feat: add Letta agent self-history analysis to /init skill#954
Open
sarahwooders wants to merge 2 commits intomainfrom
Open
feat: add Letta agent self-history analysis to /init skill#954sarahwooders wants to merge 2 commits intomainfrom
sarahwooders wants to merge 2 commits intomainfrom
Conversation
Add scripts and SKILL.md instructions for the agent to review its own past conversation history during /init, similar to the existing Claude Code/Codex history analysis flow. New scripts: - detect-own-history.ts: list conversations + date ranges via Letta API - split-history.ts: split all history into chunk files (conversation × month) - extract-messages.ts: extract a single chunk (low-level building block) Messages are filtered for signal: user messages in full, assistant truncated to 500 chars, reasoning to 200 chars, tool calls as one-liner summaries, tool returns dropped entirely. Chunks are pre-extracted to local files so history-analyzer subagents need no API access. 🐾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta <noreply@letta.com>
Cut from 110 lines to 38 by removing duplicate explanations, verbose examples, and troubleshooting table already covered by the Claude/Codex section. 🐾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta <noreply@letta.com>
cpacker
reviewed
Feb 14, 2026
| // Main | ||
| // --------------------------------------------------------------------------- | ||
|
|
||
| async function main() { |
Collaborator
There was a problem hiding this comment.
built-in scripts using the Letta API should be converted into CLI, similar to letta messages list, since it is much more robust for auth
cpacker
requested changes
Feb 14, 2026
Collaborator
cpacker
left a comment
cpacker
left a comment
There was a problem hiding this comment.
should be folded into CLI not scripts
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add scripts and SKILL.md instructions for the agent to review its own past conversation history during /init, similar to the existing Claude Code/Codex history analysis flow.
New scripts:
Messages are filtered for signal: user messages in full, assistant truncated to 500 chars, reasoning to 200 chars, tool calls as one-liner summaries, tool returns dropped entirely. Chunks are pre-extracted to local files so history-analyzer subagents need no API access.
🐾 Generated with Letta Code