Files
wehub-resource-sync 426e9eeabd
Voice Workbench / headless workbench (mocked backends) (push) Has been cancelled
Voice Workbench / real acoustic lane (nightly, provisioned only) (push) Has been cancelled
ci / test (push) Has been cancelled
ci / lint-and-format (push) Has been cancelled
ci / build (push) Has been cancelled
ci / dev-startup (push) Has been cancelled
gitleaks / gitleaks (push) Has been cancelled
Markdown Links / Relative Markdown Links (push) Has been cancelled
Quality (Extended) / Homepage Build (PR smoke) (push) Has been cancelled
Quality (Extended) / Comment-only diff guard (push) Has been cancelled
Quality (Extended) / Format + Type Safety Ratchet (push) Has been cancelled
Quality (Extended) / Develop Gate (secret scan + UI determinism) (push) Has been cancelled
Quality (Extended) / Develop Gate (lint) (push) Has been cancelled
Chat shell gestures / Chat shell gesture + parity e2e (push) Has been cancelled
Cloud Gateway Discord / Test (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx @biomejs/biome check packages/lifeops-bench/src, benchmark-lint) (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx vitest run --config packages/lifeops-bench/vitest.config.ts --root packages/lifeops-bench --passWithNoTests, benchmark-tests) (push) Has been cancelled
Build Agent Image / build-and-push (push) Has been cancelled
Dev Smoke / bun run dev onboarding chat (push) Has been cancelled
Dev Smoke / Vite HMR dependency-level smoke (push) Has been cancelled
Electrobun Submodule Guard / electrobun gitlink is fetchable (push) Has been cancelled
Publish @elizaos/example-code / check_npm (push) Has been cancelled
Publish @elizaos/example-code / publish_npm (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / verify_version (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / publish_npm (push) Has been cancelled
Sandbox Live Smoke / Sandbox live smoke (push) Has been cancelled
Snap Build & Test / Build Snap (amd64) (push) Has been cancelled
Snap Build & Test / Build Snap (arm64) (push) Has been cancelled
Test Packaging / elizaos CLI global-install smoke (node + bun) (push) Has been cancelled
Cloud Gateway Webhook / Test (push) Has been cancelled
Cloud Tests / lint-and-types (push) Has been cancelled
Cloud Tests / unit-tests (push) Has been cancelled
Cloud Tests / integration-tests (push) Has been cancelled
Cloud Tests / e2e-tests (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Deploy Apps Worker (Product 2) / Determine environment (push) Has been cancelled
Deploy Apps Worker (Product 2) / Deploy apps worker to apps-control host (${{ needs.determine-env.outputs.environment }}) (push) Has been cancelled
Deploy Eliza Provisioning Worker / Determine environment (push) Has been cancelled
Deploy Eliza Provisioning Worker / Deploy worker to Hetzner host (${{ needs.determine-env.outputs.environment }} @ ${{ needs.determine-env.outputs.deployment_sha }}) (push) Has been cancelled
Dev Smoke / Classify changed paths (push) Has been cancelled
supply-chain / sbom (push) Has been cancelled
supply-chain / vulnerability-scan (push) Has been cancelled
Build, Push & Deploy to Phala Cloud / build-and-push (push) Has been cancelled
Test Packaging / Validate Packaging Configs (push) Has been cancelled
Test Packaging / Build & Test PyPI Package (push) Has been cancelled
Test Packaging / PyPI on Python ${{ matrix.python }} (push) Has been cancelled
Test Packaging / Pack & Test JS Tarballs (push) Has been cancelled
UI Fixture E2E / ui-fixture-e2e (push) Has been cancelled
UI Fixture E2E / fixture-e2e (push) Has been cancelled
UI Story Gate / story-gate (push) Has been cancelled
vault-ci / test (macos-latest) (push) Has been cancelled
vault-ci / test (ubuntu-latest) (push) Has been cancelled
vault-ci / test (windows-latest) (push) Has been cancelled
vault-ci / app-core wiring tests (push) Has been cancelled
verify-patches / verify patches/CHECKSUMS.sha256 (push) Has been cancelled
Voice Benchmark Smoke / voice-emotion fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voiceagentbench fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench-quality unit smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench TypeScript unit (no audio) (push) Has been cancelled
Voice Benchmark Smoke / voice bench smoke summary (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/app-core test bun run --cwd packages/elizaos test bun run --cwd packages/cloud/shared test], app-and-cli) (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/scenario-runner test bun run --cwd packages/vault test bun run --cwd packages/security test bun run --cwd plugins/plugin-coding-tools test], framework-packages) (push) Has been cancelled
