ltcai 8.8.0 → 9.0.0

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,11 +1,11 @@
 # Community And Plugins
 
-Current release: **8.8.0 — Brain Core Extraction & Recall Proof Hardening**.
+Current release: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 LatticeAI defines the path from a strong local-first framework (8.4.0
 action-aware baseline, 8.5.0 registry+DI hardening, 8.6.0 capture/navigation
-reliability, 8.7.0 runtime-state hygiene, and 8.8.0 Brain Core extraction
-readiness) to a product ecosystem. The
+reliability, 8.7.0 runtime-state hygiene, 8.8.0 Brain Core extraction
+readiness, 8.9.0 scoped Tool API hardening, and 9.0.0 cleanup closure) to a product ecosystem. The
 immediate goal is small and practical: make it clear how
 contributors can extend the Brain without weakening local-first trust,
 workspace scoping, or release quality.

package/docs/DEVELOPMENT.md

@@ -1,10 +1,10 @@
 # Lattice AI Development
 
-Current release: **8.8.0 — Brain Core Extraction & Recall Proof Hardening**.
+Current release: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 This document is for contributors working on the local-first Digital Brain
 codebase. Product positioning and quick start stay in `README.md`; release
-history is intentionally limited to 7.0.0-8.8.0 in `docs/CHANGELOG.md` and
+history is intentionally limited to 8.0.0-9.0.0 in `docs/CHANGELOG.md` and
 `RELEASE.md`.
 
 ## Product Contract
@@ -16,8 +16,8 @@ Engineering work should preserve these boundaries:
 
 - the Brain is the durable asset;
 - models are replaceable voices;
-- SQLite is the default local store;
-- PostgreSQL, Docker, cloud models, downloads, update checks, Telegram, and
+- SQLite is the live local Brain store;
+- PostgreSQL scale/migration tooling, Docker, cloud models, downloads, update checks, Telegram, and
   Brain Network are opt-in;
 - import-only paths must not initialize MLX/GPU, write files, or make network
   calls;
@@ -114,10 +114,10 @@ For user-facing, API, runtime, release, or packaging changes, check:
 Release/publish examples must use exact target-version filenames. Do not
 document wildcard artifact upload commands.
 
-For 8.8.0 release work, exact artifacts are:
+For 9.0.0 release work, exact artifacts are:
 
-- `dist/ltcai-8.8.0-py3-none-any.whl`
-- `dist/ltcai-8.8.0.tar.gz`
-- `ltcai-8.8.0.tgz`
-- `dist/ltcai-8.8.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_8.8.0_aarch64.dmg`
+- `dist/ltcai-9.0.0-py3-none-any.whl`
+- `dist/ltcai-9.0.0.tar.gz`
+- `ltcai-9.0.0.tgz`
+- `dist/ltcai-9.0.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_9.0.0_aarch64.dmg`

package/docs/LEGACY_COMPATIBILITY.md

@@ -1,6 +1,6 @@
 # Legacy Compatibility Map
 
-Current target: **8.8.0 — Internal shim removal & Brain Core extraction prep**.
+Current target: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 Lattice AI is moving toward a smaller, modular architecture centered on
 `lattice_brain`, `latticeai.services`, `latticeai.api`, and `latticeai.runtime`.

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **8.8.0 — Brain Core Extraction & Recall Proof Hardening**.
+Current release: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 The first-run goal is a five-minute path from "I opened the app" to "my Brain
 has a source, a question, and proof." This page is the product contract behind
@@ -32,7 +32,7 @@ read the docs first.
 
