Files

T

can1357 79e2f8b2b1 feat(coding-agent): introduced keyed union format for chunk operations

- Changed chunk edit operation format from flat `op` field to nested keyed union structure with operation name as object key.
- Added parseKeyedChunkOp() function to normalize both keyed and legacy flat operation formats for backward compatibility.
- Enhanced chunk selector sanitization with filename prefix stripping and case-insensitive CRC checksum matching.
- Updated chunk edit prompt documentation and test suite to reflect new nested operation JSON structure.

2026-04-06 18:50:08 +02:00

424 KiB

Raw Blame History

Changelog

[Unreleased]

Added

Added new_segment option to init_experiment to force a new segment even when contract fields match, enabling re-initialization with unchanged parameters
Added skip_restore option to log_experiment to preserve working tree state when discarding or failing experiments, useful when runs did not modify tracked files
Added tracking of pre-run dirty paths to distinguish run-produced changes from pre-existing uncommitted changes
Autoresearch init_experiment options from_autoresearch_md (load contract from autoresearch.md with only name) and abandon_unlogged_runs (stamp pending run artifacts abandoned)
Autoresearch run_experiment option force to override benchmark command equality and the direct-autoresearch.sh invocation rule (with warnings when used)
abandonUnloggedAutoresearchRuns helper and abandonedAt run metadata so abandoned artifacts are ignored as pending runs
Support for LSP diagnostic versioning to track document versions and suppress stale diagnostics
Options parameter to waitForDiagnostics for controlling diagnostic freshness validation with expectedDocumentVersion and allowUnversioned flags

Changed

Changed chunk edit operation format from flat { "op": "splice", ... } to keyed { "splice": { ... } } format for improved clarity and schema validation
Updated chunk edit schema to use discriminated union types with operation-specific field requirements (insert ops no longer require CRC, mutation ops require CRC)
Improved chunk selector sanitization to strip filename prefixes and normalize checksums to uppercase, handling model output variations
Changed log_experiment revert behavior to only restore run-modified files instead of reverting entire working tree, preserving pre-existing uncommitted changes
Changed init_experiment error message for pending unlogged runs to include command, metric, and pass/fail status for better context
Changed init_experiment to detect when contract fields match current state and skip re-initialization (no-op) unless new_segment=true
Changed secondary metrics handling to be informational only—missing or new secondary metrics no longer require force=true flag
Updated prompt documentation to clarify that log_experiment reverts only run-modified files and preserves pre-existing changes
Autoresearch log_experiment refreshes benchmark/scope/constraints from autoresearch.md after resolving a pending run (so keep validation matches disk); success output includes a short refresh notice
Autoresearch log_experiment force also skips ASI requirements and allows keeping a primary-metric regression versus the best kept run in the segment
/autoresearch with no autoresearch.md matches /plan-style flow: bare command enables mode and waits for the next composer message when off, or disables when already on; non-empty slash args are submitted as the user message only; setup protocol lives in the autoresearch system prompt (command-initialize.md removed)
Enabled versionSupport in LSP client capabilities to receive diagnostic version information from servers
Diagnostics storage now tracks both diagnostics and their associated document version for freshness validation
Updated getDiagnosticsForFile to accept options object instead of positional parameters for better extensibility
Redesigned chunk-mode read output to use a single recursive chunk rendering rule with $XXXX checksum suffixes and inline large-chunk previews
Normalized copied #chunk_path$XXXX selectors across chunk-mode read and edit inputs so pasted chunk headers resolve without manual cleanup

Removed

Autoresearch segment fingerprint hashing and segmentFingerprint on experiment state / autoresearch.jsonl config lines

Fixed

Fixed log_experiment to correctly identify and revert only files modified by the run, leaving pre-existing uncommitted changes intact
/autoresearch with no arguments toggles off when mode is already on (same idea as /plan), and slash-argument completion no longer offers off/clear on an empty prefix so Tab after the command does not auto-insert a subcommand.
Fixed chunk-mode edit/read edge cases around zero-width gap splices, stale batch diagnostics, grouped Go receiver rendering, rendered line-count headers, and parse rejection location details.

[13.19.0] - 2026-04-05

Added

Added idle auto-compaction settings and scheduling so sessions can compact after inactive turns without auto-continuing.
Added onExternalEditor callback to extension UI dialog options for handling external editor shortcut in select dialogs
Added external editor shortcut support in plan review selector, allowing users to open and edit the plan in their configured editor
Added matchesAppExternalEditor keybinding matcher to detect external editor shortcut (Ctrl+G or configured binding)
Added trimTrailingNewline option to openInEditor function to preserve trailing newlines when editing files
Added GitHub CLI utilities to git module (utils/git.github) with available(), run(), json(), and text() methods for GitHub CLI operations
Exported git utilities from main package entry point for use by extensions
Added comprehensive git utility module (utils/git) with organized namespaces for common git operations (branch, commit, diff, log, patch, ref, stage, status, head, repository)

Changed

Changed idle compaction settings (compaction.idleThresholdTokens and compaction.idleTimeoutSeconds) from enum to numeric type for flexible configuration
Modified secret obfuscation to deobfuscate restored session messages for local display while keeping outbound LLM messages obfuscated
Updated stash pop operation to preserve staged changes with --index flag when restoring after task branch merges
Changed secret placeholders to deterministic hash-style redaction tokens and deobfuscated assistant output for local display.
Updated hook editor and hook selector components to use matchesAppExternalEditor matcher for consistent external editor keybinding detection
Modified plan review flow to read the latest plan content from disk before approval, allowing changes made in external editor to be reflected
Enhanced plan review help text to dynamically display the configured external editor keybinding
Refactored git operations to use centralized utility module instead of ControlledGit class throughout codebase
Replaced ControlledGit dependency injection pattern with direct cwd parameter in commit agent tools
Migrated git HEAD resolution in footer and status-line components to use new synchronous and asynchronous utilities
Updated git status summary calculation in status-line component to use new git utility API
Simplified git branch operations in task execution and cleanup to use new utility functions
Refactored patch application logic in task worktree to use new git patch utilities

Removed

Removed gh-cli.ts module; GitHub CLI functionality now available via utils/git.github
Removed ControlledGit class and associated git wrapper infrastructure from commit/git module
Removed mergeStdoutStderr helper function from autoresearch git utilities
Removed findGitHeadPathAsync and findGitHeadPathSync from modes/shared module (replaced by git utilities)
Removed ./commit/git export from package.json (internal diff parsing still available via ./commit/git/*)

Fixed

Fixed idle compaction timer to properly cancel when event controller is disposed, preventing memory leaks
Fixed session resumption to preserve the last non-empty session when starting a fresh session
Fixed stash detection to use git ref resolution instead of output parsing for reliable stash state tracking
Fixed isolated task merge-back to preserve task outputs on merge failure and stash dirty worktrees before cherry-pick.
Fixed web search source rendering to truncate long title, metadata, and URL lines before they overflow the UI.
Fixed PR checkout tool to resolve symlinks in worktree paths, ensuring consistent path references in results and metadata
Fixed read output for file-backed internal URLs like local://... to include hashline prefixes in hashline edit mode, preserving usable line refs for follow-up edits
Fixed the plan review selector to support the external editor shortcut for opening and updating the current plan from the approval screen

[13.18.0] - 2026-04-02

Breaking Changes

Removed standalone fetch tool; URL fetching is now integrated into the read tool

Added

Added URL reading capability to read tool with support for web pages, GitHub issues, Stack Overflow, Wikipedia, Reddit, NPM, arXiv, technical blogs, RSS/Atom feeds, and JSON endpoints
Added offset and limit parameter support for paginating cached URL fetch results
Added URL caching mechanism to avoid redundant network requests when reading the same URL multiple times

Changed

Renamed fetch.enabled setting to Read URLs with updated description to reflect integration with read tool
Updated read tool to accept timeout and raw parameters for URL handling
Updated read tool to support file:// URLs for local file paths
Removed fetch tool from agent tool lists (explore, librarian, oracle, plan, reviewer agents)

Fixed

Fixed read tool to properly handle file:// URL scheme by converting to filesystem paths

[13.17.5] - 2026-04-01

Added

Added support for writing to ZIP archives using fflate library for cross-platform compatibility

Changed

Modified archive writing to detect and handle ZIP files separately from Bun archives

Removed

Removed GhPrPushTool test case

[13.17.4] - 2026-04-01

Added

Support for writing to archive entries in .tar, .tar.gz, .tgz, and .zip files using archive.ext:path/inside/archive syntax
Ability to create new archives when writing to archive subpaths that don't yet exist

[13.17.3] - 2026-04-01

Added

Added support for converting Jupyter notebooks (.ipynb) to markdown via markit
Added markit-ai npm package for native document and notebook conversion
Added support for reading files from .tar, .tar.gz, .tgz, and .zip archives using virtual subpaths like archive.ext:path/to/file
Added ability to list archive contents and navigate subdirectories within supported archive formats
Added archive-aware read support for .tar, .tar.gz, .tgz, and .zip, including virtual subpaths like archive.ext:path/to/file
Added /tools slash command to show the tools currently visible to the agent in the interactive session

Changed

Replaced Python-based markitdown CLI tool with native markit-ai library for document conversion
Updated document conversion to use markit library instead of external markitdown command
Removed markitdown from Python tools manager (no longer needed as external dependency)
Updated read tool documentation to reflect archive support and usage patterns

[13.17.2] - 2026-04-01

Added

Added /marketplace help command to display usage guide for all marketplace operations
Added dedicated gh-renderer.ts module for rich terminal rendering of GitHub Actions workflow runs with live status snapshots and job details
Added gh_pr_checkout tool to check out GitHub pull requests into dedicated git worktrees with contributor push metadata
Added gh_pr_push tool to push checked-out pull request branches back to their source branches
Added gh_repo_view tool to read GitHub repository metadata using the local GitHub CLI
Added gh_issue_view tool to read GitHub issues with optional comment context
Added gh_pr_view tool to read GitHub pull requests with optional comment context
Added gh_pr_diff tool to read GitHub pull request diffs with optional file filtering
Added gh_search_issues tool to search GitHub issues with repository scoping
Added gh_search_prs tool to search GitHub pull requests with repository scoping
Added gh_run_watch tool to watch GitHub Actions workflow runs, fast-fail on job failures, and stream tailed logs for failed jobs
Added github.enabled setting to enable read-only gh_* GitHub CLI tools for repository, issue, pull request, diff, and search workflows
Added bundled /green command to generate iterative CI fix prompts with optional tag instructions when HEAD is tagged
Added github.enabled setting to enable read-only gh_* GitHub CLI tools for repository, issue, pull request, diff, and search workflows
Added gh_repo_view tool to read GitHub repository metadata using the local GitHub CLI
Added gh_issue_view tool to read GitHub issues with optional comment context
Added gh_pr_view tool to read GitHub pull requests with optional comment context
Added gh_pr_diff tool to read GitHub pull request diffs with optional file filtering
Added gh_search_issues tool to search GitHub issues with repository scoping
Added gh_search_prs tool to search GitHub pull requests with repository scoping
Added gh_run_watch tool to watch GitHub Actions workflow runs, fast-fail on job failures, and stream tailed logs for failed jobs
Added bundled /green command to generate iterative CI fix prompts with optional tag instructions when HEAD is tagged
Project-scoped marketplace plugin installs: omp plugin install --scope project name@marketplace and /marketplace install --scope project name@marketplace install plugins into the nearest .omp/ or .git-rooted project directory instead of the user directory (#581)
--scope user|project flag added to /marketplace uninstall, /marketplace upgrade, /plugins enable, and /plugins disable to disambiguate when a plugin is installed in both scopes
omp plugin upgrade --scope project with no plugin ID warns that --scope is ignored for bulk upgrades
Added opt-in gh_* GitHub CLI tools behind the github.enabled setting for repository, issue, pull request, diff, and search workflows
Added opt-in gh_run_watch to fast-fail GitHub Actions runs, stream job status snapshots, and return tailed logs for failed jobs
Added bundled /green command to generate the iterative “fix CI until green” prompt, with final tag instructions included only when HEAD already has a tag

Changed

Improved marketplace catalog parsing to skip invalid plugin entries with warnings instead of failing the entire catalog load
Enhanced /marketplace discover command to suggest adding the official marketplace when no plugins are available
Improved /marketplace command messaging with clearer guidance for first-time setup and available commands
Enhanced gh_run_watch tool call rendering to display animated spinner status and target description (run ID, branch, or current HEAD) with improved visual hierarchy
Enhanced gh_pr_view tool to include inline review comments alongside pull request reviews for improved discussion context
Improved gh_run_watch tool output rendering with dedicated visual component for streaming run snapshots and job status updates

Fixed

Fixed marketplace error messages to display error details instead of object stringification
Fixed artifact storage for non-persistent sessions to use in-memory fallback instead of returning undefined, enabling proper spill truncation for all session types
Fixed prompt file formatting to include trailing newlines at EOF for consistency across all prompt markdown files
Fixed gh_pr_diff to preserve raw patch content instead of normalizing tabs and whitespace
Fixed gh_pr_view to include inline review comments alongside pull request reviews and issue-style comments for discussion context
Fixed gh_run_watch to resolve explicit branch watches against the selected branch head instead of local HEAD
Fixed gh_run_watch to hide repo and polling internals from the tool schema and save full failed-job logs as session artifacts alongside the inline tailed output
Fixed gh_* tool outputs to spill full large results to artifacts instead of pre-truncating the head with unusable offset= guidance
Fixed bundled /green to watch the workflow runs for the current HEAD commit instead of whichever branch run was newest
Fixed OpenAI Responses session rehydration to strip stale assistant replay payloads before resumed requests (#594 by @daandden)
Fixed inline image rendering to cap image height and preserve multiplexer scrollback during terminal resizes (#587 by @smileynet)

[13.17.1] - 2026-04-01

Removed

Removed code_search tool for code snippet and documentation search

Fixed

Fixed edit tool diff rendering to wrap long diff lines with continuation gutters instead of truncating them at terminal width (#578)
Fixed --list-models and /model provider filtering to hide models from disabled providers (#588)
Fixed edit tool diffstats to use diff-specific add/remove theme colors instead of success/error status colors (#589)

[13.17.0] - 2026-03-30

Added

Added marketplace.autoUpdate setting (off/notify/auto, default notify) for automatic plugin update checking on startup
Added background marketplace catalog refresh on startup when catalogs are stale (>24h)
Added /marketplace upgrade [name@marketplace] slash command to upgrade outdated plugins
Added omp plugin upgrade [name@marketplace] CLI command for plugin upgrades
Added checkForUpdates(), upgradePlugin(), upgradeAllPlugins(), and refreshStaleMarketplaces() to MarketplaceManager
Added marketplace plugin system: registry types, ID helpers, atomic read/write for marketplaces.json and installed_plugins.json (Claude Code-compatible format)
Added MarketplaceManager orchestrator for marketplace and plugin lifecycle (add/remove/update marketplaces, install/uninstall/enable plugins)
Added marketplace fetcher with source classification (GitHub, git, URL, local) and catalog validation
Added plugin source resolver with pathIsWithin containment checks and versioned cache manager
Added CLI commands: omp plugin marketplace add|remove|update|list, omp plugin discover [marketplace]
Added classifyInstallTarget() to distinguish name@marketplace from npm install targets
Extended listClaudePluginRoots() to read OMP's installed plugins registry alongside Claude Code's, with OMP as authoritative for duplicate plugin IDs
Added --plugin-dir <path> repeatable CLI flag for loading plugins from local directories
Added /reload-plugins slash command that invalidates fs content cache and plugin roots cache
Added printPluginHelp() entries for marketplace and discover commands
Added MCP server loading from marketplace plugin .mcp.json files with ${CLAUDE_PLUGIN_ROOT} variable substitution
Added skill and command namespacing for marketplace plugins (plugin-name:skill-name)
Added LSP config loading from marketplace plugin roots via getPreloadedPluginRoots()
Wired --plugin-dir runtime injection into plugin roots at session startup with highest precedence
Added git (GitHub, SSH, HTTPS) and HTTP URL marketplace source fetching
Added /marketplace TUI slash command with subcommands: add, remove, update, list, discover, install, uninstall, installed
Added /plugins TUI slash command to view all installed plugins (npm + marketplace) and enable/disable marketplace plugins

Changed

Changed marketplace clone promotion to occur after duplicate and drift checks, improving safety of concurrent marketplace operations

Removed

Removed grep.app code search provider support; code search now uses Exa exclusively
Removed providers.codeSearch setting and related configuration options

Fixed

Fixed git-subdir plugin source resolution to properly clean up temporary clone directories on path validation errors
Fixed LSP config loading to use correct filenames variable when scanning plugin roots
Fixed plugin selector UI to request render on cancel, preventing stale display state
Fixed marketplace install command error handling to display user-friendly error messages instead of crashing
Fixed MCP tools from newly added servers not being activated after /mcp add — refreshMCPTools preserves prior MCP tool selections, so brand-new servers had their tools registered in the registry but never passed to the agent; tools are now explicitly activated on successful connection
Fixed skill:// URI resolver to handle namespaced skills via longest-prefix matching against registered skill names

[13.16.5] - 2026-03-29

Fixed

Fixed --model provider/id resolving to wrong provider when model ID exists in multiple catalogs (#560)

[13.16.4] - 2026-03-28

Changed

Renamed hashline helper functions from hlineref/hlinefull to href/hline for brevity
Simplified hashline edit location API: replaced separate line and block properties with unified range property accepting { pos, end } for all range-based edits
Updated hashline prompt documentation to reflect new range syntax and clarified editing guidelines

Fixed

Added detection for kysely-codegen generated files in auto-generated file guard

[13.16.1] - 2026-03-27

Added

Added searchDb parameter to PromptActionAutocompleteProvider constructor for native search database integration in autocomplete workflows
Added searchDb parameter to enable native search database integration for grep and find operations
Exported SearchDb type from tools module for type-safe search database usage

Changed

Updated grep tool to accept and utilize searchDb parameter for improved search performance
Updated find tool to pass searchDb parameter to underlying search operations
Updated grep tool description to remove ripgrep-specific implementation detail

[13.16.0] - 2026-03-27

Added

Implemented root path alias: bare / in tool inputs now resolves to the session working directory instead of the filesystem root
Added browser.screenshotDir setting to configure screenshot save directory with path expansion

Changed

Improved hashline tool documentation with clearer guidance on block boundary handling and closing delimiter duplication prevention
Updated screenshot path resolution to use resolveToCwd for consistent workspace-relative path handling
Updated hook editor hint text to include ctrl+g external editor option when using prompt style
Refactored question result formatting to consistently include question ID in output

[13.15.3] - 2026-03-26

Added

Added configurable app.model.selectTemporary keybinding for temporary model selection.

