Fix: Data utils and Training CLI#54
Closed
hahuyhoang411 wants to merge 2 commits into
Closed
Conversation
|
|
Author
|
Update the example training CLI by adding |
Member
|
ah sorry, missed this, but has been fixed in recent pushes |
samsja
added a commit
that referenced
this pull request
Apr 23, 2026
rlm/#54 dropped the randomized-threshold form from _parse_summarize_at_tokens on the engine side, so the engine now rejects "lo,hi" strings in RLM_SUMMARIZE_AT_TOKENS. Mirror that here: the harness kwarg is int | None, the formatter emits only "N", and the docstring no longer promises the tuple form. Fails at harness-build time instead of inside the sandbox if a caller still passes a tuple.
samsja
added a commit
that referenced
this pull request
Apr 23, 2026
* rlm_harness: add summarize_at_tokens, drop rlm_max_turns_in_context Plumbs the new rlm auto-compaction knob from kwarg -> env var. Accepts an int for a fixed threshold or a (lo, hi) pair to draw a uniform threshold per rollout/compaction; None leaves RLM_SUMMARIZE_AT_TOKENS unset so rlm disables auto-compaction. Invalid shapes fail at harness-build time instead of deep inside the sandbox. rlm_max_turns_in_context and RLM_MAX_TURNS_IN_CONTEXT are gone upstream (rlm now uses token-based compaction instead of turn caps). Default rlm_tools drops "summarize" to match rlm's new tool set. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ruff * rlm_harness: summarize_at_tokens is int-only, drop (lo, hi) form rlm/#54 dropped the randomized-threshold form from _parse_summarize_at_tokens on the engine side, so the engine now rejects "lo,hi" strings in RLM_SUMMARIZE_AT_TOKENS. Mirror that here: the harness kwarg is int | None, the formatter emits only "N", and the docstring no longer promises the tuple form. Fails at harness-build time instead of inside the sandbox if a caller still passes a tuple. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Sami Jaghouar <sami.jaghouar@hotmail.fr>
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.
When run training with
mmluit throws this error due to double quotes