 ## Release Gate
 
-8.8.0 treats onboarding as a release gate, not marketing copy. The current
+9.0.0 treats onboarding as a release gate, not marketing copy. The current
 machine-checkable product readiness report requires this five-minute contract,
 the Brain Home surface, setup helpers, graph ingestion tests, and exact release
 artifact documentation before the release can be called complete.

package/docs/PRODUCT_DIRECTION_REVIEW.md

@@ -23,8 +23,9 @@ Already aligned:
 - The post-setup home is the living Brain plus conversation.
 - The graph appears only after progressive depth: Brain -> Memories ->
   Knowledge -> Relationships -> Graph.
-- Brain Core, SQLite default storage, optional PostgreSQL/pgvector scale mode,
-  backup/restore, and encrypted `.latticebrain` archives support user ownership.
+- Brain Core, SQLite live local storage, optional PostgreSQL/pgvector
+  scale/migration tooling, backup/restore, and encrypted `.latticebrain`
+  archives support user ownership.
 - Models are treated as swappable runtime workers rather than the durable asset.
 
 Gaps corrected in this review:

package/docs/ROADMAP_RECOMMENDATIONS.md

@@ -5,43 +5,12 @@ small release-sized work. The operating principle stays unchanged:
 
 > Models are temporary. Knowledge is durable. The Brain is the product.
 
-## 7.3.0 Applied Slice
+## Applied Release History
 
-7.3.0 implements the first narrow slice of the roadmap:
-
-- Runtime evolution: single-agent and multi-agent execution share
-  `agent-run-contract/v1`, making mode/status/timeline evidence inspectable.
-- Hybrid search optimization: the Brain quality gate now includes deterministic
-  recall and ranking regression thresholds.
-- Security and trust: run contracts distinguish runtime type and execution mode
-  so simulated output is not presented as real execution.
-
-## 7.4.0 Applied Slice
-
-7.4.0 completes the next roadmap slice without deferring it:
-
-- Runtime convergence: agent runs, workflow runs, audit events, and realtime
-  events all expose the `agent-run-contract/v1` family envelope while keeping
-  legacy top-level fields for compatibility.
-- Trust and operations: persisted run rows refresh their contract through
-  queued, running, terminal, cancelled, and interrupted states; audit events are
-  contracted only after secret redaction.
-- Retrieval quality and scale: the CI quality gate now seeds a real local
-  Knowledge Graph corpus and scores SearchService hybrid retrieval with judged
-  queries, recall, precision, NDCG, and must-include hit-rate thresholds.
-
-## 7.5.0 Applied Slice
-
-7.5.0 burns down the remaining 7.4.0 risk instead of deferring it:
-
-- Contract consumption: AgentRuntime and realtime feed APIs now emit compact
-  `contracts` views so UI, replay, admin, and export consumers can depend on the
-  shared family envelope directly.
-- Retrieval scale: the corpus fixture now runs against 250+ local records while
-  keeping judged queries, graded relevance, and must-include expectations.
-- Release trust: stale artifact mixing is handled through clean exact-version
-  artifact generation, npm audit findings are cleared, and the Tauri 2 stack is
-  updated past the old `block v0.1.6` future-incompatibility warning.
+Release-specific applied-slice history is now kept only for 8.0.0 and newer in
+[docs/CHANGELOG.md](CHANGELOG.md) and [RELEASE.md](../RELEASE.md). Pre-8.0.0
+release-history notes were removed from the tracked documentation surface during
+the 9.0.0 documentation cleanup.
 
