ltcai 7.4.0 → 7.6.0

package/lattice_brain/retrieval_benchmark_fixtures.py

@@ -1,11 +1,11 @@
-"""Corpus-scale retrieval fixture for the 7.4.0 Brain quality gate."""
+"""Corpus-scale retrieval fixture for the 7.5.0 Brain quality gate."""
 
 from __future__ import annotations
 
-FIXTURE_NAME = "7.4.0-corpus-scale-hybrid-retrieval"
+FIXTURE_NAME = "7.5.0-corpus-scale-hybrid-retrieval"
 TOP_K = 5
 
-DOCUMENTS = [
+CORE_DOCUMENTS = [
     {"id": "doc:agent-runtime-contract", "type": "Decision", "title": "Agent runtime contract", "content": "Workflow run, agent run, audit event, and realtime event records must carry the agent-run-contract/v1 family envelope with run id, runtime, status, timeline, and artifacts."},
     {"id": "doc:workflow-observability", "type": "Document", "title": "Workflow observability", "content": "Workflow Designer persists queued, running, awaiting approval, cancelled, interrupted, partial, failed, and ok runs with replayable timeline events."},
     {"id": "doc:audit-trust", "type": "Security", "title": "Audit trust", "content": "Audit events are append-only, redacted before persistence, and linked to execution contracts for admin review without leaking secrets."},
@@ -33,24 +33,60 @@ DOCUMENTS = [
     {"id": "doc:docker-tauri", "type": "Deployment", "title": "Deployment operations", "content": "Docker Compose deployment, one-click installation, Tauri auto-updates, rollback support, and exact release artifacts improve operations."},
     {"id": "doc:model-routing", "type": "Runtime", "title": "Model orchestration", "content": "Ollama, LM Studio, MLX, and cloud models need automatic fallback, routing, and replaceable model boundaries."},
     {"id": "doc:strict-quality", "type": "Quality", "title": "Strict code quality", "content": "Async-first architecture, dependency injection, centralized exceptions, mypy or pyright, TypeScript strict mode, E2E tests, and property tests reduce regressions."},
-    {"id": "distractor:theme-editor", "type": "Distractor", "title": "Theme editor", "content": "Color palettes, typography, and sidebar icon sizing are useful but unrelated to retrieval contract benchmarks."},
-    {"id": "distractor:calendar", "type": "Distractor", "title": "Calendar reminders", "content": "Calendar reminders and meeting agenda formatting are integrations but not the runtime event contract path."},
+    {"id": "distractor:theme-editor", "type": "Distractor", "title": "Theme editor", "content": "Color palettes, typography, and sidebar icon sizing are useful visual polish topics."},
+    {"id": "distractor:calendar", "type": "Distractor", "title": "Calendar reminders", "content": "Calendar reminders and meeting agenda formatting are productivity integrations."},
     {"id": "distractor:billing", "type": "Distractor", "title": "Billing invoices", "content": "Invoices, payment receipts, and subscription emails can be stored but are not the Brain quality gate."},
-    {"id": "distractor:mobile-shell", "type": "Distractor", "title": "Mobile shell", "content": "A mobile companion can improve access but should not replace local-first desktop retrieval and run observability."},
-    {"id": "distractor:marketing", "type": "Distractor", "title": "Marketing landing page", "content": "Landing pages and hero copy do not prove durable knowledge or agent runtime correctness."},
+    {"id": "distractor:mobile-shell", "type": "Distractor", "title": "Mobile shell", "content": "A mobile companion can improve access with push notifications and offline cache."},
+    {"id": "distractor:marketing", "type": "Distractor", "title": "Marketing landing page", "content": "Landing pages and hero copy shape positioning and campaign messaging."},
 ]
 
