- Added Cursor OAuth provider support to CLI authentication flow.
- Fixed race conditions in OAuth callback handling and session picker cleanup.
- Improved JWT token parsing and error handling across OAuth providers.
- Replaced Bun.sleep() with abortable sleep for proper cancellation support.
- Enhanced process execution with concurrent stream reading and better timeout handling.
- Added cache cleanup mechanism for auth storage with 5-minute intervals.
- Created new @oh-my-pi/pi-utils workspace package with shared utilities for logging, process management, stream handling, and temporary directory management.
- Migrated all packages to use centralized logger from @oh-my-pi/pi-utils instead of local winston implementations.
- Replaced custom process spawning and stream reading implementations with standardized cspawn and readLines utilities across all modules.
- Converted synchronous file operations and process spawning to async patterns using Bun shell syntax and fs/promises.
- Added streaming edit abort functionality with configurable setting to abort on patch preview failures.
- Updated test framework from vitest to bun:test across all test suites.
- Added OAuth callback server with automatic port fallback and CSRF protection.
- Added persistent SQLite-based credential storage replacing auth.json file system.
- Added logout and status CLI commands for OAuth provider management.
- Refactored all OAuth flows to use common OAuthCallbackFlow base class.
- Added automatic regex pattern validation with fallback to literal mode in grep tool.
- Enhanced OAuth authentication flow with proper state generation and validation.
- Added configurable cache control support for tool blocks and user text messages.
- Improved security with increased PKCE verifier size and better token handling.
- Simplified OAuth tool name handling and unified client creation flows.
- Added normative rewrite and read line numbers settings for tool configuration.
- Enhanced edit and write tools with streaming preview and spinner animation.
- Improved normative patch tool to auto-derive anchors from diff hunks.
- Updated read tool to respect default line numbers setting.
- Reformatted code indentation and spacing across multiple TypeScript files.
- Standardized export statements to single-line format in various modules.
- Fixed async/await precedence and corrected indentation in benchmark files.
- Added benchmark report files for GPT-5.1-codex-mini model performance.
- Added normative patch generation for canonicalizing edit tool output.
- Implemented tool call argument rewriting for session history persistence.
- Enhanced patch applicator to support normalized patch input processing.
- Updated agent and AI types to include normative input parameters.
- Removed tar-stream dependency and replaced with Bun.Archive for benchmark package.
- Enhanced patch applicator with fallback variant generation and improved fuzzy matching.
- Added support for ellipsis placeholders, top-of-file anchors, and comment-prefix normalization.
- Renamed operation and moveTo parameters to op and rename across patch tool interfaces.
- Added batch processing system to benchmark runner for parallel task execution.
- Added comprehensive benchmark reports for Claude Haiku and GPT-5.1-codex-mini models.
- Added new @oh-my-pi/react-edit-benchmark package for React source code mutation testing.
- Added --no-title flag to disable automatic session title generation in coding-agent.
- Changed default behavior of read tool to omit line numbers by default.
- Added environment variable support for edit tool configuration and fuzzy matching.
- Updated test files to use import.meta.dir for ES module compatibility.
- Added Prettier configuration and CI improvements for private package handling.
- Added allowFuzzy option to control fuzzy matching behavior in patch operations.
- Added validation for line numbers to ensure they are >= 1 in patch headers and hints.
- Enhanced fuzzy matching algorithms to respect the allowFuzzy setting for precise control.
- Fixed patch application to prefer actual diff over cached preview when displaying results.
Previously, substring context matching required the pattern to be at least
30% of the line length to prevent ambiguous matches. This caused failures
when matching short identifiers like 'class EditTool' against long export
lines with generics and implements clauses.
Now, if exactly one substring match exists in the file, it is accepted
regardless of the ratio threshold - uniqueness alone is sufficient for
disambiguation. The ratio filter is only applied when multiple substring
matches exist.
Added regression tests for model edit attempts from session analysis.
