- Use describe.skipIf pattern matching other tests
- Skip when ANTHROPIC_API_KEY and ANTHROPIC_OAUTH_TOKEN are missing
- Use explicit --provider anthropic --model claude-sonnet-4-5
- 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
Fix race condition where app_mention event fires before message event
logs to log.jsonl, causing the user's triggering message to be missing
from the agent's context. Now append the current message directly from
ctx.message to recentMessages.
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!
Previously, the selected line in @ fuzzy search and Tab completion used
accent color for prefix/label but muted color for description. Now the
entire selected line uses the accent color for better visual consistency.
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
- 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
Breaking Changes:
- Timestamps now use Slack format - run migrate-timestamps.ts for existing logs
Added:
- Channel/user ID mappings in system prompt
- Skills documentation in system prompt
- Debug last_prompt.txt output
- Bash working directory info
- Token-efficient log queries filtering tool calls
Changed:
- Turn-based message context (groups consecutive bot messages as one turn)
- Messages sorted by Slack timestamp
- Condensed system prompt (~5k → ~2.7k chars)
- Simplified user prompt
- Selective logging (skip UI status labels)
Fixed:
- Duplicate message logging from app_mention handler
- Username obfuscation in thread messages
- Messages > 40k chars are split into multiple Slack messages
- Full tool results now shown in thread (no truncation)
- Main message truncates with 'see thread for full response' if too long
- Keep jsonl log truncation for storage efficiency
- Truncate messages exceeding Slack's 40,000 char limit
- Catch Slack API errors in queue and post to thread instead of crashing
- Add error context to queue operations for better debugging
- Wrap replaceMessage in try/catch
- During execution: show tool labels, thinking, and text in main message
- After completion: replace main message with only final assistant text
- Post thinking (italic) and text to thread for full audit trail
- Add promise queue to ensure ctx.respond calls execute sequentially
- Add log.logThinking() and log.logResponse() for console output
- Get final text from agent.state.messages instead of tracking
Closes#65
- Footer now displays active git branch after directory path (e.g., ~/project (main))
- Branch detected by reading .git/HEAD directly (fast, synchronous)
- Cache refreshed after each assistant message to detect branch changes
- Handles normal branches, detached HEAD, and non-git repos
Closes#55
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
- Added timestamps to each user and assistant message (HH:MM:SS format)
- Fixed text clipping issues with comprehensive word-wrapping CSS
- Improved font selection: ui-monospace, Cascadia Code, Source Code Pro
- Reduced font sizes for more compact display (12px base, down from 14px)
- Added model switch indicators in conversation timeline with subtle background
- Created dedicated Tokens & Cost section showing:
- Cumulative input/output/cache read/write tokens
- Cost breakdown by token type with 4 decimal precision
- Total cost in bold
- Context usage with token count, percentage, and model identification
- Now displays all unique models used during session (not just initial model)
- Made Messages section more compact (reduced gaps, removed redundant fields)
Closes#51Closes#52
- Up/down arrows now navigate visual (wrapped) lines instead of logical lines
- Fixed double cursor display at wrap boundaries
- Added word by word navigation via Option+Left/Right or Ctrl+Left/Right
- Updated README keyboard shortcuts documentation
Closes#61
- Fix line numbers showing incorrect values for edits far from file start
(e.g., 1,2,3 instead of 336,337,338). Skip count was added after displaying
lines instead of before.
- Rewrite splitIntoTokensWithAnsi in pi-tui to preserve whitespace as separate
tokens instead of discarding it. Wrapped lines now maintain proper alignment
and code indentation.
- Update mom README: rename title, remove em-dashes for cleaner prose
- Type @ to fuzzy-search files/folders across project
- Respects .gitignore and skips hidden files
- Pure Node.js implementation using readdir with withFileTypes
- No external dependencies (fd/find) required
- Also optimized Tab completion to use withFileTypes instead of statSync
Based on PR #60 by @fightbulc, reimplemented for performance.
Fixed crash when rendering text containing emojis followed by long content.
