ltcai 9.3.0 → 9.5.0

package/README.md

@@ -1,10 +1,21 @@
 # Lattice AI
 
-**Lattice AI 9.3.0 is the local-first Digital Brain platform. Proactive Brain Intelligence turns the Brain from a passive store into an active steward of its own knowledge: it scores its health across freshness, connectivity, search readiness, and consistency, surfaces contradictions and stale knowledge, proposes consent-first duplicate consolidation, and upgrades recall to hybrid lexical+semantic evidence.**
+**Lattice AI 9.5.0 is the local-first Digital Brain platform. The Command Center puts everything one keystroke away: a Cmd+K palette that searches knowledge, past conversations, automations, and app pages in one query, and a daily briefing that condenses recent knowledge, automation state, pending reviews, Brain health, and suggested next steps into one glance with one-click quick actions.**
 
 **Lattice AI는 모델이 바뀌어도 내 지식과 맥락을 보존하는 로컬 우선 AI 브레인입니다.**
 
-> The 9.3.0 release wires the previously dormant Brain quality layer into
+> The 9.5.0 release adds the Command Center: a deterministic, local
+> `/api/command` surface serving a daily briefing (recent knowledge,
+> conversation activity, automation state, pending reviews, health snapshot,
+> top suggestions, state-derived quick actions) and a universal search across
+> knowledge nodes, the user's own conversations, and installed automations —
+> surfaced in the app as a Cmd+K command palette and a Today's Briefing panel.
+> The 9.4.0 release adds question-driven automation: a deterministic local
+> pattern miner clusters your recurring questions (the evidence shown is your
+> own words, no model call), an /api/automation surface turns patterns and
+> connected folders into one-click suggestions, and every accepted suggestion
+> becomes a disabled, review-gated draft workflow you enable deliberately.
+> The 9.3.0 release wired the previously dormant Brain quality layer into
 > the product: /api/brain health diagnosis with recommended care actions, a
 > proactive insights digest, contradiction surfacing across memories and the
 > graph, dry-run-first duplicate consolidation, and hybrid recall that blends
@@ -97,11 +108,11 @@ You need Lattice AI when:
 The screenshots below are the latest checked-in visual evidence captures. They
 keep the first-run Brain flow, memory graph, source capture, model library,
 system view, admin console, and review center visible as release gates while
-9.3.0 makes the Brain proactively intelligent: it diagnoses its own health,
-surfaces contradictions and stale knowledge, proposes consent-first
-consolidation, and recalls with hybrid lexical+semantic evidence. The
-captures below are the checked-in 9.3.0 visual release evidence for that
-product flow.
+9.5.0 puts the whole Brain one keystroke away: the Cmd+K Command Palette
+searches knowledge, conversations, automations, and pages in one query, and
+Today's Briefing condenses the Brain's state into one glance with one-click
+next steps. The captures below are the checked-in 9.5.0 visual release
+evidence for that product flow.
 
 ### 1. Wake Brain
 
@@ -113,21 +124,21 @@ confirm owner, check the computer, choose the Brain voice.
 Choose the owner of the Brain. The profile is not a SaaS account by default; it
 is the local identity for the knowledge you keep.
 
-![Login](output/release/v9.3.0/screenshots/01-login.png)
+![Login](output/release/v9.5.0/screenshots/01-login.png)
 
 ### 3. Recommended Models
 
 Start with a short list: safest recommendation, faster model, stronger model.
 Advanced details stay available without overwhelming first-time users.
 
-![Recommended Models](output/release/v9.3.0/screenshots/02-recommended-models.png)
+![Recommended Models](output/release/v9.5.0/screenshots/02-recommended-models.png)
 
 ### 4. Install And Load
 
 Download and load only after consent. Lattice explains model size, local
 execution, and network use before work starts.
 
-![Install and Load](output/release/v9.3.0/screenshots/03-install-load-progress.png)
+![Install and Load](output/release/v9.5.0/screenshots/03-install-load-progress.png)
 
 ### 5. Brain Chat
 
@@ -139,14 +150,14 @@ and its visible life signal follow real listening, recall, synthesis, and action
 state. Detailed memory rings, provenance, conversation history, and
 model/runtime proof open as overlays only when requested.
 
