jesse-ux
8b11ae7dab
BUG-937 撤回 thinking 模式下的 required toolChoice，只留 activeTools。BUG-938 让咨询流识别 Mastra error 块，公开码 calculation_failed，内部码进日志且不触发合同 retry。
261 lines
15 KiB
TypeScript
261 lines
15 KiB
TypeScript
import assert from "node:assert/strict";
|
||
import { readFileSync } from "node:fs";
|
||
import test from "node:test";
|
||
import {
|
||
consultationNatalPrepareStep,
|
||
consultationWindowPrepareStep,
|
||
} from "../src/mastra/consultation-tools.ts";
|
||
|
||
const route = readFileSync(new URL("../src/app/api/consult/route.ts", import.meta.url), "utf8");
|
||
const reportsRoute = readFileSync(new URL("../src/app/api/reports/route.ts", import.meta.url), "utf8");
|
||
const mastra = readFileSync(new URL("../src/mastra/index.ts", import.meta.url), "utf8");
|
||
const tools = readFileSync(new URL("../src/mastra/consultation-tools.ts", import.meta.url), "utf8");
|
||
const stream = readFileSync(new URL("../src/lib/stream-agent-response.ts", import.meta.url), "utf8");
|
||
const workflow = readFileSync(new URL("../src/mastra/consultation-workflow.ts", import.meta.url), "utf8");
|
||
const plan = readFileSync(new URL("../src/lib/consultation-plan.ts", import.meta.url), "utf8");
|
||
const routeService = readFileSync(new URL("../src/lib/consultation-route-service.ts", import.meta.url), "utf8");
|
||
const pythonPlanContract = readFileSync(new URL("../../scripts/consultation_plan_contract.py", import.meta.url), "utf8");
|
||
const stagingCompose = readFileSync(new URL("../../deploy/docker-compose.staging.yml", import.meta.url), "utf8");
|
||
|
||
|
||
|
||
test("natal and window instructions require a chart tool every turn (BUG-922)", () => {
|
||
assert.doesNotMatch(mastra, /follow-ups may use the existing/);
|
||
assert.match(mastra, /Call run-jyotish-consultation before answering every turn/);
|
||
assert.match(mastra, /Call run-jyotish-window-consultation before answering every turn/);
|
||
});
|
||
|
||
test("natal and window first steps require the chart tool (BUG-923)", () => {
|
||
// 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
|
||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 0 }), {
|
||
activeTools: ["run-jyotish-consultation"],
|
||
toolChoice: "auto",
|
||
});
|
||
assert.deepEqual(consultationNatalPrepareStep({ stepNumber: 1 }), {
|
||
toolChoice: "auto",
|
||
});
|
||
assert.deepEqual(consultationWindowPrepareStep({ stepNumber: 0 }), {
|
||
activeTools: ["run-jyotish-window-consultation"],
|
||
toolChoice: "auto",
|
||
});
|
||
assert.deepEqual(consultationWindowPrepareStep({ stepNumber: 1 }), {
|
||
toolChoice: "auto",
|
||
});
|
||
});
|
||
|
||
test("consultation prepareStep never sends required or named toolChoice (BUG-282 / BUG-937)", () => {
|
||
assert.doesNotMatch(tools, /toolChoice:\s*"required"/);
|
||
assert.doesNotMatch(tools, /type:\s*"tool",\s*toolName/);
|
||
});
|
||
|
||
test("consultation plans are server-owned and bounded", () => {
|
||
assert.match(plan, /consultationPlanSchema/);
|
||
assert.match(plan, /requestedDomains/);
|
||
