smashimo/oh-my-pi

Fork 0

Files

T

can1357 c8d5ada528 chore: bump version to 10.0.0

2026-02-01 19:38:28 +01:00

208 KiB

Raw Blame History

Changelog

[Unreleased]

[10.0.0] - 2026-02-01

Added

Added shell subcommand for interactive shell console testing with brush-core
Added --cwd / -C option to set working directory for shell commands
Added --timeout / -t option to configure per-command timeout in milliseconds
Added --no-snapshot option to skip sourcing snapshot from user shell

Fixed

find now returns a single match when given a file path instead of failing with "not a directory"

[9.8.0] - 2026-02-01

Breaking Changes

Removed persistent shell session support; bash execution now uses native bindings via brush-core for improved reliability

Added

Added sessionKey option to bash executor to isolate shell sessions per agent instance
Added shell snapshot support for bash execution to preserve shell state across commands
Added onChunk callback support for streaming command output in real-time

Changed

Refactored bash executor to queue output chunks asynchronously for improved reliability
Updated bash executor to pass environment variables separately as sessionEnv to native bindings
Migrated system information collection to use native bindings from brush-core instead of shell command execution
Updated CPU information to report core count alongside model name
Simplified OS version reporting to use Node.js built-in APIs
Migrated bash command execution from ptree-based persistent sessions to native shell bindings with streaming support
Simplified bash executor to use brush-core native API instead of managing long-lived shell processes
Routed clipboard copy and image paste through native arboard bindings instead of shell commands
Embedded native addon payload for compiled binaries and extract to ~/.omp/natives/<version> on first run

Removed

Removed shell configuration from environment information display
Removed shell-session.ts module providing persistent shell session management
Removed shell session test suite for persistent execution patterns

[9.6.2] - 2026-02-01

Changed

Replaced hardcoded ellipsis strings with Unicode ellipsis character (…) throughout rendering code
Removed format.ellipsis symbol from theme configuration; ellipsis now uses literal Unicode character
Updated truncate() function to truncateToWidth() with simplified API accepting default ellipsis parameter
Simplified formatMoreItems() function signature by removing theme parameter dependency

Removed

Removed format.ellipsis symbol key from theme symbol maps (Unicode, Nerd, and ASCII presets)
Removed ellipsis property from SymbolTheme type

[9.6.1] - 2026-02-01

Fixed

Fixed output handling to prioritize text/markdown over text/plain when both are available, ensuring Markdown content is displayed correctly
Fixed bash command normalization to preserve newlines in heredocs and multiline commands

[9.6.0] - 2026-02-01

Breaking Changes

Replaced SettingsManager class with new Settings singleton providing sync get/set API with background persistence
Changed settings access from method calls (e.g., getTheme()) to path-based access (e.g., settings.get("theme"))
Removed settingsManager parameter from CreateAgentSessionOptions in favor of settingsInstance
Removed loadSettings() export from public API
Removed example file examples/sdk/10-settings.ts demonstrating old SettingsManager API

Added

New Settings singleton class with sync get/set operations and background persistence
Added Settings.isolated() factory for creating isolated settings instances in tests
Added Settings.init() for initializing global settings instance
Added settings global export for convenient access to settings singleton
New settings-schema.ts providing unified, type-safe settings definitions with UI metadata
Added "none" option to doubleEscapeAction setting to disable double-escape behavior entirely (#973 by @juanibiapina)

Changed

Unified settings schema into single source of truth with settings-schema.ts replacing scattered definitions
Refactored settings CLI to use new schema-based path resolution instead of SETTINGS_DEFS
Updated config command examples to use new nested path syntax (e.g., compaction.enabled instead of autoCompact)
Changed InteractiveModeContext.settingsManager to InteractiveModeContext.settings
Updated all internal settings access throughout codebase to use new settings.get() and settings.set() API
Moved DEFAULT_BASH_INTERCEPTOR_RULES from settings-manager to bash-interceptor module

Removed

Deleted settings-manager.ts (2035 lines) - functionality replaced by new Settings singleton
Removed SettingsManager.create(), SettingsManager.acquire(), and SettingsManager.inMemory() factory methods
Removed individual getter/setter methods from settings API (e.g., getTheme(), setTheme(), getCompactionSettings())

Fixed

Respect .gitignore, .ignore, and .fdignore files when scanning package resources for skills, prompts, themes, and extensions

[9.5.1] - 2026-02-01

Changed

Changed persistent shell from opt-out to opt-in (default: off) for improved reliability; enable via Settings > Bash > Persistent shell or OMP_SHELL_PERSIST=1
Added new "Bash" settings tab grouping shell-related settings (force basic shell, persistent shell, interceptor, intercept ls)

[9.5.0] - 2026-02-01

Added

Added head and tail parameters to bash tool to limit output lines without breaking streaming
Added automatic normalization of bash commands to extract | head -n N and | tail -n N patterns into native parameters
Added maxResults parameter to find tool to limit result set at the native layer
Added context-structure template showing required sections (Goal, Constraints, Existing Code, API Contract) with examples of good vs bad context
Added explicit dependency test: 'Can agent B write correct code without seeing agent A's output?' to determine sequencing
Added detailed phased execution pattern with four phases (Foundation, Parallel Implementation, Integration, Dependent Layer) and WASM-to-N-API migration example
Added table of dependency patterns that must be sequential (API creation before bindings, interface definition before implementation, etc.)
Added phased execution guidance for migrations and refactors to prevent parallel work on dependent layers
Added example demonstrating phased execution pattern for porting WASM to N-API with sequential foundation, parallel implementation, integration, and dependent layer phases

Changed

Improved find tool performance by delegating mtime-based sorting to native layer instead of post-processing results in JavaScript
Simplified find tool result processing by removing redundant filesystem stat calls when native metadata is available
Updated bash tool documentation to recommend using head and tail parameters instead of piping through head/tail commands
Updated binary build process to exclude worker files from compilation, reducing binary size
Modified update mechanism to download and install native addon alongside CLI binary for platform-specific functionality
Updated find tool to emit streaming match updates via callback, allowing real-time progress feedback during file searches
Modified find tool to use native match metadata (mtime, fileType) from WASM layer instead of redundant filesystem stats, improving performance
Restructured Task tool documentation to emphasize context quality and explicit API contracts for subagent success
Updated task execution guidance to require structured context with Goal, Constraints, Existing Code, and API Contract sections
Reorganized parallelization rules with explicit dependency patterns and phased execution guidance for migrations
Clarified that response format requirements must go in schema parameter, never in context descriptions
Centralized Python runtime resolution into shared ipy/runtime.ts module, removing duplicate code from kernel and gateway coordinator

Removed

Removed Nushell language server configuration from LSP defaults

Fixed

Fixed race condition in shell session where command completion could occur before stream data was fully processed
Fixed Python gateway spawning console window on Windows by using windowless Python interpreter (pythonw.exe)

[9.4.0] - 2026-01-31

Changed

Migrated environment variable handling to use centralized getEnv() and getEnvApiKey() utilities from pi-ai package for consistent API key resolution across web search providers and image tools
Simplified web search error messages to remove provider-specific configuration hints
Replaced manual space padding with padding() utility function from pi-tui across UI components for consistent whitespace handling
Improved rendering performance for Python cell output by implementing caching in the table and cell results renderers
Updated task tool documentation to clarify that subagents can access parent conversation context via a searchable file, reducing need to repeat information in context parameter
Updated plan mode prompt to guide model toward using edit tool for incremental plan updates instead of defaulting to write

Removed

Removed environment variable denylist that blocked API keys from being passed to subprocesses; API keys are now controlled via allowlist only

[9.3.1] - 2026-01-31

Added

Added getCompactContext() API to retrieve parent conversation context for subagents, excluding system prompts and tool results
Added automatic submit_result tool injection for subagents with explicit tool lists
Added contextFile parameter to pass parent conversation context to subagent sessions

Changed

Updated subagent system prompt to reference parent conversation context file when available
Enhanced subagent system prompt formatting with clearer backtick notation for tool and parameter names

Removed

Removed schema override notification from task summary prompt

[9.2.5] - 2026-01-31

Changed

Clarified that user instructions about delegation override tool-use defaults
Updated coordinator guidance to emphasize Task tool preference for substantial work with improved emphasis on context window limitations
Enhanced context parameter documentation to require self-contained information for subagents, including file contents and user requirements

[9.2.4] - 2026-01-31

Fixed

Prevented interactive commands from blocking on stdin by redirecting from /dev/null in POSIX and Fish shell sessions

[9.2.3] - 2026-01-31

Added

Persistent shell session support for bash tool with environment variable preservation across commands
New shellForceBasic setting to force bash/sh even if user's default shell is different (default: true)
New OMP_SHELL_PERSIST environment variable to control persistent shell behavior (set to 0 to disable)

Changed

Bash tool now reuses a persistent shell session by default on Unix systems for improved performance and state preservation
Replaced Bun file APIs with Node.js fs module for better cross-runtime compatibility
LSP configuration loading is now synchronous instead of async
Shell snapshot generation now sanitizes BASH_ENV and ENV variables to prevent shell exit issues
Shell snapshot caching now per-shell-binary instead of global to avoid cross-shell contamination
System prompt restructured with coordinator-specific guidance for parallel task delegation
Bash tool now reuses a persistent shell session by default on Unix. Set OMP_SHELL_PERSIST=0 to disable or fall back to per-command execution on Windows/unsupported shells.
Added a shellForceBasic setting to force bash/sh and keep environment changes across bash commands (default: true).

Fixed

Shell snapshots now filter unsafe bash options (onecmd, monitor, restricted) to prevent session exits
Git branch detection in status line now works synchronously without race conditions
Shell session initialization properly restores trap handlers and shell functions after command execution
Sanitized BASH_ENV/ENV during persistent shell startup and snapshot creation to prevent basic shells from exiting immediately.
Cached shell snapshots per shell binary to avoid sourcing zsh snapshots in bash sessions.
Filtered unsafe bash options (onecmd/monitor/restricted) out of shell snapshots to prevent session exits.

[9.2.2] - 2026-01-31

Added

Added grep CLI subcommand (omp grep) for testing pattern matching
Added fuzzy matching for model resolution with scoring and ranking fallback
Added 'Open: artifact folder' menu option to debug selector for quick access to session artifacts
Added Kimi API format setting for selecting between OpenAI and Anthropic formats
Added Codex and Gemini web search providers with OAuth and grounding support
Added /debug command with interactive menu for profiling, heap snapshots, session dumps, and diagnostics
Added configurable ask timeout and notification settings
Added gitignore-aware project tree scanning with ripgrep integration
Added project tree visualization to system prompts with configurable depth and entry limits
Added reset() method to CountdownTimer with integration into HookSelectorComponent
Added custom message support to AgentSession via promptCustomMessage() method
Added skill message component for rendering /skill command messages as compact entries
Added model preference matching system for intelligent model selection based on usage history
Added designer agent with UI/UX review and accessibility audit capabilities
Added model-specific edit variant configuration for patch/replace modes
Added automatic browser opening when stats dashboard starts
Added model statistics table and TTFT/throughput metrics to stats dashboard
Added artifact allocation for truncated fetch responses to preserve full content
Added 30-second timeout to ask tool with auto-selection of recommended option
Added recommended parameter (0-indexed) to ask tool for specifying default option
Added JTD to TypeScript converter for rendering schemas in system prompts
Added tools list to system prompt for better agent awareness
Added synthetic message flag for system-injected prompts
Added session compaction enhancements with auto-continue, tool pruning, and remote endpoint support
Added detection and rendering of missing complete tool warning in subagent output
Added outline UI components for bordered list containers
Added macOS NFD normalization and curly quote variant resolution for file paths
Enhanced session compaction with dynamic token ratio adjustment and improved summary preservation

Changed

Simplified find tool API by consolidating path and pattern parameters
Replaced bulk file loading with streaming for read tool to reduce memory overhead
Migrated grep and find tools to WASM-based implementation
Replaced ripgrep-based file listing with glob-based file discovery for project scans
Updated minimum Bun runtime requirement to >=1.3.7
Renamed task parameter from output to schema
Renamed complete tool to submit_result for clarity and consistency
Improved output preview logic: shows full output for ≤30 lines, truncates to 10 lines for larger output

Fixed

Enhanced error reporting with debug stack trace when DEBUG env is set
Improved OAuth token refresh error handling to distinguish transient vs definitive failures
Added windowsHide option to child process spawn calls to prevent console windows on Windows
External edits to config.yml are now preserved when omp reloads or saves settings
Exposed LSP server startup errors in session display and logs
Improved error handling and security in agent storage initialization with restrictive file permissions
Fixed LSP server display showing unknown when server warmup fails
Preserved null timeout when user disables ask timeout setting
Removed incorrect timeout unit conversion logic in cursor, fetch, gemini-image, and ssh tools
Blocked /fork command while streaming to prevent split session logs

[9.0.0] - 2026-01-29

Fixed

External edits to config.yml are now preserved when omp reloads or saves unrelated settings. Previously, editing config.yml directly (e.g., removing a package from packages array) would be silently reverted on next omp startup when automatic setters like setLastChangelogVersion() triggered a save. (#1046 by @nicobailonMD)

[8.13.0] - 2026-01-29

Added

Added /debug command with interactive menu for bug report generation:
- Report: performance issue - CPU profiling with reproduction flow
- Report: dump session - Immediate session bundle creation
- Report: memory issue - Heap snapshot with bundle
- View: recent logs - Display last 50 log entries
- View: system info - Show environment details
- Clear: artifact cache - Remove old session artifacts

Fixed

Fixed LSP server errors not being visible in /session output or logs when startup fails

[8.12.7] - 2026-01-29

Fixed

Fixed LSP servers showing as "unknown" in status display when server warmup fails
Fixed Read tool loading entire file into memory when offset/limit was specified

[8.12.2] - 2026-01-28

Changed

Replaced ripgrep-based file listing with fs.glob for project scans and find/read tooling

[8.11.14] - 2026-01-28

Changed

Rendered /skill command messages as compact skill entries instead of full prompt text

[8.8.8] - 2026-01-28

Added

Added /fork command to create a new session with the exact same state (entries and artifacts) as the current session

Changed

Renamed the complete tool to submit_result for subagent result submission

[8.6.0] - 2026-01-27

Added

Added plan model role for specifying the model used by the plan agent
Added --plan CLI flag and OMP_PLAN_MODEL environment variable for ephemeral plan model override
Added plan model selection in model selector UI with PLAN badge

Changed

Task tool subagents now execute in-process instead of using worker threads

Fixed

Queued skill commands as follow-ups when the agent is already streaming to avoid load failures
Deduplicated repeated review findings in subagent progress rendering
Restored MCP proxy tool timeout handling to prevent subagent hangs

[8.5.0] - 2026-01-27

Added

Added subagent support for preloading skill contents into the system prompt instead of listing available skills
Added session init entries to capture system prompt, task, tools, and output schema for subagent session logs

Fixed

Reduced Task tool progress update overhead to keep the UI responsive during high-volume streaming output
Fixed subagent session logs dropping pre-assistant entries (user/task metadata) before the first assistant response

Removed

Removed enter-plan-mode tool

[8.4.5] - 2026-01-26

Added

Model usage tracking to record and retrieve most recently used models
Model sorting in selector based on usage history

Changed

Renamed head_limit parameter to limit in grep and find tools for consistency
Added context as an alias for the c context parameter in grep tool
Made hidden files inclusion configurable in find tool via hidden parameter (defaults to true)
Added support for reading ignore patterns from .gitignore and .ignore files in find tool

Fixed

Respected .gitignore rules when filtering find tool results by glob pattern

[8.4.2] - 2026-01-25

Changed

Clarified and condensed plan mode prompts for improved clarity and consistency

[8.4.1] - 2026-01-25

Added

Added core plan mode with plan file approval workflow and tool gating
Added plan:// internal URLs for plan file access and subagent plan-mode system prompt
Added plan mode toggle shortcut with paused status indicator

Fixed

Fixed plan reference injection and workflow prompt parameters for plan mode
Fixed tool downloads hanging on slow/blocked GitHub by adding timeouts and zip extraction fallback
Fixed missing UI notification when tools are downloaded or installed on demand

[8.4.0] - 2026-01-25

Added

Added extension API to set working/loading messages during streaming
Added task worker propagation of context files, skills, and prompt templates
Added subagent option to skip Python preflight checks when Python tooling is unused
Model field now accepts string arrays for fallback model prioritization

Changed

Merged patch application warnings into edit tool diagnostics output
Cached Python prelude docs for subagent workers to avoid repeated warmups
Simplified image placeholders inserted on paste to match Claude-style markers

Fixed

Rewrote empty or corrupted session files to restore valid headers
Improved patch applicator ambiguity errors with match previews and overlap detection
Fixed Task tool agent model resolution to honor comma-separated model lists

[8.3.0] - 2026-01-25

Changed

Added request parameter tracking to LSP tool rendering for better diagnostics visibility
Added async diff computation and Kitty protocol support to tool execution rendering
Refactored patch applicator with improved fuzzy matching (7-pass sequence matching with Levenshtein distance) and indentation adjustment
Added inline rendering flag to bash and fetch tool renderers
Extracted constants for preview formatting to improve code maintainability
Exposed mergeCallAndResult and inline rendering options from tools to their wrappers
Added timeout validation and normalization for tool timeout parameters

Fixed

Fixed output block border rendering (bottom-right corner was missing)
Added background control parameter to output block rendering

[8.2.2] - 2026-01-24

Removed

Removed git utility functions (_git, git_status, git_diff, git_log, git_show, git_file_at, git_branch, git_has_changes) from IPython prelude

[8.2.0] - 2026-01-24

Added

Added omp commit command to generate conventional commits with changelog updates
Added agentic commit mode with commit-specific tools and --legacy fallback
Added configurable settings for map-reduce analysis including concurrency, timeout, file thresholds, and token limits
Added support for excluding YAML lock files (.lock.yml, .lock.yaml, -lock.yml, -lock.yaml) from commit analysis
Added new TUI component library with reusable rendering utilities including code cells, file lists, tree lists, status lines, and output blocks
Added renderCodeCell component for displaying code with optional output sections, supporting syntax highlighting and status indicators
Added renderFileList component for rendering file/directory listings with language icons and metadata
Added renderTreeList component for hierarchical tree-based item rendering with expand/collapse support
Added renderStatusLine component for standardized tool status headers with icons, descriptions, and metadata
Added renderOutputBlock component for bordered output containers with structured sections
Added renderOutputBlock to Bash tool for improved output formatting with status indicators
Added --legacy flag to omp commit for using the deterministic pipeline instead of agentic mode
Added split commit support to automatically create multiple atomic commits for unrelated changes
Added git hunk inspection tools for fine-grained diff analysis in commit generation
Added commit message validation with filler word and meta phrase detection
Added automatic unicode normalization in commit summaries
Added real-time progress output to agentic commit mode showing thinking status, tool calls, and completion summary
Added hunk-level staging support in split commits allowing partial file changes per commit
Added dependency ordering for split commits ensuring commits are applied in correct sequence
Added circular dependency detection with validation errors for split commit plans
Added parallel file analysis with cross-file context awareness via analyze_files tool
Added AGENTS.md context file discovery for commit generation
Added progress indicators during changelog generation and model resolution
Added propose_changelog tool for agent-provided changelog entries in agentic commit workflow
Added fallback commit generation when agentic mode fails, using file pattern analysis and heuristic-based type inference
Added trivial change detection to automatically classify whitespace-only and import-reorganization commits
Added support for pre-computed file observations in commit agent to skip redundant analyze_files calls
Added diff content caching with smart file prioritization to optimize token usage in large changesets
Added lock file filtering (17 patterns including Cargo.lock, package-lock.json, bun.lock) from commit analysis
Added changelog deletion support to remove outdated entries via the changelog proposal interface
Added support for pre-computed changelog entries in commit agent to display existing unreleased sections for potential deletion
Added ExistingChangelogEntries interface to track changelog sections by path for changelog proposal context
Added conditional analyze_files skipping in commit agent when pre-analyzed observations are provided
Added guidance to commit agent prompts instructing subagents to write files directly instead of returning changes for manual application
Added mermaid diagram rendering with terminal graphics support (Kitty/iTerm2) for markdown output
Added renderMermaidToPng utility for converting mermaid code blocks to terminal-displayable PNG images via mmdc CLI
Added mermaid block extraction with content-addressed hashing for deduplication and cache lookup
Added background mermaid pre-rendering in assistant messages for responsive diagram display
Added two-level mermaid caching with pending deduplication to prevent redundant renders
Added Python kernel session pooling with MAX_KERNEL_SESSIONS limit and automatic eviction of oldest sessions
Added automatic idle kernel session cleanup timer (5-minute timeout, 30-second interval)
Added types/assets/index.d.ts for global TypeScript module declarations supporting .md, .py, and .wasm?raw imports
Added bunfig.toml loader configuration for importing markdown, Python, and WASM files as text modules
Added color manipulation utilities (hexToHsv, hsvToHex, shiftHue) to pi-utils for accessible theme adjustments
Added color-blind mode setting for improved accessibility
Added filesystem error type guards (isEnoent, isEacces, isPerm, isEnotempty, isFsError, hasFsCode) to pi-utils for safe error handling
Added tarball installation test Dockerfile to validate npm publish/install flow