-![One-viewport Living Brain Home](output/release/v9.3.0/screenshots/04-brain-chat-home.png)
+![One-viewport Living Brain Home](output/release/v9.5.0/screenshots/04-brain-chat-home.png)
 
 ### 6. Review Center
 
 Automation results are staged for review before they become durable decisions.
 Snooze, unsnooze, run now, approve, and dismiss actions stay explicit.
 
-![Review Center](output/release/v9.3.0/screenshots/12-review-center.png)
+![Review Center](output/release/v9.5.0/screenshots/12-review-center.png)
 
 ## Brain Depths
 
@@ -162,10 +173,10 @@ The user travels inward from everyday memory to deeper structure:
 
 Walkthrough:
 
-![v9.3.0 Living Brain walkthrough](output/release/v9.3.0/gifs/v9.3.0-living-brain-walkthrough.gif)
+![v9.5.0 Living Brain walkthrough](output/release/v9.5.0/gifs/v9.5.0-living-brain-walkthrough.gif)
 
 Screenshot index and capture notes:
-[output/release/v9.3.0/SCREENSHOT_INDEX.md](output/release/v9.3.0/SCREENSHOT_INDEX.md)
+[output/release/v9.5.0/SCREENSHOT_INDEX.md](output/release/v9.5.0/SCREENSHOT_INDEX.md)
 
 ## Install
 
@@ -250,43 +261,45 @@ See [docs/DEVELOPMENT.md](docs/DEVELOPMENT.md) for developer workflow details.
 
 ## Current Release
 
-The current release is **9.3.0 — Proactive Brain Intelligence**:
-
-- A new `latticeai.core.file_generation` pipeline treats every model reply as
-  untrusted content: extension-aware strict prompting, extraction of the real
-  payload from fences/`<think>` blocks/chat framing, per-type structural
-  validation (complete HTML documents, parseable JSON, CSS rule blocks), one
-  corrective retry that tells the model what was wrong, and a deterministic
-  repair fallback that guarantees a valid file.
-- Type-only requests without an explicit filename ("html 파일 만들어줘",
-  "웹페이지 만들어줘") now resolve to an inferred target and use the
-  deterministic direct-write path instead of the model-driven agent loop.
-- The agent executor tolerates small-model formatting slips: `<think>` blocks
-  and trailing commas are stripped from action JSON, and parse failures feed a
-  corrective format reminder back to the model instead of aborting the run.
-- The executor prompt pins exact file-content rules for `write_file` so
-  agent-created files are complete and fence-free.
-- File writes report whether content was generated cleanly, retried, or
-  auto-repaired in the response payload (`generation` metadata).
-
-Expected artifacts for 9.3.0 release must use exact filenames:
-
-- `dist/ltcai-9.3.0-py3-none-any.whl`
-- `dist/ltcai-9.3.0.tar.gz`
-- `ltcai-9.3.0.tgz`
-- `dist/ltcai-9.3.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_9.3.0_aarch64.dmg`
+The current release is **9.5.0 — Command Center**:
+
+- A new `CommandCenterService` (`/api/command/briefing`, `/api/command/search`)
+  aggregates every Brain surface read-only and deterministically: recent
+  knowledge from the scoped graph, conversation activity, automation
+  enable/draft counts, pending review items, a Brain-health snapshot, and the
+  top automation suggestions — each section degrades independently when a
+  backend is unavailable.
+- State-derived quick actions with stable ids ("N items waiting for review",
+  "enable your draft automations", "connect a knowledge folder") give the UI
+  one-click jumps that always reflect the actual product state.
+- Universal search groups results across knowledge nodes (scoped keyword
+  search), the user's own conversations (deduped per conversation, newest
+  first), and installed automations — all scoped to the requesting user and
+  workspace.
+- The frontend gains a Cmd+K Command Palette (grouped results, keyboard
+  navigation, page jumps, fully ko/en localized) and a Today's Briefing panel
+  on the Brain home with stat chips, recent knowledge, and quick actions.
+- Everything is read-only, local, and model-free: no model calls, no writes,
+  no external actions.
+
+Expected artifacts for 9.5.0 release must use exact filenames:
+
+- `dist/ltcai-9.5.0-py3-none-any.whl`
+- `dist/ltcai-9.5.0.tar.gz`
+- `ltcai-9.5.0.tgz`
+- `dist/ltcai-9.5.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_9.5.0_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
 See [docs/ROADMAP_RECOMMENDATIONS.md](docs/ROADMAP_RECOMMENDATIONS.md) for the
-strategic roadmap slices applied through 9.3.0 and the follow-up tracks.
+strategic roadmap slices applied through 9.5.0 and the follow-up tracks.
 
