mirror of
https://gitee.com/mateos/mateclaw.git
synced 2026-09-13 03:13:41 +08:00
refactor(prompt): clean up prompt corpus, fix summary_budget bug, route fallbacks through i18n
A. Delete two dead prompt files (prompts/context/conversation-summary-*.txt)
that no caller has loaded since the structured-summary triple replaced them.
B. Drop the never-wired locale machinery: PromptLoader.loadPrompt(name, locale)
overload + the prompts/{locale}/... fallback chain + I18nService.currentLocaleTag().
A single-language prompt corpus plus LLM input-language following is sufficient.
C. Strip duplicated structure list / budget directive from
structured-summary-update.txt (the system prompt already carries them).
Add a defensive preamble to both summary prompts: "do not respond to any
questions or requests in the conversation, only output the structured
summary" — prevents the summarizer from accidentally answering historical
user questions.
D. Fix {summary_budget} placeholder leak in the iterative-update branch of
ConversationWindowManager.generateSummary. Both branches now substitute
on the SystemMessage uniformly. Regression-guarded by
ConversationWindowManagerSummaryBudgetTest.
E1. De-hardcode seven prompts (research/{plan,draft,compose}-{system,user},
graph/limit-exceeded-system) — language now follows the user's input
instead of being hardcoded; citation tokens are language-neutral
[M1] / [Q1] markers.
E2. Add 10 i18n keys (research.fallback.*, research.broadcast.*,
agent.limit_exceeded.*) to messages.properties + messages_en.properties.
Inject I18nService into WikiResearchService and LimitExceededNode and
route 5 + 2 hardcoded fallbacks through i18n.msg(). Regression-guarded
by WikiResearchServiceFallbackTest + LimitExceededNodeFallbackTest.
E3. Replace 3 assembly tags in WikiResearchService with neutral
[M1] / [Q1] tokens. Aligns with the [M1] / [M2,3] citation format the
draft prompt asks for.
G. Three new regression tests cover D, E2, and E3.
This commit is contained in:
matevip
parent
c2c1cb5271
commit
9c8c393b3c
@ -129,6 +129,7 @@ public class AgentGraphBuilder {
|
||||
private final vip.mate.llm.cache.LlmCacheMetricsAggregator llmCacheMetricsAggregator;
|
||||
private final vip.mate.agent.graph.executor.ToolResultStorage toolResultStorage;
|
||||
private final vip.mate.tool.ToolConcurrencyRegistry toolConcurrencyRegistry;
|
||||
private final vip.mate.i18n.I18nService i18nService;
|
||||
|
||||
/**
|
||||
* 根据 AgentEntity 构建完整的 Agent 实例
|
||||
@ -354,7 +355,7 @@ public class AgentGraphBuilder {
|
||||
ObservationProcessor observationProcessor = new ObservationProcessor(graphObservationProperties);
|
||||
ObservationNode observationNode = new ObservationNode(observationProcessor, streamTracker);
|
||||
SummarizingNode summarizingNode = new SummarizingNode(chatModel, streamingHelper, streamTracker);
|
||||
LimitExceededNode limitExceededNode = new LimitExceededNode(chatModel, observationProcessor, streamingHelper);
|
||||
LimitExceededNode limitExceededNode = new LimitExceededNode(chatModel, observationProcessor, streamingHelper, i18nService);
|
||||
FinalAnswerNode finalAnswerNode = new FinalAnswerNode();
|
||||
|
||||
KeyStrategyFactory keyStrategyFactory = KeyStrategy.builder()
|
||||
|
||||
@ -435,19 +435,20 @@ public class ConversationWindowManager {
|
||||
String systemPrompt;
|
||||
String userPrompt;
|
||||
|
||||
// System prompt always carries the budget directive; both branches
|
||||
// must replace the placeholder. The previous code applied the
|
||||
// replace only on the first-compression branch, so iterative-mode
|
||||
// calls leaked the literal "{summary_budget}" string to the LLM.
|
||||
systemPrompt = STRUCTURED_SUMMARY_SYSTEM
|
||||
.replace("{summary_budget}", String.valueOf(summaryBudget));
|
||||
if (previousSummary != null) {
|
||||
// 迭代更新模式：旧摘要 + 新轮次
|
||||
systemPrompt = STRUCTURED_SUMMARY_SYSTEM;
|
||||
// Iterative update: previous summary + new turns.
|
||||
userPrompt = STRUCTURED_SUMMARY_UPDATE
|
||||
.replace("{previous_summary}", previousSummary)
|
||||
.replace("{conversation}", conversationText)
|
||||
.replace("{summary_budget}", String.valueOf(summaryBudget));
|
||||
.replace("{conversation}", conversationText);
|
||||
log.debug("[ConversationWindow] 使用迭代更新模式（第 {} 次压缩）, conv={}",
|
||||
compressionCounts.getOrDefault(conversationId, 0) + 1, conversationId);
|
||||
} else {
|
||||
// 首次压缩
|
||||
systemPrompt = STRUCTURED_SUMMARY_SYSTEM
|
||||
.replace("{summary_budget}", String.valueOf(summaryBudget));
|
||||
userPrompt = STRUCTURED_SUMMARY_USER
|
||||
.replace("{conversation}", conversationText);
|
||||
log.debug("[ConversationWindow] 使用首次压缩模式, conv={}", conversationId);
|
||||
|
||||
@ -13,6 +13,7 @@ import vip.mate.agent.graph.observation.ObservationProcessor;
|
||||
import vip.mate.agent.graph.state.FinishReason;
|
||||
import vip.mate.agent.graph.state.MateClawStateAccessor;
|
||||
import vip.mate.agent.prompt.PromptLoader;
|
||||
import vip.mate.i18n.I18nService;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
@ -44,20 +45,28 @@ public class LimitExceededNode implements NodeAction {
|
||||
private final ChatModel chatModel;
|
||||
private final ObservationProcessor observationProcessor;
|
||||
private final NodeStreamingChatHelper streamingHelper;
|
||||
/** Optional i18n service; nullable so legacy/tests without Spring context still work. */
|
||||
private final I18nService i18n;
|
||||
|
||||
public LimitExceededNode(ChatModel chatModel, ObservationProcessor observationProcessor,
|
||||
NodeStreamingChatHelper streamingHelper) {
|
||||
this(chatModel, observationProcessor, streamingHelper, null);
|
||||
}
|
||||
|
||||
public LimitExceededNode(ChatModel chatModel, ObservationProcessor observationProcessor,
|
||||
NodeStreamingChatHelper streamingHelper, I18nService i18n) {
|
||||
this.chatModel = chatModel;
|
||||
this.observationProcessor = observationProcessor;
|
||||
this.streamingHelper = streamingHelper;
|
