实现RAG参考文献显示模式

This commit is contained in:
吉鑫升 committed 2026-05-27 17:40:10 +08:00
1 parent eda0ccffdb
commit c56db15a03
22 files changed
+1733 -192

No files matched your search

+157 -39
View File
@@ -168,6 +168,7 @@ export function collectRuntimeDisplaySources(
const seenCitationKeys = new Map<string, RuntimeDisplaySource>();
const seenDisplayKeys = new Set<string>();
const consumedToolMessageIds = new Set<string>();
const consumedToolMessages = new Set<Message>();
for (let index = start; index < limit; index++) {
const message = messages[index];
@@ -180,14 +181,24 @@ export function collectRuntimeDisplaySources(
displays,
toolCall.args,
);
const result = findToolResultPayload(toolCall, messages, index);
const toolMessage = findToolResultMessage(
toolCall,
messages,
index,
consumedToolMessageIds,
consumedToolMessages,
);
if (!toolMessage) {
continue;
}
const result = parseToolMessagePayload(toolMessage);
if (result === undefined) {
continue;
}
const linkedToolMessage = findToolMessageById(toolCall.id, messages);
if (linkedToolMessage?.id) {
consumedToolMessageIds.add(linkedToolMessage.id);
if (toolMessage.id) {
consumedToolMessageIds.add(toolMessage.id);
}
consumedToolMessages.add(toolMessage);
if (isDisplaySamplePayload(result)) {
continue;
}
@@ -223,7 +234,12 @@ export function collectRuntimeDisplaySources(
for (let index = start; index < limit; index++) {
const message = messages[index];
if (!message || message.type !== "tool" || consumedToolMessageIds.has(message.id ?? "")) {
if (
!message ||
message.type !== "tool" ||
consumedToolMessages.has(message) ||
consumedToolMessageIds.has(message.id ?? "")
) {
continue;
}
const result = parseToolMessagePayload(message);
@@ -238,7 +254,8 @@ export function collectRuntimeDisplaySources(
}
const normalized = match
? normalizeDisplaySources(result, match.display)
: shouldUseDefaultCitationMode(toolName, result)
: shouldUseDefaultCitationMode(toolName, result) ||
normalizeDefaultDisplaySources(result).length > 0
? normalizeDefaultDisplaySources(result)
: [];
appendDisplaySources(
@@ -268,16 +285,14 @@ function appendDisplaySources(
) {
for (const draft of drafts) {
if (draft.mode === "citation") {
const key = citationSourceKey(draft);
const existing = seenCitationKeys.get(key);
if (existing) {
continue;
}
const source = {
...draft,
index: nextCitationIndex(),
};
seenCitationKeys.set(key, source);
const key = citationSourceKey(draft);
if (key) {
seenCitationKeys.set(`${key}:${source.index}`, source);
}
target.push(source);
continue;
}
@@ -331,12 +346,19 @@ function citationSourceKey(source: RuntimeDisplaySourceDraft): string {
stringifyMaybe(raw.docId) ||
stringifyMaybe(raw.id);
if (id) {
return normalizeName(`${source.skillName}:${id}`);
return normalizeCitationKey(String(id));
}
const fallback = [source.skillName, source.title, source.source, source.time]
const fallback = [
source.skillName,
source.title,
source.source,
source.time,
source.content,
source.snippet,
]
.filter(Boolean)
.join("|");
return normalizeName(fallback) || JSON.stringify(raw).slice(0, 300);
return normalizeCitationKey(fallback) || normalizeCitationKey(JSON.stringify(raw).slice(0, 300));
}
function nonCitationSourceKey(source: RuntimeDisplaySourceDraft): string {
@@ -543,7 +565,12 @@ export function normalizeDefaultDisplaySources(payload: unknown): DisplaySourceI
: undefined,
);
return normalized.map((item, index) => ({
id: item.url ?? String(index + 1),
id:
item.recUuid ??
item.uuid ??
item.docId ??
item.id ??
item.url,
title: item.title ?? item.source ?? `结果 ${index + 1}`,
type: "result",
snippet: item.snippet ?? item.content ?? "",
@@ -620,18 +647,79 @@ function replaceCitationTokens(
byIndex: Map<number, RuntimeDisplaySource>,
orderedSources: RuntimeDisplaySource[],
): string {
return content
const normalized = normalizeLooseCitationTokens(content, byIndex, orderedSources);
const withDoubleBracketCitations = normalized
.replace(/\[\[(\d+)\]\]/g, (match, rawIndex: string) =>
citationMarkdown(match, Number(rawIndex), byIndex, orderedSources),
)
.replace(/(^|[^:\[!])\[(\d+)\](?!\()/g, (match, prefix: string, rawIndex: string) =>
`${prefix}${citationMarkdown(
match.slice(prefix.length),
Number(rawIndex),
byIndex,
orderedSources,
)}`,
);
return replaceBracketCitationTokens(
withDoubleBracketCitations,
byIndex,
orderedSources,
);
}
function replaceBracketCitationTokens(
content: string,
byIndex: Map<number, RuntimeDisplaySource>,
orderedSources: RuntimeDisplaySource[],
): string {
const tokenPattern = /\\?\[(\d{1,3})\\?\](?!\()/g;
let cursor = 0;
let next = "";
for (const match of content.matchAll(tokenPattern)) {
const start = match.index ?? 0;
const previous = start > 0 ? content[start - 1] : "";
if (previous === ":" || previous === "[" || previous === "!") {
continue;
}
next += content.slice(cursor, start);
next += citationMarkdown(match[0], Number(match[1]), byIndex, orderedSources);
