Commit Graph
80 Commits
Author SHA1 Message Date
can1357 138e7e1d91 fix(interactive-mode): corrected mic cursor width measurement to prevent TUI overflow
- 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).
- Extracted mic cursor styling into dedicated method to consolidate color and width calculation logic.

Fixes #484
2026-03-20 23:40:48 +01:00
can1357 20cdf31b9f feat: display session title in terminal tab
fixes #461
2026-03-18 22:46:22 +01:00
can1357 fb76484aa4 fix: route all app-level shortcuts through KeybindingsManager
fixes #468
2026-03-18 22:46:22 +01:00
2825c894f5 feat: session deletion (#448)
* feat: session deletion

* better session deletion cleanup error handling

* fix: complete deletion including artifacts
fix: native confirmation for session deletion

* even better native configmation for session picker

* fix(coding-agent): detach active session before deletion

* fix(coding-agent): keep failed session deletes visible

* fix(coding-agent): await session delete command

* fix(coding-agent): surface session artifact cleanup failures

---------

Co-authored-by: can1357 <me@can.ac>
Co-authored-by: Can Bölük <can1357@users.noreply.github.com>
2026-03-17 14:51:21 +01:00
lukeandGitHub c0f14aa248 feat(coding-agent): auto-clear completed todo tasks (#435)
- Schedule auto-removal of completed/abandoned tasks after ~1 minute delay
- Strip already-done tasks when restoring session from branch history
- Add todo_auto_clear event to trigger UI refresh on removal
- Add blank line before Todos header for visual spacing
2026-03-15 19:02:02 +01:00
maximharandGitHub 952db9fd93 feat: add ephemeral /btw side-question panel (#399)
* feat: add ephemeral /btw side-question panel

* fix: preserve /btw live context and payload hooks

* fix: send /btw question through session pipeline
2026-03-14 10:42:26 +01:00
can1357 ffa208adcf feat(modes): added /copy subcommands for flexible code and command extraction
- Added `/copy` command subcommands (code, all, cmd, last) for flexible code block and command copying.
- Added support for copying last executed bash or python command via `/copy cmd` subcommand.
- Refactored handleCopyCommand() to route subcommands with dedicated private methods for each copy operation.
- Added regex-based code block extraction from markdown with fallback warnings for missing blocks.
2026-03-11 03:08:51 +01:00
486fd4c753 refactor(theme): replace CoreFoundation FFI with OSC 11 for machine-agnostic dark/light detection (#347)
* refactor(theme): replace CoreFoundation FFI + Mode 2031 with OSC 11 for dark/light detection

Replace the 415-line Rust CoreFoundation FFI module and Mode 2031-only
detection with OSC 11 background color queries — the machine-agnostic
method used by Neovim, fish, bat, and terminal-colorsaurus.

Detection stack:
- OSC 11 query + DA1 sentinel at startup (works over SSH, mobile clients)
- Mode 2031 subscribe: re-queries OSC 11 with 100ms debounce (Neovim
  convention) instead of trusting binary dark/light value directly
- 2s OSC 11 poll for terminals without Mode 2031 (Warp, Alacritty,
  WezTerm, iTerm2); self-disables once Mode 2031 fires
- COLORFGBG env var fallback (free, no I/O)
- macOS defaults read fallback (Zellij edge case)

Deleted:
- crates/pi-natives/src/appearance.rs (414 lines of unsafe FFI)
- packages/natives/src/appearance/ (66 lines of TS bindings)
- macOS appearance observer and SIGWINCH coupling in theme.ts

Net: -424 lines. Rust crate lighter, detection works over SSH.

