Fixes#237
When web-ui sends a chat message, it includes conversation_history with only
user and assistant messages — tool calls and tool results are filtered out.
Meanwhile, it sends session_id in the request body but does NOT pass the
X-Hermes-Session-Id header.
Without the header, the gateway falls back to using the incomplete
conversation_history from the body, so the AI agent loses context about
previous tool calls, especially after idle periods.
Fix: Pass X-Hermes-Session-Id as a request header so the gateway loads
complete session history from the session DB (including tool messages).
Co-authored-by: 356252190-star <356252190-star@users.noreply.github.com>
* feat: restore group chat system with Socket.IO and SQLite persistence
- GroupChatServer: Socket.IO server with room management, message history, typing indicators
- SQLite storage for rooms, messages, and agent configuration
- AgentClients: manages AI agent connections via socket.io-client, forwards @mentions to Hermes gateway
- REST API: room CRUD, agent management, invite codes
- Agent auto-restoration on server restart
- Tests for all REST endpoints
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* docs: add context-engine design document for group chat compression
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: handle special-character session search
* fix: keep unicode dotted session search on quoted FTS path
* feat: add context engine and group chat frontend UI
- Context engine: three-zone compression (head/tail/summary) with LLM
summarization, incremental updates, TTL cache, and graceful degradation
- Frontend: group chat page with Socket.IO client, room sidebar, message
list, agent/member display, create/join-by-code modals
- Integration: wire context engine into agent-clients before /v1/runs
- Refactor ChatStorage to use global DB (getDb/ensureTable) with gc_ prefix
- Add i18n keys for group chat to all 8 locales
- Add sidebar nav entry and router for group chat page
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove leftover main branch code from merge conflict resolution
The `isNumericQuery`, `hasUnsafeChars`, and `runLikeContentSearch` functions
no longer exist — they were replaced by HEAD's `shouldUseLiteralContentSearch`
and `runLiteralContentSearch`. This dead code block caused a TypeScript
compile error after the merge.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: install missing socket.io dep and type ack params
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: enable WebSocket proxy and fix socket.io transport for group chat
- Add ws: true to Vite proxy config so WebSocket upgrade requests
are forwarded to the backend
- Allow both polling and websocket transports on server and client
(polling as fallback when WebSocket upgrade fails through proxy)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: separate socket.io path from REST routes for group chat
socket.io was mounted at /api/hermes/group-chat which intercepted all
REST requests to /api/hermes/group-chat/rooms etc, returning
"Transport unknown". Changed socket.io path to /api/hermes/group-chat/ws
to avoid conflicts.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: improve group chat UI, agent management, and socket.io reliability
- Redesign GroupChatPanel with Naive UI, stacked agent avatars, and popover management
- Match GroupChatInput style with single chat input, add IME composition handling
- Add agent add/remove per room with profile selection and duplicate prevention
- Use @multiavatar for SVG avatar generation with caching
- Decouple joinRoom from socket.io, use REST API for data loading
- Switch socket.io to default path with /group-chat namespace to avoid proxy conflicts
- Restore agent connections after server is listening
- Add getRoomDetail REST endpoint and duplicate agent prevention (409)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: server-side @mention routing with context compression status and queue
- Move @mention detection from agent socket listeners to server-side processMentions()
- Add per-room processing lock to block mention dispatch during compression
- Queue mentions during processing, drain only the latest when ready
- Emit context_status events (compressing/replying/ready) to room via Socket.IO
- Frontend displays compression status indicator above input
- Token-based compression trigger (100k threshold) with CJK-aware estimation
- Fix compressor type errors (countTokens parameter type)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: improve group chat profile handling and session sync
Refine group chat room/session behavior with per-room compression controls, sidebar updates, and better stale session cleanup so multi-profile group chat state stays consistent.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: group chat improvements — session lifecycle, typing recovery, mention highlighting
- Fix cross-profile session deletion with deferred delete queue
- Move saveSessionProfile to after gateway response confirmation
- Replace all console.log with logger in group-chat modules
- Add server-side typing/context_status state tracking for room rejoin
- Fix @ mention popup position to follow cursor
- Add @ mention highlighting (blue) in chat message content
- Fix mention regex to match all occurrences after HTML tags
- Enable esbuild minify and treeShaking
- Move @multiavatar/multiavatar to devDependencies
- Add i18n keys for group chat features
- Update tests for new functionality
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: bump version to 0.4.5 and move @multiavatar to devDependencies
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Zhicheng Han <zhicheng.han@mathematik.uni-goettingen.de>
* fix: context-length API returns 200K instead of actual model context
Two bugs cause the /api/hermes/sessions/context-length endpoint to
always return DEFAULT_CONTEXT_LENGTH (200K):
1. getModelContextLength ignores config.yaml model.context_length
The function only checks models_dev_cache.json (which doesn't
exist in default installations) and falls back to the hardcoded
200K default, completely ignoring the user's explicit
model.context_length setting in config.yaml.
