|
22 | 22 | - Conversation save/load helpers |
23 | 23 | - OpenAI-compatible endpoint support through `openai::Config::baseUrl` |
24 | 24 |
|
| 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 | + |
25 | 42 | ## Quick Start |
26 | 43 |
|
27 | 44 | ```cpp |
@@ -89,7 +106,7 @@ target("demo") |
89 | 106 | add_packages("llmapi") |
90 | 107 | ``` |
91 | 108 |
|
92 | | -See [docs/en/getting-started.md](docs/en/getting-started.md) and [docs/en/providers.md](docs/en/providers.md) for more setup detail. |
| 109 | +See [docs/en/getting-started.md](docs/en/getting-started.md), [docs/en/providers.md](docs/en/providers.md), and [docs/en/README.md](docs/en/README.md) for more setup and readiness detail. |
93 | 110 |
|
94 | 111 | ## License |
95 | 112 |
|
|
0 commit comments