Commit graph

145 commits

Author SHA1 Message Date
Mario Zechner
05644ebcd5 Use ordered root build instead of parallel workspace build in CI 2025-12-03 15:05:04 +01:00
Mario Zechner
e0c057ecc6 Add web-ui/example to workspaces, remove CI workaround 2025-12-03 14:27:02 +01:00
Mario Zechner
24fcca5b7b Try fixing root level compiles 2025-12-03 14:16:00 +01:00
Mario Zechner
15428f10ed Clean-up out.html 2025-12-02 13:01:13 +01:00
badlogic
ccae220032 Fix Windows binary path resolution for Bun compiled executable 2025-12-02 12:58:00 +01:00
Mario Zechner
b348c2549e docs: update AGENTS.md style guide - no emojis, no fluff 2025-12-02 12:20:32 +01:00
Mario Zechner
1f55424d2d chore: update models.generated.ts 2025-12-02 09:38:49 +01:00
Mario Zechner
5a65ce5349 fix: use TruncatedText in oauth-selector to prevent line overflow 2025-12-02 09:28:27 +01:00
Mario Zechner
d2b60f11eb 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!
2025-12-01 01:19:17 +01:00
Mario Zechner
dd71f877e5 docs(coding-agent): add changelog entry for git branch watcher (#79) 2025-11-29 21:54:02 +01:00
Mario Zechner
754e745b1f Restore prompt to editor on API key validation failure
fixes #77
2025-11-28 23:00:37 +01:00
Mario Zechner
9ebee631be mom: turn-based context, timestamp fixes, system prompt improvements (#68)
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
2025-11-27 23:45:25 +01:00
Mario Zechner
a59553a881 Fix edit diff line number alignment and whitespace preservation
- 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
2025-11-27 11:53:00 +01:00
Mario Zechner
213bc4df1c mom: add centralized logging, usage tracking, and improve prompt caching
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
2025-11-26 18:04:16 +01:00
Mario Zechner
82d4ac93e1 ai: update models list (removed grok-4.1-fast non-free variant) 2025-11-26 13:21:59 +01:00
Mario Zechner
aa9e058249 mom: Slack bot with abort support, streaming console output, removed sandbox 2025-11-26 00:27:21 +01:00
Mario Zechner
b42df6848c Add $ prefix to cost in footer
Fixes #53
2025-11-25 21:32:52 +01:00
Mario Zechner
0148f0ac3d v0.9.3: Added Anthropic Claude Opus 4.5 support 2025-11-24 21:03:32 +01:00
Mario Zechner
52325adb97 Release v0.9.2 2025-11-24 19:32:55 +01:00
Mario Zechner
68ca83441b Changes to AGENTS.md 2025-11-24 19:17:50 +01:00
Mario Zechner
e1856daf57 fix: rename pi-agent to pi-agent-core (npm deprecation issue) 2025-11-21 22:20:43 +01:00
Mario Zechner
1d8bc9d6eb Fix path completion hanging and autocomplete arrow key behavior
- 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
2025-11-21 12:47:23 +01:00
Mario Zechner
e7a5ca144c Release v0.8.4 2025-11-21 05:09:58 +01:00
Mario Zechner
d44073b140 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
2025-11-20 20:39:43 +01:00
Mario Zechner
e694d435fd Release v0.7.27
- Fix slash command submission requiring two Enter presses (#30)
- Fix slash command autocomplete not re-triggering after typos (#29)
2025-11-20 18:56:27 +01:00
Mario Zechner
de39f1f493 Add custom headers support for models.json
Fixes #39

- Added headers field to Model type (provider and model level)
- Model headers override provider headers when merged
- Supported in all APIs:
  - Anthropic: defaultHeaders
  - OpenAI (completions/responses): defaultHeaders
  - Google: httpOptions.headers
- Enables bypassing Cloudflare bot detection for proxied endpoints
- Updated documentation with examples

