unknown) {
|
|
anthropicVertexCtorMock(options);
|
|
} as unknown as AnthropicVertexStreamDeps["AnthropicVertex"];
|
|
|
|
return {
|
|
deps: {
|
|
AnthropicVertex: MockAnthropicVertex,
|
|
streamAnthropic: streamAnthropicMock,
|
|
},
|
|
streamAnthropicMock,
|
|
anthropicVertexCtorMock,
|
|
};
|
|
}
|
|
|
|
let createAnthropicVertexStreamFn: typeof import("./stream-runtime.js").createAnthropicVertexStreamFn;
|
|
let createAnthropicVertexStreamFnForModel: typeof import("./stream-runtime.js").createAnthropicVertexStreamFnForModel;
|
|
|
|
function makeModel(params: { id: string; maxTokens?: number }): Model<"anthropic-messages"> {
|
|
return {
|
|
id: params.id,
|
|
api: "anthropic-messages",
|
|
provider: "anthropic-vertex",
|
|
...(params.maxTokens !== undefined ? { maxTokens: params.maxTokens } : {}),
|
|
} as Model<"anthropic-messages">;
|
|
}
|
|
|
|
const CACHE_BOUNDARY_PROMPT = `Stable prefix${SYSTEM_PROMPT_CACHE_BOUNDARY}Dynamic suffix`;
|
|
|
|
type PayloadHook = (payload: unknown, payloadModel: unknown) => Promise<unknown>;
|
|
|
|
function streamAnthropicCall(streamAnthropicMock: ReturnType<typeof vi.fn>): unknown[] {
|
|
const call = streamAnthropicMock.mock.calls[0];
|
|
if (!call) {
|
|
throw new Error("Expected streamAnthropic call");
|
|
}
|
|
return call;
|
|
}
|
|
|
|
function streamTransportOptions(
|
|
streamAnthropicMock: ReturnType<typeof vi.fn>,
|
|
): Record<string, unknown> {
|
|
const options = streamAnthropicCall(streamAnthropicMock)[2];
|
|
if (!options || typeof options !== "object") {
|
|
throw new Error("Expected streamAnthropic transport options");
|
|
}
|
|
return options as Record<string, unknown>;
|
|
}
|
|
|
|
function captureCacheBoundaryPayloadHook(
|
|
onPayload: PayloadHook,
|
|
deps: AnthropicVertexStreamDeps,
|
|
streamAnthropicMock: ReturnType<typeof vi.fn>,
|
|
) {
|
|
const streamFn = createAnthropicVertexStreamFn("vertex-project", "us-east5", undefined, deps);
|
|
const model = makeModel({ id: "claude-sonnet-4-6", maxTokens: 64000 });
|
|
|
|
void streamFn(
|
|
model,
|
|
{
|
|
systemPrompt: CACHE_BOUNDARY_PROMPT,
|
|
messages: [{ role: "user", content: "Hello" }],
|
|
} as never,
|
|
{
|
|
cacheRetention: "short",
|
|
onPayload,
|
|
} as never,
|
|
);
|
|
|
|
const transportOptions = streamTransportOptions(streamAnthropicMock);
|
|
|
|
return { model, onPayload: transportOptions.onPayload as PayloadHook | undefined };
|
|
}
|
|
|
|
function buildExpectedCacheBoundaryPayload(messageText: string) {
|
|
return {
|
|
system: [
|
|
{
|
|
type: "text",
|
|
text: "Stable prefix",
|
|
cache_control: { type: "ephemeral" },
|
|
},
|
|
{
|
|
type: "text",
|
|
text: "Dynamic suffix",
|
|
},
|
|
],
|
|
messages: [
|
|
{
|
|
role: "user",
|
|
content: [
|
|
{
|
|
type: "text",
|
|
text: messageText,
|
|
cache_control: { type: "ephemeral" },
|
|
},
|
|
],
|
|
},
|
|
],
|
|
};
|
|
}
|
|
|
|
describe("createAnthropicVertexStreamFn", () => {
|
|
beforeAll(async () => {
|
|
({ createAnthropicVertexStreamFn, createAnthropicVertexStreamFnForModel } =
|
|
await import("./stream-runtime.js"));
|
|
});
|
|
|
|
it("omits projectId when ADC credentials are used without an explicit project", () => {
|
|
const { deps, anthropicVertexCtorMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn(undefined, "global", undefined, deps);
|
|
|
|
void streamFn(makeModel({ id: "claude-sonnet-4-6", maxTokens: 128000 }), { messages: [] }, {});
|
|
|
|