assert.match(plan, /requiredEvidenceCategories/);
|
||
assert.match(plan, /createConsultationPlan/);
|
||
assert.match(tools, /const userIntent = ctx\.plan\?\.userIntent \?\? input\.question/);
|
||
assert.match(tools, /input\.domains === undefined && context\.plan && context\.theme/);
|
||
assert.match(tools, /return \[context\.theme\]/);
|
||
assert.match(tools, /chartCalculationProgressLabel\(index \+ 1, domains\.length\)/);
|
||
assert.match(tools, /phase: "chart-calculation"/);
|
||
assert.match(tools, /userIntent,[\s\S]*theme: domain/);
|
||
assert.match(tools, /question: userIntent,[\s\S]*theme: domain/);
|
||
assert.match(tools, /plan: domainPlan/);
|
||
assert.match(workflow, /packet_version: "consultation-evidence-packet-v2"/);
|
||
assert.match(workflow, /claim_cards/);
|
||
assert.match(tools, /modelOutput: toModelOutput\(agentContext, domainPlan\)/);
|
||
assert.match(tools, /modelOutput: toModelOutput[\s\S]*ctx\.state\.consultationToolCompleted = true/);
|
||
assert.match(plan, /precisionBoundary/);
|
||
assert.match(plan, /consultationPlanMaxCreditCost = 1/);
|
||
const modelToolInput = tools.slice(tools.indexOf("const consultationToolInputSchema"), tools.indexOf("const MAX_RECORDED_STEPS"));
|
||
assert.doesNotMatch(modelToolInput, /birth|latitude|longitude|engine|script|credit/i);
|
||
const prepareCall = route.slice(route.indexOf("prepared = await prepareConsultationRoute"), route.indexOf("const modelSelection"));
|
||
assert.match(prepareCall, /beforeReserve: \(\{ consultationMode \}\) => createConsultationPlan\(\{/);
|
||
assert.ok(prepareCall.indexOf("beforeReserve:") < prepareCall.indexOf("reserve: () => reserveConsultationModel("));
|
||
assert.ok(routeService.indexOf("const preReserveResult = input.beforeReserve") < routeService.indexOf("const reservation = await input.reserve()"));
|
||
assert.match(route, /plan: prepared\.preReserveResult,[\s\S]*theme: consultationTheme/);
|
||
assert.match(route, /runConsultationWorkflow\(toolInput, \{[\s\S]*plan: prepared\.preReserveResult/);
|
||
assert.match(workflow, /plan_version: workflowRequest\.plan_version/);
|
||
assert.match(workflow, /strict_workflow_route: workflowRequest\.strictWorkflowRoute/);
|
||
assert.match(workflow, /required_layers: workflowRequest\.requiredLayers/);
|
||
assert.match(workflow, /claim_boundary: workflowRequest\.claimBoundary/);
|
||
assert.match(workflow, /precision_boundary: workflowRequest\.precision_boundary/);
|
||
assert.match(workflow, /required_evidence_categories: workflowRequest\.required_evidence_categories/);
|
||
assert.match(pythonPlanContract, /PLAN_VERSION = "consultation-plan-v2"/);
|
||
assert.match(pythonPlanContract, /server_allowlist_validated/);
|
||
assert.match(pythonPlanContract, /can_answer_precise_timing": False/);
|
||
});
|
||
|
||
test("the model step budget and the wall-clock budget are declared as one pair", () => {
|
||
// The pair now lives beside the domain cap it funds: the cap is derived from
|
||
// the wall clock, so a change to one that forgets the other is impossible.
