chenmoranzhi/writing-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

会话与前端接上听书、呈现投影、请求轮廓和旁观气泡偏好。

Browse Source 
新建作品可选听书连载，朗读与消费进度走专用接口。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
chenmoranzhi
2026-10-07 23:49:44 +08:00
co-authored by Cursor
parent cf6cb68429
commit 66ed1eaca8
21 changed files with 2395 additions and 357 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/server/session-manager.ts
+299 -35
View File
@@ -93,6 +93,7 @@ import {
sessionSkillPackId,
skillPacksMatch,
} from "../book/skill-id.js";
import type { RequestOutline } from "../llm/context-outline.js";
import {
pruneContextTraces,
type LlmContextTrace,
@@ -102,6 +103,8 @@ import type { BlackboardItem } from "../types/blackboard.js";
import { Blackboard } from "../blackboard/blackboard.js";
import { parseWorkerSetYaml } from "../skills/worker-set-parse.js";
import { parseShellAdaptationFromReplyFormat } from "../skills/present-packet.js";
import { parseReplyDataContract } from "../skills/reply-contract.js";
import { projectPresentBlocks } from "../skills/present-project.js";
import {
CREATION_ACCEPTED_CONTENT_TAG,
CREATION_ACCEPTED_UNITS_TAG,
@@ -182,6 +185,16 @@ import {
sortDictateProducts,
type DictateProduct,
} from "../dictate/index.js";
import {
LISTEN_SERIAL_MODE_VALUE,
isListenSerialModeValue,
markListenConsumed,
readListenState,
runListenSerialTurn,
toListenView,
type ListenSerialView,
} from "../listen-serial/index.js";
import { synthesizeSpeech, type TtsSynthesizeResult } from "../tts/index.js";
import {
formatQuestionAnswersForAi,
formatQuestionAnswersForDisplay,
@@ -255,6 +268,8 @@ export type ChatMessage = {
thinking?: string;
/** 该次 LLM 请求实际携带的全量上下文（观察用；按设置只保留最新 N 条） */
contextTrace?: LlmContextTrace;
/** 本条回复对应的各次请求标签轮廓（选题、填写都在；不含正文） */
requestOutlines?: RequestOutline[];
/** run 验收后过程讨论折叠（主 feed 隐藏）；创作 messages 不删不藏 */
compressed?: boolean;
tokenUsage?: MessageTokenUsage;
@@ -323,6 +338,14 @@ export type SessionView = {
block_labels?: Record<string, string>;
empty_states?: Record<string, string>;
};
/** 正文组成固定前端。游玩和开场把 present.v1 灌进去，替换示例内容。 */
presentationFrontend?: { html: string; css: string; js: string };
/** 正文组成数据契约里的区。格式化时按 id 填进对应 data-block。 */
presentationSlots?: Array<{ id: string; type: string }>;
/**
* 程序投影块（来自 变量.当前 等）。前端灌 present 时与消息正文合并，随真值刷新。
*/
presentationProjection?: Record<string, unknown>;
/** 总管正在输出的思维链（流式，轮询用） */
agentThinking?: string;
/** Agent / Worker 流式输出（轮询用） */
@@ -333,10 +356,12 @@ export type SessionView = {
*/
runActive?: boolean;
resumed?: boolean;
/** 创作进料：recipe=配方节点流；dictate=转述整理直填 */
creationMode?: "recipe" | "dictate";
/** 创作进料：recipe=配方节点流；dictate=转述整理；listen_serial=听书连载 */
creationMode?: "recipe" | "dictate" | "listen_serial";
/** 转述式已写入黑板的产物（按相对序） */
dictateProducts?: Array<{ tag: string; content: string; order?: number }>;
/** 听书连载投影（大纲/正文缓冲/未读字数） */
listenSerial?: ListenSerialView;
tokenStats?: {
sessionTotal: number;
sessionCached?: number;
@@ -555,8 +580,16 @@ export class SessionManager {
this.writeOpeningPersonaChoice(s, true);
}
// 与进游玩一致：用完整文档（含 present.v1），勿用侧栏预览的压扁正文
const rawOnBoard = board.getContentByTag(picked.tag)?.trim() ?? "";
const body =
splitOpeningDocument(
rawOnBoard || picked.document || picked.text,
).text.trim() ||
picked.document?.trim() ||
picked.text.trim();
const expanded = this.expandDirectivesText(
