ltcai 10.8.0 → 10.9.0

package/README.md

@@ -11,7 +11,7 @@
 [![CI Status](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
 
-![v10.8.0 Living Brain walkthrough](output/release/v10.8.0/gifs/v10.8.0-living-brain-walkthrough.gif)
+![v10.9.0 Living Brain walkthrough](output/release/v10.9.0/gifs/v10.9.0-living-brain-walkthrough.gif)
 
 Chat, files, folders, notes, and web pages all flow into one durable knowledge
 graph on your computer. Any model — local MLX or cloud — can speak with that
@@ -24,10 +24,10 @@ memory. Nothing leaves your machine without explicit consent.
 
 | | |
 | --- | --- |
-| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v10.8.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.8.0/screenshots/05-memory-graph.png) |
-| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.8.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.8.0/screenshots/12-review-center.png) |
-| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.8.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.8.0/screenshots/10-admin-console.png) |
-| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v10.8.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v10.8.0/screenshots/08-system.png) |
+| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v10.9.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.9.0/screenshots/05-memory-graph.png) |
+| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.9.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.9.0/screenshots/12-review-center.png) |
+| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.9.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.9.0/screenshots/10-admin-console.png) |
+| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v10.9.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v10.9.0/screenshots/08-system.png) |
 
 ## Why Lattice AI
 
@@ -58,63 +58,64 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v10.8.0/screenshots/01-login.png) | ![Model install](output/release/v10.8.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.8.0/screenshots/07-model-library.png) |
+| ![Login](output/release/v10.9.0/screenshots/01-login.png) | ![Model install](output/release/v10.9.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.9.0/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v10.8.0/SCREENSHOT_INDEX.md](output/release/v10.8.0/SCREENSHOT_INDEX.md)
+[output/release/v10.9.0/SCREENSHOT_INDEX.md](output/release/v10.9.0/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **10.8.0 — Within Reach**:
-
-10.7.0 rearranged all twelve screens. 10.8.0 is about the things that were
-already there but out of reach: a button below the fold, a message in a
-language you did not choose, a file a small model nearly produced.
-
-- **The first three screens fit on the screen.** Onboarding rendered a 390px
-  decorative Brain above *every* step, so on a 1440×900 display the login
-  form, the recommended model and the install progress all began below the
-  fold — the first thing the product asked a new person to do was scroll. The
-  organism is a hero on the welcome step and a 104px mark after it; the
-  welcome screen itself went from 1175px of content to 770px, so its primary
-  button is visible without scrolling.
-- **One language per screen, including the ones the server writes.** API
-  messages were literals at the raise site, written in whichever language the
-  endpoint's author was thinking in — Korean from `auth.py`, English from
-  `browser.py`. `latticeai/core/messages.py` is a catalog with both, resolved
-  from `X-Lattice-Language` (falling back to `Accept-Language`); the browser
-  extension, which showed English and Korean in the same popup, has one too.
-  `tests/unit/test_server_messages.py` fails on a message that exists in only
-  one language, and on a router that reverts to a hardcoded literal.
-- **A small model's near-miss is no longer thrown away.** File generation
-  picked the *longest* rejected reply to repair, so a 900-character apology
-  beat a truncated-but-real HTML document; it now scores candidates by how
-  close they are to being a file. A byte-identical repeated reply buys one
-  extra attempt with a prompt that names the repetition. Prose file types
-  (`.md`, `.txt`) had no validation at all and would save "Sure! Here is the
-  document:" as the document.
-- **Re-indexing costs what changed.** The incremental vector rebuild