* fix(theme): ignore bogus zellij osc11 dark reading

* fix(theme): scope macOS fallback to broken terminal paths

* fix(tui): swallow DA1 sentinels for OSC 11 probes

---------

Co-authored-by: can1357 <me@can.ac>
2026-03-11 00:58:17 +01:00
can1357 1a5bbc3e51 feat(coding-agent): added details field to TodoItem for storing implementation specifics
- Added optional `details` field to TodoItem type for storing implementation specifics, file paths, and edge cases.
- Enhanced todo item display to show multi-line details with automatic indentation in interactive and reminder modes.
- Updated eager-todo system prompt to enforce separation of short task content (5-10 words) from detailed implementation information.
- Extended TodoWriteTool to support creating and updating tasks with details field via add_task and update operations.
- Added comprehensive test coverage for details field handling across todo operations (replace, add_task, update).
2026-03-11 00:56:54 +01:00
can1357 f256376e90 feat(coding-agent): added cancellation support for pending user submissions
- Introduced SubmittedUserInput type to track submission state including cancelled and started flags. Added startPendingSubmission, cancelPendingSubmission, markPendingSubmissionStarted, and finishPendingSubmission methods to manage the lifecycle of user input submissions. Enhanced escape key handling to prioritize canceling pending optimistic submissions before aborting active sessions.
2026-03-10 06:25:38 +01:00
can1357 e019a3e352 refactor(coding-agent): restructured loading animation lifecycle into ensureLoadingAnimation
- Extracted loading animation lifecycle management into centralized ensureLoadingAnimation() method.
- Consolidated duplicate loading animation setup across event-controller and interactive-mode into single reusable method.
- Updated showError() to properly clean up loading animation state when errors occur.
- Added comprehensive test coverage for InputController escape key behavior with optimistic submission.
2026-03-10 05:51:09 +01:00
ravshansboxandGitHub c4715a918a Fix delayed display of submitted user messages (#312) 2026-03-10 02:42:46 +01:00
can1357 aa18e3f26d feat: add hash prompt actions
Fixes #283
2026-03-09 15:38:39 +01:00
can1357 8e3e0ebf9e feat: introduced Effort enum and ThinkingConfig for model-aware reasoning
- Introduced Effort enum and ThinkingConfig metadata for per-model reasoning capabilities with min/max effort levels.
- Migrated thinking level API from string-based ThinkingLevel to structured Effort enum across agent and AI packages.
- Added model-thinking module with effort mapping, policy application, and semantic versioning utilities for provider-specific thinking modes.
- Removed supportsXhigh() function and replaced effort clamping with model-aware validation using ThinkingConfig metadata.
- Expanded models.json with thinking configuration objects for 50+ models including Claude, Gemini, and OpenAI variants.
- Added Python analysis scripts for edit tool usage patterns and tool invocation stream processing.
2026-03-06 12:35:01 +01:00
can1357 fd5c1e9115 fix(coding-agent): removed unnecessary awaits from non-promise function calls
- Removed await from stream() calls that return async iterables directly.
- Removed await from synchronous utility functions like findApiKey(), resolvePythonRuntime(), and getToolPath().
- Removed await from prerenderMermaid() and findExaKey() calls that don't require awaiting.
2026-03-04 02:09:12 +01:00
can1357 bce8d4e4c9 feat(coding-agent): added Kagi login and cleaner search formatting
- Added `/login <provider>` command for direct OAuth provider login with automatic selector routing.
- Added Kagi API key authentication support as new OAuth provider across ai and coding-agent packages.
- Added optional `providerId` parameter to `showOAuthSelector()` for direct provider selection without manual input.
- Simplified web search result formatting by removing empty sections (Answer, Sources, Meta, Related).
- Fixed MCP tool schema dereferencing and Ajv validation warnings for non-standard format keywords.
- Refactored OAuth login/logout logic into extracted handler methods for improved maintainability.
2026-03-04 01:08:09 +01:00
can1357 4e0f8aace0 fix(coding-agent): corrected exit_plan_mode to abort turn before approval
- Fixed exit_plan_mode handler to abort active agent turn before opening plan approval selector, ensuring proper session cleanup.
- Added test to verify abort is called before handleExitPlanModeTool in exit_plan_mode event handling.
2026-03-01 20:29:31 +01:00
can1357 0fbd76d3fa feat(coding-agent/modes): added debug transcript export command to dump visible TUI conversation
- Added transcript export option to debug menu that writes visible TUI conversation to a temporary text file.
- Implemented handleDebugTranscriptCommand in CommandController to render chat messages, strip ANSI codes, and write to temp directory.
- Updated InteractiveModeContext interface and InteractiveMode to expose the new debug transcript command handler.
2026-03-01 08:53:49 +01:00
Kevin LoftisandGitHub 751ff62f8e Allow /plan to accept an inline prompt (#222)
/plan without args still toggles plan mode on/off as before.
/plan <prompt> enters plan mode and immediately starts planning
with the given prompt, skipping the extra enter-then-type step.
2026-02-28 18:45:03 +01:00
lederniermagicienandGitHub 8664af3a3c feat(theme): implement Mode 2031 for automatic dark/light theme switching (#196)
Add cross-platform terminal dark/light mode detection using the Mode 2031
VT extension (DECSET 2031). On startup, query the terminal's current
appearance with CSI ? 996 n, then subscribe to live appearance change
notifications with CSI ? 2031 h. When the OS or terminal switches between
dark and light mode, the terminal sends a DSR that triggers an automatic
theme re-evaluation.

