fix: inject memory in connect() before subprocess starts - #8
Open
just-cameron wants to merge 1 commit into
Open
Conversation
Fixes #6 The ClaudeInterceptor was patching write() to inject memory, but by that time connect() had already spawned the subprocess with the system prompt baked into CLI args. Changes: - Patch connect() instead of write() for memory injection - Memory is now injected BEFORE _build_command() runs - write() patch now only captures outgoing messages - Handle both sync and async clients in memory retrieval Written by Cameron ◯ Letta Code "The only way to do great work is to love what you do." - Steve Jobs 🐾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta <noreply@letta.com>
Contributor
Author
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #6
The
ClaudeInterceptorwas patchingwrite()to inject memory, but by that timeconnect()had already spawned the subprocess with the system prompt baked into CLI args.Root Cause
The execution order was:
connect()calls_build_command()which readssystem_promptconnect()spawns subprocess with those argswrite()is called - now the interceptor runs, but it's too lateFix
connect()instead ofwrite()for memory injection_build_command()runswrite()patch now only captures outgoing messagesTest plan
🐾 Generated with Letta Code