||||
this.i18n = i18n;
|
||||
}
|
||||
|
||||
/**
|
||||
* @deprecated Use constructor with NodeStreamingChatHelper
|
||||
* @deprecated use the constructor with {@link NodeStreamingChatHelper} (and optionally {@link I18nService})
|
||||
*/
|
||||
@Deprecated
|
||||
public LimitExceededNode(ChatModel chatModel, ObservationProcessor observationProcessor) {
|
||||
this(chatModel, observationProcessor, null);
|
||||
this(chatModel, observationProcessor, null, null);
|
||||
}
|
||||
|
||||
@Override
|
||||
@ -88,7 +97,7 @@ public class LimitExceededNode implements NodeAction {
|
||||
contextForLLM = observationProcessor.truncate(sb.toString(),
|
||||
observationProcessor.getMaxTotalObservationChars());
|
||||
} else {
|
||||
contextForLLM = "（尚未收集到工具调用结果）";
|
||||
contextForLLM = i18n != null ? i18n.msg("agent.limit_exceeded.empty_context") : "(no tool results)";
|
||||
}
|
||||
|
||||
// 构建 prompt
|
||||
@ -110,8 +119,11 @@ public class LimitExceededNode implements NodeAction {
|
||||
log.info("[LimitExceededNode] Generated limit-exceeded final answer: {} chars",
|
||||
finalDraft != null ? finalDraft.length() : 0);
|
||||
|
||||
String fallbackMsg = i18n != null
|
||||
? i18n.msg("agent.limit_exceeded.fallback")
|
||||
: "Sorry, the maximum reasoning steps were reached.";
|
||||
return MateClawStateAccessor.output()
|
||||
.finalAnswerDraft(finalDraft != null ? finalDraft : "抱歉，已达到最大推理步数，未能获得完整结果。")
|
||||
.finalAnswerDraft(finalDraft != null ? finalDraft : fallbackMsg)
|
||||
.currentThinking(result.thinking())
|
||||
.limitExceeded(true)
|
||||
.contentStreamed(true)
|
||||
|
||||
@ -9,14 +9,14 @@ import java.nio.charset.StandardCharsets;
|
||||
import java.util.concurrent.ConcurrentHashMap;
|
||||
|
||||
/**
|
||||
* Prompt 文件加载器
|
||||
* <p>
|
||||
* 从 classpath:/prompts/ 目录加载 .txt 文件，使用 ConcurrentHashMap 做线程安全的懒加载缓存。
|
||||
* <p>
|
||||
* 未来扩展点：可在 loadPrompt() 中增加"先查数据库覆盖 → 再读 resource → 最后代码兜底"的优先级链，
|
||||
* 但本次只实现 resource 读取。
|
||||
* Loads prompt text files from {@code classpath:/prompts/} with a thread-safe
|
||||
* lazy cache.
|
||||
*
|
||||
* @author MateClaw Team
|
||||
* <p>Single-language by design: prompts are written in the system's default
|
||||
* language and the LLM is trusted to follow the user's input language for
|
||||
* its output. The previous {@code loadPrompt(name, locale)} overload and
|
||||
* {@code prompts/{locale}/...} fallback chain were never wired up by any
|
||||
* caller and have been removed.</p>
|
||||
*/
|
||||
@Slf4j
|
||||
public final class PromptLoader {
|
||||
@ -28,44 +28,19 @@ public final class PromptLoader {
|
||||
private PromptLoader() {}
|
||||
|
||||
/**
|
||||
* 加载 prompt 文件内容（默认语言）
|
||||
* Load a prompt file's contents.
|
||||
*
|
||||
* @param promptName 文件名（不含路径前缀和 .txt 后缀），例如 "graph/summarize-system"
|
||||
* @return 文件文本内容
|
||||
* @throws RuntimeException 文件不存在或读取失败时抛出，不会静默返回空字符串
|
||||
* @param promptName file name without the {@code prompts/} prefix or {@code .txt} suffix
|
||||
* (e.g. {@code "graph/summarize-system"})
|
||||
* @return file text content
|
||||
* @throws RuntimeException when the file is missing or unreadable; the loader never
|
||||
* silently returns an empty string
|
||||
*/
|
||||
public static String loadPrompt(String promptName) {
|
||||
return promptCache.computeIfAbsent(promptName, name -> readPromptFile(name, null));
|
||||
return promptCache.computeIfAbsent(promptName, PromptLoader::readPromptFile);
|
||||
}
|
||||
|
||||
/**
|
||||
* 加载指定语言的 prompt 文件内容
|
||||
* <p>
|
||||
* 查找顺序：{@code prompts/{locale}/{name}.txt} → {@code prompts/{name}.txt}
|
||||
*
|
||||
* @param promptName 文件名（不含路径前缀和 .txt 后缀）
|
||||
* @param locale 语言标识（如 "en"、"zh"），为 null 或 "zh" 时使用默认文件
|
||||
* @return 文件文本内容
|
||||
*/
|
||||
public static String loadPrompt(String promptName, String locale) {
|
||||
if (locale == null || locale.isBlank() || "zh".equals(locale)) {
|
||||
return loadPrompt(promptName);
|
||||
}
|
||||
String cacheKey = locale + ":" + promptName;
|
||||
return promptCache.computeIfAbsent(cacheKey, key -> readPromptFile(promptName, locale));
|
||||
}
|
||||
|
||||
private static String readPromptFile(String name, String locale) {
|
||||
// 优先尝试 locale 目录
|
||||
if (locale != null && !locale.isBlank()) {
|
||||
String localeFileName = PROMPT_PATH_PREFIX + locale + "/" + name + ".txt";
|
||||
try (InputStream is = PromptLoader.class.getClassLoader().getResourceAsStream(localeFileName)) {
|
||||
if (is != null) {
|
||||
return StreamUtils.copyToString(is, StandardCharsets.UTF_8);
|
||||
}
|
||||
} catch (IOException ignored) {}
|
||||
}
|
||||
// 回退到默认目录
|
||||
private static String readPromptFile(String name) {
|
||||
String fileName = PROMPT_PATH_PREFIX + name + ".txt";
|
||||
try (InputStream inputStream = PromptLoader.class.getClassLoader().getResourceAsStream(fileName)) {
|
||||
if (inputStream == null) {
|
||||
@ -78,18 +53,12 @@ public final class PromptLoader {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 清空缓存
|
||||
*/
|
||||
/** Drop the entire cache. Useful for tests and hot-reload tooling. */
|
||||
public static void clearCache() {
|
||||
promptCache.clear();
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取缓存大小
|
||||
*
|
||||
* @return 已缓存的 prompt 数量
|
||||
*/
|
||||
/** Number of prompts currently cached. */
|
||||
public static int getCacheSize() {
|
||||
return promptCache.size();
|
||||
}
|
||||
|
||||
@ -46,17 +46,8 @@ public class I18nService {
|
||||
}
|
||||
|
||||
/**
|
||||
* 获取当前语言的 locale 标识（用于 PromptLoader 等需要 locale 字符串的场景）
|
||||
*
|
||||
* @return "zh" 或 "en"
|
||||
*/
|
||||
public String currentLocaleTag() {
|
||||
String lang = settingService.getLanguage();
|
||||
return lang.startsWith("en") ? "en" : "zh";
|
||||
}
|
||||
|
||||
/**
|
||||
* 清除缓存的 Locale（语言切换时调用）
|
||||
* Clear the cached Locale. Call after a language switch so that the next
|
||||
* {@link #msg(String, Object...)} call re-reads {@code SystemSettingService.getLanguage()}.