Also fixed:
- Mistral/Chutes syntax error (iif -> if)
- process.env.ANTHROPIC_API_KEY bug (use delete instead of = undefined)
2025-11-20 17:05:31 +01:00
butelo
b76f7a0f88 Merge branch 'main' into fix/chutes-ai-provider-400-error 2025-11-20 15:04:29 +01:00
butelo
bd1731c9ba fix 400 error when trying to use chutes ai provider 2025-11-20 14:56:22 +01:00
Mario Zechner
e3c4dd22ae Fix TypeScript error in version check 2025-11-20 12:00:51 +01:00
Mario Zechner
1f68d6eb40 Release v0.7.22 2025-11-19 01:50:45 +01:00
Mario Zechner
38ac29acfb Add ANSI-aware word wrapping to TUI components
- Created shared wrapTextWithAnsi() function in utils.ts
- Handles word-based wrapping while preserving ANSI escape codes
- Properly tracks active ANSI codes across wrapped lines
- Supports multi-byte characters (emoji, surrogate pairs)
- Updated Markdown and Text components to use shared wrapping
- Removed duplicate wrapping logic (158 lines total)
2025-11-18 22:26:24 +01:00
Mario Zechner
a11c1aa4ff Release v0.7.17 2025-11-18 17:49:12 +01:00
Mario Zechner
587d7c39a4 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
2025-11-18 17:33:33 +01:00
Mario Zechner
387cc97bac Fix Anthropic API rejection when resubmitting aborted thinking blocks
- Convert thinking blocks with missing/empty signatures to text blocks
- Prevents 400 error: 'Invalid signature in thinking block'
- Occurs when stream is aborted mid-thinking and message is resubmitted
2025-11-18 14:36:57 +01:00
Mario Zechner
f2b3953711 v0.7.15: Anthropic OAuth support 2025-11-17 12:53:57 +01:00
Mario Zechner
063b7e0f11 chore: bump coding-agent to 0.7.14 - fix Anthropic OAuth and Mistral API compatibility 2025-11-17 12:46:59 +01:00
Mario Zechner
e0c2745989 Add gpt-5.1-codex to model list 2025-11-16 22:35:09 +01:00
Mario Zechner
901449b38a Pin pdfjs-dist to exact version 5.4.394 to fix worker version mismatch 2025-11-16 00:03:58 +01:00
Mario Zechner
8ae236f956 Add /branch command for conversation branching (fixes #16)
- Add /branch slash command to create conversation branches
- New UserMessageSelectorComponent shows all user messages chronologically
- Selecting a message creates new session with messages before selection
- Selected message is placed in editor for modification/resubmission
- SessionManager.createBranchedSession() creates new session files
- Updated README.md and CHANGELOG.md with /branch documentation
2025-11-14 23:52:46 +01:00
Mario Zechner
a686f61c1d feat(tui): improve editor Ctrl/Alt word and line deletion shortcuts
- Add Ctrl+W for word deletion (stops at whitespace/punctuation)
- Add Ctrl+U for delete to start of line (merges with previous line at col 0)
- Change Ctrl+K from delete entire line to delete to end of line (merges with next line at EOL)
- Add Option+Backspace support in Ghostty (maps to Ctrl+W via ESC+DEL sequence)
- Cmd+Backspace in Ghostty works as Ctrl+U (terminal sends same control code)
- Update README and CHANGELOG with new keyboard shortcuts

Fixes #2, Fixes #3
2025-11-14 23:19:24 +01:00
Mario Zechner
ced5fc3394 Bump version to 0.7.8 2025-11-13 23:49:04 +01:00
Mario Zechner
fede1303b1 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
2025-11-13 21:56:58 +01:00
Denis Badurina
1ecf02020d regen models and openrouter auto 2025-11-13 10:20:38 +01:00
Mario Zechner
c8d762833a chore: bump version to 0.7.4 2025-11-13 01:30:26 +01:00
Mario Zechner
d2e4a34772 fix: make read tool output more concise for images 2025-11-13 01:28:39 +01:00
Mario Zechner
b1410ef903 chore: bump versions to 0.7.0 2025-11-12 23:54:57 +01:00
Mario Zechner
a2dc1187dc fix: handle Windows paths in session directory generation
- Replace backslashes in addition to forward slashes
- Remove colons from Windows drive letters (C:, D:, etc)
- Fixes ENOENT error on Windows when creating session directories
2025-11-12 23:50:30 +01:00
Mario Zechner
43a1c1ae44 chore: sync all versions to 0.6.2 and fix workspace references 2025-11-12 23:44:05 +01:00
Mario Zechner
e533aebacd Fix Lit dependency duplication and update mini-lit to 0.2.0
- Move lit from dependencies to peerDependencies in web-ui to prevent multiple Lit instances being loaded
- Update mini-lit from 0.1.8/0.1.10 to 0.2.0 in root package.json and web-ui/package.json
- Install @tailwindcss/vite in web-ui/example
- Run biome formatting fixes across codebase

This resolves HMR custom element re-registration errors caused by duplicate Lit registries.
2025-11-12 16:03:43 +01:00
Mario Zechner
09564f2940 Update coding-agent dependencies to 0.6.0 2025-11-12 14:36:59 +01:00