agent/pi
2
0
Fork 0
mirror of https://github.com/earendil-works/pi.git synced 2026-06-18 15:54:04 +08:00
Code Issues Packages Projects Releases Wiki Activity
982 Commits 32 Branches 288 Tags
716516d61e442ded33a59badf04673b28c0fd39f
Commit Graph

74 Commits

  • Wrap custom tools with hooks (#248)
    Nico Bailon · 2025-12-19 19:05:20 +01:00
    74f7e6c9d5
  • Refactor subagent tool, fix custom tool discovery, fix JSON mode stdout flush 
    Breaking changes:
- Custom tools now require index.ts entry point in subdirectory
  (e.g., tools/mytool/index.ts instead of tools/mytool.ts)

Subagent tool improvements:
- Refactored to use Message[] from ai package instead of custom types
- Extracted agent discovery to separate agents.ts module
- Added parallel mode streaming (shows progress from all tasks)
- Added turn count to usage stats footer
- Removed redundant Query section from scout output

Fixes:
- JSON mode stdout flush: Fixed race condition where pi --mode json
  could exit before all output was written, causing consumers to
  miss final events

Also:
- Added signal/timeout support to pi.exec() for custom tools and hooks
- Renamed pi-pods bin to avoid conflict with pi
    Mario Zechner · 2025-12-19 04:54:02 +01:00
    4fb3af93fb
  • fix(coding-agent): detect image MIME via file-type (#205) 
    Co-authored-by: Mario Zechner <badlogicgames@gmail.com>
    Peter Steinberger · 2025-12-17 17:11:56 +01:00
    d70edf571e
  • Custom tools with session lifecycle, examples for hooks and tools 
    - Custom tools: TypeScript modules that extend pi with new tools
  - Custom TUI rendering via renderCall/renderResult
  - User interaction via pi.ui (select, confirm, input, notify)
  - Session lifecycle via onSession callback for state reconstruction
  - Examples: todo.ts, question.ts, hello.ts

- Hook examples: permission-gate, git-checkpoint, protected-paths

- Session lifecycle centralized in AgentSession
  - Works across all modes (interactive, print, RPC)
  - Unified session event for hooks (replaces session_start/session_switch)

- Box component added to pi-tui

- Examples bundled in npm and binary releases

Fixes #190
    Mario Zechner · 2025-12-17 16:03:23 +01:00
    e7097d911a
  • Release v0.22.4 
    - Add --list-models CLI flag for listing/finding models with fuzzy search

fixes #203
    Mario Zechner · 2025-12-17 00:39:14 +01:00
    03b061773c
  • Add skills system with Claude Code compatibility (#171) 
    * Add skills system with Claude Code compatibility

* consolidate skills into single module, merge loaders, add <available_skills> XML tags

* add Codex CLI skills compatibility, skip hidden/symlinks
    Nico Bailon · 2025-12-12 18:24:52 +01:00
    09bca9672f
  • Add --version/-v flag to CLI (#170) 
    - Parse --version and -v flags in args.ts
- Handle version flag early in main.ts (print and exit)
- Add flag to help text
- Add comprehensive test coverage for CLI arg parsing

Co-authored-by: cc-vps <crcatala+vps@gmail.com>
    Christian Catalan · 2025-12-12 00:01:06 +01:00
    f614892406
  • fixes #161: stop theme watcher and exit cleanly in print mode 
    The theme file watcher was keeping the Node.js process alive indefinitely
even in print mode where hot-reload is unnecessary. This simple fix calls
stopThemeWatcher() and process.exit(0) after print mode completes.

- Added stopThemeWatcher() call after runPrintMode() completes
- Added process.exit(0) to ensure clean process termination
- Imported stopThemeWatcher from theme module

This is a minimal fix that addresses the symptom (process hanging) without
changing the theme initialization logic.
    Mario Zechner · 2025-12-10 21:16:47 +01:00
    7323af1f69
  • fixes #161: disable theme watcher in print mode 
    The theme file watcher was keeping the Node.js process alive indefinitely
even in print mode where hot-reload is unnecessary. This fix adds an
enableWatcher parameter to initTheme() and setTheme() functions, and only
enables watchers in interactive mode.