2. getDefaultModel regex fails when api_key/base_url come before default
The regex /^model:\s*\n\s+default:\s*(.+)$/m assumes 'default' is
the first child key under 'model:', but when api_key or base_url
appear first in the YAML, the match fails. This causes
getModelContextLength to short-circuit to DEFAULT_CONTEXT_LENGTH
before even reaching the cache lookup.
Fix:
- Add getDefaultModelRobust() that extracts the entire model: block
first, then searches for default: within it
- Add getConfigContextLength() that reads model.context_length from
config.yaml as a fallback (matching hermes-agent priority)
- Update getModelContextLength() resolution order:
1. models_dev_cache.json (existing)
2. config.yaml model.context_length (new)
3. DEFAULT_CONTEXT_LENGTH (existing fallback)
Closes#169
* refactor: rewrite model-context to use js-yaml, add context_length to provider form
- Replace fragile regex-based YAML parsing with js-yaml for reliable config.yaml reads
- Fix context_length resolution priority: config.yaml override > custom_providers > models_dev_cache > 200K default
- Add context_length input field when adding custom providers in ProviderFormModal
- Backend: persist context_length to custom_providers models.<model>.context_length in config.yaml
- Add i18n keys (contextLength, contextLengthPlaceholder) to all 8 locales
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: use NInputNumber instead of NInput type=number for context_length
NInput does not support type="number" in Naive UI.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: devilardis <53129661@qq.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Display persistent warning bar when Node.js version < 23
- Fix provider model fetching to support non-v1 API versions (e.g. /v4)
- Add v0.4.4 changelog entries to frontend
- Bump version to 0.4.4
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add file browser and file download with multi-backend support
Adds a built-in File Browser page and a File Download system to Hermes
Web UI, enabling users to browse, edit, preview, upload, and download
files from the workspace directly from the web dashboard.
File Browser (/hermes/files):
- New view FilesView.vue plus components under components/hermes/files/
(FileTree, FileList, FileBreadcrumb, FileToolbar, FileContextMenu,
FileEditor, FilePreview, FileRenameModal, FileUploadModal)
- New Pinia store stores/hermes/files.ts for directory tree, selection,
and editing state
- New API module api/hermes/files.ts
- New server routes routes/hermes/files.ts with CRUD, rename, upload,
and directory listing
- New service services/hermes/file-provider.ts with a pluggable
provider architecture (local filesystem + multi-terminal backends)
File Download:
- New server route routes/hermes/download.ts and client API
api/hermes/download.ts
- Integration in chat messages (MessageItem.vue, MarkdownRenderer.vue)
to surface downloadable file references
Packaging:
- package.json: add a prepare script so the package can be installed
directly from a git URL with dist/ built automatically
i18n: add files/download translations to en.ts and zh.ts.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix: use clipboard fallback for non-secure HTTP contexts
navigator.clipboard is undefined on HTTP intranet deployments (only
available in secure contexts). The previous synchronous calls threw
silently and the success toast still fired, making 'copy' actions
appear broken.
- Add packages/client/src/utils/clipboard.ts with execCommand fallback
via a hidden textarea
- Use the helper in FileContextMenu (copy file path), CodexLoginModal
(copy user code), NousLoginModal (copy user code), ChatPanel (copy
session id)
- Each call now awaits the result and shows success/failure based on
the actual outcome
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Add StepFun provider (API key auth, STEPFUN_API_KEY)
- Add Nous Portal provider with full OAuth device code flow
(device code request → poll for token → mint agent key → save to auth.json)
- Add NousLoginModal component for OAuth UI (user code display + verification link)
- Update ProviderFormModal to handle Nous OAuth flow (hide API key fields)
- Add nous-auth backend controller and routes
- Update PROVIDER_ENV_MAP with stepfun and nous entries
- Add i18n translations for Nous OAuth in all 8 locales
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: specify TS_NODE_PROJECT for dev:server script
ts-node/register resolves tsconfig from the entry file upward,
finding the root solution-style tsconfig.json (no compilerOptions).