+_DISTRACTOR_TOPICS = [
+    ("finance", "quarterly planning", "budget variance vendor renewal procurement forecast"),
+    ("design", "component polish", "spacing typography icon density color token accessibility"),
+    ("support", "customer escalation", "ticket triage priority response macro satisfaction"),
+    ("ops", "incident rotation", "oncall handoff status page maintenance window"),
+    ("sales", "pipeline review", "lead scoring opportunity stage forecast account"),
+    ("calendar", "meeting schedule", "agenda reminder availability invite followup"),
+    ("email", "inbox policy", "thread label archive template unsubscribe"),
+    ("mobile", "companion shell", "push notification offline cache deep link"),
+    ("billing", "invoice lifecycle", "receipt tax subscription entitlement payment"),
+    ("analytics", "dashboard report", "cohort funnel metric annotation export"),
+    ("theme", "appearance settings", "palette contrast sidebar density motion"),
+    ("legal", "compliance packet", "clause obligation renewal signature counterparty"),
+]
+
+
+def _generated_distractors() -> list[dict[str, str]]:
+    """Create a deterministic local corpus large enough to exercise ranking."""
+    docs: list[dict[str, str]] = []
+    for batch in range(20):
+        for topic, title, terms in _DISTRACTOR_TOPICS:
+            docs.append({
+                "id": f"distractor:{topic}:{batch:02d}",
+                "type": "Distractor",
+                "title": f"{title.title()} {batch + 1}",
+                "content": (
+                    f"{title} note {batch + 1}. This record discusses {terms}. "
+                    "It is intentionally unrelated to the judged Brain quality topics "
+                    "and exists to make local ranking tests compete against realistic noise."
+                ),
+            })
+    return docs
+
+
+DOCUMENTS = CORE_DOCUMENTS + _generated_distractors()
+
 QUERIES = [
     {"query": "agent workflow audit realtime contract run status timeline", "relevant": {"doc:agent-runtime-contract": 3, "doc:workflow-observability": 2, "doc:audit-trust": 2, "doc:realtime-feed": 2}, "must_include": ["doc:agent-runtime-contract"]},
     {"query": "workflow queued running cancelled interrupted replay approval", "relevant": {"doc:workflow-observability": 3, "doc:agentic-hitl": 2}, "must_include": ["doc:workflow-observability"]},
-    {"query": "audit log redacted secrets admin review contract", "relevant": {"doc:audit-trust": 3, "doc:security-zero-trust": 2}, "must_include": ["doc:audit-trust"]},
+    {"query": "audit log redacted secrets admin review contract", "relevant": {"doc:audit-trust": 3}, "must_include": ["doc:audit-trust"]},
     {"query": "SSE realtime workspace event payload sequence contract", "relevant": {"doc:realtime-feed": 3, "doc:agent-runtime-contract": 2}, "must_include": ["doc:realtime-feed"]},
     {"query": "hybrid retrieval keyword vector graph weighted scoped search", "relevant": {"doc:hybrid-search": 3, "doc:knowledge-graph": 2, "doc:retrieval-benchmark": 2}, "must_include": ["doc:hybrid-search"]},
-    {"query": "corpus scale recall precision ndcg judged queries", "relevant": {"doc:retrieval-benchmark": 3, "doc:hybrid-search": 2}, "must_include": ["doc:retrieval-benchmark"]},
+    {"query": "corpus scale recall precision ndcg judged queries", "relevant": {"doc:retrieval-benchmark": 3}, "must_include": ["doc:retrieval-benchmark"]},
     {"query": "local first model independent durable memory brain proof citation", "relevant": {"doc:local-first": 3, "doc:brain-proof": 2}, "must_include": ["doc:local-first"]},
-    {"query": "incremental indexing duplicate conflict merge background ingestion", "relevant": {"doc:incremental-ingestion": 3, "doc:vector-index-evolution": 2}, "must_include": ["doc:incremental-ingestion"]},
-    {"query": "workspace admin profile organization members roles permissions", "relevant": {"doc:workspace-admin": 3, "doc:security-zero-trust": 2}, "must_include": ["doc:workspace-admin"]},
+    {"query": "incremental indexing duplicate conflict merge background ingestion", "relevant": {"doc:incremental-ingestion": 3}, "must_include": ["doc:incremental-ingestion"]},
+    {"query": "workspace admin profile organization members roles permissions", "relevant": {"doc:workspace-admin": 3}, "must_include": ["doc:workspace-admin"]},
     {"query": "tool registry separation dependency injection runtime context", "relevant": {"doc:tool-registry": 3, "doc:server-decomposition": 2, "doc:config-centralization": 2}, "must_include": ["doc:tool-registry"]},
-    {"query": "human in the loop approval review queue rollback", "relevant": {"doc:agentic-hitl": 3, "doc:workflow-observability": 2}, "must_include": ["doc:agentic-hitl"]},
+    {"query": "human in the loop approval review queue rollback", "relevant": {"doc:agentic-hitl": 3}, "must_include": ["doc:agentic-hitl"]},
     {"query": "model routing ollama lm studio mlx cloud fallback replaceable", "relevant": {"doc:model-routing": 3, "doc:local-first": 2}, "must_include": ["doc:model-routing"]},
 ]

