* refactor: introduce DCP pipeline layer for unified context assembly
Introduce a Deterministic Context Pipeline (DCP) inspired by Cahciua,
providing event-driven context assembly for LLM conversations.
- Add `internal/pipeline/` package with Canonical Event types, Projection
(reduce), Rendering (XML RC), Pipeline manager, and EventStore persistence
- Change user message format from YAML front-matter to XML `<message>` tags
with self-contained attributes (sender, channel, conversation, type)
- Merge CLI/Web dual API into single `/local/` endpoint, remove CLI handler
- Add `bot_session_events` table for event persistence and cold-start replay
- Add `discuss` session type (reserved for future Cahciua-style mode)
- Wire pipeline into HandleInbound: adapt → persist → push on every message
- Lazy cold-start replay: load events from DB on first session access
* feat: implement discuss mode with reactive driver and probe gate
Add discuss session mode where the bot autonomously decides when to speak
in group chats via tool-gated output (send tool only, no direct text reply).
- Add discuss driver (per-session goroutine, RC watch, step loop via
agent.Generate, TR persistence, late-binding prompt with mention hints)
- Add system_discuss.md prompt template ("text = inner monologue, send = speak")
- Add context composition (MergeContext, ComposeContext, TrimContext) for
RC + assistant/tool message interleaving by timestamp
- Add probe gate: when discuss_probe_model_id is set, cheap model pre-filters
group messages; no tool calls = silence, tool calls = activate primary
- Add /new [chat|discuss] command: explicit mode selection, defaults to
discuss in groups, chat in DMs, chat-only for WebUI
- Add ResolveRunConfig on flow.Resolver for discuss driver to reuse
model/tools/system-prompt resolution without reimplementing
- Fix send tool for discuss mode: same-conversation sends now go through
SendDirect (channel adapter) instead of the local emitter shortcut
- Add target attribute to XML message format (reply_target for routing)
- Add discuss_probe_model_id to bots table settings
- Remove pipeline compaction (SetCompactCursor) — reuse existing compaction.Service
- Persist full SDK messages (including tool calls) in discuss mode
* refactor: unify DCP event layer, fix persistence and local channel
- Fix bot_session_events dedup index to include event_kind so that
message + edit events for the same external_message_id coexist.
- Change CreateSessionEvent from :one to :exec so ON CONFLICT DO NOTHING
does not produce spurious errors on duplicate delivery.
- Move ACL evaluation before event ingest; denied messages no longer
enter bot_session_events or the in-memory pipeline.
- Let chat mode consume RenderedContext from the DCP pipeline when
available, sharing the same event-driven context assembly as discuss.
- Collapse local WebSocket handler to route through HandleInbound
instead of directly calling StreamChatWS, eliminating the dual
business entry point.
- Extract buildBaseRunConfig shared builder so resolve() and
ResolveRunConfig() no longer duplicate model/credentials/skills setup.
- Add StoreRound to RunConfigResolver interface so discuss driver
persists assistant output with full metadata, usage, and memory
extraction (same quality as chat mode).
- Fix discuss driver context: use context.Background() instead of the
short-lived HTTP request context that was getting cancelled.
- Fix model ID passed to StoreRound: return database UUID from
ResolveRunConfig instead of SDK model name.
- Remove dead CLIAdapter/CLIType and update legacy web/cli references
in tests and comments.
* fix: stop idle discuss goroutines after 10min timeout
Discuss session goroutines were never cleaned up when a session became
inactive (e.g. after /new). Add a 10-minute idle timer that auto-exits
the goroutine and removes it from the sessions map when no new RC
arrives.
* refactor: pipeline details — event types, structured reply, display content
- Remove [User sent N attachments] placeholder text from buildInboundQuery;
attachment info is now expressed via pipeline <attachment> tags.
- Unify in-reply-to as structured ReplyRef (Sender/Preview fields) across
Telegram, Discord, Feishu, and Matrix adapters instead of prepending
[Reply to ...] text into the message body. Remove now-unused
buildTelegramQuotedText, buildDiscordQuotedText, buildMatrixQuotedText.
