{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "danielxu0208-rsi-eval--run-codex-candidate-on-terminal-bench-task",
 "repo": "Danielxu0208/rsi_eval",
 "repo_url": "https://github.com/Danielxu0208/rsi_eval",
 "repo_slug": "danielxu0208-rsi-eval",
 "title": "Run a Codex candidate on one Terminal-Bench task",
 "page_title": "How to run a Codex candidate on one Terminal-Bench task with Rsi Eval",
 "summary": "Score a candidate agent on a single Terminal-Bench 2.0 task and read the per-task result.",
 "who": "A software engineer testing a coding agent setup who needs a real score on one task before running a larger suite.",
 "problem": "Setting up Docker, Harbor, and a dedicated Codex login is easy to get wrong, and a first run can be hard to diagnose.",
 "outcome": "A result.json and resolved.json for the candidate, plus a reference oracle run to compare against.",
 "steps": [
  "`python -m pip install -e '.[harbor]'`",
  "`docker info`",
  "`CODEX_HOME=\"$HOME/.codex-rsi-eval\" codex -c 'cli_auth_credentials_store=\"file\"' login` (inferred, check the README)",
  "`rsi-eval configure --model YOUR_MODEL --auth-dir \"$HOME/.codex-rsi-eval\" --output profile.json` (inferred, check the README)",
  "`rsi-eval check --config examples/evaluate.json`",
  "`rsi-eval run --config examples/evaluate.json --output runs/tb20-candidate` (inferred, check the README)"
 ],
 "agent_prompt": "In the rsi_eval repo, set target.model and the Codex login directory in examples/evaluate.json for <model-name>, then run `rsi-eval run --config examples/evaluate.json --output runs/<new-output-dir>`. Report status and per-task reward from result.json. Verify that the output directory did not exist before the run.",
 "agents": [
  "codex"
 ],
 "difficulty": "Advanced",
 "time": "180 minutes",
 "basis": "readme",
 "caveat": "The candidate run consumes model quota, and the README says the bundled subscription Codex target requires concurrency=1.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.12 or newer and git",
  "Docker Engine with Compose and Buildx, or Docker Desktop, for benchmark runs",
  "Codex CLI on PATH and access to a model for candidate runs",
  "Harbor 0.18.0 installed through the harbor extra for benchmark runs"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "The Codex login directory and the profile hold account access, so keep them outside the repository and out of candidate artifacts."
  }
 ],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/danielxu0208-rsi-eval/run-codex-candidate-on-terminal-bench-task/",
 "md": "https://dedupedai.com/use-cases/danielxu0208-rsi-eval/run-codex-candidate-on-terminal-bench-task/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/danielxu0208-rsi-eval--run-codex-candidate-on-terminal-bench-task.json",
 "api_version": "v1"
}