Changed

Changed changelog diff truncation limit to be configurable via settings
Changed tool result rendering to use new TUI component library across multiple tools (bash, calculator, fetch, find, grep, ls, notebook, python, read, ssh, write, lsp, web search) for consistent output formatting
Changed Bash tool output rendering to use renderOutputBlock with proper section handling and width-aware truncation
Changed Python tool output rendering to use renderCodeCell component for code cell display with status indicators
Changed Read tool output rendering to use renderCodeCell with syntax highlighting and warnings display
Changed Write tool output rendering to use renderCodeCell for code display with streaming preview support
Changed Fetch tool output rendering to use renderOutputBlock with metadata and content preview sections
Changed LSP tool output rendering to use renderStatusLine and renderOutputBlock for structured output display
Changed Web Search result rendering to use renderOutputBlock with answer, sources, related questions, and metadata sections
Changed Find, Grep, and Ls tools to use renderFileList and renderTreeList for consistent file/item listing
Changed Calculator tool result rendering to use renderTreeList for result item display
Changed Notebook and TodoWrite tools to use new TUI rendering components for consistent output format
Refactored render-utils to move tree-related utilities to TUI module (getTreeBranch, getTreeContinuePrefix)
Changed import organization in sdk.ts for consistency
Changed tool result rendering to merge call and result displays, showing tool arguments (command, pattern, query, path) in result headers for Bash, Calculator, Fetch, Find, Grep, Ls, LSP, Notebook, Read, SSH, TodoWrite, Web Search, and Write tools
Changed Read tool title to display line range when offset or limit arguments are provided
Changed worker instantiation to use direct URL import instead of pre-bundled worker files
Changed omp commit to use agentic mode by default with tool-based git inspection
Changed agentic commit progress output to show real-time thinking previews and structured tool argument details
Changed agentic commit progress output to display full multi-line assistant messages and render tool arguments with tree-style formatting for improved readability
Changed agentic commit progress output to render assistant messages as formatted Markdown with proper word wrapping
Changed output block border color to reflect state (error, success, warning) for improved visual feedback
Changed LSP hover rendering to display documentation text before code blocks in both collapsed and expanded views
Changed Write tool to show streaming preview of content being written with syntax highlighting
Changed Read tool to display resolved path information when reading from URLs or symlinks
Changed Calculator tool result display to show both expression and output (e.g., 2+2 = 4) instead of just the result
Changed Python tool output to group status information under a labeled section for clearer organization
Changed SSH tool output to apply consistent styling to non-ANSI output lines
Changed Todo Write tool to respect expanded/collapsed state and use standard preview limits
Changed Web Search related questions to respect expanded/collapsed state instead of always showing all items
Changed empty and error state rendering across multiple tools (Find, Grep, Ls, Notebook, Calculator, Ask) to include consistent status headers
Changed split commit to support hunk selectors (all, indices, or line ranges) instead of whole-file staging
Changed analyze_file tool to analyze_files for batch parallel analysis of multiple files
Switched agentic commit from auto-generated changelogs to agent-proposed entries with validation and retry logic
Commit agent now resolves a separate smaller model for commit generation instead of reusing the primary model
Normalized code formatting and indentation across tool renderers and UI components
Changed git-file-diff tool to prioritize files by type and respect token budget limits with intelligent truncation
Changed git-overview tool to filter and report excluded lock files separately from staged files
Changed analyze-file tool to include file type inference and enriched related files with line counts
Changed propose-changelog tool to support optional deletion entries for removing existing changelog items
Changed commit agent to accept pre-computed file observations and format them into session prompts
Changed changelog skip condition in applyChangelogProposals to also check for empty deletions object
Changed createCommitTools() to build tools array incrementally with conditional analyze_files inclusion based on enableAnalyzeFiles flag
Changed system prompt guidance to clarify that pre-computed observations prevent redundant analyze_files calls
Removed map-reduce preprocessing phase from commit agent for faster iteration
Changed commit agent to process full diff text directly instead of pre-computed file observations
Changed commit agent initialization to load settingsManager, authStorage, modelRegistry, and stagedFiles in parallel
Changed commit agent prompt to remove pre-computed observations guidance and encourage direct analyze_files usage
Changed AuthStorage from constructor-based instantiation to async factory method (AuthStorage.create())
Changed Python kernel resource management with gateway shutdown on session disposal
Updated TypeScript configuration for better publish-time configuration handling with tsconfig.publish.json
Updated TypeScript and Bun configuration for monorepo-wide build consistency and reduced boilerplate
Removed WASM base64 encoding build script; imports now use Bun loader with wasm?raw query parameter
Unified TypeScript checking pipeline with tsgo-based configuration instead of per-package tsconfig.publish.json boilerplate
Refactored scanDirectoryForSkills to use async/await with concurrent directory scanning via Promise.all
Improved error logging in settings manager for config file access failures
Migrated node module imports from named to namespace imports across all packages for consistency with project guidelines
Improved filesystem error handling in extension loader with additional type guards (isEacces, hasFsCode) for permission and EPERM errors
Changed model discovery to synchronous file operations for more immediate initialization

Fixed

Fixed database busy errors during concurrent access by adding retry logic with exponential backoff when opening storage
Find tool now rejects searches from root directory and enforces a 5-second timeout on fd operations
Commit command now exits cleanly with exit code 0 on success
Handle undefined code parameter in code cell renderer
Fixed indentation formatting in split-commit tool function signature
Fixed changelog application to process proposals containing only deletion entries without additions
Fixed indentation formatting in Python tool output renderer
Fixed Python kernel resource management with proper timing instrumentation for performance monitoring
Fixed model discovery to re-check file existence after JSON to YAML migration
Fixed branch change callbacks in footer component to properly update state after git resolution
Added guard clause in plugin-settings to prevent null reference when settings list is undefined
Fixed agent task discovery to support symlinks and improved error handling for file access failures

[8.0.0] - 2026-01-23

Added

Added antigravity provider support for image generation with Google Cloud authentication
Added support for google-antigravity API credentials in model registry
Added antigravity-specific request handling with SSE streaming
Added projectId parameter to antigravity credentials parsing
Added antigravity provider to preferred image provider selection
Added list-limit utility for consistent result limiting across tools
Added output-utils module with tail buffer and artifact allocation helpers
Added tool-result module for standardized tool result construction
Added truncation summary options to OutputMetaBuilder for better output tracking
Added artifact storage system for truncated tool outputs with artifact:// URL protocol
Added structured output metadata system with fluent OutputMetaBuilder for consistent notices
Added standardized tool error types (ToolError, MultiError, ToolAbortError) for better error handling
Added internal URL routing system with protocol handlers:
agent://<id> - access agent output artifacts
agent://<id>/<path> and agent://<id>?q=<query> - JSON extraction from agent outputs
skill://<name> and skill://<name>/<path> - read skill files and relative paths
rule://<name> - read rule content
URL resolution includes filesystem path in output for bash/python interop
Added fetch tool for URL content retrieval with enhanced processing capabilities
Added isolated option to task tool for git worktree execution with automatic patch generation and application
Added format-prompts script to standardize prompt file formatting

Changed

Updated default line limit from 4000 to 3000 lines for output truncation
Reordered truncation notice to show offset continuation before artifact reference
Applied meta notice wrapper to all tools in createTools function
Updated test expectations to reflect new 3000 line limit
Removed output tool from schema validation test list
Replaced inline output truncation notices with structured metadata system across all tools
Updated bash, python, and ssh executors to track detailed output statistics (total lines/bytes vs output lines/bytes)
Modified artifact storage to use pre-allocated paths instead of inline file writing
Changed message format to use meta field instead of fullOutputPath for truncation information
Updated interactive components to display truncation metadata from structured format
Standardized tool result building with new ToolResultBuilder for consistent metadata handling
Simplified Python gateway coordination by removing reference counting and client tracking
Updated Python gateway to use global shared instance instead of per-process coordination
Modified Python kernel initialization to set working directory and environment per kernel
Updated interactive status display to show Python and venv paths instead of client count
Changed system prompt to clarify CHECKPOINT step 0 timing
Updated Python environment warming to use await instead of void for proper error handling
Updated interactive mode shutdown to use postmortem.quit instead of process.exit
Updated bash tool documentation to clarify specialized tool usage
Updated task tool documentation to escape placeholder syntax in examples
Updated Python environment warming to use await instead of void for proper error handling
Updated interactive mode shutdown to use postmortem.quit instead of process.exit
Updated bash tool documentation to clarify specialized tool usage
Updated task tool documentation to escape placeholder syntax in examples
Updated all tools to use structured metadata instead of inline notices for truncation, limits, and diagnostics
Replaced manual error formatting with ToolError.render() and standardized error handling
Enhanced bash and python executors to save full output as artifacts when truncated
Improved abort signal handling across all tools with consistent ToolAbortError
Renamed task parameter from vars to args throughout task tool interface and updated template rendering to support built-in {{id}} and {{description}} placeholders
Simplified todo-write tool by removing active_form parameter, using single content field for task descriptions
Updated system prompt structure with <important> and <avoid> tags, clearer critical sections, and standardized whitespace handling
Renamed web_fetch tool to fetch and removed internal URL handling (use read tool instead)
Standardized tool parameter names from camelCase to snake_case across edit, grep, python, and todo-write tools
Unified timeout parameters across all tools with auto-conversion from milliseconds and reasonable clamping (1s-3600s for bash/ssh, 1s-600s for python/gemini-image)
Simplified web-search tool by removing advanced parameters (max_tokens, model, search_domain_filter, search_context_size, return_related_questions) and using recency instead of search_recency_filter
Restructured tool documentation with standardized <instruction>, <output>, <critical>, and <avoid> sections across all 18 tools
Updated find tool to always sort results by modification time
Updated bash prompt to use cwd parameter instead of workdir
Improved output truncation limits: bash to 50KB/2000 lines, python to 100KB
Removed model parameter from task and gemini-image tools to use session/provider defaults
Improved MCP tool name handling with explicit server and tool name properties
Marked read tool as non-abortable to improve performance
Converted dynamic imports to static imports in installer and exa tools

Removed

Removed output tool (replaced by agent:// URLs via read tool)
Removed web_fetch tool (replaced by fetch tool)

Fixed

Fixed Python kernel environment initialization for external and shared gateways
Fixed gateway status reporting to include Python and virtual environment paths
Fixed inconsistent error formatting across tools by standardizing on ToolError types
Fixed timeout parameter handling to auto-convert milliseconds to seconds and clamp to reasonable ranges
Fixed whitespace formatting in json-query.ts comment
Fixed interactive shutdown to await postmortem cleanup so Python kernel gateways are terminated
Fixed shared Python gateway reuse across working directories by initializing kernel cwd and env per kernel
Fixed Python gateway coordination to use a single global gateway without ref counting

[7.0.0] - 2026-01-21

Added

Added usage report deduplication to prevent duplicate account entries
Added debug logging for usage fetch operations to aid diagnostics
Added provider sorting in usage display by total usage amount
Added isolated parameter to task tool for running each task in separate git worktrees
Added git worktree management for isolated task execution with patch generation
Added patch application system that applies changes only when all patches are valid
Added working directory information to environment info display
Added /usage command to display provider usage and limits
Added support for multiple usage providers beyond Codex
Added usage report caching with configurable TTL
Added visual usage bars and account aggregation in usage display
Added fetchUsageReports() method to agent session
Added output() function to read task/agent outputs by ID with support for multiple formats and queries
Added session file support to Python executor for accessing task outputs
Added support for jq-like queries when reading JSON outputs
Added offset and limit parameters for reading specific line ranges from outputs
Added "." and "c" shortcuts to continue agent without sending visible message
Added debug logging for usage fetch results to aid /usage diagnostics

Changed

Updated discoverSkills function to return object with skills property
Enhanced usage report merging to combine limits and metadata from duplicate accounts
Improved OAuth credential handling to preserve existing fields when updating
Removed cd function from Python prelude to encourage using cwd parameter
Updated task tool to generate and apply patches when running in isolated mode
Enhanced task tool rendering to display isolated execution status and patch paths
Updated system prompt structure and formatting for better readability
Reorganized tool hierarchy and discipline sections
Added parallel work guidance for task-based workflows
Enhanced verification and integration methodology sections
Updated skills and rules formatting for cleaner presentation
Added stronger emphasis on completeness and quality standards
Refactored usage tracking from Codex-specific to generic provider system
Updated usage limit detection to work with multiple provider APIs
Changed usage cache to use persistent storage instead of in-memory only
Limited diagnostic messages to 50 items to prevent overwhelming output when processing files with many issues
Changed /dump command to include complete agent context: system prompt, model config, available tools with schemas, and all message types (bash/python executions, custom messages, branch summaries, compaction summaries, file mentions)
Changed /dump format to use YAML instead of JSON for tool schemas and arguments (more readable)

Fixed

Fixed TypeScript error in bash executor by properly typing caught exception
Fixed usage display ordering to show providers with lowest usage first
Fixed task tool result rendering to show fallback text when no results are available
Fixed external editor to work properly on Unix systems by correctly handling terminal I/O
Fixed external editor to show warning message when it fails to open instead of silently failing
Fixed find tool to properly handle no matches case without treating as error
Fixed find tool to wait for fd exit so error messages no longer report exit null
Fixed read tool to properly handle no matches case without treating as error
Fixed orphaned Python kernel gateway processes not being killed on process exit
Fixed /usage provider ordering to sort by aggregate usage (most used last)
Fixed /usage account dedupe to collapse identical accounts using usage metadata

[6.9.69] - 2026-01-21

Added

Added cell-by-cell status tracking with duration and exit code for Python execution
Added syntax highlighting for Python code in execution display
Added template system with {{placeholders}} for task tool context
Added task variables support for filling context placeholders
Added enhanced task progress display with variable values
Added concurrent work handling guidance in system prompt
Added extension system support for user Python execution events
Added Python mode border color theming across all themes
Added Python execution indicator to welcome screen help text
Added omp stats command for viewing AI usage statistics dashboard
Added support for JSON output and console summary of usage statistics
Added configurable port option for stats dashboard server
Added multi-cell Python execution with sequential processing in persistent kernel
Added cell titles for better Python code organization and debugging
Added $ command prefix for user-initiated Python execution in shared kernel
Added $$ prefix variant for Python execution excluded from LLM context

Changed

Updated Python execution to display cells in bordered blocks with status indicators
Changed task tool to use template-based context instead of simple concatenation
Enhanced Python execution component with proper syntax highlighting
Improved patch applicator to preserve exact indentation when intended
Updated task tool schema to require vars instead of task field
Updated Python execution component to use pythonMode theming instead of bashMode
Enhanced UI helpers to handle pending Python components properly
Changed Python tool to use cells array instead of single code parameter
Renamed workdir parameter to cwd in Bash and Python tools for consistency
Updated Python tool to display cell-by-cell output when multiple cells are provided

Fixed

Fixed indentation preservation for exact matches and indentation-only patches
Fixed Python execution status updates to show real-time cell progress
Fixed indentation adjustment logic to handle edge cases with mixed indentation levels
Fixed patch indentation normalization for fuzzy matches, tab/space diffs, and ambiguous context alignment

[6.9.0] - 2026-01-21

Removed

Removed Git tool and all related functionality
Removed voice control and TTS features
Removed worktree management system
Removed bundled wt custom command
Removed voice-related settings and configuration options
Removed @oh-my-pi/pi-git-tool dependency

[6.8.5] - 2026-01-21

Breaking Changes

Changed timeout parameter from seconds to milliseconds in Python tool
Updated PythonExecutorOptions interface to use timeoutMs instead of timeout

Changed

Updated default timeout to 30000ms (30 seconds) for Python tool
Improved streaming output handling and buffer management

[6.8.4] - 2026-01-21

Changed

Updated output sink to properly handle large outputs
Improved error message formatting in SSH executor
Updated web fetch timeout bounds and conversion

Fixed

Fixed output truncation handling in streaming output
Fixed timeout handling in web fetch tool
Fixed async stream dumping in executors

[6.8.3] - 2026-01-21

Changed

Updated keybinding system to normalize key IDs to lowercase
Changed label edit shortcut from 'l' to 'Shift+L' in tree selector
Changed output file extension from .out.md to .md for artifacts

Removed

Removed bundled worktree command from custom commands loader

Fixed

Fixed keybinding case sensitivity issues by normalizing all key IDs
Fixed task artifact path handling and simplified file structure

[6.8.2] - 2026-01-21

Fixed

Improved error messages when multiple text occurrences are found by showing line previews and context
Enhanced patch application to better handle duplicate content in context lines
Added occurrence previews to help users disambiguate between multiple matches
Fixed cache invalidation for streaming edits to prevent stale data
Fixed file existence check for prompt templates directory
Fixed bash output streaming to prevent premature stream closure
Fixed LSP client request handling when signal is already aborted
Fixed git apply operations with stdin input handling

Security

Updated Anthropic authentication to handle manual code input securely

[6.8.1] - 2026-01-20

Fixed

Fixed unhandled promise rejection when tool execution fails by adding missing .catch() to floating .finally() chain in createAbortablePromise

[6.8.0] - 2026-01-20

Added

Added streaming abort setting to control edit tool behavior when patch preview fails

Changed

Replaced internal logger with @oh-my-pi/pi-utils logger across all modules
Updated process spawning to use cspawn and ptree utilities from pi-utils
Migrated file operations to use async fs/promises and Bun file APIs
Refactored promise handling to use Promise.withResolvers and utility functions
Updated timeout and abort handling to use standardized utility functions
Refactored authentication login method to use OAuthController interface instead of individual callbacks

Fixed

Fixed Python package installation to handle async operations properly
Fixed streaming output truncation to use consistent column limits
Fixed shell command execution to properly handle process cleanup and timeouts
Fixed SSH connection management to properly await async operations
Fixed voice supervisor process cleanup to use proper async handling
Added automatic regex pattern validation in grep tool to handle invalid patterns by switching to literal mode

Security

Updated temporary file cleanup to use secure async removal methods

[6.7.67] - 2026-01-19

Added

Added normative rewrite setting to control tool call argument normalization in session history
Added read line numbers setting to prepend line numbers to read tool output by default
Added streaming preview for edit and write tools with spinner animation
Added automatic anchor derivation for normative patches when anchors not specified

Changed

Enhanced edit and write tool renderers to show streaming content preview
Updated read tool to respect default line numbers setting
Improved normative patch anchor handling to support undefined anchors

[6.7.0] - 2026-01-19

Added

Normative patch generation to canonicalize edit tool output with tool call argument rewriting for session history
Patch matching fallback variants: trimmed context, collapsed duplicates, single-line reduction, comment-prefix normalization
Extended anchor syntax: ellipsis placeholders, top of file/start of file, @@ line N, nested @@ anchors, space-separated hierarchical contexts
Relaxed fuzzy threshold fallback and unique substring acceptance for context matching
Added --no-title flag to disable automatic session title generation
Environment variables for edit tool configuration (OMP_EDIT_VARIANT, OMP_EDIT_FUZZY, OMP_EDIT_FUZZY_THRESHOLD)
Configurable fuzzy matching threshold setting (0.85 lenient to 0.98 strict)
Apply-patch mode for edit tool (edit.patchMode setting) with create, update, delete, and rename operations
Added MCP tool caching for faster startup with cached tool definitions

Changed

Patch applicator now supports normalized input, implicit context lines, and improved indentation adjustment
Patch operation schema uses 'op' instead of 'operation' and 'rename' instead of 'moveTo'
Fuzzy matching tries comment-prefix normalized matches before unicode normalization
Updated patch prompts with clearer anchor selection rules and verbatim context requirements
Changed default behavior of read tool to omit line numbers by default
Changed default edit tool mode to use apply-patch format instead of oldText/newText
Converted tool implementations from factory functions to class-based architecture
Refactored edit tool with modular patch architecture (moved from edit/ to patch/ module)
Enhanced patch parsing: unified diff format, Codex-style patches, nested anchors, multi-file markers
Improved fuzzy matching with multiple match tracking, ambiguity detection, and out-of-order hunk processing
Better diff rendering: smarter truncation, optional line numbers, trailing newline preservation
Improved error messages with hierarchical context display using > separator
Centralized output sanitization in streaming-output module
Enhanced MCP startup with deferred tool loading and cached fallback

