- Added `repeatToolDescriptions` configuration setting to control tool description rendering in system prompts.
- Implemented conditional tool display logic that renders full tool descriptions when enabled or a concise comma-separated list when disabled.
- Threaded `repeatToolDescriptions` setting through SDK and system prompt building pipeline.
- Added animated microphone icon with color cycling during voice recording and transcription states.
- Added support for discovering skills via symbolic links in the skills directory.
- Changed STT status messages to display via state change callbacks instead of dedicated status line segment.
- Removed dedicated STT status line segment in favor of animated cursor-based feedback.
- Added cursor override feature to TUI editor for customizing end-of-text cursor glyph with ANSI-styled strings.
Cross-platform audio recording with automatic tool detection and
fallback chain (SoX > FFmpeg > arecord > PowerShell mciSendString).
Transcription via Python openai-whisper with automatic pip install
on first use.
Recording:
- SoX with explicit waveaudio device on Windows (-t waveaudio 0)
- FFmpeg with auto-detected dshow device name on Windows
- arecord for ALSA on Linux
- PowerShell mciSendString as zero-dependency Windows fallback
- Process health check after spawn, graceful stop for FFmpeg/PS
- Fallback chain: if one tool fails, tries the next automatically
Transcription:
- Python openai-whisper as primary backend (pip install openai-whisper)
- Custom WAV loader in transcribe.py using Python wave module
- Resamples to 16kHz mono via numpy (no ffmpeg dependency)
- Passes float32 numpy array directly to whisper.transcribe()
- 120s timeout with process kill guard
TUI integration:
- Alt+H keybinding to toggle recording (configurable in keybindings)
- /stt command with on|off|status|setup subcommands
- Status line segment showing REC/STT state
- Transcribed text inserted directly into editor prompt
- Lazy controller instantiation on first use
Settings:
- stt.enabled (default: false)
- stt.language (default: en)
- stt.modelName (default: base.en)
New files: packages/coding-agent/src/stt/{downloader,index,recorder,
setup,stt-controller,transcribe.py,transcriber}.ts
Replace single `theme` setting with `theme.dark` and `theme.light`.
Auto-detection is always on — COLORFGBG determines which slot to use.
On SIGWINCH, re-check COLORFGBG and switch themes if background changed.
Old `theme` setting auto-migrated using luminance detection.
Fixes#65
- Added autonomous memory extraction and consolidation system with two-phase pipeline for extracting durable knowledge and consolidating into reusable skills.
- Added /memory slash command with subcommands (view, clear, reset, enqueue, rebuild) for inspecting and managing memory maintenance.
- Added configurable memory settings including concurrency limits, lease timeouts, token budgets, and rollout age constraints.
- Added memory injection payload that includes learned context in system prompts with operational rules for reading and using memory artifacts.
- Improved system prompt building to support memory guidance injection and enhanced error handling in resolvePromptInput function for multiline input.
- Added automatic retry logic for WebSocket stream closures before response completion with configurable retry budget.
- Changed `providers.openaiWebsockets` setting from boolean to enum with values 'auto', 'off', 'on' for more granular WebSocket policy control.
- Implemented WebSocket stream retry mechanism that attempts reconnection before falling back to SSE transport when retry budget is exhausted.
- Fixed WebSocket stream retry logic to properly handle mid-stream connection closures and preferWebsockets option handling.
- Added helper functions isCodexWebSocketTransportError() and isCodexWebSocketRetryableStreamError() to classify WebSocket errors.
- Reorganized imports across multiple files for better code organization and consistency.
- Added WebSocket transport support for OpenAI Codex responses with automatic fallback to SSE on connection failure.
- Added preferWebsockets option to Agent and Model configurations to hint that WebSocket transport should be preferred when supported by provider implementations.
- Added prewarmOpenAICodexResponses() function to pre-establish WebSocket connections for improved performance.
- Added getProviderDetails() function and getOpenAICodexTransportDetails() function to expose transport state and provider configuration information.
