feat(memory,conversation): 记忆富化/证据包、时间线幂等字段与对话分段全链路

数据库
- 新增迁移 0003:timeline_events.memory_source_id 外键 → memory_sources,便于按 ingest 源做时间线幂等

后端 - 记忆
- 新增 ingest 后 LLM 富化(摘要/事实/时间线),可配置开关与最大字符数
- 新增证据包组装:合并 chunk、摘要、事实、时间线、故事等检索结果;支持空 query 时是否仍带 rolling 等开关
- repo/retriever/service/router/schemas/summarizer/timeline/extractor 等扩展;文档 memory-retrieval.md 更新

后端 - 对话 WS
- 增加 PING/PONG;分段 ASR 日志与空音频处理;转写失败与「无助手回复」错误提示更明确
- 助手多段回复持久化使用统一分隔符,与分段逻辑一致

后端 - Agent
- reply_limits:按 [SPLIT] 与段落拆段,并保证非空 fallback,供 WS 与 TTS 多段下发

后端 - 回忆录任务
- transcript ingest 记录 source_id;任务成功结?
This commit is contained in:
Kevin
2026-03-27 16:01:28 +08:00
parent 1374f6e8f5
commit e4bf0710c7
70 changed files with 3404 additions and 557 deletions

View File

@@ -38,7 +38,7 @@ class TencentASRProvider:
async def transcribe(self, audio: bytes, format: str = "m4a") -> str:
client = self._get_client()
if not client:
return ""
return "转写失败: 腾讯云 ASR 客户端未初始化(请检查密钥与依赖)"
try:
from tencentcloud.asr.v20190614 import models
@@ -46,12 +46,26 @@ class TencentASRProvider:
req = models.SentenceRecognitionRequest()
req.EngSerViceType = "16k_zh"
req.SourceType = 1
req.VoiceFormat = format
# 小写与文档一致。iOS 常见为 m4a(AAC) 容器,与 16k 引擎匹配
req.VoiceFormat = (format or "m4a").lower()
req.Data = audio_base64
req.DataLen = len(audio)
resp = client.SentenceRecognition(req)
return (resp.Result or "").strip()
text = (resp.Result or "").strip()
if text:
return text
err = getattr(resp, "Error", None) or getattr(resp, "Message", None)
logger.warning(
"Tencent ASR empty Result, audio_len={} format={} err={}",
len(audio),
req.VoiceFormat,
err,
)
return (
"转写失败: 腾讯云返回空文本(常见原因:采样率与 16k_zh 不匹配、"
"格式不受支持或音频无效;请确认客户端为 16kHz 单声道 m4a"
)
except Exception as e:
logger.error("Tencent ASR transcribe failed: {}", e)
return ""
logger.error("Tencent ASR transcribe failed: {}", e, exc_info=True)
return f"转写失败: {e}"[:500]