Fixed

Patch application handles repeated context blocks, preserves original indentation on fuzzy match
Ambiguous context matching resolves duplicates using adjacent @@ anchor positioning
Patch parser handles bare *** terminators, model hallucination markers, line hint ranges
Function context matching handles signatures with and without empty parentheses
Fixed session title generation to respect OMP_NO_TITLE environment variable
Fixed Python module discovery to use import.meta.dir for ES module compatibility
Fixed LSP writethrough batching to flush when delete operations complete a batch
Fixed line number validation, BOM detection, and trailing newline preservation in patches
Fixed hierarchical context matching and space-separated anchor parsing
Fixed fuzzy matching to avoid infinite loops when allowFuzzy is disabled
Fixed tool completion logic to only mark tools as complete when streaming is not aborted or in error state
Fixed MCP tool path formatting to correctly display provider information

[6.2.0] - 2026-01-19

Changed

Improved LSP batching to coalesce formatting and diagnostics for parallel edits
Updated edit and write tools to support batched LSP operations

Fixed

Coalesced LSP formatting/diagnostics for parallel edits so only the final write triggers LSP across touched files

[6.1.0] - 2026-01-19

Added

Added lspmux integration for LSP server multiplexing to reduce startup time and memory usage
Added LSP tool proxy support for subagent workers
Updated LSP status command to show lspmux connection state
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

Changed

Simplified rust-analyzer default configuration by removing custom initOptions and settings

[6.0.0] - 2026-01-19

Added

Added Cursor and OpenAI Codex OAuth providers
Added Windows installer bash shell auto-configuration
Added dedicated TTSR settings tab (separated from Voice/TTS)

Fixed

Fixed TTSR abbreviation expansion from TTSR to Time Traveling Stream Rules

[5.8.0] - 2026-01-19

Changed

Updated WASM loading to use streaming for development environments with base64 fallback
Added scripts directory to published package files

[5.7.68] - 2026-01-18

Changed

Updated WASM loading to use base64-encoded WASM for better compatibility with compiled binaries

Fixed

Fixed WASM loading issues in compiled binary builds

[5.7.67] - 2026-01-18

Changed

Replaced external photon-node dependency with vendored WebAssembly implementation
Updated image processing to use local photon library for better performance

[5.6.70] - 2026-01-18

Added

Added support for loading Python prelude extension modules from user and project directories
Added automatic discovery of Python modules from .omp/modules and .pi/modules directories
Added prioritized module loading with project-level modules overriding user-level modules

[5.6.7] - 2026-01-18

Added

Added Python shared gateway setting to enable resource-efficient kernel reuse across sessions
Added Python tool cancellation support with proper timeout and cleanup handling
Added enhanced Python prelude helpers including file operations, text processing, and Git utilities
Added Python tool documentation rendering with categorized helper functions
Added session-scoped Python kernel isolation with workdir-aware session IDs
Added structured status events for Python prelude functions with TUI rendering
Added status event display system with operation icons and formatted descriptions
Added support for rich output using IPython.display.display() in Python tool
Added setup subcommand to install dependencies for optional features
Added Python setup component to install Jupyter kernel dependencies
Added setup command help with component and option documentation
Added Python tool dependency check in help output
Added file locking mechanism for shared Python gateway to prevent race conditions
Added Python gateway status monitoring with URL, PID, client count, and uptime information
Added comprehensive Git helpers to Python prelude including status, diff, log, show, branch, and file operations
Added line-based operations to Python prelude including line extraction, deletion, insertion, and pattern matching
Added automatic categorization system for Python prelude functions with discoverable documentation
Added enhanced /status command display showing Python gateway, LSP servers, and MCP server connections
Added shared Python gateway coordinator for resource-efficient kernel management across sessions
Added Python shared gateway setting with session-scoped kernel reuse and fallback behavior
Added automatic idle shutdown for shared Python gateway after 30 seconds of inactivity
Added environment filtering for shared Python gateway to exclude sensitive API keys
Added virtual environment detection and automatic PATH configuration for Python gateway
Added IPython-backed Python tool with streaming output, image/JSON rendering, and Jupyter kernel gateway integration
Added Python prelude with 30+ shell-like utility functions for file operations
Added Python tool exposure settings with session-scoped kernel reuse and fallback behavior
Added streaming output system with automatic spill-to-disk for large outputs
Added extension input interception with source metadata and command argument completion
Added extension command context compact() helper plus context usage accessors
Added ExtensionAPI setLabel() for extension and entry labels
Added startup quiet setting to suppress welcome screen and startup messages
Added support for auto-discovering APPEND_SYSTEM.md files
Added support for piped input in non-interactive mode (auto-print mode)
Added global session listing across all project directories with enhanced search metadata
Added session fork prompt when resolving sessions from other projects
Added key hint formatting utilities plus public exports for getShellConfig/getAgentDir/VERSION
Added bash tool timeout display in tool output
Added fuzzy text normalization for improved edit diff matching
Added $@ argument slicing syntax in prompt templates
Added configurable keybindings for expand tools and dequeue actions
Added process title update on CLI startup

Changed

Updated Python tool description to display categorized helper functions with improved formatting
Enhanced Python kernel startup to use shared gateway by default for better resource utilization
Improved Python prelude functions to emit structured status events instead of text output
Updated agent prompts to use bash tool instead of exec for git operations
Changed default Python tool mode from ipy-only to both to enable shell execution
Enhanced Python gateway coordination with Windows environment support and stale process cleanup
Updated Python prelude functions to emit structured status events instead of text output
Enhanced Python tool renderer to display status events alongside output
Improved Python tool output formatting with status event integration
Improved shared Python gateway coordination with environment validation and stale process cleanup
Updated Python prelude to rename bash() function to sh() for consistency
Changed default Python tool mode from "ipy-only" to "both" to enable both IPython and shell execution
Enhanced Python gateway metadata tracking to include Python path and virtual environment information
Improved Python kernel startup to use shared gateway by default for better resource utilization
Updated Python tool to support proxy execution mode for worker processes
Enhanced Python kernel availability checking with faster validation
Optimized Python environment warming to avoid blocking during tool initialization
Reorganized settings interface into behavior, tools, display, voice, status, lsp, and exa tabs
Migrated environment variables from PI* to OMP* prefix with automatic migration
Updated model selector to use TabBar component for provider navigation
Changed role badges to inverted style with colored backgrounds
Added support for /models command alias in addition to /model
Improved error retry detection to include fetch failures
Enhanced session selector search and overflow handling
Updated skill command execution to include skill path metadata
Surfaced loaded prompt templates during initialization
Updated compaction summarization to use serialized prompt text
Cleaned up Python prelude sh() and run() output to only show stdout/stderr without noisy metadata

Fixed

Fixed Python kernel cancellation handling and WebSocket cleanup for in-flight executions
Fixed Python tool session scoping to include workdir and honor sharedGateway settings
Fixed gist sharing output draining to avoid truncated URLs
Fixed streaming output byte accounting and UTF-8 decoder flushing
Fixed Python prelude integration tests to detect virtual environments and cover helper exports
Fixed Python kernel cancellation/timeout handling and WebSocket close cleanup for in-flight executions
Fixed Python output byte accounting and UTF-8 decoder flushing in streaming output
Fixed shared Python gateway coordination (Windows env allowlist, lock staleness, refcount recovery)
Fixed Python tool session scoping to include workdir and honor sharedGateway settings
Fixed subagent Python proxy session isolation and cancellation/timeout propagation
Fixed print-mode cleanup to dispose Python sessions before exit
Fixed gist share output draining to avoid truncated URLs
Fixed explore agent tool list to use bash for git operations
Fixed Python prelude integration tests to detect venv-only Python and cover helper exports

Security

Enhanced Python gateway environment filtering to exclude sensitive API keys and Windows system paths

[5.5.0] - 2026-01-18

Changed

Updated task execution guidelines to improve prompt framing and parallelization instructions

[5.4.2] - 2026-01-16

Changed

Updated model resolution to accept pre-serialized settings for better performance
Improved system prompt guidance for position-addressed vs content-addressed file edits
Enhanced edit tool documentation with clear use cases for bash alternatives

[5.3.0] - 2026-01-15

Changed

Expanded bash tool guidance to explicitly list appropriate use cases including file operations, build commands, and process management

[5.2.1] - 2026-01-14

Fixed

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

[5.2.0] - 2026-01-14

Added

Added withLines parameter to read tool for optional line number output (default: true, cat -n format)

Changed

Changed find/grep/ls tool output to render inline without background box for cleaner visual flow

Fixed

Fixed task tool abort to return partial results instead of failing (completed tasks preserved, cancelled tasks shown as skipped)
Fixed TUI crash when bash output metadata lines exceed terminal width on narrow terminals
Fixed find tool not matching **/filename patterns (was incorrectly using --full-path for glob depth wildcards)

[5.1.1] - 2026-01-14

Fixed

Fixed clipboard image paste getting stuck on Wayland when no image is present (was falling back to X11 and timing out)

[5.1.0] - 2026-01-14

Changed

Updated light theme colors for WCAG AA compliance (4.5:1 contrast against white background)
Changed dequeue hint text from "restore" to "edit all queued messages"

Fixed

Fixed session selector staying open when current folder has no sessions (shows hint to press Tab)
Fixed print mode JSON output to emit session header at start
Fixed "database is locked" SQLite errors when running subagents by serializing settings to workers instead of opening the database
Fixed /new command to create a new session file (previously reused the same file when --session was specified)
Fixed session selector page up/down navigation

[5.0.1] - 2026-01-12

Changed

Replaced wasm-vips with Photon for more stable WASM image processing
Added graceful fallback to original images when image resizing fails
Added error handling for image conversion failures in interactive mode to prevent crashes
Replace wasm-vips with Photon for more stable WASM image processing (fixes worker thread crashes)

[5.0.0] - 2026-01-12

Added

Implemented xhigh thinking level for Anthropic models with increased reasoning limits

[4.8.3] - 2026-01-12

Changed

Replace sharp with wasm-vips for cross-platform image processing without native dependencies

[4.8.0] - 2026-01-12

Fixed

Move sharp to optional dependencies with all platform binaries to fix arm64 runtime errors

[4.7.0] - 2026-01-12

Added

Add omp config subcommand for managing settings (list, get, set, reset, path)
Add todoCompletion setting to warn agent when it stops with incomplete todos (up to 3 reminders)
Add multi-part questions support to ask tool via questions array parameter

Changed

Updated multi-select cursor behavior in ask tool to stay on the toggled option instead of jumping to top
Single-file reads now render inline (e.g., Read AGENTS.md:23) instead of tree structure

Fixed

Subagent model resolution now respects explicit provider prefix (e.g., zai/glm-4.7 no longer matches cerebras/zai-glm-4.7)
Auto-compaction now skips to next model candidate when retry delay exceeds 30 seconds

[4.6.0] - 2026-01-12

Added

Add /skill:name slash commands for quick skill access (toggle via skills.enableSkillCommands setting)
Add cwd to SessionInfo for session list display
Add custom summarization instructions option in tree selector
Add Alt+Up (dequeue) to restore all queued messages at once
Add shutdownRequested and checkShutdownRequested() for extension-initiated shutdown

Fixed

Component invalidate() now properly rebuilds content on theme changes
Force full re-render after returning from external editor

[4.4.8] - 2026-01-12

Changed

Changed review finding priority format from numeric (0-3) to string labels (P0-P3) for clearer severity indication
Replaced Type.Union with Type.Literal patterns with StringEnum helper across tool schemas for cleaner enum definitions

[4.4.5] - 2026-01-11

Changed

Removed format: "date-time" from timestamp type conversion in JTD to JSON Schema transformation
Reorganized system prompt to display context, environment, and tools sections before discipline guidelines
Updated system prompt to show file paths more clearly in output
Improved YAML frontmatter parsing with better error messages including source file information

Fixed

Fixed frontmatter parsing to properly report source location when YAML parsing fails

[4.4.4] - 2026-01-11

Added

Added todo_write tool for creating and managing structured task lists during coding sessions
Added persistent todo panel above the editor that displays task progress
Added Ctrl+T keybinding to toggle todo list expansion
Added grouped display for consecutive Read tool calls, showing multiple file reads in a compact tree view
Added todo_write tool and persistent todo panel above the editor

Changed

Changed Ctrl+Enter to insert a newline when not streaming (previously Alt+Enter)
Changed Ctrl+T from toggling thinking block visibility to toggling todo list expansion
Changed system prompt to use more direct, field-oriented language with emphasis on verification and assumptions
Changed temporary model selector keybinding from Ctrl+Y to Alt+P
Changed expand hint text from "Ctrl+O to expand" to "Ctrl+O for more"
Changed Read tool result display to hide content by default, showing only file path and status
Changed Ctrl+T to toggle todo panel expansion

Removed

Removed yaml package dependency in favor of Bun's built-in YAML parser

Fixed

Fixed Alt+Enter to insert a newline when not streaming, instead of submitting the message
Fixed Alt+Enter inserting a new line when not streaming instead of submitting a message
Fixed Cursor provider to avoid advertising the Edit tool, relying on full-file Write operations instead
Fixed prompt template loading to strip leading HTML comment metadata blocks

[4.3.2] - 2026-01-11

Changed

Increased default bash output preview from 5 to 10 lines when collapsed
Updated expanded bash output view to show full untruncated output when available

[4.3.1] - 2026-01-11

Changed

Expanded system prompt with defensive reasoning guidance and assumption checks
Allowed agent frontmatter to override subagent thinking level, clamped to model capabilities

Fixed

Ensured reviewer agents use structured output schemas and include reported findings in task outputs

[4.3.0] - 2026-01-11

Added

Added Cursor provider support with browser-based OAuth authentication
Added default model configuration for Cursor provider (claude-sonnet-4-5)
Added execution bridge for Cursor tool calls including read, ls, grep, write, delete, shell, diagnostics, and MCP operations

Fixed

Improved fuzzy matching accuracy for edit operations when file and target have inconsistent indentation patterns

[4.2.3] - 2026-01-11

Changed

Changed default for hidden option in find tool from false to true, now including hidden files by default

Fixed

Fixed serialized auth storage initialization so OAuth refreshes in subagents don't crash

[4.2.2] - 2026-01-11

Added

Added persistent cache storage for Codex usage data that survives application restarts
Added --no-lsp to disable LSP tools, formatting, diagnostics, and warmup for a session

Changed

Changed SettingsManager.create() to be async, requiring await when creating settings managers
Changed loadSettings() to be async, requiring await when loading settings
Changed discoverSkills() to be async, requiring await when discovering skills
Changed loadSlashCommands() to be async, requiring await when loading slash commands
Changed buildSystemPrompt() to be async, requiring await when building system prompts
Changed loadSkills() to be async, requiring await when loading skills
Changed loadProjectContextFiles() to be async, requiring await when loading context files
Changed getShellConfig() to be async, requiring await when getting shell configuration
Changed capability provider load() methods to be async-only, removing synchronous loadSync API
Updated plan agent with enhanced structured planning process, parallel exploration via explore agent spawning, and improved output format with examples
Removed planner agent command template, consolidating planning functionality into the plan agent

[4.2.1] - 2026-01-11

Added

Added automatic discovery and listing of AGENTS.md files in the system prompt, providing agents with an authoritative list of project-specific instruction files without runtime searching
Added planner built-in agent for comprehensive implementation planning with slow model

Changed

Refactored skill discovery to use unified loadSkillsFromDir helper across all providers, reducing code duplication
Updated skill discovery to scan only skills/*/SKILL.md entries instead of recursive walks in Codex provider
Added guidance to Task tool documentation to isolate file scopes when assigning tasks to prevent agent conflicts
Updated Task tool documentation to emphasize that subagents have no access to conversation history and require all relevant context to be explicitly passed
Revised task agent prompt to clarify that subagents have full tool access and can make file edits, run commands, and create files
OpenAI Codex: updated to use bundled system prompt from upstream
Changed complete tool to make data parameter optional when aborting, while still requiring it for successful completions
Skills discovery now scans only skills/*/SKILL.md entries instead of recursive walks

Removed

Removed architect-plan, implement, and implement-with-critic built-in agent commands

Fixed

Fixed editor border rendering glitch after canceling slash command autocomplete
Fixed login/logout credential path message to reference agent.db

[4.2.0] - 2026-01-10

Added

Added /dump slash command to copy the full session transcript to the clipboard
Added automatic Nerd Fonts detection for terminals like iTerm, WezTerm, Kitty, Ghostty, and Alacritty to set appropriate symbol preset
Added NERD_FONTS environment variable override (1 or 0) to manually control Nerd Fonts symbol preset
Added Handlebars templating engine for prompt template rendering with {{arg}} helper for positional arguments
Added support for custom share scripts at ~/.omp/agent/share.ts to replace default GitHub Gist sharing

Changed

Changed rules system to use read tool for loading rule content instead of dedicated rulebook tool
Separated /export and /dump commands—/export now only exports to HTML file, while /dump copies session transcript to clipboard
Updated /export command to no longer accept --copy flag (use /dump instead)
Changed prompt template rendering to use Handlebars instead of simple string replacement
Updated prompt layout optimization to normalize indentation and collapse excessive blank lines
Changed auth migration to merge credentials per-provider instead of skipping when any credentials exist in database
Migrated settings and auth credential storage from JSON files to SQLite database (agent.db)
Updated credential migration message to reference agent.db instead of auth.json
Renamed Glob tool references to Find tool throughout prompts and documentation
Updated project context formatting to use XML-style tags for clearer structure
Refined bash tool guidance to prefer dedicated tools (read/grep/find/ls) over bash for file operations
Updated system prompt with clearer tone guidelines emphasizing directness and conciseness
Revised workflow instructions to require explicit planning for non-trivial tasks
Enhanced verification guidance to prefer external feedback loops like tests and linters
Added explicit alignment and prohibited behavior sections to improve response quality

Removed

Removed rulebook tool - rules are now loaded via the read tool instead of a dedicated tool

Fixed

Fixed message submission lag caused by synchronous history database writes by deferring DB operations with setImmediate

Security

Hardened file permissions on agent database directory (700) and database file (600) to restrict access

[4.1.0] - 2026-01-10

Added

Added persistent prompt history with SQLite-backed storage and Ctrl+R search

Fixed

Fixed credential blocking logic to correctly check for remaining available credentials instead of always returning true

[4.0.1] - 2026-01-10

Added

Added usage limit error detection to enable automatic credential switching when Codex accounts hit rate limits
Added Codex usage API integration to proactively check account limits before credential selection
Added credential backoff tracking to temporarily skip rate-limited accounts during selection
Multi-credential usage-aware selection for OpenAI Codex OAuth accounts with automatic fallback when rate limits are reached
Consistent session-to-credential hashing (FNV-1a) for stable credential assignment across sessions
Codex usage API integration to detect and cache rate limit status per account
Automatic mid-session credential switching when usage limits are hit

Changed

Changed credential selection to use deterministic FNV-1a hashing for consistent session-to-credential mapping
Changed OAuth credential resolution to try credentials in priority order, skipping blocked ones

[4.0.0] - 2026-01-10

Added

Exported InteractiveModeOptions type for programmatic SDK usage
Exported additional UI components for extensions: ArminComponent, AssistantMessageComponent, BashExecutionComponent, BranchSummaryMessageComponent, CompactionSummaryMessageComponent, CustomEditor, CustomMessageComponent, FooterComponent, ExtensionEditorComponent, ExtensionInputComponent, ExtensionSelectorComponent, LoginDialogComponent, ModelSelectorComponent, OAuthSelectorComponent, SessionSelectorComponent, SettingsSelectorComponent, ShowImagesSelectorComponent, ThemeSelectorComponent, ThinkingSelectorComponent, ToolExecutionComponent, TreeSelectorComponent, UserMessageComponent, UserMessageSelectorComponent
Exported renderDiff, truncateToVisualLines, and related types for extension use
setFooter() and setHeader() methods on ExtensionUIContext for custom footer/header components
setEditorComponent() method on ExtensionUIContext for custom editor components
supportsUsageInStreaming model config option to control stream_options: { include_usage: true } behavior
Terminal setup documentation for Kitty keyboard protocol configuration (Ghostty, wezterm, Windows Terminal)
Documentation for paid Cloud Code Assist subscriptions via GOOGLE_CLOUD_PROJECT env var
Environment variables reference section in README
--no-tools flag to disable all built-in tools, enabling extension-only setups
--no-extensions flag to disable extension discovery while still allowing explicit -e paths
blockImages setting to prevent images from being sent to LLM providers
thinkingBudgets setting to customize token budgets per thinking level
PI_SKIP_VERSION_CHECK environment variable to disable new version notifications at startup
Anthropic OAuth support via /login to authenticate with Claude Pro/Max subscription
OpenCode Zen provider support via OPENCODE_API_KEY env var and opencode/<model-id> syntax
Session picker (pi -r) and --session flag support searching/resuming by session ID (UUID prefix)
Session ID forwarding to LLM providers for session-based caching (used by OpenAI Codex for prompt caching)
dequeue keybinding (Alt+Up) to restore queued steering/follow-up messages back into the editor
Pluggable operations for built-in tools enabling remote execution via SSH or other transports (ReadOperations, WriteOperations, EditOperations, BashOperations, LsOperations, GrepOperations, FindOperations)
/model <search> pre-filters the model selector or auto-selects on exact match; use provider/model syntax to disambiguate
Managed binaries directory (~/.omp/bin/) for fd and rg tools
FooterDataProvider for custom footers with getGitBranch(), getExtensionStatuses(), and onBranchChange()
ctx.ui.custom() accepts { overlay: true } option for floating modal components
ctx.ui.getAllThemes(), ctx.ui.getTheme(name), ctx.ui.setTheme(name | Theme) for theme management
setActiveTools() for dynamic tool management
setModel(), getThinkingLevel(), setThinkingLevel() methods for runtime model and thinking level changes
ctx.shutdown() for requesting graceful shutdown
pi.sendUserMessage() for sending user messages from extensions
Extension UI dialogs (select, confirm, input) support timeout option with live countdown display
Extension UI dialogs accept optional AbortSignal to programmatically dismiss dialogs
Async extension factories for dynamic imports and lazy-loaded dependencies
user_bash event for intercepting user !/!! commands
Built-in renderers used automatically for tool overrides without custom renderCall/renderResult
InteractiveMode, runPrintMode(), runRpcMode() exported for building custom run modes
Copy link button on messages for deep linking to specific entries
Codex injection info display showing system prompt modifications
URL parameter support for leafId and targetId deep linking
Wayland clipboard support for /copy command using wl-copy with xclip/xsel fallback

Changed

Bash tool output truncation now recalculates on terminal resize instead of using cached width
Web search tool headers updated to match Claude Code client format for better compatibility
discoverSkills() return type documented as { skills: Skill[], warnings: SkillWarning[] } in SDK docs
Default model for OpenCode provider changed from claude-sonnet-4-5 to claude-opus-4-5
Terminal color mode detection defaults to truecolor for modern terminals instead of 256color
System prompt restructured with XML tags and clearer instructions format
before_agent_start event receives systemPrompt in the event object and returns systemPrompt (full replacement) instead of systemPromptAppend
discoverSkills() returns { skills: Skill[], warnings: SkillWarning[] } instead of Skill[]
ctx.ui.custom() factory signature changed from (tui, theme, done) to (tui, theme, keybindings, done)
ExtensionRunner.initialize() signature changed from options object to positional params (actions, contextActions, commandContextActions?, uiContext?)