- Added provider details display in session info showing active provider configuration and authentication details.
- Added OpenAI websockets setting to enable WebSocket transport preference for OpenAI Codex models in coding agent configuration.
- Replaced all direct `process.cwd()` calls with `getProjectDir()` utility function across 40+ files to centralize project directory resolution logic.
- Added `getProjectDir()` and `setProjectDir()` functions to `@oh-my-pi/pi-utils/dirs` module to provide abstracted project directory management.
- Made `SessionManager.list()` method asynchronous to support asynchronous session discovery operations.
- Updated default working directory resolution throughout codebase to use `getProjectDir()` instead of `process.cwd()` for improved project directory detection.
- Extracted directory path utilities from multiple packages into a centralized '@oh-my-pi/pi-utils/dirs' module.
- Moved 30+ path helper functions (getAgentDir, getConfigRootDir, getPluginsDir, getMCPConfigPath, etc.) from scattered locations into a single shared utility module.
- Consolidated APP_NAME, CONFIG_DIR_NAME, and VERSION constants into the centralized dirs module for reuse across packages.
- Updated 70+ import statements across packages/ai, packages/coding-agent, packages/stats, and packages/tui to use the new centralized module.
- Removed local path construction logic and replaced with utility function calls for improved maintainability and consistency.
- Deleted packages/coding-agent/src/extensibility/plugins/paths.ts as its functions were moved to the centralized dirs module.
- Changed default edit mode from `patch` to `hashline` for more precise code modifications.
- Changed `readHashLines` setting default from false to true to enable hash line reading by default.
- Added SwiftLint linter client with JSON reporter support for Swift file linting.
- Changed SwiftLint configuration to use 'lint' command with JSON reporter for structured output.
- Changed bash.virtualTerminal default setting from 'on' to 'off' for standard non-interactive execution.
- Implemented SwiftLintClient with lint() method that executes swiftlint with JSON output and converts violations to LSP diagnostics.
- Added bash.virtualTerminal settings option with 'on' (PTY-backed interactive) and 'off' (standard non-interactive) values.
- Added PTY (pseudo-terminal) backed interactive command execution with streaming output support via PtySession class in pi-natives.
- Added PtyStartOptions and PtyRunResult types to configure and report PTY session execution status.
- Added write(), resize(), and kill() methods to PtySession for interactive control of running commands.
- Added interactive bash execution via PTY with real-time terminal rendering and input forwarding in bash-interactive tool.
- Added --no-pty CLI flag and PI_NO_PTY environment variable to disable PTY-based interactive bash execution.
- Added bash.virtualTerminal setting to control PTY-backed interactive execution behavior.
Add support for MiniMax Coding Plan with OpenAI-compatible API:
- New providers: minimax-code (international) and minimax-code-cn (China)
- Environment variables: MINIMAX_CODE_API_KEY and MINIMAX_CODE_CN_API_KEY
- Uses thinkingFormat: 'zai' for reasoning compatibility
- Models: MiniMax-M2, MiniMax-M2.1, MiniMax-M2.1-lightning
- Base URLs: https://api.minimax.io/v1 (intl), https://api.minimaxi.com/v1 (CN)
The Coding Plan is a subscription-based service separate from regular MiniMax API.
- Changed hashline format separator from two spaces to pipe character (|) throughout codebase for consistency.
- Simplified ollama installation checks in test files by replacing execSync with Bun.which() and inverting PI_NO_LOCAL_LLM to PI_LOCAL_LLM environment variable.
- Added early return guards in test beforeAll hooks to skip tests when required tools (ollama, magick) are unavailable.
- Added debug instrumentation to system prompt building via PI_DEBUG_STARTUP environment variable for startup performance monitoring.
- Removed prompt cache retention assertion from openai-codex streaming test.
- Changed hashline display format separator from pipe to two spaces for improved readability.
- Removed `lines` and `hashes` parameters from read tool in favor of automatic file display mode resolution.