- Modified initTheme() to accept enableWatcher parameter (default: false)
- Modified setTheme() to accept enableWatcher parameter (default: false)
- Updated main.ts to only enable watchers in interactive mode
- Updated InteractiveMode to enable watchers when changing themes
    Mario Zechner · 2025-12-10 21:16:47 +01:00
    9516424cae
  • Add hooks system with pi.send() for external message injection 
    - Hook discovery from ~/.pi/agent/hooks/, .pi/hooks/, --hook flag
- Events: session_start, session_switch, agent_start/end, turn_start/end, tool_call, tool_result, branch
- tool_call can block execution, tool_result can modify results
- pi.send(text, attachments?) to inject messages from external sources
- UI primitives: ctx.ui.select/confirm/input/notify
- Context: ctx.exec(), ctx.cwd, ctx.sessionFile, ctx.hasUI
- Docs shipped with npm package and binary builds
- System prompt references docs folder
    Mario Zechner · 2025-12-10 00:50:30 +01:00
    7c553acd1e
  • Fix --session flag to load session messages and restore model/thinking
    Mario Zechner · 2025-12-09 01:59:20 +01:00
    75c2eea151
  • Move config.ts from utils/ to src/
    Mario Zechner · 2025-12-09 01:28:06 +01:00
    14d99b5f86
  • Remove old implementation files (main.ts, cli.ts, tui-renderer.ts), rename new files
    Mario Zechner · 2025-12-09 01:21:28 +01:00
    6c9a264b63
  • Reorganize file structure: core/, utils/, modes/interactive/components/, modes/interactive/theme/
    Mario Zechner · 2025-12-09 00:51:33 +01:00
    83a6c26969
  • Add bash mode for executing shell commands 
    - Add ! prefix in TUI editor to execute shell commands directly
- Output streams in real-time and is added to LLM context
- Supports multiline commands, cancellation (Escape), truncation
- Preview mode shows last 20 lines, Ctrl+O expands full output
- Commands persist in session history as bashExecution messages
- Add bash command to RPC mode via {type:'bash',command:'...'}
- Add RPC tests for bash command execution and context inclusion
- Update docs: rpc.md, session.md, README.md, CHANGELOG.md

Closes #112

Co-authored-by: Markus Ylisiurunen <markus.ylisiurunen@gmail.com>
    Mario Zechner · 2025-12-08 22:40:32 +01:00
    bd0d0676d4
  • Add xhigh thinking level for OpenAI codex-max models 
    - Add 'xhigh' to ThinkingLevel type in ai and agent packages
- Map xhigh to reasoning_effort: 'max' for OpenAI providers
- Add thinkingXhigh color token to theme schema and built-in themes
- Show xhigh option only when using codex-max models
- Update CHANGELOG for both ai and coding-agent packages

closes #143
    Mario Zechner · 2025-12-08 21:12:54 +01:00
    00370cab39
  • Run version check in parallel with TUI startup 
    Instead of blocking startup for up to 1 second waiting for the version check,
run it in the background and insert the notification into chat when it completes.
    Mario Zechner · 2025-12-05 23:36:06 +01:00
    7352072bc2
  • Add authHeader option and fix print mode error handling 
    - Add 'authHeader' boolean option to models.json provider config
  When true, adds 'Authorization: Bearer <apiKey>' to model headers
  Useful for providers requiring explicit auth headers (fixes #81)