Fixed

Wayland clipboard copy (wl-copy) no longer blocks when the process doesn't exit promptly
Empty --tools flag now correctly enables all built-in tools instead of disabling them
Bash tool handles spawn errors gracefully instead of crashing the agent
Components properly rebuild their content on theme change via invalidate() override
setTheme() triggers a full rerender so previously rendered components update with new theme colors
Session ID updates correctly when branching sessions
External edits to settings.json while pi is running are preserved when pi saves settings
Default thinking level from settings applies correctly when enabledModels is configured
LM Studio compatibility for OpenAI Responses tool strict mapping
Symlinked directories in prompts/ folders are followed when loading prompt templates
String systemPrompt in createAgentSession() works as a full replacement instead of having context files and skills appended
Update notification for bun binary installs shows release download URL instead of npm command
ESC key works during "Working..." state after auto-retry
Abort messages show correct retry attempt count
Antigravity provider returning 429 errors despite available quota
Malformed thinking text in Gemini/Antigravity responses where thinking content appeared as regular text
--no-skills flag correctly prevents skills from loading in interactive mode
Overflow-based compaction skips if error came from a different model or was already handled
OpenAI Codex context window reduced from 400k to 272k tokens to match Codex CLI defaults
Context overflow detection recognizes context_length_exceeded errors
Key presses no longer dropped when input is batched over SSH
Clipboard image support works on Alpine Linux and other musl-based distros
Queued steering/follow-up messages no longer wipe unsent editor input
OAuth token refresh failure no longer crashes app at startup
Status bar shows correct git branch when running in a git worktree
Ctrl+V clipboard image paste works on Wayland sessions
Extension directories in settings.json respect package.json manifests

[3.37.0] - 2026-01-10

Changed

Improved bash command display to show relative paths for working directories within the current directory, and hide redundant cd prefix when working directory matches current directory

[3.36.0] - 2026-01-10

Added

Added calc tool for basic mathematical calculations with support for arithmetic operators, parentheses, and hex/binary/octal literals
Added support for multiple API credentials per provider with round-robin distribution across sessions
Added file locking for auth.json to prevent concurrent write corruption
Added clickable OAuth login URL display in terminal
Added workdir parameter to bash tool to execute commands in a specific directory without requiring cd commands

Changed

Updated bash tool rendering to display working directory context when workdir parameter is used

Fixed

Fixed completion notification to only send when interactive mode is in foreground
Improved completion notification message to include session title when available

[3.35.0] - 2026-01-09

Added

Added retry logic with exponential backoff for auto-compaction failures
Added fallback to alternative models when auto-compaction fails with the primary model
Added support for pi/<role> model aliases in task tool (e.g., pi/slow, pi/default)
Added visual cycle indicator when switching between role models showing available roles
Added automatic model inheritance for subtasks when parent uses default model
Added -- separator in grep tool to prevent pattern interpretation as flags

Changed

Changed role model cycling to remember last selected role instead of matching current model
Changed edit tool to merge call and result displays into single block
Changed model override behavior to persist in settings when explicitly set via CLI

Fixed

Fixed retry-after parsing from error messages supporting multiple header formats (retry-after, retry-after-ms, x-ratelimit-reset)
Fixed image attachments being dropped when steering/follow-up messages are queued during streaming
Fixed image auto-resize not applying to clipboard images before sending
Fixed clipboard image attachments being dropped when steering/follow-up messages are queued while streaming
Fixed clipboard image attachments ignoring the auto-resize setting before sending

[3.34.0] - 2026-01-09

Added

Added caching for system environment detection to improve startup performance
Added disk usage information to automatic environment detection in system prompt
Added compat option for SSH hosts to wrap commands in a POSIX shell on Windows systems
Added automatic working directory handling for PowerShell and cmd.exe on Windows SSH hosts
Added automatic environment detection to system prompt including OS, distro, kernel, CPU, GPU, shell, terminal, desktop environment, and window manager information
Added SSH tool with project ssh.json/.ssh.json discovery, persistent connections, and optional sshfs mounts
Added SSH host OS/shell detection with compat mode and persistent host info cache

Changed

Changed GPU detection on Linux to prioritize discrete GPUs (NVIDIA, AMD) over integrated graphics and skip server management adapters
Changed SSH host info cache to use versioned format for automatic refresh on schema changes
Changed SSH compat shell detection to actively probe for bash/sh availability on Windows hosts
Changed SSH tool description to show detected shell type and available commands per host

[3.33.0] - 2026-01-08

Added

Added env support in settings.json for automatically setting environment variables on startup
Added environment variable management methods to SettingsManager (get/set/clear)

Fixed

Fixed bash output previews to recompute on resize, preventing TUI line width overflow crashes
Fixed session title generation to retry alternate smol models when the primary model errors or is rate-limited
Fixed file mentions to resolve extensionless paths and directories, using read tool truncation limits for injected content
Fixed interactive UI to show auto-read file mention indicators
Fixed task tool tree rendering to use consistent tree connectors for progress, findings, and results
Fixed last-branch tree connector symbol in the TUI
Fixed output tool previews to use compact JSON when outputs are formatted with leading braces

[3.32.0] - 2026-01-08

Added

Added progress indicator when starting LSP servers at session startup
Added bundled /init slash command available by default

Changed

Changed LSP server warmup to use a 5-second timeout, falling back to lazy initialization for slow servers

Fixed

Fixed Task tool subagent model selection to inherit explicit CLI --model overrides

[3.31.0] - 2026-01-08

Added

Added temporary model selection: Ctrl+Y opens model selector for session-only model switching (not persisted to settings)
Added setModelTemporary() method to AgentSession for ephemeral model changes
Added empty Enter to flush queued messages: pressing Enter with empty editor while streaming aborts current stream
Added auto-chdir to temp directories when starting in home unless --allow-home is set
Added upfront diff parsing and filtering for code review command to exclude lock files, generated code, and binary assets

Fixed

Fixed auto-chdir to only use existing directories and fall back to tmpdir()
Added automatic reviewer agent count recommendation based on diff weight and file count
Added file grouping guidance for parallel review distribution across multiple agents
Added diff preview mode for large changesets that exceed size thresholds
Added in-memory session storage implementation for testing and ephemeral sessions
Added createToolUIKit helper to consolidate common UI formatting utilities across tool renderers
Added configurable bash interceptor rules via bashInterceptor.patterns setting for custom command blocking
Added bashInterceptor.simpleLs setting to control interception of bare ls commands
Added LSP server configuration via external JSON defaults file for easier customization
Added abort signal propagation to web scrapers for improved cancellation handling
Added diagnosticsVersion tracking to LSP client for more reliable diagnostic polling
Added 80+ specialized web scrapers for structured content extraction from popular sites including GitHub, GitLab, npm, PyPI, crates.io, Wikipedia, YouTube, Stack Overflow, Hacker News, Reddit, arXiv, PubMed, and many more
Added site-specific API integrations for package registries (npm, PyPI, crates.io, Hex, Hackage, NuGet, Maven, RubyGems, Packagist, pub.dev, Go packages)
Added scrapers for social platforms (Mastodon, Bluesky, Lemmy, Lobsters, Dev.to, Discourse)
Added scrapers for academic sources (arXiv, bioRxiv, PubMed, Semantic Scholar, ORCID, CrossRef, IACR)
Added scrapers for security databases (NVD, OSV, CISA KEV)
Added scrapers for documentation sites (MDN, Read the Docs, RFC Editor, W3C, SPDX, tldr, cheat.sh)
Added scrapers for media platforms (YouTube, Vimeo, Spotify, Discogs, MusicBrainz)
Added scrapers for AI/ML platforms (Hugging Face, Ollama)
Added scrapers for app stores and marketplaces (VS Code Marketplace, JetBrains Marketplace, Firefox Add-ons, Open VSX, Flathub, F-Droid, Snapcraft)
Added scrapers for business data (SEC EDGAR, OpenCorporates, CoinGecko)
Added scrapers for reference sources (Wikipedia, Wikidata, OpenLibrary, Choose a License)

Changed

Changed Ctrl+P to cycle through role models (slow → default → smol) instead of all available models
Changed Shift+Ctrl+P to cycle role models temporarily (not persisted)
Changed Extension Control Center to scale with terminal height instead of fixed 25-line limit
Changed review command to parse git diff upfront and provide structured context to reviewer agents
Changed session persistence to use structured logging instead of console.error for persistence failures
Changed find tool to use fd command for .gitignore discovery instead of Bun.Glob for better abort handling
Changed LSP config loading to only mark overrides when servers are actually defined
Changed task tool to require explicit task id field instead of auto-generating names from agent type
Changed grep and find tools to use native Bun file APIs instead of Node.js fs module for improved performance
Changed YouTube scraper to use async command execution with proper stream handling
Improved rust-analyzer diagnostic polling to use version-based stability detection instead of time-based delays
Changed theme icons for extension types to use Unicode symbols (✧, ⚒) instead of text abbreviations (SK, TL, MCP)
Changed task tool to use short CamelCase task IDs instead of agent-based naming (e.g., 'SessionStore' instead of 'explore_0')
Changed task tool to accept single agent parameter at top level instead of per-task agent specification
Changed reviewer agent to use complete tool instead of submit_review for finishing reviews
Changed theme icons for extensions to use Unicode symbols instead of text abbreviations
Changed LSP file type matching to support exact filename matches in addition to extensions
Improved rust-analyzer diagnostic polling to use version-based stability detection
Refactored web-fetch tool to use modular scraper architecture for improved maintainability

Removed

Removed submit_review tool - reviewers now finish via complete tool with structured output

Fixed

Fixed session persistence to call fsync before renaming temp file for durability
Fixed duplicate persistence error logging by tracking whether error was already reported
Fixed byte counting in task output truncation to correctly handle multi-byte Unicode characters
Fixed parallel task execution to propagate abort signals and fail fast on first error
Fixed task worker abort handling to properly clean up on cancellation
Fixed parallel task execution to fail fast on first error instead of waiting for all workers
Fixed byte counting in task output truncation to handle multi-byte Unicode characters correctly

[3.30.0] - 2026-01-07

Added

Added environment variable configuration for task limits: OMP_TASK_MAX_PARALLEL, OMP_TASK_MAX_CONCURRENCY, OMP_TASK_MAX_OUTPUT_BYTES, OMP_TASK_MAX_OUTPUT_LINES, and OMP_TASK_MAX_AGENTS_IN_DESCRIPTION
Added specialized web-fetch handlers for 50+ platforms including GitHub, GitLab, npm, PyPI, crates.io, Stack Overflow, Wikipedia, arXiv, PubMed, Hacker News, Reddit, Mastodon, Bluesky, and many more
Added automatic yt-dlp installation for YouTube transcript extraction
Added YouTube video support with automatic transcript extraction via yt-dlp

Changed

Changed task executor to gracefully handle worker termination with proper cleanup and timeout handling

Fixed

Fixed Lobsters front page handler to use correct API endpoint (/hottest.json instead of invalid .json)
Fixed task worker error handling to prevent hanging on worker crashes, uncaught errors, and unhandled rejections
Fixed double-stringified JSON output from subagents being returned as escaped strings instead of parsed objects
Fixed markitdown tool installation to use automatic tool installer instead of requiring manual installation

[3.25.0] - 2026-01-07

Added

Added complete tool for structured subagent output with JSON schema validation
Added query parameter to output tool for jq-like JSON querying
Added output_schema parameter to task tool for structured subagent completion
Added JTD (JSON Type Definition) to JSON Schema converter for schema flexibility
Added memorable two-word task identifiers (e.g., SwiftFalcon) for better task tracking

Changed

Changed task output IDs from agent_index format to memorable names for easier reference
Changed subagent completion flow to require explicit complete tool call with retry reminders
Simplified worker agent system prompt to be more concise and focused

[3.24.0] - 2026-01-07

Added

Added ToolSession interface to unify tool creation with session context including cwd, UI availability, and rulebook rules
Added Bun Worker-based execution for subagent tasks, replacing subprocess spawning for improved performance and event streaming
Added toolNames option to filter which built-in tools are included in agent sessions
Added BUILTIN_TOOLS registry constant for programmatic access to available tool factories
Added unit tests for createTools function covering tool filtering and conditional tool creation

Changed

Changed subagent execution from spawning separate omp processes to running in Bun Workers with direct event streaming
Changed tool factories to accept ToolSession parameter instead of separate cwd and options arguments
Changed createTools to return tools as a Map and support conditional tool creation based on session context
Changed system prompt builder to dynamically generate tool descriptions from the tool registry
Changed task tool description to be generated from a template with dynamic agent list injection
Changed tool creation to use a unified ToolSession interface instead of separate parameters for cwd, options, and callbacks
Changed createTools to return tools as a Map instead of an array for consistent tool registry access
Changed system prompt builder to receive tool registry Map for dynamic tool description generation
Changed subprocess usage tracking to accumulate incrementally from message_end events rather than parsing stored events after completion

Removed

Removed browser embedded agent from task tool agent discovery
Removed recursive property from agent definitions
Removed environment variables OMP_NO_SUBAGENTS, OMP_BLOCKED_AGENT, and OMP_SPAWNS for subagent control
Removed pre-instantiated tool exports (readTool, bashTool, editTool, writeTool, grepTool, findTool, lsTool) in favor of factory functions
Removed createCodingTools and createReadOnlyTools helper functions
Removed codingTools and readOnlyTools convenience exports
Removed wrapToolsWithExtensions function from extensions API
Removed hidden property support from custom tools
Removed subagent and question custom tool examples

Fixed

Fixed memory accumulation in task subprocess by streaming events directly to disk instead of storing in memory
Fixed session persistence to exclude transient streaming data (partialJson, jsonlEvents) that was causing unnecessary storage bloat
Fixed createTools respecting explicit tool lists instead of returning all non-hidden tools

[3.21.0] - 2026-01-06

Changed

Switched from local @oh-my-pi/pi-ai to upstream @oh-my-pi/pi-ai package

Added

Added webSearchProvider setting to override auto-detection priority (Exa > Perplexity > Anthropic)
Added imageProvider setting to override auto-detection priority (OpenRouter > Gemini)
Added git.enabled setting to enable/disable the structured git tool
Added offset and limit parameters to Output tool for paginated reading of large outputs
Added provider fallback chain for web search that tries all configured providers before failing
Added WebSearchProviderError class with HTTP status for actionable provider error messages
Added bash interceptor rule to block git commands when structured git tool is enabled
Added validation requiring message parameter for git commit operations (prevents interactive editor)
Added output ID hints in multi-agent Task results pointing to Output tool for full logs
Added fuzzy matching support for all: true mode in edit tool, enabling replacement of similar text blocks with whitespace differences
Added all parameter to edit tool for replacing all occurrences instead of requiring unique matches
Added OpenRouter support for image generation when OPENROUTER_API_KEY is set
Added ImageMagick fallback for image processing when sharp module is unavailable
Added slash commands to the extensions inspector panel for visibility and management
Added support for file-based slash commands from commands/ directories
Added $ARGUMENTS placeholder for slash command argument substitution, aligning with Claude and Codex conventions

Changed

Refactored tool renderers to be co-located with their respective tool implementations for improved code organization
Changed web search to try all configured providers in sequence with fallback before reporting errors
Changed default Anthropic web search model from claude-sonnet-4-5-20250514 to claude-haiku-4-5
Changed read tool to show first 50KB of oversized lines instead of directing users to bash sed
Changed web_fetch to use Bun.which() instead of spawning which/where for command detection
Changed web_fetch to check Content-Length header before downloading to reject oversized files early
Changed generate_image tool to save images to temp files and report paths instead of inline base64
Changed system prompt with tool usage guidance (ground answers with tools, minimize context, iterate on results)
Changed Task tool prompt with plan-then-execute guidance and output tool hints
Changed edit tool success message to report count when replacing multiple occurrences with all: true
Changed default image generation model to gemini-3-pro-image-preview
Changed error message for multiple occurrences to suggest using all: true option
Changed web_fetch tool label from web_fetch to Web Fetch for improved display
Changed argument substitution order in slash commands to process positional args ($1, $2) before wildcards ($@, $ARGUMENTS) to prevent re-substitution issues
Changed image tool name from gemini_image to generate_image with label GenerateImage

Fixed

Fixed read tool markitdown truncation message using broken template string (missing ${ around format call)
Fixed web_fetch URL normalization order to run before special handlers
Fixed TUI image display for generate_image tool by sourcing images from details.images in addition to content blocks
Fixed context file preview in inspector panel to display content correctly instead of attempting async file reads
Fixed Linux ARM64 installs failing on fresh Debian when the sharp module is unavailable during session image compression

[3.20.1] - 2026-01-06

Fixed

Fixed find tool failing to match patterns with path separators (e.g., reports/**) by enabling full-path matching in fd

Changed

Changed multi-task display to show task descriptions instead of agent names when available
Changed ls tool to show relative modification times (e.g., "2d ago", "just now") for each entry

[3.20.0] - 2026-01-06

Added

Added extensions API with auto-discovery (.omp/extensions) and --extension/-e loading for custom tools, commands, and lifecycle hooks
Added prompt templates loaded from global and project .omp/prompts directories with /template expansion in the input box
Built-in provider overrides in models.json: override just baseUrl to route a built-in provider through a proxy while keeping all its models, or define models to fully replace the provider
Shell commands without context contribution: use !!command to execute a bash command that is shown in the TUI and saved to session history but excluded from LLM context. Useful for running commands you don't want the AI to see
Added VoiceSupervisor class for realtime voice mode using OpenAI Realtime API with continuous mic streaming and semantic VAD turn detection
Added VoiceController class for steering user input and deciding presentation of assistant responses
Added echo suppression and noise floor filtering for microphone input during voice playback
Added fallback transcript handling when realtime assistant produces no tool call or audio output
Added voice progress notifications that speak partial results after 15 seconds of streaming
Added platform-specific audio tool detection with helpful installation instructions for missing tools
Added realtime voice mode using OpenAI gpt-5-realtime with continuous mic streaming, interruptible input, and supervisor-controlled spoken updates
Added gemini_image tool for Gemini Nano Banana image generation when GEMINI_API_KEY (or GOOGLE_API_KEY) is set
Added description field to task tool for displaying short user-facing summaries in progress output
Added getApiKeyForProvider() method to ModelRegistry for retrieving API keys by provider name
Added voice settings configuration for transcription model, TTS model, voice, and audio format
Added shared render utilities module with standardized formatting functions for truncation, byte/token/duration display, and tree rendering
Added resolveOmpCommand() helper to resolve subprocess command from environment or entry point
Added /background (or /bg) command to detach UI and continue agent execution in the background
Added completion notification system with configurable methods (bell, osc99, osc9, auto, off) when agent finishes
Added completionNotification setting to configure how the agent notifies on completion
Added OMP_NOTIFICATIONS environment variable to suppress notifications globally
Added /wt slash command for git worktree management with create, list, merge, remove, status, spawn, and parallel operations
Added worktree library with collapse strategies (simple, merge-base, rebase) for merging changes between worktrees
Added worktree session tracking for managing agent tasks across isolated worktrees
Added structured git tool with safety guards, caching, and GitHub operations
Added cycleRoleModels() method to cycle through configured role-based models in a fixed order with deduplication
Added language-specific file icons to LSP diagnostics output showing file locations
Added language-specific file icon to edit tool header display