- Make AdaptInbound return CanonicalEvent interface and dispatch to
adaptMessage/adaptEdit/adaptService based on metadata["event_type"].
- Add event_id column to bot_history_messages (migration 0059) so user
messages can reference their canonical pipeline event.
- PersistEvent now returns the event UUID; HandleInbound passes it through
to both persistPassiveMessage and ChatRequest.EventID for storeRound.
- Add FillDisplayContent to message service: extracts plain text from
event_data for clean frontend display.
- Frontend extractMessageText prefers display_content when available,
falling back to legacy strip logic for old messages.
- Fix: always generate headerifiedQuery for storage even when usePipeline
is true, so user messages are persisted via storeRound in chat mode.
* fix: use json.Marshal for pipeline context content serialization
The manual string escaping in buildMessagesFromPipeline only handled
double quotes but not newlines, backslashes, and other JSON special
characters, producing invalid json.RawMessage values. The LLM then
received empty/malformed context and complained about having no history.
* fix: restore WebSocket handler to use StreamChatWS directly
The previous refactoring replaced the WS handler with HandleInbound +
RouteHub subscription, which broke streaming because RouteHub events
use a different format (channel.StreamEvent) than what the frontend
expects (flow.WSStreamEvent with text_delta, tool_call_start, etc.).
Restore the original direct StreamChatWS call path so WebUI streaming
works again. The WS handler now matches the pre-refactoring behavior
while all other changes (pipeline, ACL, event types, etc.) are kept.
* feat: store display_text directly in bot_history_messages
Instead of computing display content at API response time by querying
bot_session_events via event_id, store the raw user text in a dedicated
display_text column at write time. This works for all paths including
the WebSocket handler which does not go through the pipeline/event layer.
- Migration 0060: add display_text TEXT column
- PersistInput gains DisplayText; filled from trimmedText (passive) and
req.Query (storeRound)
- toMessageFields reads display_text into DisplayContent
- Remove FillDisplayContent runtime query and ListSessionEventsByEventID
- Frontend already prefers display_content when available (no change)
* fix: display_text should contain raw user text, not XML-wrapped query
req.Query gets overwritten to headerifiedQuery (with XML <message> tags)
before storeRound runs. Add RawQuery field to ChatRequest to preserve
the original user text, and use it for display_text in storeMessages.
* fix(web): show discuss sessions
* refactor: introduce DCP pipeline layer for unified context assembly
Introduce a Deterministic Context Pipeline (DCP) inspired by Cahciua,
providing event-driven context assembly for LLM conversations.
- Add `internal/pipeline/` package with Canonical Event types, Projection
(reduce), Rendering (XML RC), Pipeline manager, and EventStore persistence
- Change user message format from YAML front-matter to XML `<message>` tags
with self-contained attributes (sender, channel, conversation, type)
- Merge CLI/Web dual API into single `/local/` endpoint, remove CLI handler
- Add `bot_session_events` table for event persistence and cold-start replay
- Add `discuss` session type (reserved for future Cahciua-style mode)
- Wire pipeline into HandleInbound: adapt → persist → push on every message
- Lazy cold-start replay: load events from DB on first session access
* feat: implement discuss mode with reactive driver and probe gate
Add discuss session mode where the bot autonomously decides when to speak
in group chats via tool-gated output (send tool only, no direct text reply).