 ## Known Limitations
 
 - External package registries are owner-published and can lag behind GitHub.
 - PostgreSQL/pgvector is optional scale/migration tooling. SQLite remains the
-  live local Brain store in 9.3.0.
+  live local Brain store in 9.5.0.
 - Docker, model downloads, cloud model calls, Telegram, Brain Network, and update
   checks require explicit user action.
 - Conversation does not fabricate answers when no model is loaded.
@@ -298,6 +311,8 @@ strategic roadmap slices applied through 9.3.0 and the follow-up tracks.
 
 | Version | Theme |
 | --- | --- |
+| 9.5.0 | Command Center: a Cmd+K palette searching knowledge, conversations, automations, and pages in one query, plus a daily briefing with Brain state at a glance and state-derived one-click quick actions |
+| 9.4.0 | Question-Driven Everyday Automation: the Brain mines recurring user questions and connected knowledge folders into one-click, consent-first automation suggestions installed as review-gated drafts |
 | 9.3.0 | Proactive Brain Intelligence: the Brain diagnoses its own health, surfaces contradictions and stale knowledge, proposes consent-first duplicate consolidation, and recalls with hybrid lexical+semantic evidence behind an honest quality gate |
 | 9.2.0 | Model-Agnostic File Generation: chat file requests always produce structurally valid files with any LLM via extraction, per-type validation, corrective retry, deterministic repair, inferred file targets, and a fault-tolerant agent JSON loop |
 | 9.1.0 | Code Review Completion & Fail-Closed Runtime: all July 11 review findings closed across fail-closed security, typed runtime/model/chat boundaries, honest frontend failures and tests, and repository hygiene |

package/docs/CHANGELOG.md

@@ -4,6 +4,54 @@ The top entry is either the current unreleased main-branch work or the current
 release line. Older entries are historical and may describe behavior as it
 existed at that release.
 
+## [9.5.0] - 2026-07-20
+
+### Added
+- Added `latticeai/services/command_center.py` and the `/api/command/*`
+  router: a daily briefing aggregating recent knowledge, conversation
+  activity, automation state, pending reviews, a Brain-health snapshot, top
+  automation suggestions, and state-derived quick actions with stable ids;
+  and a universal search grouping knowledge nodes, the user's own
+  conversations (deduped per conversation), and installed automations.
+- Added the Cmd+K Command Palette (grouped results, keyboard navigation,
+  debounced universal search, static page jumps) and the collapsible
+  "오늘의 브리핑 / Today's briefing" panel on the Brain home, fully ko/en
+  localized.
+- Added `tests/unit/test_command_center.py` (11 tests) and
+  `frontend/src/features/command/CommandPalette.test.tsx` (3 tests).
+
+### Changed
+- Cmd+K now opens the Command Palette instead of only focusing the chat
+  composer; the palette includes a direct jump to the Brain conversation.
+
+### Security
+- Both Command Center endpoints are read-only and scoped to the requesting
+  user and workspace; scoped reads exclude legacy-global rows, and every
+  briefing section degrades independently without leaking errors.
+
+## [9.4.0] - 2026-07-20
+
+### Added
+- Added `latticeai/services/automation_intelligence.py` and the
+  `/api/automation/*` router: recurring-question pattern mining
+  (deterministic local token-signature clustering with literal-question
+  evidence), automation suggestions from question patterns and connected
+  knowledge folders, idempotent consent-first install (disabled draft,
+  review-queue gated, local-only), and a combined overview payload.
+- Added the "Automation suggestions for you" panel to the Act page with
+  evidence chips and one-click creation, fully ko/en localized.
+- Added `tests/unit/test_automation_intelligence.py` (10 tests).
+
+### Changed
+- Recurring question intents that match a starter recipe (daily digest,
+  weekly project review, follow-up radar) suggest that recipe; other
+  repeated questions become parameterized "scheduled answer" workflows.
+
+### Security
+- History mining respects user/workspace scoping and excludes legacy-global
+  rows for scoped reads; suggestion installs carry provenance metadata and
+  never enable themselves.
+
 ## [9.3.0] - 2026-07-20
 