This causes target to default to ES3, breaking MapIterator spread
syntax (TS2802). Set TS_NODE_PROJECT env var to point to the server
tsconfig which targets ES2024.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add token usage tracking, context display, and dynamic context length
- Intercept SSE proxy to capture run.completed events and persist token
usage (input_tokens, output_tokens) per session to SQLite/JSON store
- Display context usage bar in ChatInput showing used/total/remaining tokens
- Resolve actual context length from Hermes models_dev_cache.json based
on the active profile's default model (fallback 200K), with 5min in-memory cache
- Move sessions-db.ts to db/hermes/ for unified database layer
- Add usage store with SQLite + JSON fallback (auto-migration via ensureTable)
- Fix proxy SSE path regex to match rewritten upstream path
- Fix route ordering: /sessions/usage before /sessions/:id to avoid 404
- Fetch per-session usage on session enter instead of batch
- Add unit tests for usage-store, db index, and proxy SSE interception
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add single-page live session monitor and chat pinning
* fix: restore full test green after main merge
* fix: use Array.from instead of Set spread for ts-node compatibility
[...new Set()] requires downlevelIteration which isn't enabled in
ts-node dev mode, causing sonic-boom crash on startup.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: ekko <fqsy1416@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Use `last_active` from SQLite (max message timestamp) for accurate
sorting, with fallback chain: last_active → ended_at → started_at.
CLI mode lacks last_active so falls back to ended_at.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Profile-aware proxy: inject API key from profile-specific .env, route requests via X-Hermes-Profile header
- Remove auth.json dependency: built-in providers use .env, custom providers use config.yaml
- Add allProviders field to available-models response with all hardcoded provider catalogs
- Add Models tab in Settings for editing provider API keys (built-in → .env, custom → config.yaml)
- Add PUT /api/config/providers/:poolKey for updating provider credentials
- ProviderFormModal uses backend allProviders for preset dropdown
- Gateway log format support: parse both agent and gateway log formats
- Add webui server.log to log viewer with log rotation at 3MB
- Fix provider delete loading state and OAuth provider cleanup
- Setup script: require Node.js 23+, auto-upgrade if version too low
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When multiple providers share the same model name, the selector now
uses both model ID and provider as the unique identifier instead of
model name alone. Backend returns default_provider alongside default
model, and model switching sends provider to the config.
Fixes#52
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add GatewayManager for multi-profile gateway lifecycle management
- Auto-detect running gateways on startup via PID + health check
- Port conflict detection: check managed gateways, allocated ports, and
system-level port availability (TCP bind test)
- Two-phase startup: sequential port resolution, parallel process launch
- Use `gateway start/restart` on normal systems, `gateway run --replace`
on WSL/Docker
- Wait for health check before returning start/stop responses
- Add Gateways page with card-based layout showing profile status
- Reorganize sidebar navigation into collapsible groups
- Hide API server settings (now auto-managed by GatewayManager)
- Profile switch reloads page; Ctrl+C no longer stops gateways
- Remove redundant ensureApiServerConfig from index.ts and profiles.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add OpenAI Codex Device Code Flow login (backend polling + frontend modal)
- Codex provider integrated into preset dropdown (hides URL/API key fields)
- Sync provider model catalogs with Hermes system
- Fix channel config not displaying on first visit (wait for data load)
- Fix sidebar model list not refreshing after adding provider
- Add autocomplete="off" to API key input to prevent browser autofill
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix#25: job update sends schedule as plain string but upstream expects
{ kind, expr, display } object, causing "'str' object has no attribute 'get'"
- Move hermes-cli.ts, hermes.ts, hermes-profile.ts into services/hermes/
for multi-agent namespacing consistency
- Fix ts-node Set spread compatibility in filesystem.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Change profile import from server path input to browser file upload (multipart)
- Fix startup script to wait for health check before opening browser
- Add overflow scroll with hidden scrollbar to sidebar nav
- Graceful degradation when node-pty fails to load (WSL compatibility)
- Remove rename button from profile cards
- Restrict profile name input to English letters, numbers, hyphens
- Use raw.githubusercontent.com URLs in README setup script
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add hermes-profile.ts for dynamic profile path resolution (all backend
routes now read from active profile directory instead of hardcoded ~/.hermes/)
- Add profile switcher dropdown in sidebar, reload page on switch
- Sync PROVIDER_PRESETS with Hermes CLI (fix keys: kimi-coding→kimi-for-coding,
kilocode→kilo, ai-gateway→vercel, opencode-zen→opencode; remove moonshot)
- Sync PROVIDER_ENV_MAP with Hermes models.dev + overlays (correct env var names)
- Add gateway restart after adding model provider
- Don't write GLM_BASE_URL/KIMI_BASE_URL for zai/kimi (let Hermes auto-detect)
- Write API keys to .env and credential_pool for all providers
- Built-in providers skip custom_providers in config.yaml
- Add debounce + per-field loading state for channel settings inputs
- Run hermes setup --reset for profiles without config.yaml
- Create empty .env for new profiles (not copied from default)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add frontend API layer, Pinia store, and 5 components (ProfileCard, ProfilesPanel, ProfileCreateModal, ProfileRenameModal, ProfileImportModal)
- Add ProfilesView page with card grid layout and expandable details
- Modify export endpoint to stream file as browser download instead of returning server path
- Add sidebar nav entry, router route, and i18n translations (en/zh)
- Support create, rename, delete, switch (with gateway restart), export, and import profiles
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ww