|
||||
*/
|
||||
public void clearLocaleCache() {
|
||||
cachedLocale = null;
|
||||
|
||||
@ -15,6 +15,7 @@ import org.springframework.stereotype.Service;
|
||||
import vip.mate.agent.AgentGraphBuilder;
|
||||
import vip.mate.agent.prompt.PromptLoader;
|
||||
import vip.mate.channel.web.ChatStreamTracker;
|
||||
import vip.mate.i18n.I18nService;
|
||||
import vip.mate.llm.model.ModelConfigEntity;
|
||||
import vip.mate.llm.service.ModelConfigService;
|
||||
import vip.mate.wiki.model.WikiRawMaterialEntity;
|
||||
@ -50,6 +51,7 @@ public class WikiResearchService {
|
||||
private final ModelConfigService modelConfigService;
|
||||
private final AgentGraphBuilder agentGraphBuilder;
|
||||
private final ChatStreamTracker streamTracker;
|
||||
private final I18nService i18n;
|
||||
|
||||
private static final RetryTemplate NO_RETRY = RetryTemplate.builder().maxAttempts(1).build();
|
||||
private static final ExecutorService EXECUTOR = Executors.newVirtualThreadPerTaskExecutor();
|
||||
@ -73,8 +75,8 @@ public class WikiResearchService {
|
||||
// Stage 1: Plan
|
||||
List<SubQuestion> questions = planStage(topic);
|
||||
if (questions.isEmpty()) {
|
||||
broadcast(sessionId, "research.error", Map.of("message", "主题无法分解为可研究的子问题"));
|
||||
return new ResearchResult(topic, List.of(), "无法为该主题生成研究计划。");
|
||||
broadcast(sessionId, "research.error", Map.of("message", i18n.msg("research.broadcast.no_plan")));
|
||||
return new ResearchResult(topic, List.of(), i18n.msg("research.fallback.no_plan"));
|
||||
}
|
||||
broadcast(sessionId, "research.plan", Map.of(
|
||||
"questions", questions.stream().map(q -> Map.of("question", q.question, "intent", q.intent)).toList()
|
||||
@ -83,8 +85,8 @@ public class WikiResearchService {
|
||||
// Stage 2: Retrieve + Draft (并行)
|
||||
List<Section> sections = draftStage(kbId, questions, topK, sessionId);
|
||||
if (sections.stream().allMatch(s -> s.content == null || s.content.isBlank())) {
|
||||
broadcast(sessionId, "research.error", Map.of("message", "所有子问题都未能起草出内容"));
|
||||
return new ResearchResult(topic, sections, "没有足够的材料回答该主题。");
|
||||
broadcast(sessionId, "research.error", Map.of("message", i18n.msg("research.broadcast.draft_all_empty")));
|
||||
return new ResearchResult(topic, sections, i18n.msg("research.fallback.no_materials"));
|
||||
}
|
||||
|
||||
// Stage 3: Compose
|
||||
@ -97,8 +99,8 @@ public class WikiResearchService {
|
||||
return new ResearchResult(topic, sections, report);
|
||||
} catch (Exception e) {
|
||||
log.error("[Research] Failed: kbId={}, topic={}: {}", kbId, topic, e.getMessage(), e);
|
||||
broadcast(sessionId, "research.error", Map.of("message", e.getMessage() != null ? e.getMessage() : "研究失败"));
|
||||
return new ResearchResult(topic, List.of(), "研究过程失败: " + e.getMessage());
|
||||
broadcast(sessionId, "research.error", Map.of("message", e.getMessage() != null ? e.getMessage() : i18n.msg("research.broadcast.failed")));
|
||||
return new ResearchResult(topic, List.of(), i18n.msg("research.fallback.failed", e.getMessage()));
|
||||
}
|
||||
}
|
||||
|
||||
@ -174,10 +176,13 @@ public class WikiResearchService {
|
||||
List<HybridRetriever.ChunkHit> hits = hybridRetriever.searchChunks(kbId, q.question, topK);
|
||||
|
||||
if (hits.isEmpty()) {
|
||||
return new Section(q.question, "现有材料中未找到与该问题相关的内容。", List.of());
|
||||
return new Section(q.question, i18n.msg("research.fallback.no_materials_for_question"), List.of());
|
||||
}
|
||||
|
||||
// 装配材料文本（带编号）
|
||||
// Assemble material snippets with neutral [M1]/[M2]... markers so the
|
||||
// LLM is not biased toward any output language. The same `[Mn]` token
|
||||
// is the citation format the draft prompt asks for, so the model can
|
||||
// refer to materials without translation.
