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

agents/voice-trainer.md

@@ -133,7 +133,7 @@ Architecture: [prose/sectioned/framework]
 
 ### Analysis Process
 
-1. **Gather** — Read all files in `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/voice-samples/`, existing profile from `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/profile/user-profile.md`, and template from `config/user-profile.template.md`
+1. **Gather (published-only gold signal first)** — Read the user's actual published posts from `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/ingest/published/` (`provenance=published` — the highest-trust source). Then read the human-curated `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/voice-samples/` corpus (kept as a tributary, not reshaped), the existing profile from `${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/profile/user-profile.md`, and the template from `config/user-profile.template.md`. **Never learn voice patterns from any content marked `provenance=ai-draft`** — a content engine that learns its own voice from its own drafts collapses toward its priors (this generalises voice-scrubber's "gold standard = approved editions, never the draft corpus"). **Fence:** any future auto-capture into a learning corpus (the voice-samples template's Stop-hook hint) MUST tag provenance and admit `provenance=published` only — never blind-append generated drafts.
 2. **Analyze** — Apply all six dimensions to each sample. Note dates for temporal analysis. Flag inconsistent samples as outliers or evolution.
 3. **Synthesize** — Patterns in 70%+ of samples = core traits. 40-70% = situational traits (note context). <40% = experimental traits. Track temporal trends.
 4. **Build** — Compile into Voice Profile Document format. Include confidence levels (high/medium/low) and concrete examples for every trait.
@@ -141,12 +141,15 @@ Architecture: [prose/sectioned/framework]
 
 ### Sample Quality Priorities
 
+0. **`ingest/published/` records (`provenance=published`) — the gold signal; rank above all else.**
 1. Published posts with high engagement (audience-validated authenticity)
 2. Recent samples (last 6 months reflect current voice)
 3. Author-confirmed samples ("this sounds like me")
 4. Longer samples (more data points)
 5. Varied contexts (different content types reveal range)
 
+**Exclude unconditionally: anything marked `provenance=ai-draft`** (the model-collapse guard — never train voice on the engine's own drafts).
+
 Flag if: fewer than 5 samples (low confidence), single time period (temporal bias), or contradictory patterns (possible ghostwriting).
 