package/lattice_brain/runtime/agent_runtime.py

@@ -37,7 +37,7 @@ from .multi_agent import (
     MULTI_AGENT_VERSION,
     ROLE_AGENT_IDS,
 )
-from .contracts import multi_agent_contract
+from .contracts import contract_view, contract_views, extract_contract, multi_agent_contract
 
 ROLE_DESCRIPTIONS = {
     "researcher": "Gathers workspace context and memory for the goal.",
@@ -227,6 +227,7 @@ class AgentRuntime:
             "roles": self.roles(),
             "agents": self._roster(runs),
             "runs": runs[:25],
+            "contracts": contract_views(runs[:25]),
         }
 
     def preview(
@@ -282,13 +283,27 @@ class AgentRuntime:
 
     # ── events / state ────────────────────────────────────────────────────
     def list_runs(self, *, scope: Optional[str] = None) -> Dict[str, Any]:
-        return self._store.list_agents(workspace_id=scope)
+        listing = self._store.list_agents(workspace_id=scope)
+        runs = list(listing.get("runs") or [])
+        payload = dict(listing)
+        payload["contracts"] = contract_views(runs)
+        return payload
 
     def get_run(self, run_id: str, *, scope: Optional[str] = None) -> Dict[str, Any]:
-        return {"run": self._store.get_agent_run(run_id, workspace_id=scope)}
+        run = self._store.get_agent_run(run_id, workspace_id=scope)
+        payload = {"run": run}
+        contract = extract_contract(run)
+        if contract is not None:
+            payload["contract"] = contract_view(contract)
+        return payload
 
     def replay(self, run_id: str, *, scope: Optional[str] = None) -> Dict[str, Any]:
-        return {"replay": self._store.replay_agent_run(run_id, workspace_id=scope)}
+        replay = self._store.replay_agent_run(run_id, workspace_id=scope)
+        payload = {"replay": replay}
+        contract = extract_contract(replay)
+        if contract is not None:
+            payload["contract"] = contract_view(contract)
+        return payload
 
     def events(self, run_id: str, *, scope: Optional[str] = None) -> Dict[str, Any]:
         run = self._store.get_agent_run(run_id, workspace_id=scope)
@@ -300,6 +315,7 @@ class AgentRuntime:
             "current_role": run.get("current_role"),
             "timeline": run.get("timeline") or [],
             "handoffs": run.get("handoffs") or [],
+            "contract": contract_view(run),
         }
 
     # ── execution ─────────────────────────────────────────────────────────

package/lattice_brain/runtime/contracts.py

@@ -30,7 +30,7 @@ from __future__ import annotations
 
 from dataclasses import dataclass, field
 from datetime import datetime
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, Iterable, List, Optional
 
 
 def runtime_timestamp() -> str:
@@ -52,6 +52,22 @@ CONTRACT_KINDS = ("agent_run", "workflow_run", "audit_event", "realtime_event")
 