|
||||
StringBuilder materials = new StringBuilder();
|
||||
List<MaterialRef> refs = new ArrayList<>();
|
||||
Map<Long, String> rawTitleCache = new HashMap<>();
|
||||
@ -188,8 +193,7 @@ public class WikiResearchService {
|
||||
WikiRawMaterialEntity raw = rawService.getById(id);
|
||||
return raw != null ? raw.getTitle() : "unknown";
|
||||
});
|
||||
materials.append("### 材料 ").append(i + 1)
|
||||
.append("（来自《").append(rawTitle).append("》）\n")
|
||||
materials.append("### [M").append(i + 1).append("] Source: ").append(rawTitle).append("\n")
|
||||
.append(hit.snippet())
|
||||
.append("\n\n");
|
||||
refs.add(new MaterialRef(i + 1, hit.chunkId(), hit.rawId(), rawTitle));
|
||||
@ -203,7 +207,7 @@ public class WikiResearchService {
|
||||
|
||||
String content = callLlm(systemPrompt, userPrompt, "draft: " + q.question);
|
||||
if (content == null || content.isBlank()) {
|
||||
content = "现有材料不足以回答该子问题。";
|
||||
content = i18n.msg("research.fallback.draft_empty");
|
||||
}
|
||||
|
||||
return new Section(q.question, content, refs);
|
||||
@ -217,7 +221,9 @@ public class WikiResearchService {
|
||||
|
||||
for (int i = 0; i < sections.size(); i++) {
|
||||
Section s = sections.get(i);
|
||||
sectionsText.append("### 子问题 ").append(i + 1).append("：").append(s.question).append("\n");
|
||||
// Use neutral [Q1]/[Q2] tokens — keeps prompt and (in compose-failure
|
||||
// fallback) the report itself language-independent.
|
||||
sectionsText.append("### [Q").append(i + 1).append("] ").append(s.question).append("\n");
|
||||
sectionsText.append(s.content).append("\n\n");
|
||||
for (MaterialRef ref : s.materialRefs) {
|
||||
usedMaterials.putIfAbsent(ref.index, ref.rawTitle);
|
||||
@ -226,7 +232,7 @@ public class WikiResearchService {
|
||||
|
||||
StringBuilder materialsRef = new StringBuilder();
|
||||
usedMaterials.forEach((idx, title) ->
|
||||
materialsRef.append("- 材料 ").append(idx).append("：").append(title).append("\n"));
|
||||
materialsRef.append("- [M").append(idx).append("] ").append(title).append("\n"));
|
||||
|
||||
String systemPrompt = PromptLoader.loadPrompt("research/compose-system");
|
||||
String userPrompt = PromptLoader.loadPrompt("research/compose-user")
|
||||
|
||||
@ -241,3 +241,17 @@ guard.path.symlink_escape=\u8def\u5f84\u901a\u8fc7\u7b26\u53f7\u94fe\u63a5\u9003
|
||||
context.current_time=[system-context] \u5f53\u524d\u65f6\u95f4: {0} {1} (Asia/Shanghai)
|
||||
context.working_dir=[system-context] \u5de5\u4f5c\u76ee\u5f55: {0}
|
||||
context.working_dir_hint=\u4f60\u53ea\u80fd\u5728\u6b64\u76ee\u5f55\u53ca\u5176\u5b50\u76ee\u5f55\u5185\u8bfb\u5199\u6587\u4ef6\u548c\u6267\u884c\u547d\u4ee4\u3002
|
||||
|
||||
# --- Wiki Research Fallback (RFC: prompt-cleanup) ---
|
||||
research.fallback.no_plan=\u65e0\u6cd5\u4e3a\u8be5\u4e3b\u9898\u751f\u6210\u7814\u7a76\u8ba1\u5212\u3002
|
||||
research.fallback.no_materials=\u6ca1\u6709\u8db3\u591f\u7684\u6750\u6599\u56de\u7b54\u8be5\u4e3b\u9898\u3002
|
||||
research.fallback.no_materials_for_question=\u73b0\u6709\u6750\u6599\u4e2d\u672a\u627e\u5230\u4e0e\u8be5\u95ee\u9898\u76f8\u5173\u7684\u5185\u5bb9\u3002
|
||||
research.fallback.draft_empty=\u73b0\u6709\u6750\u6599\u4e0d\u8db3\u4ee5\u56de\u7b54\u8be5\u5b50\u95ee\u9898\u3002
|
||||
research.fallback.failed=\u7814\u7a76\u8fc7\u7a0b\u5931\u8d25: {0}
|
||||
research.broadcast.no_plan=\u4e3b\u9898\u65e0\u6cd5\u5206\u89e3\u4e3a\u53ef\u7814\u7a76\u7684\u5b50\u95ee\u9898
|
||||
research.broadcast.draft_all_empty=\u6240\u6709\u5b50\u95ee\u9898\u90fd\u672a\u80fd\u8d77\u8349\u51fa\u5185\u5bb9
|
||||
research.broadcast.failed=\u7814\u7a76\u5931\u8d25
|
||||
|
||||
# --- Agent Limit Exceeded Fallback (RFC: prompt-cleanup) ---
|
||||
agent.limit_exceeded.fallback=\u62b1\u6b49\uff0c\u5df2\u8fbe\u5230\u6700\u5927\u63a8\u7406\u6b65\u6570\uff0c\u672a\u80fd\u83b7\u5f97\u5b8c\u6574\u7ed3\u679c\u3002
|
||||
agent.limit_exceeded.empty_context=\uff08\u5c1a\u672a\u6536\u96c6\u5230\u5de5\u5177\u8c03\u7528\u7ed3\u679c\uff09
|
||||
|
||||
@ -249,3 +249,17 @@ err.approval.not_found=Approval record not found or expired
|
||||
context.current_time=[system-context] Current time: {0} {1} (Asia/Shanghai)
|
||||
context.working_dir=[system-context] Working directory: {0}
|
||||
context.working_dir_hint=You can only read/write files and execute commands within this directory and its subdirectories.
|
||||
|
||||
# --- Wiki Research Fallback (RFC: prompt-cleanup) ---
|
||||
research.fallback.no_plan=Unable to generate a research plan for this topic.
|
||||
research.fallback.no_materials=Not enough material to answer this topic.
|
||||
research.fallback.no_materials_for_question=No relevant material was found in the knowledge base for this question.
|
||||
research.fallback.draft_empty=Insufficient material to answer this sub-question.
|
||||
research.fallback.failed=Research failed: {0}
|
||||
research.broadcast.no_plan=Topic cannot be decomposed into researchable sub-questions.
|
||||
research.broadcast.draft_all_empty=No sub-question could be drafted from available material.
|
||||
research.broadcast.failed=Research failed.
