This release represents a comprehensive transformation of the codebase from Codex to LLMX, enhanced with LiteLLM integration to support 100+ LLM providers through a unified API. ## Major Changes ### Phase 1: Repository & Infrastructure Setup - Established new repository structure and branching strategy - Created comprehensive project documentation (CLAUDE.md, LITELLM-SETUP.md) - Set up development environment and tooling configuration ### Phase 2: Rust Workspace Transformation - Renamed all Rust crates from `codex-*` to `llmx-*` (30+ crates) - Updated package names, binary names, and workspace members - Renamed core modules: codex.rs → llmx.rs, codex_delegate.rs → llmx_delegate.rs - Updated all internal references, imports, and type names - Renamed directories: codex-rs/ → llmx-rs/, codex-backend-openapi-models/ → llmx-backend-openapi-models/ - Fixed all Rust compilation errors after mass rename ### Phase 3: LiteLLM Integration - Integrated LiteLLM for multi-provider LLM support (Anthropic, OpenAI, Azure, Google AI, AWS Bedrock, etc.) - Implemented OpenAI-compatible Chat Completions API support - Added model family detection and provider-specific handling - Updated authentication to support LiteLLM API keys - Renamed environment variables: OPENAI_BASE_URL → LLMX_BASE_URL - Added LLMX_API_KEY for unified authentication - Enhanced error handling for Chat Completions API responses - Implemented fallback mechanisms between Responses API and Chat Completions API ### Phase 4: TypeScript/Node.js Components - Renamed npm package: @codex/codex-cli → @valknar/llmx - Updated TypeScript SDK to use new LLMX APIs and endpoints - Fixed all TypeScript compilation and linting errors - Updated SDK tests to support both API backends - Enhanced mock server to handle multiple API formats - Updated build scripts for cross-platform packaging ### Phase 5: Configuration & Documentation - Updated all configuration files to use LLMX naming - Rewrote README and documentation for LLMX branding - Updated config paths: ~/.codex/ → ~/.llmx/ - Added comprehensive LiteLLM setup guide - Updated all user-facing strings and help text - Created release plan and migration documentation ### Phase 6: Testing & Validation - Fixed all Rust tests for new naming scheme - Updated snapshot tests in TUI (36 frame files) - Fixed authentication storage tests - Updated Chat Completions payload and SSE tests - Fixed SDK tests for new API endpoints - Ensured compatibility with Claude Sonnet 4.5 model - Fixed test environment variables (LLMX_API_KEY, LLMX_BASE_URL) ### Phase 7: Build & Release Pipeline - Updated GitHub Actions workflows for LLMX binary names - Fixed rust-release.yml to reference llmx-rs/ instead of codex-rs/ - Updated CI/CD pipelines for new package names - Made Apple code signing optional in release workflow - Enhanced npm packaging resilience for partial platform builds - Added Windows sandbox support to workspace - Updated dotslash configuration for new binary names ### Phase 8: Final Polish - Renamed all assets (.github images, labels, templates) - Updated VSCode and DevContainer configurations - Fixed all clippy warnings and formatting issues - Applied cargo fmt and prettier formatting across codebase - Updated issue templates and pull request templates - Fixed all remaining UI text references ## Technical Details **Breaking Changes:** - Binary name changed from `codex` to `llmx` - Config directory changed from `~/.codex/` to `~/.llmx/` - Environment variables renamed (CODEX_* → LLMX_*) - npm package renamed to `@valknar/llmx` **New Features:** - Support for 100+ LLM providers via LiteLLM - Unified authentication with LLMX_API_KEY - Enhanced model provider detection and handling - Improved error handling and fallback mechanisms **Files Changed:** - 578 files modified across Rust, TypeScript, and documentation - 30+ Rust crates renamed and updated - Complete rebrand of UI, CLI, and documentation - All tests updated and passing **Dependencies:** - Updated Cargo.lock with new package names - Updated npm dependencies in llmx-cli - Enhanced OpenAPI models for LLMX backend This release establishes LLMX as a standalone project with comprehensive LiteLLM integration, maintaining full backward compatibility with existing functionality while opening support for a wide ecosystem of LLM providers. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Sebastian Krüger <support@pivoine.art>
160 lines
4.4 KiB
Rust
160 lines
4.4 KiB
Rust
use std::borrow::Borrow;
|
|
use std::hash::Hash;
|
|
use std::num::NonZeroUsize;
|
|
|
|
use lru::LruCache;
|
|
use sha1::Digest;
|
|
use sha1::Sha1;
|
|
use tokio::sync::Mutex;
|
|
use tokio::sync::MutexGuard;
|
|
|
|
/// A minimal LRU cache protected by a Tokio mutex.
|
|
pub struct BlockingLruCache<K, V> {
|
|
inner: Mutex<LruCache<K, V>>,
|
|
}
|
|
|
|
impl<K, V> BlockingLruCache<K, V>
|
|
where
|
|
K: Eq + Hash,
|
|
{
|
|
/// Creates a cache with the provided non-zero capacity.
|
|
#[must_use]
|
|
pub fn new(capacity: NonZeroUsize) -> Self {
|
|
Self {
|
|
inner: Mutex::new(LruCache::new(capacity)),
|
|
}
|
|
}
|
|
|
|
/// Returns a clone of the cached value for `key`, or computes and inserts it.
