chore(linkedin-studio): SB-S2 gate brain floor 63→82 + consolidation-loop doc

Bump BRAIN_TESTS_FLOOR to 82 (SB-S2 adds consolidate(12)+consolidate-cli(7)).
No new test-runner section → ASSERT_BASELINE_FLOOR unchanged at 78 (the hook
SC6 test runs separately via `node --test hooks/scripts/__tests__/*.test.mjs`,
not the structure gate). Add docs/second-brain/consolidation-loop.md (CLI usage,
engine rules, the candidate-file session↔engine contract, operator gate, honest
limits incl. no-reader-until-S3). Gate 93/0/0; hook suite 136/0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RigJBiRFNtFZKCz21qNbQ4

docs/second-brain/consolidation-loop.md

@@ -0,0 +1,74 @@
+# Consolidation loop — the compounding mechanism (SB-S2)
+
+> How the second brain turns the published gold signal into an ever-improving, drift-resistant
+> `brain/profile.md` — operator-invoked, operator-gated, deterministic. Part of the second-brain arc
+> (`architecture.md`); landed in SB-S2.
+
+## The shape
+
+The loop is **operator-invoked** ("sleep-time" = when you run it), not automatic — the session-start
+hook is zero-dep and cannot run AI, so it only **nudges** when consolidation is due. The pass itself is:
+
+```
+brain consolidate --gather      # 1. dump new published deltas + the current profile
+   → (the session reads them and extracts a Candidate[] JSON)
+brain consolidate --propose --candidates cand.json   # 2. deterministic diff → brain/pending-diff.{md,json}
+   → (you review brain/pending-diff.md — the [OPERATØR] gate)
+brain consolidate --apply --diff brain/pending-diff.json --confirm   # 3. the ONLY write to profile.md
+```
+
+`--apply` records `brain/consolidation-state.json` `{last_run}`; the session-start nudge reads it +
+counts `ingest/published/*.md` to know when to nudge again. Roll back any apply via git.
+
+## The deterministic engine (`scripts/brain/src/consolidate.ts`)
+
+`proposeDiff({current, candidates, today, opts})` classifies each candidate (matched to existing facts
+by the candidate's `key`):
+
+| Rule | Condition | Effect |
+|------|-----------|--------|
+| **reject** | `provenance: ai-draft` | dropped — never learns from the engine's own drafts (model-collapse guard) |
+| **add** | no matching fact, provenance `published`/`human` | new dynamic fact, `evidence_count: 1` |
+| **evidence-bump** | matching fact, same value | `evidence_count++`, `last_seen = today` |
+| **promote** | a dynamic fact reaches `N = 3` observations | dynamic → static |
+| **conflict** | matching key, different value | **keep both**, timestamped, with DISTINCT ids; the old fact is untouched (**no supersede** in S2 — that's S3) |
+| **decay-flag** | a dynamic fact's `last_seen` > `90` days | listed in `staleFlags` (informational; never auto-removed) |
+
+**Id model (no duplicate ids):** a concept's primary fact id is `mintEntityId({kind:'observed', key})`;
+a conflict alt fact id is `mintContentId('observed-alt:'+key+'::'+value+'::'+date)` — byte-distinct, so
+two facts never share an id. The SB-S0 folded `profile-field` static seeds use a different kind, so
+consolidation never mutates them (immutable in S2). `applyDiff` produces a `ProfileDoc` that round-trips
+exactly through the SB-S0 grammar; re-running is idempotent (bump, not duplicate).
+
+Defaults: `promoteThreshold = 3`, `decayDays = 90` (operator-confirmed).
+
+## The candidate file — the session↔engine contract
+
+`--propose --candidates <file.json>` takes a JSON **array** of candidates; each is validated
+(malformed → non-zero exit, nothing written):
+
+```json
+[
+  { "key": "primary-expertise", "value": "AI governance in the public sector",
+    "provenance": "published", "source": "published:1a2b3c4d5e6f", "observed_date": "2026-05-26" }
+]
+```
+
+- `key`, `value`, `source`, `observed_date` — non-empty strings; `provenance ∈ {human, published, ai-draft}`.
+- `key` and `value` must be **single-line** (no newline/CR — the profile grammar is one fact per line).
+- The session produces this from `--gather`'s output. The engine guarantees the *mechanics*; the *quality*
+  of the candidates is the session's job (see limits).
+
+## Honest limits
+
+- **The loop's value depends on the session's extraction.** The engine only guarantees threshold/conflict/
+  decay/provenance mechanics. Garbage candidates → a garbage diff. The operator gate + candidate-shape
+  validation catch shape errors, not insight quality.
+- **`brain/profile.md` has no reader yet.** S2 evolves the profile; wiring content agents/commands to
+  *consume* it is SB-S3. The value is deferred: the profile compounds now so S3's reader inherits rich data.
+- **No supersede / no auto-demotion.** Conflicts keep both; stale facts are flagged, never auto-removed —
+  the operator (or S3) reconciles. Conflict alt facts persist until then.
+- **No AI at session-start.** The nudge is a deterministic file-count + sidecar read; the consolidation
+  pass is always operator-invoked.
+- **The session-start nudge is consolidation-due only** — it counts published records + days since last run;
+  it does not parse `profile.md` for per-fact staleness (that cost/parser is deferred).