fix(agent): include skills in distribution tarball and flatten root structure ...

- The agent update tarball now includes the 'skills/' directory.\n- Flattened the tarball root so files extract directly into the agent directory instead of a nested 'agent-node-source/' folder.

fix(agent): robust daemon install and gRPC config ...

- bootstrap_installer now forces config overwrite during daemon setup to prevent stale token reuse.\n- ai-hub now preserves gRPC port in generated config, preventing agents from defaulting to localhost.\n- installer now ensures gRPC endpoint always has an explicit port.

refactor: organize agent-node client code structure by moving core packages to src/ ...

- Moved agent_node, protos, and shared_core inside src/

- Updated Dockerfile, deployment scripts, compile_protos.sh, installers

- Updated bundle generation in ai-hub to reflect cleaner structure and better README

doc: update bundled run scripts to recommend daemon installer

feat: add swarm control chat history clear & agent node auto-update system ...

- Added API and UI to clear chat history in Swarm Control while preserving node sync

- Implemented HTTP-based auto-update agent bootstrapper and core daemon

- Removed unused workflow profile and orphaned voice-interaction-handler skill

- Fixed voice chat response duplication and tool-belt instructions

fix(hub): restore source code inclusion in agent bundle and fix path resolution for production

feat(hub): exclude source code and requirements.txt from agent bundle; add binary execution support to runner scripts

feat: enhance node access control, user preferences, and skill management ...

- Secured node-related endpoints with group-based access control.
- Fixed user preference merging to preserve node attachments.
- Restricted modification and deletion of system skills.
- Hidden administrative node controls for non-admin users.
- Fixed WebSocket connectivity and permission checks for node mesh.
- Filtered node visibility in profile and swarm control to granted nodes only.

fix(bundle): correct source path and improve runner robustness

feat(nodes): add explicit macOS double-click support with run_mac.command in agent bundle

feat(nodes): enhance agent bundle with README, run.sh (Linux/Mac) and run.bat (Windows) for seamless execution

fix(mesh): sync terminal status codes and implement periodic ghost mirror cleanup

fix(orchestration): resolve skill hallucination, brace crashes, and silent turns in swarm control ...

- Implemented strictly-worded 'Tool-belt' in system prompt to prevent hallucinating external skills.
- Replaced fragile .format() with robust .replace() for system prompts to prevent crashes on curly braces.
- Optimized TTS streaming: increased concurrency and reduced chunk sizes to eliminate mid-sentence pauses.
- Fixed 'silent turn' bug in Swarm Control by ensuring fallback content is yielded even if AI only produces reasoning/tools.
- Improved history formatting to handle assistant turns mapping to tool calls without main content.
- Corrected Gemini model fallback to gemini-1.5-flash.

refactor: remove dspy dependency and migrate to orchestration modules

feat: Implement real-time streaming for Swarm Chat and premium Antigravity UI

feat: Remove DSPy dependency and implement Swarm Control ...

- Removed DSPy-based pipelines (code assistant, file selector, question decider).
- Implemented Swarm Control for multi-node command execution and terminal handling.
- Updated gRPC services for batch command processing and improved perception.
- Replaced Coding Assistant page with Swarm Control interface in the UI.
- Updated Protobuf definitions to support interactive terminal sessions.
- Improved node registry and RAG services for better agent performance.

chore: backup local changes before investigation

fix(mesh/skills): fix incorrect get_db import causing uvicorn crash in production

feat(skills): central UI for creating, viewing, sharing and cloning LLM skills and workflows

fix(mesh): session node attach correctly parses and persists database changes via sqlalchemy

feat(mesh): proactive session cleanup algorithm

feat(mesh): robust node connectivity and sync reliability fixes ...

- Fixed Node Registry persistence by adding missing db.commit() for online/offline status updates.
- Resolved 'Seed from Local' sync failures by correctly tracking mesh memberships in the TaskAssistant service.
- Enhanced frontend safety: disabled offline node selection and filtered source node candidates.
- Added 'Receiver Only' toggle for more granular control over multi-node synchronization.
- Corrected false-positive 'Source Node Disconnected' alert by verifying global connection status.
- Improved logging in Hub and Agent Nodes for better debugging of file transfer events.

feat: agent node mesh integration and UI polish

feat(mesh): implement Phase 6 Rich Health Metrics ...

- Enhanced agent-node to collect per-core CPU, frequency, available RAM, and load avg.
- Updated gRPC server to ingest and propagate rich health metrics via heartbeats.
- Updated Pydantic schemas to expose rich metrics in REST and WebSocket snapshots.
- Fixed UI tooltips in NodesPage.js to pop downwards and show detailed statistics.
- Fixed RegistrationResponse field mismatch (message -> error_message).
- Updated feature documentation for Agent Node Mesh.

fix(fs): fix delete 422 error, add binary filter, and improve modal height

fix(fs): decouple node management from sync logic and hide dots in node explorer

fix(fs): fix recursive creation/deletion and add sync status indicators

fix: exhaustive fix for Node File Explorer 500 errors. Added orchestrator health checks, fixed gRPC subscript bugs, and added detailed production logging.

