Commit Graph

13 Commits

Author SHA1 Message Date
Cameron
e96ddc1db1 feat: add voice memo responses via TTS (#394) 2026-02-25 16:47:33 -08:00
Cameron
d33a280d77 feat: add reaction support for Signal channel (#353) 2026-02-24 12:05:51 -08:00
Jason Carreira
1fbd6d5a2e Add send-file directive and Discord/CLI file support (#319)
Co-authored-by: Jason Carreira <jason@visotrust.com>
Co-authored-by: Cameron <cameron@pfiffer.org>
Co-authored-by: Charles Packer <packercharles@gmail.com>
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
Co-authored-by: Letta <noreply@letta.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-23 15:44:34 -08:00
Cameron
01ed38a15d feat: per-agent todo system with heartbeat integration (#288) 2026-02-12 10:23:14 -08:00
Cameron
358339b76b fix: clarify system prompt to prevent duplicate message delivery (#269) 2026-02-10 19:47:13 -08:00
Cameron
5f7cdd3471 feat: XML response directives via <actions> wrapper block (#239)
Agents can now include an <actions> block at the start of their text
response to perform actions without tool calls. The block is stripped
before the message is delivered to the user.

Example:
  <actions>
    <react emoji="thumbsup" />
  </actions>
  Great idea!
  → Sends "Great idea!", reacts with thumbsup

- New directives parser (src/core/directives.ts) finds <actions> block
  at response start, parses self-closing child directives inside it
- addReaction() added to ChannelAdapter interface (Telegram, Slack,
  WhatsApp already implement it)
- Streaming holdback covers the full <actions> block duration (prefix
  check + incomplete block detection), preventing raw XML from flashing
- Directive execution extracted to executeDirectives() helper (no
  duplication between finalizeMessage and final send paths)
- Message envelope includes Response Directives section so all agents
  learn the feature regardless of system prompt
- System prompt documents the <actions> block syntax
- 19 unit tests for parser and stripping

Significantly cheaper than the Bash tool call approach (lettabot-react)
since no tool_call round trip is needed.

Relates to #19, #39, #240. Subsumes #210.

Written by Cameron ◯ Letta Code

"The best code is no code at all." - Jeff Atwood
2026-02-09 15:53:10 -08:00
Cameron
b1d69965b5 feat: add <no-reply/> silent marker for agent opt-out (#196)
* feat: add {{NO_REPLY}} silent marker for agent opt-out

Allow the agent to respond with {{NO_REPLY}} to suppress message
delivery for messages that don't warrant a reply. The marker is
checked in three places: the streaming edit guard (prefix match to
prevent partial sends), finalizeMessage(), and the post-stream
response handler.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: use <no-reply/> XML marker instead of {{NO_REPLY}}

Switch to XML-style self-closing tag for consistency with the XML
envelope format used elsewhere, and because LLMs produce well-formed
XML tags more reliably than template syntax.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: add no-reply hint to group chat envelopes

Agents created outside lettabot (via ADE, Letta Cloud) won't have the
system prompt telling them about <no-reply/>. Adding the hint to group
chat envelopes makes the opt-out mechanism self-documenting.

Written by Cameron ◯ Letta Code

"Silence is one of the great arts of conversation." -- Marcus Tullius Cicero

---------

Co-authored-by: Gabriele Sarti <gabriele.sarti996@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-06 11:08:56 -08:00
Gabriele Sarti
0aef80157a feat: add lettabot-channels CLI for channel discovery (#121)
Allow the agent to discover channel IDs across Discord and Slack so it
can send messages to channels it hasn't received messages from (e.g.
"write something in #announcements"). Updates the system prompt so the
agent knows the command exists.

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 11:02:35 -08:00
Parth Modi
d1d758739d feat(whatsapp): add lettabot-message CLI support for text and files (#89)
Merged WhatsApp CLI support with HTTP API server.

Features:
- HTTP API server for CLI-to-bot communication across Docker boundaries
- WhatsApp text + file sending via `lettabot-message send --file photo.jpg`
- Unified multipart endpoint at /api/v1/messages
- Security: timing-safe auth, localhost binding, same-origin CORS
- Bad MAC error handling for WhatsApp encryption renegotiation

Written by Cameron ◯ Letta Code
2026-02-03 17:21:27 -08:00
Jason Carreira
d420e5d3b5 Add reactions CLI for Telegram/Slack/Discord (#20)
* Add lettabot-react CLI and message IDs

* Expose message IDs for reactions

---------

Co-authored-by: Jason Carreira <jason@visotrust.com>
2026-01-29 15:40:50 -08:00
Jason Carreira
0f68b9b52f Add Discord channel support (#16)
* Add Discord channel support and pairing (#15)

* Address Discord adapter review feedback

* Fix stream counter after merge

* Remove stream count logging

---------

Co-authored-by: Jason Carreira <jason@visotrust.com>
2026-01-29 14:11:50 -08:00
Sarah Wooders
1c99351736 Add scheduling docs and fix GitHub issues link in system prompt 2026-01-28 18:59:05 -08:00
Sarah Wooders
22770e6e88 Initial commit - LettaBot multi-channel AI assistant
Co-authored-by: Cameron Pfiffer <cameron@pfiffer.org>
Co-authored-by: Caren Thomas <carenthomas@gmail.com>
Co-authored-by: Charles Packer <packercharles@gmail.com>
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
2026-01-28 18:02:51 -08:00