[13.15.0] - 2026-03-23

Breaking Changes

Changed hashline edit schema from flat op/pos/end/lines fields to structured loc/content format with location-specific objects
Renamed hashline edit operations: replace_line → { line: anchor }, replace_range → { block: { pos, end } }, append_at → { append: anchor }, prepend_at → { prepend: anchor }, append_file → "append", prepend_file → "prepend"
Changed lines parameter to content in hashline edit entries
Renamed hashline edit operation types: append → append_at, prepend → prepend_at, append_eof → append_file, prepend_bof → prepend_file
Changed hashline edit operation types from replace (with optional end) to explicit replace_line and replace_range operations
Added required append_eof and prepend_bof operations for file-level edits; append and prepend now require an anchor position
Made pos parameter required for replace_line, append, and prepend operations; append_eof and prepend_bof no longer accept anchors

Added

Added custom model roles/tags via config YAML
Added ability to reorder model role/tag cycling via config YAML
Added prompt for tradeoff metrics during autoresearch setup to collect secondary metrics alongside primary metric
Added validation of contract path specifications to reject absolute paths and parent directory references
Added stricter benchmark command validation in isAutoresearchShCommand() to reject chained commands, pipes, and redirects
Added protection against prototype pollution in ASI data and metric cloning by filtering __proto__, constructor, and prototype keys
Added autoResumeArmed flag to track when autoresearch should automatically resume pending runs
Added lastAutoResumePendingRunNumber to prevent duplicate auto-resume prompts for the same pending run
Added git clean -X invocation during failed experiment rollback to remove ignored build artifacts
Added validation to reject init_experiment when a previous run is still pending and unlogged
Added autoresearch contract system for validating benchmark commands, metrics, scope paths, off-limits paths, and constraints with fingerprint tracking to detect configuration drift
Added autoresearch.program.md support for repo-local playbook overlays that guide session strategy while preserving autoresearch.md as source of truth
Added pending run artifact tracking and recovery to resume incomplete experiments from .autoresearch/runs/ directory with run numbers and benchmark logs
Added run directory organization with numbered run artifacts, benchmark logs, and optional checks logs for experiment traceability
Added segment fingerprinting to detect when benchmark configuration changes between runs and warn about potential incomparability
Added support for secondary metrics tracking alongside primary metric with configurable direction (lower/higher is better)
Added getCurrentAutoresearchBranch() helper to detect and validate existing autoresearch branches for session resumption
Added PendingRunSummary type to track unlogged run state including parsed metrics, ASI data, and pass/fail status
Added hidden next-turn message delivery via deliverAs: 'nextTurn' with optional triggerTurn to queue context for next LLM call without exposing in editable queue
Added #queueHiddenNextTurnMessage() and #promptQueuedHiddenNextTurnMessages() to AgentSession for autonomous tool reactions
Added resume context support in command-resume.md template for user-provided guidance when resuming sessions
Added current segment snapshot display in autoresearch prompt showing recent runs, baseline metrics, and best results
Added pending run indicator in autoresearch prompt to guide users to complete unlogged experiments before starting new benchmarks
Added local playbook section in autoresearch prompt when autoresearch.program.md exists
Added tab replacement in dashboard and tool output rendering to prevent display corruption from shell commands with tabs
Added boundary duplication warning when replace_range or replace_line operations include a last inserted line that matches the next surviving line, helping detect off-by-one range errors
Added git branch isolation for autoresearch sessions via ensureAutoresearchBranch() to safely revert failed experiments
Added branch status line to autoresearch initialization and resume prompts showing created or reused branch name
Added Files in Scope, Off Limits, and Constraints sections to autoresearch.md template for explicit scope definition
Added validation of ASI metadata requirements in log_experiment tool, requiring hypothesis for all runs and rollback context for failed runs
Added keybinding matcher utilities matchesAppInterrupt() and matchesSelectCancel() for consistent escape key handling across components
Added support for customizable app.interrupt and tui.select.cancel keybindings in interactive components
Added defaultInactive property to ToolDefinition to allow tools to be registered but excluded from the initial active set, with extension responsibility for activation/deactivation
Added dynamic tool activation/deactivation in autoresearch mode via setActiveTools() API
Added separate initialization and resume workflows for autoresearch with command-initialize.md and command-resume.md prompts
Added intent dialog to prompt users for autoresearch optimization goals when starting fresh
Added automatic detection of existing autoresearch.md to resume from previous sessions without re-prompting for intent
Added autoresearch extension with autonomous experiment loop capabilities
Added init_experiment tool to initialize and reset autoresearch sessions with configurable metrics
Added log_experiment tool to record experiment results with metric parsing and confidence tracking
Added run_experiment tool to execute commands and capture metrics with timeout and crash detection
Added autoresearch dashboard controller for displaying experiment results and optimization progress
Added support for secondary metrics tracking alongside primary metric
Added ExtensionWidgetContent and ExtensionUiComponentFactory types for flexible widget configuration
Added ExtensionWidgetOptions interface with placement parameter to position widgets above or below editor
Added WidgetPlacement type supporting 'aboveEditor' and 'belowEditor' placement options
Added hookWidgetContainerAbove and hookWidgetContainerBelow containers to InteractiveMode for separate widget management
Added autoresearch mode for autonomous experiment loops with init_experiment, log_experiment, and run_experiment tools
Added autoresearch dashboard widget displaying experiment results, metrics, and optimization progress
Added support for metric tracking with configurable direction (lower/higher is better) and secondary metrics
Added widget placement options to position extensions above or below the editor via placement parameter
Added ExtensionWidgetContent and ExtensionWidgetOptions types for flexible widget configuration
Added ACP (Agent Client Protocol) mode for headless agent operation via --mode acp
Added support for Agent Client Protocol SDK integration with session management, MCP server configuration, and streaming communication
Added ensureOnDisk() method to SessionManager to persist sessions immediately for ACP discovery
Added multiline custom input for ask custom answers, using the prompt-style editor without inactivity timeout while composing (#506)

Changed

Changed autoresearch initialization to collect and validate benchmark command, metric definition, scope paths, off-limits list, and constraints before init_experiment
Changed init_experiment to require exact benchmark command, metric definition, scope, off-limits, and constraints matching collected contract
Changed log_experiment to record run number, benchmark command, scope paths, off-limits list, constraints, and segment fingerprint with each result
Changed run_experiment to organize output in numbered run directories with separate benchmark and checks logs for artifact preservation
Changed autoresearch dashboard to show pending run indicator when unlogged experiment exists
Changed autoresearch resume workflow to detect and offer recovery of pending run artifacts before continuing experiment loop
Changed ExperimentResult to include runNumber, benchmarkCommand, scopePaths, offLimits, constraints, and segmentFingerprint fields
Changed RunningExperiment to track runDirectory and runNumber for artifact organization
Changed AutoresearchRuntime to include lastRunArtifactDir, lastRunNumber, lastRunSummary, benchmarkCommand, secondaryMetrics, scopePaths, offLimits, constraints, and segmentFingerprint
Changed autoresearch prompts to emphasize autoresearch.md as source of truth for benchmark, scope, and constraints
Changed command-initialize.md to display collected setup (benchmark command, metric, direction, scope, off-limits, constraints) before initialization
Changed resume-message.md to reference pending run artifacts and guide completion of unlogged experiments
Changed sendMessage() API documentation to clarify deliverAs: 'nextTurn' behavior for hidden context delivery
Changed SendMessageHandler type documentation to explain hidden next-turn message queuing during prompt teardown
Changed autoresearch startup to create or reuse a dedicated autoresearch/... git branch before enabling the experiment loop
Changed autoresearch to refuse startup when unrelated worktree changes would make auto-reverts unsafe
Changed autoresearch prompts to emphasize scope and constraints as source of truth for session direction
Changed component escape key handling to use keybinding manager for app.interrupt and tui.select.cancel with fallback to raw Escape matching
Updated autoresearch prompt guidance to require explicit files in scope, off-limits paths, and session constraints
Changed autoresearch command to use intent-based initialization instead of goal parameter, with user input dialog for new sessions
Changed autoresearch startup to create or reuse a dedicated autoresearch/... git branch before enabling the experiment loop, and to refuse startup when unrelated worktree changes would make auto-reverts unsafe
Changed autoresearch startup to activate experiment tools (init_experiment, run_experiment, log_experiment) only when autoresearch mode is enabled
Changed autoresearch shutdown to deactivate experiment tools when mode is disabled or cleared
Changed autoresearch session rehydration to dynamically manage experiment tool activation based on session state
Changed autoresearch prompts and notes guidance to require explicit files in scope, off-limits paths, and session constraints
Refactored hashline edit validation to enforce stricter anchor requirements per operation type
Updated edit application logic to handle explicit file-level operations (append_eof, prepend_bof) separately from anchor-based operations
Changed setWidget API to accept ExtensionWidgetOptions parameter for placement control
Changed widget placement logic to manage widgets above and below editor separately
Changed hashline edit application to preserve duplicated boundary lines exactly as provided instead of auto-correcting them
Updated RPC mode to support widget placement option in setWidget requests
Changed hashline edit application to preserve duplicated boundary lines exactly as provided instead of auto-correcting them
Changed widget API to support placement options and component factories in addition to string arrays
Updated extension UI controller to manage widgets above and below the editor separately
Updated ask tool rendering to support markdown formatting in questions and option labels
Refactored hook input and selector components to render titles as markdown for richer text formatting
Changed session collection to include sessions with zero messages, enabling ACP mode to create discoverable sessions immediately
Changed session persistence logic to use atomic file rewrite when flushing unflushed sessions to prevent duplication
Removed hashline edit autocorrection for duplicated boundary lines; escaped-tab autocorrection remains available for leading \\t sequences

Removed

Removed command-start.md prompt template in favor of separate initialize and resume workflows
Removed auto-correction of off-by-one range edits that duplicated closing braces or boundary lines
Removed shouldAutocorrect function and related boundary line deduplication logic from hashline editor
Removed auto-correction of off-by-one range edits that duplicated closing braces or boundary lines

Fixed

Fixed autoresearch resume to detect and recover pending run artifacts that were left unlogged from previous sessions
Fixed dashboard overlay to display when running experiment even with zero completed results
Fixed tab character rendering in dashboard command display and tool output summaries
Fixed autoresearch logging to require durable ASI metadata (hypothesis, rollback_reason, next_action_hint) for every run including rollback context for discarded, crashed, and checks-failed experiments
Fixed autoresearch logging to require durable ASI metadata for every run, including rollback context for discarded, crashed, and checks-failed experiments

Fixed

Fixed resumed and session-switched GitHub Copilot/OpenAI Responses conversations replaying stale assistant native history from older saved sessions by sanitizing persisted assistant replay metadata on rehydration and resetting provider session state across live session boundaries (#505)

Added

Session observer overlay (Ctrl+S): view running subagent sessions with a picker and read-only transcript showing thinking, text, tool calls, and results

[13.14.0] - 2026-03-20

Added

Auto-reconnect MCP servers on connection loss with proactive SSE stream monitoring and retry backoff
Tool-level reconnect: retriable connection errors (ECONNREFUSED, ECONNRESET, stale session 404/502/503) trigger automatic reconnection and single retry
/mcp reconnect <name> command for manual server recovery after extended outages

Changed

Extended transport reconnect handling to all transport types (not just HTTP/SSE), ensuring stdio and other transports trigger automatic reconnection on connection loss
Improved reconnect robustness by aborting retry attempts when MCP server configuration changes during reconnection sequence
Updated explore agent thinking level from off to med for improved reasoning
Simplified explore agent output schema: consolidated file references into single ref field with optional line ranges instead of separate path, line_start, line_end fields
Removed code section from explore agent output (critical code excerpts no longer extracted)
Removed dependencies section from explore agent output
Removed risks section from explore agent output
Removed start_here section from explore agent output

Fixed

Fixed reconnect retry loop continuing after configuration changes by checking epoch before each reconnection attempt
roots/list timeout on MCP server initialization: connectToServer now always installs a default handler for ping and roots/list
Fixed resumed GitHub Copilot conversations that could fail with 401 input item does not belong to this connection on the first follow-up after process restart (#488)
Fixed STT Alt+H mic cursor rendering to measure the actual microphone glyph width, preventing one-column TUI overflow crashes when the active symbol preset uses a wide icon (#484)

[13.13.2] - 2026-03-18

Added

Added automatic stripping of hashline display prefixes (LINE#ID:) from write tool content when hashline edit mode is enabled, preventing the model from accidentally copying display markers into files
Added mcpServerName and mcpToolName optional properties to custom tools for MCP server discovery and search metadata

[13.13.1] - 2026-03-18

Added

Automatic deduplication of identical context files by content, keeping the closest (lowest depth) copy when duplicates are discovered

[13.13.0] - 2026-03-18

Added

Added edit.blockAutoGenerated setting to control whether auto-generated file detection is enforced (enabled by default)
Improved auto-generated file detection to use language-specific comment parsing instead of broad regex patterns, reducing false positives
Added auto-generated file detection to prevent accidental modification of generated code (protoc, sqlc, buf, swagger, etc.)
Added validation in Edit and Write tools to block modifications to files with auto-generated markers or naming patterns

Changed

Enhanced auto-generated marker detection to only scan leading header comments rather than entire file prefix, improving accuracy for files with generated markers in code

[13.12.10] - 2026-03-17

Added

Added args field to ShellResult to capture the executed command
Added exit_code property to ShellResult as an alias for returncode
Added check_returncode() method to ShellResult to raise CalledProcessError on non-zero exit codes

Changed

Renamed code field to returncode in ShellResult (accessible via code property for backward compatibility)
Updated run() command documentation to clarify available ShellResult fields

[13.12.9] - 2026-03-17

Added

Added /session delete command to delete current session with confirmation and return to session selector
Added session deletion in session selector via Delete key with confirmation dialog

Changed

Changed session deletion callback to return a boolean indicating success, allowing callers to distinguish between failed deletions and upstream cancellations

Fixed

Fixed OAuth redirect URI validation to preserve exact configured values without adding trailing slashes
Fixed session deletion error handling to display error messages in the session selector UI instead of silently failing
Added oauth.redirectUri, oauth.clientSecret, and oauth.callbackPath support for MCP server OAuth config so providers can use exact registered redirect URIs while preserving local callback listener settings (#445)

[13.12.8] - 2026-03-16

Breaking Changes

Changed SessionManager.create() to require explicit sessionDir parameter instead of optional—callers must now pass SessionManager.getDefaultSessionDir(cwd) to use default behavior
Changed SessionManager.continueRecent() to require explicit sessionDir parameter instead of optional—callers must now pass SessionManager.getDefaultSessionDir(cwd) to use default behavior
Changed SessionManager.forkFrom() to require explicit sessionDir parameter instead of optional—callers must now pass SessionManager.getDefaultSessionDir(cwd) to use default behavior
Changed SessionManager.list() signature to accept only sessionDir parameter instead of cwd and optional sessionDir—callers must now compute and pass the session directory explicitly

Added

Added SessionManager.getDefaultSessionDir() static method to explicitly resolve the canonical default session directory for a working directory
Added support for quoted paths in grep, ast_grep, and find tools to handle directory names with spaces
Added normalizePathLikeInput utility function to consistently handle quoted and whitespace-trimmed path inputs

Changed

Made sessionDir parameter optional in SessionManager.create(), SessionManager.continueRecent(), and SessionManager.forkFrom()—callers can now omit it to use the default session directory
Changed SessionManager.list() signature to accept cwd as the first parameter instead of requiring an explicit sessionDir—callers can now omit sessionDir to use the default for the given working directory
Updated SessionManager.getDefaultSessionDir() to accept optional agentDir parameter for computing session directories within a custom agent root
Improved status line path display to strip display roots using canonical path resolution, correctly handling symlink aliases to home and Projects directories
Improved error messaging in ast_grep when no matches are found with parse errors, now suggests narrowing path/glob or setting lang to resolve mis-scoped queries

Fixed

Fixed SDK-created default sessions to honor the configured agentDir for session storage, preventing tests from writing stray session directories into the real ~/.omp/agent/sessions root
Fixed session directory resolution to correctly handle symlink-equivalent paths, ensuring aliased home and temp directories resolve to the same session storage location as their real targets

[13.12.7] - 2026-03-16

Changed

Modified getSelectedMCPToolNames() to return only active MCP tools in non-discovery sessions, filtering by tool registry availability
Updated search_tool_bm25 tool instantiation to conditionally create the tool only when MCP discovery mode is enabled and execution hooks are available
Changed search results to exclude already-selected MCP tools before applying the limit parameter, allowing discovery of additional tools in subsequent searches

Fixed

Fixed MCP tool selection tracking to properly distinguish between discovery-enabled and non-discovery sessions, preventing orphaned tool selections after manual deactivation

[13.12.6] - 2026-03-15

Changed

Updated llama.cpp model discovery to read context window from the /props endpoint's default_generation_settings.n_ctx field instead of using hardcoded 128000 default
Updated llama.cpp model discovery to detect vision capabilities from the /props endpoint's modalities.vision field instead of defaulting to text-only input
Changed llama.cpp maxTokens calculation to respect discovered context window limits, capping at 8192 or the server's context window, whichever is smaller

Fixed

Fixed llama.cpp auto-discovery to read context window and vision support from the native /props endpoint instead of relying on hardcoded defaults

[13.12.5] - 2026-03-15

Added

Automatic discovery of Ollama model context window from model metadata, enabling accurate token limit configuration
Added attribution option to PromptOptions to explicitly control billing/initiator attribution for prompts
Added automatic clearing of completed and abandoned todo tasks after ~1 minute

Changed

Ollama model registration now uses discovered context window instead of hardcoded 128000 token default
Ollama model maxTokens now respects discovered context window constraints
Improved session directory migration to handle legacy absolute paths with double-dash format, automatically relocating them to new canonical locations
Enhanced session directory encoding to use -tmp- prefix for temporary directories instead of legacy double-dash format for better clarity
Updated SessionManager.create() to require both cwd and sessionDir parameters for explicit session directory control
Improved session directory naming for temporary working directories using -tmp- prefix instead of legacy -- format
Made cwd and sessionDir fields mutable in SessionManager to support session relocation without type casting
Changed subagent prompts to explicitly set attribution: "agent" for accurate billing attribution
Strip already-completed tasks when restoring session from branch history

Fixed

Fixed automatic migration of legacy session directories to new -tmp- prefixed naming scheme for temp-root sessions

[13.12.4] - 2026-03-15

Added

Exposed settings instance in CustomToolContext for session-specific configuration access

Changed

Improved artifact spill configuration to use session settings with schema defaults as fallback
Refactored type annotations for better type safety in tool result handling

[13.12.2] - 2026-03-15

Added

Added compaction.thresholdTokens setting as a fixed token limit alternative to percentage-based compaction threshold
Added more artifact spill threshold options (1 KB to 1 MB) with size descriptions
Added more artifact tail bytes and tail lines options with descriptions
Added toExtensionId capability method to enable granular disabling of individual capabilities by ID
Added support for disabling specific capabilities (skills, tools, hooks, rules, prompts, instructions, slash commands, MCP servers, extension modules, and context files) via disabledExtensions setting
Added includeDisabled and disabledExtensions options to LoadOptions for capability loading
Added plugin manifest support for extensions entry points to allow plugins to contribute extension modules
Added extensions field to plugin features for feature-specific extension entry points
Added automatic discovery of extension modules from installed plugins during extension loading
Added disabledExtensions setting to allow disabling specific extensions and skills by ID
Added support for filtering skills by disabled extension IDs with skill: prefix

Changed

Changed capability loading to filter out disabled items based on extension IDs before returning results
Changed plugin loader to support extensions as a manifest entry type alongside tools, hooks, and commands
Changed extension discovery to include extension entry points from all enabled plugins
Changed context file path handling to use path.basename() for consistent cross-platform filename extraction

Fixed

Fixed skill loading to properly respect disabled skill names when loading from custom directories

[13.12.1] - 2026-03-15

Added

Support for move-only operations that preserve exact bytes including binary files

Fixed

Fixed handling of file moves when no edits are specified, now correctly preserves binary content
Fixed validation to reject move operations where source and destination paths are identical

[13.12.0] - 2026-03-14

Added

Added per-rule TTSR interrupt mode override via interruptMode field in rule frontmatter to allow fine-grained control over when TTSR interrupts stream processing
Added task model role to allow configuring a dedicated model for subtask execution via modelRoles.task setting
Added moveCursorToMessageEnd and moveCursorToMessageStart prompt actions to navigate to the beginning and end of the entire message
Added support for provider-level compat configuration to apply OpenAI compatibility settings across all models from a provider
Added reasoningEffortMap configuration option to map reasoning effort levels to provider-specific values
Added support for supportsUsageInStreaming, requiresToolResultName, requiresAssistantAfterToolResult, requiresThinkingAsText, thinkingFormat, and supportsStrictMode OpenAI compatibility options
Added support for provider-configurable OpenAICompat.extraBody to inject request-body fields for custom gateway/proxy routing
Added close() method to SessionManager for properly closing persistent writers after flushing pending data
Added omp config init-xdg command to initialize XDG Base Directory structure on Linux
Added getHistoryDbPath(), getModelDbPath(), getMemoriesDir(), getTerminalSessionsDir() path helpers

Changed

Path resolution on Linux redirects to XDG locations when XDG_DATA_HOME / XDG_STATE_HOME / XDG_CACHE_HOME environment variables are set

Changed

Changed TTSR interrupt logic to respect per-rule interruptMode settings, falling back to global ttsr.interruptMode when rule-level override is not specified
Reorganized settings tabs from 12 tabs (display, agent, input, tools, config, services, bash, lsp, ttsr, status) to 8 focused tabs (appearance, model, interaction, context, editing, tools, tasks, providers) for improved discoverability
Consolidated status line settings into the Appearance tab instead of a separate Status tab
Reorganized sampling parameters (temperature, topP, topK, minP, presencePenalty, repetitionPenalty) into the Model tab
Moved edit tool settings (mode, fuzzyMatch, fuzzyThreshold, streamingAbort) to the Editing tab
Moved read tool settings (readLineNumbers, readHashLines, read.defaultLimit) to the Editing tab
Moved LSP settings (lsp.enabled, lsp.formatOnWrite, lsp.diagnosticsOnWrite, lsp.diagnosticsOnEdit) to the Editing tab
Moved bash interceptor settings to the Editing tab
Moved Python settings (python.toolMode, python.kernelMode, python.sharedGateway) to the Editing tab
Moved task delegation settings (task.isolation.*, task.eager, task.maxConcurrency, task.maxRecursionDepth) to the Tasks tab
Moved skill and command settings to the Tasks tab
Moved provider selection settings (providers.webSearch, providers.codeSearch, providers.image, etc.) to the Providers tab
Moved Exa settings to the Providers tab
Moved secret handling settings to the Providers tab
Moved speech-to-text settings to the Interaction tab
Moved context promotion, compaction, branch summary, memories, and TTSR settings to the Context tab
Updated tab icon symbols across unicode, nerd, and ASCII presets to match new tab structure
Changed default agent model from default to pi/task to enable independent model configuration for subtasks
Changed agent model resolution to support single-pattern inheritance fallback, allowing pi/task agents to inherit the active session model when the task role is unconfigured
Changed system prompt to use ISO 8601 date format (YYYY-MM-DD) instead of locale-specific formatting
Changed system prompt template to use {{date}} instead of {{dateTime}} for current date display
Changed tool download timeout from 15 seconds to 120 seconds to accommodate slower network conditions
Changed working directory paths in system prompt to use forward slashes for consistency across platforms
Modified bash executor to fall back to one-shot shell execution after a persistent session hard timeout, preventing subsequent commands from hanging

Removed

Removed bash executor hard timeout recovery test file (functionality already documented in existing entries)

Fixed

Fixed bash execution to fall back to one-shot shell runs after a persistent session hard timeout, preventing later commands from hanging until restart
Fixed timeout handling in RpcClient to properly clear timeouts and prevent resource leaks
Fixed AgentSession disposal to call SessionManager's close() method when available, ensuring proper cleanup of persistent writers
Removed redundant path.join() call wrapping getHistoryDbPath() in history-storage.ts

[13.11.1] - 2026-03-13

Added

Added llama.cpp as local provider
Added code_search tool supporting both Exa and grep.app providers for code snippet and documentation search
Added providers.codeSearch setting to configure code search provider (exa or grep)
Added grep.app integration for public code search with result ranking by context relevance

