mirror of https://github.com/garrytan/gstack.git
8e9ec52d6f
Adds ProtectAI DeBERTa-v3-base-injection-onnx as an optional L4c layer
for cross-model agreement. Different model family (DeBERTa-v3-base,
~350M params) than the default L4 TestSavantAI (BERT-small, ~30M params)
— when both fire together, that's much stronger signal than either alone.
Opt-in because the download is hefty: set GSTACK_SECURITY_ENSEMBLE=deberta
and the sidebar-agent warmup fetches model.onnx (721MB FP32) into
~/.gstack/models/deberta-v3-injection/ on first run. Subsequent runs are
cached.
Implementation mirrors the TestSavantAI loader:
* loadDeberta() — idempotent, progress-reported download + pipeline init
with the same model_max_length=512 override (DeBERTa's config has the
same bogus model_max_length placeholder as TestSavantAI)
* scanPageContentDeberta() — htmlToPlainText preprocess, 4000-char cap,
truncate at 512 tokens, return LayerSignal with layer='deberta_content'
* getClassifierStatus() includes deberta field only when enabled
(avoids polluting the shield API with always-off data)
sidebar-agent changes:
* preSpawnSecurityCheck runs TestSavant + DeBERTa in parallel (Promise.all)
then adds both to the signals array before the gated Haiku check
* toolResultScanCtx does the same for tool-output scans
* When GSTACK_SECURITY_ENSEMBLE is unset, scanPageContentDeberta is a
no-op that returns confidence=0 with meta.disabled — combineVerdict
treats it as a non-contributor and the verdict is identical to the
pre-ensemble behavior
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| bin | ||
| scripts | ||
| src | ||
| test | ||
| PLAN-snapshot-dropdown-interactive.md | ||
| SKILL.md | ||
| SKILL.md.tmpl | ||