明说要校正时，第一步就能打开（BUG-1317）
本命和申报时段的第 0 步，校正工具挂上时可以排盘，也可以直接打开校正。还没看盘就顺口提议不算已经提议过。规则第一句写明 explicitRequest=true。定向测试 149 通过，类型检查和 lint 通过，隐私标记通过。名人生平回测未跑。 Co-Authored-By: Grok (agent loop)
This commit is contained in:
jesse-ux
co-authored by
Grok (agent loop)
Grok (agent loop)
parent
0c04755560
commit
bccceff91f
@@ -679,26 +679,40 @@ test("guided-topic entrypoint ignores a model domain rewrite instead of executin
|
||||
|
||||
test("natal first step exposes only the chart calculation tool", () => {
|
||||
assert.equal(CONSULTATION_NATAL_CALC_TOOL_ID, "run-jyotish-consultation");
|
||||
// 原值: 第 0 步 toolChoice "required" / 新值: "auto"
|
||||
// 原因: BUG-282 供应商拒收 thinking 模式下的 required，BUG-937 撤回
|
||||
// 原值: 第 0 步 toolChoice "required"，后来改为只有排盘工具且 toolChoice "auto"
|
||||
// 新值: 没挂校正工具时第 0 步仍只有排盘工具；挂了时是排盘工具和 offer-birth-time-rectification。toolChoice 仍是 "auto"。第 1 步不收窄。
|
||||
// 原因: BUG-937 保持 auto；BUG-1317 按产品选择，第 0 步在工具确实挂上时可以打开校正。
|
||||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 0 }), {
|
||||
activeTools: ["run-jyotish-consultation"],
|
||||
toolChoice: "auto",
|
||||
});
|
||||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 1 }), {
|
||||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 0, rectificationOffer: false }), {
|
||||
activeTools: ["run-jyotish-consultation"],
|
||||
toolChoice: "auto",
|
||||
});
|
||||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 0, rectificationOffer: true }), {
|
||||
activeTools: ["run-jyotish-consultation", "offer-birth-time-rectification"],
|
||||
toolChoice: "auto",
|
||||
});
|
||||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 1, rectificationOffer: true }), {
|
||||
toolChoice: "auto",
|
||||
});
|
||||
});
|
||||
|
||||
test("window first step requires the window consultation tool", () => {
|
||||
assert.equal(CONSULTATION_WINDOW_CALC_TOOL_ID, "run-jyotish-window-consultation");
|
||||
// 原值: 第 0 步 toolChoice "required" / 新值: "auto"
|
||||
// 原因: BUG-282 供应商拒收 thinking 模式下的 required，BUG-937 撤回
|
||||
// 原值: 第 0 步 toolChoice "required"，后来改为只有窗口排盘工具且 toolChoice "auto"
|
||||
// 新值: 没挂校正工具时第 0 步仍只有窗口排盘工具；挂了时再加上 offer-birth-time-rectification。toolChoice 仍是 "auto"。
|
||||
// 原因: 与本命同一条 BUG-1317 决定，申报时段也要能在第一步打开校正。
|
||||
assert.deepEqual(consultationWindowPrepareStep({ stepNumber: 0 }), {
|
||||
activeTools: ["run-jyotish-window-consultation"],
|
||||
toolChoice: "auto",
|
||||
});
|
||||
assert.deepEqual(consultationWindowPrepareStep({ stepNumber: 1 }), {
|
||||
assert.deepEqual(consultationWindowPrepareStep({ stepNumber: 0, rectificationOffer: true }), {
|
||||
activeTools: ["run-jyotish-window-consultation", "offer-birth-time-rectification"],
|
||||
toolChoice: "auto",
|
||||
});
|
||||
assert.deepEqual(consultationWindowPrepareStep({ stepNumber: 1, rectificationOffer: true }), {
|
||||
toolChoice: "auto",
|
||||
});
|
||||
});
|
||||
|
||||
@@ -233,8 +233,12 @@ test("consult streams reserve an answer budget and keep provider thinking on a s
|
||||
route.indexOf("const natalStreamOptions = {"),
|
||||
);
|
||||
assert.doesNotMatch(sharedStreamOptions, /prepareStep/);
|
||||
assert.match(route, /prepareStep: consultationNatalPrepareStep/);
|
||||
assert.match(route, /prepareStep: consultationWindowPrepareStep/);
|
||||
// 原值：prepareStep: consultationNatalPrepareStep / consultationWindowPrepareStep，函数本身不知道校正工具在不在。
|
||||
// 新值：路由把 rectificationOffer: true 传进去，因为这两条路线都会挂上校正工具。
|
||||
// 原因：BUG-1317，第 0 步在工具挂上时要能打开校正；没传时函数仍只留排盘工具。
|
||||
assert.match(route, /prepareStep: \(input: \{ stepNumber: number \}\) => consultationNatalPrepareStep\(\{/);
|
||||
assert.match(route, /prepareStep: \(input: \{ stepNumber: number \}\) => consultationWindowPrepareStep\(\{/);
|
||||
assert.match(route, /rectificationOffer: true/);
|
||||
assert.match(route, /streamWithOverflowRetry\(agent, natalStreamOptions\)/);
|
||||
assert.match(route, /streamWithOverflowRetry\(agent, windowStreamOptions\)/);
|
||||
assert.match(
|
||||
|
||||
@@ -72,8 +72,14 @@ function offerTool(options: {
|
||||