Changed

Changed voice mode toggle from Caps Lock to Ctrl+Y with auto-send on silence behavior
Changed default TTS model from gpt-4o-mini-tts to tts-1
Changed voice mode description to reflect realtime input/output with auto-send on silence
Updated hotkeys help to show Ctrl+Y for voice mode toggle instead of Caps Lock
Voice mode now uses OpenAI Realtime (gpt-5-realtime) with Ctrl+Y toggle and auto-send on silence
Updated web search tool to support auto as explicit provider option for auto-detection
Standardized tool result rendering across grep, find, ls, notebook, ask, output, and web search tools with consistent tree formatting and expand hints
Updated grep and find tool output to display language-specific icons for files and folder icons for directories
Updated file listing to display language-specific icons based on file extension instead of generic file icons

Fixed

Fixed task tool race condition where subprocess stdout events were skipped due to resolved flag being set before stream readers finished, causing completed tasks to display "0 tools · 0 tokens"
/model selector now opens instantly instead of waiting for OAuth token refresh. Token refresh is deferred until a model is actually used
Fixed cross-platform browser opening to work on Windows (via cmd /c start) and fail gracefully when unavailable

[3.15.1] - 2026-01-05

Added

Added 65 new built-in color themes including dark variants (abyss, aurora, cavern, copper, cosmos, eclipse, ember, equinox, lavender, lunar, midnight, nebula, rainforest, reef, sakura, slate, solstice, starfall, swamp, taiga, terminal, tundra, twilight, volcanic), light variants (aurora-day, canyon, cirrus, coral, dawn, dunes, eucalyptus, frost, glacier, haze, honeycomb, lagoon, lavender, meadow, mint, opal, orchard, paper, prism, sand, savanna, soleil, wetland, zenith), and material themes (alabaster, amethyst, anthracite, basalt, birch, graphite, limestone, mahogany, marble, obsidian, onyx, pearl, porcelain, quartz, sandstone, titanium)

Fixed

Fixed status line end cap rendering to properly apply background colors and use correct powerline separator characters

[3.15.0] - 2026-01-05

Added

Added spinner type variants (status and activity) with distinct animation frames per symbol preset
Added animated spinner for task tool progress display during subagent execution
Added language/file type icons for read tool output with support for 35+ file types
Added async cleanup registry for graceful session flush on SIGINT, SIGTERM, and SIGHUP signals
Added subagent token usage aggregation to session statistics and task tool results
Added streaming NDJSON writer for session persistence with proper backpressure handling
Added flush() method to SessionManager for explicit control over pending write completion
Added /exit slash command to exit the application from interactive mode
Added fuzzy path matching suggestions when read tool encounters file-not-found errors, showing closest matches using Levenshtein distance
Added status.shadowed symbol for theme customization to properly indicate shadowed extension state
Added Biome CLI-based linter client as alternative to LSP for more reliable diagnostics
Added LinterClient interface for pluggable formatter/linter implementations
Added status line segment editor for arranging and toggling status line components
Added status line presets (default, minimal, compact, developer, balanced) for quick configuration
Added status line separator styles (powerline, powerline-thin, arrow, slash, pipe, space)
Added configurable status line segments including time, hostname, and subagent count
Added symbol customization via theme overrides for icons, separators, and glyphs
Added 30+ built-in color themes including Catppuccin, Dracula, Nord, Gruvbox, Tokyo Night, and more
Added configurable status line with customizable segments, presets, and separators
Added status line segment editor for arranging and toggling status line components
Added symbol preset setting to switch between Unicode, Nerd Font, and ASCII glyphs
Added file size limit (20MB) for image files to prevent memory issues during serialization

Changed

Changed isError property in tool result events to be optional instead of required
Changed SessionManager.open() and SessionManager.continueRecent() to async methods for proper initialization
Changed session file writes to use atomic rename pattern with fsync for crash-safe persistence
Changed read tool display to show file type icons and metadata inline with path
Changed AgentSession.dispose() to async method that flushes pending writes before cleanup
Changed read tool result display to hide content by default with expand hint, showing only metadata until expanded
Changed diagnostics display to group messages by file with tree structure and severity icons
Changed diff stats formatting to use colored +/- indicators with slash separators
Changed session persistence to use streaming writes instead of synchronous file appends for better performance
Changed read tool to automatically redirect to ls when given a directory path instead of a file
Changed tool description prompts to be more concise with clearer usage guidelines and structured formatting
Moved tool description prompts from inline strings to external markdown files in src/prompts/tools/ directory for better maintainability
Changed Exa web search provider from MCP protocol to direct REST API for simpler integration
Changed web search result rendering to handle malformed response data with fallback text display
Changed compaction prompts to preserve tool outputs, command results, and repository state in context summaries
Changed init prompt to include runtime/tooling preferences section and improved formatting guidelines
Changed reviewer prompt to require evidence-backed findings anchored to diff hunks with stricter suggestion block formatting
Changed system prompt to include explicit core behavior guidelines for task completion and progress updates
Changed task prompt to emphasize end-to-end task completion and tool verification
Moved all prompt templates from inline strings to external markdown files in src/prompts/ directory for better maintainability
Changed tool result renderers to use structured tree layouts with consistent expand hints and truncation indicators
Changed grep, find, and ls tools to show scope path and detailed truncation reasons in output
Changed web search and web fetch result rendering to display structured metadata sections with bounded content previews
Changed task/subagent progress rendering to use badge-style status labels and structured output sections
Changed notebook tool to display cell content preview with line counts
Changed ask tool result to show checkbox-style selection indicators
Changed output tool to include provenance metadata and content previews for retrieved outputs
Changed collapsed tool views to show consistent "Ctrl+O to expand" hints with remaining item counts
Changed Biome integration to use CLI instead of LSP to avoid stale diagnostics issues
Changed hardcoded UI symbols throughout codebase to use theme-configurable glyphs
Changed tree drawing characters to use theme-defined box-drawing symbols
Changed status line rendering to support left/right segment positioning with separators
Changed hardcoded UI symbols to use theme-configurable glyphs throughout the interface
Changed tree drawing characters to use theme-defined box-drawing symbols
Changed CLI image attachments to resize if larger than 2048px (fit within 1920x1080) and convert >2MB images to JPEG

Removed

Removed custom renderers for ls, find, and grep tools in favor of generic tool display

Fixed

Fixed spinner animation crash when spinner frames array is empty by adding length check
Fixed session persistence to properly await all queued writes before closing or switching sessions
Fixed session persistence to truncate oversized content blocks before writing to prevent memory exhaustion
Fixed extension list and inspector panel to use correct symbols for disabled and shadowed states instead of reusing unrelated status icons
Fixed token counting for subagent progress to handle different usage object formats (camelCase and snake_case)
Fixed image file handling by adding 20MB size limit to prevent memory issues during serialization
Fixed session persistence to truncate oversized entries before writing JSONL to prevent out-of-memory errors

[3.14.0] - 2026-01-04

Added

Added getUsageStatistics() method to SessionManager for tracking cumulative token usage and costs across session messages

Changed

Changed status line to display usage statistics more efficiently by using centralized session statistics instead of recalculating from entries

[3.9.1337] - 2026-01-04

Changed

Changed default for lsp.formatOnWrite setting from true to false
Updated status line thinking level display to use emoji icons instead of abbreviated text
Changed auto-compact indicator from "(auto)" text to icon

Fixed

Fixed status line not updating token counts and cost after starting a new session
Fixed stale diagnostics persisting after file content changes in LSP client

[3.8.1337] - 2026-01-04

Added

Added automatic browser opening after exporting session to HTML
Added automatic browser opening after sharing session as a Gist

Fixed

Fixed session titles not persisting to file when set before first flush

[3.7.1337] - 2026-01-04

Added

Added EditMatchError class for structured error handling in edit operations
Added utils module export with once and untilAborted helper functions
Added in-memory LSP content sync via syncContent and notifySaved client methods

Changed

Refactored LSP integration to use writethrough callbacks for edit and write tools, improving performance by syncing content in-memory before disk writes
Simplified FileDiagnosticsResult interface with renamed fields: diagnostics → messages, hasErrors → errored, serverName → server
Session title generation now triggers before sending the first message rather than after agent work begins

Fixed

Fixed potential text decoding issues in bash executor by using streaming TextDecoder instead of Buffer.toString()

[3.5.1337] - 2026-01-03

Added

Added session header and footer output in text mode showing version, model, provider, thinking level, and session ID
Added Extension Control Center dashboard accessible via /extensions command for unified management of all providers and extensions
Added ability to enable/disable individual extensions with persistent settings
Added three-column dashboard layout with sidebar tree, extension list, and inspector panel
Added fuzzy search filtering for extensions in the dashboard
Added keyboard navigation with Tab to cycle panes, j/k for navigation, Space to toggle, Enter to expand/collapse

Changed

Redesigned Extension Control Center from 3-column layout to tabbed interface with horizontal provider tabs and 2-column grid
Replaced sidebar tree navigation with provider tabs using TAB/Shift+TAB cycling

Fixed

Fixed title generation flag not resetting when starting a new session

[3.4.1337] - 2026-01-03

Added

Added Time Traveling Stream Rules (TTSR) feature that monitors agent output for pattern matches and injects rule reminders mid-stream
Added ttsr_trigger frontmatter field for rules to define regex patterns that trigger mid-stream injection
Added TTSR settings for enabled state, context mode (keep/discard partial output), and repeat mode (once/after-gap)

Fixed

Fixed excessive subprocess spawns by caching git status for 1 second in the footer component

[3.3.1337] - 2026-01-03

Changed

Improved /status command output formatting to use consistent column alignment across all sections
Updated version update notification to suggest omp update instead of manual npm install command

[3.1.1337] - 2026-01-03

Added

Added spawns frontmatter field for agent definitions to control which sub-agents can be spawned
Added spawn restriction enforcement preventing agents from spawning unauthorized sub-agents

Fixed

Fixed duplicate skill loading when the same SKILL.md file was discovered through multiple paths

[3.0.1337] - 2026-01-03

Added

Added unified capability-based discovery system for loading configuration from multiple AI coding tools (Claude Code, Cursor, Windsurf, Gemini, Codex, Cline, GitHub Copilot, VS Code)
Added support for discovering MCP servers, rules, skills, hooks, tools, slash commands, prompts, and context files from tool-specific config directories
Added Discovery settings tab in interactive mode to enable/disable individual configuration providers
Added provider source attribution showing which tool contributed each configuration item
Added support for Cursor MDC rule format with frontmatter (description, globs, alwaysApply)
Added support for Windsurf rules from .windsurf/rules/*.md and global_rules.md
Added support for Cline rules from .clinerules file or directory
Added support for GitHub Copilot instructions with applyTo glob patterns
Added support for Gemini extensions and system.md customization files
Added support for Codex AGENTS.md and config.toml settings
Added automatic migration of PI_* environment variables to OMP_* equivalents for backwards compatibility
Added multi-path config discovery supporting .omp, .pi, and .claude directories with priority ordering
Added getConfigDirPaths(), findConfigFile(), and readConfigFile() functions for unified config resolution
Added documentation for config module usage patterns

Changed

Changed MCP tool name parsing to use last underscore separator for better server name handling
Changed /config output to show provider attribution for discovered items
Renamed CLI binary from pi to omp and updated all command references
Changed config directory from .pi to .omp with fallback support for legacy paths
Renamed environment variables from PI_* to OMP_* prefix (e.g., OMP_SMOL_MODEL, OMP_SLOW_MODEL)
Changed model role alias prefix from pi/ to omp/ (e.g., omp/slow instead of pi/slow)

[2.1.1337] - 2026-01-03

Added

Added omp update command to check for and install updates from GitHub releases or via bun

Changed

Changed HTML export to use compile-time bundled templates via Bun macros for improved performance
Changed exportToHtml and exportFromFile functions to be async
Simplified build process by embedding assets (themes, templates, agents, commands) directly into the binary at compile time
Removed separate asset copying steps from build scripts

[2.0.1337] - 2026-01-03

Added

Added shell environment snapshot to preserve user aliases, functions, and shell options when executing bash commands
Added support for OMP_BASH_NO_CI, OMP_BASH_NO_LOGIN, and OMP_SHELL_PREFIX environment variables for shell customization
Added zsh support alongside bash for shell detection and configuration

Changed

Changed shell detection to prefer user's $SHELL when it's bash or zsh, with improved fallback path resolution
Changed Edit tool to reject .ipynb files with guidance to use NotebookEdit tool instead

[1.500.0] - 2026-01-03

Added

Added provider tabs to model selector with Tab/Arrow navigation for filtering models by provider
Added context menu to model selector for choosing model role (Default, Smol, Slow) instead of keyboard shortcuts
Added LSP diagnostics display in tool execution output showing errors and warnings after file edits
Added centralized file logger with daily rotation to ~/.omp/logs/ for debugging production issues
Added logger property to hook and custom tool APIs for error/warning/debug logging
Added output tool to read full agent/task outputs by ID when truncated previews are insufficient
Added task tool to reviewer agent, enabling parallel exploration of large codebases during reviews
Added subprocess tool registry for extracting and rendering tool data from subprocess agents in real-time
Added combined review result rendering showing verdict and findings in a tree structure
Auto-read file mentions: Reference files with @path/to/file.ext syntax in prompts to automatically inject their contents, eliminating manual Read tool calls
Added hidden property for custom tools to exclude them from default tool list unless explicitly requested
Added explicitTools option to createAgentSession for enabling hidden tools by name
Added example review tools (report_finding, submit_review) with structured findings accumulation and verdict rendering
Added /review example command for interactive code review with branch comparison, uncommitted changes, and commit review modes
Custom TypeScript slash commands: Create programmable commands at ~/.omp/agent/commands/[name]/index.ts or .omp/commands/[name]/index.ts. Commands export a factory returning { name, description, execute(args, ctx) }. Return a string to send as LLM prompt, or void for fire-and-forget actions. Full access to HookCommandContext for UI dialogs, session control, and shell execution.
Claude command directories: Markdown slash commands now also load from ~/.claude/commands/ and .claude/commands/ (parallel to existing .omp/commands/ support)
commands.enableClaudeUser and commands.enableClaudeProject settings to disable Claude command directory loading
/export --copy option to copy entire session as formatted text to clipboard

Changed

Changed model selector keyboard shortcuts from S/L keys to a context menu opened with Enter
Changed model role indicators from symbols (✓ ⚡ 🧠) to labeled badges ([ DEFAULT ] [ SMOL ] [ SLOW ])
Changed model list sorting to include secondary sort by model ID within each provider
Changed silent error suppression to log warnings and debug info for tool errors, theme loading, and command loading failures
Changed Task tool progress display to show agent index (e.g., reviewer(0)) for easier Output tool ID derivation
Changed Task tool output to only include file paths when Output tool is unavailable, providing Read tool fallback
Changed Task tool output references to use simpler ID format (e.g., reviewer_0) with line/char counts for Output tool integration
Changed subagent recursion prevention from blanket blocking to same-agent blocking. Non-recursive agents can now spawn other agent types (e.g., reviewer can spawn explore agents) but cannot spawn themselves.
Changed /review command from markdown to interactive TypeScript with mode selection menu (branch comparison, uncommitted changes, commit review, custom)
Changed bundled commands to be overridable by user/project commands with same name
Changed subprocess termination to wait for message_end event to capture accurate token counts
Changed token counting in subprocess to accumulate across messages instead of overwriting
Updated bundled reviewer agent to use structured review tools with priority-based findings (P0-P3) and formal verdict submission
Task tool now streams artifacts in real-time: input written before spawn, session jsonl written by subprocess, output written at completion

Removed

Removed separate Exa error logger in favor of centralized logging system
Removed findings_count parameter from submit_review tool - findings are now counted automatically
Removed artifacts location display from task tool output

Fixed

Fixed race condition in event listener iteration by copying array before iteration to prevent mutation during callbacks
Fixed potential memory leak from orphaned abort controllers by properly aborting existing controllers before replacement
Fixed stream reader resource leak by adding proper releaseLock() calls in finally blocks
Fixed hook API methods throwing clear errors when handlers are not initialized instead of silently failing
Fixed LSP client race conditions with concurrent client creation and file operations using proper locking
Fixed Task tool progress display showing stale data by cloning progress objects before passing to callbacks
Fixed Task tool missing final progress events by waiting for readline to close before resolving
Fixed RPC mode race condition with concurrent prompt commands by serializing execution
Fixed pre-commit hook race condition causing index.lock errors when GitKraken/IDE git integrations detect file changes during formatting
Fixed Task tool output artifacts (out.md) containing duplicated text from streaming updates
Fixed Task tool progress display showing repeated nearly-identical lines during streaming
Fixed Task tool subprocess model selection ignoring agent's configured model and falling back to settings default. The --model flag now accepts provider/model format directly.
Fixed Task tool showing "done + succeeded" when aborted; now correctly displays "⊘ aborted" status

[1.341.0] - 2026-01-03

Added

Added interruptMode setting to control when queued messages are processed during tool execution.
Implemented getter and setter methods in SettingsManager for interrupt mode persistence.
Exposed interruptMode configuration in interactive settings UI with immediate/wait options.
Wired interrupt mode through AgentSession and SDK to enable runtime configuration.
Model roles: Configure different models for different purposes (default, smol, slow) via /model selector
Model selector key bindings: Enter sets default, S sets smol, L sets slow, Escape closes
Model selector shows role markers: ✓ for default, ⚡ for smol, 🧠 for slow
pi/<role> model aliases in Task tool agent definitions (e.g., model: pi/smol, haiku, flash, mini)
Smol model auto-discovery using priority chain: haiku > flash > mini
Slow model auto-discovery using priority chain: gpt-5.2-codex > codex > gpt > opus > pro
CLI args for model roles: --smol <model> and --slow <model> (ephemeral, not persisted)
Env var overrides: OMP_SMOL_MODEL and OMP_SLOW_MODEL
Title generation now uses configured smol model from settings
LSP diagnostics on edit: Edit tool can now return LSP diagnostics after editing code files. Disabled by default to avoid noise during multi-edit sequences. Enable via lsp.diagnosticsOnEdit setting.
LSP workspace diagnostics: New lsp action=workspace_diagnostics command checks the entire project for errors. Auto-detects project type and uses appropriate checker (rust-analyzer/cargo for Rust, tsc for TypeScript, go build for Go, pyright for Python).
LSP local binary resolution: LSP servers installed in project-local directories are now discovered automatically. Checks node_modules/.bin/ for Node.js projects, .venv/bin//venv/bin/ for Python projects, and vendor/bundle/bin/ for Ruby projects before falling back to $PATH.
LSP format on write: Write tool now automatically formats code files using LSP after writing. Uses the language server's built-in formatter (e.g., rustfmt for Rust, gofmt for Go). Controlled via lsp.formatOnWrite setting (enabled by default).
LSP diagnostics on write: Write tool now returns LSP diagnostics (errors/warnings) after writing code files. This gives immediate feedback on syntax errors and type issues. Controlled via lsp.diagnosticsOnWrite setting (enabled by default).
LSP server warmup at startup: LSP servers are now started at launch to avoid cold-start delays when first writing files.
LSP server status in welcome banner: Shows which language servers are active and ready.
Edit fuzzy match setting: Added edit.fuzzyMatch setting (enabled by default) to control whether the edit tool accepts high-confidence fuzzy matches for whitespace/indentation differences. Toggle via /settings.
Multi-server LSP diagnostics: Diagnostics now query all applicable language servers for a file type. For TypeScript/JavaScript projects with Biome, this means both type errors (from tsserver) and lint errors (from Biome) are reported together.
Comprehensive LSP server configurations for 40+ languages including Rust, Go, Python, Java, Kotlin, Scala, Haskell, OCaml, Elixir, Ruby, PHP, C#, Lua, Nix, and many more. Each server includes sensible defaults for args, settings, and init options.
Extended LSP config file search paths: Now searches for lsp.json, .lsp.json in project root and .omp/ subdirectory, plus user-level configs in ~/.omp/ and home directory.

Changed

LSP settings moved to dedicated "LSP" tab in /settings for better organization
Improved grep tool description to document pagination options (headLimit, offset) and clarify recursive search behavior
LSP idle timeout now disabled by default. Configure via idleTimeoutMs in lsp.json to auto-shutdown inactive servers.
Model settings now use role-based storage (modelRoles map) instead of single defaultProvider/defaultModel fields. Supports multiple model roles (default, small, etc.)
Session model persistence now uses "provider/modelId" string format with optional role field

Fixed

Recent sessions now show in welcome banner (was never wired up).
Auto-generated session titles: Sessions are now automatically titled based on the first message using a small model (Haiku/GPT-4o-mini/Flash). Titles are shown in the terminal window title, recent sessions list, and --resume picker. The resume picker shows title with dimmed first message preview below.