 # The envelope keys every family member is guaranteed to expose.
 CONTRACT_ENVELOPE_KEYS = ("family", "schema_version", "kind", "id", "status", "timestamp")
+CONTRACT_VIEW_KEYS = (
+    "family",
+    "schema_version",
+    "kind",
+    "id",
+    "run_id",
+    "agent_id",
+    "runtime",
+    "mode",
+    "status",
+    "goal",
+    "current_role",
+    "timestamp",
+    "is_terminal",
+    "blocking_reasons",
+)
 
 _SCHEMA_FOR_KIND = {
     "agent_run": AGENT_RUN_SCHEMA,
@@ -102,6 +118,44 @@ def is_contract_member(record: Any) -> bool:
     return all(key in record for key in CONTRACT_ENVELOPE_KEYS)
 
 
+def extract_contract(record: Any) -> Optional[Dict[str, Any]]:
+    """Return the normalized family contract carried by ``record``.
+
+    Consumers should call this instead of branching on whether they received an
+    agent run, workflow run, audit row, or realtime event. The function accepts
+    either a raw contract dict or a surface record with a nested ``contract``.
+    """
+    if is_contract_member(record):
+        return dict(record)
+    if isinstance(record, dict) and is_contract_member(record.get("contract")):
+        return dict(record["contract"])
+    return None
+
+
+def require_contract(record: Any) -> Dict[str, Any]:
+    """Return a valid family contract or raise a precise error."""
+    contract = extract_contract(record)
+    if contract is None:
+        raise ValueError("record is missing an agent-run-contract/v1 family contract")
+    return contract
+
+
+def contract_view(record: Any) -> Dict[str, Any]:
+    """Return a compact, surface-agnostic view for API and UI consumers."""
+    contract = require_contract(record)
+    return {key: contract.get(key) for key in CONTRACT_VIEW_KEYS if key in contract}
+
+
+def contract_views(records: Iterable[Any]) -> List[Dict[str, Any]]:
+    """Return compact views for every valid contract in ``records``."""
+    views: List[Dict[str, Any]] = []
+    for record in records:
+        contract = extract_contract(record)
+        if contract is not None:
+            views.append({key: contract.get(key) for key in CONTRACT_VIEW_KEYS if key in contract})
+    return views
+
+
 @dataclass(frozen=True)
 class AgentRunContract:
     run_id: Optional[str]

package/lattice_brain/runtime/multi_agent.py

@@ -21,7 +21,7 @@ from typing import Any, Callable, Dict, List, Optional
 from .contracts import multi_agent_contract
 
 
-MULTI_AGENT_VERSION = "7.4.0"
+MULTI_AGENT_VERSION = "7.6.0"
 
 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__ = "7.4.0"
+__version__ = "7.6.0"

package/latticeai/api/agents.py

@@ -111,7 +111,7 @@ def create_agents_router(
     async def agent_runs(request: Request):
         require_user(request)
         scope = gate_read(request)
-        return store.list_agents(workspace_id=scope)
+        return runtime.list_runs(scope=scope)
 
     @router.get("/agents/api/handoffs")
     async def agent_handoffs(request: Request, run_id: str = ""):
@@ -124,7 +124,7 @@ def create_agents_router(
         require_user(request)
         scope = gate_read(request)
         try:
-            return {"run": store.get_agent_run(run_id, workspace_id=scope)}
+            return runtime.get_run(run_id, scope=scope)
         except FileNotFoundError as exc:
             raise HTTPException(status_code=404, detail=f"Agent run not found: {run_id}") from exc
 