|
||
assert.match(tools, /export const AGENT_MAX_STEPS = 8;\nexport const AGENT_TIMEOUT_MS = 110_000;/);
|
||
assert.match(tools, /export const AGENT_SLICE_MAX_STEPS = 1;/);
|
||
assert.match(tools, /MAX_CONSULTATION_DOMAINS = Math\.max\(\s*1,\s*Math\.floor\(CONSULTATION_DOMAIN_WALL_CLOCK_MS \/ CONSULTATION_DOMAIN_DURATION_MS\),\s*\)/);
|
||
assert.doesNotMatch(route, /const AGENT_(MAX_STEPS|TIMEOUT_MS) =/);
|
||
assert.match(route, /maxSteps: AGENT_MAX_STEPS,/);
|
||
assert.match(route, /maxSteps: AGENT_SLICE_MAX_STEPS,/);
|
||
assert.match(route, /AbortSignal\.timeout\(AGENT_TIMEOUT_MS\)/);
|
||
assert.match(route, /createConsultationRuntimeState\(\{ plannedSteps: AGENT_MAX_STEPS \}\)/);
|
||
assert.doesNotMatch(route, /maxSteps: \d/);
|
||
assert.doesNotMatch(route, /AbortSignal\.timeout\(\d/);
|
||
});
|
||
|
||
test("consult streams reserve an answer budget and keep provider thinking on a separate channel", () => {
|
||
const settings = readFileSync(new URL("../src/lib/agent-generation-settings.ts", import.meta.url), "utf8");
|
||
assert.match(settings, /export const AGENT_ANSWER_OUTPUT_TOKENS = 16_384;/);
|
||
assert.match(settings, /export const AGENT_THINKING_OUTPUT_TOKENS = 8_192;/);
|
||
assert.match(settings, /export const AGENT_MAX_OUTPUT_TOKENS = AGENT_ANSWER_OUTPUT_TOKENS;/);
|
||
assert.match(settings, /options\.thinking \?\? "disabled"/);
|
||
assert.match(settings, /agentOutputTokenBudget\(thinkingMode,/);
|
||
assert.match(tools, /function consultationGenerationSettings/);
|
||
assert.match(tools, /return agentGenerationSettings\(model, \{ thinking: "enabled" \}\)/);
|
||
assert.match(tools, /function consultationContinueGenerationSettings/);
|
||
assert.match(tools, /return agentGenerationSettings\(model, \{ thinking: "disabled" \}\)/);
|
||
assert.match(tools, /function consultationSliceGenerationSettings/);
|
||
assert.match(tools, /reasoningEffort: "low"/);
|
||
assert.match(tools, /AGENT_MAX_OUTPUT_TOKENS as CONSULTATION_MAX_OUTPUT_TOKENS/);
|
||
assert.match(route, /\.\.\.consultationGenerationSettings\(selectedModel\.model\)/);
|
||
assert.match(route, /consultationContinueGenerationSettings\(selectedModel\.model\)/);
|
||
assert.match(route, /consultationSliceGenerationSettings\(selectedModel\.model\)/);
|
||
assert.match(route, /composeSection,/);
|
||
assert.doesNotMatch(route, /maxOutputTokens:\s*\d/);
|
||
assert.equal(route.match(/const continueAfterLength = async \(output: string\) => \{/g)?.length, 3);
|
||
assert.equal(route.match(/const composeSection = async \(\s*heading: string,\s*priorOutput: string,\s*reason: "write" \| "empty-retry" = "write",\s*\) => \{/g)?.length, 1);
|
||
assert.match(route, /toolChoice: "none"/);
|
||
assert.match(route, /entrypoint: consultEntrypoint/);
|
||
assert.match(route, /entrypoint: parsed\.data\.entrypoint/);
|
||
assert.match(tools, /export function consultationNatalPrepareStep/);
|
||