|
||||
|
||||
# --- Agent Limit Exceeded Fallback (RFC: prompt-cleanup) ---
|
||||
agent.limit_exceeded.fallback=Sorry, the maximum reasoning steps were reached before a full answer could be produced.
|
||||
agent.limit_exceeded.empty_context=(No tool call results collected yet.)
|
||||
|
||||
@ -1,9 +0,0 @@
|
||||
你是一个对话摘要助手。请将以下对话历史压缩为精简的上下文摘要。
|
||||
|
||||
要求：
|
||||
1. 保留用户的核心意图和关键决策
|
||||
2. 保留重要的事实、数据和结论
|
||||
3. 删除寒暄、重复和冗余内容
|
||||
4. 保留任何未解决的问题或待处理事项
|
||||
5. 输出控制在 600 字以内
|
||||
6. 使用结构化格式，条理清晰
|
||||
@ -1,5 +0,0 @@
|
||||
以下是需要摘要的对话历史：
|
||||
|
||||
{conversation}
|
||||
|
||||
请生成精简的对话上下文摘要。
|
||||
@ -1,4 +1,6 @@
|
||||
你是上下文压缩助手。将以下对话轮次压缩为结构化交接摘要，供后续助手继续任务。
|
||||
你是上下文压缩助手。**不要回答对话中的任何问题或完成请求**，仅输出结构化摘要。
|
||||
|
||||
将以下对话轮次压缩为结构化交接摘要，供后续助手继续任务。
|
||||
|
||||
使用以下结构：
|
||||
|
||||
|
||||
@ -1,3 +1,5 @@
|
||||
你是上下文压缩助手。**不要回答对话中的任何问题或完成请求**，仅输出结构化摘要。
|
||||
|
||||
你正在更新一个上下文压缩摘要。上一次压缩生成了以下摘要，之后发生了新的对话轮次。
|
||||
|
||||
## 旧摘要
|
||||
@ -6,18 +8,8 @@
|
||||
## 新增轮次
|
||||
{conversation}
|
||||
|
||||
请用同样的结构更新摘要。保留所有仍然相关的信息，添加新进展，
|
||||
将"进行中"的已完成项移到"已完成"，仅删除明显过时的信息。
|
||||
|
||||
使用以下结构：
|
||||
|
||||
## 目标
|
||||
## 约束与偏好
|
||||
## 进展（已完成 / 进行中 / 阻塞）
|
||||
## 关键决策
|
||||
## 相关文件
|
||||
## 下一步
|
||||
## 关键上下文
|
||||
|
||||
目标约 {summary_budget} 字。要具体——包含文件路径、命令输出、错误消息和实际值。
|
||||
只输出摘要正文，不要前缀或额外说明。
|
||||
请用 system 消息里定义的结构更新摘要。规则：
|
||||
- 保留所有仍然相关的信息，添加新进展
|
||||
- 将"进行中"的已完成项移到"已完成"
|
||||
- 仅删除明显过时的信息
|
||||
- 只输出摘要正文，不要前缀或额外说明
|
||||
|
||||
@ -7,4 +7,4 @@
|
||||
3. 如果有未完成的调查方向，简要列出建议的后续步骤
|
||||
4. 不要为未完成道歉，直接给结论
|
||||
5. 保持输出简洁，避免重复已知内容
|
||||
6. 在回答末尾告知用户：「已达到本轮最大推理步数，如需继续，请发送"继续"或补充新指令，我会接着完成剩余工作。」
|
||||
6. 在回答末尾用**与用户问题相同的语言**告知：本轮已达到最大推理步数；如需继续请发送 "继续" / "continue" 或补充新指令，我会接着完成剩余工作。
|
||||
@ -5,7 +5,8 @@
|
||||
2. 开头加一句话概述（基于主题）
|
||||
3. 每个子问题作为一个二级标题（## 标题）
|
||||
4. 段落之间做必要的衔接，但不要引入新信息
|
||||
5. 末尾加一段"### 参考材料"，列出所有段落中引用过的材料序号和对应的材料标题
|
||||
6. 输出 Markdown 格式
|
||||
5. **报告语言与 topic 一致**：topic 为英文，所有标题、概述、参考材料清单都用英文；topic 为中文则用中文
|
||||
6. 末尾加一段「参考材料」（中文）或「References」（英文），列出所有段落中引用过的材料编号（`[M1]`、`[M2]` 等）和对应的材料标题
|
||||
7. 输出 Markdown 格式
|
||||
|
||||
如果某些段落说"材料不足"，在报告中保留这个声明，不要掩盖。
|
||||
如果某些段落说"材料不足" / "Not enough material"，在报告中保留这个声明，不要掩盖。
|
||||
|
||||
@ -1,14 +1,14 @@
|
||||
## 研究主题
|
||||
## 研究主题 / Topic
|
||||
{topic}
|
||||
|
||||
## 已写好的段落
|
||||
## 已写好的段落 / Drafted sections
|
||||
|
||||
{sections}
|
||||
|
||||
## 使用过的材料
|
||||
## 使用过的材料 / Materials used
|
||||
|
||||
{materials_ref}
|
||||
|
||||
---
|
||||
|
||||
请组装为一份 Markdown 格式的综合研究报告。
|
||||
请组装为一份 Markdown 格式的综合研究报告（语言跟随 topic）。
|
||||
|
||||
@ -1,10 +1,11 @@
|
||||
你是一个研究助手。基于提供的**材料片段**，针对**子问题**写一段 150-300 字的中文回答。
|
||||
你是一个研究助手。基于提供的**材料片段**，针对**子问题**写一段简洁回答。
|
||||
|
||||
规则：
|
||||
1. **只基于提供的材料片段**——不要引入外部知识、不要虚构
|
||||
2. **如果材料不足以回答，明确说"现有材料不足以回答"**，不要强行编造
|
||||
3. 语言简洁准确，适合作为综合报告的一节
|
||||
4. 不要使用 markdown 标题（##），输出纯段落文本
|
||||
5. 尽量在段末注明使用了哪个材料片段的序号，格式 `[材料 1]`、`[材料 2, 3]`
|
||||
1. **回答的语言与子问题保持一致**（中文子问题用中文，英文子问题用英文）。中文长度约 150-300 字，英文按对应字数/词数自行调整
|
||||
2. **只基于提供的材料片段**——不要引入外部知识、不要虚构
|
||||
3. **如果材料不足以回答，明确说明"材料不足"**（中文）或 "Not enough material"（英文），不要强行编造
|
||||
4. 语言简洁准确，适合作为综合报告的一节
|
||||
5. 不要使用 markdown 标题（##），输出纯段落文本
|
||||
6. 在段末注明使用了哪个材料片段，引用格式 `[M1]`、`[M2, 3]`（语言中立的方括号 token，不要再用「材料 N」之类的中文）
|
||||
|
||||
输出只包含正文段落，不要任何额外说明。
|
||||
|
||||
@ -1,13 +1,13 @@
|
||||
## 子问题
|
||||
## 子问题 / Sub-question
|
||||
{question}
|
||||
|
||||
## 意图
|
||||
## 意图 / Intent
|
||||
{intent}
|
||||
|
||||
## 材料片段（按相关度排序）
|
||||
## 材料片段（按相关度排序）/ Sources (ordered by relevance)
|
||||
|
||||
{materials}
|
||||
|
||||
---
|
||||
|
||||
请基于上述材料片段写出 150-300 字的回答段落。
|
||||
请基于上述材料片段写出一段简洁回答（语言与子问题一致；中文约 150-300 字，英文按对应字数自适应）。
|
||||
|
||||
@ -3,6 +3,7 @@
|
||||
1. 独立可检索——能在知识库中找到直接相关的材料
|
||||
2. 互相覆盖主题的不同侧面——避免重复，保证广度
|
||||
3. 简短明确——一个子问题一句话表达
|
||||
4. **子问题与 intent 的语言与 topic 一致**：topic 为英文则用英文，中文则用中文
|
||||
|
||||
严格输出 JSON（不要 markdown 代码块包裹）：
|
||||
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
研究主题：{topic}
|
||||
|
||||
请拆解为 3-5 个可独立检索的子问题。
|
||||
请拆解为 3-5 个可独立检索的子问题。子问题语言与 topic 保持一致（topic 为英文则子问题亦用英文）。
|
||||
|
||||
@ -0,0 +1,109 @@
|
||||
package vip.mate.agent.context;
|
||||
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.DisplayName;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.mockito.ArgumentCaptor;
|
||||
import org.springframework.ai.chat.messages.Message;
|
||||