-  materialised every node and chunk in memory and asked one `SELECT` per item
-  whether it had changed. It streams now, with a single prefetched hash map —
-  and a settled index performs zero embeddings, asserted rather than assumed.
-- **More ground under the frontend.** Statement coverage 47.35% → 52.26%,
-  424 → 504 tests, including the app shell (`App.tsx`, previously 0%), the
-  admin console (0%), the folder picker (2.7%) and the API client.
-- **Evidence bound to this build.** `output/release/v10.8.0/` holds the twelve
+The current release is **10.9.0 — Never Blocks**:
+
+Lattice AI runs one event loop on your computer. Several things you could ask
+it to do were being done *on* that loop, so while they ran the server could not
+answer anything else. Downloading a model has a fifteen-minute timeout; that is
+how long the whole product could be frozen by one click.
+
+- **Nothing long runs on the event loop.** Model pulls, engine installs, MCP
+  package installs and the CPU/RAM probe behind the System screen all moved to
+  a worker thread. `/local/sysinfo` is the one most people met without knowing:
+  it is read by the System screen *and* by first-run analysis, so its ~2s
+  freeze landed exactly while an answer was streaming. Two things keep it
+  fixed — ruff's `ASYNC` blocking-call rules, and
+  `tests/unit/test_event_loop_not_blocked.py`, which runs a ticker coroutine
+  during the handler and asserts the loop kept getting control.
+- **A focus ring you can see.** 10.8.0 added `border-color` to the transition
+  on the capture pills, so keyboard focus faded in over 150ms and at the
+  instant it landed the pill still looked idle. Focus rings may not ease.
+- **The Brain stops thinking when it has answered.** A retrieval pulse parked a
+  900ms timer that put the organism back into "thinking"; if the answer
+  finished inside that window the timer still fired, and the Brain sat visibly
+  working on a question it had already answered.
+- **One language, further in.** Fourteen more routers moved to the message
+  catalog — chat, memory, graph, files, portability, review, models, tools,
+  MCP, setup. `models.py`, `mcp.py` and `tools.py` had been answering some
+  errors in Korean and others in English on the same screen. Two gates keep
+  them migrated, and a third fails if the two gates disagree.
+- **The welcome screen fits.** It measured 770px against a 747px viewport, so
+  the line explaining what you are agreeing to sat under the fold. Nothing was
+  removed; the whitespace gave back the 25px.
+- **The streaming answer path has tests.** `useBrainChat` was 12% covered
+  because asserting anything about a stream needs frames arriving over time.
+  `frontend/src/test/fakeChatStream.ts` is that harness; eleven cases now cover
+  the answer building up, the stop button, refusals, grounding badges and live
+  step frames.
+- **Evidence bound to this build.** `output/release/v10.9.0/` holds the twelve
   capture screens, walkthrough gif/webm, and the asset-manifest / mock-server
-  fingerprints that lint re-checks before merge.
-- **Exact artifact names only.** Publish paths list `dist/ltcai-10.8.0-*` and
-  `ltcai-10.8.0.tgz` — never `dist/*`.
+  fingerprints that lint re-checks before merge. 10.9.0 claims no screen
+  redesign, and `scripts/release_screen_claims.json` says so explicitly.
+- **Exact artifact names only.** Publish paths list `dist/ltcai-10.9.0-*` and
+  `ltcai-10.9.0.tgz` — never `dist/*`.
 
 Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)
 
-Expected artifacts for 10.8.0 release must use exact filenames:
+Expected artifacts for 10.9.0 release must use exact filenames:
 
-- `dist/ltcai-10.8.0-py3-none-any.whl`
-- `dist/ltcai-10.8.0.tar.gz`
-- `ltcai-10.8.0.tgz`
-- `dist/ltcai-10.8.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_10.8.0_aarch64.dmg`
+- `dist/ltcai-10.9.0-py3-none-any.whl`
+- `dist/ltcai-10.9.0.tar.gz`
+- `ltcai-10.9.0.tgz`
+- `dist/ltcai-10.9.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_10.9.0_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -149,6 +150,7 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 | Version | Theme |
 | --- | --- |
+| 10.9.0 | Never Blocks |
 | 10.8.0 | Within Reach |
 | 10.7.0 | Plain Surface |
 | 10.6.4 | Loud Limits |

package/docs/CHANGELOG.md

@@ -4,6 +4,43 @@ 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.
 