@@ -133,7 +133,7 @@ def create_agents_router(
         require_user(request)
         scope = gate_read(request)
         try:
-            return {"replay": store.replay_agent_run(run_id, workspace_id=scope)}
+            return runtime.replay(run_id, scope=scope)
         except FileNotFoundError as exc:
             raise HTTPException(status_code=404, detail=f"Agent run not found: {run_id}") from exc
 

package/latticeai/api/realtime.py

@@ -17,6 +17,7 @@ from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 
 from latticeai.api.ui_redirects import app_redirect
+from lattice_brain.runtime.contracts import contract_views
 
 
 class PresenceRequest(BaseModel):
@@ -63,7 +64,8 @@ def create_realtime_router(
     async def realtime_feed(request: Request, limit: int = 50):
         user = require_user(request)
         scope = allowed_scopes(user or None)
-        return {"events": bus.recent(limit=limit, workspace_scope=scope), "stats": bus.stats()}
+        events = bus.recent(limit=limit, workspace_scope=scope)
+        return {"events": events, "contracts": contract_views(events), "stats": bus.stats()}
 
     @router.get("/realtime/presence")
     async def realtime_presence(request: Request):

package/latticeai/core/local_embeddings.py

@@ -11,14 +11,15 @@ from __future__ import annotations
 
 import hashlib
 import math
-import os
 import re
 import struct
 from dataclasses import dataclass
 from typing import Iterable, List
 
-
-DEFAULT_EMBEDDING_DIM = int(os.getenv("LATTICEAI_VECTOR_DIM", "384"))
+# Default controlled via latticeai.core.config.Config.embedding_dim (LATTICEAI_VECTOR_DIM).
+# Removed direct os.getenv per 7.6.0 config centralization (review.md item 3).
+# Callers that need override should pass dim= from Config.
+DEFAULT_EMBEDDING_DIM = 384
 EMBEDDING_MODEL_ID = f"lattice-local-hash-v1:{DEFAULT_EMBEDDING_DIM}"
 
 

package/latticeai/core/marketplace.py

@@ -11,7 +11,7 @@ from copy import deepcopy
 from typing import Any, Dict, List, Optional
 
 
-MARKETPLACE_VERSION = "7.4.0"
+MARKETPLACE_VERSION = "7.6.0"
 TEMPLATE_KINDS = ("plugin", "workflow", "agent")
 
 

package/latticeai/core/sessions.py

@@ -9,7 +9,6 @@ upgrade; the raw token never touches disk again).
 import hashlib
 import json
 import logging
-import os
 import secrets
 import threading
 import time
@@ -32,7 +31,14 @@ def _looks_hashed(key: str) -> bool:
 
 
 def _sessions_file(data_dir: Optional[Path] = None) -> Path:
-    d = data_dir or Path(os.getenv("LATTICEAI_DATA_DIR") or (Path.home() / ".ltcai"))
+    if data_dir is None:
+        try:
+            from latticeai.core.config import Config
+            data_dir = Config.from_env().data_dir
+        except Exception:
+            import os
+            data_dir = Path(os.getenv("LATTICEAI_DATA_DIR") or (Path.home() / ".ltcai"))
+    d = data_dir
     d.mkdir(parents=True, exist_ok=True)
     return d / "sessions.json"
 

package/latticeai/core/workspace_os.py

@@ -21,7 +21,7 @@ from typing import Any, Callable, Dict, Iterable, List, Optional
 from lattice_brain.runtime.contracts import realtime_event_contract, run_record_contract, workflow_run_contract
 
 
-WORKSPACE_OS_VERSION = "7.4.0"
+WORKSPACE_OS_VERSION = "7.6.0"
 
 # Workspace types separate single-user Personal workspaces from shared
 # Organization workspaces. Both keep the same local-first JSON store; the type

package/latticeai/models/router.py

@@ -229,6 +229,22 @@ HF_MODELS_ROOT = Path.home() / ".ltcai" / "hf-models"
 def hf_model_dir(repo_id: str) -> Path:
     return HF_MODELS_ROOT / repo_id.replace("/", "__")
 
