valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,916 Commits 9 Branches 11 Tags
0c2c36e14e5731a3d90c053153e6db18dd2fc5f0
Commit Graph

4 Commits

Author SHA1 Message Date
Sebastian Krüger
a6c537ac50 Phase 2 Part 2: Fix Rust compilation errors after rename 
Fixed all compilation errors resulting from the crate rename:

- Fixed FunctionCallOutputPayload::from() double reference issue in response_processing.rs:61
  - Removed unnecessary & as call_tool_result was already a reference
- Fixed spawn_task method call in llmx.rs by adding & reference to Arc<Session>
- Fixed Arc type inference by adding explicit type annotations
- Fixed tokio::join! type inference by separating future creation
- Updated all remaining crate::codex imports to crate::llmx across:
  - tools/orchestrator.rs
  - tools/handlers/shell.rs
  - apply_patch.rs
  - compact.rs
  - unified_exec/mod.rs
  - tools/context.rs
  - tools/sandboxing.rs
  - tools/events.rs

Successfully verified with cargo check --bin llmx (31.50s compile time).

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-11 14:41:08 +01:00
Sebastian Krüger
27909b7495 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
 2025-11-11 14:33:00 +01:00
Sebastian Krüger
cb8d941adf Phase 2: Rust Workspace Transformation (Part 1) 
- Renamed directory: codex-backend-openapi-models -> llmx-backend-openapi-models
- Updated all Cargo.toml files:
  - Package names: codex-* -> llmx-*
  - Library names: codex_* -> llmx_*
  - Workspace dependencies updated
- Renamed Rust source files:
  - codex*.rs -> llmx*.rs (all modules)
  - codex_conversation -> llmx_conversation
  - codex_delegate -> llmx_delegate
  - codex_message_processor -> llmx_message_processor
  - codex_tool_* -> llmx_tool_*
- Updated all Rust imports:
  - use codex_* -> use llmx_*
  - mod codex* -> mod llmx*
- Updated environment variables in code:
  - CODEX_HOME -> LLMX_HOME
  - .codex -> .llmx paths
- Updated protocol crate lib name for proper linking

Note: Some compilation errors remain (type inference issues) but all
renaming is complete. Will fix compilation in next phase.

🤖 Generated with Claude Code
 2025-11-11 14:29:57 +01:00
Sebastian Krüger
f237fe560d Phase 1: Repository & Infrastructure Setup 
- Renamed directories: codex-rs -> llmx-rs, codex-cli -> llmx-cli
- Updated package.json files:
  - Root: llmx-monorepo
  - CLI: @llmx/llmx
  - SDK: @llmx/llmx-sdk
- Updated pnpm workspace configuration
- Renamed binary: codex.js -> llmx.js
- Updated environment variables: CODEX_* -> LLMX_*
- Changed repository URLs to valknar/llmx

🤖 Generated with Claude Code
 2025-11-11 14:01:52 +01:00