import org.springframework.ai.chat.messages.SystemMessage;
|
||||
import org.springframework.ai.chat.messages.UserMessage;
|
||||
import org.springframework.ai.chat.metadata.ChatGenerationMetadata;
|
||||
import org.springframework.ai.chat.model.ChatModel;
|
||||
import org.springframework.ai.chat.model.ChatResponse;
|
||||
import org.springframework.ai.chat.model.Generation;
|
||||
import org.springframework.ai.chat.prompt.Prompt;
|
||||
import vip.mate.config.ConversationWindowProperties;
|
||||
import vip.mate.memory.spi.MemoryManager;
|
||||
import vip.mate.workspace.conversation.ConversationService;
|
||||
|
||||
import java.lang.reflect.Field;
|
||||
import java.lang.reflect.Method;
|
||||
import java.util.List;
|
||||
import java.util.concurrent.ConcurrentHashMap;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
import static org.mockito.ArgumentMatchers.any;
|
||||
import static org.mockito.Mockito.mock;
|
||||
import static org.mockito.Mockito.when;
|
||||
|
||||
/**
|
||||
* Regression test for the RFC: prompt-cleanup D bug — the iterative-update
|
||||
* branch of {@link ConversationWindowManager#generateSummary} previously
|
||||
* used the raw {@code STRUCTURED_SUMMARY_SYSTEM} template without
|
||||
* substituting {@code {summary_budget}}, leaking the literal placeholder
|
||||
* into the LLM prompt.
|
||||
*
|
||||
* <p>Both branches must now produce a SystemMessage where {@code {summary_budget}}
|
||||
* is replaced by the configured budget number.</p>
|
||||
*/
|
||||
class ConversationWindowManagerSummaryBudgetTest {
|
||||
|
||||
private ConversationWindowManager manager;
|
||||
private ChatModel chatModel;
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
ConversationWindowProperties props = new ConversationWindowProperties();
|
||||
MemoryManager memory = mock(MemoryManager.class);
|
||||
ConversationService conv = mock(ConversationService.class);
|
||||
manager = new ConversationWindowManager(props, memory, conv);
|
||||
|
||||
chatModel = mock(ChatModel.class);
|
||||
// Return a non-null, non-empty response so generateSummary stores the result.
|
||||
Generation gen = new Generation(new org.springframework.ai.chat.messages.AssistantMessage("STUB SUMMARY"),
|
||||
ChatGenerationMetadata.NULL);
|
||||
ChatResponse response = new ChatResponse(List.of(gen));
|
||||
when(chatModel.call(any(Prompt.class))).thenReturn(response);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("First-compression branch: {summary_budget} is substituted in SystemMessage")
|
||||
void firstCompressionReplacesBudget() throws Exception {
|
||||
Prompt sentPrompt = invokeGenerateSummaryAndCapture("conv-first", null);
|
||||
SystemMessage system = (SystemMessage) sentPrompt.getInstructions().stream()
|
||||
.filter(m -> m instanceof SystemMessage).findFirst().orElseThrow();
|
||||
String text = system.getText();
|
||||
assertFalse(text.contains("{summary_budget}"),
|
||||
"first-compression: literal placeholder must not leak into the SystemMessage");
|
||||
assertTrue(text.matches("(?s).*\\d{2,}.*"),
|
||||
"first-compression: SystemMessage should contain a numeric budget after substitution");
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Iterative-update branch: {summary_budget} is substituted in SystemMessage")
|
||||
void iterativeUpdateReplacesBudget() throws Exception {
|
||||
// Seed previousSummaries so generateSummary takes the iterative-update path.
|
||||
Field f = ConversationWindowManager.class.getDeclaredField("previousSummaries");
|
||||
f.setAccessible(true);
|
||||
@SuppressWarnings("unchecked")
|
||||
ConcurrentHashMap<String, String> prev = (ConcurrentHashMap<String, String>) f.get(manager);
|
||||
prev.put("conv-iter", "PRIOR SUMMARY (placeholder for the iterative-update branch test)");
|
||||
|
||||
Prompt sentPrompt = invokeGenerateSummaryAndCapture("conv-iter", null);
|
||||
SystemMessage system = (SystemMessage) sentPrompt.getInstructions().stream()
|
||||
.filter(m -> m instanceof SystemMessage).findFirst().orElseThrow();
|
||||
String text = system.getText();
|
||||
assertFalse(text.contains("{summary_budget}"),
|
||||
"iterative-update: literal placeholder must not leak into the SystemMessage (the bug regression guard)");
|
||||
}
|
||||
|
||||
/**
|
||||
* Reflectively invoke the private {@code generateSummary} method and capture
|
||||
* the {@link Prompt} sent to the mocked {@link ChatModel}.