 ### Added

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,13 +1,14 @@
 # Community And Plugins
 
-Current release: **9.3.0 — Proactive Brain Intelligence**.
+Current release: **9.5.0 — Command Center**.
 
 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, 8.8.0 Brain Core extraction
 readiness, 8.9.0 scoped Tool API hardening, 9.0.0 cleanup closure, 9.1.0
-fail-closed review completion, 9.2.0 model-agnostic file generation, and
-9.3.0 proactive Brain intelligence) to a product ecosystem. The
+fail-closed review completion, 9.2.0 model-agnostic file generation, 9.3.0
+proactive Brain intelligence, 9.4.0 question-driven everyday automation, and 9.5.0 Command Center)
+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: **9.3.0 — Proactive Brain Intelligence**.
+Current release: **9.5.0 — Command Center**.
 
 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 8.0.0-9.3.0 in `docs/CHANGELOG.md` and
+history is intentionally limited to 8.0.0-9.5.0 in `docs/CHANGELOG.md` and
 `RELEASE.md`.
 
 ## Product Contract
@@ -153,10 +153,10 @@ 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 9.3.0 release work, exact artifacts are:
+For 9.5.0 release work, exact artifacts are:
 
-- `dist/ltcai-9.3.0-py3-none-any.whl`
-- `dist/ltcai-9.3.0.tar.gz`
-- `ltcai-9.3.0.tgz`
-- `dist/ltcai-9.3.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_9.3.0_aarch64.dmg`
+- `dist/ltcai-9.5.0-py3-none-any.whl`
+- `dist/ltcai-9.5.0.tar.gz`
+- `ltcai-9.5.0.tgz`
+- `dist/ltcai-9.5.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_9.5.0_aarch64.dmg`

package/docs/LEGACY_COMPATIBILITY.md

@@ -1,6 +1,6 @@
 # Legacy Compatibility Map
 
-Current target: **9.3.0 — Proactive Brain Intelligence**.
+Current target: **9.5.0 — Command Center**.
 
 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: **9.3.0 — Proactive Brain Intelligence**.
+Current release: **9.5.0 — Command Center**.
 
 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
@@ -40,7 +40,7 @@ read the docs first.
 
 ## Release Gate
 
-9.3.0 treats onboarding as a release gate, not marketing copy. The current
+9.5.0 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/OPERATIONS.md

@@ -1,4 +1,4 @@
-# Lattice AI — Operations Guide (v9.3.0)
+# Lattice AI — Operations Guide (v9.5.0)
 
 ## 1. 데이터 파일 위치
 

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **9.3.0 — Proactive Brain Intelligence**.
+Current release: **9.5.0 — Command Center**.
 
 Lattice AI is local-first, explicit about external communication, and honest
 when a capability is unavailable.

package/docs/WHY_LATTICE.md

@@ -1,6 +1,6 @@
 # Why Lattice AI Exists
 
-Current release: **9.3.0 — Proactive Brain Intelligence**.
+Current release: **9.5.0 — Command Center**.
 