 ## Voice Drift Detection

docs/second-brain/ingest-manual-import.md

@@ -0,0 +1,87 @@
+# Manual-import contract — ingest + the published gold signal (SB-S1)
+
+> The contract for getting your **actual published posts** into the second brain as the
+> **gold signal** (`provenance=published`) that voice/profile learning is allowed to learn from.
+> Part of the second-brain arc (`architecture.md`); landed in SB-S1.
+
+## Why this exists
+
+Profile and voice must learn from **human-published content only** — never from what the engine
+itself drafted. A content engine that learns its own voice from its own drafts collapses toward its
+own priors (model collapse). So the brain has one provenance vocabulary — `human | published | ai-draft`
+— and the learning surfaces are bound to `published` and **forbidden from `provenance=ai-draft`**.
+
+A published post already lands in three non-referencing places today (the state file's `## Recent Posts`,
+the dead `analytics/content-history.md`, and `analytics/posts/*.json` from the CSV) — but **none of them
+holds the full post text**. Voice learning needs the verbatim text, so `ingest/published/` storing it is
+additive, not a re-count. (Threading a shared id across those silos is a later slice, SB-S3.)
+
+## The drop-zone model
+
+```
+${LINKEDIN_STUDIO_DATA:-$HOME/.claude/linkedin-studio}/ingest/
+  inbox/        # drop-zone: paste a published post here as a .md file (manual, or a future connector)
+  published/    # processed gold records, provenance=published — one file per post, <id>.md
+```
+
+- **`inbox/`** — you drop raw post files here (top-level `*.md`, one post per file).
+- **`published/`** — the `ingest` CLI writes processed, provenance-tagged records here. `<id>.md` where
+  `<id> = sha256(verbatim body)[:12]` — byte-identity, so the same post never duplicates and two
+  genuinely different posts never collide.
+
+## CLI usage
+
+Run from `scripts/brain` (`node --import tsx src/cli.ts <cmd>`), or via the package's `start` script.
+
+```bash
+# one post from a file → ingest/published/<id>.md, tagged provenance=published
+brain ingest --file path/to/post.md [--source manual] [--date 2026-05-26]
+
+# process everything dropped in ingest/inbox/ (top-level *.md, skips dotfiles), non-destructive
+brain ingest --scan-inbox
+
+# inspect the gold corpus — id · provenance · date · first line (eyeball that nothing ai-draft leaked)
+brain published list [--json]
+```
+
+- `--date` is the real publish date; it defaults to the ingest date when omitted.
+- Re-ingesting the same body is a **no-op** (idempotent). An id-collision with a *differing* body is
+  disambiguated to `<id>-2.md` — a differing gold record is **never silently dropped**.
+- `ingest` **creates `ingest/published/` on demand** — it does not require a prior `brain init`.
+
+## Record file grammar (no YAML)
+
+One file per post: a fixed five-line header, a `---` sentinel, then the **verbatim body**.
+
+```
+id: 1a2b3c4d5e6f
+provenance: published
+published_date: 2026-05-26
+captured_at: 2026-06-23
+source: manual
+---
+The verbatim post body goes here.
+
+It may contain anything — blank lines, ] | characters, even a line that looks
+like --- — because the parser splits on the FIRST sentinel only.
+```
+
+`parse ∘ serialize` is an exact identity over all six fields including the body. A record in
+`published/` whose `provenance` is anything other than `published` is treated as a **corruption signal**
+and rejected on parse.
+
+## The published-only learning rule (and its honest limit)
+
+- `agents/voice-trainer.md` is wired to read `ingest/published/` as its primary gold source and to
+  **exclude `provenance=ai-draft` unconditionally**. This wiring is **gate-enforced** by a structure-lint
+  (`scripts/test-runner.sh`, the Brain Published-Only Invariant section): the lint asserts the agent
+  carries both the `ingest/published` source and the `provenance=ai-draft` exclusion.
+- **Honest limit:** the *wiring* is gate-enforced, but an agent instruction can still be ignored at
+  runtime — the gate proves the rule is present, not that the model obeyed it on a given run. The
+  strongest enforcement short of executing the agent.
+
+## What SB-S1 does NOT do
+
+No consolidation loop and **no automatic `brain/profile.md` mutation** (SB-S2 owns the sleep-time
+profile-diff loop) · no session-start wiring · no cross-silo id threading (SB-S3) · no connector
+(SB-S4). `source` carries a forward-compatible field for a future connector, but no connector code ships.

scripts/test-runner.sh

@@ -711,7 +711,7 @@ if [ -x "$BR_DIR/node_modules/.bin/tsx" ]; then
   BR_OUT=$( set +e; (cd "$BR_DIR" && npm test) 2>&1; echo "BR_EXIT:$?" )
   BR_EXIT=$(echo "$BR_OUT" | grep -oE 'BR_EXIT:[0-9]+' | grep -oE '[0-9]+' | head -1)
   BR_TESTS=$(echo "$BR_OUT" | grep -oE 'tests [0-9]+' | grep -oE '[0-9]+' | tail -1)
-  BRAIN_TESTS_FLOOR=34  # SB-S0: id(11) + profile(6) + fold(12) + scaffold(5)
+  BRAIN_TESTS_FLOOR=63  # SB-S0 34 [id(11)+profile(6)+fold(12)+scaffold(5)] + SB-S1 29 [ingest(14)+publish(9)+cli(6)]
   if [ "$BR_EXIT" = "0" ] && [ -n "$BR_TESTS" ] && [ "$BR_TESTS" -ge "$BRAIN_TESTS_FLOOR" ]; then
     pass "brain suite green: $BR_TESTS tests pass (floor $BRAIN_TESTS_FLOOR)"
   else
@@ -723,6 +723,62 @@ fi
 
 echo ""
 