[1.340.0] - 2026-01-03

Changed

Replaced vendored highlight.js and marked.js with CDN-hosted versions for smaller exports
Added runtime minification for HTML, CSS, and JS in session exports
Session share URL now uses gistpreview.github.io instead of shittycodingagent.ai

[1.339.0] - 2026-01-03

Added

MCP project config setting to disable loading .mcp.json/mcp.json from project root
Support for both mcp.json and .mcp.json filenames (prefers mcp.json if both exist)
Automatic Exa MCP server filtering with API key extraction for native integration

[1.338.0] - 2026-01-03

Added

Bash interceptor setting to block shell commands that have dedicated tools (disabled by default, enable via /settings)

Changed

Refactored settings UI to declarative definitions for easier maintenance
Shell detection now respects $SHELL environment variable before falling back to bash/sh
Tool binary detection now uses Bun.which() instead of spawning processes

Fixed

CLI help text now accurately lists all default tools

[1.337.1] - 2026-01-02

Added

MCP support and plugin system for external tool integration
Git context to system prompt for repo awareness
Bash interception to guide tool selection
Fuzzy matching to handle indentation variance in edit tool
Specialized Exa tools with granular toggles
/share command for exporting conversations to HTML
Edit diff preview before tool execution

Changed

Renamed package scope to @oh-my-pi for consistent branding
Simplified toolset and enhanced navigation
Improved process cleanup with tree kill
Updated CI/CD workflows for GitHub Actions with provenance-signed npm publishing

Fixed

Template string interpolation in image read output
Prevented full re-renders during write tool streaming
Edit tool failing on files with UTF-8 BOM

[1.337.0] - 2026-01-02

Initial release under @oh-my-pi scope. See previous releases at badlogic/pi-mono.

[0.31.1] - 2026-01-02

Fixed

Model selector no longer allows negative index when pressing arrow keys before models finish loading (#398 by @mitsuhiko)
Type guard functions (isBashToolResult, etc.) now exported at runtime, not just in type declarations (#397)

[0.31.0] - 2026-01-02

This release introduces session trees for in-place branching, major API changes to hooks and custom tools, and structured compaction with file tracking.

Session Tree

Sessions now use a tree structure with id/parentId fields. This enables in-place branching: navigate to any previous point with /tree, continue from there, and switch between branches while preserving all history in a single file.

Existing sessions are automatically migrated (v1 → v2) on first load. No manual action required.

New entry types: BranchSummaryEntry (context from abandoned branches), CustomEntry (hook state), CustomMessageEntry (hook-injected messages), LabelEntry (bookmarks).

See docs/session.md for the file format and SessionManager API.

Hooks Migration

The hooks API has been restructured with more granular events and better session access.

Type renames:

HookEventContext → HookContext
HookCommandContext is now a new interface extending HookContext with session control methods

Event changes:

The monolithic session event is now split into granular events: session_start, session_before_switch, session_switch, session_before_branch, session_branch, session_before_compact, session_compact, session_shutdown
session_before_switch and session_switch events now include reason: "new" | "resume" to distinguish between /new and /resume
New session_before_tree and session_tree events for /tree navigation (hook can provide custom branch summary)
New before_agent_start event: inject messages before the agent loop starts
New context event: modify messages non-destructively before each LLM call
Session entries are no longer passed in events. Use ctx.sessionManager.getEntries() or ctx.sessionManager.getBranch() instead

API changes:

pi.send(text, attachments?) → pi.sendMessage(message, triggerTurn?) (creates CustomMessageEntry)
New pi.appendEntry(customType, data?) for hook state persistence (not in LLM context)
New pi.registerCommand(name, options) for custom slash commands (handler receives HookCommandContext)
New pi.registerMessageRenderer(customType, renderer) for custom TUI rendering
New ctx.isIdle(), ctx.abort(), ctx.hasQueuedMessages() for agent state (available in all events)
New ctx.ui.editor(title, prefill?) for multi-line text editing with Ctrl+G external editor support
New ctx.ui.custom(component) for full TUI component rendering with keyboard focus
New ctx.ui.setStatus(key, text) for persistent status text in footer (multiple hooks can set their own)
New ctx.ui.theme getter for styling text with theme colors
ctx.exec() moved to pi.exec()
ctx.sessionFile → ctx.sessionManager.getSessionFile()
New ctx.modelRegistry and ctx.model for API key resolution

HookCommandContext (slash commands only):

ctx.waitForIdle() - wait for agent to finish streaming
ctx.newSession(options?) - create new sessions with optional setup callback
ctx.branch(entryId) - branch from a specific entry
ctx.navigateTree(targetId, options?) - navigate the session tree

These methods are only on HookCommandContext (not HookContext) because they can deadlock if called from event handlers that run inside the agent loop.

Removed:

hookTimeout setting (hooks no longer have timeouts; use Ctrl+C to abort)
resolveApiKey parameter (use ctx.modelRegistry.getApiKey(model))

See docs/hooks.md and examples/hooks/ for the current API.

Custom Tools Migration

The custom tools API has been restructured to mirror the hooks pattern with a context object.

Type renames:

CustomAgentTool → CustomTool
ToolAPI → CustomToolAPI
ToolContext → CustomToolContext
ToolSessionEvent → CustomToolSessionEvent

Execute signature changed:

// Before (v0.30.2)
execute(toolCallId, params, signal, onUpdate)

// After
execute(toolCallId, params, onUpdate, ctx, signal?)

The new ctx: CustomToolContext provides sessionManager, modelRegistry, model, and agent state methods:

ctx.isIdle() - check if agent is streaming
ctx.hasQueuedMessages() - check if user has queued messages (skip interactive prompts)
ctx.abort() - abort current operation (fire-and-forget)

Session event changes:

CustomToolSessionEvent now only has reason and previousSessionFile
Session entries are no longer in the event. Use ctx.sessionManager.getBranch() or ctx.sessionManager.getEntries() to reconstruct state
Reasons: "start" | "switch" | "branch" | "tree" | "shutdown" (no separate "new" reason; /new triggers "switch")
dispose() method removed. Use onSession with reason: "shutdown" for cleanup

See docs/custom-tools.md and examples/custom-tools/ for the current API.

SDK Migration

Type changes:

CustomAgentTool → CustomTool
AppMessage → AgentMessage
sessionFile returns string | undefined (was string | null)
model returns Model | undefined (was Model | null)
Attachment type removed. Use ImageContent from @oh-my-pi/pi-ai instead. Add images directly to message content arrays.

AgentSession API:

branch(entryIndex: number) → branch(entryId: string)
getUserMessagesForBranching() returns { entryId, text } instead of { entryIndex, text }
reset() → newSession(options?) where options has optional parentSession for lineage tracking
newSession() and switchSession() now return Promise<boolean> (false if cancelled by hook)
New navigateTree(targetId, options?) for in-place tree navigation

Hook integration:

New sendHookMessage(message, triggerTurn?) for hook message injection

SessionManager API:

Method renames: saveXXX() → appendXXX() (e.g., appendMessage, appendCompaction)
branchInPlace() → branch()
reset() → newSession(options?) with optional parentSession for lineage tracking
createBranchedSessionFromEntries(entries, index) → createBranchedSession(leafId)
SessionHeader.branchedFrom → SessionHeader.parentSession
saveCompaction(entry) → appendCompaction(summary, firstKeptEntryId, tokensBefore, details?)
getEntries() now excludes the session header (use getHeader() separately)
getSessionFile() returns string | undefined (undefined for in-memory sessions)
New tree methods: getTree(), getBranch(), getLeafId(), getLeafEntry(), getEntry(), getChildren(), getLabel()
New append methods: appendCustomEntry(), appendCustomMessageEntry(), appendLabelChange()
New branch methods: branch(entryId), branchWithSummary()

ModelRegistry (new):

ModelRegistry is a new class that manages model discovery and API key resolution. It combines built-in models with custom models from models.json and resolves API keys via AuthStorage.

import { discoverAuthStorage, discoverModels } from "@oh-my-pi/pi-coding-agent";

const authStorage = discoverAuthStorage(); // ~/.omp/agent/auth.json
const modelRegistry = discoverModels(authStorage); // + ~/.omp/agent/models.json

// Get all models (built-in + custom)
const allModels = modelRegistry.getAll();

// Get only models with valid API keys
const available = await modelRegistry.getAvailable();

// Find specific model
const model = modelRegistry.find("anthropic", "claude-sonnet-4-20250514");

// Get API key for a model
const apiKey = await modelRegistry.getApiKey(model);

This replaces the old resolveApiKey callback pattern. Hooks and custom tools access it via ctx.modelRegistry.

Renamed exports:

messageTransformer → convertToLlm
SessionContext alias LoadedSession removed

See docs/sdk.md and examples/sdk/ for the current API.

RPC Migration

Session commands:

reset command → new_session command with optional parentSession field

Branching commands:

branch command: entryIndex → entryId
get_branch_messages response: entryIndex → entryId

Type changes:

Messages are now AgentMessage (was AppMessage)
prompt command: attachments field replaced with images field using ImageContent format

Compaction events:

auto_compaction_start now includes reason field ("threshold" or "overflow")
auto_compaction_end now includes willRetry field
compact response includes full CompactionResult (summary, firstKeptEntryId, tokensBefore, details)

See docs/rpc.md for the current protocol.

Structured Compaction

Compaction and branch summarization now use a structured output format:

Clear sections: Goal, Progress, Key Information, File Operations
File tracking: readFiles and modifiedFiles arrays in details, accumulated across compactions
Conversations are serialized to text before summarization to prevent the model from "continuing" them

The before_compact and before_tree hook events allow custom compaction implementations. See docs/compaction.md.

Interactive Mode

/tree command:

Navigate the full session tree in-place
Search by typing, page with ←/→
Filter modes (Ctrl+O): default → no-tools → user-only → labeled-only → all
Press l to label entries as bookmarks
Selecting a branch switches context and optionally injects a summary of the abandoned branch

Entry labels:

Bookmark any entry via /tree → select → l
Labels appear in tree view and persist as LabelEntry

Theme changes (breaking for custom themes):

Custom themes must add these new color tokens or they will fail to load:

selectedBg: background for selected/highlighted items in tree selector and other components
customMessageBg: background for hook-injected messages (CustomMessageEntry)
customMessageText: text color for hook messages
customMessageLabel: label color for hook messages (the [customType] prefix)

Total color count increased from 46 to 50. See docs/theme.md for the full color list and copy values from the built-in dark/light themes.

Settings:

enabledModels: allowlist models in settings.json (same format as --models CLI)

Added

ctx.ui.setStatus(key, text) for hooks to display persistent status text in the footer (#385 by @prateekmedia)
ctx.ui.theme getter for styling status text and other output with theme colors
/share command to upload session as a secret GitHub gist and get a shareable URL via shittycodingagent.ai (#380)
HTML export now includes a tree visualization sidebar for navigating session branches (#375)
HTML export supports keyboard shortcuts: Ctrl+T to toggle thinking blocks, Ctrl+O to toggle tool outputs
HTML export supports theme-configurable background colors via optional export section in theme JSON (#387 by @mitsuhiko)
HTML export syntax highlighting now uses theme colors and matches TUI rendering
Snake game example hook: Demonstrates ui.custom(), registerCommand(), and session persistence. See examples/hooks/snake.ts.
thinkingText theme token: Configurable color for thinking block text. (#366 by @paulbettner)

Changed

Entry IDs: Session entries now use short 8-character hex IDs instead of full UUIDs
API key priority: ANTHROPIC_OAUTH_TOKEN now takes precedence over ANTHROPIC_API_KEY
HTML export template split into separate files (template.html, template.css, template.js) for easier maintenance

Fixed

HTML export now properly sanitizes user messages containing HTML tags like <style> that could break DOM rendering
Crash when displaying bash output containing Unicode format characters like U+0600-U+0604 (#372 by @HACKE-RC)
Footer shows full session stats: Token usage and cost now include all messages, not just those after compaction. (#322)
Status messages spam chat log: Rapidly changing settings (e.g., thinking level via Shift+Tab) would add multiple status lines. Sequential status updates now coalesce into a single line. (#365 by @paulbettner)
Toggling thinking blocks during streaming shows nothing: Pressing Ctrl+T while streaming would hide the current message until streaming completed.
Resuming session resets thinking level to off: Initial model and thinking level were not saved to session file, causing --resume/--continue to default to off. (#342 by @aliou)
Hook tool_result event ignores errors from custom tools: The tool_result hook event was never emitted when tools threw errors, and always had isError: false for successful executions. Now emits the event with correct isError value in both success and error cases. (#374 by @nicobailon)
Edit tool fails on Windows due to CRLF line endings: Files with CRLF line endings now match correctly when LLMs send LF-only text. Line endings are normalized before matching and restored to original style on write. (#355 by @Pratham-Dubey)
Edit tool fails on files with UTF-8 BOM: Files with UTF-8 BOM marker could cause "text not found" errors since the LLM doesn't include the invisible BOM character. BOM is now stripped before matching and restored on write. (#394 by @prathamdby)
Use bash instead of sh on Unix: Fixed shell commands using /bin/sh instead of /bin/bash on Unix systems. (#328 by @dnouri)
OAuth login URL clickable: Made OAuth login URLs clickable in terminal. (#349 by @Cursivez)
Improved error messages: Better error messages when apiKey or model are missing. (#346 by @ronyrus)
Session file validation: findMostRecentSession() now validates session headers before returning, preventing non-session JSONL files from being loaded
Compaction error handling: generateSummary() and generateTurnPrefixSummary() now throw on LLM errors instead of returning empty strings
Compaction with branched sessions: Fixed compaction incorrectly including entries from abandoned branches, causing token overflow errors. Compaction now uses sessionManager.getPath() to work only on the current branch path, eliminating 80+ lines of duplicate entry collection logic between prepareCompaction() and compact()
enabledModels glob patterns: --models and enabledModels now support glob patterns like github-copilot/* or *sonnet*. Previously, patterns were only matched literally or via substring search. (#337)

[0.30.2] - 2025-12-26

Changed

Consolidated migrations: Moved auth migration from AuthStorage.migrateLegacy() to new migrations.ts module.

[0.30.1] - 2025-12-26

Fixed

Sessions saved to wrong directory: In v0.30.0, sessions were being saved to ~/.omp/agent/ instead of ~/.omp/agent/sessions/<encoded-cwd>/, breaking --resume and /resume. Misplaced sessions are automatically migrated on startup. (#320 by @aliou)
Custom system prompts missing context: When using a custom system prompt string, project context files (AGENTS.md), skills, date/time, and working directory were not appended. (#321)

[0.30.0] - 2025-12-25

Breaking Changes

SessionManager API: The second parameter of create(), continueRecent(), and list() changed from agentDir to sessionDir. When provided, it specifies the session directory directly (no cwd encoding). When omitted, uses default (~/.omp/agent/sessions/<encoded-cwd>/). open() no longer takes agentDir. (#313)

Added

--session-dir flag: Use a custom directory for sessions instead of the default ~/.omp/agent/sessions/<encoded-cwd>/. Works with -c (continue) and -r (resume) flags. (#313 by @scutifer)
Reverse model cycling and model selector: Shift+Ctrl+P cycles models backward, Ctrl+L opens model selector (retaining text in editor). (#315 by @mitsuhiko)

[0.29.1] - 2025-12-25

Added

Automatic custom system prompt loading: OMP now auto-loads SYSTEM.md files to replace the default system prompt. Project-local .omp/SYSTEM.md takes precedence over global ~/.omp/agent/SYSTEM.md. CLI --system-prompt flag overrides both. (#309)
Unified /settings command: New settings menu consolidating thinking level, theme, queue mode, auto-compact, show images, hide thinking, and collapse changelog. Replaces individual /thinking, /queue, /theme, /autocompact, and /show-images commands. (#310)

Fixed

Custom tools/hooks with typebox subpath imports: Fixed jiti alias for @sinclair/typebox to point to package root instead of entry file, allowing imports like @sinclair/typebox/compiler to resolve correctly. (#311 by @kim0)

[0.29.0] - 2025-12-25

Breaking Changes

Renamed /clear to /new: The command to start a fresh session is now /new. Hook event reasons before_clear/clear are now before_new/new. Merry Christmas @mitsuhiko! (#305)

Added

Auto-space before pasted file paths: When pasting a file path (starting with /, ~, or .) after a word character, a space is automatically prepended. (#307 by @mitsuhiko)
Word navigation in input fields: Added Ctrl+Left/Right and Alt+Left/Right for word-by-word cursor movement. (#306 by @kim0)
Full Unicode input: Input fields now accept Unicode characters beyond ASCII. (#306 by @kim0)

Fixed

Readline-style Ctrl+W: Now skips trailing whitespace before deleting the preceding word, matching standard readline behavior. (#306 by @kim0)

[0.28.0] - 2025-12-25

Changed

Credential storage refactored: API keys and OAuth tokens are now stored in ~/.omp/agent/auth.json instead of oauth.json and settings.json. Existing credentials are automatically migrated on first run. (#296)
SDK API changes (#296):
- Added AuthStorage class for credential management (API keys and OAuth tokens)
- Added ModelRegistry class for model discovery and API key resolution
- Added discoverAuthStorage() and discoverModels() discovery functions
- createAgentSession() now accepts authStorage and modelRegistry options
- Removed configureOAuthStorage(), defaultGetApiKey(), findModel(), discoverAvailableModels()
- Removed getApiKey callback option (use AuthStorage.setRuntimeApiKey() for runtime overrides)
- Use getModel() from @oh-my-pi/pi-ai for built-in models, modelRegistry.find() for custom models + built-in models
- See updated SDK documentation and README
Settings changes: Removed apiKeys from settings.json. Use auth.json instead. (#296)

Fixed

Duplicate skill warnings for symlinks: Skills loaded via symlinks pointing to the same file are now silently deduplicated instead of showing name collision warnings. (#304 by @mitsuhiko)

[0.27.9] - 2025-12-24

Fixed

Model selector and --list-models with settings.json API keys: Models with API keys configured in settings.json (but not in environment variables) now properly appear in the /model selector and --list-models output. (#295)

[0.27.8] - 2025-12-24

Fixed

API key priority: OAuth tokens now take priority over settings.json API keys. Previously, an API key in settings.json would trump OAuth, causing users logged in with a plan (unlimited tokens) to be billed via PAYG instead.

[0.27.7] - 2025-12-24

Fixed

Thinking tag leakage: Fixed Claude mimicking literal </thinking> tags in responses. Unsigned thinking blocks (from aborted streams) are now converted to plain text without <thinking> tags. The TUI still displays them as thinking blocks. (#302 by @nicobailon)

[0.27.6] - 2025-12-24

Added

Compaction hook improvements: The before_compact session event now includes:
- previousSummary: Summary from the last compaction (if any), so hooks can preserve accumulated context
- messagesToKeep: Messages that will be kept after the summary (recent turns), in addition to messagesToSummarize
- resolveApiKey: Function to resolve API keys for any model (checks settings, OAuth, env vars)
- Removed apiKey string in favor of resolveApiKey for more flexibility
SessionManager API cleanup:
- Renamed loadSessionFromEntries() to buildSessionContext() (builds LLM context from entries, handling compaction)
- Renamed loadEntries() to getEntries() (returns defensive copy of all session entries)
- Added buildSessionContext() method to SessionManager

[0.27.5] - 2025-12-24

Added

HTML export syntax highlighting: Code blocks in markdown and tool outputs (read, write) now have syntax highlighting using highlight.js with theme-aware colors matching the TUI.
HTML export improvements: Render markdown server-side using marked (tables, headings, code blocks, etc.), honor user's chosen theme (light/dark), add image rendering for user messages, and style code blocks with TUI-like language markers. (@scutifer)

Fixed

Ghostty inline images in tmux: Fixed terminal detection for Ghostty when running inside tmux by checking GHOSTTY_RESOURCES_DIR env var. (#299 by @nicobailon)

[0.27.4] - 2025-12-24

Fixed

Symlinked skill directories: Skills in symlinked directories (e.g., ~/.omp/agent/skills/my-skills -> /path/to/skills) are now correctly discovered and loaded.

[0.27.3] - 2025-12-24

Added

API keys in settings.json: Store API keys in ~/.omp/agent/settings.json under the apiKeys field (e.g., { "apiKeys": { "anthropic": "sk-..." } }). Settings keys take priority over environment variables. (#295)

Fixed

Allow startup without API keys: Interactive mode no longer throws when no API keys are configured. Users can now start the agent and use /login to authenticate. (#288)
--system-prompt file path support: The --system-prompt argument now correctly resolves file paths (like --append-system-prompt already did). (#287 by @scutifer)

[0.27.2] - 2025-12-23

Added

Skip conversation restore on branch: Hooks can return { skipConversationRestore: true } from before_branch to create the branched session file without restoring conversation messages. Useful for checkpoint hooks that restore files separately. (#286 by @nicobarray)

[0.27.1] - 2025-12-22

Fixed

Skill discovery performance: Skip node_modules directories when recursively scanning for skills. Fixes ~60ms startup delay when skill directories contain npm dependencies.