+## [10.9.0] - 2026-08-05
+
+### Fixed
+- 모델 내려받기(`ollama pull`, Hugging Face), 엔진 설치, MCP `pip`/`npm` 설치,
+  `/local/sysinfo` 호스트 측정이 `async def` 안에서 그대로 실행되어 실행 중
+  서버 전체가 다른 요청을 처리하지 못하던 문제 — 전부 `asyncio.to_thread`로
+  이관. 최악의 경우 15분(다운로드 타임아웃)간 채팅·`/health`·UI가 모두 멈췄습니다.
+- Telegram 브리지의 사진/문서 업로드가 파일을 이벤트 루프에서 읽던 문제.
+- 캡처 필의 키보드 포커스 테두리가 150ms에 걸쳐 서서히 나타나, 포커스가 닿는
+  순간에는 여전히 idle 색이던 문제(`home-simple.css` transition에서
+  `border-color` 제거).
+- 답변이 끝난 뒤에도 Brain 유기체가 "생각 중"에 머물던 문제 — 회상 펄스가
+  건 900ms 타이머가 스트림 종료 시 취소되지 않았습니다.
+- 같은 틱에 두 번 전송될 때 `stopStreaming`이 중단 핸들을 잃던 문제.
+- 환영 화면이 747px 뷰포트에서 770px이라 마지막 안내 문장이 접힌 부분 아래에
+  있던 문제(`@media (max-height: 820px)` 단계 추가).
+
+### Added
+- `tests/unit/test_event_loop_not_blocked.py` — 핸들러 실행 중 티커 코루틴을
+  돌려 이벤트 루프가 실제로 제어권을 받았는지 측정하는 회귀 테스트.
+- `frontend/src/test/fakeChatStream.ts` — 프레임이 시간에 걸쳐 도착하는 가짜
+  SSE 하네스. `useBrainChat.test.tsx` 11개 시나리오.
+- `scripts/check_server_i18n.mjs` — 이관 완료 선언된 라우터에서 문자열 리터럴
+  detail을 금지하는 lint 게이트(`npm run lint`에 편입).
+- `tests/visual/v3.spec.js` — 환영 화면 fold 테스트, 캡처 필 포커스 테두리.
+- ruff `ASYNC210/220/221/222/230/251` 규칙.
+
+### Changed
+- 서버 메시지 카탈로그를 14개 라우터로 확대(chat, chat_history, chat_intents,
+  memory, knowledge_graph, local_files, portability, review_queue,
+  project_sessions, network_boundary, models, tools, mcp, setup) — 총 17개.
+  `MIGRATED_ROUTERS`와 lint 게이트 목록이 어긋나면 테스트가 실패합니다.
+- `latticeai/services/model_loading.py`: 엔진 준비/다운로드 블록을
+  `_prepare_model_sources()`로 추출(워커 스레드에서 실행 가능한 동기 함수).
+- `latticeai/api/static_routes.py`: 호스트 측정을 `_probe_host_capacity()`로
+  추출.
+
 ## [10.8.0] - 2026-08-04
 
 ### Fixed

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **10.8.0 — Within Reach**.
+Current release: **10.9.0 — Never Blocks**.
 
 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

package/docs/DEVELOPMENT.md

@@ -3,7 +3,7 @@
 > **Status: canonical** — current contributor guidance, kept in sync with the
 > current release.
 
-Current release: **10.8.0 — Within Reach**.
+Current release: **10.9.0 — Never Blocks**.
 
 This document is for contributors working on the local-first Digital Brain
 codebase. Product positioning and quick start stay in `README.md`; release

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **10.8.0 — Within Reach**.
+Current release: **10.9.0 — Never Blocks**.
 
 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

package/docs/OPERATIONS.md

@@ -1,4 +1,4 @@
-# Lattice AI — Operations Guide (v10.8.0)
+# Lattice AI — Operations Guide (v10.9.0)
 
 > **Status: canonical** — kept in sync with the current release. Storage layout
 > below reflects the SQLite live Brain store and workspace scoping, not the

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **10.8.0 — Within Reach**.
+Current release: **10.9.0 — Never Blocks**.
 
