Conversation
model_run_key is the immutable benchmark identity of one model plus one option set; benchmark files and the warehouse's dim_model_run key on it. Add a PR check that dumps (model_run_key, model_key, options) for every run on the base branch and on the PR head and fails when a base run is missing or has a different model_key or options. Adding runs stays allowed; slug, release dates, Models.dev metadata and `active` are not compared. scripts/check_model_run_immutability.py has two subcommands: `dump` (NDJSON of the immutable fields, sorted, with a fingerprint) and `check` (compare two dumps, print a report, exit 1 on violation). The workflow installs the base and PR versions of the package into separate venvs and runs the PR's copy of the script by file path against each, so the check does not depend on the base branch already carrying the script. Document the freeze rule in AGENTS.md. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XSAqY76fnCZj5zFnM7gHFL Co-authored-by: nflechner <60731786+nflechner@users.noreply.github.com>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
model_run_keyis the immutable benchmark identity of one model plus one option set; benchmark files and the warehouse's dim_model_run key on it. Add a PR check that dumps (model_run_key, model_key, options) for every run on the base branch and on the PR head and fails when a base run is missing or has a different model_key or options. Adding runs stays allowed; slug, release dates, Models.dev metadata andactiveare not compared.scripts/check_model_run_immutability.pyhas two subcommands:dump(NDJSON of the immutable fields, sorted, with a fingerprint) andcheck(compare two dumps, print a report, exit 1 on violation). The workflow installs the base and PR versions of the package into separate venvs and runs the PR's copy of the script by file path against each, so the check does not depend on the base branch already carrying the script.Document the freeze rule in AGENTS.md.
Co-Authored-By: Claude Fable 5.1 noreply@anthropic.com
Claude-Session: https://claude.ai/code/session_01XSAqY76fnCZj5zFnM7gHFL