- Added support for nested @@ context anchors and hierarchical context matching.
- Enhanced patch parser to handle @@ line N syntax and multiple context accumulation.
- Improved diff rendering and error messages with hierarchical context display.
- Added comprehensive regression tests for model-generated patch formats.
- Refactored output sanitization logic into centralized streaming-output module.
- Converted tool implementations from factory functions to class-based architecture.
- Updated SSH executor to use shared output streaming infrastructure.
- Moved voice recording logic from function to class-based implementation.
- Converted all tool implementations from factory functions to class-based architecture.
- Updated SDK exports to expose tool classes instead of create*Tool factory functions.
- Refactored tool instantiation patterns across all built-in tools and test files.
- Added proper TypeScript typing with AgentToolResult and AgentToolUpdateCallback interfaces.
- Added comprehensive apply-patch mode for edit tool with create, update, delete, rename operations.
- Converted edit tool from factory function to class-based implementation with improved API.
- Enhanced patch application with ambiguity detection, fuzzy matching, and better error handling.
- Added line ending preservation, BOM handling, and trailing newline policy for file formatting.
- Added validation for empty oldText and multi-file patch rejection to improve reliability.
- Refactored edit tool implementation with modular patch architecture.
- Moved edit tool implementation from edit/ to patch/ module.
- Updated import paths for EditToolDetails across core modules.
- Enhanced patch parsing with unified diff and Codex-style patch support.
- Improved fuzzy matching algorithms for more robust text location.
- Added ToolCallContext interface with batch execution metadata including batchId, index, and total.
- Enhanced getToolContext() to accept optional ToolCallContext parameter for batch-aware tool execution.
- Implemented LSP batching support to coalesce formatting and diagnostics operations on parallel edits.
- Added comprehensive tests for tool call batch context and LSP writethrough batching functionality.
- Added lspmux integration for LSP server multiplexing to reduce startup time and memory usage.
- Added LSP tool proxy support for subagent workers with async request handling.
- Updated LSP status command to show lspmux connection state and availability.
- Simplified rust-analyzer default configuration by removing custom initOptions and settings.
- Added maxdepth and mindepth parameters to find function for depth-controlled file search.
- Added counter function to count occurrences and sort by frequency.
- Added basenames function to extract base names from paths.
- Fixed biome.json configuration to remove invalid double negation pattern.
- Added Windows ARM64 binary support and architecture detection in installers.
- Updated WASM loading to use streaming with base64 fallback for binary compatibility.
- Moved TTSR settings to dedicated tab and expanded abbreviation to Time Traveling Stream Rules.
- Added comprehensive install testing infrastructure with Docker validation.
- Updated package name from @oh-my-pi/omp-coding-agent to @oh-my-pi/pi-coding-agent.
- Added documentation for Python tool with IPython kernel integration.
- Added documentation for Todo tool with task tracking capabilities.
- Added documentation for new CLI subcommands (config, setup) and xhigh thinking level.
- Updated AI package description to include Bedrock provider.
- Moved test files from src/core to test/core directory.
- Moved test files from src/core/tools to test/tools directory.
- Moved test files from src/discovery to test/discovery directory.
- Updated import paths to reflect new test file locations.
- Replaced external photon-node dependency with vendored WebAssembly implementation.
- Added local photon library with 200+ image processing functions and WASM bindings.
- Updated image conversion and resize utilities to use local photon implementation.
- Added error handling for unknown OAuth providers in AI package.
- Added Python shared gateway setting for resource-efficient kernel reuse across sessions.
- Enhanced Python tool with session-scoped kernel isolation and workdir-aware session IDs.
- Added Python tool cancellation support with timeout handling and proper cleanup.
- Expanded Python prelude with enhanced file operations, git utilities, and improved output handling.
- Fixed AI provider message transformation for proper tool call handling and error recovery.
- Added structured status events for Python prelude functions with TUI rendering.
- Implemented status event parsing and display system with operation icons.
