Add benchmark harness: scripts, docs, config, and tests - #14
Merged
Merged
Conversation
Scripts (35): core runner (run-e2e-benchmark.sh, run-swe-benchmark.sh, run-swe-headless.py, run-multi-model-benchmark.sh, run-benchmark-batch.sh, run-throughput-harness.py, run-swe-router-headless.py), judge pipeline (llm_as_judge.py, codex_judge.py, judge_common.py, judge_prompt.txt), dataset/runner config (dataset_loader.py, runner_config.py, runner.example.yaml), token accounting, preflight checks, chart generators, Bedrock proxy script. Docs (6): harness-reference.md, path guides for all three hosting paths, end-to-end self-hosted run-book, agent-cli Bedrock setup. Tests (21): full test coverage for scripts. Config: litellm-mantle.yaml, pyproject.toml, uv.lock. Fixed aarora79 repo URL in agent-cli-bedrock-setup.md and build_vended_models.py.
…sitive-data cmd never contains credentials - api_key is passed via OPENAI_API_KEY env var only. Copying cmd to cmd_display breaks the false taint trace from config.password through _build_codex_cmd to the print call.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds the full benchmark harness under
benchmarks/— the scripts, docs, config, and tests that make the repo actually runnable.Scripts (35): core runners (
run-e2e-benchmark.sh,run-swe-benchmark.sh,run-swe-headless.py,run-multi-model-benchmark.sh), judge pipeline (llm_as_judge.py,codex_judge.py), dataset/runner config (dataset_loader.py,runner_config.py), token accounting, preflight checks, chart generators, Bedrock proxy script.Docs (6):
harness-reference.md, path guides for all three hosting paths, end-to-end self-hosted run-book, agent-cli Bedrock setup.Tests (21): full test coverage for all new scripts.
Config:
litellm-mantle.yaml,runner.example.yaml,pyproject.toml,uv.lock.Test plan
aarora79repo URLs (external reference toclaude-codex-bedrock-ec2is legitimate, left as-is)benchmarks/README.mdrenders correctly