Integrated FileSystemNavigator for Agent Node Mesh

feat(terminal): overhaul with xterm.js, raw TTY streaming, and dynamic resizing ...

- Replaced simulated terminal with xterm.js for native emulation
- Implemented raw TTY byte streaming over WebSockets
- Added support for persistent shell sessions and window resizing (ioctl TIOCSWINSZ)
- Improved SkillManager with a transparent TTY bypass to prevent thread pool saturation
- Added periodic heartbeat-based latency monitoring (RTT)
- Fixed skill_config parsing crash in AI Hub registry
- Enabled auto-scrolling and terminal-to-PTY grid synchronization

feat: implement real-time node monitoring and workspace initialization strategies

feat(M6): fully integrate gRPC Agent Orchestrator into AI Hub backend, update deployment, and scale multi-node monitoring

feat(M3+M4): persistent sessions with node attachment + invite token auth ...

M3 — Persistent Session Model:
  DB:
  - Session model: +sync_workspace_id, +attached_node_ids (JSON), +node_sync_status (JSON)
  - Migration: auto-adds 3 new columns to existing sessions table
  API (sessions router):
  - POST /sessions/        now auto-attaches user's default_node_ids from preferences
    on creation, generates sync_workspace_id, seeds 'pending' sync status
  - POST /sessions/{id}/nodes       attach nodes to an existing session
  - DELETE /sessions/{id}/nodes/{node_id}   detach a node
  - GET  /sessions/{id}/nodes       live sync status (merges DB + live registry)
  Schemas: NodeAttachRequest, NodeSyncStatusEntry, SessionNodeStatusResponse

M4 — Invite Token Validation:
  API (nodes router):
  - GET  /nodes/admin/{id}/config.yaml  generate ready-to-deploy agent_config.yaml
    (contains node_id, hub_url, grpc_endpoint, invite_token, skill toggles)
  - POST /nodes/validate-token          internal endpoint called by gRPC server;
    validates token against DB, returns skill_config for SandboxPolicy
  gRPC (grpc_server.py):
  - SyncConfiguration now calls POST /nodes/validate-token before registering node
  - HUB_API_URL env var controls this; empty = dev mode (skip validation)
  - Shell skill disabled by admin → empty allowed_commands in SandboxPolicy
  - Gracefully degrades if Hub is unreachable (logs warning, proceeds in dev)

feat(M1+M2): Agent Node API — admin-owned nodes, group access, DB persistence ...

DB Models:
- AgentNode: admin-owned, display_name, skill_config toggles (shell/browser/sync),
  invite_token, is_active, last_status/last_seen_at persisted on every connect
- NodeGroupAccess: admin grants groups access with access_level (view/use/admin)
- Migration updated for all new columns + node_group_access table

NodeRegistryService (M2 persistence):
- register() → upserts AgentNode in DB (status=online)
- deregister() → marks AgentNode offline in DB, keeps record for UI
- update_stats() → bumps last_seen_at on every heartbeat
- EventBus with 20 event types: per-node + per-user WS fan-out
- Uses get_db_session() context manager (no extra deps)

API (13 routes):
Admin:
  POST   /nodes/admin              — Create node + generate invite_token
  GET    /nodes/admin              — List all nodes (full detail)
  GET    /nodes/admin/{id}         — Node detail incl. invite_token
  PATCH  /nodes/admin/{id}         — Update skill_config toggles, description
  POST   /nodes/admin/{id}/access  — Grant group access
  DELETE /nodes/admin/{id}/access/{group_id} — Revoke group access
User:
  GET    /nodes/                   — List user-accessible nodes (group-filtered)
  GET    /nodes/{id}/status        — Quick probe
  POST   /nodes/{id}/dispatch      — Dispatch task
  PATCH  /nodes/preferences        — Set default_node_ids + data_source config
  GET    /nodes/preferences        — Read node preferences
WebSocket:
  WS     /nodes/{id}/stream        — Single node live execution stream
  WS     /nodes/stream/all         — Multi-node global bus (split-pane UI)

feat(M1): add Agent Node REST + WebSocket API to AI Hub ...

- NodeRegistryService: in-memory live node registry with rich EventBus
  - emit() delivers all execution events to per-node and per-user subscribers
  - EVENT_TYPES: 20 structured event types (task_start, sync_drift, retry, etc.)
- AgentNode DB model: persists node registrations + invite_token + last_status
- DB migration: auto-creates agent_nodes table + adds new columns
- REST API (/nodes):
  GET  /nodes                   - list all user's nodes (live+DB merged)
  GET  /nodes/{node_id}         - full live status
  GET  /nodes/{node_id}/status  - quick online/offline probe
  POST /nodes/{node_id}/dispatch - dispatch shell/browser task to a node
- WebSocket API:
  WS /nodes/{node_id}/stream    - single-node live execution stream
  WS /nodes/stream/all          - multi-node global bus (split-pane UI ready)

