feat: read model_provider and model_providers from config.toml (#853)

This is the first step in supporting other model providers in the Rust
CLI. Specifically, this PR adds support for the new entries in `Config`
and `ConfigOverrides` to specify a `ModelProviderInfo`, which is the
basic config needed for an LLM provider. This PR does not get us all the
way there yet because `client.rs` still categorically appends
`/responses` to the URL and expects the endpoint to support the OpenAI
Responses API. Will fix that next!
This commit is contained in:
Michael Bolin authored and GitHub committed 2025-05-07 17:38:28 -07:00
1 parent cfe50c7107
commit 86022f097e
12 files changed
+208 -30

No files matched your search

@@ -158,6 +158,7 @@ impl CodexToolCallParam {
approval_policy: approval_policy.map(Into::into),
sandbox_policy,
disable_response_storage,
provider: None,
};
let cfg = codex_core::config::Config::load_with_overrides(overrides)?;