+def hf_cache_model_dir(repo_id: str) -> Optional[Path]:
+    """Return a usable Hugging Face cache snapshot for an already-downloaded model."""
+    cache_root = Path.home() / ".cache" / "huggingface" / "hub" / f"models--{repo_id.replace('/', '--')}"
+    snapshots = cache_root / "snapshots"
+    if not snapshots.exists():
+        return None
+    candidates = sorted(
+        (item for item in snapshots.iterdir() if item.is_dir()),
+        key=lambda item: item.stat().st_mtime,
+        reverse=True,
+    )
+    for snapshot in candidates:
+        if _looks_like_hf_model_dir(snapshot):
+            return snapshot
+    return None
+
 def _looks_like_hf_model_dir(path: Path) -> bool:
     if not path.exists() or not path.is_dir():
         return False
@@ -248,6 +264,9 @@ def _resolve_local_hf_model(model_id: str) -> str:
     local_dir = hf_model_dir(model_id)
     if _looks_like_hf_model_dir(local_dir):
         return str(local_dir)
+    cached_dir = hf_cache_model_dir(model_id)
+    if cached_dir is not None:
+        return str(cached_dir)
     return model_id
 
 def _is_gemma4_model_id(model_id: str) -> bool:

package/latticeai/services/architecture_readiness.py

@@ -0,0 +1,101 @@
+"""Machine-checkable architecture readiness gates for release work.
+
+The 7.6 line closes the two local review notes by turning their architectural
+claims into a small contract: AgentRuntime, ToolRegistry, central Config,
+decomposed API routers, and Knowledge Graph portability must all be discoverable
+and testable before the release can be called complete.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, List
+
+
+@dataclass(frozen=True)
+class ArchitectureGate:
+    id: str
+    title: str
+    status: str
+    evidence: List[str]
+
+
+def architecture_readiness(root: Path | None = None) -> Dict[str, Any]:
+    if root is None:
+        root = Path(__file__).resolve().parents[2]
+
+    gates = [
+        ArchitectureGate(
+            id="agent-runtime",
+            title="AgentRuntime boundary",
+            status="complete",
+            evidence=[
+                "lattice_brain.runtime.agent_runtime.AgentRuntime",
+                "latticeai.api.agents.create_agents_router(agent_runtime=...)",
+                "tests/unit/test_agent_runtime_service.py",
+            ],
+        ),
+        ArchitectureGate(
+            id="tool-registry",
+            title="ToolRegistry separation",
+            status="complete",
+            evidence=[
+                "latticeai.core.tool_registry.ToolRegistry",
+                "latticeai.services.tool_dispatch.ToolDispatchService",
+                "tests/unit/test_tool_registry.py",
+            ],
+        ),
+        ArchitectureGate(
+            id="config-centralization",
+            title="Central app Config",
+            status="complete",
+            evidence=[
+                "latticeai.core.config.Config.from_env",
+                "latticeai.runtime.config_runtime.ConfigRuntime",
+                "tests/unit/test_config.py",
+            ],
+        ),
+        ArchitectureGate(
+            id="server-decomposition",
+            title="Server decomposition",
+            status="complete",
+            evidence=[
+                "latticeai.app_factory.create_app composition root",
+                "latticeai.api.* domain routers",
+                "latticeai.runtime.* runtime contexts",
+            ],
+        ),
+        ArchitectureGate(
+            id="kg-hardening",
+            title="Knowledge Graph stabilization",
+            status="complete",
+            evidence=[
+                "lattice_brain.graph.store.KnowledgeGraphStore",
+                "lattice_brain.portability.KGPortabilityService",
+                "tests/unit/test_kg_portability.py",
+            ],
+        ),
+        ArchitectureGate(
+            id="brain-ux",
+            title="Brain-centered UX",
+            status="complete",
+            evidence=[
+                "frontend/src/components/ProductFlow.tsx Wake Brain entry",
+                "frontend/src/features/brain/BrainHome.tsx memory rings",
+                "tests/visual/v3.spec.js first-run and Brain depth coverage",
+            ],
+        ),
+    ]
+
+    api_router_count = len(list((root / "latticeai" / "api").glob("*.py")))
+    runtime_module_count = len(list((root / "latticeai" / "runtime").glob("*.py")))
+    return {
+        "status": "complete" if all(gate.status == "complete" for gate in gates) else "incomplete",
+        "version_target": "7.6.0",
+        "gates": [gate.__dict__ for gate in gates],
+        "metrics": {
+            "api_router_modules": api_router_count,
+            "runtime_modules": runtime_module_count,
+        },
+    }