picked.text,
body,
this.playDirectiveContext(s),
);
board.write({
@@ -566,7 +599,13 @@ export class SessionManager {
});
const openingAt = s.messages.findIndex((m) => m.title === "开场白");
if (openingAt >= 0) {
s.messages[openingAt] = this.playOpeningMessage(expanded);
// 保留 id，前端才能 patch 呈现壳 forceFill，而不是拆 iframe 后软灌样本槽
s.messages[openingAt] = this.playOpeningMessage(
expanded,
s.messages[openingAt]!.id,
);
} else {
s.messages.unshift(this.playOpeningMessage(expanded));
}
if (s.bookId) this.persist(s);
return this.toView(sessionId);
@@ -613,11 +652,13 @@ export class SessionManager {
const next = applyContextOrderEdit(current!, edit);
const serialized = serializeContextOrder(next);
const orderMeta = bb.getLatestByTag(CONTEXT_ORDER_TAG)?.metadata;
bb.write({
tag: CONTEXT_ORDER_TAG,
content: serialized,
source: "user",
metadata: orderMeta,
});
if (workerSetRaw) {
@@ -631,6 +672,7 @@ export class SessionManager {
tag: targetTag,
content: mergeContextOrderIntoWorkerSetJson(workerSetRaw, next),
source: "user",
metadata: bb.getLatestByTag(targetTag)?.metadata,
});
}
} else {
@@ -639,6 +681,7 @@ export class SessionManager {
tag: CONTEXT_ORDER_TAG,
content: serialized,
source: "user",
metadata: orderMeta,
});
}
@@ -670,7 +713,7 @@ export class SessionManager {
bookId?: string,
preselectSkillId?: string,
selectedRecipeId?: string,
opts?: { creationMode?: "recipe" | "dictate" },
opts?: { creationMode?: "recipe" | "dictate" | "listen_serial" },
): Promise<SessionView> {
const id = randomUUID();
const messages: ChatMessage[] = [];
@@ -713,18 +756,22 @@ export class SessionManager {
} else {
await runtime.start();
}
const useDictate = opts?.creationMode === "dictate";
const creationMode = opts?.creationMode ?? "recipe";
const useDictate = creationMode === "dictate";
const useListen = creationMode === "listen_serial";
await this.refreshRecipeOptions(
managed,
useDictate ? "dictate" : "recipe",
useDictate || useListen ? "dictate" : "recipe",
);
if (selectedRecipeId?.trim()) {
await this.applySelectedRecipe(managed, selectedRecipeId.trim(), {
seedFlow: !useDictate,
seedFlow: !useDictate && !useListen,
});
}
if (useDictate) {
if (useListen) {
this.enterListenSerialMode(managed);
} else if (useDictate) {
this.enterDictateMode(managed);
} else {
await this.maybeKickAgentAfterDemand(runtime);
@@ -780,6 +827,145 @@ export class SessionManager {
);
}
/** 听书连载：薄上下文连续产文，不走对话落盘工具环 */
private enterListenSerialMode(s: ManagedSession): void {
const board = s.runtime.getBlackboard();
board.write({
tag: CREATION_INTAKE_MODE_TAG,
content: LISTEN_SERIAL_MODE_VALUE,
source: "runtime",
});
s.runtime.enterDictateIntake(
"听书连载：用几句话描述题材与爽点；确认后我会生成大纲并自动补正文。不满意就说一句意见改后面。",
);
const welcome =
"听书连载：说几句你想听的故事（题材、人设、爽点即可）。我会轻回问或给出草案；确认后自动出大纲和正文缓冲。听的过程中随时一句意见，只改后面的走向。";
s.messages.push({
id: randomUUID(),
role: "system",
text: welcome,
createdAt: new Date().toISOString(),
kind: "orchestrator_prompt",
actor: "orchestrator",
title: "听书连载",
body: welcome,
});
}
private isListenSerialMode(s: ManagedSession): boolean {
return isListenSerialModeValue(
s.runtime.getBlackboard().getContentByTag(CREATION_INTAKE_MODE_TAG),
);
}
private creationIntakeMode(
s: ManagedSession,
): "recipe" | "dictate" | "listen_serial" {
if (this.isListenSerialMode(s)) return "listen_serial";
if (this.isDictateMode(s)) return "dictate";
return "recipe";
}