- Fix print mode (-p) silently failing on errors
  Now outputs error message to stderr and exits with code 1
  when assistant message has stopReason of error/aborted
    Mario Zechner · 2025-12-05 11:31:14 +01:00
    51195bc9fc
  • support appending content to the system prompt via cli argument
    Markus Ylisiurunen · 2025-12-05 09:25:10 +02:00
    ef8bb6c062
  • feat(coding-agent): add auto-compaction to RPC mode, add RPC compaction test 
    - RPC mode now auto-compacts when context exceeds threshold (same as TUI)
- Add RPC test for manual compaction via compact command
- Auto-compaction emits compaction event with auto: true flag
    Mario Zechner · 2025-12-04 02:49:22 +01:00
    c3f63dd243
  • Context compaction: commands, auto-trigger, RPC support, /branch rework (fixes #92) 
    - Add compaction settings to Settings interface
- /compact [instructions]: manual compaction with optional focus
- /autocompact: toggle auto-compaction on/off
- Auto-compaction triggers after assistant message_end when threshold exceeded
- Footer shows (auto) when auto-compact is enabled
- RPC mode: {type: 'compact'} command emits CompactionEntry
- /branch now reads from session file to show ALL historical user messages
- createBranchedSessionFromEntries preserves compaction events
    Mario Zechner · 2025-12-04 00:25:53 +01:00
    79731249eb
  • feat(coding-agent): configurable app name and config dir for forks (#95) 
    - Add piConfig to package.json for app name and config directory
- Consolidate paths.ts into config.ts with clearer naming
- Fix Bun binary detection (changed from %7EBUN to $bunfs)
- Update all hardcoded paths to use config.ts exports
- getThemesDir() for built-in themes, getCustomThemesDir() for user themes
    Mario Zechner · 2025-12-03 16:18:59 +01:00
    e82fb0fc83
  • feat: standalone binary support with Bun 
    - Add build:binary script for Bun compilation
- Add paths.ts for cross-platform asset resolution (npm/bun/tsx)
- Add GitHub Actions workflow for automated binary releases
- Update README with installation options

Based on #89 by @steipete
    Mario Zechner · 2025-12-02 12:18:42 +01:00
    c4a65ad8b9
  • Release v0.11.5
    Mario Zechner · 2025-12-01 20:22:14 +01:00
    7a1884f85c
  • fix: RPC mode session management not saving sessions 
    Since version 0.9.0, RPC mode (--mode rpc) was not saving messages to
session files. The agent.subscribe() call with session management logic
was only present in the TUI renderer after it was refactored.

RPC mode now properly saves sessions just like interactive mode.

Added test for RPC mode session management to prevent regression.

Fixes #83

Thanks @kiliman for reporting this issue!
    Mario Zechner · 2025-12-01 01:19:17 +01:00
    d2b60f11eb
  • feat(coding-agent): add --export CLI flag to convert session files to HTML 
    Closes #80
    Mario Zechner · 2025-11-29 23:05:07 +01:00
    8900897840
  • feat(coding-agent): add read-only exploration tools (grep, find, ls) and --tools flag 
    Add grep, find, and ls tools for safe code exploration without modification risk.
These tools are available via the new --tools CLI flag.

- grep: Uses ripgrep (auto-downloaded) for fast regex searching. Respects .gitignore,
  supports glob filtering, context lines, and hidden files.
- find: Uses fd (auto-downloaded) for fast file finding. Respects .gitignore, supports
  glob patterns, and hidden files.
- ls: Lists directory contents with proper sorting and directory indicators.
- --tools flag: Specify available tools (e.g., --tools read,grep,find,ls for read-only mode)
- Dynamic system prompt adapts to selected tools with relevant guidelines

Closes #74
    Mario Zechner · 2025-11-29 00:59:23 +01:00
    186169a820
  • fix: file @ autocomplete performance using fd 
    - Replace slow synchronous directory walking with fd for fuzzy file search
- Auto-download fd to ~/.pi/agent/tools/ if not found in PATH
- Performance improved from ~900ms to ~10ms per keystroke on large repos
- Remove minimatch dependency from tui package
- Graceful degradation if fd unavailable (empty results)

Fixes #69
    Mario Zechner · 2025-11-28 23:38:44 +01:00
    a61eca5dee
  • coding-agent: remove identity override from system prompt (#73) 
    Models now use their native identity instead of being told they are Pi.
    Mario Zechner · 2025-11-27 23:57:02 +01:00
    8b1cca8279
  • Add CLI file arguments support via @file prefix 
    Implements ability to include files directly in the initial message using @ prefix.