Changed

Updated compact diff preview to include line hashes for visibility and integrity verification of unchanged and added lines
Modified compact diff preview to track line number synchronization between old and new files when processing insertions and deletions
Simplified web search tools: removed web_search_deep, web_search_crawl, web_search_linkedin, and web_search_company tools
Removed exa.enableLinkedin and exa.enableCompany settings; LinkedIn and company research are no longer available
Refactored code search to use pluggable provider system instead of Exa-only implementation

Removed

Removed Exa LinkedIn search tool (exa_linkedin)
Removed Exa company research tool (exa_company)
Removed Exa deep search tool (exa_search_deep)
Removed Exa URL crawl tool (exa_crawl)

Fixed

Fixed line number parsing in compact diff preview to handle variable-width line number fields with leading whitespace

[13.11.0] - 2026-03-12

Added

Added Parallel as a web search provider with support for fast and research modes
Added Parallel extract API integration for URL content fetching and YouTube video extraction
Added providers.parallelFetch setting to enable/disable Parallel extract for URL fetching
Added /login parallel command support for Parallel API authentication
Added subcommands to /copy command: code (copy last code block), all (copy all code blocks), cmd (copy last bash/python command), and last (copy full message)
Added support for copying last executed bash or python command via /copy cmd subcommand
Added assignment field to task progress and result objects to track the raw per-task assignment text separately from the full templated task
Added details field to todo items for storing implementation specifics, file paths, and edge cases (shown only when task is active)
Added support for multi-line details in todo items with automatic indentation in interactive and reminder displays
Added todo.eager setting to automatically create a comprehensive todo list after the first user message
Added buildNamedToolChoice utility function to build provider-aware tool choice constraints for named tools
Support for comma/space-separated path lists in find, grep, ast_grep, and ast_edit tools (e.g., apps/,packages/,phases/ or apps/ packages/ phases/)
New resolveMultiSearchPath and resolveMultiFindPattern functions to handle multi-path search inputs with automatic common base path detection
Added display.showTokenUsage setting to show per-turn token usage (input, output, cache) on assistant messages

Changed

Updated HTML-to-text rendering to prefer Parallel extract when credentials are available, before falling back to jina, trafilatura, or lynx
Updated YouTube scraper to prefer Parallel extract when credentials are available, before falling back to yt-dlp
Updated web search provider priority order to include Parallel between Exa and Kagi
Updated hashline tool documentation with explicit guidance on replace operation semantics, clarifying that lines must not extend past end to avoid unintended line duplication
Improved diagnostic message formatting to group errors by file path with indented details for better readability
Modified eager todo prelude to use hidden custom message type instead of visible developer message, preventing duplicate prompt text in session history
Updated eager todo prompt to remove dynamic user request injection, simplifying the template and preventing request repetition in displayed messages
Modified eager todo enforcement to prepend the todo reminder to the first user turn instead of executing it as a separate synthetic turn, reducing unnecessary prompt calls
Updated task rendering to display assignment text instead of full task template when available, reducing noise in progress and result displays
Modified task section rendering to show trimmed assignment text without stripping context blocks, simplifying the display logic
Updated todo item display to show details field indented below active tasks in both interactive mode and todo reminder component
Modified tool choice resolution to support per-turn tool choice overrides via consumeNextToolChoiceOverride()
Updated tool documentation to clarify that path parameter accepts files, directories, glob patterns, or comma/space-separated path lists
Refactored path resolution logic in find, grep, ast_grep, and ast_edit tools to use unified multi-path handling

Fixed

Fixed hashline line normalization to trim trailing whitespace and strip carriage returns instead of removing all whitespace, preserving intentional spacing in code
Fixed noop detection in hashline replace operations to check array length equality before comparing lines, preventing false noop classification when single-line replacements expand to multiple lines
Fixed path resolution to accept bare directory names without trailing slashes in comma/space-separated path lists (e.g., apps packages phases)
Per-role modelRoles thinking selectors now propagate through commit/title helper model selection, legacy commit analysis, and agentic commit sessions while preserving default thinking inheritance when no role override is configured

[13.10.1] - 2026-03-10

Added

Exported submitInteractiveInput() function for programmatic submission of user input in interactive mode
Added proactive OAuth token refresh for MCP server connections with 5-minute expiry buffer
Added reactive 401/403 retry with automatic token refresh on HTTP MCP transports
Added refreshMCPOAuthToken() for standard OAuth 2.0 refresh_token grants
Persisted tokenUrl, clientId, and clientSecret in MCP auth config for cross-session token refresh

Fixed

Respected PI_CONFIG_DIR when discovering native user config paths for slash commands and related config directories (#349)

[13.10.0] - 2026-03-10

Fixed

Preserved text signature metadata (id and phase) when building OpenAI native history during session compaction

[13.9.16] - 2026-03-10

Breaking Changes

Web search tool no longer accepts provider parameter in tool calls; use internal provider resolution instead
Removed no_fallback option from search parameters

Added

Added before_provider_request extension event to intercept and modify provider request payloads before sending
Added emitBeforeProviderRequest() method to ExtensionRunner for chaining payload transformations across extensions
Added refreshInBackground() method to ModelRegistry for non-blocking model discovery
Added refreshProvider() method to refresh models for a specific provider on demand
Added getDiscoverableProviders() method to list all configured discoverable providers
Added getProviderDiscoveryState() method to inspect provider discovery status, cache age, and errors
Added provider discovery state tracking with status indicators (idle, ok, cached, unavailable, unauthenticated)
Added model caching with 24-hour TTL to preserve discovered models across sessions
Added provider-specific empty state messages in model selector showing cache age and discovery status
Added live provider refresh when switching provider tabs in model selector

Changed

Changed model discovery to load cached models immediately before attempting live refresh, improving startup performance
Changed model selector to refresh offline by default when reloading config, deferring live discovery to background
Changed model discovery timeout from 3000ms to 250ms for faster failure detection
Changed model discovery error handling to preserve cached models when live refresh fails
Changed refresh() strategy parameter to support 'offline' mode for config-only reloads
Changed main.ts to defer model refresh until needed (--list-models or background refresh)
Changed SDK session creation to use background refresh instead of blocking on model discovery
Removed provider parameter from web search tool schema; provider selection now handled internally
Removed no_fallback parameter from web search parameters; fallback behavior now automatic based on provider availability
Renamed SearchParams type to SearchToolParams for tool execution; introduced SearchQueryParams for CLI queries with optional provider selection

Fixed

Fixed model discovery to continue using cached models when provider is temporarily unavailable
Fixed unauthenticated provider discovery to preserve cached models instead of discarding them
Fixed model selector to show discovery status messages when provider has no models

[13.9.15] - 2026-03-10

Added

Added ensureLoadingAnimation() method to manage loading animation lifecycle and prevent duplicate spinners

Changed

Refactored loading animation initialization to use centralized ensureLoadingAnimation() method in event and input controllers
Updated showError() to properly clean up loading animation state when errors occur

[13.9.12] - 2026-03-09

Added

Added Tavily as a supported web search provider with TAVILY_API_KEY credential discovery and provider fallback support
Added #-triggered prompt action suggestions in the editor, with keybinding hints for line navigation and prompt copy actions
Added Tavily as a supported web search provider with TAVILY_API_KEY credential discovery and provider fallback support (#313)

Removed

Removed Kagi Universal Summarizer integration from fetch tool—HTML rendering now uses jina, trafilatura, and lynx only
Removed fetch.useKagiSummarizer setting
Removed Kagi summarization from YouTube video handling

Fixed

Canonicalized bash executor working directories before handing them to brush so pwd stays aligned with canonical Git worktree paths in symlinked workspaces

[13.9.10] - 2026-03-08

Added

Added env parameter to bash tool to pass environment variables safely without shell re-parsing, preventing quote and special character bugs with multiline or untrusted values
Added support for rendering partial env assignments in command preview while tool arguments are still streaming
Added env support to the bash tool so commands can reference safe shell variables without inline quoting bugs for multiline or quote-heavy values

Changed

Changed bash tool to display environment variable assignments in command preview when env parameter is used

[13.9.8] - 2026-03-08

Added

Added docs.rs scraper for extracting Rust crate documentation from rustdoc JSON, including support for modules, functions, structs, traits, enums, and other Rust items with caching

[13.9.7] - 2026-03-08

Added

Added skipPostPromptRecoveryWait option to handoff operations to defer recovery work until after handoff completion
Added deferred auto-compaction scheduling to allow threshold-triggered handoffs to complete while the original prompt is still unwinding

Changed

Extracted handoff document template to dedicated prompt file for improved maintainability and template variable support
Changed handoff prompt generation to use template rendering with support for custom focus instructions
Refactored internal prompt-in-flight tracking from boolean flag to counter to properly handle nested prompt operations
Moved llms.txt endpoint discovery to fallback strategy when rendered page content is low quality, prioritizing page-specific content over site-wide files
Enhanced llms.txt endpoint detection to scope candidates to the requested URL path, searching section-specific files before site-wide ones

[13.9.6] - 2026-03-08

Added

Added glob parameter to ast_grep and ast_edit tools for additional glob filtering relative to the path parameter
Added combineSearchGlobs utility function to merge glob patterns from path and glob parameters

Changed

Renamed patterns parameter to pat in ast_grep tool for consistency
Renamed selector parameter to sel in ast_grep and ast_edit tools for brevity
Updated tool documentation with expanded guidance on AST pattern syntax, metavariable usage, and contextual matching strategies
Updated grep tool to combine glob patterns from path and glob parameters instead of throwing an error when both are provided

[13.9.4] - 2026-03-07

Added

Automatic detection of Ollama model capabilities including reasoning/thinking support and vision input via the /api/show endpoint
Improved Kagi API error handling with extraction of detailed error messages from JSON and plain text responses

Changed

Updated Kagi provider description to clarify requirement for Kagi Search API beta access

[13.9.3] - 2026-03-07

Breaking Changes

Changed ThinkingLevel type to be imported from @oh-my-pi/pi-agent-core instead of @oh-my-pi/pi-ai
Changed thinking level representation from string literals to Effort enum values (e.g., Effort.High instead of "high")
Changed getThinkingLevel() return type to ThinkingLevel | undefined to support models without thinking support
Changed model reasoning property to thinking property with ThinkingConfig for explicit effort level configuration
Changed thinkingLevel in session context to be optional (ThinkingLevel | undefined) instead of always present

Added

Added thinking.ts module with getThinkingLevelMetadata() and resolveThinkingLevelForModel() utilities for thinking level handling
Added ThinkingConfig support to model definitions for specifying supported thinking effort levels per model
Added enrichModelThinking() function to apply thinking configuration to models during registry initialization
Added clampThinkingLevelForModel() function to constrain thinking levels to model-supported ranges
Added getSupportedEfforts() function to retrieve available thinking efforts for a model
Added Effort enum import from @oh-my-pi/pi-ai for type-safe thinking level representation
Added /fast slash command to toggle OpenAI service tier priority mode for faster response processing
Added serviceTier setting to control OpenAI processing priority (none, auto, default, flex, scale, priority)
Added compaction.remoteEnabled setting to control use of remote compaction endpoints
Added remote compaction support for OpenAI and OpenAI Codex models with encrypted reasoning preservation
Added fast mode indicator (⚡) to model segment in status line when priority service tier is active
Added context usage threshold levels (normal, warning, purple, error) with token-aware thresholds for better context awareness
Added isFastModeEnabled(), setFastMode(), and toggleFastMode() methods to AgentSession for fast mode control

Changed

Changed credential deletion to disable credentials with persisted cause instead of permanent deletion
Added disabledCause parameter to credential deletion methods to track reason for disabling
Changed thinking level parsing to use parseEffort() from local thinking module instead of parseThinkingLevel() from pi-ai
Changed model list display to show supported thinking efforts (e.g., "low,medium,high") instead of yes/no reasoning indicator
Changed footer and status line to check model.thinking instead of model.reasoning for thinking level display
Changed thinking selector to work with Effort type instead of ThinkingLevel for available levels
Changed model resolver to return undefined for thinking level instead of "off" when no thinking is specified
Changed compaction reasoning parameters to use Effort enum values instead of string literals
Changed RPC types to use Effort for cycling thinking levels and ThinkingLevel | undefined for session state
Changed theme thinking border color function to accept both ThinkingLevel and Effort types
Changed context usage coloring in footer and status line to use token-aware thresholds instead of fixed percentages
Changed compaction to preserve OpenAI remote compaction state and encrypted reasoning across sessions
Changed compaction to skip emitting kept messages when using OpenAI remote compaction with preserved history
Changed session context to include serviceTier field for tracking active service tier across session branches
Changed compact() function to accept remoteInstructions option for custom remote compaction prompts
Changed model registry to apply hardcoded policies (gpt-5.4 context window) consistently across all model loading paths

Fixed

Fixed OpenAI remote compaction to correctly append incremental responses instead of replacing entire history
Fixed thinking level display logic in main.ts to correctly check for undefined instead of "off"
Fixed model registry to preserve explicit thinking configuration on runtime-registered models
Fixed usage limit reset time calculation to use absolute resetsAt timestamps instead of deprecated resetInMs field
Fixed compaction summary message creation to no longer be automatically added to chat during compaction (now handled by session manager)
Fixed Kagi web search errors to surface the provider's beta-access message and clarified that Kagi search requires Search API beta access

[13.9.2] - 2026-03-05

Added

Support for Python code execution messages with output display and error handling
Support for mode change entries in session exports
Support for TTSR injection and session initialization entries in tree filtering

Changed

Updated label lookup to use targetId field instead of parentId for label references
Changed model change entry display to use model field instead of separate provider and modelId fields
Simplified model change rendering by removing OpenAI Codex bridge prompt display
Updated searchable text extraction to include Python code from pythonExecution messages

Removed

Removed codexInjectionInfo from session data destructuring
Removed OpenAI Codex-specific bridge prompt UI from model change entries

Fixed

Auto-corrected off-by-one range start errors in hashline edits that would duplicate preceding lines

[13.9.0] - 2026-03-05

Added

Added read.defaultLimit setting to configure default number of lines returned by read tool when no limit is specified (default: 300 lines)
Added preset options for read default limit (200, 300, 500, 1000, 5000 lines) in settings UI

Changed

Updated read tool prompt to distinguish between default limit and maximum limit per call
Moved ThinkingLevel type from @oh-my-pi/pi-agent-core to @oh-my-pi/pi-ai for centralized thinking level definitions
Replaced local thinking level validation with parseThinkingLevel() and ALL_THINKING_LEVELS from @oh-my-pi/pi-ai
Updated thinking level option providers to use THINKING_MODE_DESCRIPTIONS from @oh-my-pi/pi-ai for consistent descriptions
Renamed RoleThinkingMode type to ThinkingMode and changed default value from 'default' to 'inherit' for clarity
Replaced formatThinkingEffortLabel() utility with formatThinking() from @oh-my-pi/pi-ai
Renamed extractExplicitThinkingLevel() to extractExplicitThinkingSelector() in model resolver
Updated thinking level clamping to use getAvailableThinkingLevel() from @oh-my-pi/pi-ai

Removed

Removed thinking-effort-label.ts utility file (functionality moved to @oh-my-pi/pi-ai)
Removed local VALID_THINKING_LEVELS constant definitions across multiple files
Removed isValidThinkingLevel() function (replaced by parseThinkingLevel() from @oh-my-pi/pi-ai)
Removed parseThinkingLevel() helper from discovery module (now uses centralized version from @oh-my-pi/pi-ai)

Fixed

Fixed provider session state not being cleared when branching or navigating tree history, preventing resource leaks with codex provider sessions

[13.8.0] - 2026-03-04

Added

Added buildCompactHashlineDiffPreview() function to generate compact diff previews for model-visible tool responses, collapsing long unchanged runs and consecutive additions/removals to show edit shape without full file content
Added project-level discovery for .agent/ and .agents/ directories, walking up from cwd to repo root (matching behavior of other providers like .omp, .claude, .codex). Applies to skills, rules, prompts, commands, context files (AGENTS.md), and system prompts (SYSTEM.md)

Changed

Changed edit tool response to include diff summary with line counts (+added -removed) and a compact diff preview instead of warnings-only output
Limited auto context promotion to models with explicit contextPromotionTarget; models without a configured target now compact on overflow instead of switching to arbitrary larger models (#282)

Fixed

Fixed :thinking suffix in modelRoles config values silently breaking model resolution (e.g., slow: anthropic/claude-opus-4-6:high) and being stripped on Ctrl+P role cycling

[13.7.6] - 2026-03-04

Added

Exported dedupeParseErrors utility function to deduplicate parse error messages while preserving order

Fixed

Reduced duplicate parse error messages when multiple patterns fail on the same file
Normalized parse error output in ast-grep to remove pattern-specific prefixes and show only file-level errors

[13.7.4] - 2026-03-04

Added

Added fetch.useKagiSummarizer setting to toggle Kagi Universal Summarizer usage in the fetch tool.

Fixed

Fixed incorrect message history reference in session title generation that could cause missing or stale titles on first message
Added startup check requiring Bun 1.3.7+ for JSONL session parsing (Bun.JSONL.parseChunk) and clear upgrade guidance so /resume and --resume do not silently report missing sessions on older Bun runtimes

[13.7.3] - 2026-03-04

Added

Added Kagi Universal Summarizer integration for URL summarization, now prioritized before Jina and other methods
Added Kagi Universal Summarizer support for YouTube video summaries when credentials are available
Exported searchWithKagi and summarizeUrlWithKagi functions from new web/kagi module for direct API access
Added KagiApiError exception class for Kagi API-specific error handling

Changed

Updated hashline prompt documentation with clearer operation syntax and improved examples showing full edit structure with path and edits array
Refactored href Handlebars helper to return JSON-quoted strings for safer embedding in JSON blocks within prompts
Improved hashlineParseText to correctly preserve blank lines and trailing empty strings in array input while stripping trailing newlines from string input
Optimized duplicate line detection in range replacements to use trimmed comparison, reducing false positives from whitespace differences
Refactored Kagi search provider to use shared Kagi API utilities from web/kagi module
Changed HTML-to-text rendering priority order to try Kagi first, then Jina, Trafilatura, and Lynx

Fixed

Fixed isEscapedTabAutocorrectEnabled environment variable parsing to use switch statement for clearer logic and consistent default behavior

[13.7.2] - 2026-03-04

Added

Added support for direct OAuth provider login via /login <provider> command (e.g., /login kagi)
Added optional providerId parameter to showOAuthSelector() to enable direct provider selection without UI selector

Changed

Simplified web search result formatting to omit empty sections and metadata when not present

[13.7.0] - 2026-03-03

Fixed

Fixed ask timeout handling to auto-select the recommended option instead of aborting the turn, while preserving explicit user-cancel abort behavior (#266)

[13.6.2] - 2026-03-03

Fixed

Fixed LM Studio API key retrieval to use configured provider name instead of hardcoded 'lm-studio'
Fixed resource content handling to properly check for empty text values (null/undefined)
Fixed resource refresh tracking to prevent stale promise reuse when server connection changes
Fixed update target resolution to properly handle cases where binary path cannot be resolved

[13.6.1] - 2026-03-03

Fixed

Fixed omp update silently succeeding without actually updating the binary when the update channel (bun global vs compiled binary) doesn't match the installation method (#247)
Added post-update verification that checks the resolved omp binary reports the expected version, with actionable warnings on mismatch
omp update now detects when the omp in PATH is not managed by bun and falls back to binary replacement instead of updating the wrong location

[13.6.0] - 2026-03-03

Added

Added mcp:// internal URL protocol for reading MCP server resources directly via the read tool (e.g., read(path="mcp://resource-uri"))
Added LM Studio integration to the model registry and discovery flow.
Added support for authenticating with LM Studio using the /login lm-studio command.
Added fuse-projfs task isolation mode for Windows ProjFS-backed overlays.
Added /mcp registry search <keyword> integration with Smithery, including interactive result selection, editable server naming before deploy, Smithery configSchema prompts, and immediate runtime reload so selected MCP tools are available without restarting
Added OAuth failure fallback in /mcp registry search deploy flow to prompt for manual bearer tokens and validate them before saving configuration
Added Smithery auth support for /mcp registry search with cached API key login (/mcp registry login, /mcp registry logout) and automatic login prompt/retry on auth or rate-limit responses

Changed

Updated MCP resource update notifications to recommend using read(path="mcp://<uri>") instead of the deprecated read_resource tool
Updated Anthropic Foundry environment variable documentation and CLI help text to the canonical names: CLAUDE_CODE_USE_FOUNDRY, CLAUDE_CODE_CLIENT_CERT, and CLAUDE_CODE_CLIENT_KEY
Documented Foundry-specific Anthropic runtime configuration (FOUNDRY_BASE_URL, ANTHROPIC_FOUNDRY_API_KEY, ANTHROPIC_CUSTOM_HEADERS, NODE_EXTRA_CA_CERTS) in environment variable reference docs
fuse-overlay task isolation now targets fuse-overlayfs on Unix hosts only; on Windows it falls back to worktree with a <system-notification> suggesting fuse-projfs.
fuse-projfs now performs Windows ProjFS preflight checks and falls back to worktree when host or repository prerequisites are unavailable.
Cross-repo patch capture now uses the platform null device (NUL on Windows, /dev/null elsewhere) for git diff --no-index.