 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: **10.8.0 — Within Reach**.
+Current release: **10.9.0 — Never Blocks**.
 
 **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: **10.8.0 — Within Reach**.
+Current release: **10.9.0 — Never Blocks**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `lattice_brain/graph/schema.py`

package/lattice_brain/__init__.py

@@ -26,7 +26,7 @@ from .storage import (
     storage_from_env,
 )
 
-__version__ = "10.8.0"
+__version__ = "10.9.0"
 
 __all__ = [
     "AgentRuntime",

package/lattice_brain/runtime/multi_agent.py

@@ -49,7 +49,7 @@ from typing import Any, Callable, Dict, List, Optional
 from ..utils import now_iso as _now
 from .contracts import multi_agent_contract
 
-MULTI_AGENT_VERSION = "10.8.0"
+MULTI_AGENT_VERSION = "10.9.0"
 
 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__ = "10.8.0"
+__version__ = "10.9.0"

package/latticeai/api/chat.py

@@ -51,6 +51,7 @@ from latticeai.api.chat_hybrid import (
 )
 from latticeai.api.chat_intents import ChatIntentController
 from latticeai.api.chat_stream import stream_chat
+from latticeai.core.messages import DEFAULT_LANGUAGE, resolve_language, translate
 from latticeai.core.project_sessions import ProjectSessionStore
 from latticeai.core.run_store import AgentRunStore
 from latticeai.services.app_context import AppContext
@@ -122,12 +123,13 @@ def create_chat_router(context: AppContext) -> APIRouter:
     def authenticated_identity(
         current_user: str,
         claimed_email: Optional[str],
+        language: str = DEFAULT_LANGUAGE,
     ) -> Optional[str]:
         if current_user and claimed_email:
             if current_user.strip().lower() != claimed_email.strip().lower():
                 raise HTTPException(
                     status_code=403,
-                    detail="user_email must match the authenticated user.",
+                    detail=translate("common.user_mismatch", language),
                 )
         return current_user or claimed_email or None
 
@@ -239,12 +241,12 @@ def create_chat_router(context: AppContext) -> APIRouter:
         notify=notify_chat_message,
     )
 
-    def request_model(model_id: Optional[str]) -> Optional[str]:
+    def request_model(model_id: Optional[str], language: str = DEFAULT_LANGUAGE) -> Optional[str]:
         selected = model_id or model_router.current_model_id
         if model_id and model_id not in model_router.loaded_model_ids:
             raise HTTPException(
                 status_code=404,
-                detail=f"Model '{model_id}' not loaded.",
+                detail=translate("chat.model_not_loaded", language, model=model_id),
             )
         return selected
 
@@ -258,7 +260,7 @@ def create_chat_router(context: AppContext) -> APIRouter:
             len(req.image_data) if req.image_data else 0,
             len(req.message or ""),
         )
-        effective_email = authenticated_identity(current_user, req.user_email)
+        effective_email = authenticated_identity(current_user, req.user_email, resolve_language(request))
         workspace_id = write_workspace(
             workspace_scope_from_request(request),
             current_user,
@@ -293,7 +295,7 @@ def create_chat_router(context: AppContext) -> APIRouter:
                 history_user=history_user,
             )
 
-        selected_model_id = request_model(req.model)
+        selected_model_id = request_model(req.model, resolve_language(request))
         file_intent = is_file_action_request(req.message)
         if file_intent and context.funnel_metrics is not None:
             context.funnel_metrics.increment("file_requests")
@@ -303,11 +305,12 @@ def create_chat_router(context: AppContext) -> APIRouter:
                 model_id=selected_model_id,
                 effective_email=effective_email,
                 workspace_id=workspace_id,
+                language=resolve_language(request),
             )
             if direct_response is not None:
                 return direct_response
         if not selected_model_id:
-            return intent_controller.no_model_response()
+            return intent_controller.no_model_response(resolve_language(request))
         if file_intent:
             return await intent_controller.route_file_to_agent(
                 req,

package/latticeai/api/chat_agent_http.py

@@ -29,6 +29,7 @@ from latticeai.api.chat_helpers import (
 )
 from latticeai.api.chat_stream import agent_live_stream
 from latticeai.core.agent import AgentRunContext, AgentState, normalize_plan
+from latticeai.core.messages import resolve_language
 from latticeai.core.quiet import quiet
 from latticeai.core.run_explain import explain_run
 