private extractListenDialogue(
messages: ChatMessage[],
): Array<{ role: "user" | "assistant"; text: string }> {
const out: Array<{ role: "user" | "assistant"; text: string }> = [];
for (const m of messages) {
if (m.kind === "user_input" || m.role === "user") {
const t = (m.body ?? m.text ?? "").trim();
if (t) out.push({ role: "user", text: t });
continue;
}
if (m.kind === "listen_reply") {
const t = (m.body ?? m.text ?? "").trim();
if (t) out.push({ role: "assistant", text: t });
}
}
return out;
}
private async runListenSerialTurnForSession(
s: ManagedSession,
userText: string,
): Promise<void> {
const llm = createDefaultMainAgentLlm(s.trackingRef, () =>
this.personaForManaged(s),
);
const dialogue = this.extractListenDialogue(s.messages);
const result = await runListenSerialTurn({
llm,
board: s.runtime.getBlackboard(),
dialogue,
userText,
});
const keep = normalizeContextTraceKeepLatest(
loadAppSettings().contextTraceKeepLatest,
);
const requestOutlines = s.trackingRef.current.pendingOutlines;
const pendingTrace = s.trackingRef.current.pendingContextTrace;
const tokenUsage = s.trackingRef.current.pendingUsage;
s.trackingRef.current.pendingOutlines = undefined;
s.trackingRef.current.pendingContextTrace = undefined;
s.trackingRef.current.pendingUsage = undefined;
s.messages.push({
id: randomUUID(),
role: "system",
text: result.reply,
createdAt: new Date().toISOString(),
kind: "listen_reply",
actor: "orchestrator",
title: "听书连载",
body: result.reply,
...(tokenUsage ? { tokenUsage } : {}),
...(keep > 0 && pendingTrace ? { contextTrace: pendingTrace } : {}),
...(requestOutlines?.length ? { requestOutlines } : {}),
});
s.messages = pruneContextTraces(s.messages, keep);
s.runtime.enterDictateIntake(
result.softStop
? "本段已告一段落。输入「下一波」或「收工」，或一句意见改向。"
: "继续听/读，或说「继续」补货；不满意直接一句意见。",
);
}
/** 听书：标记已消费字数（阅读进度） */
markListenSerialConsumed(
sessionId: string,
consumedChars: number,
): SessionView {
const s = this.require(sessionId);
if (!this.isListenSerialMode(s)) {
throw new Error("当前不是听书连载模式");
}
markListenConsumed(s.runtime.getBlackboard(), consumedChars);
if (s.bookId) this.persist(s);
return this.toView(sessionId);
}
/** 听书：按节合成语音（默认 Edge） */
async synthesizeListenSection(
sessionId: string,
sectionId: string,
): Promise<TtsSynthesizeResult & { sectionId: string; title: string }> {
const s = this.require(sessionId);
if (!this.isListenSerialMode(s)) {
throw new Error("当前不是听书连载模式");
}
const id = sectionId.trim();
if (!id) throw new Error("需要 sectionId");
const state = readListenState(s.runtime.getBlackboard());
const section = state.sections.find((x) => x.id === id);
if (!section?.text?.trim()) {
throw new Error("未找到该节正文");
}
const spoken = `【${section.title}】\n${section.text}`.trim();
const result = await synthesizeSpeech({
text: spoken,
cacheKey: `${sessionId}:${id}`,
});
return { ...result, sectionId: id, title: section.title };
}
private listDictateProducts(s: ManagedSession): DictateProduct[] {
const board = s.runtime.getBlackboard();
const products: DictateProduct[] = [];
@@ -897,11 +1083,10 @@ export class SessionManager {
if (dictateProductFamily(tag) === OPENING_PRODUCT_FAMILY) {
const split = splitOpeningDocument(content);
if (split.persona) {
ensureProtagonistFromPersona(
board,
split.persona,
protagonistTagForOpeningSlot(tag),
);
const personaTag = protagonistTagForOpeningSlot(tag);