Previously, detectTerminalBackground() only checked the COLORFGBG
environment variable once at launch — a static value that never updates
when the system appearance changes mid-session. The SIGWINCH listener
only fires on terminal resize, not on appearance changes.

Mode 2031 is supported by Ghostty, Kitty (0.38.1+), Contour (0.4.0+),
VTE/GNOME Terminal (0.82.0+), and tmux (3.6+). Unsupported terminals
silently ignore the escape sequences and fall back to the existing
COLORFGBG heuristic.
2026-02-28 05:26:38 +01:00
can1357 0e668a25ed fix: persist approved plan file to new session local directory
After plan approval, handleClearCommand() creates a new session with a
fresh artifacts directory. The local:// URL is session-scoped, so the
renamed plan file in the old session local dir was unreachable from
the execution session.

Write the plan content to the new session local dir after the session
switch so the titled plan artifact resolves correctly.
2026-02-26 09:45:23 +01:00
can1357 049a5a8a2c Merge PR #148 2026-02-26 09:16:56 +01:00
can1357 a83175c94c refactor: migrated imports to unified package root and consolidated skill discovery logic
- Consolidated @oh-my-pi/pi-utils subpath imports into single package root import across 100+ files.
- Moved tryParseJson utility from local web scrapers module to @oh-my-pi/pi-utils package for centralized JSON parsing.
- Renamed loadSkillsFromDir to scanSkillsFromDir and refactored skill discovery to use fs.promises.readdir instead of glob-based approach.
- Replaced custom parseJSON with tryParseJson across discovery modules for consistent error handling.
- Removed emitCustomToolSessionEvent method and cleanupSshResources function, consolidating shutdown logic into dispose method.
- Updated glob pattern construction to use GlobBuilder with literal_separator(true) for improved path handling.
2026-02-23 20:59:17 +01:00
julia 85219821ff feat(oauth): Enabled manual OAuth callbacks via slash command input
- Introduced OAuthManualInputManager and routed callback-server logins to await pasted redirect URLs with a visible tip.
- Extended /login slash command to submit redirect URLs, block overlapping logins, and covered manual callbacks in tests.
- Propagated onManualCodeInput through OAuth provider login helpers with a default authorization prompt.
- Resolved docs index generation paths using path.resolve relative to the script directory.
2026-02-23 06:21:32 +00:00
can1357 0298a88601 feat(coding-agent): added in-memory todo phase management to ToolSession API
- Added getTodoPhases() and setTodoPhases() methods to ToolSession API for in-memory todo phase management.
- Added getLatestTodoPhasesFromEntries() export to retrieve todo phases from session history entries.
- Changed todo state management from file-based (todos.json) to in-memory session cache with automatic persistence.
- Changed todo phases to sync from session branch history during branching and rewriting operations.
- Removed file-based todo loading logic and replaced with session-based todo phase retrieval throughout codebase.
2026-02-22 19:11:24 +01:00
can1357 2574d4c977 feat(todo): add phased todo ops and task statuses 2026-02-22 18:35:06 +01:00
can1357 cd5c9655aa refactor: renamed notes protocol to local
- Renamed the `notes://` protocol to `local://` for better clarity.
- Updated all internal references, prompts, and tool documentation.
- Migrated plan storage paths to use the new `local://` scheme.
2026-02-22 18:05:22 +01:00
can1357 563d6a0ab9 feat(coding-agent): introduced notes:// protocol for session-scoped artifact storage
- Replaced plan:// protocol with notes:// for session-scoped artifact storage and plan finalization.
- Added title parameter to exit_plan_mode tool to enable plan file renaming during approval workflow.
- Implemented NotesProtocolHandler for notes:// URL scheme with path traversal protection and session fallback.
- Added renameApprovedPlanFile function to handle plan artifact finalization with validation and error handling.
- Updated system prompt documentation to reference notes:// protocol and internal URL schemes for artifact access.
2026-02-22 17:41:01 +01:00
can1357 476b858b3a feat(coding-agent): added async background job execution with configurable concurrency limits
- Added async background job execution for bash and task tools with configurable concurrency limits and automatic result delivery.
- Added cancel_job tool and /jobs slash command to manage and inspect running background jobs with status display.
- Added jobs:// internal protocol handler for querying job status and retrieving job execution details.
- Added async.enabled and async.maxJobs settings to control background job execution behavior.
- Enhanced status line to display count of running background jobs with visual indicator.
- Implemented AsyncJobManager with exponential backoff retry delivery, job lifecycle tracking, and automatic eviction.

