mirror of https://github.com/garrytan/gstack.git
4328748136
The L4b Haiku transcript classifier and the opt-in DeBERTa ensemble
(GSTACK_SECURITY_ENSEMBLE=deberta, a documented 721MB download) had ZERO
production callers since the chat-path agent that invoked them was ripped.
The only live ML path is scanPageContent (testsavant) inside the security
sidecar subprocess. Deleted by import graph:
- security-classifier.ts 614 -> 265 lines: HAIKU_MODEL, checkTranscript,
shouldRunTranscriptCheck, loadDeberta, scanPageContentDeberta, ToolCallInput,
all DEBERTA_* consts + load state. Header now states the live truth
(imported only by security-sidecar-entry.ts). downloadFile kept, name
intact — it is an enumerated egress sink (HF model download).
- security-bunnative.ts + test: a research skeleton self-described as 'NOT a
production replacement', shipped into src/ with zero importers.
- security-bench-ensemble{,-live}.test.ts + the Haiku response fixture: a
paid live-model benchmark for a layer that could not fire. The
security-classifier-tdz test's only case exercised checkTranscript — gone.
- security.ts: layer-model header rewritten to the live architecture;
StatusDetail.layers -> {testsavant, canary}; getStatus() no longer requires
the impossible transcript==='ok' for 'protected' (old on-disk session state
with a transcript key is tolerated on read, never re-emitted).
- security-sidecar-entry.ts needed zero changes: it serializes
getClassifierStatus() verbatim and no consumer read .transcript (verified
in sidecar-client + server.ts).
- BROWSER.md security section matches reality (ensemble knob gone, 112MB not
22MB, sidecar hosting documented). combineVerdict/THRESHOLDS retained as
the pure, tested combiner of record — comments now flag transcript/deberta
votes as producer-less.
Net: 26 pass in security.test.ts incl. a NEW regression test for stale-
transcript disk tolerance; egress-receipt tripwire green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| app | ||
| host-adapters | ||
| resolvers | ||
| analytics.ts | ||
| archetypes.ts | ||
| brain-cache-spec.ts | ||
| build-app.sh | ||
| build.sh | ||
| capture-baseline.ts | ||
| compare-pr-version.ts | ||
| declared-annotation.ts | ||
| detect-bump.ts | ||
| dev-skill.ts | ||
| discover-skills.ts | ||
| eval-compare.ts | ||
| eval-list.ts | ||
| eval-select.ts | ||
| eval-summary.ts | ||
| eval-watch.ts | ||
| garry-output-comparison.ts | ||
| gen-llms-txt.ts | ||
| gen-skill-docs.ts | ||
| gstack-schema-pack.ts | ||
| host-config-export.ts | ||
| host-config.ts | ||
| jargon-list.json | ||
| models.ts | ||
| one-way-doors.ts | ||
| preflight-agent-sdk.ts | ||
| proactive-suggestions.json | ||
| psychographic-signals.ts | ||
| question-registry.ts | ||
| setup-scc.sh | ||
| skill-check.ts | ||
| slop-diff.ts | ||
| task-emission-schema.ts | ||
| test-free-shards.ts | ||
| test-paid-shards.ts | ||
| test-strict-output.ts | ||
| update-readme-throughput.ts | ||
| write-version-files.sh | ||