The breakLongWord function was iterating over UTF-16 code units instead of
grapheme clusters, causing emojis (surrogate pairs) to be miscounted during
line wrapping. Now uses Intl.Segmenter to properly handle multi-codepoint
characters.
Removed confusing parenthetical that suggested context files aren't loaded when continuing/resuming sessions. They are always freshly loaded from disk at startup - the parenthetical only applied to console logging behavior.
Working Indicator:
- Add '...' to channel messages while mom is processing
- Automatically removed when work completes or stops
- Applies to working message, not status messages
Improved Stop Command:
- Posts separate 'Stopping...' message that updates to 'Stopped'
- Original working message continues updating with tool results
- Clean separation between status and work output
- Properly handles abort during multi-step operations
Clean Stop Reason Handling:
- Agent run() now returns { stopReason } instead of throwing
- Handle 'aborted', 'error', 'stop', 'length', 'toolUse' cases cleanly
- No more exception-based control flow
- Track stopReason from assistant message.stopReason field
New SlackContext Methods:
- replaceMessage() - replace message text instead of appending
- setWorking() - add/remove working indicator
- Improved context tracking for stop command updates
Major improvements to mom's logging and cost reporting:
Centralized Logging System:
- Add src/log.ts with type-safe logging functions
- Colored console output (green=user, yellow=mom, dim=details)
- Consistent format: [HH:MM:SS] [context] message
- Replace scattered console.log/error calls throughout codebase
Usage Tracking & Cost Reporting:
- Track tokens (input, output, cache read/write) and costs per run
- Display summary at end of each run in console and Slack thread
- Example: 💰 Usage: 12,543 in + 847 out (5,234 cache read) = $0.0234
Prompt Caching Optimization:
- Move recent messages from system prompt to user message
- System prompt now mostly static (only changes with memory files)
- Enables effective use of Anthropic's prompt caching
- Significantly reduces costs on subsequent requests
Model & Cost Improvements:
- Switch from Claude Opus 4.5 to Sonnet 4.5 (~40% cost reduction)
- Fix Claude Opus 4.5 cache pricing in ai package (was 3x too expensive)
- Add manual override in generate-models.ts until upstream fix merges
- Submitted PR to models.dev: https://github.com/sst/models.dev/pull/439
UI/UX Improvements:
- Extract actual text from tool results instead of JSON wrapper
- Cleaner Slack thread formatting with duration and labels
- Tool args formatting shows paths with offset:limit notation
- Add chalk for colored terminal output
Dependencies:
- Add chalk package for terminal colors
- Add MEMORY.md files for persistent working memory
- Global memory: workspace/MEMORY.md (shared across channels)
- Channel memory: workspace/<channel>/MEMORY.md (channel-specific)
- Automatically loaded into system prompt on each request
- Enhance JSONL log format with ISO 8601 dates
- Add 'date' field for easy grepping (e.g., grep '"date":"2025-11-26"')
- Migrated existing logs to include date field
- Improve log query efficiency
- Add jq query patterns to prevent context overflow
- Emphasize limiting NUMBER of messages (10-50), not truncating text
- Show full message text and attachments in queries
- Handle null/empty attachments with (.attachments // [])
- Optimize system prompt
- Add current date/time for date-aware operations
- Format recent messages as TSV (43% token savings vs raw JSONL)
- Add efficient query examples with both JSON and TSV output
- Enhanced security documentation
- Add prompt injection risk warnings
- Document credential exfiltration scenarios
- Provide mitigation strategies
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.
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
When pressing Enter on a highlighted slash command suggestion (e.g., typing
`/mod` with `/model` highlighted), the completion is now applied before
submitting. Previously, the partial text was submitted instead of the
selected command.
Fixes#49
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
- Fixed catastrophic regex backtracking in extractPathPrefix that caused
terminal to hang when text contained many / characters (e.g., URLs).
Replaced complex regex with simple lastIndexOf approach. (#18)
- Fixed arrow keys moving both autocomplete selection and editor cursor
by adding missing return statement after handling arrow keys in
autocomplete mode.
Closes#18
- 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
- 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