|
| 1 | +--- |
| 2 | +title: "Forking of existing sessions" |
| 3 | +--- |
| 4 | + |
| 5 | +Author(s): [@josevalim](https://github.com/josevalim) |
| 6 | + |
| 7 | +## Elevator pitch |
| 8 | + |
| 9 | +> What are you proposing to change? |
| 10 | +
|
| 11 | +We propose adding the ability to "fork" a new session based on an existing one. |
| 12 | +This will allow us to use the current conversation as context to generate pull |
| 13 | +request descriptions, summaries, etc. without polluting the user history. |
| 14 | + |
| 15 | +## Status quo |
| 16 | + |
| 17 | +> How do things work today and what problems does this cause? Why would we change things? |
| 18 | +
|
| 19 | +Imagine we want to summarize the current conversation to use it in a future chat. If we send a message |
| 20 | +asking for the summary, it will become part of its context, affecting future user interactions. |
| 21 | +Therefore we want to be able to fork a session, issue additional messages, and then close the fork. |
| 22 | + |
| 23 | +## What we propose to do about it |
| 24 | + |
| 25 | +> What are you proposing to improve the situation? |
| 26 | +
|
| 27 | +One possible solution is to add a session/fork command. |
| 28 | + |
| 29 | +## Shiny future |
| 30 | + |
| 31 | +> How will things will play out once this feature exists? |
| 32 | +
|
| 33 | +We will be able to implement functionality that requires using the current chat |
| 34 | +without polluting its history, ranging from summaries to potentially subagents. |
| 35 | + |
| 36 | +I can also see this feature being extended in the future to support an optional |
| 37 | +message ID, so the fork happens at a specific message, allowing clients to implement |
| 38 | +functionality like editing previous messages and similar. |
| 39 | + |
| 40 | +## Implementation details and plan |
| 41 | + |
| 42 | +> Tell me more about your implementation. What is your detailed implementation plan? |
| 43 | +
|
| 44 | +<!-- |
| 45 | + Use this section to add details that were not covered in the "What we propose to do about it" section and also include an implementation plan with phases. |
| 46 | + |
| 47 | + Note: This section is OPTIONAL and NOT RECOMMENDED when RFDs are first opened. It can distract from the discussion of the problem. |
| 48 | +--> |
| 49 | + |
| 50 | +## Frequently asked questions |
| 51 | + |
| 52 | +> What questions have arisen over the course of authoring this document or during subsequent discussions? |
| 53 | + |
| 54 | +<!-- |
| 55 | + Keep this section up-to-date as discussion proceeds. The goal is to capture major points that came up on a PR or in a discussion forum -- and if they reoccur, to point people to the FAQ so that we can start the dialog from a more informed place. |
| 56 | +--> |
| 57 | + |
| 58 | +### What alternative approaches did you consider, and why did you settle on this one? |
| 59 | + |
| 60 | +None. This proposal is inspired by the abilities exposed in Claude Agent SDK. It must be validated against other agents too. |
| 61 | + |
| 62 | +<!-- You...may want to adjust this. --> |
| 63 | + |
| 64 | +## Revision history |
| 65 | + |
| 66 | +<!-- If there have been major updates to this RFD, you can include the git revisions and a summary of the changes. --> |
0 commit comments