 ## Near-Term Tracks
 
@@ -79,3 +48,59 @@ small release-sized work. The operating principle stays unchanged:
 - Interoperability with Obsidian, Notion, Email, Calendar, Git, Slack, and Teams.
 - Encrypted Brain Network sharing.
 - Plugin marketplace and public benchmarks.
+
+## Large-Scale Work Feasibility Assessment (2026-07-07)
+
+2026-07-07 코드베이스 검사 + 테스트 실행 결과 기반. (app_factory 1214줄, workspace_os 1391줄, 최근 AgentRuntime facade + KG mixin 분해 완료, 833 unit tests passed)
+
+### 1. Knowledge Graph / Retrieval at Large Corpus Scale (가장 추천, 기반 탄탄)
+- Incremental/background ingestion + advanced dedup(콘텐츠해시 이상), conflict resolution, merge.
+- Larger corpus benchmarks (현재 250+ → 수천~수만 아이템), latency budget, channel별 진단.
+- pgvector 풀 프로덕션 경로 + 마이그레이션.
+- **실행 가능성**: IngestionPipeline + provenance + vector mixin + benchmark fixtures 이미 존재. discovery/retrieval 분해 완료. hooks lifecycle 통합됨. 대형 작업으로 적합. 테스트: test_ingestion_pipeline.py 14/14 green.
+
+### 2. Multi-Modal Brain (스키마 준비됨, 구현 공백 큼)
+- 이미지: vision LLM describe + 임베딩, IMAGE/IMAGE_TEXT 노드 + CONTAINS_IMAGE 엣지 완성, UI 증거 표시.
+- 오디오(전사), 비디오(키프레임).
+- **실행 가능성**: schema.py에 IMAGE/IMAGE_TEXT/CONTAINS_IMAGE 정의됨. discovery_index.py에 PIL + pytesseract OCR (include_ocr) 부분 구현. embeddings.py / LLMRouter에 vision 지원 부재. retrieval도 이미지 노드 미처리. ingestion 라우팅 확장 필요. 대형 + 차별화 포인트.
+
+### 3. Server / Runtime Composition 완전화 (구조 부채 해소)
+- app_factory.py 잔여 로직 추가 추출 (더 많은 wiring → runtime/* 전용 모듈).
+- dict(locals()) 레거시 제거, 강력한 RuntimeContext / DI.
+- Config 중앙화 감사 및 강제 (core/config.py 이미 중앙).
+- **실행 가능성**: 최근 review0707 + decomp (1214줄로 감소, runtime/ 디렉토리 풍부) 후에도 여전히 1.2k 라인. AGENTS.md 우선순위 #3,4 정확히 매치. AgentRuntime은 lattice_brain/runtime/agent_runtime.py 로 facade 추출 완료. ToolRegistry도 core/ + services 분리 진행.
+
+### 4. Proactive Synthesis + Temporal / Contradiction (최근 작업 연장)
+- 백그라운드 합성 잡, 그래프 이력 기반 모순 검출, temporal 쿼리.
+- 최근 커밋(Brain synthesis memories, follow-up) 을 스케줄 + 자동화로 확장.
+- **실행 가능성**: MultiAgentOrchestrator + workflow_engine + IngestionPipeline + Brain Brief 이미 wired. hooks/audit 있음. agent synthesis UI 표면 최근 추가. 대형 기능으로 자연스러운 확장.
+
+### 5. Ecosystem / Interop + Plugin Marketplace (외부 연동 대형)
+- Obsidian/Notion/Email/Calendar import bridge (MCP 또는 전용 ingestion).
+- 서명된 플러그인, 원격 카탈로그, marketplace UI.
+- Brain Network (암호화 공유).
+- **실행 가능성**: plugins/ (hello-world, git-insights), mcp_registry, marketplace.py, core/plugins.py 존재. ingestion이 단일 관문. 하지만 실제 외부 브릿지/마켓플레이스 UI/보안 스캔은 대형.
+
+기타: Tauri auto-update + native scale, Workflow Designer 프론트엔드 완성, VSCode 확장 심화 통합 등.
+
+**검증 결과 (2026-07-07)**:
+- Core imports (Config, IngestionPipeline, AgentRuntime, ToolRegistry): OK
+- Unit tests: 833 passed (tests/unit/)
+- Ingestion specific: 14 passed
+- Agent runtime tests: 29 passed
+- Frontend lint: typecheck + privacy + OpenAPI 335 paths + lint all pass
+- Git: clean (inspection 시점)
+
+**2026-07-07 pts_grok 대형 후보 1~5 슬라이스 실행 결과 (자율 진행)**:
+- 1. KG/Retrieval: background ingestion queue seam, schedule_background, vector index scale diagnostics, backlog reasons/samples, coverage ratio, and rebuild latency budget.
+- 2. Multimodal: offline VisionStub describe/embed path and discovery_index vision_caption fallback so image files have searchable evidence without remote calls.
+- 3. Server decomp: explicit _RUNTIME_BUNDLE in app_factory as the migration contract toward DI while dict(locals()) compatibility remains.
+- 3a. Server decomp follow-up: filtered app_factory runtime namespace so internal scratch imports/runtime dicts no longer leak through lazy server_app compatibility; namespace reduced from 300 to 253 keys while legacy helpers remain, with typed RuntimeBundle added behind legacy _RUNTIME_BUNDLE.
+- 4. Proactive/Temporal: stronger MemoryQualityManager conflict detection, including pairwise opposite-preference and temporal-negation flags.
+- 4a. Proactive UX follow-up: Brain Brief now emits proactive_actions, and BrainHome renders one-click ask/delegate/review/graph action cards.
+- 4b. Proactive UX completion: BrainHome now keeps a local activity trail for suggested actions, showing whether Brain ask, Agent delegation, Review draft, or graph navigation actions are running, completed, or failed.
+- 5. Interop/Marketplace: ingestion_bridge marketplace templates and /marketplace/interop/bridges exposure for future Obsidian/Calendar-style connector imports through unified-ingestion.
+- 총 affected tests: 45 passed in the first targeted gate. Broader lint/static/doc checks are run before commit.
+- 남은: 각 슬라이스는 기반 확장. full background workers, real local VLM/image embeddings, full locals() removal, graph-level temporal queries, and production connector installs remain follow-up work.
+
+이 항목들은 "대형사이즈" 에도 할 만하며, mission (local-first, KG, AgentRuntime, security) 과 AGENTS 우선 리팩토링 순서에 부합. 작은 슬라이스로 시작 추천.