@@ -266,7 +267,7 @@ class AgentHTTPController:
         """
         current_user = self.require_user(request)
         self.enforce_rate_limit(current_user, "agent")
-        effective_email = self.authenticated_identity(current_user, req.user_email)
+        effective_email = self.authenticated_identity(current_user, req.user_email, resolve_language(request))
         header_workspace = workspace_scope_from_request(request)
         if req.workspace_id and header_workspace and req.workspace_id != header_workspace:
             raise HTTPException(

package/latticeai/api/chat_history.py

@@ -9,7 +9,9 @@ from __future__ import annotations
 from dataclasses import dataclass
 from typing import Any, Callable, Dict
 
-from fastapi import APIRouter, HTTPException, Request
+from fastapi import APIRouter, Request
+
+from latticeai.core.messages import http_error, resolve_language
 
 
 @dataclass(frozen=True)
@@ -48,7 +50,7 @@ def register_history_routes(router: APIRouter, deps: HistoryRouteDependencies) -
             **deps.scope_for_user(current_user),
         )
         if not messages:
-            raise HTTPException(status_code=404, detail="대화를 찾을 수 없습니다.")
+            raise http_error(404, "chat.conversation_not_found", resolve_language(request))
         return {"id": conversation_id, "messages": messages}
 
     @router.delete("/history/conversations/{conversation_id:path}")

package/latticeai/api/chat_intents.py

@@ -31,9 +31,10 @@ from latticeai.core.file_generation import (
     repair_bundle_references,
     validate_project_bundle,
 )
+from latticeai.core.messages import DEFAULT_LANGUAGE, translate
 
 
-def next_available_path(root: Path, target: str) -> str:
+def next_available_path(root: Path, target: str, language: str = DEFAULT_LANGUAGE) -> str:
     """Return ``target`` unchanged, or a ``name_2.ext``-style variant when the
     file already exists in the workspace.
 
@@ -54,7 +55,7 @@ def next_available_path(root: Path, target: str) -> str:
             return str(Path(target).with_name(variant.name))
     raise HTTPException(
         status_code=409,
-        detail=f"'{target}' 이름의 파일이 너무 많습니다. 다른 이름을 지정해 주세요.",
+        detail=translate("chat.file_name_collision", language, name=target),
     )
 
 
@@ -118,14 +119,10 @@ class ChatIntentController:
         except Exception as exc:  # noqa: BLE001 — metrics must never break chat
             logging.warning("funnel metrics increment failed: %s", exc)
 
