Repository navigation
docs: refresh README and drop private-repo reference - #1
Conversation
Make the README more engaging while preserving the engineering-preview scope, required brand wording, section ordering and honest limits. - Add a benefit-first intro, a "What makes it worth inspecting" table and a four-step run walkthrough with a quickstart CTA. - Remove the private libreevolve-experimental repository reference. - Update test_brand_docs to assert the private reference is absent. Verification: brand/docs tests pass (34 passed, 10 subtests) and brand/check_claims.py reports validation passed.
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. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: bfbbbfc43f
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| bounded local space of changes, and saves every candidate workspace and | ||
| evaluation so you can read the evidence yourself — before a fresh export check |
There was a problem hiding this comment.
If a run is forcibly terminated or persistence fails after evaluation but before db.log()—the loop has separate evaluated and history_logging phases—the run may contain only partial state, as docs/run-artifacts.md explicitly acknowledges. Saying the tool saves “every” candidate workspace and evaluation therefore promises evidence that may not exist; qualify this as successfully persisted candidates or restore the previous non-universal wording.
AGENTS.md reference: AGENTS.md:L37-L39
Useful? React with 👍 / 👎.
| | **Bounded by design** | Local call, evaluation and runtime limits keep a run small enough to follow. They are not token or dollar caps, and subscription usage may stay unknown. | | ||
| | **Saved, not summarized** | Candidate workspaces, evaluations, archive events and LLM calls land in a run directory you can read. | | ||
| | **Honest by construction** | Run status, validity, quality, retention and usage stay separate, so a finished run is never mistaken for a win. | | ||
| | **Checked again before use** | Reports and exports re-run the selected candidate in fresh local subprocesses instead of trusting old metadata. | |
There was a problem hiding this comment.
When best_workspace/ differs from the saved history candidate, alpha report always evaluates the on-disk workspace, whereas alpha export requires an explicit --source workspace or --source history choice. Saying both commands re-run “the selected candidate” hides this source divergence and can make the report sound like verification of the history-selected program; describe the report’s workspace source separately from export’s selected source.
AGENTS.md reference: AGENTS.md:L44-L45
Useful? React with 👍 / 👎.
1 participant
Summary
Makes the README more engaging while preserving the engineering-preview scope, required brand wording, section ordering and honest limits.
libreevolve-experimentalrepository reference.tests/test_brand_docs.pyto assert the private reference is absent.Verification
pytest tests/test_brand_docs.py tests/test_brand_claims.py tests/test_agents_docs.py tests/test_community_templates.py-> 34 passed, 10 subtests passedpython brand/check_claims.py-> validation passed