alreadyOffered?: boolean;
|
||||
decide?: () => Promise<OfferDecision>;
|
||||
loadResumableSessionId?: () => Promise<string | null>;
|
||||
/** False only for a step-0 call that has not seen the chart yet. */
|
||||
chartReady?: boolean;
|
||||
} = {}) {
|
||||
const state = createConsultationRuntimeState();
|
||||
if (options.chartReady !== false) {
|
||||
state.consultationToolCompleted = true;
|
||||
state.consultationToolSuccessCount = 1;
|
||||
}
|
||||
let decisions = 0;
|
||||
let loads = 0;
|
||||
const tools = createConsultationTools({
|
||||
@@ -520,6 +526,111 @@ test("an ordinary consultation still retries once when the calculation never fin
|
||||
assert.equal(events.some((event) => event.type === "activity" && event.label === "正在补齐方法与计算步骤"), true);
|
||||
});
|
||||
|
||||
test("step 0 explicit request opens rectification without calculating a chart", async () => {
|
||||
const fresh = offerTool({ chartReady: false });
|
||||
const result = await fresh.tool.execute({ explicitRequest: true });
|
||||
assert.equal(result.directEntry, "new");
|
||||
assert.equal(fresh.state.consultationToolCallCount, 0);
|
||||
assert.equal(fresh.state.consultationToolCompleted, false);
|
||||
assert.equal(fresh.state.rectificationDirectEntry?.sentence, RECTIFICATION_DIRECT_NEW_COPY);
|
||||
let contractRetries = 0;
|
||||
const response = streamAgentResponse({
|
||||
runId: "run-step0-explicit",
|
||||
requestId: REQUEST_ID,
|
||||
state: fresh.state,
|
||||
requireTool: true,
|
||||
pass4Mode: "verified_chart",
|
||||
stepScopedAnswer: true,
|
||||
toolStatus: () => "ready",
|
||||
receipt: () => receipt(fresh.state),
|
||||
stream: (async function* () {
|
||||
yield { type: "text-delta", payload: { text: "我先看看盘，然后写一段解读。" } };
|
||||
yield STOP_FINISH;
|
||||
})(),
|
||||
retry: async () => {
|
||||
contractRetries += 1;
|
||||
return (async function* () { yield STOP_FINISH; })();
|
||||
},
|
||||
});
|
||||
const events = await readStream(response);
|
||||
assert.equal(contractRetries, 0);
|
||||
assert.equal(visibleAnswer(events), RECTIFICATION_DIRECT_NEW_COPY);
|
||||
assert.equal(events.some((event) => event.type === "run.completed" && event.responseKind === "smalltalk"), true);
|
||||
});
|
||||
|
||||
test("step 0 text without a tool still retries into a chart answer", async () => {
|
||||
const state = createConsultationRuntimeState();
|
||||
let contractRetries = 0;
|
||||
const response = streamAgentResponse({
|
||||
runId: "run-step0-empty",
|
||||
requestId: REQUEST_ID,
|
||||
state,
|
||||
requireTool: true,
|
||||
pass4Mode: "verified_chart",
|
||||
stepScopedAnswer: true,
|
||||
toolStatus: () => "ready",
|
||||
receipt: () => receipt(state),
|
||||
stream: (async function* () {
|
||||
yield { type: "text-delta", payload: { text: "还没排盘就想写。" } };
|
||||
yield STOP_FINISH;
|
||||
})(),
|
||||
retry: async () => {
|
||||
contractRetries += 1;
|
||||
state.consultationToolCompleted = true;
|
||||
state.consultationToolSuccessCount = 1;
|
||||
return (async function* () {
|
||||
yield { type: "text-delta", payload: { text: "事业方向可以看。" } };
|
||||
yield STOP_FINISH;
|
||||
})();
|
||||
},
|
||||
});
|
||||
const events = await readStream(response);
|
||||
assert.equal(contractRetries, 1);
|
||||
assert.equal(visibleAnswer(events), "事业方向可以看。");
|
||||
assert.equal(state.rectificationDirectEntry, undefined);
|
||||
assert.equal(events.some((event) => event.type === "activity" && event.label === "正在补齐方法与计算步骤"), true);
|
||||
});
|
||||
|
||||
test("a soft offer before the chart is not recorded, then a chart answer can still offer", async () => {
|
||||
const fresh = offerTool({ chartReady: false });
|
||||
const early = await fresh.tool.execute({});
|
||||
assert.equal(early.offered, false);
|
||||
assert.match(String(early.note), /先排盘，看过盘再决定要不要提/);
|
||||
// 记在局部上再断言。直接断言 state 上的字段会把它收成永远是空，排盘后再读就对不上类型。
|
||||
const offerBeforeChart = fresh.state.rectificationOffer;
|
||||
assert.equal(offerBeforeChart, undefined);
|
||||