Features:
- All @file arguments are coalesced into the first user message
- Text files wrapped in <file name="path">content</file> tags
- Images (.jpg, .jpeg, .png, .gif, .webp) attached as base64-encoded attachments
- Supports ~ expansion, relative and absolute paths
- Empty files are skipped silently
- Non-existent files cause immediate error with clear message
- Works in interactive, --print, and --mode text/json modes
- Not supported in --mode rpc (errors with clear message)

Examples:
  pi @prompt.md @image.png "Do this"
  pi --print @code.ts "Review this code"
  pi @requirements.md @design.png "Implement this"

Closes #54
    Mario Zechner · 2025-11-27 12:47:11 +01:00
    f95f41b1c4
  • fix: pass attachments to agent prompt from RPC interface 
    This PR updates the call to `agent.prompt` with the `attachments` prop provided in the JSON input.
    kiliman · 2025-11-25 21:56:32 -05:00
    958d265112
  • fix: rename pi-agent to pi-agent-core (npm deprecation issue)
    Mario Zechner · 2025-11-21 22:20:43 +01:00
    e1856daf57
  • fix(coding-agent): suppress informational output in non-interactive modes 
    In -p, --mode json, and --mode rpc modes, don't print informational
messages like 'Loaded project context from:' or model restore messages.
Only the actual output should be printed.
    Mario Zechner · 2025-11-21 22:07:17 +01:00
    56450a4f19
  • feat(coding-agent): allow starting CLI with prompt in interactive mode (#46) 
    BREAKING CHANGE: Passing a prompt on the command line now starts interactive
mode with the prompt pre-submitted, instead of exiting after completion.
Use --print or -p to get the previous non-interactive behavior.

- Add --print / -p flag for non-interactive mode
- Update runInteractiveMode to accept initial messages
- Update README documentation
- Fix Model Selection Priority docs to include --models scope
    Mario Zechner · 2025-11-21 21:57:35 +01:00
    e89e657045
  • feat: enhance model cycling with thinking levels and --thinking flag 
    PR #47 enhancements:
- Add thinking level syntax to --models (e.g., --models sonnet:high,haiku:low)
- First model in scope used as initial model when starting new session
- Auto-apply thinking level when cycling models with Ctrl+P
- Save both model and thinking to session AND settings for persistence
- Simplify UX by removing autoThinkingDisabled flag
- Fix model matching to prioritize exact matches over partial
- Support provider/modelId format (e.g., openrouter/openai/gpt-5.1-codex)

Issue #45:
- Add --thinking CLI flag to set thinking level directly
- Takes highest priority over all other thinking level sources

Closes #45
    Mario Zechner · 2025-11-21 21:32:30 +01:00
    ba8c073ed2
  • Merge remote-tracking branch 'origin/main' into feat/model-cycling-enhancements
    Mario Zechner · 2025-11-21 21:16:05 +01:00
    df3af27288
  • feat: add /clear command to reset context and start fresh session
    Mario Zechner · 2025-11-21 20:59:00 +01:00
    1b6a70ccb1
  • feat: enhance model cycling with thinking level support 
    - Add exact match support with '/' prefix (/gpt-5.1-codex or /provider/model)
- Prefer exact ID matches over partial matches in fuzzy search
- Parse thinking levels from --models flag (pattern:level format)
- Use first scoped model as initial model with its thinking level
- Auto-apply thinking when cycling with Ctrl+P
- Track manual thinking changes to disable auto-switching
- Clear model scope when using /model command
- Support mixed configs: --models sonnet:high,haiku,opus:low
- Silently ignore thinking for models that don't support it
- Only allow Ctrl+P cycling when --models is explicitly provided
- Update help text with examples
- Improve code organization by resolving scope early
    Tino Ehrich · 2025-11-21 12:02:56 +01:00
    ea4e234f66
  • Release v0.8.0
    Mario Zechner · 2025-11-21 03:12:42 +01:00
    85adcf22bf
  • WIP: Add theming system with /theme command 
    - Consolidated theme system into single src/theme/ directory
- Created Theme class with fg(), bg(), bold(), italic(), underline()
- Added dark and light built-in themes with 36 color tokens
- Support for custom themes in ~/.pi/agent/themes/*.json
- JSON schema for theme validation
- Theme selector UI with /theme command
- Save theme preference to settings
- Uses chalk for text formatting to preserve colors