ensureProtagonistFromPersona(board, split.persona, personaTag, {
overwrite: personaTag !== PROTAGONIST_TAG,
});
}
// 仅有用户角色 meta、无叙事：抬到主角设定，不污染开场白
if (split.persona && !split.text.trim()) {
@@ -1009,6 +1194,15 @@ export class SessionManager {
s.messages.length,
this.captureCheckpoint(s),
);
const keep = normalizeContextTraceKeepLatest(
loadAppSettings().contextTraceKeepLatest,
);
const requestOutlines = s.trackingRef.current.pendingOutlines;
const pendingTrace = s.trackingRef.current.pendingContextTrace;
const tokenUsage = s.trackingRef.current.pendingUsage;
s.trackingRef.current.pendingOutlines = undefined;
s.trackingRef.current.pendingContextTrace = undefined;
s.trackingRef.current.pendingUsage = undefined;
s.messages.push({
id: randomUUID(),
role: "system",
@@ -1019,7 +1213,11 @@ export class SessionManager {
title: "转述整理",
body: result.reply,
...(thinking ? { thinking } : {}),
...(tokenUsage ? { tokenUsage } : {}),
...(keep > 0 && pendingTrace ? { contextTrace: pendingTrace } : {}),
...(requestOutlines?.length ? { requestOutlines } : {}),
});
s.messages = pruneContextTraces(s.messages, keep);
s.runtime.enterDictateIntake();
}
@@ -1494,6 +1692,7 @@ export class SessionManager {
// 转述聊天常夹确认/建议，不能当开场白
if (
kind === "dictate_reply" ||
kind === "listen_reply" ||
kind === "agent_tool" ||
kind === "orchestrator_thinking" ||
kind === "worker_questions"
@@ -1830,9 +2029,9 @@ export class SessionManager {
);
}
private playOpeningMessage(text: string): ChatMessage {
private playOpeningMessage(text: string, keepId?: string): ChatMessage {
return {
id: randomUUID(),
id: keepId || randomUUID(),
role: "system",
text,
createdAt: new Date().toISOString(),
@@ -1917,6 +2116,29 @@ export class SessionManager {
return count;
}
/**
* 切换/改了全局用户角色：游玩层开场按新 @玩家 重展开，并改用全局角色卡。
*/
rebindPlayOpeningsForActivePersona(): number {
let count = 0;
for (const [sessionId, s] of this.sessions) {
if (!isPlayLayerActive(s.runtime.getSession().slots)) continue;
if (inferLifecycleStage(s.runtime.getSession()) !== "play") continue;
const aux = buildPlayAuxView(
s.runtime.getBlackboard(),
s.runtime.getSession().slots,
);
if (!aux.openings.length) continue;
try {
this.selectPlayOpening(sessionId, aux.selectedOpeningIndex, false);
count += 1;
} catch {
/* 单局失败不挡其它局 */
}
}
return count;
}
async sendMessage(
id: string,
text: string,
@@ -1983,13 +2205,15 @@ export class SessionManager {
const inPlay =
isPlayLayerActive(sess.slots) ||
inferLifecycleStage(sess) === "play";
if (
this.isDictateMode(s) &&
reason?.kind === "input" &&
!inPlay
) {
await this.runDictateTurnForSession(s, trimmed || text);
return;
if (reason?.kind === "input" && !inPlay) {
if (this.isListenSerialMode(s)) {
await this.runListenSerialTurnForSession(s, trimmed || text);
return;
}
if (this.isDictateMode(s)) {
await this.runDictateTurnForSession(s, trimmed || text);
return;
}
}
}
if (reason?.kind === "approve_step") {
@@ -2237,13 +2461,15 @@ export class SessionManager {
const inPlay =
isPlayLayerActive(sess.slots) ||
inferLifecycleStage(sess) === "play";
if (
this.isDictateMode(s) &&
reason?.kind === "input" &&
!inPlay
) {
await this.runDictateTurnForSession(s, trimmed);
return;
if (reason?.kind === "input" && !inPlay) {
if (this.isListenSerialMode(s)) {
await this.runListenSerialTurnForSession(s, trimmed);
return;
}
if (this.isDictateMode(s)) {
