Skip to content

Commit 3534149

Browse files
committed
update readme
1 parent b51d246 commit 3534149

File tree

3 files changed

+0
-51
lines changed

3 files changed

+0
-51
lines changed

README.md

Lines changed: 0 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -22,23 +22,6 @@
2222
- Conversation save/load helpers
2323
- OpenAI-compatible endpoint support through `openai::Config::baseUrl`
2424

25-
## Production Readiness
26-
27-
`llmapi` is usable for internal tools, prototypes, and early production experiments, but it should not yet be treated as fully industrial-grade infrastructure.
28-
29-
Required gaps before that bar:
30-
31-
- Unified error model across providers and transport
32-
- Retry, backoff, timeout, and idempotency policy
33-
- Request cancellation for long-running and streaming calls
34-
- Logging, metrics, trace hooks, and request correlation
35-
- Hardening of the custom HTTP/TLS transport layer
36-
- Fault-injection, concurrency, and large-scale mock testing
37-
- Stronger API compatibility and versioning guarantees
38-
- More complete production configuration surface
39-
- Explicit thread-safety and concurrency semantics
40-
- Operational documentation for retries, keys, proxies, and failure handling
41-
4225
## Quick Start
4326

4427
```cpp

README.zh.hant.md

Lines changed: 0 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -22,23 +22,6 @@
2222
- 支援儲存 / 載入對話歷史
2323
- 可透過 `baseUrl` 存取 OpenAI 相容端點
2424

25-
## 生產可用性
26-
27-
`llmapi` 目前適合內部工具、原型專案與早期生產試用,但還不應直接視為完整工業級基礎設施。
28-
29-
要達到那個標準,至少還需要補齊:
30-
31-
- 統一的 provider / 傳輸層錯誤模型
32-
- 重試、退避、逾時、冪等策略
33-
- 長請求與串流請求的取消能力
34-
- 日誌、指標、trace hook、請求關聯資訊
35-
- 自研 HTTP/TLS 傳輸層的進一步加固
36-
- 故障注入、並發、Mock、大規模測試
37-
- 更強的 API 相容性與版本穩定性承諾
38-
- 更完整的生產設定面
39-
- 明確的執行緒安全與並發語義
40-
- 面向維運的重試、金鑰、代理、故障處理文件
41-
4225
## 快速開始
4326

4427
```cpp

README.zh.md

Lines changed: 0 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -22,23 +22,6 @@
2222
- 支持保存 / 加载对话历史
2323
- 可通过 `baseUrl` 访问 OpenAI 兼容端点
2424

25-
## 生产可用性
26-
27-
`llmapi` 目前适合内部工具、原型项目和早期生产试用,但还不应直接视为完整工业级基础设施。
28-
29-
要达到那个标准,至少还需要补齐:
30-
31-
- 统一的 provider / 传输层错误模型
32-
- 重试、退避、超时、幂等策略
33-
- 长请求和流式请求的取消能力
34-
- 日志、指标、trace hook、请求关联信息
35-
- 自研 HTTP/TLS 传输层的进一步加固
36-
- 故障注入、并发、Mock、大规模测试
37-
- 更强的 API 兼容性与版本稳定性承诺
38-
- 更完整的生产配置面
39-
- 明确的线程安全和并发语义
40-
- 面向运维的重试、密钥、代理、故障处理文档
41-
4225
## 快速开始
4326

4427
```cpp

0 commit comments

Comments
 (0)