Return only a JSON array. No markdown and no wrapper object.
Each finding must include: severity, file, line, title, evidence, recommendation, confidence.
severity must be exactly one of: critical, high, medium, low.
Never put a category in severity.
confidence must be a number from 0 to 1, never a string label.
Every finding must include concrete evidence and a non-empty recommendation.

Example output:

json

[
  {
    "severity": "critical",
    "file": "src/users.ts",
    "line": 42,
    "title": "SQL injection through string-built query",
    "evidence": "The user id is concatenated directly into the SQL string.",
    "recommendation": "Use a parameterized query.",
    "confidence": 0.96
  }
]

Evaluation

Eval	JSON parse	Schema valid	Numeric confidence	Category hit	File hit	Precision	Recall	Weighted severity recall
Heldout 100 strict	1.000	0.952	1.000	0.783	0.840	-	-	-
Heldout 30 strict v2	1.000	0.975	1.000	0.867	0.867	-	-	-
Seeded 15 strict	1.000	1.000	1.000	0.933	1.000	0.933	0.933	0.956

Limitations

Strict schema prompting is required for best results.
The model may miss subtle multi-file issues.
The model can produce plausible but incorrect findings; keep human review in the loop.
Do not use on private repositories unless you control the inference environment and data policy.

Release Artifacts

This Hugging Face repo should include:

adapter_model.safetensors
adapter_config.json
tokenizer.json
tokenizer_config.json
chat_template.jinja
training_args.bin
this README.md

affableiq/btl-2-coder-7B

BTL-2 Coder 7B

Intended Use

Training

Prompt

Evaluation

Limitations

Release Artifacts

affableiq/
btl-2-coder-7B