- Added `resolveFileDisplayMode` utility to centralize file display mode configuration logic.
- Integrated file display mode settings into grep and read tools for consistent output formatting.
- Consolidated tool parameter types to use schema-derived types via Typebox `Static` utility.
- Updated parseLineRef to handle both legacy pipe-separator and new two-space hashline formats.
- Added mutation preview hints to error messages when edits fail with 'No changes made' errors, showing line numbers, hashes, and added/removed lines.
- Changed formatter to pin JavaScript fixtures to the flow parser to avoid parser-dependent formatting drift.
- Added whitespace preservation logic to treat whitespace-only differences as passing in file verification.
- Added computeHashlineDiff function to compute diffs for hashline-based edits without applying them.
- Added support for hashline edits in tool execution with caching mechanism to avoid redundant diff computations.
- Added formatStreamingHashlineEdits function to format and display hashline edits with configurable limits.
- Enhanced EditRenderArgs interface with optional previewDiff and edits fields for hashline mode support.
- Refactored import paths from absolute package-scoped imports to relative imports for better module resolution.
- Exported `./patch/*` subpath in package.json for direct access to patch utilities.
- Updated import statements to use relative paths instead of package name imports.
- Added hashline edit mode for line-addressed edits using hash-verified line references with xxHash64 integrity verification.
- Replaced `edit.patchMode` boolean setting with `edit.mode` enum supporting 'replace', 'patch', and 'hashline' modes.
- Added `readHashLines` configuration setting to include line hashes in read output for hashline edit mode.
- Implemented `computeLineHash`, `formatHashLines`, `parseLineRef`, `validateLineRef`, and `applyHashlineEdits` utility functions for hashline operations.
- Updated read tool to support optional `hashes` parameter and prioritize hash lines over line numbers when both are requested.
- Changed `getEditModelVariants()` return type from `Record<string, 'patch' | 'replace'>` to `Record<string, EditMode | null>` and removed hardcoded model-specific defaults.
- Added `temperature` configuration setting to control LLM sampling temperature with values from 0 (deterministic) to 1 (creative) to -1 (provider default).
- Added temperature option selector in settings UI with preset values: Default, 0, 0.2, 0.5, 0.7, 1.
- Renamed `settingsInstance` parameter to `settings` in `CreateAgentSessionOptions` for consistency.
- Updated all internal references from `settingsInstance` to `settings` throughout SDK and components.
- Integrated temperature setting into agent configuration and selector controller.
- Migrated console.error() calls to structured logger.warn() and logger.error() throughout codebase.
- Updated os.tmpdir() import style in browser tool from destructured to namespace import.
- Made shell command execution in configuration values asynchronous to prevent blocking the TUI, improving responsiveness during long-running operations.
- Added deduplication of concurrent shell command executions to prevent redundant processing when the same command is requested multiple times simultaneously.
- Enhanced git URL parsing with credential stripping and validation of URI-encoded hash fragments to improve security and robustness.
- Improved @ prefix normalization for path syntaxes to correctly handle well-known patterns while preserving literal paths like '@my-file.txt'.
- Refactored prompt cache key calculation in OpenAI responses to improve code clarity and ensure cache retention is only set when a cache key exists.
- Migrated authentication storage from JSON-based (auth.json) to database-based (agent.db) format across test files and configuration.
- Simplified auth storage discovery in sdk.ts by removing manual path construction and fallback logic in favor of centralized getAgentDbPath() function.
- Removed dbPath instance property from AuthStorage class as database path is now managed centrally.
- Updated environment variable precedence documentation to reflect agent.db instead of auth.json as the lowest priority source.
- Removed OAuth provider section header comments from multiple test files for cleaner test organization.
- Added support for JSON and JSONC configuration file formats without requiring migration to YAML.
- Renamed web search types and functions to remove 'Web' prefix for broader applicability (WebSearchProvider -> SearchProviderId, WebSearchResponse -> SearchResponse, WebSearchTool -> SearchTool, etc.).