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **8.8.0 — Brain Core Extraction & Recall Proof Hardening**.
+Current release: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 Lattice AI is local-first, explicit about external communication, and honest
 when a capability is unavailable.
@@ -34,6 +34,10 @@ External communication requires configuration plus a user/admin action:
 
 Token presence alone must not start external communication.
 
+Authenticated history, Knowledge Graph reads, and Tool API calls must also stay
+inside the caller's user/workspace scope. Direct HTTP/MCP tool routes run
+ToolRegistry policy before hooks or handlers execute.
+
 ## Consent And Honesty Gates
 
 Lattice AI should fail closed or show an unavailable state for:

package/docs/WHY_LATTICE.md

@@ -1,6 +1,6 @@
 # Why Lattice AI Exists
 
-Current release: **8.8.0 — Brain Core Extraction & Recall Proof Hardening**.
+Current release: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 **Lattice AI is a local-first Digital Brain that keeps your knowledge durable
 across any AI model.**
@@ -32,8 +32,9 @@ The graph matters, but it is not the product identity. The product identity is a
 local-first Digital Brain: a place where the user can talk, add sources, watch
 memory grow, and inspect the Knowledge Graph when they need proof.
 
-In 8.8.0 the first screen is intentionally not a dashboard. The living Brain,
-conversation composer, evidence-backed Brain Brief, and five-minute onboarding
+In 9.0.0 the first screen is intentionally not a dashboard. The living Brain,
+conversation composer, evidence-backed Brain Brief, scoped memory isolation,
+and five-minute onboarding
 path appear together so the user immediately knows what matters, what to add,
 and why the answer is grounded in local memory.
 

package/docs/architecture.md

@@ -1,5 +1,9 @@
 # Lattice AI Architecture
 
+> Historical subsystem note. The canonical current architecture document is
+> [`ARCHITECTURE.md`](../ARCHITECTURE.md). This file preserves the v3.6.0
+> Knowledge Graph First architecture detail for background.
+
 > v3.6.0 — **Knowledge Graph First.** Every data source converges into the graph
 > through one unified ingestion pipeline (`latticeai/services/ingestion.py`), with
 > formalized entities/relationships (`docs/kg-schema.md`), browser/web inputs,

package/docs/kg-schema.md

@@ -1,6 +1,6 @@
 # Knowledge Graph Schema
 
-Current release: **8.8.0 — Brain Core Extraction & Recall Proof Hardening**.
+Current release: **9.0.0 — Code Review Closure & Runtime Cleanup**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `kg_schema.py`

package/lattice_brain/__init__.py

@@ -26,7 +26,7 @@ from .storage import (
     storage_from_env,
 )
 