Windows CI / windows ([bun run --cwd plugins/plugin-elizacloud test bun run --cwd plugins/plugin-discord test bun run --cwd plugins/plugin-anthropic test bun run --cwd plugins/plugin-openai test bun run --cwd plugins/plugin-app-control test bun run --cwd plugins/pl… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run build --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/agent --concurrency=4 node packages/scripts/run-bash-linux-only.mjs scripts/verify-riscv64-buildpaths.sh node packages/scripts/run… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run typecheck --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/cloud-shared --concurrency=4 bun run --cwd packages/core test bun run --cwd packages/shared test], core-runtime, 75) (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:43:05 +08:00

226 lines
8.0 KiB
TypeScript

/**
* Shape tests for the effort/thinking provider options: ANTHROPIC_EFFORT(_SMALL/
* _LARGE) becomes adaptive thinking + the AI SDK `effort` option, per-model
* ceilings clamp xhigh/max on models that reject them, the legacy fixed CoT
* budget survives (and loses to effort), invalid values are dropped, and
* thinking-active requests carry temperature=1 with topP removed. Drives the
* real handlers against a mocked AI SDK — no live API.
*/
import type { IAgentRuntime } from "@elizaos/core";
import { afterEach, describe, expect, it, vi } from "vitest";
function createRuntime(settings: Record<string, string>) {
return {
character: { name: "Claude Agent", system: "system prompt" },
emitEvent: vi.fn(),
getSetting: vi.fn((key: string) => settings[key]),
} as unknown as IAgentRuntime;
}
function mockAiSdk() {
const generateText = vi.fn(async () => ({
text: "ok",
finishReason: "stop",
usage: { inputTokens: 5, outputTokens: 2 },
}));
vi.doMock("ai", () => ({ generateText, streamText: vi.fn() }));
vi.doMock("../providers/anthropic", () => ({
createAnthropicClientWithTopPSupport: () => (modelName: string) => ({
modelId: modelName,
}),
}));
return generateText;
}
function anthropicOptionsOf(generateText: ReturnType<typeof vi.fn>) {
const call = generateText.mock.calls[0]?.[0] as
| {
providerOptions?: { anthropic?: Record<string, unknown> };
temperature?: number;
topP?: number;
}
| undefined;
if (!call) throw new Error("generateText was not called");
return {
anthropic: call.providerOptions?.anthropic,
temperature: call.temperature,
topP: call.topP,
};
}
afterEach(() => {
vi.doUnmock("ai");
vi.doUnmock("../providers/anthropic");
vi.clearAllMocks();
vi.resetModules();
});
describe("Anthropic effort/thinking provider options", () => {
it("sends adaptive thinking + effort from ANTHROPIC_EFFORT_LARGE and forces temperature=1", async () => {
const generateText = mockAiSdk();
const { handleTextLarge } = await import("../models/text");
await handleTextLarge(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_LARGE_MODEL: "claude-opus-4-8",
ANTHROPIC_EFFORT_LARGE: "xhigh",
}),
{ prompt: "hi", temperature: 0.7 } as never
);
const { anthropic, temperature } = anthropicOptionsOf(generateText);
expect(anthropic?.thinking).toEqual({ type: "adaptive" });
expect(anthropic?.effort).toBe("xhigh");
expect(temperature).toBe(1);
}, 60_000);
it("falls back to the shared ANTHROPIC_EFFORT and normalizes case", async () => {
const generateText = mockAiSdk();
const { handleTextSmall } = await import("../models/text");
await handleTextSmall(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_SMALL_MODEL: "claude-sonnet-5",
ANTHROPIC_EFFORT: "Medium",
}),
{ prompt: "hi" } as never
);
const { anthropic } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBe("medium");
expect(anthropic?.thinking).toEqual({ type: "adaptive" });
}, 60_000);
it("clamps xhigh to high on models without the extended tiers (sonnet)", async () => {
const generateText = mockAiSdk();
const { handleTextSmall } = await import("../models/text");
await handleTextSmall(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_SMALL_MODEL: "claude-sonnet-4-6",
ANTHROPIC_EFFORT_SMALL: "xhigh",
}),
{ prompt: "hi" } as never
);
const { anthropic } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBe("high");
}, 60_000);
// Live-probed 2026-07-12: haiku-4-5 rejects the effort parameter outright
// ("This model does not support the effort parameter"), so a configured
// effort must never reach the wire for it.