expect(anthropicVertexCtorMock).toHaveBeenCalledWith({
|
|
region: "global",
|
|
});
|
|
});
|
|
|
|
it("passes an explicit baseURL through to the Vertex client", () => {
|
|
const { deps, anthropicVertexCtorMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn(
|
|
"vertex-project",
|
|
"us-east5",
|
|
"https://proxy.example.test/vertex/v1",
|
|
deps,
|
|
);
|
|
|
|
void streamFn(makeModel({ id: "claude-sonnet-4-6", maxTokens: 128000 }), { messages: [] }, {});
|
|
|
|
expect(anthropicVertexCtorMock).toHaveBeenCalledWith({
|
|
projectId: "vertex-project",
|
|
region: "us-east5",
|
|
baseURL: "https://proxy.example.test/vertex/v1",
|
|
});
|
|
});
|
|
|
|
it("defaults maxTokens to the model limit instead of the old 32000 cap", () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn("vertex-project", "us-east5", undefined, deps);
|
|
const model = makeModel({ id: "claude-opus-4-6", maxTokens: 128000 });
|
|
|
|
void streamFn(model, { messages: [] }, {});
|
|
|
|
expect(streamTransportOptions(streamAnthropicMock).maxTokens).toBe(128000);
|
|
});
|
|
|
|
it("clamps explicit maxTokens to the selected model limit", () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn("vertex-project", "us-east5", undefined, deps);
|
|
const model = makeModel({ id: "claude-sonnet-4-6", maxTokens: 128000 });
|
|
|
|
void streamFn(model, { messages: [] }, { maxTokens: 999999 });
|
|
|
|
expect(streamTransportOptions(streamAnthropicMock).maxTokens).toBe(128000);
|
|
});
|
|
|
|
it("maps xhigh reasoning to max effort for adaptive Opus models", () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn("vertex-project", "us-east5", undefined, deps);
|
|
const model = makeModel({ id: "claude-opus-4-6", maxTokens: 64000 });
|
|
|
|
void streamFn(model, { messages: [] }, { reasoning: "xhigh" });
|
|
|
|
const transportOptions = streamTransportOptions(streamAnthropicMock);
|
|
expect(transportOptions.thinkingEnabled).toBe(true);
|
|
expect(transportOptions.effort).toBe("max");
|
|
});
|
|
|
|
it("maps xhigh reasoning to xhigh effort for Opus 4.7", () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn("vertex-project", "us-east5", undefined, deps);
|
|
const model = makeModel({ id: "claude-opus-4-7", maxTokens: 64000 });
|
|
|
|
void streamFn(model, { messages: [] }, { reasoning: "xhigh" });
|
|
|
|
const transportOptions = streamTransportOptions(streamAnthropicMock);
|
|
expect(transportOptions.thinkingEnabled).toBe(true);
|
|
expect(transportOptions.effort).toBe("xhigh");
|
|
});
|
|
|
|
it("applies Anthropic cache-boundary shaping before forwarding payload hooks", async () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const onPayload = vi.fn(async (payload: unknown) => payload);
|
|
const { model, onPayload: transportPayloadHook } = captureCacheBoundaryPayloadHook(
|
|
onPayload,
|
|
deps,
|
|
streamAnthropicMock,
|
|
);
|
|
const payload = {
|
|
system: [
|
|
{
|
|
type: "text",
|
|
text: CACHE_BOUNDARY_PROMPT,
|
|
cache_control: { type: "ephemeral" },
|
|
},
|
|
],
|
|
messages: [{ role: "user", content: "Hello" }],
|
|
};
|
|
|
|
const nextPayload = await transportPayloadHook?.(payload, model);
|
|
|
|
const expectedPayload = buildExpectedCacheBoundaryPayload("Hello");
|
|
expect(onPayload).toHaveBeenCalledWith(expectedPayload, model);
|
|
expect(nextPayload).toEqual(expectedPayload);
|
|
});
|
|
|
|
it("reapplies Anthropic cache-boundary shaping when payload hooks return a fresh payload", async () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const onPayload = vi.fn(async () => ({