cursor = start + match[0].length;
}
next += content.slice(cursor);
return next;
}
function normalizeLooseCitationTokens(
content: string,
byIndex: Map<number, RuntimeDisplaySource>,
orderedSources: RuntimeDisplaySource[],
): string {
const isValidIndex = (index: number) =>
Number.isInteger(index) &&
index > 0 &&
(byIndex.has(index) || !!orderedSources[index - 1]);
const toCitationRun = (raw: string) => {
const parts = raw.match(/\\?\[\d{1,3}\\?\]|\d{1,3}/g) ?? [];
const indexes = parts.map((part) => Number(part.replace(/\D/g, "")));
if (indexes.length === 0 || indexes.some((index) => !isValidIndex(index))) {
return raw;
}
return indexes.map((index) => `[${index}]`).join("");
};
let next = content.replace(
/(^|[^\d\[\]\\])((?:\d{1,3}|\\?\[\d{1,3}\\?\])(?:\\?\[\d{1,3}\\?\]|\d{1,3})+)/g,
(match, prefix: string, rawRun: string) => {
if (!rawRun.includes("[")) {
return match;
}
return `${prefix}${toCitationRun(rawRun)}`;
},
);
next = next.replace(
/(^|[\s\uFF0C\u3002\uFF1B\uFF1A\u3001,!?!?)])(\d{1,3})(?=([\s\uFF0C\u3002\uFF1B\uFF1A\u3001,!?!?)]|$))/g,
(match, prefix: string, rawIndex: string) => {
const index = Number(rawIndex);
if (!isValidIndex(index)) {
return match;
}
return `${prefix}[${index}]`;
},
);
return next;
}
function normalizeExistingCitationLinks(
@@ -654,16 +742,16 @@ function normalizeExistingCitationLinks(
const index = Number(numberMatch[1]);
const source = byIndex.get(index) ?? orderedSources[index - 1];
if (source) {
return `[citation:[${source.index}]](#reference-${source.index})`;
return citationLinkMarkdown(source);
}
}
const sourceByUrl = byUrl.get(url);
if (sourceByUrl) {
return `[citation:[${sourceByUrl.index}]](#reference-${sourceByUrl.index})`;
return citationLinkMarkdown(sourceByUrl);
}
const sourceByTitle = byTitle.get(label);
if (sourceByTitle) {
return `[citation:[${sourceByTitle.index}]](#reference-${sourceByTitle.index})`;
return citationLinkMarkdown(sourceByTitle);
}
return match;
},
@@ -680,11 +768,11 @@ function citationMarkdown(
if (!source) {
return fallback;
}
return `[citation:[${source.index}]](#reference-${source.index})`;
return citationLinkMarkdown(source);
}
function hasCitationMarkdown(content: string): boolean {
return /\[citation:\[[^\]]+\]\]\(#reference-[^)]+\)/.test(content);
return /\[citation:(?:\[[^\]]+\]|\d+)\]\(#reference-[^)]+\)/.test(content);
}
function appendCitationSummary(
@@ -693,7 +781,7 @@ function appendCitationSummary(
): string {
const citations = citationSources
.slice(0, 5)
.map((source) => `[citation:[${source.index}]](#reference-${source.index})`)
.map((source) => citationLinkMarkdown(source))
.join(" ");
if (!citations) {
return content;
@@ -702,10 +790,22 @@ function appendCitationSummary(
return `${trimmed}${trimmed ? "\n\n" : ""}参考来源:${citations}`;
}
function citationLinkMarkdown(source: RuntimeDisplaySource): string {
return `[citation:${source.index}](#reference-${source.index})`;
}
function normalizeName(name: string): string {
return name.toLowerCase().replace(/[^a-z0-9]+/g, "");
}
function normalizeCitationKey(value: string): string {
return value
.toLowerCase()
.normalize("NFKC")
.replace(/\s+/g, " ")
.trim();
}
function isRecord(value: unknown): value is Record<string, unknown> {
return !!value && typeof value === "object" && !Array.isArray(value);
}
@@ -714,18 +814,28 @@ function stringifyMaybe(value: unknown): string | undefined {
return typeof value === "string" && value.trim() ? value : undefined;
}
function findToolResultPayload(
function findToolResultMessage(
toolCall: RuntimeToolCall,
messages: Message[],
toolCallMessageIndex = -1,
): unknown {
const toolMessage =
findToolMessageById(toolCall.id, messages) ??
findToolMessageByName(toolCall, messages, toolCallMessageIndex);
if (!toolMessage) {
return undefined;
consumedToolMessageIds?: Set<string>,
consumedToolMessages?: Set<Message>,
): Message | undefined {
const byId = findToolMessageById(toolCall.id, messages);
if (
byId &&
!consumedToolMessages?.has(byId) &&
(!byId.id || !consumedToolMessageIds?.has(byId.id))
) {
return byId;
}
return parseToolMessagePayload(toolMessage);
return findToolMessageByName(
toolCall,
messages,
toolCallMessageIndex,
consumedToolMessageIds,
consumedToolMessages,
);
}
function parseToolMessagePayload(toolMessage: Message): unknown {
@@ -782,6 +892,8 @@ function findToolMessageByName(
toolCall: RuntimeToolCall,
messages: Message[],
toolCallMessageIndex: number,
consumedToolMessageIds?: Set<string>,
consumedToolMessages?: Set<Message>,
): Message | undefined {
const start = Math.max(toolCallMessageIndex + 1, 0);
for (let index = start; index < messages.length; index++) {
@@ -795,6 +907,12 @@ function findToolMessageByName(
if (message.type !== "tool") {
continue;
}
if (message.id && consumedToolMessageIds?.has(message.id)) {
continue;
}
if (consumedToolMessages?.has(message)) {
continue;
}
const name =
stringifyMaybe((message as { name?: unknown }).name) ??
stringifyMaybe(