Release BenchFlow 0.7.6 - #1103
Merged
Merged
Conversation
Publish the reviewer-grade trajectory viewer and rollout catalog, the claude-agent-acp 0.73.0 pin that lets claude-fable-5-1 run at all, the modernized codex-acp dispatch, Z.ai Coding Plan routing, the HF bucket / eval-results publish flags, and the Gemini and ACP reliability fixes accumulated since 0.7.5 — and set the public package version to 0.7.6. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cuts the first public release since 0.7.5 (2026-08-19), covering 25 commits on
main.Sets
[project].versionto0.7.6(from0.7.6.dev0), syncsuv.lock, and opens the0.7.6CHANGELOG section. Once this merges, pushingv0.7.6triggerspublic-release.yml(PyPI + GitHub Release);mainthen bumps to0.7.7.dev0.Why now
claude-fable-5-1is unusable on every stable install. Released 0.7.5 pins@agentclientprotocol/claude-agent-acp@0.40.0, which bundles@anthropic-ai/claude-agent-sdk0.3.160; the model rejects Claude Code older than 2.1.251 withclaude_code_version_too_old(HTTP 400), so rollouts fail on the first API call. #1086 fixed that onmainon 2026-09-01, but no tagged release contains it — stable users have been stuck patchingsite-packagesby hand or opting into--prerelease allow.Release contents
Added — reviewer-grade trajectory viewer and rollout catalog with
hf://browsing (#1034), Z.ai Coding Plan routing (#1074),--publish-bucketand--eval-results-*onbench eval run(#1035).Fixed — the
claude-agent-acp0.73.0 pin (#1086), modernizedcodex-acpdispatch (#1044), ACP usage/terminal evidence on timeout (#1080), idle-watchdog deferral cap (#1066), resume of infra-retryable verifier errors (#1063), verifier-setup budget for hardening execs (#1062),--trials/--matrixvalidation (#1064), plus the Gemini, LiteLLM, Codex and OpenClaw routing corrections. Full list in the CHANGELOG diff.Verification
mainis green at3b9dd067—integration-lightandinternal-preview-releaseboth succeeded 2026-09-04.uv lock --checkclean.TAG_NAME=v0.7.6 uv run --with packaging --no-project python tools/release_version.py public-release→version=0.7.6.🤖 Generated with Claude Code