|
|
system: [
|
|
{
|
|
type: "text",
|
|
text: CACHE_BOUNDARY_PROMPT,
|
|
},
|
|
],
|
|
messages: [{ role: "user", content: "Hello again" }],
|
|
}));
|
|
const { model, onPayload: transportPayloadHook } = captureCacheBoundaryPayloadHook(
|
|
onPayload,
|
|
deps,
|
|
streamAnthropicMock,
|
|
);
|
|
|
|
const nextPayload = await transportPayloadHook?.(
|
|
{
|
|
system: [
|
|
{
|
|
type: "text",
|
|
text: CACHE_BOUNDARY_PROMPT,
|
|
},
|
|
],
|
|
messages: [{ role: "user", content: "Hello" }],
|
|
},
|
|
model,
|
|
);
|
|
|
|
expect(nextPayload).toEqual(buildExpectedCacheBoundaryPayload("Hello again"));
|
|
});
|
|
|
|
it("omits maxTokens when neither the model nor request provide a finite limit", () => {
|
|
const { deps, streamAnthropicMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFn("vertex-project", "us-east5", undefined, deps);
|
|
const model = makeModel({ id: "claude-sonnet-4-6" });
|
|
|
|
void streamFn(model, { messages: [] }, { maxTokens: Number.NaN });
|
|
|
|
expect(streamAnthropicMock).toHaveBeenCalledTimes(1);
|
|
const [calledModel, payload, transportOptions] = streamAnthropicCall(streamAnthropicMock);
|
|
expect(calledModel).toBe(model);
|
|
expect(payload).toEqual({ messages: [] });
|
|
expect(transportOptions).toBeTypeOf("object");
|
|
expect(Object.hasOwn(transportOptions as object, "maxTokens")).toBe(false);
|
|
});
|
|
});
|
|
|
|
describe("createAnthropicVertexStreamFnForModel", () => {
|
|
it("derives project and region from the model and env", () => {
|
|
const { deps, anthropicVertexCtorMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFnForModel(
|
|
{ baseUrl: "https://europe-west4-aiplatform.googleapis.com" },
|
|
{ GOOGLE_CLOUD_PROJECT_ID: "vertex-project" } as NodeJS.ProcessEnv,
|
|
deps,
|
|
);
|
|
|
|
void streamFn(makeModel({ id: "claude-sonnet-4-6", maxTokens: 64000 }), { messages: [] }, {});
|
|
|
|
expect(anthropicVertexCtorMock).toHaveBeenCalledWith({
|
|
projectId: "vertex-project",
|
|
region: "europe-west4",
|
|
baseURL: "https://europe-west4-aiplatform.googleapis.com/v1",
|
|
});
|
|
});
|
|
|
|
it("preserves explicit custom provider base URLs", () => {
|
|
const { deps, anthropicVertexCtorMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFnForModel(
|
|
{ baseUrl: "https://proxy.example.test/custom-root/v1" },
|
|
{ GOOGLE_CLOUD_PROJECT_ID: "vertex-project" } as NodeJS.ProcessEnv,
|
|
deps,
|
|
);
|
|
|
|
void streamFn(makeModel({ id: "claude-sonnet-4-6", maxTokens: 64000 }), { messages: [] }, {});
|
|
|
|
expect(anthropicVertexCtorMock).toHaveBeenCalledWith({
|
|
projectId: "vertex-project",
|
|
region: "global",
|
|
baseURL: "https://proxy.example.test/custom-root/v1",
|
|
});
|
|
});
|
|
|
|
it("adds /v1 for path-prefixed custom provider base URLs", () => {
|
|
const { deps, anthropicVertexCtorMock } = createStreamDeps();
|
|
const streamFn = createAnthropicVertexStreamFnForModel(
|
|
{ baseUrl: "https://proxy.example.test/custom-root" },
|
|
{ GOOGLE_CLOUD_PROJECT_ID: "vertex-project" } as NodeJS.ProcessEnv,
|
|
deps,
|
|
);
|
|
|
|
void streamFn(makeModel({ id: "claude-sonnet-4-6", maxTokens: 64000 }), { messages: [] }, {});
|
|
|
|
expect(anthropicVertexCtorMock).toHaveBeenCalledWith({
|
|
projectId: "vertex-project",
|
|
region: "global",
|
|
baseURL: "https://proxy.example.test/custom-root/v1",
|
|
});
|
|
});
|
|
});
|