- Refactored web search provider system from object-based configuration to class-based architecture with abstract SearchProvider base class and concrete provider implementations.
- Refactored ModelRegistry to use direct constructor instantiation instead of discoverModels() helper function, simplifying model discovery pattern.
- Refactored config system to use new ConfigFile class with schema validation, caching, and multi-format support (JSON, JSONC, YAML).
- Simplified Exa API key discovery to check environment variables only, removing .env file reading logic.
- Added task isolation setting to enable running subagents in isolated git worktrees.
- Made task schema dynamically include isolated parameter only when isolation is enabled.
- Added validation to reject isolated parameter when task isolation is disabled.
- Updated task tool to conditionally render isolation documentation based on feature flag.
- Refactored task schema into factory function to support dynamic isolation configuration.
- Converted class properties to TypeScript parameter properties across 51 files to reduce boilerplate code.
- Removed explicit field declarations and manual assignments in constructors by using TypeScript's parameter property syntax with access modifiers.
- Applied consistent pattern of declaring private readonly and public readonly properties directly in constructor parameters.
- Fixed temporary model roles persisting by using override instead of set in settings initialization.
- Refactored model role assignment to use dedicated overrideModelRoles method instead of manual object manipulation.
- Migrated all environment variable access from Node.js `process.env` to Bun runtime `Bun.env` API across the entire codebase.
- Updated 71 files including source code, tests, documentation, and configuration to use Bun's native environment variable API.
- Added comprehensive environment variables documentation in `packages/coding-agent/docs/environment-variables.md` covering 100+ environment variables organized by category.
- Updated CHANGELOG entries to reflect migration from `process.env` to `Bun.env` and environment variable prefix changes (PI_* vs OMP_*).
- Maintained identical behavior and logic across all changes - only the environment variable access method was updated.
- Added UI dropdown options for `task.maxRecursionDepth` setting with presets (Unlimited, None, Single, Double, Triple).
- Added UI dropdown options for `grep.contextBefore` setting with presets (0-5 lines).
- Added UI dropdown options for `grep.contextAfter` setting with presets (0-10 lines).
- Simplified `task.maxRecursionDepth` description in settings UI to remove specific value examples.
- Migrated environment variable access from direct process.env to centralized getEnv() utility function across all packages.
- Renamed environment variable prefix from OMP_ to PI_ throughout codebase (e.g., OMP_CODING_AGENT_DIR -> PI_CODING_AGENT_DIR).
- Removed automatic environment variable migration from PI_ to OMP_ prefixes via migrate-env.ts module.
- Removed env setting from configuration schema and applyEnvironmentVariables() method from settings.
- Updated CI/CD build configuration to use PI_COMPILED flag instead of OMP_COMPILED.
- Changed venvPath property in PythonRuntime from nullable (string | null) to optional (string | undefined).
- Added terminal-capabilities module with NotifyProtocol enum and notification formatting/sending methods to TerminalInfo class.
- Renamed TERMINAL_INFO export to TERMINAL and consolidated terminal image/capability exports from terminal-image to terminal-capabilities module.
- Removed terminal-image module exports from public API with functionality migrated to terminal-capabilities.
- Simplified notification settings in coding-agent by removing protocol detection logic and delegating to TERMINAL.sendNotification().
- Removed terminal-notify.ts utility module from coding-agent, consolidating notification handling into pi-tui package.
- Added task.maxRecursionDepth setting to control how many levels deep subagents can spawn their own subagents (0=none, 1=one level, 2=two levels, -1=unlimited).
- Added nested task artifact naming with parent task prefixes (e.g., '0-Auth.1-Subtask') to support hierarchical task identification.
- Added taskDepth and parentTaskPrefix options to CreateAgentSessionOptions for supporting nested/subagent sessions.
- Changed task tool spawns configuration from 'explore' to '*' to allow spawning any type of subagent.
