chore(renderers): advance to latest main (PR #38, closes #2492)#2518
Merged
Conversation
Picks up: - PrimeIntellect-ai/renderers#38: per-message / per-role analytics on RenderedTokens (tokens_per_message, tokens_by_role, message_token_spans, role_token_spans, message_roles field). Also fixes attribution loss in bridge_to_next_turn so bridge output is included in per-message accounting. Confirms PrimeIntellect-ai/renderers#33 (sampled_mask AND in build_training_sample) is current — closes #2492. The fix was already live at the prior pin (87084dc); this bump just keeps us current with renderers main. No prime-rl callers touch the new RenderedTokens APIs; bump is purely additive. pyproject.toml / uv.lock unchanged (renderers is a workspace member; submodule SHA change doesn't affect the lock). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
mikasenghaas
approved these changes
May 16, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Bumps the
deps/rendererssubmodule from87084dc→17d0584(latest renderersmain, now taggedrenderers-v0.1.8.dev3).Closes #2492
Confirms PrimeIntellect-ai/renderers#33 (
sampled_maskAND inbuild_training_sample) is current. The SFT renderer path no longer trains on<|im_start|>assistant\nscaffolding —build_training_sampleANDs role attribution withsampled_mask, keeping SFT byte-aligned with the RL trajectory mask. (The upstream fix was already live at the prior pin87084dc; this bump just keeps us current.)Picks up
PrimeIntellect-ai/renderers#38 — per-message / per-role analytics on
RenderedTokens:tokens_per_message,tokens_by_role,message_token_spans,role_token_spansmessage_roles(every renderer now populates)bridge_to_next_turn— bridges previously discardedmsg_idx/is_sampledeven though local emit helpers received them. Bridges now populatemessage_indices(relative tonew_messages),sampled_mask(uniformlyFalse— bridge output is a prompt), andmessage_roles. Consumers can run the new analytics on bridge output for incremental per-message accounting without re-rendering.Upstream tag
Cut
renderers-v0.1.8.dev3at commit17d0584fto unblock CI: renderers useshatch-vcswith the defaultguess-next-devscheme, which refuses to derive a version for untagged commits past a.devN(N>0) tag. The first CI run failed with:Tagging
17d0584fasv0.1.8.dev3puts HEAD on a tag so hatch-vcs uses the tag verbatim — no bumping needed. This continues the existingv0.1.8.devNpre-release ladder leading up to the eventualv0.1.8release.Surface impact
RenderedTokensAPIs (grepconfirms).renderers>=0.1.8.dev0constraint is satisfied; its consumers (renderer_client.py) only readbridged.token_idsandbridged.multi_modal_data, both unchanged.pyproject.toml/uv.lockunchanged —renderersis a uv workspace member, so the submodule SHA change doesn't propagate to the lock.tests/unit/train/sft/test_sft_dataset.py: 17/17).🤖 Generated with Claude Code
Note
Low Risk
Low risk because this PR only advances the
deps/rendererssubmodule pointer; behavior changes are confined to the external renderers dependency and won’t affect this repo unless callers rely on updated renderer outputs.Overview
Advances the
deps/renderersgit submodule to a newer upstream commit/tag.This pulls in upstream renderer changes around mask/role attribution and new per-message/per-role token analytics on
RenderedTokens, without modifying any first-party code in this repo.Reviewed by Cursor Bugbot for commit d31376d. Bugbot is set up for automated code reviews on this repo. Configure here.