feat: 回忆录证据血缘与内部评测可追溯,顺带对齐本地评测台与 CI

数据库与模型:新增多版迁移(章节证据快照、对话血缘、记忆事实/时间线 lineage 等),把「成稿 ↔ 对话/记忆」的溯源信息落到表结构里。
业务链路:会话与 WS、回忆录/故事流水线、记忆写入与 enrichment 等跟着接上线索与快照;新增章节证据快照与评测侧 EvalTraceService 等模块,方便组评审用的证据包。
内部评测:自动化 run 与手工 memoir 评审共用可追溯证据;rubric/ judge 相关脚本与文档有配套调整。
app-eval-web:Memoir/实验详情里能展开看证据摘要与 evidence_trace(含对话轮次 id);Vite 代理与 development.sh 注入的 API 端口与当前默认内部评测端口一致,避免改端口后页面连错服务。
工程杂项:GitHub Actions / 仓库说明有更新;各适配器与支付/配额/plan 等多处为小改动或跟随主改动的收尾;新增/扩充了?
This commit is contained in:
Kevin
2026-04-08 15:37:09 +08:00
parent 6772e1269c
commit 309a051038
109 changed files with 4125 additions and 858 deletions

View File

@@ -2,7 +2,9 @@
import asyncio
import base64
from app.core.logging import get_logger
from app.ports.asr import ASRTranscriptionError
logger = get_logger(__name__)
@@ -39,7 +41,9 @@ class TencentASRProvider:
async def transcribe(self, audio: bytes, format: str = "m4a") -> str:
client = self._get_client()
if not client:
return "转写失败: 腾讯云 ASR 客户端未初始化(请检查密钥与依赖)"
raise ASRTranscriptionError(
"Tencent ASR client not initialized (check credentials)"
)
try:
from tencentcloud.asr.v20190614 import models
@@ -64,10 +68,11 @@ class TencentASRProvider:
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"
raise ASRTranscriptionError(
"Tencent ASR empty Result (check sample rate / format / audio)"
)
except ASRTranscriptionError:
raise
except Exception as e:
logger.error("Tencent ASR transcribe failed: {}", e, exc_info=True)
return f"转写失败: {e}"[:500]
raise ASRTranscriptionError(f"Tencent ASR transcribe failed: {e!s}") from e

View File

@@ -9,6 +9,7 @@ import tempfile
from typing import Any, Iterable
from app.core.logging import get_logger
from app.ports.asr import ASRTranscriptionError
logger = get_logger(__name__)
@@ -104,7 +105,7 @@ class WhisperASRProvider:
# 与 v1.1.0 相同的单次 transcribe推理放线程池避免阻塞 asynciotag 上为同步调用)。
self._load_model()
if not self._model:
return ""
raise ASRTranscriptionError("Whisper model not loaded")
model = self._model
@@ -182,9 +183,11 @@ class WhisperASRProvider:
logger.warning("Whisper decode_audio 回退失败: {}", ex)
return text
except ASRTranscriptionError:
raise
except Exception as e:
logger.error("Whisper transcribe failed: {}", e)
return ""
raise ASRTranscriptionError(f"Whisper transcribe failed: {e!s}") from e
finally:
if tmp_path and os.path.exists(tmp_path):
try: