Allow users to configure what percentage of older messages to compact,
keeping the most recent portion intact. Default ratio is 80%, meaning
the oldest 80% of uncompacted messages are summarized while the newest
20% remain as-is for full-fidelity context.
These two fields controlled history context window (time-based) and token-based
trimming. They are no longer needed — the resolver now always uses the hardcoded
24-hour default and skips token-based history trimming.
When input tokens exceed a configurable threshold after a conversation round,
the system asynchronously compacts older messages into a summary. Cascading
compactions reference prior summaries via <prior_context> tags to maintain
conversational continuity without duplicating content.
- Add bot_history_message_compacts table and compact_id on messages
- Add compaction_enabled, compaction_threshold, compaction_model_id to bots
- Implement compaction service (internal/compaction) with LLM summarization
- Integrate into conversation flow: replace compacted messages with summaries
wrapped in <summary> tags during context loading
- Add REST API endpoints (GET/DELETE /bots/:bot_id/compaction/logs)
- Add frontend Compaction tab with settings and log viewer
- Wire compaction service into both dev (cmd/agent) and prod (cmd/memoh) entry points
- Update test mocks to include new GetBotByID columns
* refactor: introduce multi-session chat support (#session)
Replace the single-context-per-bot model with multiple chat sessions.
Database:
- Add bot_sessions table (route_id, channel_type, title, metadata, soft delete)
- Migrate bot_history_messages from (route_id, channel_type) to session_id
- Add active_session_id to bot_channel_routes
- Migration 0036 handles data migration from existing messages
Backend:
- New internal/session service for session CRUD
- Update message service/types to use session_id instead of route_id
- Update conversation flow (resolver, history, store) for session context
- Channel inbound auto-creates/retrieves active session via SessionEnsurer
- New REST endpoints: /bots/:bot_id/sessions (CRUD)
- WebSocket and message handlers accept optional session_id
- Wire session service into FX dependency graph (agent + memoh)
Frontend:
- Refactor chat store: sessions replaces chats, sessionId replaces chatId
- Session-aware message loading, sending, and pagination
- WebSocket sends include session_id
- New session sidebar component with select/delete
- Chat area header shows active session title + new session button
- API layer updated: fetchSessions, createSession, deleteSession
- i18n strings for session management (en + zh)
SDK:
- Regenerated TypeScript SDK and Swagger docs with session endpoints
* fix: update tests for session refactoring (RouteID → SessionID)
Remove references to removed RouteID and Platform fields from
PersistInput/Message in channel_test.go and service_integration_test.go.
* fix: restore accidentally deleted SDK files and guard migration 0032
- Restore packages/sdk/src/container-stream.ts and extra/index.ts that
were accidentally removed during SDK regeneration
- Wrap migration 0032 route_id index creation in a column existence check
to avoid failure on fresh databases where 0001_init.up.sql no longer
has route_id
* fix: guard migration 0036 data steps for fresh databases
Wrap steps 3-7 (which reference route_id/channel_type on
bot_history_messages) in a column existence check so the migration
is safe on fresh databases where 0001_init.up.sql already reflects
the final schema without those columns.
* feat: add title model setting and auto-generate session titles on user input
- Add title_model_id to bots table (migration 0037) and bot settings API
- Implement async title generation triggered at user message time (not after
assistant response) for faster title availability
- Publish session_title_updated events via SSE event hub for real-time
frontend updates without page refresh
- Fix SSE message event parsing: use direct JSON.parse instead of
normalizeStreamEvent which silently dropped non-chat-stream event types
- Add title model selector in bot settings UI with i18n support
* fix: session-scoped message filtering and URL-based chat routing
- Filter realtime SSE messages by session_id to prevent cross-session
message leakage after page refresh
- Add /chat/:sessionId? route with bidirectional URL ↔ store sync
- Visiting /chat shows a clean state with no bot or session pre-selected
- Visiting /chat/:sessionId loads the specific session directly
- Session switches from sidebar automatically update the URL
- Fix stale RouteID field in dedupe test (removed during session refactor)
* fix: skip cross-channel stream events to prevent session leakage
The bot-level web stream pushes events from all channels (Telegram,
Discord, etc.) without session_id context. Previously these were
rendered inline in the current chat view regardless of session.
Now cross-channel events are ignored in handleLocalStreamEvent;
persisted messages arrive via the SSE message events stream with
proper session_id filtering through appendRealtimeMessage.
* feat: show IM avatars and platform badges on session sidebar
- Add sender_avatar_url to route metadata from identity resolution
- Resolve group avatar and handle via directory adapter for group chats
- JOIN bot_channel_routes in ListSessionsByBot to return route metadata
- Display avatar with ChannelBadge on IM session items (group avatar
for groups, sender avatar for private chats)
- Show @groupname or @username as session sub-label
* fix: clean up RunConfig unused fields, fix skill system and copy bug
- Remove unused RunConfig fields: Tools, Channels, CurrentChannel,
ActiveContextTime
- Remove unused SessionContext fields: DisplayName, ConversationType
- Fix EnabledSkillNames copy bug: make([]string, 0, n) + copy copies
zero elements; changed to make([]string, n)
- Fix prepareRunConfig dead code: remove no-op loop over
CurrentPlatform runes; compute supportsImageInput from model's
InputModalities
- Fix EnabledSkills always nil in system prompt: resolve enabled skill
entries from EnabledSkillNames + Skills
- Fix use_skill tool returning empty response: now returns full skill
content (description + instructions) so LLM gets it in the same turn
- Skip use_skill tool registration when no skills are available
- Conditionally render Skills section in system prompt (hidden when
no skills exist)
* feat: add session type field and bind sessions to heartbeat/schedule executions
- Add `type` column to `bot_sessions` (chat | heartbeat | schedule)
- Add `session_id` to `bot_heartbeat_logs` for per-execution session tracking
- Create `schedule_logs` table binding schedule_id + session_id
- Heartbeat and schedule runs now create independent sessions and persist
agent messages via storeRound, enabling full conversation replay
- Add schedule logs API endpoints (list by bot, list by schedule, delete)
- Update Triggerer interfaces to return TriggerResult with status/usage/model
* refactor: modular system prompts per session type (chat/heartbeat/schedule)
Split the monolithic system.md into three type-specific system prompts
with shared fragments via {{include:_xxx}} syntax, so each session type
gets a focused prompt without irrelevant instructions.
* fix: prevent message duplication after task completion
message_created events from Persist() had an empty platform field because
toMessageFromCreate() didn't extract it from the session. This caused
appendRealtimeMessage to fail the platform === 'web' guard, and
hasMessageWithId to fail because local IDs differ from server UUIDs,
resulting in all messages being appended as duplicates.
- Extract platform from metadata in toMessageFromCreate so published events
carry the correct value
- Pass channel_type: 'web' when creating sessions from the web frontend so
List queries return the correct platform via the session JOIN
* fix: use per-message usage from SDK instead of misaligned step-level usages
Previously, token usage was stored via a separate per-step usages array
that didn't align with messages (off-by-one from prepending user message,
step count != message count). This caused:
- User messages incorrectly receiving usage data
- Usage values shifted across messages in multi-step rounds
- Last assistant message getting the accumulated total instead of its own step usage
- InputTokenDetails/OutputTokenDetails lost during manual accumulation
Now each sdk.Message carries its own per-step Usage (set by the SDK in
buildStepMessages), which is extracted in sdkMessagesToModelMessages and
stored directly via ModelMessage.Usage. The storeRound/storeMessages path
no longer needs external usage/usages parameters.
Also fixes the totalUsage accumulation in runStream to include all detail
fields (InputTokenDetails, OutputTokenDetails).
* feat: add /new slash command to create a new active session from IM channels
Users in Telegram/Discord/Feishu can now send /new to start a fresh
conversation, resetting the session context for the current chat thread.
The command resolves the channel route, creates a new session, sets it as
the active session on the route, and replies with a confirmation message.
* feat: distinguish heartbeat and schedule sessions with dedicated icons in sidebar
Heartbeat sessions show a heart-pulse icon (rose), schedule sessions
show a clock icon (amber), and both display a type label beneath the
session title.
* refactor: remove enabledSkills system prompt injection, keep sorted skill listing
use_skill now returns skill content directly as tool output, so there is
no need to inject enabled skill body text into the system prompt. Remove
the entire enabledSkills tracking chain (RunConfig.EnabledSkillNames,
StreamEvent.Skills, GenerateResult.Skills, ChatRequest/Response.Skills,
enableSkill closures in runStream/runGenerate, prepareRunConfig matching).
Keep a lightweight skills listing (name + description only) in the system
prompt so the model knows which skills are available. Sort entries by name
to guarantee deterministic ordering and maximize KV cache reuse.
* refactor: remove inbox system, persist passive messages directly to history
Replace the bot_inbox table and service with direct writes to
bot_history_messages for group conversations where the bot is not
@mentioned. Trigger-path messages continue to be persisted after the
agent responds (unchanged).
- Drop bot_inbox table and max_inbox_items column (migration 0039)
- Delete internal/inbox/, handlers/inbox.go, command/inbox.go,
agent/tools/inbox.go and the MCP message provider
- Add persistPassiveMessage() in channel inbound to write user
messages into the active session immediately
- Rewrite ListObservedConversationsByChannelIdentity to query
bot_history_messages + bot_sessions instead of bot_inbox
- Extract shared send/react logic into internal/messaging/executor.go;
agent/tools/message.go is now a thin SDK adapter
- Clean up all inbox references from agent prompts, flow resolver,
email trigger, settings, commands, DI wiring, and frontend
- Regenerate sqlc, swagger, and SDK
* feat: add list_sessions and search_messages agent tools
Provide agents with the ability to query session metadata and search
message history across all sessions. search_messages supports filtering
by time range, keyword (JSONB-aware ILIKE), session, contact, and role,
with a default 7-day lookback when no start_time is given.
* feat: inject last_heartbeat time and improve heartbeat search guidance
Query the previous heartbeat's started_at timestamp and pass it through
TriggerPayload into the heartbeat prompt template. Update system prompt
and HEARTBEAT.md checklist to guide agents to use search_messages with
start_time=last_heartbeat for efficient cross-session message review.
* fix: pass BridgeProvider to FSClient and store full heartbeat prompt
FSClient was always created with nil provider, causing all container
file reads (IDENTITY.md, SOUL.md, MEMORY.md, HEARTBEAT.md, etc.) to
silently return empty strings. Expose Agent.BridgeProvider() and wire
it into Resolver. Also fix heartbeat trigger to store the full prompt
template as the user message instead of the literal "heartbeat" string.
* feat: add line numbers to container file read output
Move line-number formatting from the bridge gRPC server to the agent
tool layer so that the raw content stored and transmitted via gRPC
remains clean, while the read_file tool output includes numbered lines
for easier reference by the agent.
* chore(deps): update twilight-ai to v0.3.2
* fix: lint, test
* feat(container): add explicit data workflows and snapshot rollback
Make container upgrades and recreation data-safe by adding explicit preserve, export, import, restore, and rollback flows across the backend, SDK, and web UI.
* fix(container): resolve go lint issues
Fix formatting and lint violations introduced by the container data workflow changes so the Go CI lint job passes cleanly.
Replace the host bind-mount + containerd exec approach with a per-bot
in-container gRPC server (ContainerService, port 9090). All file I/O,
exec, and MCP stdio sessions now go through gRPC instead of running
shell commands or reading host-mounted directories.