|
||||
*/
|
||||
private Prompt invokeGenerateSummaryAndCapture(String conversationId, String memoryExtra) throws Exception {
|
||||
// Two synthetic user messages so serializeForSummary produces non-empty content.
|
||||
List<Message> oldMessages = List.of(
|
||||
new UserMessage("hello"),
|
||||
new UserMessage("world"));
|
||||
|
||||
Method m = ConversationWindowManager.class.getDeclaredMethod(
|
||||
"generateSummary", List.class, ChatModel.class, String.class, int.class, String.class);
|
||||
m.setAccessible(true);
|
||||
m.invoke(manager, oldMessages, chatModel, conversationId, 1500, memoryExtra);
|
||||
|
||||
ArgumentCaptor<Prompt> captor = ArgumentCaptor.forClass(Prompt.class);
|
||||
org.mockito.Mockito.verify(chatModel).call(captor.capture());
|
||||
return captor.getValue();
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,100 @@
|
||||
package vip.mate.agent.graph.node;
|
||||
|
||||
import com.alibaba.cloud.ai.graph.OverAllState;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.DisplayName;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.springframework.ai.chat.messages.AssistantMessage;
|
||||
import org.springframework.ai.chat.model.ChatModel;
|
||||
import vip.mate.agent.graph.NodeStreamingChatHelper;
|
||||
import vip.mate.agent.graph.observation.ObservationProcessor;
|
||||
import vip.mate.i18n.I18nService;
|
||||
|
||||
import java.util.HashMap;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
import static org.mockito.ArgumentMatchers.any;
|
||||
import static org.mockito.ArgumentMatchers.anyInt;
|
||||
import static org.mockito.ArgumentMatchers.anyString;
|
||||
import static org.mockito.Mockito.mock;
|
||||
import static org.mockito.Mockito.when;
|
||||
import static vip.mate.agent.graph.state.MateClawStateKeys.*;
|
||||
|
||||
/**
|
||||
* Verifies that {@link LimitExceededNode} surfaces fallback strings via
|
||||
* {@link I18nService} (RFC: prompt-cleanup E2) instead of literal Chinese
|
||||
* hardcodes. Two paths are covered:
|
||||
*
|
||||
* <ul>
|
||||
* <li>Empty observation history — the inline {@code contextForLLM}
|
||||
* defaults to {@code i18n.msg("agent.limit_exceeded.empty_context")}</li>
|
||||
* <li>LLM returns empty text — the {@code finalAnswerDraft} fallback
|
||||
* comes from {@code i18n.msg("agent.limit_exceeded.fallback")}</li>
|
||||
* </ul>
|
||||
*/
|
||||
class LimitExceededNodeFallbackTest {
|
||||
|
||||
private ChatModel chatModel;
|
||||
private ObservationProcessor observationProcessor;
|
||||
private NodeStreamingChatHelper streamingHelper;
|
||||
private I18nService i18n;
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
chatModel = mock(ChatModel.class);
|
||||
observationProcessor = mock(ObservationProcessor.class);
|
||||
when(observationProcessor.getMaxTotalObservationChars()).thenReturn(24000);
|
||||
when(observationProcessor.truncate(anyString(), anyInt())).thenAnswer(inv -> inv.getArgument(0));
|
||||
|
||||
streamingHelper = mock(NodeStreamingChatHelper.class);
|
||||
|
||||
i18n = mock(I18nService.class);
|
||||
when(i18n.msg("agent.limit_exceeded.empty_context")).thenReturn("CANNED_EMPTY_CTX");
|
||||
when(i18n.msg("agent.limit_exceeded.fallback")).thenReturn("CANNED_FALLBACK");
|
||||
}
|
||||
|
||||
private LimitExceededNode createNode() {
|
||||
return new LimitExceededNode(chatModel, observationProcessor, streamingHelper, i18n);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Empty LLM response → finalAnswerDraft uses i18n fallback (not Chinese literal)")
|
||||
void emptyLlmResponse_usesI18nFallback() throws Exception {
|
||||
// LLM returns null text → triggers the i18n fallback branch.
|
||||
NodeStreamingChatHelper.StreamResult result = new NodeStreamingChatHelper.StreamResult(
|
||||
null, "", new AssistantMessage(""), List.of(), false, 0, 0);
|
||||
when(streamingHelper.streamCall(any(), any(), anyString(), anyString())).thenReturn(result);
|
||||
|
||||
Map<String, Object> output = createNode().apply(buildStateWithObservations());
|
||||
|
||||
assertEquals("CANNED_FALLBACK", output.get(FINAL_ANSWER_DRAFT),
|
||||
"finalAnswerDraft must come from i18n.msg(\"agent.limit_exceeded.fallback\") when the LLM returns nothing");
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Non-empty LLM response → finalAnswerDraft uses LLM text (i18n untouched)")
|
||||
void nonEmptyLlmResponse_usesLlmText() throws Exception {
|
||||
NodeStreamingChatHelper.StreamResult result = new NodeStreamingChatHelper.StreamResult(
|
||||
"real answer", "", new AssistantMessage("real answer"), List.of(), false, 10, 5);
|
||||
when(streamingHelper.streamCall(any(), any(), anyString(), anyString())).thenReturn(result);
|
||||
|
||||
Map<String, Object> output = createNode().apply(buildStateWithObservations());
|
||||
|
||||
assertEquals("real answer", output.get(FINAL_ANSWER_DRAFT));
|
||||
}
|
||||
|
||||
private OverAllState buildStateWithObservations() {
|
||||
Map<String, Object> map = new HashMap<>();
|
||||
map.put(CONVERSATION_ID, "test-conv");
|
||||
map.put(USER_MESSAGE, "hello");
|
||||
map.put(MAX_ITERATIONS, 5);
|
||||
map.put(CURRENT_ITERATION, 5);
|
||||
// Non-empty observations so contextForLLM doesn't take the empty-context branch
|
||||
// (that branch is exercised separately by an integration test, hard to mock here
|
||||
// because OverAllState.value() may return immutable empty list defaults).