-__version__ = "8.8.0"
+__version__ = "9.0.0"
 
 __all__ = [
     "AgentRuntime",

package/lattice_brain/archive.py

@@ -9,7 +9,6 @@ restore on another machine without contacting a service.
 from __future__ import annotations
 
 import base64
-import hashlib
 import io
 import json
 import os
@@ -27,6 +26,8 @@ from cryptography.hazmat.primitives.ciphers.aead import AESGCM
 from cryptography.exceptions import InvalidTag
 from cryptography.hazmat.primitives.kdf.pbkdf2 import PBKDF2HMAC
 
+from .utils import sha256_file as _sha256_file
+
 
 ARCHIVE_FORMAT = "latticebrain.encrypted"
 ARCHIVE_VERSION = 2
@@ -68,15 +69,9 @@ def _derive_key(passphrase: str, salt: bytes) -> bytes:
 
 
 def _sha256_bytes(data: bytes) -> str:
-    return hashlib.sha256(data).hexdigest()
+    import hashlib
 
-
-def _sha256_file(path: Path) -> str:
-    h = hashlib.sha256()
-    with open(path, "rb") as fh:
-        for block in iter(lambda: fh.read(65536), b""):
-            h.update(block)
-    return h.hexdigest()
+    return hashlib.sha256(data).hexdigest()
 
 
 def _safe_json(value: Any) -> Any:

package/lattice_brain/conversations.py

@@ -60,27 +60,76 @@ class ConversationStore:
                   user_nickname TEXT,
                   source TEXT,
                   timestamp TEXT NOT NULL,
-                  metadata_json TEXT NOT NULL DEFAULT '{}'
+                  metadata_json TEXT NOT NULL DEFAULT '{}',
+                  workspace_id TEXT,
+                  organization_id TEXT
                 );
                 CREATE INDEX IF NOT EXISTS idx_conv_messages_conv
                   ON conversation_messages(conversation_id);
                 CREATE INDEX IF NOT EXISTS idx_conv_messages_time
                   ON conversation_messages(timestamp);
+                CREATE INDEX IF NOT EXISTS idx_conv_messages_user
+                  ON conversation_messages(user_email);
                 """
             )
+            columns = {row["name"] for row in conn.execute("PRAGMA table_info(conversation_messages)").fetchall()}
+            if "workspace_id" not in columns:
+                conn.execute("ALTER TABLE conversation_messages ADD COLUMN workspace_id TEXT")
+            if "organization_id" not in columns:
+                conn.execute("ALTER TABLE conversation_messages ADD COLUMN organization_id TEXT")
+            conn.execute(
+                """
+                CREATE INDEX IF NOT EXISTS idx_conv_messages_workspace
+                  ON conversation_messages(workspace_id)
+                """
+            )
+            rows = conn.execute(
+                """
+                SELECT id, metadata_json FROM conversation_messages
+                WHERE workspace_id IS NULL OR organization_id IS NULL
+                """
+            ).fetchall()
+            for row in rows:
+                try:
+                    meta = json.loads(row["metadata_json"] or "{}")
+                except Exception:
+                    meta = {}
+                workspace_id = meta.get("workspace_id")
+                organization_id = meta.get("organization_id")
+                if workspace_id or organization_id:
+                    conn.execute(
+                        """
+                        UPDATE conversation_messages
+                        SET workspace_id=COALESCE(workspace_id, ?),
+                            organization_id=COALESCE(organization_id, ?)
+                        WHERE id=?
+                        """,
+                        (workspace_id, organization_id, row["id"]),
+                    )
 