 **Lattice AI is a local-first Digital Brain that keeps your knowledge durable
 across any AI model.**

package/docs/kg-schema.md

@@ -1,6 +1,6 @@
 # Knowledge Graph Schema
 
-Current release: **9.3.0 — Proactive Brain Intelligence**.
+Current release: **9.5.0 — Command Center**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `kg_schema.py`

package/docs/mcp-tools.md

@@ -1,4 +1,4 @@
-# MCP 도구 카탈로그 (v9.3.0)
+# MCP 도구 카탈로그 (v9.5.0)
 
 Lattice AI는 MCP(Model Context Protocol) 서버로 동작하여 Claude Desktop, Cursor 등에서 직접 도구를 사용할 수 있습니다.
 

package/lattice_brain/__init__.py

@@ -26,7 +26,7 @@ from .storage import (
     storage_from_env,
 )
 
-__version__ = "9.3.0"
+__version__ = "9.5.0"
 
 __all__ = [
     "AgentRuntime",

package/lattice_brain/runtime/multi_agent.py

@@ -21,7 +21,7 @@ from .contracts import multi_agent_contract
 from ..utils import now_iso as _now
 
 
-MULTI_AGENT_VERSION = "9.3.0"
+MULTI_AGENT_VERSION = "9.5.0"
 
 AGENT_ROLES = ("researcher", "planner", "executor", "reviewer", "release")
 CORE_PIPELINE = ("planner", "executor", "reviewer")

package/latticeai/__init__.py

@@ -1,3 +1,3 @@
 """Lattice AI - modular server package."""
 
-__version__ = "9.3.0"
+__version__ = "9.5.0"

package/latticeai/api/automation_intelligence.py

@@ -0,0 +1,129 @@
+"""Question-driven everyday automation API router (v9.4.0).
+
+Exposes :class:`~latticeai.services.automation_intelligence.AutomationIntelligenceService`:
+recurring-question patterns with evidence, automation suggestions (from the
+user's own questions and connected knowledge folders), one-click consent-first
+install, and a combined overview for the automation surface.
+
+Installs follow the same consent contract as the starter recipes: the
+workflow is created as a disabled draft (unless the user explicitly asks to
+enable), review-queue gated, local-only, and idempotent per suggestion.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Callable, Optional
+
+from fastapi import APIRouter, HTTPException, Request
+from pydantic import BaseModel
+
+from latticeai.services.automation_intelligence import AutomationIntelligenceService
+from latticeai.services.brain_automation import find_installed_recipe_workflow
+
+
+class SuggestionInstallRequest(BaseModel):
+    suggestion_id: str
+    enabled: bool = False
+
+
+def create_automation_intelligence_router(
+    *,
+    service: AutomationIntelligenceService,
+    store: Any,
+    require_user: Callable[[Request], str],
+    gate_read: Callable[[Request], Optional[str]],
+    gate_write: Callable[[Request], Optional[str]],
+    append_audit_event: Callable[..., None],
+    workspace_graph: Callable[[], Any],
+) -> APIRouter:
+    from lattice_brain.workflow import legacy_steps_from_nodes, validate_definition
+
+    router = APIRouter()
+
+    @router.get("/api/automation/patterns")
+    async def automation_patterns(request: Request):
+        user = require_user(request)
+        scope = gate_read(request)
+        return service.question_patterns(user_email=user, workspace_id=scope)
+
+    @router.get("/api/automation/suggestions")
+    async def automation_suggestions(request: Request):
+        user = require_user(request)
+        scope = gate_read(request)
+        return service.suggestions(user_email=user, workspace_id=scope)
+
+    @router.get("/api/automation/overview")
+    async def automation_overview(request: Request):
+        user = require_user(request)
+        scope = gate_read(request)
+        return service.overview(user_email=user, workspace_id=scope)
+
+    @router.post("/api/automation/install")
+    async def automation_install(req: SuggestionInstallRequest, request: Request):
+        user = require_user(request)
+        scope = gate_write(request)
+        suggestion = service.find_suggestion(
+            req.suggestion_id, user_email=user, workspace_id=scope
+        )
+        if suggestion is None:
+            raise HTTPException(
+                status_code=404,
+                detail=f"Automation suggestion not found: {req.suggestion_id}",
+            )
+        definition = service.build_suggestion_workflow(suggestion, enabled=req.enabled)
+
+        # Idempotent per suggestion: reuse the workflow provenance match used
+        # for recipes, keyed on suggestion_id instead of recipe_id.
+        existing = None
+        for workflow in store.list_workflows(workspace_id=scope).get("workflows") or []:
+            metadata = (workflow or {}).get("metadata") or {}
+            if (
+                metadata.get("created_from") == "automation_suggestion"
+                and metadata.get("suggestion_id") == req.suggestion_id
+            ):
+                existing = workflow
+                break
+        if existing is None and suggestion.get("recipe_id"):
+            existing = find_installed_recipe_workflow(
+                store.list_workflows(workspace_id=scope).get("workflows"),
+                suggestion["recipe_id"],
+            )
+        if existing is not None:
+            return {
+                "workflow": existing,
+                "suggestion": suggestion,
+                "enabled": bool((existing.get("metadata") or {}).get("automation_state") == "enabled"),
+                "already_installed": True,
+            }
+
+        errors = validate_definition({"name": definition["name"], "nodes": definition["nodes"]})
+        if errors:
+            raise HTTPException(status_code=400, detail={"validation_errors": errors})
+        workflow = store.create_workflow(
+            name=definition["name"],
+            steps=legacy_steps_from_nodes(definition["nodes"]),
+            nodes=definition["nodes"],
+            metadata=definition["metadata"],
+            user_email=user or None,
+            graph=workspace_graph(),
+            workspace_id=scope,
+        )
+        append_audit_event(
+            "automation_suggestion_installed",
+            user_email=user,
+            workflow_id=workflow.get("id"),
+            suggestion_id=req.suggestion_id,
+            suggestion_kind=suggestion.get("kind"),
+            enabled=bool(req.enabled),
+        )
+        return {
+            "workflow": workflow,
+            "suggestion": suggestion,
+            "enabled": bool(req.enabled),
+            "already_installed": False,
+        }
+
+    return router
+
+
+__all__ = ["create_automation_intelligence_router"]