|
||||
map.put(OBSERVATION_HISTORY, List.of("obs1", "obs2"));
|
||||
return new OverAllState(map);
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,112 @@
|
||||
package vip.mate.wiki.service;
|
||||
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.DisplayName;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.springframework.ai.chat.model.ChatModel;
|
||||
import org.springframework.ai.chat.model.ChatResponse;
|
||||
import vip.mate.agent.AgentGraphBuilder;
|
||||
import vip.mate.channel.web.ChatStreamTracker;
|
||||
import vip.mate.i18n.I18nService;
|
||||
import vip.mate.llm.model.ModelConfigEntity;
|
||||
import vip.mate.llm.service.ModelConfigService;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
import static org.mockito.ArgumentMatchers.any;
|
||||
import static org.mockito.ArgumentMatchers.anyString;
|
||||
import static org.mockito.Mockito.mock;
|
||||
import static org.mockito.Mockito.verify;
|
||||
import static org.mockito.Mockito.when;
|
||||
|
||||
/**
|
||||
* Verifies that {@link WikiResearchService} surfaces fallback strings via
|
||||
* {@link I18nService} (RFC: prompt-cleanup E2) instead of literal Chinese
|
||||
* hardcodes when the LLM produces empty output. The plan-stage failure path
|
||||
* is exercised because it is the cleanest to mock — a null LLM response
|
||||
* causes {@code planStage} to return an empty list, which triggers the
|
||||
* {@code research.fallback.no_plan} branch.
|
||||
*/
|
||||
class WikiResearchServiceFallbackTest {
|
||||
|
||||
private HybridRetriever hybridRetriever;
|
||||
private WikiRawMaterialService rawService;
|
||||
private ModelConfigService modelConfigService;
|
||||
private AgentGraphBuilder agentGraphBuilder;
|
||||
private ChatStreamTracker streamTracker;
|
||||
private I18nService i18n;
|
||||
private ChatModel chatModel;
|
||||
private WikiResearchService service;
|
||||
|
||||
@BeforeEach
|
||||
void setUp() {
|
||||
hybridRetriever = mock(HybridRetriever.class);
|
||||
rawService = mock(WikiRawMaterialService.class);
|
||||
modelConfigService = mock(ModelConfigService.class);
|
||||
agentGraphBuilder = mock(AgentGraphBuilder.class);
|
||||
streamTracker = mock(ChatStreamTracker.class);
|
||||
i18n = mock(I18nService.class);
|
||||
chatModel = mock(ChatModel.class);
|
||||
|
||||
ModelConfigEntity model = mock(ModelConfigEntity.class);
|
||||
when(modelConfigService.getDefaultModel()).thenReturn(model);
|
||||
when(agentGraphBuilder.buildRuntimeChatModel(any(), any())).thenReturn(chatModel);
|
||||
// Empty-response stub: planStage will return List.of() and trigger the no_plan fallback.
|
||||
ChatResponse empty = mock(ChatResponse.class);
|
||||
when(empty.getResult()).thenReturn(null);
|
||||
when(chatModel.call(any(org.springframework.ai.chat.prompt.Prompt.class))).thenReturn(empty);
|
||||
|
||||
when(i18n.msg(anyString())).thenAnswer(inv -> "I18N[" + inv.getArgument(0) + "]");
|
||||
when(i18n.msg(anyString(), any())).thenAnswer(inv -> "I18N[" + inv.getArgument(0) + "]");
|
||||
|
||||
service = new WikiResearchService(
|
||||
hybridRetriever, rawService, modelConfigService,
|
||||
agentGraphBuilder, streamTracker, i18n);
|
||||
}
|
||||
|
||||
@Test
|
||||
@DisplayName("Empty plan response → report comes from i18n, not literal Chinese")
|
||||
void noPlanFallback_usesI18n() {
|
||||
WikiResearchService.ResearchResult result = service.research(1L, "Test topic", "sess-1", 5);
|
||||
|
||||
assertEquals("I18N[research.fallback.no_plan]", result.report(),
|
||||
"report must come from i18n.msg(\"research.fallback.no_plan\")");
|
||||
assertTrue(result.sections().isEmpty());
|
||||
|
||||
// Also verify the broadcast went through i18n (not a Chinese literal).
|
||||
verify(i18n).msg("research.broadcast.no_plan");
|
||||
verify(i18n).msg("research.fallback.no_plan");
|
||||
// Critical regression guard: never emit the old literal.
|
||||
assertFalse(result.report().contains("无法为该主题生成研究计划"),
|
||||
"literal Chinese fallback must not leak through after the i18n migration");
|
||||
}
|
||||
|
||||
// Note: the research() catch-block fallback (research.fallback.failed) is not unit-tested
|
||||
// here because callLlm internally swallows LLM exceptions and returns null, so they never
|
||||
// propagate up to research()'s try/catch. Triggering that branch cleanly would require
|
||||
// mocking an exception inside draftStage (post planStage). Coverage is left to the
|
||||
// end-to-end smoke test described in the RFC.
|
||||
|
||||
@Test
|
||||
@DisplayName("Compose-fallback path uses neutral [Q]/[M] tokens (no '### 子问题' / '- 材料')")
|
||||
void composeFallbackUsesNeutralTokens() throws Exception {
|
||||
// Reach into composeStage via reflection with a non-empty section list so the
|
||||
// built-in fallback string is exercised. The compose LLM call returns null
|
||||
// (chatModel mocked above), so composeStage falls through to the manual concat.
|
||||
var section = new WikiResearchService.Section(
|
||||
"What is X?",
|
||||
"Answer body referencing [M1].",
|
||||
List.of(new WikiResearchService.MaterialRef(1, 100L, 200L, "Source A")));
|
||||
|
||||
java.lang.reflect.Method compose = WikiResearchService.class.getDeclaredMethod(
|
||||
"composeStage", String.class, List.class);
|
||||
compose.setAccessible(true);
|
||||
String fallbackReport = (String) compose.invoke(service, "Topic", List.of(section));
|
||||
|
||||
// E3 regression guard: the assembled fallback report must use neutral tokens.
|
||||
assertFalse(fallbackReport.contains("### 子问题"), "must not contain Chinese assembly tag '### 子问题'");
|
||||
assertFalse(fallbackReport.contains("- 材料"), "must not contain Chinese assembly tag '- 材料'");
|
||||
assertTrue(fallbackReport.contains("[Q1]"), "must contain neutral [Q1] token");
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user