Files
my-pi/pi-permission-system/test/auto-review-runtime.test.ts
云服务部-叶林立andDevin <158243242+devin-ai-integration[bot]@users.noreply.github.com> 7e6a8faae1 feat(pi-permission-system): AutoReview 改为跟随主模型的对话式工具调用审查
AutoReview:

- 审查器回到 Codex Guardian 风格的对话式审查,默认跟随会话当前主模型
  (每次审查实时读取 ctx.model);provider/model 必须同时设置才固定审查
  模型,只设其一视为配置错误并转人工。
- 结论只通过 approve / reject 两个工具给出,参数仅 reason;不强制
  toolChoice,正文文本(即使是合法 JSON)一律忽略。
- approve 自动放行;reject 转人工并在弹窗显示理由(标注模型生成)。
  超时、Provider 错误、截断、未调用工具、多次调用、参数无效等异常同样
  转人工,并附固定的系统说明;用户按 Esc 中止时直接拒绝。
- 模型调用改为 modelRegistry.streamSimple(...).result():Pi 1.3.0 面向
  扩展的 ModelRegistry 没有 completeSimple,原写法在真实环境中每次都会
  转人工。
- 对话记录保留可信度标注;工具结果在有更短的 pi-compaction 摘要时替换
  为摘要;token 估算改为非 ASCII 字符按 1 token 计;预算可配置。
- 同一条用户消息内完全相同的请求只缓存 approve 结论。
- 默认 reasoning low、总超时 30 秒、最多 2 次尝试、maxOutputTokens 4000。

删除:

- 未发布过的 TypeSafe Jev 分类器实现、DenialCircuitBreaker。
- 整个 annotator 机制(model-explanation、注册表、registerAnnotator、
  provider-timeout);annotators 配置键保留为已弃用并忽略,避免旧配置
  被拒绝。

测试:

- 新增 reviewer / transcript / 弹窗说明 / 默认配置测试;清理重复、恒真
  或只测实现细节的旧测试。
- 使用 deepseek-v4.1-flash 实测 5 个场景各 5 次,25 次结论全部符合预期。

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-19 01:54:17 -07:00

168 lines
5.1 KiB
TypeScript

import { describe, expect, it, vi } from "vitest";
import type { Api, Model } from "@earendil-works/pi-ai";
import type { ExtensionContext } from "@earendil-works/pi-coding-agent";
import {
DEFAULT_AUTO_REVIEW_CONFIG,
type AutoReviewConfig,
} from "#src/auto-review/config";
import { installBuiltinAutoReview } from "#src/auto-review/runtime";
import type { ConfigReader } from "#src/config-store";
import type { PermissionsService } from "#src/service";
function makeModel(id: string, provider = "cfg"): Model<Api> {
return { id, provider } as unknown as Model<Api>;
}
/**
* A registry exposing `streamSimple`, as a real Pi 1.3.0 runtime does — the
* reviewer completes through `streamSimple(...).result()`.
*
* The pinned development types predate this surface, so the registry is built
* as a plain object — the same structural approach the reviewer takes.
*/
function chatRegistry(provider: string, modelId: string) {
return {
find: (p: string, m: string) =>
p === provider && m === modelId ? makeModel(m, p) : undefined,
streamSimple: vi.fn(),
};
}
interface HarnessOptions {
readonly autoReview: AutoReviewConfig;
readonly hasUI?: boolean;
readonly registry?: object;
}
function harness(options: HarnessOptions) {
const { autoReview, hasUI = true } = options;
const notify = vi.fn();
const registerAuthorizer = vi.fn(() => () => {});
const controller = installBuiltinAutoReview({
service: { registerAuthorizer } as unknown as PermissionsService,
config: {
current: () => ({
debugLog: false,
permissionReviewLog: true,
yoloMode: false,
doublePressToConfirm: true,
authorizerChain: ["auto-review"],
autoReview,
}),
} as ConfigReader,
});
const ctx = {
hasUI,
ui: { notify },
modelRegistry: options.registry ?? {},
sessionManager: { getBranch: () => [], getSessionId: () => "s" },
model: makeModel("session-model"),
signal: undefined,
} as unknown as ExtensionContext;
controller.handleSessionStart(ctx);
return { controller, notify, registerAuthorizer };
}
describe("built-in AutoReview lifecycle", () => {
it("registers the auto-review authorizer", () => {
const { registerAuthorizer } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG },
});
expect(registerAuthorizer).toHaveBeenCalledWith(
"auto-review",
expect.any(Function),
);
});
it("warns when exactly one of provider/model is set", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, provider: "cfg" },
});
expect(notify).toHaveBeenCalledTimes(1);
expect(notify.mock.calls[0]?.[1]).toBe("warning");
expect(notify.mock.calls[0]?.[0]).toMatch(/only one of/iu);
});
it("warns when the named model cannot be resolved", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, provider: "cfg", model: "missing" },
registry: chatRegistry("cfg", "present"),
});
expect(notify).toHaveBeenCalledTimes(1);
expect(notify.mock.calls[0]?.[0]).toMatch(/cfg\/missing.*not available/iu);
});
it("warns when the runtime exposes no completion capability", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, provider: "cfg", model: "m" },
registry: {},
});
expect(notify).toHaveBeenCalledTimes(1);
expect(notify.mock.calls[0]?.[0]).toMatch(/does not support an independent model call/iu);
});
it("stays silent when the named model resolves", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, provider: "cfg", model: "m" },
registry: chatRegistry("cfg", "m"),
});
expect(notify).not.toHaveBeenCalled();
});
it("stays silent in follow-the-session-model mode", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG },
registry: {},
});
expect(notify).not.toHaveBeenCalled();
});
it("stays silent when AutoReview is disabled", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, enabled: false, provider: "cfg" },
});
expect(notify).not.toHaveBeenCalled();
});
it("does not notify without a UI", () => {
const { notify } = harness({
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, provider: "cfg" },
hasUI: false,
});
expect(notify).not.toHaveBeenCalled();
});
it("stays silent when auto-review is not in the authorizer chain", () => {
const notify = vi.fn();
const controller = installBuiltinAutoReview({
service: { registerAuthorizer: vi.fn(() => () => {}) } as unknown as PermissionsService,
config: {
current: () => ({
debugLog: false,
permissionReviewLog: true,
yoloMode: false,
doublePressToConfirm: true,
authorizerChain: [],
autoReview: { ...DEFAULT_AUTO_REVIEW_CONFIG, provider: "cfg" },
}),
} as ConfigReader,
});
controller.handleSessionStart({
hasUI: true,
ui: { notify },
} as unknown as ExtensionContext);
expect(notify).not.toHaveBeenCalled();
});
});