Added

Startup timing instrumentation: Set OMP_TIMING=1 to see startup performance breakdown (interactive mode only).

[0.27.0] - 2025-12-22

Breaking

Session hooks API redesign: Merged branch event into session event. BranchEvent, BranchEventResult types and pi.on("branch", ...) removed. Use pi.on("session", ...) with reason: "before_branch" | "branch" instead. AgentSession.branch() returns { cancelled } instead of { skipped }. AgentSession.reset() and switchSession() now return boolean (false if cancelled by hook). RPC commands reset, switch_session, and branch now include cancelled in response data. (#278)

Added

Session lifecycle hooks: Added before_* variants (before_switch, before_clear, before_branch) that fire before actions and can be cancelled with { cancel: true }. Added shutdown reason for graceful exit handling. (#278)

Fixed

File tab completion display: File paths no longer get cut off early. Folders now show trailing / and removed redundant "directory"/"file" labels to maximize horizontal space. (#280)
Bash tool visual line truncation: Fixed bash tool output in collapsed mode to use visual line counting (accounting for line wrapping) instead of logical line counting. Now consistent with bash-execution.ts behavior. Extracted shared truncateToVisualLines utility. (#275)

[0.26.1] - 2025-12-22

Fixed

SDK tools respect cwd: Core tools (bash, read, edit, write, grep, find, ls) now properly use the cwd option from createAgentSession(). Added tool factory functions (createBashTool, createReadTool, etc.) for SDK users who specify custom cwd with explicit tools. (#279)

[0.26.0] - 2025-12-22

Added

SDK for programmatic usage: New createAgentSession() factory with full control over model, tools, hooks, skills, session persistence, and settings. Philosophy: "omit to discover, provide to override". Includes 12 examples and comprehensive documentation. (#272)
Project-specific settings: Settings now load from both ~/.omp/agent/settings.json (global) and <cwd>/.omp/settings.json (project). Project settings override global with deep merge for nested objects. Project settings are read-only (for version control). (#276)
SettingsManager static factories: SettingsManager.create(cwd?, agentDir?) for file-based settings, SettingsManager.inMemory(settings?) for testing. Added applyOverrides() for programmatic overrides.
SessionManager static factories: SessionManager.create(), SessionManager.open(), SessionManager.continueRecent(), SessionManager.inMemory(), SessionManager.list() for flexible session management.

[0.25.4] - 2025-12-22

Fixed

Syntax highlighting stderr spam: Fixed cli-highlight logging errors to stderr when markdown contains malformed code fences (e.g., missing newlines around closing backticks). Now validates language identifiers before highlighting and falls back silently to plain text. (#274)

[0.25.3] - 2025-12-21

Added

Gemini 3 preview models: Added gemini-3-pro-preview and gemini-3-flash-preview to the google-gemini-cli provider. (#264 by @LukeFost)
External editor support: Press Ctrl+G to edit your message in an external editor. Uses $VISUAL or $EDITOR environment variable. On successful save, the message is replaced; on cancel, the original is kept. (#266 by @aliou)
Process suspension: Press Ctrl+Z to suspend omp and return to the shell. Resume with fg as usual. (#267 by @aliou)
Configurable skills directories: Added granular control over skill sources with enableCodexUser, enableClaudeUser, enableClaudeProject, enablePiUser, enablePiProject toggles, plus customDirectories and ignoredSkills settings. (#269 by @nicobailon)
Skills CLI filtering: Added --skills <patterns> flag for filtering skills with glob patterns. Also added includeSkills setting and glob pattern support for ignoredSkills. (#268)

[0.25.2] - 2025-12-21

Fixed

Image shifting in tool output: Fixed an issue where images in tool output would shift down (due to accumulating spacers) each time the tool output was expanded or collapsed via Ctrl+O.

[0.25.1] - 2025-12-21

Fixed

Gemini image reading broken: Fixed the read tool returning images causing flaky/broken responses with Gemini models. Images in tool results are now properly formatted per the Gemini API spec.
Tab completion for absolute paths: Fixed tab completion producing //tmp instead of /tmp/. Also fixed symlinks to directories (like /tmp) not getting a trailing slash, which prevented continuing to tab through subdirectories.

[0.25.0] - 2025-12-20

Added

Interruptible tool execution: Queuing a message while tools are executing now interrupts the current tool batch. Remaining tools are skipped with an error result, and your queued message is processed immediately. Useful for redirecting the agent mid-task. (#259 by @steipete)
Google Gemini CLI OAuth provider: Access Gemini 2.0/2.5 models for free via Google Cloud Code Assist. Login with /login and select "Google Gemini CLI". Uses your Google account with rate limits.
Google Antigravity OAuth provider: Access Gemini 3, Claude (sonnet/opus thinking models), and GPT-OSS models for free via Google's Antigravity sandbox. Login with /login and select "Antigravity". Uses your Google account with rate limits.

Changed

Model selector respects --models scope: The /model command now only shows models specified via --models flag when that flag is used, instead of showing all available models. This prevents accidentally selecting models from unintended providers. (#255)

Fixed

Connection errors not retried: Added "connection error" to the list of retryable errors so Anthropic connection drops trigger auto-retry instead of silently failing. (#252)
Thinking level not clamped on model switch: Fixed TUI showing xhigh thinking level after switching to a model that doesn't support it. Thinking level is now automatically clamped to model capabilities. (#253)
Cross-model thinking handoff: Fixed error when switching between models with different thinking signature formats (e.g., GPT-OSS to Claude thinking models via Antigravity). Thinking blocks without signatures are now converted to text with <thinking> delimiters.

[0.24.5] - 2025-12-20

Fixed

Input buffering in iTerm2: Fixed Ctrl+C, Ctrl+D, and other keys requiring multiple presses in iTerm2. The cell size query response parser was incorrectly holding back keyboard input.

[0.24.4] - 2025-12-20

Fixed

Arrow keys and Enter in selector components: Fixed arrow keys and Enter not working in model selector, session selector, OAuth selector, and other selector components when Caps Lock or Num Lock is enabled. (#243)

[0.24.3] - 2025-12-19

Fixed

Footer overflow on narrow terminals: Fixed footer path display exceeding terminal width when resizing to very narrow widths, causing rendering crashes. /arminsayshi

[0.24.2] - 2025-12-20

Fixed

More Kitty keyboard protocol fixes: Fixed Backspace, Enter, Home, End, and Delete keys not working with Caps Lock enabled. The initial fix in 0.24.1 missed several key handlers that were still using raw byte detection. Now all key handlers use the helper functions that properly mask out lock key bits. (#243)

[0.24.1] - 2025-12-19

Added

OAuth and model config exports: Scripts using AgentSession directly can now import getAvailableModels, getApiKeyForModel, findModel, login, logout, and getOAuthProviders from @oh-my-pi/pi-coding-agent to reuse OAuth token storage and model resolution. (#245)
xhigh thinking level for gpt-5.2 models: The thinking level selector and shift+tab cycling now show xhigh option for gpt-5.2 and gpt-5.2-codex models (in addition to gpt-5.1-codex-max). (#236 by @theBucky)

Fixed

Hooks wrap custom tools: Custom tools are now executed through the hook wrapper, so tool_call/tool_result hooks can observe, block, and modify custom tool executions (consistent with hook type docs). (#248 by @nicobailon)
Hook onUpdate callback forwarding: The onUpdate callback is now correctly forwarded through the hook wrapper, fixing custom tool progress updates. (#238 by @nicobailon)
Terminal cleanup on Ctrl+C in session selector: Fixed terminal not being properly restored when pressing Ctrl+C in the session selector. (#247 by @aliou)
OpenRouter models with colons in IDs: Fixed parsing of OpenRouter model IDs that contain colons (e.g., openrouter:meta-llama/llama-4-scout:free). (#242 by @aliou)
Global AGENTS.md loaded twice: Fixed global AGENTS.md being loaded twice when present in both ~/.omp/agent/ and the current directory. (#239 by @aliou)
Kitty keyboard protocol on Linux: Fixed keyboard input not working in Ghostty on Linux when Num Lock is enabled. The Kitty protocol includes Caps Lock and Num Lock state in modifier values, which broke key detection. Now correctly masks out lock key bits when matching keyboard shortcuts. (#243)
Emoji deletion and cursor movement: Backspace, Delete, and arrow keys now correctly handle multi-codepoint characters like emojis. Previously, deleting an emoji would leave partial bytes, corrupting the editor state. (#240)

[0.24.0] - 2025-12-19

Added

Subagent orchestration example: Added comprehensive custom tool example for spawning and orchestrating sub-agents with isolated context windows. Includes scout/planner/reviewer/worker agents and workflow commands for multi-agent pipelines. (#215 by @nicobailon)
getMarkdownTheme() export: Custom tools can now import getMarkdownTheme() from @oh-my-pi/pi-coding-agent to use the same markdown styling as the main UI.
pi.exec() signal and timeout support: Custom tools and hooks can now pass { signal, timeout } options to pi.exec() for cancellation and timeout handling. The result includes a killed flag when the process was terminated.
Kitty keyboard protocol support: Shift+Enter, Alt+Enter, Shift+Tab, Ctrl+D, and all Ctrl+key combinations now work in Ghostty, Kitty, WezTerm, and other modern terminals. (#225 by @kim0)
Dynamic API key refresh: OAuth tokens (GitHub Copilot, Anthropic OAuth) are now refreshed before each LLM call, preventing failures in long-running agent loops where tokens expire mid-session. (#223 by @kim0)
/hotkeys command: Shows all keyboard shortcuts in a formatted table.
Markdown table borders: Tables now render with proper top and bottom borders.

Changed

Subagent example improvements: Parallel mode now streams updates from all tasks. Chain mode shows all completed steps during streaming. Expanded view uses proper markdown rendering with syntax highlighting. Usage footer shows turn count.
Skills standard compliance: Skills now adhere to the Agent Skills standard. Validates name (must match parent directory, lowercase, max 64 chars), description (required, max 1024 chars), and frontmatter fields. Warns on violations but remains lenient. Prompt format changed to XML structure. Removed {baseDir} placeholder in favor of relative paths. (#231)

Fixed

JSON mode stdout flush: Fixed race condition where omp --mode json could exit before all output was written to stdout, causing consumers to miss final events.
Symlinked tools, hooks, and slash commands: Discovery now correctly follows symlinks when scanning for custom tools, hooks, and slash commands. (#219, #232 by @aliou)

Breaking Changes

Custom tools now require index.ts entry point: Auto-discovered custom tools must be in a subdirectory with an index.ts file. The old pattern ~/.omp/agent/tools/mytool.ts must become ~/.omp/agent/tools/mytool/index.ts. This allows multi-file tools to import helper modules. Explicit paths via --tool or settings.json still work with any .ts file.
Hook tool_result event restructured: The ToolResultEvent now exposes full tool result data instead of just text. (#233)
- Removed: result: string field
- Added: content: (TextContent | ImageContent)[] - full content array
- Added: details: unknown - tool-specific details (typed per tool via discriminated union on toolName)
- ToolResultEventResult.result renamed to ToolResultEventResult.text (removed), use content instead
- Hook handlers returning { result: "..." } must change to { content: [{ type: "text", text: "..." }] }
- Built-in tool details types exported: BashToolDetails, ReadToolDetails, GrepToolDetails, FindToolDetails, LsToolDetails, TruncationResult
- Type guards exported for narrowing: isBashToolResult, isReadToolResult, isEditToolResult, isWriteToolResult, isGrepToolResult, isFindToolResult, isLsToolResult

[0.23.4] - 2025-12-18

Added

Syntax highlighting: Added syntax highlighting for markdown code blocks, read tool output, and write tool content. Uses cli-highlight with theme-aware color mapping and VS Code-style syntax colors. (#214 by @svkozak)
Intra-line diff highlighting: Edit tool now shows word-level changes with inverse highlighting when a single line is modified. Multi-line changes show all removed lines first, then all added lines.

Fixed

Gemini tool result format: Fixed tool result format for Gemini 3 Flash Preview which strictly requires { output: value } for success and { error: value } for errors. Previous format using { result, isError } was rejected by newer Gemini models. (#213, #220)
Google baseUrl configuration: Google provider now respects baseUrl configuration for custom endpoints or API proxies. (#216, #221 by @theBucky)
Google provider FinishReason: Added handling for new IMAGE_RECITATION and IMAGE_OTHER finish reasons. Upgraded @google/genai to 1.34.0.

[0.23.3] - 2025-12-17

Fixed

Check for compaction before submitting user prompt, not just after agent turn ends. This catches cases where user aborts mid-response and context is already near the limit.

Changed

Improved system prompt documentation section with clearer pointers to specific doc files for custom models, themes, skills, hooks, custom tools, and RPC.
Cleaned up documentation:
- theme.md: Added missing color tokens (thinkingXhigh, bashMode)
- skills.md: Rewrote with better framing and examples
- hooks.md: Fixed timeout/error handling docs, added import aliases section
- custom-tools.md: Added intro with use cases and comparison table
- rpc.md: Added missing hook_error event documentation
- README.md: Complete settings table, condensed philosophy section, standardized OAuth docs
Hooks loader now supports same import aliases as custom tools (@sinclair/typebox, @oh-my-pi/pi-ai, @oh-my-pi/pi-tui, @oh-my-pi/pi-coding-agent).

Breaking Changes

Hooks: turn_end event's toolResults type changed from AppMessage[] to ToolResultMessage[]. If you have hooks that handle turn_end events and explicitly type the results, update your type annotations.

[0.23.2] - 2025-12-17

Fixed

Fixed Claude models via GitHub Copilot re-answering all previous prompts in multi-turn conversations. The issue was that assistant message content was sent as an array instead of a string, which Copilot's Claude adapter misinterpreted. Also added missing Openai-Intent: conversation-edits header and fixed X-Initiator logic to check for any assistant/tool message in history. (#209)
Detect image MIME type via file magic (read tool and @file attachments), not filename extension.
Fixed markdown tables overflowing terminal width. Tables now wrap cell contents to fit available width instead of breaking borders mid-row. (#206 by @kim0)

[0.23.1] - 2025-12-17

Fixed

Fixed TUI performance regression caused by Box component lacking render caching. Built-in tools now use Text directly (like v0.22.5), and Box has proper caching for custom tool rendering.
Fixed custom tools failing to load from ~/.omp/agent/tools/ when omp is installed globally. Module imports (@sinclair/typebox, @oh-my-pi/pi-tui, @oh-my-pi/pi-ai) are now resolved via aliases.

[0.23.0] - 2025-12-17

Added

Custom tools: Extend omp with custom tools written in TypeScript. Tools can provide custom TUI rendering, interact with users via omp.ui (select, confirm, input, notify), and maintain state across sessions via onSession callback. See docs/custom-tools.md and examples/custom-tools/. (#190)
Hook and tool examples: Added examples/hooks/ and examples/custom-tools/ with working examples. Examples are now bundled in npm and binary releases.

Breaking Changes

Hooks: Replaced session_start and session_switch events with unified session event. Use event.reason ("start" | "switch" | "clear") to distinguish. Event now includes entries array for state reconstruction.

[0.22.5] - 2025-12-17

Fixed

Fixed --session flag not saving sessions in print mode (-p). The session manager was never receiving events because no subscriber was attached.

[0.22.4] - 2025-12-17

Added

--list-models [search] CLI flag to list available models with optional fuzzy search. Shows provider, model ID, context window, max output, thinking support, and image support. Only lists models with configured API keys. (#203)

Fixed

Fixed tool execution showing green (success) background while still running. Now correctly shows gray (pending) background until the tool completes.

[0.22.3] - 2025-12-16

Added

Streaming bash output: Bash tool now streams output in real-time during execution. The TUI displays live progress with the last 5 lines visible (expandable with ctrl+o). (#44)

Changed

Tool output display: When collapsed, tool output now shows the last N lines instead of the first N lines, making streaming output more useful.
Updated @oh-my-pi/pi-ai with X-Initiator header support for GitHub Copilot, ensuring agent calls are not deducted from quota. (#200 by @kim0)

Fixed

Fixed editor text being cleared during compaction. Text typed while compaction is running is now preserved. (#179)
Improved RGB to 256-color mapping for terminals without truecolor support. Now correctly uses grayscale ramp for neutral colors and preserves semantic tints (green for success, red for error, blue for pending) instead of mapping everything to wrong cube colors.
/think off now actually disables thinking for all providers. Previously, providers like Gemini with "dynamic thinking" enabled by default would still use thinking even when turned off. (#180 by @markusylisiurunen)

[0.22.2] - 2025-12-15

Changed

Updated @oh-my-pi/pi-ai with interleaved thinking enabled by default for Anthropic Claude 4 models.

[0.22.1] - 2025-12-15

Dedicated to Peter's shoulder (@steipete)

Changed

Updated @oh-my-pi/pi-ai with interleaved thinking support for Anthropic models.

[0.22.0] - 2025-12-15

Added

GitHub Copilot support: Use GitHub Copilot models via OAuth login (/login -> "GitHub Copilot"). Supports both github.com and GitHub Enterprise. Models are sourced from models.dev and include Claude, GPT, Gemini, Grok, and more. All models are automatically enabled after login. (#191 by @cau1k)

Fixed

Model selector fuzzy search now matches against provider name (not just model ID) and supports space-separated tokens where all tokens must match

[0.21.0] - 2025-12-14

Added

Inline image rendering: Terminals supporting Kitty graphics protocol (Kitty, Ghostty, WezTerm) or iTerm2 inline images now render images inline in tool output. Aspect ratio is preserved by querying terminal cell dimensions on startup. Toggle with /show-images command or terminal.showImages setting. Falls back to text placeholder on unsupported terminals or when disabled. (#177 by @nicobailon)
Gemini 3 Pro thinking levels: Thinking level selector now works with Gemini 3 Pro models. Minimal/low map to Google's LOW, medium/high map to Google's HIGH. (#176 by @markusylisiurunen)

Fixed

Fixed read tool failing on macOS screenshot filenames due to Unicode Narrow No-Break Space (U+202F) in timestamp. Added fallback to try macOS variant paths and consolidated duplicate expandPath functions into shared path-utils.ts. (#181 by @nicobailon)
Fixed double blank lines rendering after markdown code blocks (#173 by @markusylisiurunen)

[0.20.1] - 2025-12-13

Added

Exported skills API: loadSkillsFromDir, formatSkillsForPrompt, and related types are now exported for use by other packages (e.g., mom).

[0.20.0] - 2025-12-13

Breaking Changes

OMP skills now use SKILL.md convention: OMP skills must now be named SKILL.md inside a directory, matching Codex CLI format. Previously any *.md file was treated as a skill. Migrate by renaming ~/.omp/agent/skills/foo.md to ~/.omp/agent/skills/foo/SKILL.md.

Added

Display loaded skills on startup in interactive mode

[0.19.1] - 2025-12-12

Fixed

Documentation: Added skills system documentation to README (setup, usage, CLI flags, settings)

[0.19.0] - 2025-12-12

Added

Skills system: Auto-discover and load instruction files on-demand. Supports Claude Code (~/.claude/skills/*/SKILL.md), Codex CLI (~/.codex/skills/), and OMP-native formats (~/.omp/agent/skills/, .omp/skills/). Skills are listed in system prompt with descriptions, agent loads them via read tool when needed. Supports {baseDir} placeholder. Disable with --no-skills or skills.enabled: false in settings. (#169)
Version flag: Added --version / -v flag to display the current version and exit. (#170)

[0.18.2] - 2025-12-11

Added

Auto-retry on transient errors: Automatically retries requests when providers return overloaded, rate limit, or server errors (429, 500, 502, 503, 504). Uses exponential backoff (2s, 4s, 8s). Shows retry status in TUI with option to cancel via Escape. Configurable in settings.json via retry.enabled, retry.maxRetries, retry.baseDelayMs. RPC mode emits auto_retry_start and auto_retry_end events. (#157)
HTML export line numbers: Read tool calls in HTML exports now display line number ranges (e.g., file.txt:10-20) when offset/limit parameters are used, matching the TUI display format. Line numbers appear in yellow color for better visibility. (#166)

Fixed

Branch selector now works with single message: Previously the branch selector would not open when there was only one user message. Now it correctly allows branching from any message, including the first one. This is needed for checkpoint hooks to restore state from before the first message. (#163)
In-memory branching for --no-session mode: Branching now works correctly in --no-session mode without creating any session files. The conversation is truncated in memory.
Git branch indicator now works in subdirectories: The footer's git branch detection now walks up the directory hierarchy to find the git root, so it works when running omp from a subdirectory of a repository. (#156)

[0.18.1] - 2025-12-10

Added

Mistral provider: Added support for Mistral AI models. Set MISTRAL_API_KEY environment variable to use.