Removed

Removed read_resource tool; MCP resource reading is now integrated into the read tool via mcp:// URLs

Fixed

Fixed MCP resource subscription handling to prevent unsubscribing when notifications are re-enabled after being disabled
Fixed LM Studio base URL validation to preserve invalid configured URLs instead of silently falling back to localhost
Fixed URI template matching to correctly handle expressions that expand to empty strings

[13.5.6] - 2026-03-01

Changed

Updated OAuth client name from 'oh-my-pi MCP' to 'Codex' for dynamic client registration

Fixed

Fixed exit_plan_mode handler to abort active agent turn before opening plan approval selector, ensuring proper session cleanup

[13.5.5] - 2026-03-01

Added

Added Kagi web search provider (Search API v0) with related searches support and automatic KAGI_API_KEY detection

[13.5.4] - 2026-03-01

Added

Added authServerUrl field to AuthDetectionResult to capture OAuth server metadata from Mcp-Auth-Server headers
Added extractMcpAuthServerUrl() function to parse and validate Mcp-Auth-Server URLs from error messages
Added support for /.well-known/oauth-protected-resource discovery endpoint to resolve authorization servers
Added recursive auth server discovery to follow authorization_servers references when discovering OAuth endpoints
Added omp agents unpack CLI subcommand to export bundled subagent definitions to ~/.omp/agent/agents by default, with --project support for ./.omp/agents

Changed

Enhanced discoverOAuthEndpoints() to accept optional authServerUrl parameter and query both auth server and resource server for OAuth metadata
Improved OAuth metadata extraction to handle additional field name variations (clientId, default_client_id, public_client_id)
Refactored OAuth endpoint discovery logic into reusable findEndpoints() helper for consistent metadata parsing across multiple sources
Task subagents now strip inherited AGENTS.md context files and the task tool prompt no longer warns against repeating AGENTS guidance, aligning subagent context with explicit task inputs (#233)

Fixed

Fixed MCP OAuth discovery to honor Mcp-Auth-Server metadata and resolve authorization endpoints from the declared auth server, restoring Figma MCP login URLs with client_id (#235)

[13.5.3] - 2026-03-01

Added

Auto-include ast_grep and ast_edit tools when their text-based counterparts (grep, edit) are requested and the AST tools are enabled
Enforced tool decision in plan mode—agent now requires calling either ask or exit_plan_mode when a turn ends without a required tool call
Auto-correction of escaped tab indentation in edits (enabled by default, controllable via PI_HASHLINE_AUTOCORRECT_ESCAPED_TABS environment variable)
Warning when suspicious Unicode escape placeholder \uDDDD is detected in edit content

Changed

Updated bash tool description to conditionally show ast_grep and ast_edit guidance based on tool availability in the session
Replaced timeout-based cancellation with AbortSignal-based cancellation in the ask tool for more reliable user interaction handling
Updated ask tool to distinguish between user-initiated cancellation and timeout-driven auto-selection, with only user cancellation aborting the turn
Updated hashline documentation to clarify that \t in JSON represents a real tab character, not a literal backslash-t sequence

Fixed

Fixed race condition in dialog overlay handling where multiple concurrent resolutions could occur
Cancelling the ask tool now aborts the current turn instead of returning a normal cancelled selection, while timeout-driven auto-cancel still returns without aborting

[13.5.2] - 2026-03-01

Added

Added checkpoint tool to create context checkpoints before exploratory work, allowing you to investigate with many intermediate tool calls and minimize context cost afterward
Added rewind tool to end an active checkpoint and replace intermediate exploration messages with a concise investigation report
Added checkpoint.enabled setting to control availability of the checkpoint and rewind tools
Added render_mermaid tool to convert Mermaid graph source into ASCII diagram output
Added renderMermaid.enabled setting to control availability of the render_mermaid tool

Changed

Changed Mermaid rendering from PNG images to ASCII diagrams in theme rendering
Changed prerenderMermaid() function to synchronously render ASCII instead of asynchronously rendering PNG

[13.5.0] - 2026-03-01

Added

Added hlinejsonref Handlebars helper for embedding hashline references inside JSON blocks in prompts
Added librarian agent for researching external libraries and APIs by reading source code
Added oracle agent for deep reasoning on debugging, architecture decisions, and technical advice
Added dependencies and risks output fields to explore agent for better context handoff
Added support for lsp, fetch, web_search, and ast_grep tools to explore, plan, and reviewer agents

Changed

Enhanced hashline tool documentation with explicit prohibition on formatting-only edits
Added mandatory rule requiring indentation in lines to match surrounding context exactly from read output
Changed explore agent output field query to summary with expanded description for findings and conclusions

[13.4.1] - 2026-03-01

Fixed

Pending resolve reminders now trigger as soon as a preview action is queued, before the next assistant turn, with regression coverage in agent-session-resolve-reminder tests

[13.4.0] - 2026-03-01

Breaking Changes

ast_grep parameter pattern (string) replaced by patterns (string[])
ast_edit parameters pattern + rewrite replaced by ops: Array<{ pat: string; out: string }>

Added

Added resolve tool to apply or discard pending preview actions with required reasoning
AST edit now registers pending actions after preview, allowing explicit apply/discard workflow via resolve tool
Custom tools can register pending actions via pushPendingAction(action) in CustomToolAPI, enabling the resolve workflow for custom preview-apply flows
deferrable?: boolean field added to AgentTool, CustomTool, and ToolDefinition interfaces; tools that set it signal they may stage pending actions
HIDDEN_TOOLS and ResolveTool exported from @oh-my-pi/pi-coding-agent SDK for manual tool composition
PendingActionStore now uses a LIFO stack (push/peek/pop); multiple deferrable tools can stage actions that resolve in reverse order of registration
Added gemini, codex, and synthetic as supported values for the providers.webSearch setting
ast_grep tool now accepts a patterns array (replaces single pattern); multiple patterns run in one native pass and results are merged before offset/limit
ast_edit tool now accepts an ops array of { pat, out } entries (replaces pattern + rewrite); duplicate patterns are rejected upfront
AST find output now uses >> prefix on match-start lines and pads line numbers; directory-tree grouping with # dir / ## └─ file headers for directory-scoped searches
AST replace output now renders diff-style (-before / +after) change previews grouped by directory
Both AST tools now report scopePath, files, and per-file match/replacement counts in tool details
Task item id max length raised from 32 to 48 characters
Anthropic web search provider now uses buildAnthropicSearchHeaders (dedicated search header builder separate from inference headers)
Gemini web search provider: endpoint fallback (daily → sandbox) with retry on 429/5xx
Gemini web search now injects Antigravity system instruction and aligned request metadata (requestType, userAgent, requestId) for Antigravity credentials
buildGeminiRequestTools() helper for composable Gemini tool configuration (googleSearch, codeExecution, urlContext)
Web search schema exposes max_tokens, temperature, and num_search_results as tool parameters
Web search provider fallback: when an explicit provider is unavailable, resolves the auto chain instead of returning empty results

Changed

Simplified resolve tool output rendering to use inline highlighted format instead of boxed layout
Updated resolve tool to parse source tool name from label using colon separator for cleaner display
resolve tool is now conditionally injected: included only when at least one active tool has deferrable: true (previously always included)
discoverAndLoadCustomTools / loadCustomTools accept an optional pendingActionStore parameter to wire pushPendingAction for custom tools
AST edit tool no longer accepts preview parameter; all AST edit calls now return previews by default
AST edit workflow changed: preview is always shown, then use resolve tool to apply or discard changes
Agent now suggests calling resolve tool after AST edit preview with system reminder
ast_grep: include_meta parameter removed; metavariable captures are now always included in output
ast_edit: dry_run renamed to preview; max_files removed from schema and capped globally via $PI_MAX_AST_FILES (default 1000); max_replacements renamed to limit
ast_grep and ast_edit: parse errors in tool output are now capped at PARSE_ERRORS_LIMIT (20); excess errors are summarised as N / total parse issues rather than flooding the context
Updated ast_grep and ast_edit tool prompt examples to use concise, idiomatic patterns

Removed

Removed normativeRewrite setting that rewrote tool call arguments to normalized format in session history
Removed buildNormativeUpdateInput() helper and normative patch transformation logic

Fixed

ast_edit no longer rejects empty out values; an empty string now deletes matched nodes
ast_edit no longer trims pat and out values, preserving intentional whitespace
gemini_image tool: corrected responseModalities values from 'Image'/'Text' to uppercase 'IMAGE'/'TEXT' matching the API enum

[13.3.14] - 2026-02-28

Added

Expanded AST tool language support from 7 to all 25 ast-grep tree-sitter languages (Bash, C, C++, C#, CSS, Elixir, Go, Haskell, HCL, HTML, Java, JavaScript, JSON, Kotlin, Lua, Nix, PHP, Python, Ruby, Rust, Scala, Solidity, Swift, TSX, TypeScript, YAML)
AST find now emits all lines of multiline matches with hashline tags (LINE#HASH:content) consistent with read/grep output
Added AST pattern syntax reference (metavariables, wildcards, variadics) to system prompt
Added examples and scoping guidance to ast-grep and ast-edit tool prompts
Added provider-schema-compatibility.test.ts: integration test that instantiates every builtin and hidden tool, runs their parameter schemas through adaptSchemaForStrict, sanitizeSchemaForGoogle, and prepareSchemaForCCA, and asserts zero violations against each provider's compatibility rules

Fixed

Non-code files (.md, .zip, .bin, .gitignore, etc.) are now silently skipped by AST tools instead of producing misleading parse errors
Fixed grep path wildcard handling so file patterns passed via path (for example schema-review-*.test.ts) are resolved as glob filters instead of failing path existence checks

[13.3.11] - 2026-02-28

Fixed

Restored inline rendering for read tool image results in assistant transcript components, including streaming and rebuilt session history paths.
Fixed shell-escaped read paths (for example, pasted \ -escaped screenshot filenames) by resolving unescaped fallback candidates before macOS filename normalization variants.

[13.3.8] - 2026-02-28

Added

Added ast_grep tool for structural code search using AST matching via ast-grep, enabling syntax-aware pattern discovery across codebases
Added ast_edit tool for structural AST-aware rewrites via ast-grep, enabling safe syntax-level codemods without text-based fragility
Added astGrep.enabled and astEdit.enabled settings to control availability of AST tools
Added system prompt guidance to prefer AST tools over bash text manipulation (grep/sed/awk/perl) for syntax-aware operations
Extracted prompt formatting logic into reusable formatPromptContent() utility with configurable render phases and formatting options
Added type_definition action to navigate to symbol type definitions with source context
Added implementation action to find concrete implementations of symbols with source context
Added code_actions action to list and apply language server code fixes, refactors, and import suggestions
Added symbol parameter to automatically resolve column position by searching for substring on target line
Added occurrence parameter to disambiguate repeated symbol matches on the same line
Added source code context display (3 lines) for definition, type definition, and implementation results
Added context display for first 50 references with remaining references shown location-only to balance detail and performance
Added support for glob patterns in file parameter for diagnostics action (e.g., src/**/*.ts)
Added waitForIdle() method to ensure prompt completion waits for all deferred recovery work (TTSR continuations, context promotions, compaction retries) to fully settle
Added getLastAssistantMessage() method to retrieve the most recent assistant message from session state without manual array indexing
Implemented TTSR resume gate to ensure prompt() blocks until TTSR interrupt continuations complete, preventing race conditions between TTSR injections and subsequent prompts
Added tools.maxTimeout setting to enforce a global timeout ceiling across all tool calls

Changed

Replaced globSync from glob package with native Bun.Glob API for glob pattern matching
Replaced fileTypeFromBuffer from file-type package with inline MIME type detection for JPEG, PNG, GIF, and WebP formats
Reduced MIME type sniffing buffer size from 4100 bytes to 12 bytes for improved performance
Changed mermaid cache key type from string to bigint for more efficient hashing
Replaced smol-toml dependency with native Bun.TOML.parse() for TOML parsing, reducing external dependencies
Replaced node-html-parser dependency with linkedom for HTML parsing, improving performance and reducing bundle size
Updated HTML parsing API calls from node-html-parser to linkedom across all web scrapers (arXiv, IACR, Go pkg, Read the Docs, Twitter, Wikipedia)
Changed element text extraction from .text property to .textContent property for compatibility with linkedom DOM API
Optimized document link extraction to use regex-based parsing with deduplication and a 20-link limit instead of full DOM traversal
Unified path parameter in ast_grep and ast_edit tools to accept files, directories, or glob patterns directly, eliminating the separate glob parameter
Removed strictness parameter from ast_grep and ast_edit tools
Removed fail_on_parse_error parameter from ast_edit tool (now always false)
Updated ast_grep and ast_edit prompt guidance to clarify that path accepts glob patterns and no longer requires separate glob specification
Refactored prompt template rendering to use unified formatPromptContent() function with phase-aware formatting (pre-render vs post-render)
Updated format-prompts.ts script to use centralized prompt formatting utility instead of inline implementation
Replaced column parameter with symbol parameter for more intuitive position specification
Removed files parameter; use glob patterns in file parameter instead
Removed end_line and end_character parameters; range operations now use single position
Changed include_declaration parameter to always be true for references (removed from API)
Updated LSP client capabilities to advertise support for typeDefinition and implementation requests
Improved definition results to include source context alongside location information
Refactored deferred continuation scheduling to use centralized post-prompt task tracking instead of raw setTimeout() calls, improving reliability of concurrent recovery operations
Updated subagent executor to explicitly await waitForIdle() after each prompt and reminder, ensuring terminal assistant state is determined only after all background work completes
Replaced #waitForRetry() with #waitForPostPromptRecovery() to handle both retry and TTSR resume gates, ensuring prompt completion waits for all post-prompt recovery operations
Introduced structured post-prompt recovery task tracking in AgentSession and added explicit session completion APIs (waitForIdle(), getLastAssistantMessage()) for callers that need deterministic turn finalization
Updated intent field parameter name from agent__intent to _i for cleaner tool call contracts
Refined intent parameter guidance to require concise 2-6 word sentences in present participle form
Centralized per-tool timeout constants and clamping into tool-timeouts.ts

Removed

Removed file-type dependency, reducing external dependencies
Removed glob dependency in favor of native Bun.Glob API
Removed ignore dependency and ignore file handling utilities
Removed marked dependency
Removed zod dependency
Removed ms and @types/ms dev dependencies
Removed rootDir and ignoreMatcher parameters from loadFilesFromDir() (kept for API compatibility)
Removed smol-toml dependency from package.json
Removed node-html-parser dependency from package.json
Removed files array parameter for batch file operations
Removed column, end_line, and end_character parameters in favor of symbol-based positioning
Removed include_declaration parameter from references action

Fixed

Fixed TTSR violations during subagent execution aborting the entire subagent run; #waitForPostPromptRecovery() now also awaits agent idle after TTSR/retry gates resolve, preventing prompt() from returning while a fire-and-forget agent.continue() is still streaming
Fixed deferred TTSR/context-promotion continuations still racing prompt() completion by tracking compaction checks and deferred agent.continue() tasks under a shared post-prompt recovery orchestrator
Fixed subagent reminder/finalization sequencing to await session-level idle recovery between prompts before determining terminal assistant stop state
Fixed code_actions apply mode to execute command-based actions via workspace/executeCommand
Fixed diagnostics glob detection to recognize bracket character class patterns (e.g., src/[ab].ts)
Fixed LSP render metadata sanitization for symbol values to prevent tab/newline layout breakage
Fixed LSP diagnostics glob requests that appeared stuck by capping glob expansion and shortening per-file diagnostic waits in batch mode
Fixed workspace symbol search to query all configured LSP servers and filter out non-matching results
Fixed references/rename/hover symbol targeting to error when symbol is missing on the line or occurrence is out of bounds
Fixed reload without a file to reload all active configured language servers instead of only the first server
Fixed todo_write task normalization to auto-activate the first remaining task and include explicit remaining-items output in tool results, removing the need for an immediate follow-up start update

[13.3.7] - 2026-02-27

Breaking Changes

Removed preloadedSkills option from CreateAgentSessionOptions; skills are no longer inlined into system prompts
Removed skills field from Task schema; subagents now always inherit the session skill set instead of per-task skill selection
Removed Task tool per-task tasks[].skills support; subagents now always inherit the session skill set
Removed preloadedSkills system prompt plumbing and template sections; skills are no longer inlined as a separate preloaded block

Changed

Refactored schema reference resolution to inline all $ref definitions instead of preserving them at the root level, eliminating unresolved references in tool parameters
Added lenientArgValidation flag to SubmitResultTool to allow the agent loop to bypass strict argument validation errors
Modified schema validation to allow non-conforming output on second validation failure, enabling recovery from strict schema constraints after initial rejection
Updated JTD-to-TypeScript conversion to gracefully fall back to 'unknown' type when conversion fails, preventing template rendering errors
Changed JTD-to-JSON Schema conversion to normalize nested JTD fragments within JSON Schema nodes, enabling mixed schema definitions
Changed output schema validation to gracefully fall back to unconstrained object when schema is invalid, instead of rejecting submissions
Changed schema sanitization to remove strict-mode incompatible constraints (minLength, pattern, etc.) from tool parameters while preserving them for runtime validation
Simplified task execution to always pass available session skills to subagents instead of resolving per-task skill lists
Added KILO_API_KEY to CLI environment variable help text for Kilo Gateway provider setup (#193)

Removed

Removed preloaded skills section from system prompt templates; skills are now referenced only as available resources

Fixed

Fixed schema compilation validation by adding explicit AJV compilation check to catch unresolved $ref references and other schema errors before tool execution
Fixed handling of circular and deeply nested output schemas to prevent stack overflow and enable successful result submission with fallback unconstrained schema
Fixed processing of non-object output schemas (arrays, primitives, booleans) to accept valid result submissions without blocking
Fixed handling of mixed JTD and JSON Schema output definitions to properly convert all nested JTD elements (e.g., elements → items, int32 → integer)
Fixed strict schema generation for output schemas with only required fields, enabling proper Claude API compatibility
Fixed handling of union type schemas (e.g., object|null) to normalize them into strict-mode compatible variants

[13.3.6] - 2026-02-26

Breaking Changes

Changed submit_result tool parameter structure from top-level data or error fields to nested result object containing either result.data or result.error

[13.3.5] - 2026-02-26

Added

Added support for setting array and record configuration values using JSON syntax

Changed

Increased default async max jobs limit from 15 to 100 for improved concurrent task handling

Fixed

Improved config display formatting to properly render arrays and objects as JSON instead of [object Object]
Enhanced type display in config list output to show correct type indicators for number, array, and record settings

[13.3.3] - 2026-02-26

Added

Support for move parameter in computeHashlineDiff to enable file move operations alongside content edits

Changed

Modified no-op detection logic to allow move-only operations when file content remains unchanged

[13.3.1] - 2026-02-26

Added

Added topP setting to control nucleus sampling cutoff for model output diversity
Added topK setting to sample from top-K tokens for controlled generation
Added minP setting to enforce minimum probability threshold for token selection
Added presencePenalty setting to penalize introduction of already-present tokens
Added repetitionPenalty setting to penalize repeated tokens in model output

Fixed

Fixed skill discovery to continue loading project skills when user skills directory is missing

[13.3.0] - 2026-02-26

Breaking Changes

Renamed task.isolation.enabled (boolean) setting to task.isolation.mode (enum: none, worktree, fuse-overlay). Existing true/false values are auto-migrated to worktree/none.