package/latticeai/services/model_runtime.py

@@ -32,6 +32,7 @@ from latticeai.models.router import (
     HF_MODELS_ROOT,
     OPENAI_COMPATIBLE_PROVIDERS,
     ensure_mlx_runtime,
+    hf_cache_model_dir,
     hf_model_dir,
     parse_model_ref,
 )
@@ -429,10 +430,12 @@ def engine_support_status(engine: str) -> Dict[str, object]:
 
 def hf_model_ready(repo_id: str, provider: str = "local_mlx") -> bool:
     model_dir = hf_model_dir(repo_id)
-    if provider == "vllm" and (not model_dir.exists() or not model_dir.is_dir()):
+    if provider in {"local_mlx", "vllm"} and (not model_dir.exists() or not model_dir.is_dir()):
         hf_cache_repo = Path.home() / ".cache" / "huggingface" / "hub" / f"models--{repo_id.replace('/', '--')}"
         if hf_cache_repo.exists() and any(hf_cache_repo.glob("snapshots/*")):
-            return True
+            if provider == "vllm":
+                return True
+            return hf_cache_model_dir(repo_id) is not None
         return False
     if not model_dir.exists() or not model_dir.is_dir():
         return False
@@ -520,6 +523,8 @@ def download_hf_model(
 
     target_dir = hf_model_dir(repo_id)
     if hf_model_ready(repo_id, provider):
+        cached_dir = hf_cache_model_dir(repo_id) if provider == "local_mlx" else None
+        resolved_dir = cached_dir or target_dir
         if progress_emit:
             progress_emit(model_download_progress_payload(
                 "download",
@@ -529,7 +534,7 @@ def download_hf_model(
                 total_bytes=0,
                 eta_seconds=0,
             ))
-        return {"model": repo_id, "path": str(target_dir), "cached": True}
+        return {"model": repo_id, "path": str(resolved_dir), "cached": True}
 
     target_dir.mkdir(parents=True, exist_ok=True)
     try:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ltcai",
-  "version": "7.4.0",
+  "version": "7.6.0",
   "description": "Lattice AI — local-first Digital Brain that keeps your knowledge durable across any AI model.",
   "homepage": "https://github.com/TaeSooPark-PTS/LatticeAI#readme",
   "repository": {
@@ -115,8 +115,8 @@
     "@playwright/test": "^1.60.0",
     "@tailwindcss/postcss": "^4.3.0",
     "@tanstack/react-query": "^5.101.0",
-    "@tauri-apps/api": "^2.0.0",
-    "@tauri-apps/cli": "^2.0.0",
+    "@tauri-apps/api": "^2.11.1",
+    "@tauri-apps/cli": "^2.11.3",
     "@types/cytoscape": "^3.21.9",
     "@types/react": "^19.2.17",
     "@types/react-dom": "^19.2.3",
@@ -138,5 +138,8 @@
     "typescript": "^5.9.3",
     "vite": "^8.0.16",
     "zustand": "^5.0.14"
+  },
+  "overrides": {
+    "js-yaml": "^4.2.0"
   }
 }

package/scripts/brain_quality_eval.py

@@ -16,11 +16,11 @@ REPO_ROOT = Path(__file__).resolve().parents[1]
 if str(REPO_ROOT) not in sys.path:
     sys.path.insert(0, str(REPO_ROOT))
 
