feat: Complete LLMX v0.1.0 - Rebrand from Codex with LiteLLM Integration
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>
This commit is contained in:
Sebastian Krüger
347
llmx-rs/mcp-server/src/llmx_tool_config.rs
Normal file
347
llmx-rs/mcp-server/src/llmx_tool_config.rs
Normal file
@@ -0,0 +1,347 @@
|
||||
//! Configuration object accepted by the `llmx` MCP tool-call.
|
||||
|
||||
use llmx_core::protocol::AskForApproval;
|
||||
use llmx_protocol::config_types::SandboxMode;
|
||||
use llmx_utils_json_to_toml::json_to_toml;
|
||||
use mcp_types::Tool;
|
||||
use mcp_types::ToolInputSchema;
|
||||
use schemars::JsonSchema;
|
||||
use schemars::r#gen::SchemaSettings;
|
||||
use serde::Deserialize;
|
||||
use serde::Serialize;
|
||||
use std::collections::HashMap;
|
||||
use std::path::PathBuf;
|
||||
|
||||
/// Client-supplied configuration for a `llmx` tool-call.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, Default)]
|
||||
#[serde(rename_all = "kebab-case")]
|
||||
pub struct LlmxToolCallParam {
|
||||
/// The *initial user prompt* to start the LLMX conversation.
|
||||
pub prompt: String,
|
||||
|
||||
/// Optional override for the model name (e.g. "o3", "o4-mini").
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub model: Option<String>,
|
||||
|
||||
/// Configuration profile from config.toml to specify default options.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub profile: Option<String>,
|
||||
|
||||
/// Working directory for the session. If relative, it is resolved against
|
||||
/// the server process's current working directory.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub cwd: Option<String>,
|
||||
|
||||
/// Approval policy for shell commands generated by the model:
|
||||
/// `untrusted`, `on-failure`, `on-request`, `never`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub approval_policy: Option<LlmxToolCallApprovalPolicy>,
|
||||
|
||||
/// Sandbox mode: `read-only`, `workspace-write`, or `danger-full-access`.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub sandbox: Option<LlmxToolCallSandboxMode>,
|
||||
|
||||
/// Individual config settings that will override what is in
|
||||
/// LLMX_HOME/config.toml.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub config: Option<HashMap<String, serde_json::Value>>,
|
||||
|
||||
/// The set of instructions to use instead of the default ones.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub base_instructions: Option<String>,
|
||||
|
||||
/// Developer instructions that should be injected as a developer role message.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub developer_instructions: Option<String>,
|
||||
|
||||
/// Prompt used when compacting the conversation.
|
||||
#[serde(default, skip_serializing_if = "Option::is_none")]
|
||||
pub compact_prompt: Option<String>,
|
||||
}
|
||||
|
||||
/// Custom enum mirroring [`AskForApproval`], but has an extra dependency on
|
||||
/// [`JsonSchema`].
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, PartialEq)]
|
||||
#[serde(rename_all = "kebab-case")]
|
||||
pub enum LlmxToolCallApprovalPolicy {
|
||||
Untrusted,
|
||||
OnFailure,
|
||||
OnRequest,
|
||||
Never,
|
||||
}
|
||||
|
||||
impl From<LlmxToolCallApprovalPolicy> for AskForApproval {
|
||||
fn from(value: LlmxToolCallApprovalPolicy) -> Self {
|
||||
match value {
|
||||
LlmxToolCallApprovalPolicy::Untrusted => AskForApproval::UnlessTrusted,
|
||||
LlmxToolCallApprovalPolicy::OnFailure => AskForApproval::OnFailure,
|
||||
LlmxToolCallApprovalPolicy::OnRequest => AskForApproval::OnRequest,
|
||||
LlmxToolCallApprovalPolicy::Never => AskForApproval::Never,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Custom enum mirroring [`SandboxMode`] from config_types.rs, but with
|
||||
/// `JsonSchema` support.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema, PartialEq)]
|
||||
#[serde(rename_all = "kebab-case")]
|
||||
pub enum LlmxToolCallSandboxMode {
|
||||
ReadOnly,
|
||||
WorkspaceWrite,
|
||||
DangerFullAccess,
|
||||
}
|
||||
|
||||
impl From<LlmxToolCallSandboxMode> for SandboxMode {
|
||||
fn from(value: LlmxToolCallSandboxMode) -> Self {
|
||||
match value {
|
||||
LlmxToolCallSandboxMode::ReadOnly => SandboxMode::ReadOnly,
|
||||
LlmxToolCallSandboxMode::WorkspaceWrite => SandboxMode::WorkspaceWrite,
|
||||
LlmxToolCallSandboxMode::DangerFullAccess => SandboxMode::DangerFullAccess,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Builds a `Tool` definition (JSON schema etc.) for the Llmx tool-call.