Refactor UI consistency, fix layout scrolling, and remove deprecated WSS file access features

feat: resolve dynamic token limits from LiteLLM; unify context usage UI

feat: track STT/TTS models in session; fix audio progress bar; add token usage bar

fix: implement global settings fallback for LLM provider in RAG chat; allow fuzzy model name matching

fix: implement system-settings fallback in STT/TTS routes and resolve missing key 500 error

fix: relax provider health checks and allow non-admin verification for self-provided keys

fix: resolve STT/TTS provider resolution for anonymous/unauthenticated sessions

fix: resolve 'no active stt provider' by ensuring global settings fallback even without user preferences

debug: add verbose TTS logging and strict concurrency of 1 to isolate Google 500 errors

feat: adaptive TTS chunking for lower latency and better stream stability

feat: implement intelligent multi-sentence splitting to eliminate TTS streaming gaps

fix: resolve NameError for logger in TTS route

fix: resolve TTS streaming interruptions via atomic state management and Proxy timeout disabling

fix: resolve 422 validation errors for custom provider names and upgrade error reporting

chore: cleanup test scripts, secure deployment script, and implement Voice/TTS frontend refinements ...

- Removed all temporary root Python test scripts
- Secured remote_deploy.sh credentials using environment variables
- Added data/audio payloads directory to .gitignore
- Added automatic DB migration script (migrate.py) via uvicorn lifespan
- Applied major refactors to UI Voice Chat, Session handling, and unified React API configs
- Updated models and dependencies natively syncing with Nginx proxy features

feat: expose model info to users, multi-model provider cloning, cleaner profile UI ...

- Show model name under each provider button for all users (ProfilePage)
- Admin Settings: upgraded 'Register New Instance' panel with 4 fields:
  provider type, label suffix (with model-name hint), pre-set model
  dropdown, and 'Inherit API Key From' for same-type instance cloning
- Fix API key inheritance: use _clone_from marker instead of copying
  masked key; backend resolves real key from DB before saving
- Lock cloned-key instances: API key field is greyed out with lock icon
  and 'Inherited from <source>' display; Unlink button breaks the link
- Provider card header: show configured model name instead of
  'User Override / System Provided' labels
- ProfilePage: remove confusing 'Do Extra Work' override panel entirely;
  ServiceSelect is now a clean provider selector with no hidden admin UI
- SettingsPage: remove 'User Override' / 'System Provided' badge

Refactor STT model selection to dropdown, add YAML config import/export, and refine Voice/Coding Assistant UI

feat: session history sidebar with feature isolation and auto-titling ...

Backend changes:
- db/models.py: add feature_name column to Session model
- db/models.py: confirmed is_archived col for soft-delete support
- api/schemas.py: expose feature_name on SessionCreate and Session schemas
- core/services/session.py: accept feature_name in create_session()
- api/routes/sessions.py: pass feature_name on creation; add GET /sessions/
  (filtered by user + feature), DELETE /sessions/{id}, DELETE /sessions/
- core/services/rag.py: auto-title session from first user message;
  keep session.provider_name in sync with the model actually used
- core/services/workspace.py: same auto-title + provider_name sync
  on the WebSocket chat path

Frontend changes:
- services/apiService.js: createSession() now sends feature_name and
  provider_name; add getUserSessions(), deleteSession(), deleteAllSessions()
- services/websocket.js: getSessionId() accepts providerName and forwards
  it to createSession so the DB record reflects the real model
- hooks/useCodeAssistant.js: pass 'coding_assistant' namespace + 'deepseek'
  provider; expose handleSwitchSession + sessionId to page
- hooks/useVoiceChat.js: pass 'voice_chat' namespace + 'gemini' provider;
  expose handleSwitchSession + sessionId to page
- components/SessionSidebar.js: new collapsible sidebar (collapsed by default)
  showing history sessions per feature; click to switch, hover to see token
  usage tooltip, per-card delete and bulk 'Clear All'; shows smart relative
  date and provider badge per session
- components/SessionSidebar.css: theme-aware CSS (inherits Tailwind
  light/dark palette; no forced dark mode)
- pages/CodingAssistantPage.js: mount SessionSidebar with coding_assistant
- pages/VoiceChatPage.js: mount SessionSidebar with voice_chat

Tests:
- tests/core/services/test_session_service.py: new unit tests for
  SessionService covering feature_name namespace variants and DB rollback
- tests/api/routes/test_sessions.py: unit tests for new session mgmt routes
  (list by feature, single delete, bulk delete, token usage)
- integration_tests/test_sessions_api.py: end-to-end tests for feature
  isolation, single delete, 404 on missing session, and bulk delete
  confirming cross-feature sessions are unaffected

feat: Add new session UI, token counter, load history, and session isolation

add go-to-production code

enable OIDC

refactor general router

refactor the service container

use litellm underlying

add some logic in workspace

reactor ui project

introduce gcloud tts

add demo code & cors enabled & document the apis

introduce stt endpoint

refactor the routes api to be more modularized

add support of streaming TTS

add tts support from user end

refactor the integration test but tts is broken

refactor retriever

refactor the services to be plugable

add toggle on client side to enable or disable faiss db retriever

support switch model in between

support chat history

introduce the session into the frontend api

introduce the delete document funcs

further refactor

refactor db creation & centralize the config.py

refactor