- Add discuss driver (per-session goroutine, RC watch, step loop via
agent.Generate, TR persistence, late-binding prompt with mention hints)
- Add system_discuss.md prompt template ("text = inner monologue, send = speak")
- Add context composition (MergeContext, ComposeContext, TrimContext) for
RC + assistant/tool message interleaving by timestamp
- Add probe gate: when discuss_probe_model_id is set, cheap model pre-filters
group messages; no tool calls = silence, tool calls = activate primary
- Add /new [chat|discuss] command: explicit mode selection, defaults to
discuss in groups, chat in DMs, chat-only for WebUI
- Add ResolveRunConfig on flow.Resolver for discuss driver to reuse
model/tools/system-prompt resolution without reimplementing
- Fix send tool for discuss mode: same-conversation sends now go through
SendDirect (channel adapter) instead of the local emitter shortcut
- Add target attribute to XML message format (reply_target for routing)
- Add discuss_probe_model_id to bots table settings
- Remove pipeline compaction (SetCompactCursor) — reuse existing compaction.Service
- Persist full SDK messages (including tool calls) in discuss mode
* refactor: unify DCP event layer, fix persistence and local channel
- Fix bot_session_events dedup index to include event_kind so that
message + edit events for the same external_message_id coexist.
- Change CreateSessionEvent from :one to :exec so ON CONFLICT DO NOTHING
does not produce spurious errors on duplicate delivery.
- Move ACL evaluation before event ingest; denied messages no longer
enter bot_session_events or the in-memory pipeline.
- Let chat mode consume RenderedContext from the DCP pipeline when
available, sharing the same event-driven context assembly as discuss.
- Collapse local WebSocket handler to route through HandleInbound
instead of directly calling StreamChatWS, eliminating the dual
business entry point.
- Extract buildBaseRunConfig shared builder so resolve() and
ResolveRunConfig() no longer duplicate model/credentials/skills setup.
- Add StoreRound to RunConfigResolver interface so discuss driver
persists assistant output with full metadata, usage, and memory
extraction (same quality as chat mode).
- Fix discuss driver context: use context.Background() instead of the
short-lived HTTP request context that was getting cancelled.
- Fix model ID passed to StoreRound: return database UUID from
ResolveRunConfig instead of SDK model name.
- Remove dead CLIAdapter/CLIType and update legacy web/cli references
in tests and comments.
* fix: stop idle discuss goroutines after 10min timeout
Discuss session goroutines were never cleaned up when a session became
inactive (e.g. after /new). Add a 10-minute idle timer that auto-exits
the goroutine and removes it from the sessions map when no new RC
arrives.
* refactor: pipeline details — event types, structured reply, display content
- Remove [User sent N attachments] placeholder text from buildInboundQuery;
attachment info is now expressed via pipeline <attachment> tags.
- Unify in-reply-to as structured ReplyRef (Sender/Preview fields) across
Telegram, Discord, Feishu, and Matrix adapters instead of prepending
[Reply to ...] text into the message body. Remove now-unused
buildTelegramQuotedText, buildDiscordQuotedText, buildMatrixQuotedText.
- Make AdaptInbound return CanonicalEvent interface and dispatch to
adaptMessage/adaptEdit/adaptService based on metadata["event_type"].
- Add event_id column to bot_history_messages (migration 0059) so user
messages can reference their canonical pipeline event.
- PersistEvent now returns the event UUID; HandleInbound passes it through
to both persistPassiveMessage and ChatRequest.EventID for storeRound.
- Add FillDisplayContent to message service: extracts plain text from
event_data for clean frontend display.
- Frontend extractMessageText prefers display_content when available,
falling back to legacy strip logic for old messages.
- Fix: always generate headerifiedQuery for storage even when usePipeline
is true, so user messages are persisted via storeRound in chat mode.
* fix: use json.Marshal for pipeline context content serialization
The manual string escaping in buildMessagesFromPipeline only handled
double quotes but not newlines, backslashes, and other JSON special
characters, producing invalid json.RawMessage values. The LLM then
received empty/malformed context and complained about having no history.
* fix: restore WebSocket handler to use StreamChatWS directly
The previous refactoring replaced the WS handler with HandleInbound +
RouteHub subscription, which broke streaming because RouteHub events
use a different format (channel.StreamEvent) than what the frontend
expects (flow.WSStreamEvent with text_delta, tool_call_start, etc.).
Restore the original direct StreamChatWS call path so WebUI streaming
works again. The WS handler now matches the pre-refactoring behavior
while all other changes (pipeline, ACL, event types, etc.) are kept.