-    def no_model_response(self) -> JSONResponse:
-        detail = "No model loaded. Call /models/load first."
+    def no_model_response(self, language: str = DEFAULT_LANGUAGE) -> JSONResponse:
+        detail = translate("chat.no_model_loaded", language)
         if self.config.is_public:
-            detail = (
-                "No public model loaded. Set OPENAI_API_KEY and "
-                f"LATTICEAI_PUBLIC_MODEL={self.public_model}, or call /models/load "
-                "with an OpenAI-compatible model."
-            )
+            detail = translate("models.public_model_missing", language, model=self.public_model)
         return JSONResponse(
             status_code=400,
             content={
@@ -249,6 +246,7 @@ class ChatIntentController:
         model_id: Optional[str],
         effective_email: Optional[str] = None,
         workspace_id: Optional[str] = None,
+        language: str = DEFAULT_LANGUAGE,
     ):
         # An explicit path ("report.txt") wins; otherwise infer one from an
         # explicit type keyword ("html 파일 만들어줘") so weak models never
@@ -266,19 +264,20 @@ class ChatIntentController:
                     model_id=model_id,
                     effective_email=effective_email,
                     workspace_id=workspace_id,
+                    language=language,
                 )
         target_path = explicit_target or infer_file_target(req.message)
         if not target_path:
             return None
         # Never silently overwrite: an existing target gets a _2/_3 suffix so
         # regeneration is safe and repeatable without the proposal flow.
-        deduped_path = next_available_path(self.agent_root, target_path)
+        deduped_path = next_available_path(self.agent_root, target_path, language)
         renamed = deduped_path != target_path
         target_path = deduped_path
         content = inline_file_action_content(req.message)
         generation_meta: Optional[Dict[str, Any]] = None
         if content is None and not model_id:
-            return self.no_model_response()
+            return self.no_model_response(language)
         if content is None and model_id:
             # Model-agnostic pipeline: strict extension-aware prompt →
             # extraction → validation → one corrective retry → deterministic
@@ -302,7 +301,7 @@ class ChatIntentController:
         if content is None:
             raise HTTPException(
                 status_code=400,
-                detail="File content could not be generated.",
+                detail=translate("chat.file_generation_failed", language),
             )
         try:
             result = self.execute_tool(
@@ -395,6 +394,7 @@ class ChatIntentController:
         model_id: Optional[str],
         effective_email: Optional[str] = None,
         workspace_id: Optional[str] = None,
+        language: str = DEFAULT_LANGUAGE,
     ):
         """Artifact Loop: manifest → per-file generate/validate → bundle write.
 
@@ -405,8 +405,8 @@ class ChatIntentController:
         standard ``artifacts[]`` contract, and downloadable as a zip.
         """
         if not model_id:
-            return self.no_model_response()
-        project_dir = next_available_path(self.agent_root, manifest["name"])
+            return self.no_model_response(language)
+        project_dir = next_available_path(self.agent_root, manifest["name"], language)
         bundle_files = [str(f["path"]) for f in manifest["files"]]
 
         async def _generate(context: str) -> str:

package/latticeai/api/knowledge_graph.py

@@ -19,6 +19,7 @@ from latticeai.api.workspace_scope import (
     resolve_workspace_scope,
     workspace_scope_from_request,
 )
+from latticeai.core.messages import http_error, resolve_language
 from latticeai.core.quiet import quiet
 
 
@@ -456,9 +457,9 @@ def create_knowledge_graph_router(
     async def knowledge_graph_neighbors(node_id: str, request: Request):
         kg, allowed = _scoped(request)
         if not node_id:
-            raise HTTPException(status_code=400, detail="node_id required")
+            raise http_error(400, "graph.node_id_required", resolve_language(request))
         if allowed is not None and not _filter_scoped(kg, [{"id": node_id}], allowed):
-            raise HTTPException(status_code=404, detail="node not found")
+            raise http_error(404, "graph.node_not_found", resolve_language(request))
         payload = kg.neighbors(node_id)
         if allowed is not None:
             neighbors = _filter_scoped(kg, payload.get("neighbors", []), allowed)
@@ -476,13 +477,13 @@ def create_knowledge_graph_router(
         current_user = require_user(request)
         if current_user and req.user_email:
             if current_user.strip().lower() != req.user_email.strip().lower():
-                raise HTTPException(status_code=403, detail="user_email must match the authenticated user.")
+                raise http_error(403, "common.user_mismatch", resolve_language(request))
         effective_user = current_user or req.user_email or None
         kg = graph()
         workspace_id = _write_workspace(request, current_user)
         event_type = (req.type or "").strip().lower()
         if event_type not in {"message", "ai_response", "note"}:
-            raise HTTPException(status_code=400, detail="지원하는 type: message, ai_response, note")
+            raise http_error(400, "graph.unsupported_type", resolve_language(request))
         role = req.role or ("assistant" if event_type == "ai_response" else "user")
         if ingestion_pipeline is not None:
             source_type = "chat_message" if event_type in {"message", "ai_response"} else "note"