Added

Added PERPLEXITY_COOKIES env var for Perplexity web search via session cookies extracted from desktop app
Added fuse-overlay isolation mode for subagents using fuse-overlayfs (copy-on-write overlay, no baseline patch apply needed)
Added task.isolation.merge setting (patch or branch) to control how isolated task changes are integrated back. branch mode commits each task to a temp branch and cherry-picks for clean commit history
Added task.isolation.commits setting (generic or ai) for commit messages on isolated task branches and nested repos. ai mode uses a smol model to generate conventional commit messages from diffs
Nested non-submodule git repos are now discovered and handled during task isolation (changes captured and applied independently from parent repo)
Added task.eager setting to encourage the agent to delegate work to subagents by default
Added manual OAuth login flow that lets users paste redirect URLs with /login for callback-server providers and prevents overlapping logins

Fixed

Fixed nested repo changes being lost when tasks commit inside the isolation (baseline state is now committed before task runs, so delta correctly excludes it)
Fixed nested repo patches conflicting when multiple tasks contribute to the same repo (baseline untracked files no longer leak into patches)
Nested repo changes are now committed after patch application (previously left as untracked files)
Failed tasks no longer create stale branches or capture garbage patches (gated on exit code)
Merge failures (e.g. conflicting patches) are now non-fatal — agent output is preserved with merge failed status instead of failed
Stale branches are cleaned up when commitToBranch fails
Commit message generator filters lock files from diffs before AI summarization

[13.2.1] - 2026-02-24

Fixed

Fixed changelog tools to enforce category-specific arrays and reuse the shared category list for generation
Non-interactive environment variables (pager, editor, prompt suppression) were not applied to non-PTY bash execution, causing commands to potentially block on pagers or prompts

Changed

Extracted non-interactive environment config from bash-interactive.ts into shared non-interactive-env.ts module, applied consistently to all bash execution paths

[13.2.0] - 2026-02-23

Breaking Changes

Made description field required in CustomTool interface

Changed

Reorganized imports from @oh-my-pi/pi-utils/dirs to consolidate with main @oh-my-pi/pi-utils exports for cleaner dependency management
Renamed loadSkillsFromDir to scanSkillsFromDir with updated interface for improved clarity on skill discovery behavior
Moved tryParseJson utility from local scrapers module to @oh-my-pi/pi-utils for centralized JSON parsing
Simplified patch module exports by consolidating type re-exports with export * from './types'
Removed emitCustomToolSessionEvent method from AgentSession for streamlined session lifecycle management
Changed skill discovery from recursive to non-recursive (one level deep only) for improved performance and clarity
Simplified skill loading logic by removing recursive directory traversal and consolidating ignore rule handling

Removed

Removed parseJSON helper function from discovery module (replaced by tryParseJson from pi-utils)
Removed backwards compatibility comment from AskToolDetails.question field
Removed unused SSH resource cleanup functions closeAllConnections and unmountAll from session imports

[13.1.2] - 2026-02-23

Breaking Changes

Removed timeout parameter from await tool—tool now waits indefinitely until jobs complete or the call is aborted
Renamed job_ids parameter to jobs in await tool schema
Removed timedOut field from await tool result details

Changed

Resolved docs index generation paths using path.resolve relative to the script directory

[13.1.1] - 2026-02-23

Fixed

Fixed bash internal URL expansion to resolve local:// targets to concrete filesystem paths, including newly created destination files for commands like mv src.json local://dest.json
Fixed bash local URL resolution to create missing parent directories under the session local root before command execution, preventing mv destination failures for new paths

[13.1.0] - 2026-02-23

Breaking Changes

Renamed file parameter to path in replace, patch, and hashline edit operations

Added

Added clarification in hashline edit documentation that the end tag must include closing braces/brackets when replacing blocks to prevent syntax errors

Changed

Restructured task tool documentation for clarity, moving parameter definitions into a dedicated section and consolidating guidance on context, assignments, and parallelization
Reformatted system prompt template to use markdown headings instead of XML tags for skills, preloaded skills, and rules sections
Renamed deviceScaleFactor parameter to device_scale_factor in browser viewport configuration for consistency with snake_case naming convention
Moved intent field documentation from per-tool JSON schema descriptions into a single system prompt block, reducing token overhead proportional to tool count

[13.0.1] - 2026-02-22

Changed

Simplified hashline edit schema to use unified first/last anchor fields instead of operation-specific field names (tag, before, after)
Improved resilience of anchor resolution to degrade gracefully when anchors are missing or invalid, allowing edits to proceed with available anchors
Updated hashline tool documentation to reflect new unified anchor syntax across all operations (replace, append, prepend, insert)

[13.0.0] - 2026-02-22

Added

Added getTodoPhases() and setTodoPhases() methods to ToolSession API for managing todo state programmatically
Added getLatestTodoPhasesFromEntries() export to retrieve todo phases from session history
Added local:// protocol for session-scoped scratch space to store large intermediate artifacts, subagent handoffs, and reusable planning artifacts
Added title parameter to exit_plan_mode tool to specify the final plan artifact name when approving a plan
Added LocalProtocolHandler for resolving local:// URLs to session-scoped file storage
Added renameApprovedPlanFile function to finalize approved plans with user-specified titles

Changed

Changed todo state management from file-based (todos.json) to in-memory session cache for improved performance and consistency
Changed todo phases to sync from session branch history when branching or rewriting entries
Changed TodoWriteTool to update session cache instead of writing to disk, with automatic persistence through session entries
Changed XML tag from <swarm-context> to <context> in subagent prompts and task rendering
Changed system reminder XML tags from underscore to kebab-case format (<system-reminder>)
Changed plan storage from plan:// protocol to local://PLAN.md for draft plans and local://<title>.md for finalized approved plans
Changed plan mode to use session artifacts directory for plan storage instead of separate plans directory
Updated system prompt to document local:// protocol and internal URL expansion behavior
Updated exit_plan_mode tool documentation to require title parameter and explain plan finalization workflow
Updated write tool documentation to recommend local:// for large temporary artifacts and subagent handoffs
Updated task tool documentation to recommend using local:// for large intermediate outputs in subagent context
Replaced docs:// protocol with pi:// for accessing embedded documentation files
Renamed DocsProtocolHandler to PiProtocolHandler for internal documentation URL resolution
Removed artifactsDir parameter from Python executor options; artifact storage now uses artifactPath only
Renamed prompt file from read_path.md to read-path.md for consistency
Updated system prompt XML tags to use kebab-case (e.g., system-reminder, system-interrupt) for consistency
Refactored bash tool to use NO_PAGER_ENV constant for environment variable management
Updated internal URL expansion to support optional noEscape parameter for unescaped path resolution

Removed

Removed plan:// protocol handler and related plan directory resolution logic
Removed PlanProtocolHandler and resolvePlanUrlToPath exports from internal URLs module

Fixed

Fixed todo reminder XML tags from underscore to kebab-case format (system-reminder)

[12.19.3] - 2026-02-22

Added

Added pty parameter to bash tool to enable PTY mode for commands requiring a real terminal (e.g., sudo, ssh, top, less)

Changed

Changed bash tool to use per-command PTY control instead of global virtual terminal setting

Removed

Removed bash.virtualTerminal setting; use the pty parameter on individual bash commands instead

[12.19.1] - 2026-02-22

Removed

Removed replaceText edit operation from hashline mode (substring-based text replacement)
Removed autocorrect heuristics that attempted to detect and fix line merges and formatting rewrites in hashline edits

[12.19.0] - 2026-02-22

Added

Added poll_jobs tool to block until background jobs complete, providing an alternative to polling read jobs:// in loops
Added task.maxConcurrency setting to limit the number of concurrently executing subagent tasks
Added support for rendering markdown output from Python cells with proper formatting and theme styling
Added async background job execution for bash commands and tasks with async: true parameter
Added cancel_job tool to cancel running background jobs
Added jobs:// internal protocol to inspect background job status and results
Added /jobs slash command to display running and recent background jobs in interactive mode
Added async.enabled and async.maxJobs settings to control background job execution
Added background job status indicator in status line showing count of running jobs
Added support for GitLab Duo authentication provider
Added clearer truncation notices across tools with consistent line/size context and continuation hints

Changed

Updated bash and task tool guidance to recommend poll_jobs instead of polling read jobs:// in loops when waiting for async results
Improved parallel task execution to schedule multiple background jobs independently instead of batching all tasks into a single job, enabling true concurrent execution
Enhanced task progress tracking to report per-task status (pending, running, completed, failed, aborted) with individual timing and token metrics for each background task
Updated background task messaging to provide real-time progress counts (e.g., '2/5 finished') and distinguish between single and multiple task jobs
Hid internal agent__intent parameter from tool argument displays in UI and logs to reduce visual clutter
Updated Python tool to detect and handle markdown display output separately from plain text
Updated bash tool to support async execution mode with streaming progress updates
Updated task tool to support async execution mode for parallel subagent execution
Modified subagent settings to disable async execution in child agents to prevent nesting
Updated tool execution component to handle background async task state without spinner animation
Changed event controller to keep background tool calls pending until async completion
Updated status line width calculation to accommodate background job indicator
Updated the system prompt pipeline to reduce injected environment noise and make instructions more focused on execution quality
Updated system prompt/workflow guidance to emphasize root-cause fixes, code quality, and explicit handoff/testing expectations
Changed default value of todo.reminders setting from false to true to enable todo reminders by default
Improved truncation/output handling for large command results to reduce memory pressure and keep previews responsive
Updated internal artifact handling so tool output artifacts stay consistent across session switches and resumes

Removed

Removed git context (branch, status, commit history) from system prompt — version control information is no longer injected into agent instructions

Fixed

Fixed task progress display to hide tool count and token metrics when zero, reducing visual clutter in status output
Fixed Lobsters scraper to correctly parse API responses where user fields are strings instead of objects, resolving undefined user display in story listings
Fixed artifact manager caching to properly invalidate when session file changes, preventing stale artifact references
Fixed truncation behavior around UTF-8 boundaries and chunked output accounting
Fixed submit_result schema generation to use valid JSON Schema when no explicit output schema is provided

[12.18.1] - 2026-02-21

Added

Added Buffer.toBase64() polyfill for Bun compatibility to enable base64 encoding of buffers

[12.18.0] - 2026-02-21

Added

Added overlay option to custom UI hooks to display components as bottom-centered overlays instead of replacing the editor
Added automatic chat transcript rebuild when returning from custom or debug UI to prevent message duplication

Changed

Changed custom UI hook cleanup to conditionally restore editor state only when not using overlay mode
Extracted environment variable configuration for non-interactive bash execution into reusable NO_PAGER_ENV constant
Replaced custom timing instrumentation with logger.timeAsync() and logger.time() from pi-utils for consistent startup profiling
Removed PI_DEBUG_STARTUP environment variable in favor of logger.debug() for conditional debug output
Consolidated timing calls throughout initialization pipeline to use unified logger-based timing system

Removed

Deleted utils/timings.ts module - timing functionality now provided by pi-utils logger

Fixed

Fixed potential race condition in bash interactive component where output could be appended after the component was closed

[12.17.2] - 2026-02-21

Changed

Modified bash command normalization to only apply explicit head/tail parameters from tool input, removing automatic extraction from command pipes
Updated shell snapshot creation to use explicit timeout and kill signal configuration for more reliable process termination

Fixed

Fixed persistent shell session state not being reset after command abort or hard timeout, preventing stale environment variables from affecting subsequent commands
Fixed hard timeout handling to properly interrupt long-running commands that exceed the grace period beyond the configured timeout

[12.17.1] - 2026-02-21

Added

Added filterBrowser option to filter out browser automation MCP servers when builtin browser tool is enabled
Added isBrowserMCPServer() function to detect browser automation MCP servers by name, URL, or command patterns
Added filterBrowserMCPServers() function to remove browser MCP servers from loaded configurations
Added BrowserFilterResult type for browser MCP server filtering results

[12.17.0] - 2026-02-21

Added

Added timeout protection (5 seconds) for system prompt preparation with graceful fallback to minimal context on timeout

Changed

Replaced glob-based AGENTS.md discovery with depth-limited directory traversal (depth 1-4) for improved performance and control
Refactored system prompt preparation to parallelize file loading operations with a 5-second timeout to prevent startup hangs
Unified renderCall signatures to (args, options, theme) across all tool renderers and extension types

[12.16.0] - 2026-02-21

Added

Added peekApiKey method to AuthStorage for non-blocking API key retrieval during model discovery without triggering OAuth token refresh
Exported finalizeSubprocessOutput function to handle subprocess output finalization with submit_result validation
Exported SubmitResultItem interface for type-safe submit_result tool data extraction
Added automatic reminders when subagent stops without calling submit_result tool (up to 3 reminders before aborting)
Added system warnings when subagent calls submit_result with null/undefined data or exits without calling submit_result after reminders

Changed

Changed model refresh behavior to support configurable strategies: uses 'online' mode when listing models and 'online-if-uncached' mode otherwise for improved performance
Changed default thinking level from 'off' to 'high' for improved reasoning and planning
Changed model discovery to use non-blocking API key peek instead of full key retrieval, improving performance by avoiding unnecessary OAuth token refreshes
Simplified submit_result termination logic to immediately abort on successful tool execution instead of waiting for message_end event
Updated submit_result tool to only terminate on successful execution (when isError is false), allowing retries on tool errors
Refactored subprocess output finalization logic into dedicated finalizeSubprocessOutput function for better testability and maintainability
Improved handling of missing submit_result calls by automatically aborting with exit code 1 after 3 reminder prompts

Fixed

Fixed submit_result retry behavior to properly handle tool execution errors and allow the subagent to retry before aborting
Fixed submit_result tool extraction to properly validate status field and only accept 'success' or 'aborted' results

[12.15.1] - 2026-02-20

Changed

Replaced nerd font pie-chart spinner with clock-outline icons for smoother looping
Moved status icon to front of code-cell headers in formatHeader

Fixed

Fixed ReadToolGroupComponent to show status icon before title instead of trailing
Fixed bash-interactive status badge to dim only bracket characters, not the enclosed text

[12.15.0] - 2026-02-20

Added

Added includeDisabled parameter to listAuthCredentials() to optionally retrieve disabled credentials
Added disableAuthCredential() method for soft-deleting auth credentials while preserving database records

Changed

Updated browser tool prompt to bias towards observe over screenshot by default
Changed auth credential removal to use soft-delete (disable) instead of hard-delete when OAuth refresh fails, keeping credentials in database for audit purposes
Changed default value of tools.intentTracing setting from false to true

[12.14.1] - 2026-02-19

Fixed

Fixed omp stats failing on npm/bun installs by including required stats build files in published @oh-my-pi/omp-stats package (#113 by @masonc15)

[12.14.0] - 2026-02-19

Added

Support for docs:// internal URL protocol to access embedded documentation files (e.g., docs://sdk.md)
Added generate-docs-index npm script to automatically index and embed documentation files at build time
Support for executable tool files (.ts, .js, .sh, .bash, .py) in custom tools discovery alongside markdown files
Display streamed tool intent in working message during agent execution
Added tools.intentTracing setting to enable intent tracing, which asks the agent to describe the intent of each tool call before executing it
Support for file deletion in hashline edit mode via delete: true parameter
Support for file renaming/moving in hashline edit mode via rename parameter
Optional content-replace edit variant in hashline mode (enabled via PI_HL_REPLACETXT=1 environment variable)
Support for grepping internal URLs (artifact://) by resolving them to their backing files

Changed

System prompt now identifies agent as operating inside Oh My Pi harness and instructs reading docs:// URLs for omp/pi topics
Tool discovery now accepts executable script extensions (.ts, .js, .sh, .bash, .py) in addition to .json and .md files
Updated bash and read tool documentation to reference docs:// URL support
Hashline format separator changed from pipe (|) to colon (:) for improved readability (e.g., LINE#ID:content instead of LINE#ID|content)
Hashline hash representation changed from 4-character base36 to 2-character hexadecimal for more compact line references
Hashline edit API: renamed delete parameter to rm for consistency with standard file operations
Hashline edit API: renamed rename parameter to mv for consistency with standard file operations
Hashline edit API: content-replace operations now require explicit op: "replaceText" field to distinguish from other edit types
Hashline documentation terminology updated: references to 'anchors' replaced with 'tags' for clearer semantics
Intent tracing now uses _intent field name in tool schemas
Hashline edit API: renamed set operation to target/new_content for clearer semantics
Hashline edit API: renamed set_range operation to first/last/new_content
Hashline edit API: renamed insert operation fields from body to inserted_lines and made inserted_lines required non-empty
Hashline edit API: flattened replace operation to top-level fields (old_text, new_text, all) when enabled
Hashline edit validation now provides more specific error messages indicating which variant is expected

Fixed

Grep tool now properly handles internal URL resolution when searching artifact paths
Working message intent updates now fall back to tool execution events when streamed tool arguments omit the intent field

[12.13.0] - 2026-02-19

Breaking Changes

Removed automatic line relocation when hash references become stale; edits with mismatched line hashes now fail with an error instead of silently relocating to matching lines elsewhere in the file

Added

Added ssh command for managing SSH host configurations (add, list, remove)
Added /ssh slash command in interactive mode to manage SSH hosts with subcommands
Added support for SSH host configuration at project and user scopes (.omp/ssh.json and ~/.omp/agent/ssh.json)
Added --host, --user, --port, --key, --desc, --compat, and --scope flags for SSH host configuration
Added discovery of SSH hosts from project configuration files alongside manually configured hosts
Added NanoGPT as a login provider (/login nanogpt) with API key prompt flow linking to https://nano-gpt.com/api (#111)

Changed

Updated hashline reference format from LINE:HASH to LINE#ID throughout the codebase for improved clarity
Renamed hashline edit operations: set_line → set, replace_lines → set_range, insert_after → insert with support for before and between anchors
Changed hashline edit body field from string to array of strings for clearer multiline handling
Updated handlebars helpers: renamed hashline to href and added hline for formatted line output
Improved insert operation to support before, after, and between (both anchors) positioning modes
Made autocorrect heuristics (boundary echo stripping, indent restoration) conditional on PI_HL_AUTOCORRECT environment variable
Updated SSH host discovery to load from managed omp config paths (.omp/ssh.json and ~/.omp/agent/ssh.json) in addition to legacy root-level ssh.json and .ssh.json files
Improved terminal output handling in interactive bash sessions to ensure all queued writes complete before returning results

Fixed

Fixed insert-between operation to properly validate adjacent anchor lines and strip boundary echoes from both sides
Fixed terminal output handling to properly queue and serialize writes, preventing dropped or corrupted output in interactive bash sessions

[12.12.1] - 2026-02-19

Added

Added Kimi (Moonshot) as a web search provider with OAuth and API key support (#110 by @oglassdev)

Changed

Changed web search auto-resolve priority to prefer Perplexity first

Fixed

Fixed Mermaid pre-render failures from repeatedly re-triggering background renders (freeze loop) and restored resilient rendering when diagram conversion/callbacks fail (#109).

[12.12.0] - 2026-02-19

Added

Display streaming text preview during agent specification generation to show real-time progress
Added onRequestRender callback to agent dashboard for triggering UI updates during async operations
Added agent creation flow (press N in dashboard) to generate custom agents from natural language descriptions
Added ability to save generated agents to project or user scope with automatic identifier and system prompt generation
Added scope toggle (Tab) during agent creation to choose between project-level and user-level agent storage
Added agent regeneration (R key) to refine generated specifications without restarting the creation flow
Added model suggestions in model override editor to help users discover available models
Added success notices to confirm agent creation and model override updates

Changed

Updated agent creation flow to show review screen before generation completes, improving UX feedback
Changed generation status hint to display "Generating..." while specification is being created
Improved system prompt preview formatting with text wrapping and line truncation indicators

Fixed

Fixed interactive-mode editor height to stay bounded and resize-aware, preventing off-screen cursor drift during long prompt/history navigation (#99).

[12.11.3] - 2026-02-19

Fixed

Fixed model selector search initialization to apply the latest live query after asynchronous model loading.
Fixed Codex provider session lifecycle on model switches and history rewrites to clear stale session metadata before continuing the conversation.

[12.11.0] - 2026-02-19

Added

Support for Synthetic model provider in web search command
Model sorting by priority field and version number in model selector for improved model ranking
Support for Synthetic model provider with API key authentication
Support for Hugging Face model provider with API key authentication
Support for NVIDIA model provider with API key authentication
Support for Ollama model provider with optional API key authentication
Support for Cloudflare AI Gateway model provider with API key authentication
Support for Qwen Portal model provider with API key authentication
Support for LiteLLM model provider with API key authentication
Support for Moonshot model provider with API key authentication
Support for Qianfan model provider with API key authentication
Support for Together model provider with API key authentication
Support for Venice model provider with API key authentication
Support for vLLM model provider with API key authentication
Support for Xiaomi model provider with API key authentication

Changed

Refactored custom model building logic into reusable buildCustomModel function for consistency across provider configurations
Replaced generic error with AgentBusyError when attempting to send messages while agent is processing
Added automatic retry logic with idle waiting when agent is busy during prompt operations, with 30-second timeout

Fixed

Fixed model discovery to use default refresh mode instead of explicit 'online' parameter

[12.10.1] - 2026-02-18

Added

Added /login support for Cerebras and Synthetic API-key providers

[12.10.0] - 2026-02-18

Breaking Changes

Changed keyless provider auth sentinel from "<no-auth>" to kNoAuth ("N/A") for ModelRegistry.getApiKey() and ModelRegistry.getApiKeyForProvider()

Added

Added --no-rules CLI flag to disable rules discovery and loading
Added sessionDir option to RpcClientOptions for specifying agent session directory
Added Symbol.dispose method to RpcClient for resource cleanup support
Added rules option to CreateAgentSessionOptions for explicit rule configuration
Added sessionDir option to RpcClientOptions for specifying agent session directory
Added Symbol.dispose method to RpcClient for resource cleanup support
Added autocompleteMaxVisible setting to configure the number of items shown in the autocomplete dropdown (3-20, default 5) (#98 by @masonc15)
Added condition and scope fields to rule frontmatter for advanced TTSR matching and stream filtering
Added ttsr.interruptMode setting to control when TTSR rules interrupt mid-stream vs inject warnings after completion
Added support for loading rules, prompts, commands, context files (AGENTS.md), and system prompts (SYSTEM.md) from ~/.agent/ directory (with fallback to ~/.agents/)
Added scoped stream buffering for TTSR matching to isolate prose, thinking, and tool argument streams
Added file-path-aware TTSR scope matching for tool calls with glob patterns (e.g., tool:edit(*.ts))
Added legacy field support: ttsr_trigger and ttsrTrigger are accepted as fallback for condition

Changed

Changed TTSR injection tracking to record all turns where rules were injected (instead of only the last turn) to support repeat-after-gap mode across resumed sessions
Changed TTSR injection messages to use custom message type with metadata instead of synthetic user messages for better session tracking
Changed TTSR rule injection to persist injected rule names in session state for restoration when resuming sessions
Changed model discovery to automatically discover built-in provider models (Anthropic, OpenAI, Groq, Cerebras, Xai, Mistral, OpenCode, OpenRouter, Vercel AI Gateway, Kimi Code, GitHub Copilot, Google, Cursor, Google Antigravity, Google Gemini CLI, OpenAI Codex) when credentials are configured
Changed getModel() and getModels() imports to getBundledModel() and getBundledModels() across test utilities
Changed TTSR rule matching from single ttsrTrigger regex to multiple condition patterns with scope filtering
Changed TTSR buffer management to use per-stream-key buffers instead of a single global buffer
Changed rule discovery to use unified buildRuleFromMarkdown helper across all providers (builtin, cline, cursor, windsurf, agents)
Changed TTSR injection to defer warnings until stream completion when interruptMode is not always
Changed TtsrManager.addRule() to return boolean indicating successful registration instead of void

Fixed

Fixed TTSR repeat-after-gap mode to correctly calculate gaps when rules are restored from previous sessions
Fixed TTSR matching to respect tool-specific scope filters, preventing cross-tool rule contamination
Fixed path normalization in TTSR glob matching to handle both relative and absolute path variants

