Phase 3: LiteLLM Integration

- Added LiteLLM as built-in model provider in model_provider_info.rs:
  - Default base_url: http://localhost:4000/v1 (configurable via LITELLM_BASE_URL)
  - Uses Chat wire API (OpenAI-compatible)
  - Requires LITELLM_API_KEY environment variable
  - No OpenAI auth required (simple bearer token)
  - Positioned as first provider in list

- Updated default models to use LiteLLM format:
  - Changed from "gpt-5-codex" to "anthropic/claude-sonnet-4-20250514"
  - Updated all default model constants (OPENAI_DEFAULT_MODEL, etc.)
  - Uses provider/model format compatible with LiteLLM

- Provider configuration:
  - Supports base_url override via environment variable
  - Includes helpful env_key_instructions pointing to LiteLLM docs
  - Uses standard retry/timeout defaults

This makes LLMX work out-of-the-box with LiteLLM proxy, supporting
multiple providers (Anthropic, OpenAI, etc.) through a single interface.

🤖 Generated with Claude Code

llmx-rs/core/src/config/mod.rs

@@ -58,12 +58,13 @@ pub mod edit;
 pub mod profile;
 pub mod types;
 
+// Default models for LLMX using LiteLLM format (provider/model)
 #[cfg(target_os = "windows")]
-pub const OPENAI_DEFAULT_MODEL: &str = "gpt-5";
+pub const OPENAI_DEFAULT_MODEL: &str = "anthropic/claude-sonnet-4-20250514";
 #[cfg(not(target_os = "windows"))]
-pub const OPENAI_DEFAULT_MODEL: &str = "gpt-5-codex";
+pub const OPENAI_DEFAULT_MODEL: &str = "anthropic/claude-sonnet-4-20250514";
-const OPENAI_DEFAULT_REVIEW_MODEL: &str = "gpt-5-codex";
+const OPENAI_DEFAULT_REVIEW_MODEL: &str = "anthropic/claude-sonnet-4-20250514";
-pub const GPT_5_CODEX_MEDIUM_MODEL: &str = "gpt-5-codex";
+pub const GPT_5_CODEX_MEDIUM_MODEL: &str = "anthropic/claude-sonnet-4-20250514";
 
 /// Maximum number of bytes of the documentation that will be embedded. Larger
 /// files are *silently truncated* to this size so we do not take up too much of

llmx-rs/core/src/model_provider_info.rs

@@ -267,10 +267,32 @@ pub fn built_in_model_providers() -> HashMap<String, ModelProviderInfo> {
     use ModelProviderInfo as P;
 
     // We do not want to be in the business of adjucating which third-party
-    // providers are bundled with Codex CLI, so we only include the OpenAI and
+    // providers are bundled with LLMX CLI, so we include LiteLLM as the default,
-    // open source ("oss") providers by default. Users are encouraged to add to
+    // along with OpenAI and open source ("oss") providers. Users are encouraged
-    // `model_providers` in config.toml to add their own providers.
+    // to add to `model_providers` in config.toml to add their own providers.
     [
+        (
+            "litellm",
+            P {
+                name: "LiteLLM".into(),
+                // Allow users to override the default LiteLLM endpoint
+                base_url: std::env::var("LITELLM_BASE_URL")
+                    .ok()
+                    .filter(|v| !v.trim().is_empty())
+                    .or_else(|| Some("http://localhost:4000/v1".into())),
+                env_key: Some("LITELLM_API_KEY".into()),
+                env_key_instructions: Some("Set LITELLM_API_KEY to your LiteLLM master key. See https://docs.litellm.ai/ for setup.".into()),
+                experimental_bearer_token: None,
+                wire_api: WireApi::Chat,
+                query_params: None,
+                http_headers: None,
+                env_http_headers: None,
+                request_max_retries: None,
+                stream_max_retries: None,
+                stream_idle_timeout_ms: None,
+                requires_openai_auth: false,
+            },
+        ),
         (
             "openai",
             P {