     # ── writes ────────────────────────────────────────────────────────────
     def append(self, item: Dict[str, Any]) -> Dict[str, Any]:
         """Persist one chat item (the legacy chat_history.json entry shape)."""
-        known = {"role", "content", "timestamp", "user_email", "user_nickname", "source", "conversation_id"}
+        known = {
+            "role",
+            "content",
+            "timestamp",
+            "user_email",
+            "user_nickname",
+            "source",
+            "conversation_id",
+            "workspace_id",
+            "organization_id",
+        }
         extra = {k: v for k, v in item.items() if k not in known}
         with self._lock, self._connect() as conn:
             conn.execute(
                 """
                 INSERT OR IGNORE INTO conversation_messages
                   (message_hash, conversation_id, role, content, user_email,
-                   user_nickname, source, timestamp, metadata_json)
-                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+                   user_nickname, source, timestamp, metadata_json, workspace_id,
+                   organization_id)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
                 """,
                 (
                     _message_hash(item),
@@ -92,6 +141,8 @@ class ConversationStore:
                     item.get("source"),
                     str(item.get("timestamp") or ""),
                     json.dumps(extra, ensure_ascii=False) if extra else "{}",
+                    item.get("workspace_id"),
+                    item.get("organization_id"),
                 ),
             )
         return item
@@ -122,8 +173,9 @@ class ConversationStore:
                     """
                     INSERT OR IGNORE INTO conversation_messages
                       (message_hash, conversation_id, role, content, user_email,
-                       user_nickname, source, timestamp, metadata_json)
-                    VALUES (?, ?, ?, ?, ?, ?, ?, ?, '{}')
+                       user_nickname, source, timestamp, metadata_json, workspace_id,
+                       organization_id)
+                    VALUES (?, ?, ?, ?, ?, ?, ?, ?, '{}', ?, ?)
                     """,
                     (
                         _message_hash(item),
@@ -134,6 +186,8 @@ class ConversationStore:
                         item.get("user_nickname"),
                         item.get("source"),
                         str(item.get("timestamp") or ""),
+                        item.get("workspace_id"),
+                        item.get("organization_id"),
                     ),
                 )
                 imported += cur.rowcount if cur.rowcount > 0 else 0
@@ -149,7 +203,7 @@ class ConversationStore:
             "content": row["content"],
             "timestamp": row["timestamp"],
         }
-        for key in ("user_email", "user_nickname", "source", "conversation_id"):
+        for key in ("user_email", "user_nickname", "source", "conversation_id", "workspace_id", "organization_id"):
             if row[key]:
                 item[key] = row[key]
         try:
@@ -159,13 +213,62 @@ class ConversationStore:
         item.update(extra)
         return item
 
-    def history(self, *, conversation_id: Optional[str] = None, limit: Optional[int] = None) -> List[Dict[str, Any]]:
+    @staticmethod
+    def _scope_sql(
+        *,
+        user_email: Optional[str] = None,
+        allowed_workspaces: Optional[Any] = None,
+        include_legacy_global: bool = True,
+    ) -> tuple[str, List[Any]]:
+        clauses: List[str] = []
+        params: List[Any] = []
+        if user_email:
+            if include_legacy_global:
+                clauses.append("(user_email = ? OR user_email IS NULL OR user_email = '')")
+            else:
+                clauses.append("user_email = ?")
+            params.append(user_email)
+        if allowed_workspaces is not None:
+            allowed = [str(item) for item in allowed_workspaces if item]
+            if allowed:
+                placeholders = ",".join("?" for _ in allowed)
+                if include_legacy_global:
+                    clauses.append(f"(workspace_id IN ({placeholders}) OR workspace_id IS NULL OR workspace_id = '')")
+                else:
+                    clauses.append(f"workspace_id IN ({placeholders})")
+                params.extend(allowed)
+            elif include_legacy_global:
+                clauses.append("(workspace_id IS NULL OR workspace_id = '')")
+            else:
+                clauses.append("1=0")
+        return " AND ".join(clauses), params
+
+    def history(
+        self,
+        *,
+        conversation_id: Optional[str] = None,
+        limit: Optional[int] = None,
+        user_email: Optional[str] = None,
+        allowed_workspaces: Optional[Any] = None,
+        include_legacy_global: bool = True,
+    ) -> List[Dict[str, Any]]:
         """Chronological items; the unbounded successor of get_history()."""
         query = "SELECT * FROM conversation_messages"
         params: List[Any] = []
+        where: List[str] = []
         if conversation_id is not None:
-            query += " WHERE conversation_id IS ?" if conversation_id == "" else " WHERE conversation_id = ?"
+            where.append("conversation_id IS ?" if conversation_id == "" else "conversation_id = ?")
             params.append(None if conversation_id == "" else conversation_id)
+        scope_sql, scope_params = self._scope_sql(
+            user_email=user_email,
+            allowed_workspaces=allowed_workspaces,
+            include_legacy_global=include_legacy_global,
+        )
+        if scope_sql:
+            where.append(scope_sql)
+            params.extend(scope_params)
+        if where:
+            query += " WHERE " + " AND ".join(where)
         query += " ORDER BY id ASC"
         if limit is not None:
             query += " LIMIT ?"
@@ -185,25 +288,51 @@ class ConversationStore:
             return 0
 