|
||||
pub(crate) fn create_tool_for_llmx_tool_call_param() -> Tool {
|
||||
let schema = SchemaSettings::draft2019_09()
|
||||
.with(|s| {
|
||||
s.inline_subschemas = true;
|
||||
s.option_add_null_type = false;
|
||||
})
|
||||
.into_generator()
|
||||
.into_root_schema_for::<LlmxToolCallParam>();
|
||||
|
||||
#[expect(clippy::expect_used)]
|
||||
let schema_value =
|
||||
serde_json::to_value(&schema).expect("LLMX tool schema should serialise to JSON");
|
||||
|
||||
let tool_input_schema =
|
||||
serde_json::from_value::<ToolInputSchema>(schema_value).unwrap_or_else(|e| {
|
||||
panic!("failed to create Tool from schema: {e}");
|
||||
});
|
||||
|
||||
Tool {
|
||||
name: "llmx".to_string(),
|
||||
title: Some("LLMX".to_string()),
|
||||
input_schema: tool_input_schema,
|
||||
// TODO(mbolin): This should be defined.
|
||||
output_schema: None,
|
||||
description: Some(
|
||||
"Run an LLMX session. Accepts configuration parameters matching the LLMX Config struct.".to_string(),
|
||||
),
|
||||
annotations: None,
|
||||
}
|
||||
}
|
||||
|
||||
impl LlmxToolCallParam {
|
||||
/// Returns the initial user prompt to start the LLMX conversation and the
|
||||
/// effective Config object generated from the supplied parameters.
|
||||
pub async fn into_config(
|
||||
self,
|
||||
llmx_linux_sandbox_exe: Option<PathBuf>,
|
||||
) -> std::io::Result<(String, llmx_core::config::Config)> {
|
||||
let Self {
|
||||
prompt,
|
||||
model,
|
||||
profile,
|
||||
cwd,
|
||||
approval_policy,
|
||||
sandbox,
|
||||
config: cli_overrides,
|
||||
base_instructions,
|
||||
developer_instructions,
|
||||
compact_prompt,
|
||||
} = self;
|
||||
|
||||
// Build the `ConfigOverrides` recognized by llmx-core.
|
||||
let overrides = llmx_core::config::ConfigOverrides {
|
||||
model,
|
||||
review_model: None,
|
||||
config_profile: profile,
|
||||
cwd: cwd.map(PathBuf::from),
|
||||
approval_policy: approval_policy.map(Into::into),
|
||||
sandbox_mode: sandbox.map(Into::into),
|
||||
model_provider: None,
|
||||
llmx_linux_sandbox_exe,
|
||||
base_instructions,
|
||||
developer_instructions,
|
||||
compact_prompt,
|
||||
include_apply_patch_tool: None,
|
||||
show_raw_agent_reasoning: None,
|
||||
tools_web_search_request: None,
|
||||
experimental_sandbox_command_assessment: None,
|
||||
additional_writable_roots: Vec::new(),
|
||||
};
|
||||
|
||||
let cli_overrides = cli_overrides
|
||||
.unwrap_or_default()
|
||||
.into_iter()
|
||||
.map(|(k, v)| (k, json_to_toml(v)))
|
||||
.collect();
|
||||
|
||||
let cfg =
|
||||
llmx_core::config::Config::load_with_cli_overrides(cli_overrides, overrides).await?;
|
||||
|
||||
Ok((prompt, cfg))
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, JsonSchema)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct LlmxToolCallReplyParam {
|
||||
/// The conversation id for this LLMX session.
|
||||
pub conversation_id: String,
|
||||
|
||||
/// The *next user prompt* to continue the LLMX conversation.
|
||||
pub prompt: String,
|
||||
}
|
||||
|
||||
/// Builds a `Tool` definition for the `llmx-reply` tool-call.
|
||||
pub(crate) fn create_tool_for_llmx_tool_call_reply_param() -> Tool {
|
||||
let schema = SchemaSettings::draft2019_09()
|
||||
.with(|s| {
|
||||
s.inline_subschemas = true;
|
||||
s.option_add_null_type = false;
|
||||
})
|
||||
.into_generator()
|
||||
.into_root_schema_for::<LlmxToolCallReplyParam>();
|
||||
|
||||
#[expect(clippy::expect_used)]
|
||||
let schema_value =
|
||||
serde_json::to_value(&schema).expect("LLMX reply tool schema should serialise to JSON");
|
||||
|
||||
let tool_input_schema =
|
||||
serde_json::from_value::<ToolInputSchema>(schema_value).unwrap_or_else(|e| {
|
||||
panic!("failed to create Tool from schema: {e}");
|
||||
});
|
||||
|
||||
Tool {
|
||||
name: "llmx-reply".to_string(),
|
||||
title: Some("LLMX Reply".to_string()),
|
||||
input_schema: tool_input_schema,
|
||||
output_schema: None,
|
||||
description: Some(
|
||||
"Continue an LLMX conversation by providing the conversation id and prompt."
