Open
Conversation
samsja
force-pushed
the
chore/rename-tito-to-trajectory-mode
branch
from
0dcddc4 to
f6f3560
Compare
samsja
changed the title
Member
|
@cursoragent can we do "interleaved" not "interleave" ? |
Member
|
@cursoragent Also "trajectory_strategy" for config name pls |
…hing options
Replaces the boolean `use_token_client` field with a `trajectory_strategy`
enum ("interleaved" | "branching") for clarity.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
samsja
force-pushed
the
chore/rename-tito-to-trajectory-mode
branch
from
f6f3560 to
6aa87f4
Compare
Member
mikasenghaas
left a comment
mikasenghaas
left a comment
There was a problem hiding this comment.
not sure i like this renaming. seems less explicit to me. we should warn about the extension property assumption in the tito client in the config description + probably also a warning log or smth
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
use_token_clientwith atrajectory_modefield ("interleave"|"branching")openai_chat_completions_token). Requires linear history and a chat template with the extension property.openai_chat_completions), re-tokenizing each turn independently. The interleave algorithm still does best-effort compression of branches into a single trajectory when the extension property holds.Breaking change
orchestrator.use_token_client = true/false→orchestrator.trajectory_mode = "interleave"/"branching"🤖 Generated with Claude Code
Note
Medium Risk
Breaking config change and it alters which inference client is used during training, which can affect rollout tokenization/throughput and compatibility with non-linear histories.
Overview
Replaces
orchestrator.use_token_clientwithorchestrator.trajectory_strategy("interleaved" | "branching"), where the setting now explicitly controls how multi-turn trajectories are tokenized and which OpenAI client type is used.Updates orchestrator startup to pick
openai_chat_completions_tokenonly for "interleaved" (and emit an updated warning), otherwise defaulting to message-levelopenai_chat_completions. The changelog is updated to document the breaking config rename and new semantics.Written by Cursor Bugbot for commit 6aa87f4. This will update automatically on new commits. Configure here.