Fixes #56.
2026-02-22 12:44:57 +01:00
can1357 0b1514da61 feat(coding-agent): added overlay UI option and fixed viewport sync race conditions
- Added overlay option to custom UI hooks for bottom-centered component display.
- Added automatic chat transcript rebuild when returning from custom or debug UI modes.
- Fixed race condition in bash interactive component preventing output append after closure.
- Extracted environment variable configuration into reusable NO_PAGER_ENV constant for bash execution.
- Fixed viewport synchronization issue in TUI causing terminal desync during full re-renders.
2026-02-21 22:52:59 +01:00
can1357 93e28a8029 refactor: consolidated timing instrumentation to centralized logger methods
- Migrated timing instrumentation from custom utils/timings module to centralized logger.time() and logger.timeAsync() methods across coding-agent and natives packages.
- Removed PI_DEBUG_STARTUP environment variable and debugStartup() function, consolidating debug output to logger.debug() for conditional logging.
- Replaced custom TextDecoder buffer decoding with native toString('utf-8') method in natives package for simplified string conversion.
- Added RingBuffer<T> circular buffer implementation to pi-utils with comprehensive test coverage for efficient queue operations.
- Enhanced logger interface with time() and timeAsync() methods providing unified operation timing and performance tracking across packages.
2026-02-21 22:42:18 +01:00
Ken Vu b0a6d710fb fix(coding-agent): stopped forced redraws on autocomplete updates
onAutocompleteUpdate was calling requestRender(true), which resets all
differential rendering state on every keystroke while the slash menu is
open (debounced at 100ms). This caused the TUI to perform a full screen
clear and repaint on each filter update, producing visible flicker when
the editor is pushed to the bottom of the terminal.

onAutocompleteCancel retains requestRender(true) since it fires only
once on dismissal and the forced redraw is needed to erase the stale
menu rows that the differential renderer would otherwise leave on screen.

onAutocompleteUpdate is changed to requestRender() (no force), letting
the differential renderer repaint only the changed lines within the
autocomplete area.
2026-02-20 09:25:41 +13:00
can1357 e41ebe61ec feat(coding-agent): added SSH host management with CLI and slash commands
- Added SSH host management feature with `ssh` CLI command and `/ssh` slash command for add, list, and remove operations.
- Added SSH configuration support at project (.omp/ssh.json) and user (~/.omp/agent/ssh.json) scopes with host discovery from project files.
- Added SSH host configuration flags: --host, --user, --port, --key, --desc, --compat, and --scope for flexible host setup.
- Removed automatic line relocation on stale hash references; now fails with error instead.
2026-02-19 12:52:43 +01:00
can1357 69664396a8 fix(tui): fixed history navigation visibility and paging
Fixes #99
2026-02-19 05:06:10 +01:00
can1357 e2bb5041d2 feat(coding-agent): add Agent Control Center dashboard
Closes #93
2026-02-19 04:56:52 +01:00
Colin Mason bf0bcf73e2 feat(coding-agent): expose autocomplete max items setting
Wire the existing TUI autocompleteMaxVisible plumbing into the
declarative settings system so it appears in /settings under the
Input tab. Users can pick from 3/5/7/10/15/20 items; the TUI editor
clamps to 3-20 regardless.