[12.9.0] - 2026-02-17

Added

Added OpenCode discovery provider to load configuration from ~/.config/opencode/ and .opencode/ directories
Added support for loading MCP servers from opencode.json mcp key
Added support for loading skills from ~/.config/opencode/skills/ and .opencode/skills/
Added support for loading slash commands from ~/.config/opencode/commands/ and .opencode/commands/
Added support for loading extension modules (plugins) from ~/.config/opencode/plugins/ and .opencode/plugins/
Added support for loading context files (AGENTS.md) from ~/.config/opencode/
Added support for loading settings from opencode.json configuration files

Changed

Improved path display in status line to strip both /work/ and ~/Projects/ prefixes when abbreviating paths
Refactored session directory naming to use single-dash format for home-relative paths and double-dash format for absolute paths, with automatic migration of legacy session directories on first access

[12.8.2] - 2026-02-17

Changed

Changed system environment context to use built-in os values for distro, kernel, and CPU model instead of native system-info data
Changed environment info generation to stop including unavailable native system detail fallbacks

Removed

Removed the Disk field from generated environment information

[12.8.0] - 2026-02-16

Changed

Improved /changelog performance by displaying only the most recent 3 versions by default, with a --full flag for the complete history (#85 by @tctev)
Centralized builtin slash command definitions and handlers into a shared registry, replacing the large input-controller if-chain dispatch

[12.7.0] - 2026-02-16

Added

Added abort signal support to LSP file operations (ensureFileOpen, refreshFile) for cancellable file synchronization
Added abort signal propagation through LSP request handlers (definition, references, hover, symbols, rename) enabling operation cancellation
Added shouldBypassAutocompleteOnEscape callback to custom editor for context-aware escape key handling during active operations
Added contextPromotionTarget model configuration option to specify a custom target model for context promotion
Added automatic context promotion feature that switches to a larger-context model when approaching context limits
Added contextPromotion.enabled setting to control automatic model promotion (enabled by default)
Added contextPromotion.thresholdPercent setting to configure the context usage threshold for triggering promotion (default 90%)
Added Brave web search provider as an alternative search option with recency filtering support
Added BRAVE_API_KEY environment variable support for Brave web search authentication
Added pagination support for fetching GitHub issue comments, allowing retrieval of all comments beyond the initial 50-comment limit
Added comment count display showing partial results when not all comments could be fetched (e.g., '5 of 10 comments')
Added secret obfuscation: env vars matching secret patterns and secrets.json entries are replaced with placeholders before sending to LLM providers, deobfuscated in tool call arguments
Added secrets.enabled setting to toggle secret obfuscation
Added full regex literal support for secrets.json entries ("/pattern/flags" syntax with escaped / handling, automatic g flag enforcement)

Changed

Changed context promotion to trigger on context overflow instead of a configurable threshold, promoting to a larger model before attempting compaction
Changed context promotion behavior to retry immediately on the promoted model without compacting, providing faster recovery from context limits
Changed default grep context lines from 1 before/3 after to 0 before/0 after for more focused search results
Changed escape key handling in custom editor to allow bypassing autocomplete dismissal when specified by parent controller
Changed workspace diagnostics to support abort signals for cancellable diagnostic runs
Changed LSP request cancellation to send $/cancelRequest notification to language servers when operations are aborted
Changed input controller to bypass autocomplete on escape when loading animations, streaming, compacting, or running external processes
Changed context promotion logic to use configured contextPromotionTarget when available, allowing per-model promotion customization
Updated session compaction reserve token calculation to enforce a minimum 15% context window floor, ensuring more predictable compaction behavior regardless of configuration
Improved session compaction to limit file operation summaries to 20 files per category, with indication of omitted files when exceeded
Updated CLI update mechanism to support multiple native addon variants per platform, enabling fallback to baseline versions when modern variants are unavailable
Updated web search provider priority order to include Brave (Exa → Brave → Jina → Perplexity → Anthropic → Gemini → Codex → Z.AI)
Extended recency filter support to Brave provider alongside Perplexity
Changed GitHub issue comment fetching to use paginated API requests with 100 comments per page instead of single request with 50-comment limit

Removed

Removed contextPromotion.thresholdPercent setting as context promotion now triggers only on overflow

Fixed

Fixed LSP operations to properly respect abort signals and throw ToolAbortError when cancelled
Fixed workspace diagnostics process cleanup to remove abort event listeners in finally block
Fixed PTY-backed bash execution to enforce timeout completion when detached child processes keep the PTY stream open (#88)

[12.5.1] - 2026-02-15

Added

Added repeatToolDescriptions setting to render full tool descriptions in the system prompt instead of a tool name list

[12.5.0] - 2026-02-15

Breaking Changes

Replaced theme setting with theme.dark and theme.light (auto-migrated)

Added

Added previewTheme() function for non-destructive theme preview during settings browsing
Added animated microphone icon with color cycling during voice recording
Added support for discovering skills via symbolic links in skill directories
Added abort_and_prompt RPC command for atomic abort-and-reprompt without race conditions (#357)
Added automatic dark/light theme switching via SIGWINCH with separate theme.dark/theme.light settings, replacing the single theme setting (#65)
Added speech-to-text (STT) feature with Alt+H keybinding and /stt slash command
Added cross-platform audio recording: SoX, FFmpeg, arecord (Linux), PowerShell mciSendString (Windows fallback)
Added recording tool fallback chain — automatically tries each available tool in order
Added Python openai-whisper integration for transcription with automatic pip install
Added custom WAV-to-numpy pipeline in transcribe.py bypassing ffmpeg dependency
Added STT settings: stt.enabled, stt.language, stt.modelName
Added STT status line segment showing recording/transcribing state
Added /stt command with on, off, status, setup subcommands
Added auto-download of recording tools (best-effort FFmpeg via winget on Windows)
Added interactive debug log viewer with selection, copy, and expand/collapse controls
Added inline filtering and count display to the debug log viewer
Added pid filter toggle and load-older pagination controls to the debug log viewer
Enabled loading older debug logs from archived files in viewer
Added file hyperlinks for debug report paths in viewer

Changed

Changed theme preview to support asynchronous theme loading with request deduplication to prevent race conditions
Enhanced theme preview cancellation to restore the previously active theme instead of the last selected value
Refactored file discovery to use native glob with gitignore support instead of manual directory traversal, improving performance and consistency
Updated dependencies: glob to ^13.0.3, marked to ^17.0.2, puppeteer to ^24.37.3
Optimized skill and file discovery using native glob (Rust ignore crate) — reduces startup time by ~80% (1254ms → 6ms for skills)
Enhanced hashline reference parsing to handle prefixes like >>> and >> in line references
Strengthened type safety in hashline edit formatting with defensive null checks for incomplete edits
Changed STT status messages to display via state change callbacks instead of explicit status calls
Changed cursor visibility behavior during voice recording to hide hardware and terminal cursors

Removed

Removed dedicated STT status line segment in favor of animated cursor-based feedback

Fixed

Fixed theme preview updates being applied out-of-order when rapidly browsing theme options
Fixed skill discovery to correctly extract skill names from directory paths when frontmatter name is missing
Fixed session.abort() not clearing promptInFlight flag due to microtask ordering, which blocked subsequent prompts
Sanitized debug log display to strip control codes, normalize tabs, and trim width

[12.4.0] - 2026-02-14

Changed

Moved sanitizeText function from @oh-my-pi/pi-utils to @oh-my-pi/pi-natives for better code organization
Replaced internal #normalizeOutput methods with sanitizeText utility function in bash and Python execution components
Added line length clamping (4000 characters) to bash and Python execution output to prevent display of excessively long lines
Modified memory storage to isolate memories by project working directory, preventing cross-project memory contamination

Fixed

Fixed bash interactive tool to gracefully handle malformed output chunks by normalizing them before display
Fixed fetch tool incorrectly treating HTML content as plain text or markdown
Fixed output truncation notice displaying incorrect byte limit when maxBytes differs from outputBytes
Fixed Cloudflare returning corrupted bytes when compression is negotiated in web scraper requests

[12.3.0] - 2026-02-14

Added

Added autonomous memory extraction and consolidation system with configurable settings
Added /memory slash command with subcommands: view, clear, reset, enqueue, rebuild
Added memory injection payload that automatically includes learned context in system prompts
Added two-phase memory pipeline: Stage 1 extracts durable knowledge from session history, Phase 2 consolidates into reusable skills and guidance
Added memory storage layer with SQLite-backed job queue for distributed memory processing
Added configurable memory settings: concurrency limits, lease timeouts, token budgets, and rollout age constraints

Changed

Modified system prompt building to inject memory guidance when memories are enabled
Changed resolvePromptInput to handle multiline input and improve error handling for file reads

[12.2.0] - 2026-02-13

Added

Added providerSessionState property to AgentSession for managing provider-scoped transport and session caches
Added automatic cleanup of provider session state resources on session disposal
Added providers.openaiWebsockets setting to prefer websocket transport for OpenAI Codex models
Added provider details display in session info showing authentication mode, transport, and connection settings
Added automatic prewarm of OpenAI Codex websocket connections on session creation for improved performance
Added real-time authentication validation in OAuth provider selector with visual status indicators (checking, valid, invalid)
Added validateAuth and requestRender options to OAuthSelectorComponent for custom authentication validation and UI refresh callbacks

Changed

Changed providers.openaiWebsockets setting from boolean to enum with values "auto", "off", "on" for more granular websocket policy control (auto uses model defaults, on forces websocket, off disables it)
Enhanced provider details display to include live provider session state information
Enhanced session info output to display active provider configuration and authentication details
Replaced process.cwd() with getProjectDir() throughout codebase for improved project directory detection and handling
Made SessionManager.list() async to support asynchronous session discovery operations
Preserved internal whitespace and indentation in bash command normalization to support heredocs and indentation-sensitive scripts
Improved git context loading performance with configurable timeouts and parallel status/commit queries
Enhanced git context reliability with better error handling for timeout and command failures
Changed OAuth provider selector to display live authentication status instead of static login state
Changed logout flow to refresh OAuth provider authentication state before showing selector

Fixed

Improved error reporting in fetch tool to include HTTP status codes when URL fetching fails
Fixed fetch tool to preserve actual response metadata (finalUrl, contentType) instead of defaults when requests fail

[12.1.0] - 2026-02-13

Added

Filesystem scan cache invalidation helpers (invalidateFsScanAfterWrite, invalidateFsScanAfterDelete, invalidateFsScanAfterRename) to properly invalidate shared caches after file mutations
Named discovery profile for file mention candidates to standardize cache visibility and ignore semantics across callers
Comprehensive models.yml provider integration guide documenting custom model registration, provider overrides, API adapters, merge behavior, and practical integration patterns for Ollama, vLLM, LM Studio, and proxy endpoints
Claude Code marketplace plugin discovery: automatically loads skills, commands, hooks, tools, and agents from ~/.claude/plugins/cache/ based on installed_plugins.json registry (#48)

Changed

Moved directory path utilities from src/config.ts to @oh-my-pi/pi-utils/dirs for shared use across packages
Updated imports throughout codebase to use centralized directory path functions from @oh-my-pi/pi-utils/dirs
Updated interactive bash terminal UI label from 'InteractiveTerm' to 'Console' for clarity
Enhanced bash execution environment with comprehensive non-interactive defaults for pagers, editors, and package managers to prevent command blocking and interactive prompts
Updated custom models configuration to use ~/.omp/agent/models.yml (YAML format) while maintaining backward compatibility with legacy models.json

[12.0.0] - 2026-02-12

Added

Added getAllServerNames() method to MCPManager for enumerating all known servers

Changed

Changed default edit mode from patch to hashline for more precise code modifications
Changed readHashLines setting default from false to true to enable hash line reading by default

Fixed

Fixed omp setup crashing with uncaught exception when no component argument provided; now shows help (#35)
Fixed /mcp list showing "No MCP servers configured" when servers are loaded from discovery sources like .claude.json, .cursor/mcp.json, .vscode/mcp.json (#34)
Fixed model selector sorting to show newest models first within each provider instead of alphabetical; -latest aliases now appear before dated versions (#37)

[11.14.4] - 2026-02-12

Added

Exported renderPromptTemplate function for programmatic prompt template rendering
Exported computeLineHash function from patch utilities
Added ./cli export path for direct CLI module access

Changed

Replaced jsdom with linkedom for improved HTML parsing performance and reduced memory footprint

Removed

Removed @types/jsdom dependency

[11.14.1] - 2026-02-12

Changed

Improved Bun binary detection to check Bun.env.PI_COMPILED environment variable
Enhanced Bun package manager update to install specific version instead of latest
Added post-update verification for Bun installations to warn if expected version was not installed

Fixed

Fixed Bun update process to properly handle version pinning and report installation mismatches

[11.14.0] - 2026-02-12

Added

Added SwiftLint linter client with JSON reporter support for Swift file linting
Added --no-pty flag to disable PTY-based interactive bash execution
Added PI_NO_PTY environment variable to disable PTY-based interactive bash execution
Added bash.virtualTerminal setting to control PTY-backed interactive execution for bash commands
Added interactive PTY-based bash execution with real-time terminal rendering and input forwarding
Added sourcekit-lsp language server support for Swift files

Changed

Changed bash.virtualTerminal default from on to off for standard non-interactive bash execution
Changed SwiftLint configuration to use lint command with JSON reporter instead of analyze for improved diagnostic parsing
Changed diff line format from space-separated (+123 content) to pipe-delimited (+123|content) for improved parsing reliability
Changed bash tool to use interactive PTY execution by default when UI is available, falling back to standard execution when disabled

[11.13.1] - 2026-02-12

Added

Added /move slash command to move session to a different working directory
Added moveTo() method to SessionManager for relocating sessions with file migration and header updates
Added refreshSlashCommandState() method to reload slash commands and autocomplete when working directory changes
Added setSlashCommands() method to AgentSession for updating file-based slash commands
Added OAuth authentication support for Perplexity web search via www.perplexity.ai/rest/sse/perplexity_ask endpoint
Added automatic OAuth token refresh with 5-minute expiry buffer for Perplexity authentication
Added authMode field to search responses to indicate authentication method used (oauth or api_key)
Added display of authentication mode in search result output
Added support for streaming SSE responses from Perplexity OAuth API with proper event merging

Changed

Changed Perplexity provider to support both API key and OAuth authentication methods
Changed isAvailable() method to async to check for both API key and OAuth token availability
Changed error message to guide users to set PERPLEXITY_API_KEY or login via OAuth
Changed callPerplexity to callPerplexityApi to clarify it uses the API key endpoint

[11.13.0] - 2026-02-12

Breaking Changes

Removed support for .pi configuration directory alias; use .omp instead

Added

Added openPath utility function to centralize cross-platform URL and file path opening

Changed

Refactored browser/file opening across multiple modules to use unified openPath utility for improved maintainability

[11.12.0] - 2026-02-11

Added

Added resolveFileDisplayMode utility to centralize file display mode resolution across tools (read, grep, file mentions)
Added automatic hashline formatting to @file mentions when hashline mode is active
Added replace hashline edit operation for substr-style fuzzy text replacement without line references, with optional all flag for replace-all behavior
Added noopEdits array to applyHashlineEdits return value to report edits that produced no changes, including edit index, location, and current content for diagnostics
Added validation to detect and reject hashline edits using wrong-format fields (old_text/new_text from replace mode, diff from patch mode) with helpful error messages
Added additionalProperties: true to all hashline edit schemas (single, range, insertAfter, and root) to tolerate extra fields from models
Added whitespace normalization in line reference parsing to tolerate spaces around colons (e.g., 5 : ab now parses as 5:ab)
Added remaps property to HashlineMismatchError providing quick-fix mapping of stale line references to corrected hashes
Added warnings detection in applyHashlineEdits to alert users when edits affect significantly more lines than expected, indicating possible unintended reformatting
Added diagnostic output showing target line content when an edit produces no changes, helping users identify hash mismatches or incorrect replacement content
Added {{hashline}} Handlebars helper to compute accurate LINE:HASH references for prompt examples and documentation
Added deduplication of identical hashline edits targeting the same line(s) in a single call
Added replacement as accepted alias for content in insertAfter operations
Added graceful degradation of range edits with missing end field to single-line edits
Added additionalProperties: true to hashline edit schemas to tolerate extra fields from models

Changed

Reverted hashline display format from LINE:HASH content (two spaces) back to LINE:HASH|content (pipe separator) for consistency with legacy format
Changed hashline display format from LINE:HASH| content to LINE:HASH content (two spaces instead of pipe separator) for improved readability
Removed lines and hashes parameters from read tool—file display mode (line numbers, hashlines) now determined automatically by settings and edit mode
Simplified read tool prompt to reflect automatic display mode detection based on configuration
Updated grep tool to respect file display mode settings, showing hashline-prefixed output when hashline mode is active
Renamed hashline edit operation keys from single/range/insertAfter to set_line/replace_lines/insert_after for clearer semantics
Renamed hashline edit fields: loc → anchor, replacement → new_text, content → text for consistency across all operation types
Separated hashline anchor-based edits (set_line, replace_lines, insert_after) from content-replace edits (replace) in application pipeline
Improved no-op edit diagnostics to use noopEdits array from applyHashlineEdits, providing precise line-by-line comparison when replacements match current content
Enhanced error messages for wrong-format hashline edits to guide users toward correct operation syntax
Strengthened hashline prompt guidance to emphasize that replacement must differ from current line content and clarify no-op error recovery procedures
Improved hashline prompt to clarify atomicity: all edits in one call are validated against the original file state, with line numbers and hashes referring to the pre-edit state
Added explicit instruction in hashline prompt to preserve exact whitespace and formatting when replacing lines, changing only the targeted token/expression
Added guidance in hashline prompt for swap operations: use two single operations in one call rather than attempting to account for line number shifts
Strengthened anti-reformatting instructions in hashline prompt to reduce formatting-only failures
Improved no-op error recovery guidance in hashline prompt to prevent infinite retry loops
Renamed hashline edit operation keys from replaceLine/replaceLines to single/range for clearer semantics
Renamed hashline edit field content to replacement in single and range operations to distinguish from insertAfter.content
Improved no-op edit diagnostics to show specific line-by-line comparisons when replacements match current content, helping users identify hash mismatches or formatting issues
Enhanced no-op error messages to distinguish between literally identical replacements and content normalized back by heuristics
Reverted hash algorithm from 3-character base-36 back to 2-character hexadecimal for line references
Enhanced range validation during hashline edits to detect and reject relocations that change the scope of affected lines
Improved wrapped-line restoration logic to only attempt merging when source lines exhibit continuation patterns
Updated hashline tool documentation to emphasize direction-locking mutations and clarify recovery procedures for hash mismatches
Changed applyHashlineEdits return type to include optional warnings array for reporting suspicious edit patterns
Improved hash relocation logic to recompute touched lines after hash-based line number adjustments, preventing incorrect merge heuristics
Enhanced error messages for no-op edits to include preview of target lines with their current hashes and content
Changed hashline edit format from src/dst object structure to direct operation schemas (replaceLine, replaceLines, insertAfter)
Changed hash algorithm from 2-character hexadecimal to 3-character base-36 alphanumeric for improved readability and collision resistance
Improved hash mismatch handling to automatically relocate stale line references when the hash uniquely identifies a moved line
Changed HashlineEdit from src/dst format to direct operation schemas: replaceLine, replaceLines, insertAfter
Changed hash algorithm from hexadecimal (base-16) to base-36 alphanumeric for shorter, more readable line references
Increased maximum wrapped-line restoration from 6 to 10 lines to handle longer reflowed statements
Updated prompt examples to use {{hashline}} Handlebars helper for generating correct line references in tool instructions

Removed

Removed insertBefore hashline edit operation for inserting content before a line
Removed substr hashline edit operation for substring-based line replacement
Removed insertBefore and substr hashline edit variants

Fixed

Fixed parseLineRef to handle both legacy pipe-separator format (LINE:HASH| content) and new two-space format (LINE:HASH content) for backward compatibility
Fixed resource leak in browser query handler by properly disposing owned proxy elements for non-winning candidates
Fixed script evaluation to support async functions and await expressions in browser evaluate operations
Fixed range edits with missing end field to gracefully degrade to single-line edits instead of crashing
Fixed insertAfter operations to accept both content and replacement field names for consistency with other edit types
Fixed deduplication logic to correctly identify and remove identical hashline edits targeting the same line(s) in a single call
Fixed range-based edits to prevent invalid mutations when hash relocation changes the number of lines in the target range
Fixed multi-edit application to use original file state for all anchor references, preventing incorrect line numbers when earlier edits change file length

[11.10.4] - 2026-02-10

Added

Hashline diff computation with computeHashlineDiff function for preview rendering of hashline-mode edits
Streaming preview display for hashline edits in tool execution UI showing edit sources and destinations
Streaming hash line computation with progress updates via onUpdate callback in read tool
Optional onCollectedLine callback parameter to streamLinesFromFile for line collection tracking

Changed

Edit tool renderer now displays computed preview diffs for hashline operations before execution
Read tool now streams hash lines incrementally instead of computing them all at once, improving responsiveness for large files
Refactored hash line formatting to use async streamHashLinesFromLines for better performance

[11.10.3] - 2026-02-10

Added

Exported ./patch/* subpath for direct access to patch utilities

[11.10.2] - 2026-02-10

Added

Exported streamHashLinesFromUtf8 and streamHashLinesFromLines functions for streaming hashline-formatted output with configurable chunking
Added HashlineStreamOptions interface to control streaming behavior (startLine, maxChunkLines, maxChunkBytes)
Added streamHashLinesFromUtf8 function to incrementally format content with hash lines from a UTF-8 byte stream
Added streamHashLinesFromLines function to incrementally format content with hash lines from an iterable of lines

