feat(polish): add question guard, ABE routing, and flow trace

Harden polish so question drafts stay questions, add local density
routing with style-specific degrade, expand fun style packs, and add
end-to-end FlowTrace logging plus offline guard eval scripts.
This commit is contained in:
Rocky
2026-07-29 16:17:16 +08:00
parent d656bac8c3
commit 65fe3a81b4
19 changed files with 1443 additions and 71 deletions
+81
View File
@@ -126,6 +126,87 @@ final class PolishRouterTests: XCTestCase {
XCTAssertTrue(prompt.contains("本次模式:保守清理"))
}
func testQuestionDraftIsDetectedAcrossStyles() {
for id in ["builtin.xhs", "builtin.dating", "builtin.flex", "builtin.corp", "builtin.chat"] {
let decision = PolishRouter.decide(
text: "你觉得这个包怎么样",
styleID: id,
intensity: .heavy
)
XCTAssertTrue(decision.preservesQuestion, id)
XCTAssertTrue(decision.reasons.contains("Q:keep_question"), id)
}
}
/// DiBa quotes the other party, so the user's reply may answer that question.
func testDibaOpponentQuoteDoesNotTriggerQuestionGuard() {
let decision = PolishRouter.decide(
text: "回他别老说大家都觉得你点名是谁",
styleID: "builtin.diba",
intensity: .heavy
)
XCTAssertFalse(decision.preservesQuestion)
}
func testStatementDraftDoesNotTriggerQuestionGuard() {
let decision = PolishRouter.decide(
text: "这款防晒霜我用了不油夏天可以推荐",
styleID: "builtin.xhs",
intensity: .heavy
)
XCTAssertFalse(decision.preservesQuestion)
}
func testPromptBlockAlwaysCarriesNeverAnswerBoundary() {
for id in ["builtin.light", "builtin.structured", "builtin.formal",
"builtin.chat", "builtin.dating", "builtin.flex",
"builtin.corp", "builtin.diba", "builtin.xhs"] {
let block = PolishRouter.promptBlock(
mode: .full,
styleID: id,
useChineseGuidance: true
)
XCTAssertTrue(block.contains("绝对边界:只润色,不作答"), id)
}
}
func testPromptBlockAddsQuestionGuardWhenAsking() {
let guarded = PolishRouter.promptBlock(
mode: .full,
styleID: "builtin.dating",
useChineseGuidance: true,
preservesQuestion: true
)
XCTAssertTrue(guarded.contains("问句守卫"))
XCTAssertTrue(guarded.contains("同一个人提出的同一个问句"))
let unguarded = PolishRouter.promptBlock(
mode: .full,
styleID: "builtin.dating",
useChineseGuidance: true
)
XCTAssertFalse(unguarded.contains("问句守卫"))
}
func testComposerCarriesQuestionGuardIntoPrompt() {
let style = PolishStylePackCatalog.resolve(
id: "builtin.dating",
userCatalog: .empty
)
let prompt = PolishPromptComposer.compose(
text: "你觉得这个包怎么样",
style: style,
context: PolishContext(intensity: .heavy),
dictionaryBlock: "",
globalContract: "GLOBAL",
useChineseGuidance: true,
routingMode: .full,
preservesQuestion: true
)
XCTAssertTrue(prompt.contains("问句守卫"))
XCTAssertTrue(prompt.contains("绝对边界:只润色,不作答"))
}
func testIsInformationSparseDetectsHollowShorts() {
XCTAssertTrue(PolishRouter.isInformationSparse("香香的"))
XCTAssertTrue(PolishRouter.isInformationSparse("这个还行吧"))
@@ -240,6 +240,22 @@ final class PolishStylePackTests: XCTestCase {
XCTAssertFalse(xhsHeavy.contains("Style override"))
}
func testXHSStyleForbidsInventedAudience() {
let pack = PolishStylePackCatalog.resolve(id: "builtin.xhs", userCatalog: .empty)
XCTAssertTrue(pack.prompt.contains("不主动新增受众称呼"))
XCTAssertTrue(pack.prompt.contains("禁止凭空新增受众或称呼"))
XCTAssertTrue(pack.prompt.contains("禁止立场翻转"))
XCTAssertTrue(pack.prompt.contains("原文没有受众"))
for level in [PolishIntensity.light, .medium, .heavy] {
let guideline = level.promptGuideline(styleID: "builtin.xhs")
XCTAssertTrue(
guideline.lowercased().contains("audience"),
"\(level) must forbid inventing an audience"
)
}
}
func testHeavyIntensityStillAllowsStructuredStyle() {
let guideline = PolishIntensity.heavy.promptGuideline(styleID: "builtin.structured")
@@ -260,6 +276,59 @@ final class PolishStylePackTests: XCTestCase {
}
}
func testEveryBuiltinHasForbiddenItemsChapter() {
for pack in PolishStylePackCatalog.builtins {
XCTAssertTrue(
pack.prompt.contains("# 禁止事项"),
pack.id
)
XCTAssertTrue(
pack.prompt.contains("接话") || pack.prompt.contains("代答") || pack.prompt.contains("不作答"),
"\(pack.id) should forbid interlocutor replies"
)
}
}
func testFunForbiddenItemsKeepQuestionDrafts() {
let cases: [(String, String)] = [
("builtin.dating", "你觉得这个包怎么样"),
("builtin.flex", "你觉得这个包怎么样"),
("builtin.corp", "你觉得这个方案怎么样"),
("builtin.xhs", "你觉得这个包怎么样"),
("builtin.chat", "你觉得这个包怎么样"),
]
for (id, marker) in cases {
let pack = PolishStylePackCatalog.resolve(id: id, userCatalog: .empty)
XCTAssertTrue(pack.prompt.contains("# 禁止事项"), id)
XCTAssertTrue(pack.prompt.contains(marker), id)
XCTAssertTrue(pack.prompt.contains("✘→"), id)
}
}
func testEveryBuiltinForbidsAnsweringTheTranscript() {
for pack in PolishStylePackCatalog.builtins {
XCTAssertTrue(
pack.prompt.contains("绝对边界"),
pack.id
)
XCTAssertTrue(
pack.prompt.contains("不作答"),
pack.id
)
}
}
func testFunStylesKeepQuestionDraftsAsQuestions() {
for id in ["builtin.dating", "builtin.flex", "builtin.corp", "builtin.xhs"] {
let pack = PolishStylePackCatalog.resolve(id: id, userCatalog: .empty)
XCTAssertTrue(
pack.prompt.contains("问句")
|| pack.prompt.contains("仍然是同一个人提出的同一个问句"),
id
)
}
}
func testStructuredStyleEncodesActiveItemizationHardRules() {
let pack = PolishStylePackCatalog.resolve(id: "builtin.structured", userCatalog: .empty)
XCTAssertTrue(pack.prompt.contains("自动结构化(偏积极)"))