assert.equal(fresh.state.rectificationDirectEntry, undefined);
|
||||
assert.equal(fresh.decisions(), 0);
|
||||
fresh.state.consultationToolCompleted = true;
|
||||
fresh.state.consultationToolSuccessCount = 1;
|
||||
const later = await fresh.tool.execute({});
|
||||
assert.equal(later.offered, true);
|
||||
const offerAfterChart = fresh.state.rectificationOffer;
|
||||
assert.equal(offerAfterChart?.status, "offered");
|
||||
assert.equal(offerAfterChart?.autoOpen, undefined);
|
||||
assert.equal(fresh.decisions(), 1);
|
||||
const response = streamAgentResponse({
|
||||
runId: "run-step0-soft",
|
||||
requestId: REQUEST_ID,
|
||||
state: fresh.state,
|
||||
requireTool: true,
|
||||
pass4Mode: "verified_chart",
|
||||
stepScopedAnswer: true,
|
||||
toolStatus: () => "ready",
|
||||
receipt: () => receipt(fresh.state),
|
||||
stream: (async function* () {
|
||||
yield { type: "text-delta", payload: { text: "事业方向可以看。" } };
|
||||
yield STOP_FINISH;
|
||||
})(),
|
||||
retry: async () => {
|
||||
throw new Error("chart contract should already be ready");
|
||||
},
|
||||
});
|
||||
const events = await readStream(response);
|
||||
assert.equal(visibleAnswer(events), "事业方向可以看。");
|
||||
assert.equal(visibleAnswer(events).includes(RECTIFICATION_DIRECT_NEW_COPY), false);
|
||||
});
|
||||
|
||||
test("the offer rule is defined once, and direct entry settles with the free completion", () => {
|
||||
const definitions = walkSources(fileURLToPath(new URL("../src/", import.meta.url))).filter((file) => (
|
||||
readFileSync(file, "utf8").includes("export const RECTIFICATION_OFFER_RULE")
|
||||
@@ -530,7 +641,12 @@ test("the offer rule is defined once, and direct entry settles with the free com
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /不在对话里收集经历做校正/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /explicitRequest=true/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /只写那一句过渡，不写解读/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /只是不认同某个解释，按纠正规则认下、改读，不提校正/);
|
||||
// 原值：规则以「用户说你推得不准时」开头，并写「按纠正规则认下」。
|
||||
// 新值：第一句就写 explicitRequest=true，并改称「改读规则」。全文不含「纠正规则」。
|
||||
// 原因：BUG-1317，「生时纠正」和「纠正解读」撞词，正向句被埋在禁止句中间。
|
||||
assert.match(RECTIFICATION_OFFER_RULE.split("。")[0] ?? "", /explicitRequest=true/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /按改读规则认下、改读，不提校正/);
|
||||
assert.doesNotMatch(RECTIFICATION_OFFER_RULE, /纠正规则/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /userAsked=true/);
|
||||
|
||||
const tools = src("../src/mastra/consultation-tools.ts");
|
||||
|
||||
@@ -117,6 +117,11 @@ test("the server decides whether a card may be shown: self, product on, no case
|
||||
|
||||
function offerTool(options: { alreadyOffered?: boolean; decide?: () => Promise<{ ok: true; creditCost: number; questionEstimate: number } | { ok: false; reason: "not_self" | "product_disabled" | "case_in_progress" | "pricing_unavailable" }> } = {}) {
|
||||
const state = createConsultationRuntimeState();
|
||||
// 原值：建出来还没排盘也能直接提议。
|
||||
// 新值：这些用例表示已经看过盘，所以先标计算完成。
|
||||
// 原因：BUG-1317，还没排盘的顺口提议不算已经提议过。
|
||||
state.consultationToolCompleted = true;
|
||||
state.consultationToolSuccessCount = 1;
|
||||
const tools = createConsultationTools({
|
||||
userId: "user-fictional",
|
||||
sessionId: SOURCE_SESSION,
|
||||
@@ -194,7 +199,10 @@ test("the C2 rule is defined once and reaches first turns, follow-ups and declar
|
||||
assert.ok(followUpAnswerShapeInstruction().includes(RECTIFICATION_OFFER_RULE));
|
||||
const route = readFileSync(new URL("../src/app/api/consult/route.ts", import.meta.url), "utf8");
|
||||
assert.match(route, /这只是粗看。" \+ RECTIFICATION_OFFER_RULE;/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /只是不认同某个解释，按纠正规则认下、改读，不提校正/);
|
||||
// 原值：/按纠正规则认下、改读，不提校正/
|
||||
// 新值：/按改读规则认下、改读，不提校正/
|
||||
// 原因：BUG-1317，避免「生时纠正」被读成「用户在纠正解读」。
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /只是不认同某个解释，按改读规则认下、改读，不提校正/);
|
||||
assert.match(RECTIFICATION_OFFER_RULE, /userAsked=true/);
|
||||
});
|
||||
|
||||
|
||||
Reference in New Issue
Block a user