Changed

Updated hashline format to use 2-character hex hashes instead of 4-character hashes for more compact line references
Modified computeLineHash to normalize whitespace in line content and removed line number from hash seed for consistency
Improved CLI argument parsing to explicitly handle --help, --version, and subcommand detection instead of prefix-based routing

Removed

Removed @types/diff dev dependency
Removed AggregateError unwrapping from console.warn in CLI initialization

[11.10.1] - 2026-02-10

Changed

Migrated CLI framework from oclif to lightweight pi-utils CLI runner
Replaced oclif command registration with explicit command entries in cli.ts
Changed default root command name from 'index' to 'launch'
Updated all command imports to use @oh-my-pi/pi-utils/cli instead of @oclif/core

Removed

Removed @oclif/core and @oclif/plugin-autocomplete dependencies
Removed oclif configuration from package.json
Removed custom oclif help renderer (oclif-help.ts)

[11.10.0] - 2026-02-10

Breaking Changes

Changed HashlineEdit.src from string format (e.g., "5:ab", "5:ab..9:ef") to structured SrcSpec object with discriminated union types ({ kind: "single", ref: "..." }, { kind: "range", start: "...", end: "..." }, etc.)
Changed HashlineEdit API from old: string | string[] / new: string | string[] to src: string / dst: string; src uses range syntax "5:ab" (single), "5:ab..9:ef" (range), "5:ab.." (insert after), or "..5:ab" (insert before)
Removed support for comma and newline-separated line reference lists in hashline edits; use range syntax instead
Removed after field from HashlineEdit; insert-after is now expressed via open range syntax src: "5:ab.."
Changed HashlineEdit API from old: string | string[] / new: string | string[] to src: string / dst: string; multi-line content uses \n-separated strings, empty string "" for insert/delete operations
Replaced edit.patchMode boolean setting with edit.mode enum; existing edit.patchMode: true configurations should use edit.mode: patch
Changed getEditModelVariants() return type from Record<string, "patch" | "replace"> to Record<string, EditMode | null>
Removed after field from HashlineEdit; insert-after is now expressed via open range syntax src: "5:ab.."
Changed HashlineEdit.src from newline-separated line ref lists to range syntax: "5:ab" (single), "5:ab..9:ef" (range), "5:ab.." (insert after); comma and newline-separated lists are no longer supported

Added

Added substring-based source matching for hashline edits when line reference format is invalid, allowing fallback to unique substring search within the file
Added automatic detection and repair of single-line merges where models absorb adjacent lines, preventing content duplication
Added normalization of unicode-confusable hyphens (en-dash, em-dash, etc.) to ASCII hyphens when edits would otherwise be no-ops
Added heuristics to restore original indentation and preserve wrapped line formatting in hashline edits
Added abort signal support to MCP server connection and tool listing operations, allowing requests to be cancelled via Escape key during testing
Added MCPRequestOptions interface with signal property to support request cancellation via AbortSignal
Added abort signal support to MCP tool execution, allowing requests to be cancelled via Escape-to-interrupt or other abort mechanisms
Added HashlineMismatchError class that displays grep-style output with >>> markers showing correct LINE:HASH references when hash validation fails
Added HashMismatch type to represent individual hash mismatches with line number, expected hash, and actual hash
Added hashline edit mode for line-addressed edits using content hashes (LINE:HASH format) with integrity verification
Added readHashLines setting to include line hashes in read output for hashline edit mode
Added edit.mode setting (enum: replace, patch, hashline) to select edit tool variant, replacing edit.patchMode boolean
Added hashes parameter to read tool to output line hashes in format LINE:HASH| content
Added automatic hash line output when using hashline edit mode or readHashLines setting is enabled
Added computeLineHash, formatHashLines, parseLineRef, validateLineRef, and applyHashlineEdits functions for hashline operations
Added HashlineEdit and HashlineInput types for structured hashline edit operations
Added normalizeEditMode function to validate and normalize edit mode strings
Added subcommand definitions for /mcp command with 10 subcommands (add, list, remove, test, reauth, unauth, enable, disable, reload, help) including usage hints for argument completion
Added inline hint support for slash commands with simple arguments (/export [path], /compact [focus instructions], /handoff [focus instructions])
Added subcommand dropdown completion for /browser command (headless, visible modes)
Added SubcommandDef interface for declarative subcommand definitions with name, description, and usage hints
Added subcommands and inlineHint properties to BuiltinSlashCommand interface for enhanced command metadata
Added getArgumentCompletions and getInlineHint functions to materialized slash commands for autocomplete and ghost text hints
Added temperature setting to control sampling temperature (0 = deterministic, 1 = creative, -1 = provider default)
Added temperature option selector in settings UI with preset values (Default, 0, 0.2, 0.5, 0.7, 1)

Changed

Relaxed comma validation in src to allow trailing content after line references (e.g., 14:abexport function foo()), while still rejecting inputs that appear to contain multiple line refs
Improved parseLineRef to accept hash prefixes shorter than the full hash length, allowing partial hash matches
Enhanced error message for hash mismatches to guide users toward re-reading the file and using updated LINE:HASH references
Updated hashline tool documentation to clarify that accidental trailing text after LINE:HASH will be extracted, and to discourage merging multiple lines into single-line replacements
Treated same-line ranges (e.g., 5:ab..5:cd) as single-line replacements instead of range operations
Enhanced hashline edit robustness with heuristics to strip anchor line echoes and range boundary echoes that models may copy into replacement content
Improved whitespace preservation in hashline edits to handle mismatched line counts using loose matching strategy
Strengthened hashline edit validation to reject malformed src specs (embedded newlines, commas, invalid ranges)
Enhanced MCP connection timeout handling to properly respect abort signals and distinguish between timeout and user-initiated cancellation
Improved MCP test command UI to show cancellation hint (esc to cancel) and handle graceful cancellation without blocking cleanup
Updated HTTP transport session termination to use AbortSignal.timeout() for reliable cleanup with timeout protection
Enhanced bash executor to properly handle abort signals by registering abort event listeners and cleaning up resources in finally block
Improved bash tool error handling to distinguish between user-initiated aborts (via AbortSignal) and other cancellations, throwing ToolAbortError for aborted requests
Enhanced MCP request handling to propagate abort signals through HTTP, SSE, and stdio transports with proper cleanup
Improved stdio transport request handling to use Promise.withResolvers for cleaner async flow and better abort signal integration
Updated HTTP transport to combine operation abort signals with timeout signals using AbortSignal.any() for unified cancellation
Modified SSE response parsing to support abort signals and distinguish between timeout and user-initiated cancellation
Improved hashline edit robustness by automatically stripping LINE:HASH| display prefixes and unified-diff + markers that models may copy into replacement content
Enhanced replace edits to preserve original whitespace on lines where only whitespace differs, preventing spurious formatting diffs when models reformat code
Enhanced system prompt to display tool descriptions alongside tool names for improved clarity on available capabilities
Reduced hash length from 4 to 2 hex characters (16-bit hashes) for more concise line references
Updated HashlineEdit type to accept string | string[] for old and new fields, allowing single-line edits without array wrapping
Enhanced parseLineRef to strip display-format suffix (e.g., 5:ab| content → 5:ab), allowing models to copy full read output format
Improved validateLineRef to throw HashlineMismatchError with context lines instead of generic error, providing grep-style output with correct hashes
Modified hash computation to strip trailing carriage returns before hashing for consistent line hash values
Renamed HashlineEdit fields from src/dst to old/new for clarity in replace, delete, and insert operations
Enhanced hash validation in applyHashlineEdits to collect all mismatches before throwing, providing comprehensive error reporting with context lines
Changed edit.patchMode boolean setting to edit.mode enum (replace, patch, hashline) with default value patch
Changed edit tool to support three modes (replace, patch, hashline) instead of two, with dynamic mode selection based on model and settings
Changed read tool to prioritize hash lines over line numbers when both are requested
Changed getEditVariantForModel to return EditMode | null and removed hardcoded Kimi model detection
Renamed settingsInstance parameter to settings in CreateAgentSessionOptions for consistency
Updated all internal references from settingsInstance to settings throughout SDK and components

Fixed

Fixed substring source matching to reject ambiguous matches and provide helpful error messages showing all occurrences
Fixed substring source matching to require exactly one matching line in the file
Fixed MCP test command to properly clean up connections even when cancelled or aborted, preventing resource leaks

[11.9.0] - 2026-02-10

Added

Added /mcp slash command for runtime MCP server management (add, list, remove, enable, disable, test, reauth)
Added interactive multi-step wizard for adding MCP servers with transport auto-detection
Added OAuth auto-discovery and authentication flow for MCP servers requiring authorization
Added MCP config file writer for persisting server configurations at user and project level
Added enabled and timeout fields to MCP server configuration
Added runtime MCP manager reload and active tool registry rebind without restart
Added MCP command guide documentation

Changed

Replaced setTimeout with Bun.sleep() for improved performance in file lock retry logic
Refactored component invalidation handling to use dedicated helper function for cleaner code
Improved error handling in worktree baseline application to use isEnoent() utility instead of file existence checks
Updated bash tool to use standard Node.js fs.promises.stat() with isEnoent() error handling
Replaced tmpdir() named import with os namespace import for consistency
Migrated logging from chalk and console.error to structured logger from @oh-my-pi/pi-utils

Fixed

Improved browser script evaluation to handle both expression and statement forms, fixing evaluation failures for certain script types
Fixed unsafe OAuth endpoint extraction that could redirect token exchange to attacker-controlled URLs
Fixed PKCE code verifier stored via untyped property; now uses typed private field
Fixed refresh token fallback incorrectly using access token when no refresh token provided
Fixed MCP config files written with default permissions; now enforces 0o700/0o600 for secret protection
Fixed add wizard ignoring user-chosen environment variable name and auth header name
Fixed reauth endpoint discovery misclassifying non-OAuth servers as discovery failures
Fixed resolved OAuth tokens leaking into connection config, causing cache churn on token rotation
Fixed unvalidated type assertions for enabled/timeout config fields from user-controlled JSON
Fixed uncaught exceptions in /mcp add quick-add flow crashing the interactive loop
Fixed greedy /mcp prefix match routing /mcpfoo to MCP controller
Fixed stdio transport timeout timer leak keeping process alive after request completion

Removed

Removed GrepOperations interface from public API exports
Removed GrepToolOptions interface from public API exports
Removed unused _options parameter from GrepTool constructor

[11.8.1] - 2026-02-10

Added

Added current date to system prompt context in YYYY-MM-DD format for date-aware agent reasoning
Added file size display in UI when files are skipped due to size limits
Added support for gigabyte (GB) file size formatting in truncate utility

Changed

Changed skipped file messages to include file size information for better visibility into why files were excluded
Changed file processing to skip reading files exceeding 5MB (text) or 25MB (images) and include them as path-only references instead
Changed @mention auto-reading to skip files exceeding 5MB (text) or 25MB (images) to prevent out-of-memory issues with large files
Clarified that subagents automatically inherit full system prompt including AGENTS.md, context files, and skills — do not repeat project rules or conventions in task context
Updated task context guidance to focus on session-specific information subagents lack, eliminating redundant documentation of project constraints already available to them
Refined constraints template to emphasize task-specific rules and session decisions rather than global project conventions
Expanded anti-patterns section to explicitly flag redundant context that wastes tokens by repeating AGENTS.md rules, project constraints, and tool preferences

Fixed

Fixed bash tool hanging when commands spawn background jobs by properly detecting foreground process completion
Fixed bash tool occasionally hanging after command completion when background jobs keep stdout/stderr open
Fixed crash when auto-reading @mentions for very large files by skipping content injection with an explicit "skipped" note
Improved bash tool output draining after foreground completion to reduce tail output truncation

[11.8.0] - 2026-02-10

Added

Added ctx.reload() method to extension command context to reload extensions, skills, prompts, and themes from disk
Added ctx.ui.pasteToEditor() method to paste text into the editor with proper handling (e.g., large paste markers in interactive mode)
Added extension UI sub-protocol for RPC mode enabling dialog methods (select, confirm, input, editor) and fire-and-forget UI methods via client communication
Added support for tilde (~) expansion in custom skill directory paths
Added example extension demonstrating ctx.reload() usage with both command and LLM-callable tool patterns

Changed

Changed ctx.hasUI behavior: now true in RPC mode (previously false), with dialog methods working via extension UI sub-protocol
Changed warning output for invalid CLI arguments to use structured logging instead of console.error
Changed help text to indicate command-specific help is available via <command> --help
Changed tool result event handlers to chain like middleware, allowing each handler to see and modify results from previous handlers with partial patch support

Fixed

Fixed archive extraction security vulnerability by validating that extracted paths do not escape the extraction directory
Fixed archive format validation to reject unsupported formats before extraction attempt
Fixed archive extraction error handling to provide clear error messages on failure

[11.7.0] - 2026-02-07

Changed

Enhanced error messages for failed Python cells to include full combined output context instead of just the error message
Updated error cell output styling to use error color theme instead of standard tool output color for better visual distinction

Fixed

Improved error handling in Python cell execution to preserve and display combined output from previous cells when an error occurs
Fixed tab character rendering in Python tool output display to properly format whitespace in cell output and status events

[11.6.1] - 2026-02-07

Fixed

Fixed potential crash when rendering results with undefined details.results

[11.6.0] - 2026-02-07

Fixed

Fixed task tool renderer not sanitizing tabs, causing visual holes in TUI output
Fixed task tool expanded view showing redundant <swarm_context> block that is shared across all tasks
Fixed assistant message spacer appearing before tool executions when no visible content follows thinking block
Fixed extension runner emit() type safety with narrowed event/result types
Fixed extension runner tool_result event chaining across multiple extensions via dedicated emitToolResult()
Fixed queued messages not delivered after auto-compaction completes

Added

Added /quit slash command as alias for /exit
Added per-model overrides (modelOverrides) in models.json for customizing built-in model properties
Added mergeCustomModels to merge custom models with built-ins by provider+id instead of replacing

[11.5.2] - 2026-02-07

Fixed

Fixed TUI crash when ask tool renders long user input exceeding terminal width by using Text component for word wrapping instead of raw line output
Fixed TUI crash when todo_write tool renders long todo content exceeding terminal width by using Text component for word wrapping instead of truncation

[11.5.0] - 2026-02-06

Added

Added terminal breadcrumb tracking to remember the last session per terminal, enabling --continue to work correctly with concurrent sessions in different terminals

Changed

Changed screenshot format to always use PNG instead of supporting JPEG with quality parameter
Changed default extract_readable format from text to markdown
Changed screenshot storage to use temporary directory with Snowflake IDs instead of artifacts directory
Changed ResizedImage interface to return buffer as Uint8Array with lazy-loaded base64 data getter for improved memory efficiency

Removed

Removed JPEG quality parameter from screenshot options
Removed format selection for screenshots (now PNG only)
Removed ability to save screenshots to custom paths or artifacts directory

[11.4.1] - 2026-02-06

Fixed

Fixed tab character display in error messages and bash tool output by properly replacing tabs with spaces

[11.4.0] - 2026-02-06

Added

Visualize leading whitespace (indentation) in diff output with dim glyphs—tabs display as → and spaces as · for improved readability

Fixed

Fixed patch applicator to correctly handle context-only hunks (pure context lines between @@ markers) without altering indentation in tab-indented files
Fixed indentation conversion logic to infer tab width from space-to-tab patterns using linear regression (ax+b model) when pattern uses spaces and actual file uses tabs
Fixed tab character rendering in tool output previews and code cell displays, ensuring tabs are properly converted to spaces for consistent terminal display
Fixed newSession() to properly await session manager operations, ensuring new session is fully initialized before returning
Fixed session formatting to use XML structure for tools and tool invocations instead of YAML, improving compatibility with structured output parsing

[11.3.0] - 2026-02-06

Added

Added resumption hint printed to stderr on session exit showing command to resume the session (e.g., Resume this session with claude --resume <session-id>)
New BlobStore class for content-addressed storage of large binary data (images) externalized from session files
New getBlobsDir() function to get path to blob store directory
Support for externalizing large images to blob store during session persistence, reducing JSONL file size
New blob reference format (blob:sha256:<hash>) for tracking externalized image data in sessions
Exported ModeChangeEntry type for tracking agent mode transitions
Support for restoring plan mode state when resuming sessions
New appendModeChange() method in SessionManager to record mode transitions
New mode and modeData fields in SessionContext to track active agent mode
Support for PI_PACKAGE_DIR environment variable to override package directory (useful for Nix/Guix store paths)
New keybindings for session management: newSession, tree, fork, and resume actions
Support for shell command execution in configuration values (API keys, headers) using ! prefix, with result caching
New clearOnShrink display setting to control whether empty rows are cleared when content shrinks
New SlashCommandInfo, SlashCommandLocation, and SlashCommandSource types for extension slash command discovery
New getCommands() method in ExtensionAPI to retrieve available slash commands
New switchSession() action in ExtensionCommandContext to switch between sessions
New SwitchSessionHandler type for extension session switching handlers
New getSystemPrompt() method in ExtensionUIContext to access current system prompt
New getToolsExpanded() and setToolsExpanded() methods in ExtensionUIContext for tool output expansion control
New WriteToolCallEvent type for write tool call events
New isToolCallEventType() type guard for tool call events
Support for image content in RPC steer and followUp commands
New GitSource type and parseGitUrl() function for parsing git URLs in plugin system
Tool input types exported: BashToolInput, FindToolInput, GrepToolInput, ReadToolInput, WriteToolInput
Support for @ prefix normalization in file paths (strips leading @ character)
New parentSessionPath field in SessionInfo to track forked session origins
Skill file relative path resolution against skill directory in system prompt
Support for Termux/Android package installation guidance for missing tools
Support for puppeteer query handlers (aria/, text/, xpath/, pierce/) in selector parameters across all browser actions
Automatic normalization of legacy p- prefixed selectors (p-aria/, p-text/, p-xpath/, p-pierce/) to modern puppeteer query handler syntax
Improved click action with intelligent element selection that prioritizes visible, actionable candidates and retries until timeout
Enhanced actionability checking for click operations, validating visibility, pointer events, opacity, viewport intersection, and element occlusion

Changed

Modified --resume flag to accept optional session ID or path (e.g., --resume abc123 or --resume /path/to/session.jsonl), with session picker shown when no value provided
Consolidated --session flag as an alias for --resume with value for improved CLI consistency
Removed read tool grouping reset logic that was breaking grouping when text or thinking blocks appeared between tool calls
Image persistence now externalizes images ≥1KB to content-addressed blob store instead of compressing inline
Session loading now automatically resolves blob references back to base64 image data
Session forking now resolves blob references in copied entries to ensure data integrity
Screenshot tool now automatically compresses images for API content using the same resizing logic as pasted images, reducing payload size while maintaining quality
Improved text truncation across tool renderers to respect terminal width constraints and prevent output overflow
Enhanced render caching to include width parameter for accurate cache invalidation when terminal width changes
HTML export filter now treats mode_change entries as settings entries alongside model changes and thinking level changes
Replaced ellipsis string (...) with Unicode ellipsis character (…) throughout UI text and truncation logic for improved typography
Improved render performance by introducing caching for tool output blocks and search results to avoid redundant text width and padding computations
Enhanced read tool grouping to reset when non-tool content (text/thinking blocks) appears between read calls, preventing unintended coalescing
Improved string preview formatting in scalar values to show line counts and truncation indicators for multi-line strings
Refactored tool execution component to use shared mutable render state for spinner frames and expansion state, reducing closure overhead
Enhanced error handling in tool renderers with logging for renderer failures instead of silent fallbacks
Made shell command execution in configuration values asynchronous to prevent blocking the TUI
Improved @ prefix normalization to only strip leading @ for well-known path syntaxes (absolute paths, home directory, internal URL shorthands) to avoid mangling literal paths
Enhanced git URL parsing to strip credentials from repository URLs and validate URL-encoded hash fragments
Improved null data handling in task submission to preserve agent output when submit_result is called with null/undefined data, enabling fallback text extraction instead of discarding output
Updated default model IDs across providers: Claude Sonnet 4.5 → Claude Opus 4.6, Gemini 2.5 Pro → Gemini 3 Pro variants, and others
Made model definition fields optional with sensible defaults for local models (Ollama, LM Studio, etc.)
Modified custom tool execute signature to reorder parameters: (toolCallId, params, signal, onUpdate, ctx) instead of (toolCallId, params, onUpdate, ctx, signal)
Changed --version and --list-models flags to exit with process.exit(0) instead of returning
Improved --export flag to exit with process.exit(0) on success
Enhanced tree selector to preserve last selected ID across filter changes
Modified tree navigation to use real leaf ID instead of skipping metadata entries
Improved footer path truncation logic to prevent invalid truncation at boundary
Enhanced model selector to display selected model name when no matches found
Improved RPC client steer() and followUp() methods to accept optional image content
Updated extension loader to check for explicit extension entries in root directory before discovering subdirectories
Removed line limiting in custom message component when collapsed
Improved API key resolution to support shell command execution via resolveConfigValue()
Enhanced session branching to preserve parent session path reference
Updated selector parameter descriptions to document support for CSS selectors and puppeteer query handlers
Modified viewport handling in headless mode to respect custom viewport parameters while disabling viewport in headed mode for better window management
Improved click action to use specialized text query handler logic with retry mechanism for better reliability with dynamic content