+# --- Section 16c: Brain Published-Only Invariant (SB-S1) ---
+echo "--- Brain Published-Only Invariant ---"
+
+# SB-S1 wires voice-trainer to learn from the published gold signal ONLY: the agent
+# must (a) name ingest/published/ as a source AND (b) carry the explicit exclusion of
+# provenance=ai-draft (the model-collapse guard — never train voice on the engine's own
+# drafts). Both literals are required. voice-trainer.md ALREADY contains "AI-generated"
+# (a drift-cause description, line ~175), so a loose ai.?draft pattern would pass
+# vacuously — we grep the EXACT literals with grep -F. The contract doc must also state
+# the rule. Non-vacuity self-test mirrors Sections 8/13/17: a probe counts as "wired"
+# iff it carries BOTH literals; probes missing either (incl. one with "AI-generated" but
+# not "ai-draft") must NOT count as wired. The wiring is gate-enforced; the agent's
+# runtime OBEDIENCE is not provable here (stated honestly in the contract doc).
+PUB_LIT='ingest/published'
+DRAFT_LIT='provenance=ai-draft'
+
+pub_wired() {  # $1 = text; wired iff BOTH literals present (echo twice — grep consumes stdin)
+  echo "$1" | grep -qF "$PUB_LIT" && echo "$1" | grep -qF "$DRAFT_LIT"
+}
+
+PUB_SELFTEST_OK=1
+if ! pub_wired "reads from ingest/published/ and excludes provenance=ai-draft"; then
+  PUB_SELFTEST_OK=0; echo "  non-vacuity FAIL: a fully-wired probe was not detected"
+fi
+while IFS= read -r probe; do
+  [ -z "$probe" ] && continue
+  if pub_wired "$probe"; then
+    PUB_SELFTEST_OK=0; echo "  false-positive FAIL: under-wired probe accepted -> $probe"
+  fi
+done <<'NEGATIVE16C'
+reads from ingest/published/ but never states the draft exclusion
+excludes provenance=ai-draft but never names the published source
+flags AI-generated drift but carries neither required literal
+NEGATIVE16C
+if [ "$PUB_SELFTEST_OK" -eq 1 ]; then
+  pass "published-only self-test: full wiring detected; 3 under-wired forms rejected (incl. 'AI-generated'-only)"
+else
+  fail "published-only self-test failed — the invariant lint is vacuous or over-eager"
+fi
+
+VT="agents/voice-trainer.md"
+if grep -qF "$PUB_LIT" "$VT" && grep -qF "$DRAFT_LIT" "$VT"; then
+  pass "voice-trainer.md wired to published-only (names '$PUB_LIT', excludes '$DRAFT_LIT')"
+else
+  fail "voice-trainer.md missing published-only wiring — needs both '$PUB_LIT' and '$DRAFT_LIT'"
+fi
+
+PUB_DOC="docs/second-brain/ingest-manual-import.md"
+if grep -qF "$DRAFT_LIT" "$PUB_DOC"; then
+  pass "ingest-manual-import.md documents the published-only rule ('$DRAFT_LIT')"
+else
+  fail "ingest-manual-import.md missing the published-only rule literal '$DRAFT_LIT'"
+fi
+
+echo ""
+
 # --- Section 17: De-Niche Guard (B-S1 + B-S2) ---
 echo "--- De-Niche Guard ---"
 
@@ -794,8 +850,13 @@ echo ""
 # The lint self-modifies its own checks, so a green run could mask a silently dropped
 # assertion. Pin the total pass()+fail() invocations as a monotonic floor; the count
 # may only grow (brief-reviewer assumption 3). History: 74 pre-M0; +1 for the SB-S0
-# brain-suite floor (Section 16b) = 75. Runs last so TOTAL_CHECKS sees every prior check.
-ASSERT_BASELINE_FLOOR=75
+# brain-suite floor (Section 16b) = 75; +3 for SB-S1's three UNCONDITIONAL Section-16c
+# checks (published-only self-test + voice-trainer grep + contract-doc grep) = 78.
+# NB: the floor tracks the deps-absent MINIMUM (conditional TS suites warn-skip and drop
+# the count), so it is bumped only by UNCONDITIONAL new checks — NOT pinned to the
+# deps-present TOTAL_CHECKS (that would zero the warn-skip margin and false-fail a fresh
+# clone). Runs last so TOTAL_CHECKS sees every prior check.
+ASSERT_BASELINE_FLOOR=78
 TOTAL_CHECKS=$((PASS + FAIL))
 if [ "$TOTAL_CHECKS" -ge "$ASSERT_BASELINE_FLOOR" ]; then
   pass "assertion-count anti-erosion: $TOTAL_CHECKS checks >= baseline floor $ASSERT_BASELINE_FLOOR"