TODO:
- Replace hardcoded colors throughout TUI components
- Apply markdown theming to Markdown components
- Add theme support to all TUI elements
    Mario Zechner · 2025-11-20 23:16:59 +01:00
    cc88095140
  • Release v0.7.29 
    - Show offset/limit in read tool display (e.g., read src/main.ts:100-200)
- Fix PI_CODING_AGENT_DIR env var name in help and code
- Add all API key env vars to help text
    Mario Zechner · 2025-11-20 20:48:25 +01:00
    ba5bf54af4
  • Release v0.7.28 
    - Add message queuing with configurable modes (one-at-a-time/all) (#15)
- Add /queue command to select queue mode
- Add TruncatedText component for proper viewport-aware text truncation
- Queue mode setting persists in ~/.pi/agent/settings.json
- Visual feedback for queued messages with proper ANSI handling
- Press Escape to abort and restore queued messages to editor
    Mario Zechner · 2025-11-20 20:39:43 +01:00
    d44073b140
  • Fix help text to use 'pi' instead of 'coding-agent'
    Mario Zechner · 2025-11-20 13:00:38 +01:00
    ee5228becf
  • Add --models parameter for quick model cycling with Ctrl+P 
    - Add --models CLI arg accepting comma-separated patterns
- Implement smart matching: prefers aliases over dated versions
- Add Ctrl+P to cycle through scoped models (or all if no scope)
- Show model scope hint at startup
- Update help text with examples

Co-authored-by: Tino Ehrich <tino.ehrich@hey.com>
    Mario Zechner · 2025-11-20 12:57:20 +01:00
    fecf9734b0
  • Fix TypeScript error in version check
    Mario Zechner · 2025-11-20 12:00:51 +01:00
    e3c4dd22ae
  • Release v0.7.23
    Mario Zechner · 2025-11-20 11:59:17 +01:00
    b3d4478b61
  • feat(coding-agent): add OAuth authentication for Claude Pro/Max 
    - Add /login and /logout commands for OAuth flow
- OAuth tokens stored in ~/.pi/agent/oauth.json with 0600 permissions
- Auto-refresh tokens when expired (5min buffer)
- Priority: OAuth > ANTHROPIC_OAUTH_TOKEN env > ANTHROPIC_API_KEY env
- Fix model selector async loading and re-render
- Add bracketed paste support to Input component for long codes
- Update README.md with OAuth documentation
- Add implementation docs and testing checklist
    Mario Zechner · 2025-11-18 17:33:33 +01:00
    587d7c39a4
  • v0.7.12: Custom models/providers support via models.json 
    - Add ~/.pi/agent/models.json config for custom providers (Ollama, vLLM, etc.)
- Support all 4 API types (openai-completions, openai-responses, anthropic-messages, google-generative-ai)
- Live reload models.json on /model selector open
- Smart model defaults per provider (claude-sonnet-4-5, gpt-5.1-codex, etc.)
- Graceful session fallback when saved model missing or no API key
- Validation errors show precise file/field info in CLI and TUI
- Agent knows its own README.md path for self-documentation
- Added gpt-5.1-codex (400k context, 128k output, reasoning)

Fixes #21
    Mario Zechner · 2025-11-16 22:56:24 +01:00
    0c5cbd0068
  • Fix AGENTS.md support, changelog viewer, and session model storage 
    - BREAKING: Renamed AGENT.md to AGENTS.md for project context files
- Added automatic changelog viewer on startup for new sessions
- Added settings manager to track last shown changelog version
- BREAKING: Store provider and modelId separately in session files (fixes #4)
- Fixed markdown list rendering when items contain inline code with cyan formatting
- Added dynamic border component for TUI
- Updated changelog with entries for #4 and #5
    Mario Zechner · 2025-11-13 21:56:58 +01:00
    fede1303b1
  • Add settings manager, show changelog on startup if not shown yet.
    Mario Zechner · 2025-11-13 21:19:57 +01:00
    c82f9f4f8c