Fixed

Fixed background color stability in output blocks when inner content contains SGR reset sequences, preventing background color from being cleared mid-line
Fixed spurious ellipsis appended to output lines that were already padded to terminal width by trimming trailing spaces before truncation check
Fixed config file parsing to properly handle missing files instead of treating them as errors
Fixed truncation indicator in truncate tool to use ellipsis character (…) instead of verbose '[truncated]' suffix
Fixed concurrent shell command execution by de-duplicating in-flight requests for the same command
Fixed git URL parsing to properly handle URL-encoded characters in hash fragments and reject invalid encodings
Fixed task executor to properly handle agents calling submit_result with null data by treating it as missing and attempting to extract output from conversation text rather than silently failing
Fixed HTML export template to safely handle invalid argument types in tool rendering
Fixed path shortening in HTML export to handle non-string paths
Fixed custom message rendering to properly display full content without artificial line limits
Fixed tree navigation to only restore editor text when editor is empty
Fixed session creation to properly track parent session when forking
Fixed thinking level initialization to only append change entry for new sessions without existing thinking entries
Fixed tool expansion state management to properly propagate through UI context
Fixed click action to properly handle text/ query handlers with timeout and retry logic instead of failing immediately
Fixed viewport application to only apply when in headless mode or when explicitly requested, preventing conflicts in headed browser mode

Security

Added support for shell command execution in configuration values with caching to enable secure credential resolution patterns

[11.2.1] - 2026-02-05

Fixed

Fixed CLI invocation with flags only (e.g. pi --model=codex) to route to the default command instead of erroring

[11.2.0] - 2026-02-05

Added

Added omp commit command to generate commit messages and update changelogs with --push, --dry-run, --no-changelog, and model override flags
Added omp config command to manage configuration settings with actions: list, get, set, reset, path
Added omp grep command to test grep tool with pattern matching, glob filtering, context lines, and output modes
Added omp jupyter command to manage the shared Jupyter gateway with status and kill actions
Added omp plugin command to manage plugins with install, uninstall, list, link, doctor, features, config, enable, and disable actions
Added omp setup command to install dependencies for optional features like Python
Added omp shell command for interactive shell console with working directory and timeout configuration
Added omp stats command to view usage statistics with dashboard server, JSON output, and summary options
Added omp update command to check for and install updates with force and check-only modes
Added omp web-search command (alias omp q) to test web search providers with provider selection, recency filtering, and result limits
Migrated CLI from custom argument parser to oclif framework for improved command structure and help system
Added omp q CLI subcommand for testing web search providers with query, provider, recency, and limit options
Added web search provider information API with authentication requirements and provider metadata
Added support for hour recency filter option in Perplexity web search
Support for image file mentions—images are now automatically detected, resized, and attached when referenced with @filepath syntax
Image dimension information displayed in file mention UI to show image properties alongside text files

Changed

Refactored web search provider system to use individual provider classes in separate files for improved maintainability
Moved SearchProvider base class and SearchParams interface to dedicated providers/base.ts module
Updated web search execution to pass maxOutputTokens, numSearchResults, and temperature parameters to providers
Changed Perplexity search context size from 'high' to 'medium' and added search classifier, reasoning effort, and language preference settings
Increased Perplexity default max tokens from 4096 to 8192 for more comprehensive responses
Updated Anthropic and Gemini search providers to support max_tokens and temperature parameters for finer control over response generation
Simplified AuthStorage.create() to accept direct agent.db path
Renamed web search types and exports for consistency: WebSearchProvider → SearchProviderId, WebSearchResponse → SearchResponse, WebSearchTool → SearchTool, and related functions
Refactored web search provider system to use centralized provider registry with getSearchProvider() and resolveProviderChain() for improved provider management
Updated web search system prompt to emphasize comprehensive, detailed answers with concrete data and specific examples over brevity
Simplified Exa API key discovery to check environment variables only, removing .env file fallback logic
Refactored ModelRegistry instantiation to use direct constructor instead of discoverModels() helper function across codebase
Refactored CLI entry point to use oclif command framework instead of custom subcommand routing
Reorganized subcommands into individual command files under src/commands/ directory for better maintainability
Updated extension flag handling to parse raw arguments directly instead of using custom flag definitions
Refactored web search provider definitions into centralized provider-info module for better maintainability
Updated web search result rendering to support long-form answers with text wrapping in CLI mode
Removed related questions section from web search result rendering
Updated Perplexity API types to support extended message content formats including images, files, and PDFs
Updated Perplexity search to use 'pro' search type for improved search quality and relevance
File mention messages now support both text content and image attachments, with optional line count for text files
Updated file mention processing to respect image auto-resize settings

Removed

Removed legacy auth.json file—credentials are stored exclusively in agent.db

Fixed

Fixed type handling in model selector error message display to properly convert error objects to strings
Fixed web search to use search results when Perplexity API returns no citations, ensuring search results are always available to users
Fixed model switches deferred during streaming to apply correctly when the stream completes, preventing model changes from being lost
Fixed plan mode toggles during streaming to inject plan-mode context immediately, preventing file edits while in plan mode
Fixed plan mode model switches during streaming to defer model changes until the current turn completes

[11.1.0] - 2026-02-05

Added

Added sortDiagnostics() utility function to sort diagnostics by severity, location, and message for consistent output ordering
Added task.isolation.enabled setting to control whether subagents run in isolated git worktrees
Added dynamic task schema that conditionally includes isolated parameter based on isolation setting
Added openInEditor() utility function to centralize external editor handling with support for custom file extensions and stdio configuration
Added getEditorCommand() utility function to retrieve the user's preferred editor from $VISUAL or $EDITOR environment variables

Changed

Changed diagnostic output to sort results by severity (errors first), then by file location and message for improved readability
Changed task tool to validate isolation setting and reject isolated parameter when isolation is disabled
Changed task API to use assignment field instead of args for per-task instructions, with shared context prepended to every task
Changed task template rendering to use structured context/assignment separation with <swarm_context> wrapper instead of placeholder-based substitution
Changed task item schema to require assignment string (complete per-task instructions) instead of optional args object
Changed TaskItem to remove args field and add assignment field for clearer per-task instruction semantics
Changed agent frontmatter to use thinking-level field name instead of thinkingLevel for consistency
Refactored task rendering to display full task text instead of args in progress and result views
Changed SubmenuSettingDef.getOptions() method to options getter property for cleaner API access
Converted static option providers from functions to direct array definitions for improved performance
Added createSubmenuSettingDef() helper function to support both static and dynamic option providers
Modified setThinkingLevel() API to accept optional persist parameter (defaults to false) for controlling whether thinking level changes are saved to settings
Refactored hook editor and input controller to use shared external editor utilities, reducing code duplication

Removed

Removed context parameter from ExecutorOptions — context now prepended at template level before task execution
Removed args field from AgentProgress and SingleResult interfaces
Removed placeholder-based template rendering in favor of structured context/assignment model

[11.0.3] - 2026-02-05

Added

Added new subcommands to help text: commit for AI-assisted git commits, stats for AI usage statistics dashboard, and jupyter for managing the shared Jupyter gateway
Added grep subcommand to help text for testing the grep tool
Added browser tool documentation for browser automation using Puppeteer
Added todo_write tool documentation for managing todo and task lists
Added documentation for additional LLM provider API keys (Groq, Cerebras, xAI, OpenRouter, Mistral, z.ai, MiniMax, OpenCode, Cursor, Vercel AI Gateway) in environment variables reference
Added documentation for cloud provider configuration (AWS Bedrock, Google Vertex AI) in environment variables reference
Added documentation for search provider API keys (Perplexity, Anthropic Search) in environment variables reference
Added documentation for model override environment variables (PI_SMOL_MODEL, PI_SLOW_MODEL, PI_PLAN_MODEL) in CLI help text
Added comprehensive environment variables reference documentation at docs/environment-variables.md covering API keys, configuration, debugging, and testing variables
Added theme system with 44 customizable color tokens, two built-in themes (dark/light), and auto-detection based on terminal background
Added /theme command to interactively select and switch between themes
Added support for custom themes in ~/.pi/agent/themes/*.json with live editing - changes apply immediately when files are saved
Added userMessageText theme token for customizing user message text color
Added toolTitle and toolOutput theme tokens for separate coloring of tool execution box titles and output

Changed

Updated help text to reflect expanded tool availability - default now enables all tools instead of just read, bash, edit, write
Updated available tools list in help documentation to include python, notebook, task, fetch, web_search, browser, and ask
Simplified main description in help text from 'AI coding assistant with read, bash, edit, write tools' to 'AI coding assistant'
Updated --tools option documentation to clarify default behavior and list all available tools
Changed all environment variable access from process.env to Bun.env throughout the codebase for Bun runtime compatibility
Updated documentation to reference Bun.env instead of process.env in examples and comments

Fixed

Fixed Text component to properly implement invalidate() method, ensuring theme changes apply correctly to all UI elements
Fixed TruncatedText component to properly pad all lines to exactly match the specified width, preventing rendering artifacts
Fixed TruncatedText component to stop at the first newline and only display the first line
Fixed invalid or malformed themes to fall back gracefully to dark theme instead of crashing the application

[11.0.2] - 2026-02-05

Fixed

Fixed role model cycling to expand role aliases (e.g., roles pointing at pi/plan) so slow/default/smol cycles resolve correctly

[11.0.0] - 2026-02-05

Added

Added UI dropdown options for task.maxRecursion Depth setting with presets (Unlimited, None, Single, Double, Triple)
Added UI dropdown options for grep.contextBefore setting with presets (0-5 lines)
Added UI dropdown options for grep.contextAfter setting with presets (0-10 lines)
Added task.maxRecursionDepth setting to control how many levels deep subagents can spawn their own subagents (0=none, 1=one level, 2=two levels, -1=unlimited)
Added support for nested task artifact naming with parent task prefixes (e.g., "0-Auth.1-Subtask") to organize hierarchical task outputs
Added taskDepth and parentTaskPrefix options to CreateAgentSessionOptions for tracking subagent recursion depth and organizing nested artifacts
Added task.maxConcurrency setting to control concurrent limit for subagents (default: 32)
Added UI options for task concurrency configuration with presets from unlimited to 64 tasks
Added support for loading skills from ~/.agents/skills

Changed

Simplified task.maxRecursionDepth description in settings UI to remove specific value examples
Made thinking level persistence optional via persist parameter in setThinkingLevel() method, allowing temporary thinking level changes without saving to settings
Updated thinking level cycling to no longer persist changes to settings, enabling quick iteration through thinking levels without modifying user preferences
Replaced nanoid with Snowflake for ID generation throughout codebase for improved performance and collision resistance
Updated session ID format in documentation from nanoid to snowflake hex string (e.g., "a1b2c3d4e5f60001")
Renamed environment variable prefix from OMP_ to PI_ throughout codebase (e.g., OMP_DEBUG_STARTUP → PI_DEBUG_STARTUP, OMP_PYTHON_GATEWAY_URL → PI_PYTHON_GATEWAY_URL)
Removed env setting from configuration schema; environment variables are no longer automatically applied from settings
Changed venvPath property in PythonRuntime from nullable to optional (returns undefined instead of null)
Simplified notification settings from protocol-specific options (bell, osc99, osc9) to simple on/off toggle for completion.notify and ask.notify
Moved notification protocol detection and sending to TERMINAL API from local utility functions
Changed task tool spawns configuration from "explore" to "*" to allow subagents to spawn any agent type
Changed system prompt to enable parallel delegation guidance for all agents (removed coordinator-only restriction)
Changed task tool to automatically disable itself when maximum recursion depth is reached, preventing infinite nesting
Changed task concurrency from hardcoded constant to configurable setting via task.maxConcurrency
Changed concurrency limit calculation to support unlimited concurrency when set to 0

Removed

Removed nanoid dependency from package.json
Removed terminal-notify.ts utility module with detectNotificationProtocol(), sendNotification(), and isNotificationSuppressed() functions
Removed MAX_PARALLEL_TASKS constant and associated task count validation limit

Fixed

Fixed MCP tool name generation to properly sanitize server and tool names, preventing invalid characters and duplicate prefixes in tool identifiers
Fixed task ID display formatting to show hierarchical structure for nested tasks (e.g., "0.1 Auth>Subtask" instead of "0-Auth.1-Subtask")
Improved frontmatter parsing error messages to include source context for better debugging

[10.6.1] - 2026-02-04

Added

Added commit model role for dedicated commit message generation
Exported resolveModelOverride function from model resolver for external use

Changed

Updated model role resolution to accept optional roleOrder parameter for custom role priority
Made tag and color properties optional in ModelRoleInfo interface
Updated model selector to safely handle roles without tag or color definitions
Refactored role label display to use centralized MODEL_ROLES registry instead of hardcoded strings
Refactored model role system to use centralized MODEL_ROLES registry with consistent tag, name, and color definitions
Simplified model role resolution to use MODEL_ROLE_IDS array instead of hardcoded role checks
Updated model selector to dynamically generate menu actions from MODEL_ROLES registry

Removed

Removed support for omp/ model role prefix; use pi/ prefix instead

[10.6.0] - 2026-02-04

Breaking Changes

Removed output_mode parameter from grep tool—results now always use content mode with formatted match output
Renamed grep context parameters from context_pre/context_post to pre/post
Removed n (show line numbers) parameter—line numbers are now always displayed in grep results

Added

Added Jina as a web search provider option alongside Exa, Perplexity, and Anthropic
Added support for Jina Reader API integration with automatic provider detection when JINA_API_KEY is configured

Changed

Reformatted grep output to display matches grouped by file with numbered match headers and aligned context lines
Updated grep output to use >> prefix for match lines and aligned spacing for context lines for improved readability
Changed multiline matching to automatically enable when pattern contains literal newlines ( )
Split grep context parameter into separate context_pre and context_post options for independent control of lines before and after matches
Updated grep tool to use configurable default context settings from grep.contextBefore and grep.contextAfter configuration
Added configurable grep context defaults and reduced the default to 1 line before, 3 lines after
Enabled the browser tool by default

Removed

Removed filesWithMatches and count output modes from grep tool

[10.5.0] - 2026-02-04

Breaking Changes

Changed ask tool to require questions array parameter; single-question mode with question, options, multi, and recommended parameters is no longer supported
Removed support for local Python kernel gateway startup; shared gateway is now required

Added

Added browser tool powered by Ulixee Hero with support for navigation, DOM interaction, screenshots, and readable content extraction
Added /browser command to toggle browser headless vs visible mode in interactive sessions
Added browser.enabled and browser.headless settings to control browser automation behavior
Added Python prelude caching to improve startup performance by storing compiled prelude helpers and module metadata
Added OMP_DEBUG_STARTUP environment variable for conditional startup performance debugging output
Added autonomous memory system with storage, memory tools, and context injection

Changed

Updated task tool guidance to enforce small, well-defined task scope with maximum 3-5 files per task to prevent timeouts and improve parallel execution
Updated browser viewport to use 1.25x device scale factor for improved rendering on high-DPI displays
Modified device pixel ratio detection to respect actual screen capabilities instead of forcing 1x ratio
Updated system prompt guidance to state assumptions and proceed without asking for confirmation, reducing unnecessary round-trips
Tightened ask tool conditions to require multiple approaches with significantly different tradeoffs before prompting user
Strengthened ask tool guidance to default to action and only ask when genuinely blocked by decisions with materially different outcomes
Changed refactor workflow to automatically remove now-unused elements and note removals instead of asking for confirmation
Enforced exclusive concurrency mode for all file-modifying tools (edit, write, bash, python, ssh, todo-write) to prevent concurrent execution conflicts
Updated ask tool guidance to prioritize proactive problem-solving and default to action, asking only when truly blocked by decisions that materially change scope or behavior
Changed Python kernel initialization to require shared gateway mode; local gateway startup has been removed
Changed shared gateway error handling to retry on server errors (5xx status codes) before failing

Fixed

Fixed glob search returning no results when all files are ignored by gitignore by automatically retrying without gitignore filtering

[10.3.2] - 2026-02-03

Added

Added renderCall and renderResult methods to MCP tools for structured TUI display of tool calls and results
Added new mcp/render.ts module providing JSON tree rendering for MCP tool output with collapsible/expandable views

Changed

Updated renderResult signature in custom tools and extensions to accept optional args parameter for context-aware rendering
Changed environment variable from ENV_AGENT_DIR constant to hardcoded OMP_CODING_AGENT_DIR string in config and CLI help text
Fixed method binding in extension and hook tool wrappers to preserve this context for renderCall and renderResult methods

[10.3.1] - 2026-02-03

Fixed

Fixed timeout handling in LSP write-through operations to properly clear formatter and diagnostics results when operations exceed the 10-second timeout

[10.3.0] - 2026-02-03

Removed

Removed shellForceBasic setting that forced bash/sh shell selection
Removed bash.persistentShell experimental setting for shell session reuse

[10.2.3] - 2026-02-02

Added

Added find.enabled, grep.enabled, ls.enabled, notebook.enabled, fetch.enabled, web_search.enabled, lsp.enabled, and calc.enabled settings to control availability of individual tools
Added conditional tool documentation in system prompt that dynamically lists only enabled specialized tools
Added todos.enabled setting to control availability of the todo_write tool for task tracking
Added tools field to agent frontmatter for declaring agent-specific tool capabilities

Changed

Consolidated symbols action to handle both file-based document symbols and workspace symbol search (query-based)
Consolidated diagnostics action to handle both single-file and workspace-wide diagnostics (no file = workspace)
Simplified reload action to gracefully reload language server with fallback to kill
Updated LSP tool documentation to reflect simplified operation set and consolidated actions
Reorganized settings tabs from 8 to 9 tabs with clearer categorization: Display, Agent, Input, Tools, Config, Services, Bash, LSP, and TTSR
Moved behavior-related settings to new Agent tab for better organization
Moved input/interaction settings to new Input tab
Moved tool configuration settings to new Config tab
Moved provider and service settings to new Services tab
Added visual icons to settings tabs using theme symbols for improved UI clarity
Changed default settings tab from Behavior to Display on startup
Updated read tool to handle directory paths by returning formatted listings with modification times instead of redirecting to ls
Updated tool documentation to reflect that read now handles both files and directories
Updated system prompt tool precedence section to conditionally display only available specialized tools based on enabled settings
Renamed todo completion settings from todoCompletion.* to todos.reminders.* and todos.enabled for clearer organization
Updated todo reminder logic to check both todos.reminders and todos.enabled settings independently

Removed

Removed Rust-analyzer specific LSP operations: flycheck, expand_macro, ssr, runnables, related_tests, and reload_workspace
Removed workspace_diagnostics action; use diagnostics without file parameter instead
Removed workspace_symbols action; use symbols with query parameter and no file instead
Removed actions, incoming_calls, and outgoing_calls LSP operations
Removed replacement, kind, action_index, end_line, and end_character parameters from LSP tool
Removed Python prelude helper functions: pwd(), mkdir(), ls(), head(), tail(), sh(), cat(), touch(), wc(), basenames(), and batch()
Removed type guard functions (isBashToolResult, isReadToolResult, isEditToolResult, isWriteToolResult, isGrepToolResult, isFindToolResult, isLsToolResult) from public API exports
Removed ls tool—directory listing is now handled by the read tool
Removed ls.enabled setting and related configuration options
Removed bashInterceptor.simpleLs setting that redirected simple ls commands to the dedicated tool
Removed project tree snapshot generation from system prompt (unused feature)

Fixed

Fixed tool parameter schemas displaying internal TypeBox metadata fields in system prompt

[10.2.1] - 2026-02-02

Breaking Changes

Removed strippedRedirect field from NormalizedCommand interface returned by normalizeBashCommand()
Removed automatic stripping of 2>&1 stderr redirections from bash command normalization

[10.1.0] - 2026-02-01

Added

Added work scheduling profiler to debug menu for analyzing CPU scheduling patterns over the last 30 seconds
Added support for work profile data in report bundles including folded stacks, summary, and flamegraph visualization

[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 ith 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
Removed legacy auth.json file—credentials are stored exclusively in agent.db
Removed legacy auth.json file—credentials are stored exclusively in 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 SearchProviderError 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

424 KiB Raw Blame History Unescape Escape

Changelog

[Unreleased]

Added

Changed

Removed

Fixed

[13.19.0] - 2026-04-05

Added

Changed

Removed

Fixed

[13.18.0] - 2026-04-02

Breaking Changes

Added

Changed

Fixed

[13.17.5] - 2026-04-01

Added

Changed

Removed

[13.17.4] - 2026-04-01

Added

[13.17.3] - 2026-04-01

Added

Changed

[13.17.2] - 2026-04-01

Added

Changed

Fixed

[13.17.1] - 2026-04-01

Removed

Fixed

[13.17.0] - 2026-03-30

Added

Changed

Removed

Fixed

[13.16.5] - 2026-03-29

Fixed

[13.16.4] - 2026-03-28

Changed

Fixed

[13.16.1] - 2026-03-27

Added

Changed

[13.16.0] - 2026-03-27

Added

Changed

[13.15.3] - 2026-03-26

Added

[13.15.0] - 2026-03-23

Breaking Changes

Added

Changed

Removed

Fixed

Fixed

Added

[13.14.0] - 2026-03-20

Added

Changed

Fixed

[13.13.2] - 2026-03-18

Added

[13.13.1] - 2026-03-18

Added

[13.13.0] - 2026-03-18

Added

Changed

[13.12.10] - 2026-03-17

Added

Changed

[13.12.9] - 2026-03-17

Added

Changed

Fixed

[13.12.8] - 2026-03-16

Breaking Changes

Added

424 KiB

Raw Blame History