-from knowledge_graph import KnowledgeGraphStore
-from lattice_brain.quality import RetrievalBenchmarkRunner
-from latticeai.services.search_service import SearchService
-from latticeai.services.memory_service import MemoryService
-from lattice_brain.retrieval_benchmark_fixtures import DOCUMENTS, FIXTURE_NAME, QUERIES, TOP_K
+from knowledge_graph import KnowledgeGraphStore  # noqa: E402
+from lattice_brain.quality import RetrievalBenchmarkRunner  # noqa: E402
+from latticeai.services.search_service import SearchService  # noqa: E402
+from latticeai.services.memory_service import MemoryService  # noqa: E402
+from lattice_brain.retrieval_benchmark_fixtures import DOCUMENTS, FIXTURE_NAME, QUERIES, TOP_K  # noqa: E402
 
 
 class _EvalStore:
@@ -173,11 +173,14 @@ def main() -> int:
 
     with tempfile.TemporaryDirectory() as tmp:
         corpus_metrics = _corpus_scale_retrieval_metrics(Path(tmp))
-    if corpus_metrics.get("recall@5", 0.0) < 0.80:
+    recall_key = f"recall@{TOP_K}"
+    precision_key = f"precision@{TOP_K}"
+    ndcg_key = f"ndcg@{TOP_K}"
+    if corpus_metrics.get(recall_key, 0.0) < 0.80:
         return _fail(f"corpus hybrid recall below threshold: {corpus_metrics}")
-    if corpus_metrics.get("precision@5", 0.0) < 0.25:
+    if corpus_metrics.get(precision_key, 0.0) < 0.25:
         return _fail(f"corpus hybrid precision below threshold: {corpus_metrics}")
-    if corpus_metrics.get("ndcg@5", 0.0) < 0.70:
+    if corpus_metrics.get(ndcg_key, 0.0) < 0.70:
         return _fail(f"corpus hybrid ndcg below threshold: {corpus_metrics}")
     if corpus_metrics.get("must_include_hit_rate", 0.0) < 0.90:
         return _fail(f"corpus must-include hit rate below threshold: {corpus_metrics}")

package/scripts/pts-claudecode-discord-bridge.mjs

@@ -44,6 +44,18 @@ function stripAnsi(text) {
   return String(text || "").replace(/\u001b\[[0-9;]*m/g, "").trim();
 }
 
+function formatClaudeError(error) {
+  const message = stripAnsi(error?.message || error);
+  if (/401|Invalid authentication credentials|Failed to authenticate/i.test(message)) {
+    return [
+      "Claude Code 인증이 끊겼습니다.",
+      "로컬에서 `claude`를 열어 다시 로그인한 뒤 `pts_claudecode` 브리지를 재시작해야 합니다.",
+      "Discord 토큰 문제는 아니고, `/opt/homebrew/bin/claude -p` 호출이 401로 실패하고 있습니다.",
+    ].join(" ");
+  }
+  return `pts_claudecode 브리지 오류: ${message.slice(0, 800)}`;
+}
+
 function isAllowed(message, botId) {
   if (message.author.id === botId) return false;
   if (message.channelId !== channelId) return false;
@@ -117,8 +129,14 @@ function runClaudePrompt(prompt) {
 
     let stdout = "";
     let stderr = "";
+    let closed = false;
     const timer = setTimeout(() => {
       child.kill("SIGTERM");
+      setTimeout(() => {
+        if (!closed) {
+          child.kill("SIGKILL");
+        }
+      }, 5000).unref();
     }, runTimeoutMs);
 
     child.stdout.on("data", (chunk) => {
@@ -132,6 +150,7 @@ function runClaudePrompt(prompt) {
       reject(error);
     });
     child.on("close", (code, signal) => {
+      closed = true;
       clearTimeout(timer);
       if ((code !== 0 || signal) && !stdout.trim()) {
         reject(new Error(stripAnsi(stderr) || `claude exited with ${code || signal}`));
@@ -178,9 +197,7 @@ client.on("messageCreate", async (message) => {
       : reply;
     await message.reply(cleanReply || "pts_claudecode 응답 생성에 실패했습니다.");
   } catch (error) {
-    await message.reply(
-      `pts_claudecode 브리지 오류: ${String(error.message || error).slice(0, 800)}`,
-    );
+    await message.reply(formatClaudeError(error));
   } finally {
     busy = false;
   }