package/latticeai/api/command_center.py

@@ -0,0 +1,51 @@
+"""Command Center API router (v9.5.0).
+
+Read-only surface over :class:`~latticeai.services.command_center.CommandCenterService`:
+
+* ``GET /api/command/briefing`` — the daily briefing: recent knowledge,
+  conversation activity, automation state, pending reviews, health snapshot,
+  top suggestions, and state-derived quick actions.
+* ``GET /api/command/search?q=…`` — universal search across knowledge nodes,
+  the user's conversations, and installed automations. Powers Cmd+K.
+
+Both endpoints are scoped to the requesting user and workspace via the same
+require_user/gate_read contract as the rest of the platform.
+"""
+
+from __future__ import annotations
+
+from typing import Callable, Optional
+
+from fastapi import APIRouter, Query, Request
+
+from latticeai.services.command_center import CommandCenterService
+
+
+def create_command_center_router(
+    *,
+    service: CommandCenterService,
+    require_user: Callable[[Request], str],
+    gate_read: Callable[[Request], Optional[str]],
+) -> APIRouter:
+    router = APIRouter()
+
+    @router.get("/api/command/briefing")
+    async def command_briefing(request: Request):
+        user = require_user(request)
+        scope = gate_read(request)
+        return service.briefing(user_email=user, workspace_id=scope)
+
+    @router.get("/api/command/search")
+    async def command_search(
+        request: Request,
+        q: str = Query("", max_length=300),
+        limit: int = Query(8, ge=1, le=20),
+    ):
+        user = require_user(request)
+        scope = gate_read(request)
+        return service.search(q, user_email=user, workspace_id=scope, limit=limit)
+
+    return router
+
+
+__all__ = ["create_command_center_router"]

