linkedin-studio/docs/second-brain
Kjell Tore Guttormsen ac532f9218 feat(linkedin-studio): SB-S1 wire voice-trainer to published-only + gate-enforce it [skip-docs]
voice-trainer's Gather step now reads ingest/published/ (provenance=published) as
the primary gold source, keeps voice-samples as a human tributary (not reshaped),
forbids learning from provenance=ai-draft, and fences the auto-append trap. New gate
Section 16c (Brain Published-Only Invariant) enforces the wiring with exact-literal
greps (grep -F 'ingest/published' + 'provenance=ai-draft') + a non-vacuity self-test
(rejects an 'AI-generated'-only probe), against voice-trainer.md + the new contract
doc docs/second-brain/ingest-manual-import.md. BRAIN_TESTS_FLOOR 34→63; assertion
floor 75→78 (+3 unconditional checks; not pinned to deps-present TOTAL to preserve the
warn-skip margin). Gate 90→93/0/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RigJBiRFNtFZKCz21qNbQ4
2026-06-23 15:02:32 +02:00
..
research docs(linkedin-studio): second-brain architecture (approved) + 3 research reports 2026-06-23 12:55:17 +02:00
architecture.md feat(linkedin-studio): second-brain SB-S0 foundation — brain/ scaffold + profile fold + id/provenance spine [skip-docs] 2026-06-23 14:05:24 +02:00
brief-sb-s1.md docs(linkedin-studio): second-brain SB-S1 brief + plan (review-hardened) 2026-06-23 14:51:29 +02:00
brief.md docs(linkedin-studio): second-brain SB-S0 brief + plan (review-hardened) 2026-06-23 13:24:18 +02:00
ingest-manual-import.md feat(linkedin-studio): SB-S1 wire voice-trainer to published-only + gate-enforce it [skip-docs] 2026-06-23 15:02:32 +02:00
plan-sb-s0.md docs(linkedin-studio): second-brain SB-S0 brief + plan (review-hardened) 2026-06-23 13:24:18 +02:00
plan-sb-s1.md docs(linkedin-studio): second-brain SB-S1 brief + plan (review-hardened) 2026-06-23 14:51:29 +02:00