co-mono/packages/coding-agent/CHANGELOG.md

Changelog

[Unreleased]

Added

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

[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 ~/.pi/agent/hooks/*.ts and .pi/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 ~/.pi/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 ~/.pi/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 piConfig in package.json. Forks can change piConfig.name and piConfig.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 ~/.pi/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 ~/.pi/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 ~/.pi/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