15 Commits

Author	SHA1	Message	Date
Sebastian Krüger	66e0649b01	chore: Bump version to 0.1.9 ... - Wire model_max_output_tokens config to Chat Completions API - Config takes precedence over provider default for max_tokens 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-12-01 00:02:32 +01:00
Sebastian Krüger	3bc152029e	chore: Bump version to 0.1.8 ... This release includes two critical fixes: 1. fix: Accept '*** Create File:' as alias for '*** Add File:' in patch parser - Claude sometimes uses 'Create File' syntax instead of 'Add File' - Parser now accepts both markers to prevent validation failures - Updated error message to include both valid syntaxes 2. fix: Increase default max_tokens from 8192 to 20480 - Claude Sonnet 4.5 was getting cut off mid-task - New default is 5 * 4096 = 20480 tokens - Claude Sonnet 4.5 supports up to 64K tokens - Gives Claude enough space to complete comprehensive tasks 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 20:50:54 +01:00
Sebastian Krüger	ffbd2e38ec	debug: Add extensive logging for finish_reason handling ... Added debug logging to track: - Whether assistant_item and reasoning_item exist when finish_reason is received - Content being emitted - Completed event transmission This revealed the actual bug is in HTTP client layer - responses are being consumed immediately instead of streaming, causing "Request completed" to appear before any SSE chunks are processed. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 19:27:07 +01:00
Sebastian Krüger	0841ba05a8	fix: Handle finish_reason 'length' to prevent hang when hitting max_tokens ... When the response hits the max_tokens limit, the API returns finish_reason="length". Previously, this fell into the catch-all case which didn't emit pending items, causing llmx to hang with "working" status. Now: - Handle "length" the same as "stop" - emit assistant_item and reasoning_item - Also made catch-all case defensive: emit pending items for any unknown finish_reason 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 18:51:48 +01:00
Sebastian Krüger	44dc7a3bed	fix: Emit pending items before Completed when stream closes gracefully ... - When SSE stream closes with Ok(None), now emits pending assistant_item and reasoning_item BEFORE sending Completed event - Previously would send Completed immediately without emitting accumulated messages, causing UI to hang with "working" state - This fixes the hang when API returns 200 OK but SSE stream has no events - Added debug logging for graceful stream closure 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 18:31:24 +01:00
Sebastian Krüger	a3ced1f246	fix: Send Completed event when stream ends without finish_reason ... - Add debug logging for finish_reason to diagnose stream completion issues - When SSE stream ends without sending a finish_reason chunk, emit final items and Completed event - This fixes the "working" hang when the API stream closes without proper completion signal - Fixed duplicate max_tokens fields in test provider definitions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 18:23:12 +01:00
Sebastian Krüger	401b0b3935	fix: Handle empty assistant messages as turn completion ... - When the API returns an empty assistant message (content: []), treat it as turn completion signal - This fixes the "working" hang that occurs after tool calls when the API stream ends with an empty message - Updated parse_agent_message to return None for empty content - Fixes issue where llmx would hang indefinitely waiting for content that never comes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 18:15:24 +01:00
Sebastian Krüger	8f79e89db2	fix: Add max_tokens field to all test ModelProviderInfo initializations ... - Fixed all test files that initialize ModelProviderInfo - Added max_tokens: None to maintain compatibility - Ensures all tests compile with new max_tokens field 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 11:01:31 +01:00
Sebastian Krüger	c0775ad8a3	feat: Make max_tokens configurable via provider config ... - Add max_tokens field to ModelProviderInfo struct - Read from provider config, default to 8192 if not set - Add debug logging for max_tokens value - Allows per-provider customization in config.toml Example config: ```toml [model_providers.litellm] max_tokens = 16384 ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 10:40:15 +01:00
Sebastian Krüger	462b219d3f	feat: Add comprehensive Anthropic prompt caching ... - Add cache_control to system instructions (stable, high value) - Add cache_control to conversation history (4 messages before end) - Implements full Anthropic caching hierarchy: tools → system → history - Significant cost savings for repeated similar requests Cache hierarchy: 1. Tools (last tool) - already implemented 2. System instructions - new 3. Conversation history - new (stable portion) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-16 21:43:01 +01:00
Sebastian Krüger	7d2842885a	chore: Bump version to 0.1.5 ... - Fix orphaned tool_use error by tracking skip state per call_id - Handle retries with same call_id correctly - Add comprehensive debug logging for troubleshooting 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-16 21:08:14 +01:00
Sebastian Krüger	67ff31104f	chore: Bump version to 0.1.4 ... - Fix: Skip empty/whitespace text content blocks - Fix: Validate function call arguments and skip malformed calls - Fix: Skip outputs for skipped function calls to maintain consistency - Resolves Anthropic API errors: - "messages: text content blocks must contain non-whitespace text" - "Extra data: line 1 column 26 (char 25)" (invalid JSON) - "unexpected `tool_use_id` found in `tool_result` blocks" 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-14 19:52:13 +01:00
Sebastian Krüger	866ca2a372	chore: Bump version to 0.1.3 ... - Fix: Skip empty/whitespace-only text content blocks in chat completions - This resolves Anthropic API errors: - "messages: text content blocks must contain non-whitespace text" - "messages: text content blocks must be non-empty" - Updated version strings in all test files and snapshots 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-14 14:30:46 +01:00
Sebastian Krüger	ca37c07257	chore: Remove OpenAI branding and references ... Update project branding to reflect community fork status: - Changed welcome message from "OpenAI's command-line coding agent" to "your command-line coding agent" - Updated system prompt from "led by OpenAI" to "community project" - Removed broken developers.openai.com/llmx documentation URLs - Updated Windows setup instructions with correct npm package name - Removed OpenAI CLA (not applicable to community fork) - Removed OpenAI open source fund documentation - Updated config docs to remove managed configuration references - Changed npm package reference from @openai/llmx to @valknarthing/llmx These changes complete the rebranding from OpenAI's project to an independent community fork while maintaining proper attribution to the original project in README.md. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-13 10:52:57 +01:00
Sebastian Krüger	3c7efc58c8	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>	2025-11-12 20:40:44 +01:00