     # ── clears (legacy semantics preserved) ───────────────────────────────
-    def clear_all(self, keep_last: int = 0) -> Dict[str, Any]:
+    def clear_all(
+        self,
+        keep_last: int = 0,
+        *,
+        user_email: Optional[str] = None,
+        allowed_workspaces: Optional[Any] = None,
+        include_legacy_global: bool = True,
+    ) -> Dict[str, Any]:
         keep_last = max(0, min(int(keep_last or 0), 20))
         with self._lock, self._connect() as conn:
             total = conn.execute("SELECT COUNT(*) FROM conversation_messages").fetchone()[0]
+            scope_sql, scope_params = self._scope_sql(
+                user_email=user_email,
+                allowed_workspaces=allowed_workspaces,
+                include_legacy_global=include_legacy_global,
+            )
+            scope_where = f" WHERE {scope_sql}" if scope_sql else ""
             if keep_last:
                 conn.execute(
-                    """
-                    DELETE FROM conversation_messages WHERE id NOT IN (
-                      SELECT id FROM conversation_messages ORDER BY id DESC LIMIT ?
+                    f"""
+                    DELETE FROM conversation_messages
+                    WHERE id IN (
+                      SELECT id FROM conversation_messages{scope_where}
+                    )
+                    AND id NOT IN (
+                      SELECT id FROM conversation_messages{scope_where}
+                      ORDER BY id DESC LIMIT ?
                     )
                     """,
-                    (keep_last,),
+                    (*scope_params, *scope_params, keep_last),
                 )
             else:
-                conn.execute("DELETE FROM conversation_messages")
+                conn.execute(f"DELETE FROM conversation_messages{scope_where}", scope_params)
             kept = conn.execute("SELECT COUNT(*) FROM conversation_messages").fetchone()[0]
         return {"status": "cleared", "removed": max(0, total - kept), "kept": kept}
 
-    def clear_conversation(self, conversation_id: str, started_at: Optional[str] = None) -> Dict[str, Any]:
+    def clear_conversation(
+        self,
+        conversation_id: str,
+        started_at: Optional[str] = None,
+        *,
+        user_email: Optional[str] = None,
+        allowed_workspaces: Optional[Any] = None,
+        include_legacy_global: bool = True,
+    ) -> Dict[str, Any]:
         """Remove one conversation.
 
