PRE-RELEASE
d3-mini-agentcode
d3-mini-agentcode is a pre-release 4B decision model for agent diffs and snippets. See its frozen questions, reported results and missed cases.
By stonefish-labs · Public release: 4 Nov 2026
A pre-release 4B d3-mini fine-tune for reviewing code written or run by an agent. It reads the task, repository baseline, behaviour summary and change, then returns three fixed decisions about class, intent and scope. The static extractor never runs the code being inspected. It is intended to rank items for further review.
Facts
- Size
- 4B
- Licence
- Apache-2.0; LICENSE and NOTICE shipped
- Inputs
- Text task and diff or executed snippet; truncated above 8,192 tokens
- Access
- Merged weights, readout, adapter, extractor, frozen questions and thresholds
Claims and sources
- At its frozen thresholds, the maker reports 458 of 510 positives found across 14 languages and shells, with 11 of 2,150 real items and 1 of 560 authored benign controls flagged. On an independently written agent-diff set it finds 21 of 22 positives with 0 of 172 negatives flagged. These evaluations were run by the maker. vendor reportedsource
- Training positives came from one writer model; recall falls on other writers. Unrequested personal data in request headers is mostly missed (1 of 40). The release is a pre-release and is not a sole security gate. vendor reportedsource
Links
Source: Model card, weights and results → Source: Release history →
Related projects
No related projects are listed in the registry.