- Add autocompleteMaxVisible to SETTINGS_SCHEMA (number, default 5)
- Add OPTION_PROVIDERS entry for the submenu dropdown
- Handle runtime side-effect in selector-controller
- Set initial value from settings on editor construction
- Add tests for default, runtime, persistence, and config loading
2026-02-18 09:40:16 -05:00
tctev 8b293edc30 feat: add pagination to /changelog command with --full flag 2026-02-16 11:12:33 +01:00
can1357 c12be01a5f fix(coding-agent): backported pi-mono changes (34878e..5133697)
packages/ai:
- fix: hardened OpenAI tool-call JSON parsing for malformed trailing arguments
- feat: routed GitHub Copilot Claude 4.x models through anthropic-messages
- feat: centralized dynamic Copilot headers and anthropic bearer auth handling
- feat: added optional StreamOptions.metadata propagation
- test: added Copilot headers/auth/routing coverage
- fix: updated model generator and models.json for Copilot Claude API mapping

packages/coding-agent:
- fix: made CLI model resolution deterministic with provider-aware pattern parsing
- fix: corrected compaction boundary/context usage handling after compaction
- feat: expanded extension events and terminal input hook integration
- fix: hardened git source parsing to avoid local-path misclassification
- test: added git-url parser coverage and model-resolver cases

packages/tui:
- fix: scoped @ fuzzy autocomplete to typed path prefixes
- feat: added Windows VT input mode support via bun:ffi

docs:
- chore: updated porting sync point to 5133697
2026-02-16 10:08:53 +01:00
can1357 f20a964986 feat(coding-agent): added animated microphone icon and skill discovery via symlinks, improved STT feedback
- Added animated microphone icon with color cycling during voice recording and transcription states.
- Added support for discovering skills via symbolic links in the skills directory.
- Changed STT status messages to display via state change callbacks instead of dedicated status line segment.
- Removed dedicated STT status line segment in favor of animated cursor-based feedback.
- Added cursor override feature to TUI editor for customizing end-of-text cursor glyph with ANSI-styled strings.
2026-02-15 13:37:43 +01:00
can1357 d1f41ae553 merge: PR #51 — speech-to-text with Alt+H (closes #51)
- Moved /stt slash command to 'omp setup stt' CLI command
- Fixed pip install blocking TUI (sync -> async)
- Fixed 'Transcribing...' status not clearing after success
2026-02-15 10:30:47 +01:00
can1357 9e32219a21 fix(stt): address review feedback 2026-02-15 10:23:48 +01:00
daaximusandcan1357 6969076386 feat(coding-agent): add speech-to-text with Alt+H keybinding
Cross-platform audio recording with automatic tool detection and
fallback chain (SoX > FFmpeg > arecord > PowerShell mciSendString).
Transcription via Python openai-whisper with automatic pip install
on first use.

Recording:
- SoX with explicit waveaudio device on Windows (-t waveaudio 0)
- FFmpeg with auto-detected dshow device name on Windows
- arecord for ALSA on Linux
- PowerShell mciSendString as zero-dependency Windows fallback
- Process health check after spawn, graceful stop for FFmpeg/PS
- Fallback chain: if one tool fails, tries the next automatically

Transcription:
- Python openai-whisper as primary backend (pip install openai-whisper)
- Custom WAV loader in transcribe.py using Python wave module
- Resamples to 16kHz mono via numpy (no ffmpeg dependency)
- Passes float32 numpy array directly to whisper.transcribe()
- 120s timeout with process kill guard

TUI integration:
- Alt+H keybinding to toggle recording (configurable in keybindings)
- /stt command with on|off|status|setup subcommands
- Status line segment showing REC/STT state
- Transcribed text inserted directly into editor prompt
- Lazy controller instantiation on first use

Settings:
- stt.enabled (default: false)
- stt.language (default: en)
- stt.modelName (default: base.en)