|
||||
.to_string(),
|
||||
),
|
||||
annotations: None,
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use pretty_assertions::assert_eq;
|
||||
|
||||
/// We include a test to verify the exact JSON schema as "executable
|
||||
/// documentation" for the schema. When can track changes to this test as a
|
||||
/// way to audit changes to the generated schema.
|
||||
///
|
||||
/// Seeing the fully expanded schema makes it easier to casually verify that
|
||||
/// the generated JSON for enum types such as "approval-policy" is compact.
|
||||
/// Ideally, modelcontextprotocol/inspector would provide a simpler UI for
|
||||
/// enum fields versus open string fields to take advantage of this.
|
||||
///
|
||||
/// As of 2025-05-04, there is an open PR for this:
|
||||
/// https://github.com/modelcontextprotocol/inspector/pull/196
|
||||
#[test]
|
||||
fn verify_llmx_tool_json_schema() {
|
||||
let tool = create_tool_for_llmx_tool_call_param();
|
||||
let tool_json = serde_json::to_value(&tool).expect("tool serializes");
|
||||
let expected_tool_json = serde_json::json!({
|
||||
"name": "llmx",
|
||||
"title": "LLMX",
|
||||
"description": "Run an LLMX session. Accepts configuration parameters matching the LLMX Config struct.",
|
||||
"inputSchema": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"approval-policy": {
|
||||
"description": "Approval policy for shell commands generated by the model: `untrusted`, `on-failure`, `on-request`, `never`.",
|
||||
"enum": [
|
||||
"untrusted",
|
||||
"on-failure",
|
||||
"on-request",
|
||||
"never"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"sandbox": {
|
||||
"description": "Sandbox mode: `read-only`, `workspace-write`, or `danger-full-access`.",
|
||||
"enum": [
|
||||
"read-only",
|
||||
"workspace-write",
|
||||
"danger-full-access"
|
||||
],
|
||||
"type": "string"
|
||||
},
|
||||
"config": {
|
||||
"description": "Individual config settings that will override what is in LLMX_HOME/config.toml.",
|
||||
"additionalProperties": true,
|
||||
"type": "object"
|
||||
},
|
||||
"cwd": {
|
||||
"description": "Working directory for the session. If relative, it is resolved against the server process's current working directory.",
|
||||
"type": "string"
|
||||
},
|
||||
"model": {
|
||||
"description": "Optional override for the model name (e.g. \"o3\", \"o4-mini\").",
|
||||
"type": "string"
|
||||
},
|
||||
"profile": {
|
||||
"description": "Configuration profile from config.toml to specify default options.",
|
||||
"type": "string"
|
||||
},
|
||||
"prompt": {
|
||||
"description": "The *initial user prompt* to start the LLMX conversation.",
|
||||
"type": "string"
|
||||
},
|
||||
"base-instructions": {
|
||||
"description": "The set of instructions to use instead of the default ones.",
|
||||
"type": "string"
|
||||
},
|
||||
"developer-instructions": {
|
||||
"description": "Developer instructions that should be injected as a developer role message.",
|
||||
"type": "string"
|
||||
},
|
||||
"compact-prompt": {
|
||||
"description": "Prompt used when compacting the conversation.",
|
||||
"type": "string"
|
||||
},
|
||||
},
|
||||
"required": [
|
||||
"prompt"
|
||||
]
|
||||
}
|
||||
});
|
||||
assert_eq!(expected_tool_json, tool_json);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn verify_llmx_tool_reply_json_schema() {
|
||||
let tool = create_tool_for_llmx_tool_call_reply_param();
|
||||
let tool_json = serde_json::to_value(&tool).expect("tool serializes");
|
||||
let expected_tool_json = serde_json::json!({
|
||||
"description": "Continue an LLMX conversation by providing the conversation id and prompt.",
|
||||
"inputSchema": {
|
||||
"properties": {
|
||||
"conversationId": {
|
||||
"description": "The conversation id for this LLMX session.",
|
||||
"type": "string"
|
||||
},
|
||||
"prompt": {
|
||||
"description": "The *next user prompt* to continue the LLMX conversation.",
|
||||
"type": "string"
|
||||
},
|
||||
},
|
||||
"required": [
|
||||
"conversationId",
|
||||
"prompt",
|
||||
],
|
||||
"type": "object",
|
||||
},
|
||||
"name": "llmx-reply",
|
||||
"title": "LLMX Reply",
|
||||
});
|
||||
assert_eq!(expected_tool_json, tool_json);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user