package/latticeai/app_factory.py

@@ -165,7 +165,10 @@ def _build(config: "Optional[Config]" = None) -> Dict[str, Any]:
     from latticeai.api.hooks import create_hooks_router
     from latticeai.core.product_hardening import build_product_hardening_status
     from latticeai.api.agent_registry import create_agent_registry_router
+    from latticeai.api.automation_intelligence import create_automation_intelligence_router
     from latticeai.api.brain_intelligence import create_brain_intelligence_router
+    from latticeai.api.command_center import create_command_center_router
+    from latticeai.services.command_center import CommandCenterService
     from latticeai.api.memory import create_memory_router
     from latticeai.api.browser import create_browser_router
     from latticeai.api.portability import create_portability_router
@@ -385,6 +388,7 @@ def _build(config: "Optional[Config]" = None) -> Dict[str, Any]:
     AGENT_REGISTRY = _persistence_runtime["AGENT_REGISTRY"]
     MEMORY_SERVICE = _persistence_runtime["MEMORY_SERVICE"]
     BRAIN_INTELLIGENCE = _persistence_runtime["BRAIN_INTELLIGENCE"]
+    AUTOMATION_INTELLIGENCE = _persistence_runtime["AUTOMATION_INTELLIGENCE"]
     INGESTION_PIPELINE = _persistence_runtime["INGESTION_PIPELINE"]
     DEVICE_IDENTITY = _persistence_runtime["DEVICE_IDENTITY"]
     KG_PORTABILITY = _persistence_runtime["KG_PORTABILITY"]
@@ -1019,6 +1023,34 @@ def _build(config: "Optional[Config]" = None) -> Dict[str, Any]:
         create_realtime_router=create_realtime_router,
         realtime_bus=REALTIME_BUS,
     )
+    app.include_router(
+        create_automation_intelligence_router(
+            service=AUTOMATION_INTELLIGENCE,
+            store=WORKSPACE_OS,
+            require_user=require_user,
+            gate_read=PLATFORM.gate_read,
+            gate_write=PLATFORM.gate_write,
+            append_audit_event=append_audit_event,
+            workspace_graph=_workspace_graph,
+        )
+    )
+    COMMAND_CENTER = CommandCenterService(
+        conversation_store=CONVERSATIONS,
+        knowledge_graph=KNOWLEDGE_GRAPH,
+        store=WORKSPACE_OS,
+        search_service=SEARCH_SERVICE,
+        brain_intelligence=BRAIN_INTELLIGENCE,
+        automation_intelligence=AUTOMATION_INTELLIGENCE,
+        review_queue=REVIEW_QUEUE,
+        enable_graph=ENABLE_GRAPH,
+    )
+    app.include_router(
+        create_command_center_router(
+            service=COMMAND_CENTER,
+            require_user=require_user,
+            gate_read=PLATFORM.gate_read,
+        )
+    )
 
 
     # ── Health & Info ──────────────────────────────────────────────────────────────

package/latticeai/core/legacy_compatibility.py

@@ -14,7 +14,7 @@ from pathlib import Path
 from typing import Any, Dict, List
 
 
-LEGACY_COMPATIBILITY_VERSION = "9.3.0"
+LEGACY_COMPATIBILITY_VERSION = "9.5.0"
 
 
 @dataclass(frozen=True)

package/latticeai/core/marketplace.py

@@ -11,7 +11,7 @@ from copy import deepcopy
 from typing import Any, Dict, List, Optional
 
 
-MARKETPLACE_VERSION = "9.3.0"
+MARKETPLACE_VERSION = "9.5.0"
 TEMPLATE_KINDS = ("plugin", "workflow", "agent", "ingestion_bridge")
 
 

package/latticeai/core/workspace_os.py

@@ -49,7 +49,7 @@ __all__ = [
     "remove_skill_directory",
 ]
 
-WORKSPACE_OS_VERSION = "9.3.0"
+WORKSPACE_OS_VERSION = "9.5.0"
 
 # Workspace types separate single-user Personal workspaces from shared
 # Organization workspaces. Both keep the same local-first JSON store; the type