New files: packages/coding-agent/src/stt/{downloader,index,recorder,
setup,stt-controller,transcribe.py,transcriber}.ts
2026-02-15 10:23:48 +01:00
can1357 4571e505d9 feat(coding-agent): implemented codex-style memory system with two-phase extraction and consolidation pipeline
- Added autonomous memory extraction and consolidation system with two-phase pipeline for extracting durable knowledge and consolidating into reusable skills.
- Added /memory slash command with subcommands (view, clear, reset, enqueue, rebuild) for inspecting and managing memory maintenance.
- Added configurable memory settings including concurrency limits, lease timeouts, token budgets, and rollout age constraints.
- Added memory injection payload that includes learned context in system prompts with operational rules for reading and using memory artifacts.
- Improved system prompt building to support memory guidance injection and enhanced error handling in resolvePromptInput function for multiline input.
2026-02-14 02:02:48 +01:00
can1357 d1e16d2101 refactor: implemented $PWD > cwd to prevent macOS symlink resolution
- Replaced all direct `process.cwd()` calls with `getProjectDir()` utility function across 40+ files to centralize project directory resolution logic.
- Added `getProjectDir()` and `setProjectDir()` functions to `@oh-my-pi/pi-utils/dirs` module to provide abstracted project directory management.
- Made `SessionManager.list()` method asynchronous to support asynchronous session discovery operations.
- Updated default working directory resolution throughout codebase to use `getProjectDir()` instead of `process.cwd()` for improved project directory detection.
2026-02-13 23:40:02 +01:00
can1357 fcd7ff4f84 refactor(dirs): centralized directory path utilities into @oh-my-pi/pi-utils/dirs module
- Extracted directory path utilities from multiple packages into a centralized '@oh-my-pi/pi-utils/dirs' module.
- Moved 30+ path helper functions (getAgentDir, getConfigRootDir, getPluginsDir, getMCPConfigPath, etc.) from scattered locations into a single shared utility module.
- Consolidated APP_NAME, CONFIG_DIR_NAME, and VERSION constants into the centralized dirs module for reuse across packages.
- Updated 70+ import statements across packages/ai, packages/coding-agent, packages/stats, and packages/tui to use the new centralized module.
- Removed local path construction logic and replaced with utility function calls for improved maintainability and consistency.
- Deleted packages/coding-agent/src/extensibility/plugins/paths.ts as its functions were moved to the centralized dirs module.
2026-02-13 15:06:05 +01:00
can1357 1b24d4d655 fix(coding-agent): moved hook status line above editor input 2026-02-13 13:26:17 +01:00
can1357 df7a45b774 feat(coding-agent): added /move command to relocate sessions to different working directories
- Added /move slash command to allow users to relocate sessions to different working directories.
- Added moveTo() method to SessionManager for programmatic session relocation with file system operations and rollback support.
- Added refreshSlashCommandState() method to InteractiveMode for dynamic slash command reloading when changing directories.
- Added setSlashCommands() method to AgentSession to allow external management of file-based slash commands.
- Added handleMoveCommand() handler in command-controller to process /move commands with validation and error handling.
2026-02-12 02:38:59 +01:00
7e4bedf18b Runtime MCP support (#17)
* + /mcp

- Reloads MCP manager in runtime state (no restart needed) and syncs with mcp.json.
- Handles OAuth discovery/auth flow automatically for auth-required servers.
- Validates server names and config shape before saving.
- Persists OAuth credentials in auth storage and links them to MCP config.
- Provides immediate connection checks and clear status messages.
- Supports enable/disable, reauth, and unauth flows that are easy to get wrong by hand.

* active agent tool registry runtime reload + token support for bearer auth http based transport

* +session rebind on succesful connection

* fix(coding-agent): address /mcp check failures

---------

Co-authored-by: can1357 <me@can.ac>
2026-02-10 14:09:41 +01:00
can1357 acf8ab5225 style: stylistic changes 2026-02-10 07:39:39 +01:00
can1357 5e9deef6fd fix(coding-agent/modes): cleared todoItems when session file missing or todo load fails
- Ensured todoItems is cleared when no session file exists or todo file cannot be loaded.
- Added explicit initialization of todoItems to empty array in error and no-session-file cases to prevent stale todo data from persisting.
2026-02-07 08:07:48 +01:00