Configure outer loop with correct forecastbench benchmark - #162
Merged
Conversation
- Create .factory/benchmarks/forecastbench.toml with pytest format and gate test command (shadows incorrect built-in JSON config) - Fix .factory/outer_loop/config.json benchmark from "featurebench" to "forecastbench" - Add .factory/scripts/trim-backlog.sh workaround for remote-factory #1338 (--focus gap) Addresses #161 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add !.factory/benchmarks/ exclusion to .gitignore so the benchmark config is tracked while the rest of .factory stays ignored. Remove config.json and trim-backlog.sh from tracking (runtime/local-only). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Change .factory to .factory/* so git descends into the directory and evaluates the !.factory/benchmarks/ negation pattern for new files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
lukeinglis
marked this pull request as ready for review
August 20, 2026 16:14
This was referenced Aug 21, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #161
Changes
.factory/benchmarks/forecastbench.toml— project-local benchmark config withformat = "pytest",command = "uv run pytest gate/ -q",timeout = 600,method = "partial_credit". Shadows the incorrect built-in config (which usesformat = "json"andcommand = "python eval_forecast.py") via remote-factory's search-path priority.!.factory/benchmarks/to.gitignore— excludes benchmark configs from the.factoryignore pattern so the TOML is properly tracked.No Python source files were modified. Gate tests, eval.py, lab_forecaster.py, and score.py are untouched.
Context
Generation 0 of the outer loop ran with
--benchmark featurebench(copied from docs) instead of a proper forecastbench config. Remote-factory PR akashgit/remote-factory#1332 added multi-benchmark support with TOML configs and a built-inforecastbench.toml— but that built-in uses JSON format, not our pytest gate. This PR provides the correct project-local override.