|
|
pub fn get_or_insert_with(&self, key: K, value: impl FnOnce() -> V) -> V
|
|
where
|
|
V: Clone,
|
|
{
|
|
let mut guard = lock_blocking(&self.inner);
|
|
if let Some(v) = guard.get(&key) {
|
|
return v.clone();
|
|
}
|
|
let v = value();
|
|
// Insert and return a clone to keep ownership in the cache.
|
|
guard.put(key, v.clone());
|
|
v
|
|
}
|
|
|
|
/// Like `get_or_insert_with`, but the value factory may fail.
|
|
pub fn get_or_try_insert_with<E>(
|
|
&self,
|
|
key: K,
|
|
value: impl FnOnce() -> Result<V, E>,
|
|
) -> Result<V, E>
|
|
where
|
|
V: Clone,
|
|
{
|
|
let mut guard = lock_blocking(&self.inner);
|
|
if let Some(v) = guard.get(&key) {
|
|
return Ok(v.clone());
|
|
}
|
|
let v = value()?;
|
|
guard.put(key, v.clone());
|
|
Ok(v)
|
|
}
|
|
|
|
/// Builds a cache if `capacity` is non-zero, returning `None` otherwise.
|
|
#[must_use]
|
|
pub fn try_with_capacity(capacity: usize) -> Option<Self> {
|
|
NonZeroUsize::new(capacity).map(Self::new)
|
|
}
|
|
|
|
/// Returns a clone of the cached value corresponding to `key`, if present.
|
|
pub fn get<Q>(&self, key: &Q) -> Option<V>
|
|
where
|
|
K: Borrow<Q>,
|
|
Q: Hash + Eq + ?Sized,
|
|
V: Clone,
|
|
{
|
|
lock_blocking(&self.inner).get(key).cloned()
|
|
}
|
|
|
|
/// Inserts `value` for `key`, returning the previous entry if it existed.
|
|
pub fn insert(&self, key: K, value: V) -> Option<V> {
|
|
lock_blocking(&self.inner).put(key, value)
|
|
}
|
|
|
|
/// Removes the entry for `key` if it exists, returning it.
|
|
pub fn remove<Q>(&self, key: &Q) -> Option<V>
|
|
where
|
|
K: Borrow<Q>,
|
|
Q: Hash + Eq + ?Sized,
|
|
{
|
|
lock_blocking(&self.inner).pop(key)
|
|
}
|
|
|
|
/// Clears all entries from the cache.
|
|
pub fn clear(&self) {
|
|
lock_blocking(&self.inner).clear();
|
|
}
|
|
|
|
/// Executes `callback` with a mutable reference to the underlying cache.
|
|
pub fn with_mut<R>(&self, callback: impl FnOnce(&mut LruCache<K, V>) -> R) -> R {
|
|
let mut guard = lock_blocking(&self.inner);
|
|
callback(&mut guard)
|
|
}
|
|
|
|
/// Provides direct access to the cache guard for advanced use cases.
|
|
pub fn blocking_lock(&self) -> MutexGuard<'_, LruCache<K, V>> {
|
|
lock_blocking(&self.inner)
|
|
}
|
|
}
|
|
|
|
fn lock_blocking<K, V>(m: &Mutex<LruCache<K, V>>) -> MutexGuard<'_, LruCache<K, V>>
|
|
where
|
|
K: Eq + Hash,
|
|
{
|
|
match tokio::runtime::Handle::try_current() {
|
|
Ok(_) => tokio::task::block_in_place(|| m.blocking_lock()),
|
|
Err(_) => m.blocking_lock(),
|
|
}
|
|
}
|
|
|
|
/// Computes the SHA-1 digest of `bytes`.
|
|
///
|
|
/// Useful for content-based cache keys when you want to avoid staleness
|
|
/// caused by path-only keys.
|
|
#[must_use]
|
|
pub fn sha1_digest(bytes: &[u8]) -> [u8; 20] {
|
|
let mut hasher = Sha1::new();
|
|
hasher.update(bytes);
|
|
let result = hasher.finalize();
|
|
let mut out = [0; 20];
|
|
out.copy_from_slice(&result);
|
|
out
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::BlockingLruCache;
|
|
use std::num::NonZeroUsize;
|
|
|
|
#[tokio::test(flavor = "multi_thread")]
|
|
async fn stores_and_retrieves_values() {
|
|
let cache = BlockingLruCache::new(NonZeroUsize::new(2).expect("capacity"));
|
|
|
|
assert!(cache.get(&"first").is_none());
|
|
cache.insert("first", 1);
|
|
assert_eq!(cache.get(&"first"), Some(1));
|
|
}
|
|
|
|
#[tokio::test(flavor = "multi_thread")]
|
|
async fn evicts_least_recently_used() {
|
|
let cache = BlockingLruCache::new(NonZeroUsize::new(2).expect("capacity"));
|
|
cache.insert("a", 1);
|
|
cache.insert("b", 2);
|
|
assert_eq!(cache.get(&"a"), Some(1));
|
|
|
|
cache.insert("c", 3);
|
|
|
|
assert!(cache.get(&"b").is_none());
|
|
assert_eq!(cache.get(&"a"), Some(1));
|
|
assert_eq!(cache.get(&"c"), Some(3));
|
|
}
|
|
}
|