it("never sends effort for haiku (model rejects the parameter)", async () => {
const generateText = mockAiSdk();
const { handleTextSmall } = await import("../models/text");
await handleTextSmall(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_SMALL_MODEL: "claude-haiku-4-5-20251001",
ANTHROPIC_EFFORT_SMALL: "high",
}),
{ prompt: "hi" } as never
);
const { anthropic } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBeUndefined();
expect(anthropic?.thinking).toBeUndefined();
}, 60_000);
it("falls back to the CoT budget on haiku when both are configured", async () => {
const generateText = mockAiSdk();
const { handleTextSmall } = await import("../models/text");
await handleTextSmall(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_SMALL_MODEL: "claude-haiku-4-5-20251001",
ANTHROPIC_EFFORT_SMALL: "high",
ANTHROPIC_COT_BUDGET_SMALL: "1024",
}),
{ prompt: "hi" } as never
);
const { anthropic } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBeUndefined();
expect(anthropic?.thinking).toEqual({ type: "enabled", budgetTokens: 1024 });
}, 60_000);
it("keeps max on fable-5", async () => {
const generateText = mockAiSdk();
const { handleTextLarge } = await import("../models/text");
await handleTextLarge(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_LARGE_MODEL: "claude-fable-5",
ANTHROPIC_EFFORT_LARGE: "max",
}),
{ prompt: "hi" } as never
);
const { anthropic } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBe("max");
}, 60_000);
it("ignores an invalid effort value and sends no thinking block", async () => {
const generateText = mockAiSdk();
const { handleTextLarge } = await import("../models/text");
await handleTextLarge(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_LARGE_MODEL: "claude-sonnet-5",
ANTHROPIC_EFFORT_LARGE: "turbo",
}),
{ prompt: "hi" } as never
);
const { anthropic, temperature } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBeUndefined();
expect(anthropic?.thinking).toBeUndefined();
expect(temperature).toBe(0.7);
}, 60_000);
it("keeps the legacy fixed CoT budget shape when no effort is configured", async () => {
const generateText = mockAiSdk();
const { handleTextLarge } = await import("../models/text");
await handleTextLarge(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_LARGE_MODEL: "claude-sonnet-5",
ANTHROPIC_COT_BUDGET: "2048",
}),
{ prompt: "hi", temperature: 0.5 } as never
);
const { anthropic, temperature } = anthropicOptionsOf(generateText);
expect(anthropic?.thinking).toEqual({ type: "enabled", budgetTokens: 2048 });
expect(anthropic?.effort).toBeUndefined();
// Thinking-active requests only accept temperature=1.
expect(temperature).toBe(1);
}, 60_000);
it("prefers effort over a configured CoT budget when both are set", async () => {
const generateText = mockAiSdk();
const { handleTextLarge } = await import("../models/text");
await handleTextLarge(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_LARGE_MODEL: "claude-opus-4-8",
ANTHROPIC_COT_BUDGET: "2048",
ANTHROPIC_EFFORT_LARGE: "high",
}),
{ prompt: "hi" } as never
);
const { anthropic } = anthropicOptionsOf(generateText);
expect(anthropic?.thinking).toEqual({ type: "adaptive" });
expect(anthropic?.effort).toBe("high");
}, 60_000);
it("drops topP when thinking is active", async () => {
const generateText = mockAiSdk();
const { handleTextLarge } = await import("../models/text");
await handleTextLarge(
createRuntime({
ANTHROPIC_API_KEY: "test-key",
ANTHROPIC_LARGE_MODEL: "claude-sonnet-5",
ANTHROPIC_EFFORT_LARGE: "low",
}),
{ prompt: "hi", topP: 0.9 } as never
);
const { anthropic, topP } = anthropicOptionsOf(generateText);
expect(anthropic?.effort).toBe("low");
expect(topP).toBeUndefined();
}, 60_000);
});