assert.match(tools, /export function consultationWindowPrepareStep/);
|
||
assert.match(tools, /activeTools: \[CONSULTATION_NATAL_CALC_TOOL_ID\]/);
|
||
assert.match(tools, /activeTools: \[CONSULTATION_WINDOW_CALC_TOOL_ID\]/);
|
||
const sharedStreamOptions = route.slice(
|
||
route.indexOf("const streamOptions = {"),
|
||
route.indexOf("const natalStreamOptions = {"),
|
||
);
|
||
assert.doesNotMatch(sharedStreamOptions, /prepareStep/);
|
||
assert.match(route, /prepareStep: consultationNatalPrepareStep/);
|
||
assert.match(route, /prepareStep: consultationWindowPrepareStep/);
|
||
assert.match(route, /streamWithOverflowRetry\(agent, natalStreamOptions\)/);
|
||
assert.match(route, /streamWithOverflowRetry\(agent, windowStreamOptions\)/);
|
||
assert.match(
|
||
route,
|
||
/请调用 run-jyotish-window-consultation 完成计算[\s\S]*?windowStreamOptions\)/,
|
||
);
|
||
assert.doesNotMatch(route, /先加载 Jyotish Skill/);
|
||
assert.match(route, /pinsConsultationDomains\(consultEntrypoint\)/);
|
||
assert.match(route, /调用时不要填写 domains，沿用服务器已选定的主题/);
|
||
const natalRetry = route.slice(
|
||
route.indexOf("if (!prepared.serverChart)"),
|
||
route.indexOf("const continueAfterLength = async (output: string) => {", route.indexOf("if (!prepared.serverChart)")),
|
||
);
|
||
assert.match(natalRetry, /], natalStreamOptions\)/);
|
||
assert.doesNotMatch(natalRetry, /], streamOptions\)/);
|
||
const composeBlock = route.slice(
|
||
route.indexOf("const composeSection = async ("),
|
||
route.indexOf("const executionReceipt = (): AgentExecutionReceipt => ({", route.indexOf("const composeSection = async (")),
|
||
);
|
||
assert.match(composeBlock, /\.\.\.streamOptions,/);
|
||
assert.doesNotMatch(composeBlock, /natalStreamOptions/);
|
||
assert.match(stream, /section-empty-retry/);
|
||
assert.match(tools, /dailyConsultationThinkingPlan/);
|
||
assert.match(tools, /pinsConsultationDomains/);
|
||
assert.match(stream, /thinking\.section/);
|
||
assert.match(stream, /thinking\.delta/);
|
||
assert.match(stream, /continueAfterLength/);
|
||
assert.match(stream, /composeSection/);
|
||
assert.match(stream, /drainSpoken/);
|
||
assert.match(stream, /answer-continue/);
|
||
});
|
||
|
||
test("uses one runtime step append entry and no scattered hard-coded step cap", () => {
|
||
assert.match(tools, /export function appendConsultationRuntimeStep/);
|
||
assert.doesNotMatch(tools, /steps\.length\s*>=\s*32/);
|
||
assert.doesNotMatch(stream, /state\.steps\.push/);
|
||
assert.doesNotMatch(stream, /steps\.length\s*<\s*32/);
|
||
});
|
||
|
||
test("personal consultation lets the Agent invoke the server-bound workflow tool", () => {
|
||
const agenticStart = route.indexOf("async function runAgenticConsultation");
|
||
const agenticBranch = route.slice(
|
||
agenticStart,
|
||
// Former value: `const { history } = parsed.data;` ended the agentic function.
|
||
// History now comes from stored session messages, not the client field.