await this.runDictateTurnForSession(s, trimmed);
return;
}
}
await s.runtime.submitInput(trimmed);
});
@@ -3100,6 +3326,7 @@ export class SessionManager {
undefined;
const pendingTrace = managed.trackingRef.current.pendingContextTrace;
let contextTrace: LlmContextTrace | undefined;
let requestOutlines: RequestOutline[] | undefined;
if (
pendingTrace &&
classified &&
@@ -3112,10 +3339,19 @@ export class SessionManager {
contextTrace = pendingTrace;
}
managed.trackingRef.current.pendingContextTrace = undefined;
requestOutlines = managed.trackingRef.current.pendingOutlines;
managed.trackingRef.current.pendingOutlines = undefined;
}
managed.messages.push(
this.msg("system", text, usage, thinking, contextTrace),
this.msg(
"system",
text,
usage,
thinking,
contextTrace,
requestOutlines?.length ? requestOutlines : undefined,
),
);
managed.messages = pruneContextTraces(
managed.messages,
@@ -3405,6 +3641,7 @@ export class SessionManager {
tokenUsage?: MessageTokenUsage,
thinking?: string,
contextTrace?: LlmContextTrace,
requestOutlines?: RequestOutline[],
): ChatMessage {
const base = {
id: randomUUID(),
@@ -3414,6 +3651,7 @@ export class SessionManager {
...(tokenUsage ? { tokenUsage } : {}),
...(thinking ? { thinking } : {}),
...(contextTrace ? { contextTrace } : {}),
...(requestOutlines?.length ? { requestOutlines } : {}),
};
if (role === "user") {
return {
@@ -3812,10 +4050,12 @@ export class SessionManager {
lifecycleStage,
{ workerSetYaml },
);
const shellAdapt = parseShellAdaptationFromReplyFormat(
const replyFormatRaw =
s.runtime.getBlackboard().getContentByTag("设计.正文组成") ??
s.runtime.getBlackboard().getContentByTag("设计.回复格式"),
);
s.runtime.getBlackboard().getContentByTag("设计.0层正文组成") ??
s.runtime.getBlackboard().getContentByTag("设计.回复格式");
const shellAdapt = parseShellAdaptationFromReplyFormat(replyFormatRaw);
const replyContract = parseReplyDataContract(replyFormatRaw);
return {
id,
@@ -3831,10 +4071,13 @@ export class SessionManager {
actions,
pipeline: buildPipeline(session),
lifecycleStage,
creationMode: this.isDictateMode(s) ? "dictate" : "recipe",
creationMode: this.creationIntakeMode(s),
dictateProducts: this.isDictateMode(s)
? this.listDictateProducts(s)
: undefined,
listenSerial: this.isListenSerialMode(s)
? toListenView(readListenState(s.runtime.getBlackboard()))
: undefined,
playLayerActive: isPlayLayerActive(session.slots),
playReady: canEnterPlay(session),
hasProduct: Boolean(
@@ -3895,6 +4138,27 @@ export class SessionManager {
...shellAdapt.tweaks,
}
: undefined,
presentationFrontend: replyContract?.frontend,
presentationSlots: replyContract
? [...replyContract.modelBlocks, ...replyContract.programBlocks].map((block) => ({
id: block.id,
type: block.type,
}))
: undefined,
presentationProjection: (() => {
if (!replyContract?.programBlocks.length) return undefined;
const board = s.runtime.getBlackboard();
const projected = projectPresentBlocks({
contract: replyContract,
statusBarRaw:
board.getContentByTag("设计.监控栏") ??
board.getContentByTag("设计.回复呈现"),
currentVarsRaw: board.getContentByTag("变量.当前"),
topologyRaw: board.getContentByTag("运行.拓扑"),
readTag: (tag) => board.getContentByTag(tag),
});
return Object.keys(projected).length ? projected : undefined;
})(),
liveStream: this.buildLiveStreamView(id),
agentThinking: this.agentThinkingLive.get(id),
runActive: Boolean(s.runAbort),