litellm/litellm-rust
Yujong Lee 2f421ac770 fix(rust): read Messages secrets only when the request needs them
The route resolved every declared provider secret before preparing the call,
so a caller that passed api_key and api_base still hit the secret manager for
all four names, paying its latency and failing the call if a read errored.
Python reads each secret lazily through `api_key or get_secret_str(...)`.

resolve_on_demand in litellm-secrets now runs the pure prepare step against
the secrets fetched so far and fetches only the first name it asks for that is
not yet known, repeating until nothing is missing. Reads happen in the same
order and with the same short circuits as Python, and the per-config
secret_names list is gone since nothing needs to be declared up front
2026-09-24 12:08:40 -07:00
..
crates fix(rust): read Messages secrets only when the request needs them 2026-09-24 12:08:40 -07:00
.gitignore feat: add LiteLLM Rust workspace with Mistral OCR bridge (#31033) 2026-06-23 13:16:47 -07:00
Cargo.lock test(rust): encode anthropic response serialization shape as rstest cases 2026-09-24 08:17:12 -07:00
Cargo.toml feat(logger): dispatch Python logging through the Rust diagnostics processor (#42616) 2026-09-22 18:44:15 -07:00
clippy.toml wip 2026-09-19 10:36:59 -07:00