|
||
route.indexOf(" const history = storedHistory;", agenticStart),
|
||
);
|
||
assert.match(agenticBranch, /createConsultationAgentContext/);
|
||
assert.match(agenticBranch, /getJyotishAgent\(selectedModel, agentContext\)/);
|
||
assert.doesNotMatch(agenticBranch, /await runConsultationWorkflow/);
|
||
assert.doesNotMatch(agenticBranch, /JSON\.stringify\(toolInput\)/);
|
||
assert.match(tools, /\(ctx\.runWorkflow \?\? runConsultationWorkflow\)\(toolInput, \{/);
|
||
assert.match(tools, /return \{ "run-jyotish-consultation": consultationTool \};/);
|
||
assert.match(agenticBranch, /state\.workflowReceipt\?\.preciseTiming === "allowed"/);
|
||
assert.match(route, /createConsultationReplyMetadata/);
|
||
});
|
||
|
||
test("defers optional external evidence only for foreground chat", () => {
|
||
assert.match(workflow, /defer_optional_external_evidence: options\?\.foreground === true/);
|
||
assert.match(reportsRoute, /runWorkflow: \(input\) => runConsultationWorkflow\(input\)/);
|
||
assert.doesNotMatch(reportsRoute, /foreground:\s*true/);
|
||
});
|
||
|
||
test("personal Agent owns the Skill and context-bound calculation tool", () => {
|
||
const personalFactory = mastra.slice(
|
||
mastra.indexOf("export function getJyotishAgent"),
|
||
mastra.indexOf("export function getLegacyJyotishAgent"),
|
||
);
|
||
assert.match(personalFactory, /getJyotishAgent\(model: ResolvedLanguageModel, context: ConsultationAgentContext\)/);
|
||
assert.match(personalFactory, /\.\.\.jyotishSkillBinding\(\)/);
|
||
assert.match(personalFactory, /tools: createConsultationTools\(context\)/);
|
||
assert.doesNotMatch(personalFactory, /server-computed-jyotish-workflow/);
|
||
});
|
||
|
||
test("validates and emits non-sensitive workflow and execution receipts", () => {
|
||
assert.match(workflow, /consultationWorkflowResponseSchema/);
|
||
assert.match(workflow, /safeParse\(data\)/);
|
||
assert.match(workflow, /consultationWorkflowReceipt/);
|
||
assert.match(route, /agentExecutionReceipt/);
|
||
assert.match(route, /streamAgentResponse/);
|
||
});
|
||
|
||
test("consultationWorkflowResponseSchema still parses without western_evidence_packet", () => {
|
||
const schema = workflow.slice(
|
||
workflow.indexOf("export const consultationWorkflowResponseSchema"),
|
||
workflow.indexOf("function record("),
|
||
);
|
||
assert.match(schema, /success: z\.boolean\(\)/);
|
||
assert.match(schema, /chart: z\.record\(z\.unknown\(\)\)/);
|
||
assert.match(schema, /routing: z\.record\(z\.unknown\(\)\)/);
|
||
assert.match(schema, /consumer_context:/);
|
||
assert.match(schema, /\)\.passthrough\(\);/);
|
||
assert.doesNotMatch(schema, /western_evidence_packet/);
|
||
});
|
||
|
||
test("carries commercial technique truth into the model contract", () => {
|
||
assert.match(workflow, /technique_truth/);
|
||
assert.match(mastra, /deterministic_claims_forbidden_for/);
|
||
assert.doesNotMatch(mastra, /AYANAM_SUGGESTIONS|AYANAM_TITLE/);
|
||
assert.doesNotMatch(mastra, /2-5 short paragraphs/);
|
||
assert.match(mastra, /reference_only/);
|
||
assert.match(mastra, /Do not use a restricted technique/);
|
||
});
|
||
|
||
test("projects consultation themes through explicit strict workflow taxonomy", () => {
|
||
const projection = readFileSync(new URL("../src/lib/consultation-workflow-request.ts", import.meta.url), "utf8");
|
||
const registry = readFileSync(new URL("../src/lib/consultation-domain-registry.ts", import.meta.url), "utf8");
|
||
assert.match(projection, /consultationDomainDefinition/);
|
||
assert.match(registry, /strictWorkflowRoute/);
|
||
assert.match(registry, /claimBoundary/);
|
||
assert.match(registry, /requiredLayers/);
|
||
assert.match(registry, /negative holdout gate/);
|
||
});
|
||
|
||
|
||
test("agentic consultation is the safe default and legacy is explicit rollback", () => {
|
||
assert.match(stagingCompose, /CONSULTATION_AGENTIC_RUNTIME: enabled/);
|
||
assert.match(route, /CONSULTATION_AGENTIC_RUNTIME\?\.trim\(\)\.toLowerCase\(\) \?\? "enabled"/);
|
||
assert.match(route, /mode === "legacy"/);
|
||
assert.match(route, /mode !== "canary"/);
|
||
});
|