         ``legacy-previous-history`` targets unattributed messages; when
@@ -212,17 +341,23 @@ class ConversationStore:
         """
         with self._lock, self._connect() as conn:
             total = conn.execute("SELECT COUNT(*) FROM conversation_messages").fetchone()[0]
+            scope_sql, scope_params = self._scope_sql(
+                user_email=user_email,
+                allowed_workspaces=allowed_workspaces,
+                include_legacy_global=include_legacy_global,
+            )
+            scoped = f" AND {scope_sql}" if scope_sql else ""
             if conversation_id == "legacy-previous-history":
-                conn.execute("DELETE FROM conversation_messages WHERE conversation_id IS NULL")
+                conn.execute(f"DELETE FROM conversation_messages WHERE conversation_id IS NULL{scoped}", scope_params)
             else:
                 conn.execute(
-                    "DELETE FROM conversation_messages WHERE conversation_id = ?",
-                    (conversation_id,),
+                    f"DELETE FROM conversation_messages WHERE conversation_id = ?{scoped}",
+                    (conversation_id, *scope_params),
                 )
                 if started_at:
                     conn.execute(
-                        "DELETE FROM conversation_messages WHERE conversation_id IS NULL AND timestamp >= ?",
-                        (str(started_at),),
+                        f"DELETE FROM conversation_messages WHERE conversation_id IS NULL AND timestamp >= ?{scoped}",
+                        (str(started_at), *scope_params),
                     )
             kept = conn.execute("SELECT COUNT(*) FROM conversation_messages").fetchone()[0]
         return {

package/lattice_brain/embeddings.py

@@ -8,7 +8,7 @@ import os
 import re
 import struct
 from dataclasses import dataclass
-from typing import Iterable, List
+from typing import Any, Dict, Iterable, List, Optional
 
 
 DEFAULT_EMBEDDING_DIM = int(os.getenv("LATTICEAI_VECTOR_DIM", "384"))
@@ -87,4 +87,40 @@ class LocalEmbeddingModel:
         return list(struct.unpack(f"<{count}f", payload[: count * 4]))
 
 
-__all__ = ["DEFAULT_EMBEDDING_DIM", "EMBEDDING_MODEL_ID", "LocalEmbeddingModel", "embedding_model_id"]
+# --- Large candidate #2 slice: multimodal (vision) stubs ---
+# Schema already defines IMAGE / IMAGE_TEXT / CONTAINS_IMAGE.
+# These stubs allow ingestion + retrieval paths to carry image signals without
+# requiring heavy deps at core. Real impl can swap in local vision (e.g. via
+# ollama vision or onnx CLIP) behind the same interface.
+@dataclass(frozen=True)
+class VisionStub:
+    """Offline vision describe + embed stubs for multimodal Brain.
+
+    describe: returns a short textual caption derived from metadata/filename.
+    embed: produces a vector from image meta (size+format) + optional caption hash.
+    Later: replace with real embedding model that accepts image bytes/path.
+    """
+    dim: int = DEFAULT_EMBEDDING_DIM
+
+    def describe(self, path: str | None = None, meta: Optional[Dict[str, Any]] = None) -> str:
+        meta = meta or {}
+        w = meta.get("width") or meta.get("w") or "?"
+        h = meta.get("height") or meta.get("h") or "?"
+        fmt = meta.get("format") or meta.get("ext") or "img"
+        name = (path or "").split("/")[-1] or "image"
+        # deterministic caption stub (no external call)
+        return f"Image {name} ({fmt} {w}x{h})"
+
+    def embed_image(self, path: str | None = None, meta: Optional[Dict[str, Any]] = None, caption: str = "") -> List[float]:
+        meta = meta or {}
+        basis = f"{path or ''}|{meta.get('width',0)}x{meta.get('height',0)}|{meta.get('format','')}|{caption[:120]}"
+        # reuse text embedder for determinism (image content hash would be better with real vision)
+        model = LocalEmbeddingModel(dim=self.dim)
+        return model.embed(basis)
+
+
+def get_vision_embedder(dim: int | None = None) -> VisionStub:
+    return VisionStub(dim=dim or DEFAULT_EMBEDDING_DIM)
+
+
+__all__ = ["DEFAULT_EMBEDDING_DIM", "EMBEDDING_MODEL_ID", "LocalEmbeddingModel", "embedding_model_id", "VisionStub", "get_vision_embedder"]