iomgaa
|
1f83da9eb7
|
fix: embedding 改 cuda + OCR 超时 300s + 重试退避 20s 起 + jitter 防雷群
- config/default.yaml: embed.device cpu → cuda
- adapters/ocr.py: _TIMEOUT_S 15 → 300(5 分钟)
- adapters/llm.py: 指数退避加 ±50% jitter 避免 24 路同时重试
- .env: LLM_RETRY_BASE_DELAY 2→20s, LLM_RETRY_MAX_DELAY 30→120s
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-07-09 22:14:57 -04:00 |
|
iomgaa
|
f733c13dd1
|
fix(llm): call_id 移入重试循环,每 attempt 独立
消除重试时遥测主键冲突的根因。每次 attempt 独立记录,
parent_call_id 不受影响(循环外固定),更利于事后诊断重试轨迹。
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-07-09 00:12:38 -04:00 |
|
iomgaa
|
ee90fb8e88
|
fix(adapters): 修复 GovernedLLMClient 流式消费和规格偏差
- _stream_request + _consume_stream 合并为 _call_streaming,
在 async with self._http.stream() 内直接消费流,
确保看门狗作用于真实 HTTP 流而非内存列表(Critical 1)
- breaker 检查移到 call_id 生成之前(Critical 2)
- cache/ttft_timeout_s/inter_token_timeout_s 支持 None(Important 1)
- 重试失败路径遥测使用统一 call_id(Important 2)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-07-06 23:08:52 -04:00 |
|
iomgaa
|
cfd3277f80
|
style: format adapters/llm.py
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-07-06 23:01:06 -04:00 |
|
iomgaa
|
f1a0414be8
|
feat(adapters): 实现 GovernedLLMClient 四层治理栈
流式 SSE + 三层看门狗 + 重试退避 + 熔断 + Redis 缓存 + 遥测。
provider 差异处理(DeepSeek reasoning_content vs Qwen think 标签)。
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-07-06 23:00:22 -04:00 |
|