- Enhanced Python tool renderer to display status events alongside output.
- Added support for rich output using IPython.display.display() in Python tool.
- Added setup subcommand for installing optional feature dependencies.
- Implemented Python component setup with Jupyter kernel package installation.
- Added component status checking via --check flag with JSON output support.
- Created package installation logic using uv (preferred) or pip package managers.
- Added shared Python gateway coordinator with file locking and automatic resource management.
- Added comprehensive Git helpers and line-based operations to Python prelude.
- Enhanced /status command to display Python gateway, LSP servers, and MCP connections.
- Changed default Python tool mode from ipy-only to both for shell execution support.
- Fixed Python tool proxy execution and signal handling in worker processes.
- Added shared Python gateway coordinator for resource-efficient kernel management.
- Implemented automatic idle shutdown for shared Python gateway after 30 seconds.
- Added environment filtering for shared Python gateway to exclude API keys.
- Updated Python kernel startup to use shared gateway by default with fallback support.
- Fixed Python tool session requirement for proxy executor in workers.
- Added IPython-backed Python tool with streaming output and image/JSON rendering.
- Implemented Jupyter kernel gateway integration with WebSocket communication.
- Added Python prelude with 30+ shell-like utility functions for file operations.
- Migrated environment variables from PI_ to OMP_ prefix with automatic migration.
- Added streaming output system with automatic spill-to-disk for large outputs.
- Reorganized settings interface into behavior, tools, display, voice, status, lsp, and exa tabs.
- Updated model selector to use TabBar component for provider navigation.
- Added support for /models command alias in addition to /model command.
- Changed role badges to inverted style with colored backgrounds.
- Enhanced TabBar component with text wrapping for overflow content.
- Added automatic retry logic for OpenAI Codex responses with configurable delay and max retries.
- Added input event handlers for extensions to intercept user input and argument completion support.
- Added Emacs-style kill ring for text deletion operations with Alt+D and Ctrl+Y keybindings.
- Added configurable editor padding via editorPaddingX theme option and setMaxHeight() method.
- Fixed tool prefix handling in Claude provider to use case-insensitive comparison.
- Enhanced Kitty keyboard protocol support for better key detection and shifted symbol handling.
- Updated User-Agent header from 'opencode' to 'pi' for OpenAI Codex requests.
- Simplified Codex system prompt instructions and removed bridge text override.
- Removed bridge text parameter from buildCodexSystemPrompt function.
- Updated task execution guidelines with parallelization instructions.
- Improved model resolution to accept pre-serialized settings for better performance.
- Enhanced system prompt guidance for position-addressed vs content-addressed file edits.
- Added comprehensive edit tool documentation with bash alternatives comparison.
- Refactored model resolver to accept optional settings parameters for role resolution.
- Added Vercel AI Gateway model fetching with 100+ model configurations.
- Updated Amazon Bedrock models with new Claude 4.5 EU variants.
- Added GPT-5.2-codex model across OpenAI, GitHub Copilot, and OpenCode providers.
- Changed MiniMax models to use anthropic-messages API format.
- Added thinkingFormat support to ZAI provider models.
- Improved LSP diagnostic output by stripping clippy URLs and noise.
- Replaced detailed Codex system instructions with simplified pi assistant instructions that reference internal documentation via pi-internal:// protocol.
- Reduced Codex instructions from 321 lines to 11 lines by moving detailed guidance to referenced documentation.
- Changed assistant identity from 'coding agent running in opencode' to 'pi, an expert coding assistant'.
- Added documentation references for creating custom models, providers, extensions, themes, skills, and TUI components.
- Expanded bash tool guidance to explicitly list appropriate use cases including file operations, build commands, and process management.
- Reframed bash guidance from negative-only to showing both appropriate and inappropriate uses.
- Fixed stale diagnostic results by tracking diagnostic versions before file sync operations.
- Fixed race condition where LSP diagnostics could return outdated results after file modifications.
can1357