Fixed

Fixed print mode (-p) not exiting after output when custom themes are present (theme watcher now properly stops in print mode) (#161)

[0.18.0] - 2025-12-10

Added

Hooks system: TypeScript modules that extend agent behavior by subscribing to lifecycle events. Hooks can intercept tool calls, prompt for confirmation, modify results, and inject messages from external sources. Auto-discovered from ~/.omp/agent/hooks/*.ts and .omp/hooks/*.ts. Thanks to @nicobailon for the collaboration on the design and implementation. (#145, supersedes #158)
pi.send() API: Hooks can inject messages into the agent session from external sources (file watchers, webhooks, CI systems). If streaming, messages are queued; otherwise a new agent loop starts immediately.
--hook <path> CLI flag: Load hook files directly for testing without modifying settings.
Hook events: session_start, session_switch, agent_start, agent_end, turn_start, turn_end, tool_call (can block), tool_result (can modify), branch.
Hook UI primitives: ctx.ui.select(), ctx.ui.confirm(), ctx.ui.input(), ctx.ui.notify() for interactive prompts from hooks.
Hooks documentation: Full API reference at docs/hooks.md, shipped with npm package.

[0.17.0] - 2025-12-09

Changed

Simplified compaction flow: Removed proactive compaction (aborting mid-turn when threshold approached). Compaction now triggers in two cases only: (1) overflow error from LLM, which compacts and auto-retries, or (2) threshold crossed after a successful turn, which compacts without retry.
Compaction retry uses Agent.continue(): Auto-retry after overflow now uses the new continue() API instead of re-sending the user message, preserving exact context state.
Merged turn prefix summary: When a turn is split during compaction, the turn prefix summary is now merged into the main history summary instead of being stored separately.

Added

isCompacting property on AgentSession: Check if auto-compaction is currently running.
Session compaction indicator: When resuming a compacted session, displays "Session compacted N times" status message.

Fixed

Block input during compaction: User input is now blocked while auto-compaction is running to prevent race conditions.
Skip error messages in usage calculation: Context size estimation now skips both aborted and error messages, as neither have valid usage data.

[0.16.0] - 2025-12-09

Breaking Changes

New RPC protocol: The RPC mode (--mode rpc) has been completely redesigned with a new JSON protocol. The old protocol is no longer supported. See docs/rpc.md for the new protocol documentation and test/rpc-example.ts for a working example. Includes RpcClient TypeScript class for easy integration. (#91)

Changed

README restructured: Reorganized documentation from 30+ flat sections into 10 logical groups. Converted verbose subsections to scannable tables. Consolidated philosophy sections. Reduced size by ~60% while preserving all information.

[0.15.0] - 2025-12-09

Changed

Major code refactoring: Restructured codebase for better maintainability and separation of concerns. Moved files into organized directories (core/, modes/, utils/, cli/). Extracted AgentSession class as central session management abstraction. Split main.ts and tui-renderer.ts into focused modules. See DEVELOPMENT.md for the new code map. (#153)

[0.14.2] - 2025-12-08

Added

/debug command now includes agent messages as JSONL in the output

Fixed

Fix crash when bash command outputs binary data (e.g., curl downloading a video file)

[0.14.1] - 2025-12-08

Fixed

Fix build errors with tsgo 7.0.0-dev.20251208.1 by properly importing ReasoningEffort type

[0.14.0] - 2025-12-08

Breaking Changes

Custom themes require new color tokens: Themes must now include thinkingXhigh and bashMode color tokens. The theme loader provides helpful error messages listing missing tokens. See built-in themes (dark.json, light.json) for reference values.

Added

OpenAI compatibility overrides in models.json: Custom models using openai-completions API can now specify a compat object to override provider quirks (supportsStore, supportsDeveloperRole, supportsReasoningEffort, maxTokensField). Useful for LiteLLM, custom proxies, and other non-standard endpoints. (#133, thanks @fink-andreas for the initial idea and PR)
xhigh thinking level: Added xhigh thinking level for OpenAI codex-max models. Cycle through thinking levels with Shift+Tab; xhigh appears only when using a codex-max model. (#143)
Collapse changelog setting: Add "collapseChangelog": true to ~/.omp/agent/settings.json to show a condensed "Updated to vX.Y.Z" message instead of the full changelog after updates. Use /changelog to view the full changelog. (#148)
Bash mode: Execute shell commands directly from the editor by prefixing with ! (e.g., !ls -la). Output streams in real-time, is added to the LLM context, and persists in session history. Supports multiline commands, cancellation (Escape), truncation for large outputs, and preview/expand toggle (Ctrl+O). Also available in RPC mode via {"type":"bash","command":"..."}. (#112, original implementation by @markusylisiurunen)

[0.13.2] - 2025-12-07

Changed

Tool output truncation: All tools now enforce consistent truncation limits with actionable notices for the LLM. (#134)
- Limits: 2000 lines OR 50KB (whichever hits first), never partial lines
- read: Shows [Showing lines X-Y of Z. Use offset=N to continue]. If first line exceeds 50KB, suggests bash command
- bash: Tail truncation with temp file. Shows [Showing lines X-Y of Z. Full output: /tmp/...]
- grep: Pre-truncates match lines to 500 chars. Shows match limit and line truncation notices
- find/ls: Shows result/entry limit notices
- TUI displays truncation warnings in yellow at bottom of tool output (visible even when collapsed)

[0.13.1] - 2025-12-06

Added

Flexible Windows shell configuration: The bash tool now supports multiple shell sources beyond Git Bash. Resolution order: (1) custom shellPath in settings.json, (2) Git Bash in standard locations, (3) any bash.exe on PATH. This enables Cygwin, MSYS2, and other bash environments. Configure with ~/.omp/agent/settings.json: {"shellPath": "C:\\cygwin64\\bin\\bash.exe"}.

Fixed

Windows binary detection: Fixed Bun compiled binary detection on Windows by checking for URL-encoded %7EBUN in addition to $bunfs and ~BUN in import.meta.url. This ensures the binary correctly locates supporting files (package.json, themes, etc.) next to the executable.

[0.12.15] - 2025-12-06

Fixed

Editor crash with emojis/CJK characters: Fixed crash when pasting or typing text containing wide characters (emojis like ✅, CJK characters) that caused line width to exceed terminal width. The editor now uses grapheme-aware text wrapping with proper visible width calculation.

[0.12.14] - 2025-12-06

Added

Double-Escape Branch Shortcut: Press Escape twice with an empty editor to quickly open the /branch selector for conversation branching.

[0.12.13] - 2025-12-05

Changed

Faster startup: Version check now runs in parallel with TUI initialization instead of blocking startup for up to 1 second. Update notifications appear in chat when the check completes.

[0.12.12] - 2025-12-05

Changed

Footer display: Token counts now use M suffix for millions (e.g., 10.2M instead of 10184k). Context display shortened from 61.3% of 200k to 61.3%/200k.

Fixed

Multi-key sequences in inputs: Inputs like model search now handle multi-key sequences identically to the main prompt editor. (#122 by @markusylisiurunen)
Line wrapping escape codes: Fixed underline style bleeding into padding when wrapping long URLs. ANSI codes now attach to the correct content, and line-end resets only turn off underline (preserving background colors). (#109)

Added

Fuzzy search models and sessions: Implemented a simple fuzzy search for models and sessions (e.g., codexmax now finds gpt-5.1-codex-max). (#122 by @markusylisiurunen)
Prompt History Navigation: Browse previously submitted prompts using Up/Down arrow keys when the editor is empty. Press Up to cycle through older prompts, Down to return to newer ones or clear the editor. Similar to shell history and Claude Code's prompt history feature. History is session-scoped and stores up to 100 entries. (#121 by @nicobailon)
/resume Command: Switch to a different session mid-conversation. Opens an interactive selector showing all available sessions. Equivalent to the --resume CLI flag but can be used without restarting the agent. (#117 by @hewliyang)

[0.12.11] - 2025-12-05

Changed

Compaction UI: Simplified collapsed compaction indicator to show warning-colored text with token count instead of styled banner. Removed redundant success message after compaction. (#108)

Fixed

Print mode error handling: -p flag now outputs error messages and exits with code 1 when requests fail, instead of silently producing no output.
Branch selector crash: Fixed TUI crash when user messages contained Unicode characters (like ✔ or ›) that caused line width to exceed terminal width. Now uses proper truncateToWidth instead of substring.
Bash output escape sequences: Fixed incomplete stripping of terminal escape sequences in bash tool output. stripAnsi misses some sequences like standalone String Terminator (ESC \), which could cause rendering issues when displaying captured TUI output.
Footer overflow crash: Fixed TUI crash when terminal width is too narrow for the footer stats line. The footer now truncates gracefully instead of overflowing.

Added

authHeader option in models.json: Custom providers can set "authHeader": true to automatically add Authorization: Bearer <apiKey> header. Useful for providers that require explicit auth headers. (#81)
--append-system-prompt Flag: Append additional text or file contents to the system prompt. Supports both inline text and file paths. Complements --system-prompt for layering custom instructions without replacing the base system prompt. (#114 by @markusylisiurunen)
Thinking Block Toggle: Added Ctrl+T shortcut to toggle visibility of LLM thinking blocks. When toggled off, shows a static "Thinking..." label instead of full content. Useful for reducing visual clutter during long conversations. (#113 by @markusylisiurunen)

[0.12.10] - 2025-12-04

Added

Added gpt-5.1-codex-max model support

[0.12.9] - 2025-12-04

Added

/copy Command: Copy the last agent message to clipboard. Works cross-platform (macOS, Windows, Linux). Useful for extracting text from rendered Markdown output. (#105 by @markusylisiurunen)

[0.12.8] - 2025-12-04

Fix: Use CTRL+O consistently for compaction expand shortcut (not CMD+O on Mac)

[0.12.7] - 2025-12-04

Added

Context Compaction: Long sessions can now be compacted to reduce context usage while preserving recent conversation history. (#92, docs)
- /compact [instructions]: Manually compact context with optional custom instructions for the summary
- /autocompact: Toggle automatic compaction when context exceeds threshold
- Compaction summarizes older messages while keeping recent messages (default 20k tokens) verbatim
- Auto-compaction triggers when context reaches contextWindow - reserveTokens (default 16k reserve)
- Compacted sessions show a collapsible summary in the TUI (toggle with o key)
- HTML exports include compaction summaries as collapsible sections
- RPC mode supports {"type":"compact"} command and auto-compaction (emits compaction events)
Branch Source Tracking: Branched sessions now store branchedFrom in the session header, containing the path to the original session file. Useful for tracing session lineage.

[0.12.5] - 2025-12-03

Added

Forking/Rebranding Support: All branding (app name, config directory, environment variable names) is now configurable via ompConfig in package.json. Forks can change ompConfig.name and ompConfig.configDir to rebrand the CLI without code changes. Affects CLI banner, help text, config paths, and error messages. (#95)

Fixed

Bun Binary Detection: Fixed Bun compiled binary failing to start after Bun updated its virtual filesystem path format from %7EBUN to $bunfs. (#95)

[0.12.4] - 2025-12-02

Added

RPC Termination Safeguard: When running as an RPC worker (stdin pipe detected), the CLI now exits immediately if the parent process terminates unexpectedly. Prevents orphaned RPC workers from persisting indefinitely and consuming system resources.

[0.12.3] - 2025-12-02

Fixed

Rate limit handling: Anthropic rate limit errors now trigger automatic retry with exponential backoff (base 10s, max 5 retries). Previously these errors would abort the request immediately.
Usage tracking during retries: Retried requests now correctly accumulate token usage from all attempts, not just the final successful one. Fixes artificially low token counts when requests were retried.

[0.12.2] - 2025-12-02

Changed

Removed support for gpt-4.5-preview and o3 models (not yet available)

[0.12.1] - 2025-12-02

Added

Models: Added support for OpenAI's new models:
- gpt-4.1 (128K context)
- gpt-4.1-mini (128K context)
- gpt-4.1-nano (128K context)
- o3 (200K context, reasoning model)
- o4-mini (200K context, reasoning model)

[0.12.0] - 2025-12-02

Added

-p, --print Flag: Run in non-interactive batch mode. Processes input message or piped stdin without TUI, prints agent response directly to stdout. Ideal for scripting, piping, and CI/CD integration. Exits after first response.
-P, --print-streaming Flag: Like -p, but streams response tokens as they arrive. Use --print-streaming --no-markdown for raw unformatted output.
--print-turn Flag: Continue processing tool calls and agent turns until the agent naturally finishes or requires user input. Combine with -p for complete multi-turn conversations.
--no-markdown Flag: Output raw text without Markdown formatting. Useful when piping output to tools that expect plain text.
Streaming Print Mode: Added internal printStreaming option for streaming output in non-TUI mode.
RPC Mode print Command: Send {"type":"print","content":"text"} to get formatted print output via print_output events.
Auto-Save in Print Mode: Print mode conversations are automatically saved to the session directory, allowing later resumption with --continue.
Thinking level options: Added --thinking-off, --thinking-minimal, --thinking-low, --thinking-medium, --thinking-high flags for directly specifying thinking level without the selector UI.

Changed

Simplified RPC Protocol: Replaced the prompt wrapper command with direct message objects. Send {"role":"user","content":"text"} instead of {"type":"prompt","message":"text"}. Better aligns with message format throughout the codebase.
RPC Message Handling: Agent now processes raw message objects directly, with timestamp auto-populated if missing.

[0.11.9] - 2025-12-02

Changed

Change Ctrl+I to Ctrl+P for model cycling shortcut to avoid collision with Tab key in some terminals

[0.11.8] - 2025-12-01

Fixed

Absolute glob patterns (e.g., /Users/foo/**/*.ts) are now handled correctly. Previously the leading / was being stripped, causing the pattern to be interpreted relative to the current directory.

[0.11.7] - 2025-12-01

Fixed

Fix read path traversal vulnerability. Paths are now validated to prevent reading outside the working directory or its parents. The read tool can read from cwd, its ancestors (for config files), and all descendants. Symlinks are resolved before validation.

[0.11.6] - 2025-12-01

Fixed

Fix --system-prompt <path> allowing the path argument to be captured by the message collection, causing "file not found" errors.

[0.11.5] - 2025-11-30

Fixed

Fixed fatal error "Cannot set properties of undefined (setting '0')" when editing empty files in the edit tool.
Simplified edit tool output: Shows only "Edited file.txt" for successful edits instead of verbose search/replace details.
Fixed fatal error in footer rendering when token counts contain NaN values due to missing usage data.

[0.11.4] - 2025-11-30

Fixed

Fixed chat rendering crash when messages contain preformatted/styled text (e.g., thinking traces with gray italic styling). The markdown renderer now preserves existing ANSI escape codes when they appear before inline elements.

[0.11.3] - 2025-11-29

Fixed

Fix file drop functionality for absolute paths

[0.11.2] - 2025-11-29

Fixed

Fixed TUI crash when pasting content containing tab characters. Tabs are now converted to 4 spaces before insertion.
Fixed terminal corruption after exit when shell integration sequences (OSC 133) appeared in bash output. These sequences are now stripped along with other ANSI codes.

[0.11.1] - 2025-11-29

Added

Added fd integration for file path autocompletion. Now uses fd for faster fuzzy file search

Fixed

Fixed keyboard shortcuts Ctrl+A, Ctrl+E, Ctrl+K, Ctrl+U, Ctrl+W, and word navigation (Option+Arrow) not working in VS Code integrated terminal and some other terminal emulators

[0.11.0] - 2025-11-29

Added

File-based Slash Commands: Create custom reusable prompts as .txt files in ~/.omp/slash-commands/. Files become /filename commands with first-line descriptions. Supports {{selection}} placeholder for referencing selected/attached content.
/branch Command: Create conversation branches from any previous user message. Opens a selector to pick a message, then creates a new session file starting from that point. Original message text is placed in the editor for modification.
Unified Content References: Both @path in messages and --file path CLI arguments now use the same attachment system with consistent MIME type detection.
Drag & Drop Files: Drop files onto the terminal to attach them to your message. Supports multiple files and both text and image content.

Changed

Model Selector with Search: The /model command now opens a searchable list. Type to filter models by name, use arrows to navigate, Enter to select.
Improved File Autocomplete: File path completion after @ now supports fuzzy matching and shows file/directory indicators.
Session Selector with Search: The --resume and --session flags now open a searchable session list with fuzzy filtering.
Attachment Display: Files added via @path are now shown as "Attached: filename" in the user message, separate from the prompt text.
Tab Completion: Tab key now triggers file path autocompletion anywhere in the editor, not just after @ symbol.

Fixed

Fixed autocomplete z-order issue where dropdown could appear behind chat messages
Fixed cursor position when navigating through wrapped lines in the editor
Fixed attachment handling for continued sessions to preserve file references

[0.10.6] - 2025-11-28

Changed

Show base64-truncated indicator for large images in tool output

Fixed

Fixed image dimensions not being read correctly from PNG/JPEG/GIF files
Fixed PDF images being incorrectly base64-truncated in display
Allow reading files from ancestor directories (needed for monorepo configs)

[0.10.5] - 2025-11-28

Added

Full multimodal support: attach images (PNG, JPEG, GIF, WebP) and PDFs to prompts using @path syntax or --file flag

Fixed

@-references now handle special characters in file names (spaces, quotes, unicode)
Fixed cursor positioning issues with multi-byte unicode characters in editor

[0.10.4] - 2025-11-28

Fixed

Removed padding on first user message in TUI to improve visual consistency.

[0.10.3] - 2025-11-28

Added

Added RPC mode (--rpc) for programmatic integration. Accepts JSON commands on stdin, emits JSON events on stdout. See RPC mode documentation for protocol details.

Changed

Refactored internal architecture to support multiple frontends (TUI, RPC) with shared agent logic.

[0.10.2] - 2025-11-26

Added

Added thinking level persistence. Default level stored in ~/.omp/settings.json, restored on startup. Per-session overrides saved in session files.
Added model cycling shortcut: Ctrl+I cycles through available models (or scoped models with -m flag).
Added automatic retry with exponential backoff for transient API errors (network issues, 500s, overload).
Cumulative token usage now shown in footer (total tokens used across all messages in session).
Added --system-prompt flag to override default system prompt with custom text or file contents.
Footer now shows estimated total cost in USD based on model pricing.

Changed

Replaced --models flag with -m/--model supporting multiple values. Specify models as provider/model@thinking (e.g., anthropic/claude-sonnet-4-20250514@high). Multiple -m flags scope available models for the session.
Thinking level border now persists visually after selector closes.
Improved tool result display with collapsible output (default collapsed, expand with Ctrl+O).

[0.10.1] - 2025-11-25

Added

Add custom model configuration via ~/.omp/models.json

[0.10.0] - 2025-11-25

Initial public release.

Added

Interactive TUI with streaming responses
Conversation session management with --continue, --resume, and --session flags
Multi-line input support (Shift+Enter or Option+Enter for new lines)
Tool execution: read, write, edit, bash, glob, grep, think
Thinking mode support for Claude with visual indicator and /thinking selector
File path autocompletion with @ prefix
Slash command autocompletion
/export command for HTML session export
/model command for runtime model switching
/session command for session statistics
Model provider support: Anthropic (Claude), OpenAI, Google (Gemini)
Git branch display in footer
Message queueing during streaming responses
OAuth integration for Gmail and Google Calendar access
HTML export with syntax highlighting and collapsible sections

208 KiB Raw Blame History Unescape Escape

Changelog

[Unreleased]

[10.0.0] - 2026-02-01

Added

Fixed

[9.8.0] - 2026-02-01

Breaking Changes

Added

Changed

Removed

[9.6.2] - 2026-02-01

Changed

Removed

[9.6.1] - 2026-02-01

Fixed

[9.6.0] - 2026-02-01

Breaking Changes

Added

Changed

Removed

Fixed

[9.5.1] - 2026-02-01

Changed

[9.5.0] - 2026-02-01

Added

Changed

Removed

Fixed

[9.4.0] - 2026-01-31

Changed

Removed

[9.3.1] - 2026-01-31

Added

Changed

Removed

[9.2.5] - 2026-01-31

Changed

[9.2.4] - 2026-01-31

Fixed

[9.2.3] - 2026-01-31

Added

Changed

Fixed

[9.2.2] - 2026-01-31

Added

Changed

Fixed

[9.0.0] - 2026-01-29

Fixed

[8.13.0] - 2026-01-29

Added

Fixed

[8.12.7] - 2026-01-29

Fixed

[8.12.2] - 2026-01-28

Changed

[8.11.14] - 2026-01-28

Changed

[8.8.8] - 2026-01-28

Added

Changed

[8.6.0] - 2026-01-27

Added

Changed

Fixed

[8.5.0] - 2026-01-27

Added

Fixed

Removed

[8.4.5] - 2026-01-26

Added

Changed

Fixed

[8.4.2] - 2026-01-25

Changed

[8.4.1] - 2026-01-25

Added

Fixed

[8.4.0] - 2026-01-25

208 KiB

Raw Blame History