- Updated system prompt to unconditionally include parallel delegation guidance for all agent types instead of only coordinators.
- Implemented automatic task tool disabling at maximum recursion depth to prevent excessive task nesting.
- Added Grafana Pyroscope continuous profiling integration for CPU and heap profiling.
- Added seven new Pyroscope configuration settings: enabled, serverAddress, appName, basicAuthUser, basicAuthPassword, tenantID, and flushIntervalMs.
- Added support for Pyroscope configuration via environment variables: PYROSCOPE_URL, PYROSCOPE_APP_NAME, PYROSCOPE_BASIC_AUTH_USER, PYROSCOPE_BASIC_AUTH_PASSWORD, PYROSCOPE_TENANT_ID, and PYROSCOPE_FLUSH_INTERVAL_MS.
- Integrated Pyroscope initialization and shutdown into the main application lifecycle with automatic profiling start/stop.
- Added @pyroscope/nodejs dependency for continuous profiling capabilities.
- Added jsonStringify Handlebars helper to enable safe JSON serialization of template variables in frontmatter generation.
- Improved frontmatter parsing error messages to include source context, making debugging easier when YAML frontmatter parsing fails.
- Added task.maxConcurrency configuration setting with default value of 32 to control concurrent execution limits for subagents.
- Added UI options for task concurrency configuration with 8 preset levels (Unlimited, 1, 2, 4, 8, 16, 32, 64) in the tools settings tab.
- Changed task concurrency to be configurable via task.maxConcurrency setting instead of hardcoded MAX_CONCURRENCY constant.
- Changed concurrency limit calculation to support unlimited concurrency when task.maxConcurrency is set to 0.
- Removed MAX_CONCURRENCY constant and associated hardcoded concurrency limit from task execution.
- Updated task execution to dynamically retrieve maxConcurrency from session settings instead of using imported constant.
- Added 'commit' model role for dedicated commit message generation.
- Exported 'resolveModelOverride' function from model-resolver module for public use.
- Refactored model role system to centralize role configuration in MODEL_ROLES registry.
- Extracted model resolution utilities into dedicated model-resolver module for improved code organization.
- Made 'tag' and 'color' properties optional in ModelRoleInfo interface to support roles without visual indicators.
- Enhanced model selector with defensive null/undefined checks for optional role properties.
- Added default generic type parameter to Model interface, allowing Model to be used without explicit type argument.
- Removed explicit <any> generic type parameters from Model type annotations throughout codebase, leveraging new default parameter.
- Centralized model role system into MODEL_ROLES registry with metadata (tag, name, color) and MODEL_ROLE_IDS array for consistent role management across the codebase.
- Refactored model selector to dynamically generate menu actions from MODEL_ROLES registry instead of hardcoded role definitions.
- Simplified model role resolution by replacing hardcoded role checks with loops over MODEL_ROLE_IDS array.
- Removed support for 'omp/' model role prefix in favor of 'pi/' prefix throughout model selection, task execution, and configuration.
- Added getModelRoles() and overrideModelRoles() helper methods to Settings class for cleaner model role management.
- Added Jina as a new web search provider option alongside existing providers (Exa, Perplexity, and Anthropic).
- Implemented Jina Reader API integration with automatic provider detection based on JINA_API_KEY environment variable.
- Created new Jina provider module with API key detection, search execution, and response transformation.
- Updated web search configuration schema and type definitions to include Jina as a supported provider.
- Split grep context parameter into separate contextBefore and contextAfter options for more granular control over context lines displayed before and after matches.
- Added configurable grep context defaults via grep.contextBefore and grep.contextAfter settings with reduced default values (1 line before, 3 lines after).
- Updated grep tool schema to use context_pre and context_post parameters instead of unified context parameter.
- Maintained backward compatibility by keeping legacy context field in SearchOptions and GrepOptions structs.
- Added resolve_context() function to handle logic for choosing between separate before/after context values or legacy unified context value.
luk