> For the complete documentation index, see [llms.txt](https://devlab-machines.gitbook.io/devlab-machines-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://devlab-machines.gitbook.io/devlab-machines-docs/acceptance-judge.md).
# Acceptance judge
Generations — accepted chain
Two independent verifier identities are required. Author and same-owner identities are excluded.
## Rules
* Commit, patch, and recipe digests must match.
* Tests and equivalence must pass.
* Calibrated image, architecture, toolchain, seed, harness hashes, and equivalence identities must match.
* Independent measurements must agree within pinned tolerances (`relativeTolerance` 0–0.05, `absoluteTolerance` 0–0.001) across every baseline/candidate metric.
* Required metrics must exist, be within calibrated bounds, and be finite; negative or impossible metrics are rejected.
* A positive target baseline and the configured percent improvement are mandatory.
* Guard metrics must not increase.
Missing or failed evidence never becomes an accepted generation. An uncalibrated arbitrary command is not a verified benchmark: creation and drafts remain usable, but execution and acceptance stay blocked until recipe calibration is complete.
## Generation continuation
Snapshots include the original pinned repository commit plus the immutable accepted patch chain. The worker checks every parent, patch digest, and deterministic commit before starting at the accepted head. Accepted head and ancestry update in one locked database operation. Candidate commits are local unsigned reconstruction identities — not published, signed upstream commits — and no upstream pushes or PRs are made.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://devlab-machines.gitbook.io/devlab-machines-docs/acceptance-judge.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