Architecture changes:
- cmd/mcp: rewritten as a gRPC server (ContainerService) with full
file and exec API (ReadFile, WriteFile, ListDir, ReadRaw, WriteRaw,
Exec, Stat, Mkdir, Rename, DeleteFile)
- internal/mcp/mcpcontainer: protobuf definitions and generated stubs
- internal/mcp/mcpclient: gRPC client wrapper with connection pool
(Pool) and Provider interface for dependency injection
- mcp.Manager: add per-bot IP cache, gRPC connection pool, and
SetContainerIP/MCPClient methods; remove DataDir/Exec helpers
- containerd.Service: remove ExecTask/ExecTaskStreaming; network setup
now returns NetworkResult{IP} for pool routing
- internal/fs/service.go: deleted (replaced by mcpclient)
- handlers/fs.go: deleted; MCP stdio session logic moved to mcp_stdio.go
- container provider Executor: all tools (read/write/list/edit/exec)
now call gRPC client instead of running shell via exec
- storefs, containerfs, media, skills, memory: all I/O ported to
mcpclient.Provider
Database:
- migration 0022: drop host_path column from containers table
One-time data migration:
- migrateBindMountData: on first Start() after upgrade, copies old
bind-mount data into the container via gRPC, then renames src dir
to prevent re-migration; runs in background goroutine
Bug fixes:
- mcp_stdio: callRaw now returns full JSON-RPC envelope
{"jsonrpc","id","result"|"error"} matching protocol spec;
explicit "initialize" call now advances session init state to
prevent duplicate handshake on next non-initialize call
- mcpclient Pool: properly evict stale gRPC connection after snapshot
replace (container process recreated); use SetContainerIP instead
of direct map write so IP changes always evict pool entry
- migrateBindMountData: walkErr on directories now counted as failure
so partially-walked trees don't get incorrectly marked as migrated
- cmd/mcp/Dockerfile: removed dead file (docker/Dockerfile.mcp is the
canonical production build)
Tests:
- provider_test.go: restored with bufconn in-process gRPC mock
(fakeContainerService + staticProvider), 14 cases covering all 5
tools plus edge cases
- mcp_session_test.go: new, covers JSON-RPC envelope, init state
machine, pending cleanup on cancel/close, readLoop cancel
- storefs/service_test.go: restored (pure function roundtrip tests)
- Refactor RuntimeChecker interface: CheckKeys() + RunCheck() for
individual check dispatch instead of batch-all
- Add GET /bots/:id/checks/keys to list all available check keys
- Add GET /bots/:id/checks/run/:key to evaluate a single check
- MCP ConnectionChecker probes each active connection independently
via tools/list with 8s timeout
- Keep container checks (init/record/task/data_path) as fast builtins
- Graceful network setup failure in containerd handler (log warning
instead of killing task) for containerd-in-docker compatibility
- Add RuntimeChecker interface for extensible bot health checks
- Implement MCP ConnectionChecker: probes active connections via tools/list
- Show MCP server status (healthy/unreachable/no tools) in bot checks
- Register checker in main.go alongside container lifecycle
- Rename chat module to conversation with flow-based architecture
- Move channelidentities into channel/identities subpackage
- Add channel/route for routing logic
- Add message service with event hub
- Add MCP providers: container, directory, schedule
- Refactor Feishu/Telegram adapters with directory and stream support
- Add platform management page and channel badges in web UI
- Update database schema for conversations, messages and channel routes
- Add @memoh/shared package for cross-package type definitions
Align channel identity and bind flow across backend and app-facing layers, including generated swagger artifacts and package lock updates while excluding docs content changes.
- Add SetupBotContainer to ContainerLifecycle interface so containers
are automatically created when a bot is created, matching the existing
cleanup-on-delete behavior.
- Refactor schedule tools to use bot-scoped API paths and pass identity
context for proper authorization.
- Introduce dedicated trigger-schedule endpoint in chat resolver with
explicit schedule payload instead of reusing the generic chat path.
- Generate short-lived JWT tokens for schedule trigger callbacks with
resolved bot owner identity.
- Validate required parameters in NewLLMClient and NewOpenAIEmbedder
constructors, returning errors instead of falling back to defaults.
- Add unit tests for schedule token generation and chat resolver.
- Refactor channel manager with support for Sender/Receiver interfaces and hot-swappable adapters.
- Implement identity routing and pre-authentication logic for inbound messages.
- Update database schema to support bot pre-auth keys and extended channel session metadata.
- Add Telegram and Feishu channel configuration and adapter enhancements.
- Update Swagger documentation and internal handlers for channel management.
Co-authored-by: Cursor <cursoragent@cursor.com>
Major changes:
1. Core Architecture: Decoupled Bots from Users. Bots now have independent lifecycles, member management (bot_members), and dedicated configurations.
2. Channel Gateway:
- Implemented a unified Channel Manager supporting Feishu, Telegram, and Local (Web/CLI) adapters.
- Added message processing pipeline to normalize interactions across different platforms.
- Introduced a Contact system for identity binding and guest access policies.
3. Database & Tooling:
- Consolidated all migrations into 0001_init with updated schema for bots, channels, and contacts.
- Optimized sqlc.yaml to automatically track the migrations directory.
4. Agent Enhancements:
- Introduced ToolContext to provide Agents with platform-aware execution capabilities (e.g., messaging, contact lookups).
- Added tool logging and fallback mechanisms for toolChoice execution.
5. UI & Docs: Updated frontend stores, UI components, and Swagger documentation to align with the new Bot-centric model.
Acbox