* feat: store display_text directly in bot_history_messages
Instead of computing display content at API response time by querying
bot_session_events via event_id, store the raw user text in a dedicated
display_text column at write time. This works for all paths including
the WebSocket handler which does not go through the pipeline/event layer.
- Migration 0060: add display_text TEXT column
- PersistInput gains DisplayText; filled from trimmedText (passive) and
req.Query (storeRound)
- toMessageFields reads display_text into DisplayContent
- Remove FillDisplayContent runtime query and ListSessionEventsByEventID
- Frontend already prefers display_content when available (no change)
* fix: display_text should contain raw user text, not XML-wrapped query
req.Query gets overwritten to headerifiedQuery (with XML <message> tags)
before storeRound runs. Add RawQuery field to ChatRequest to preserve
the original user text, and use it for display_text in storeMessages.
* fix(web): show discuss sessions
* chore(feishu): change discuss output to stream card
* fix(channel): unify discuss/chat send path and card markdown delivery
* feat(discuss): switch to stream execution with RouteHub broadcasting
* refactor(pipeline): remove context trimming from ComposeContext
The pipeline path should not trim context by token budget — the
upstream IC/RC already bounds the event window. Remove TrimContext,
FindWorkingWindowCursor, EstimateTokens, FormatLastProcessedMs (all
unused or only used for trimming), the maxTokens parameter from
ComposeContext, and MaxContextTokens from DiscussSessionConfig.
---------
Co-authored-by: 晨苒 <16112591+chen-ran@users.noreply.github.com>
* fix(text): resolve emoji shown in telegram stream mode
* chore(text): removing "reasoing" types in plain msg.
* feat(conversation): add function to check for tool call content in assistant outputs
- In group chats, only process slash commands when the message is
directed at this bot (via @mention or reply-to-bot), preventing
all bots from responding to the same command.
- Use raw_text metadata (before quote/forward context prepending)
for command detection so quoted content like "/fs" doesn't
accidentally match a command.
- Fix isTelegramBotMentioned text_mention entity check to verify
the mentioned bot matches the current bot, not just any bot.
- Extract ContainsMarkdown to shared channel package
- Auto-detect markdown in normalizeOutboundMessage and MCP send tool
- Apply markdown-to-HTML conversion during streaming deltas, not just
on the final message
- Remove resolveTelegramParseMode which incorrectly returned Telegram's
native "Markdown" mode instead of converting to HTML
- Fix all 14 Telegram send/edit paths for consistent parse mode handling
- Reset parseMode for plain-text error messages to avoid HTML corruption
Use rune-aware truncation for user-facing text and log previews so multibyte content is not corrupted in memory context, Telegram messages, or diagnostics.
- Extract parseTelegramTarget helper to consolidate duplicated @username
vs numeric chat ID parsing from 6+ locations (builder functions,
sendTelegramTextReturnMessage, sendTelegramAttachmentImpl)
- Extract Config.baseURL() to eliminate duplicate base URL resolution
between apiEndpoint() and fileEndpoint()
- Refactor stream.go Push method: extract resetStreamState(),
deliverFinalText(), and per-event-type sub-methods (pushDelta,
pushFinal, pushToolCallStart, pushAttachment, pushPhaseEnd,
pushError), reducing the 200-line switch-case to a clean dispatcher
- Use pushFinal's existing getBot() instead of duplicating parseConfig +
getOrCreateBot
- Replace sort.SliceStable with slices.SortStableFunc + cmp.Compare
- Replace strings.Index + manual slicing with strings.Cut in
decodeDataURLBytes, ResolveAttachment, and parseTelegramUserInput
* feat(telegram): use sendMessageDraft for streaming in private chats
Use Telegram Bot API 9.3's sendMessageDraft to stream partial messages
with smooth animation in private chats, replacing the sendMessage +
editMessageText approach. Group/channel chats keep the existing
edit-based streaming.
- Add sendTelegramDraft() for the sendMessageDraft API
- Detect private chats via conversation_type metadata in OpenStream
- Use 300ms throttle for drafts (vs 5s for edits)
- Send permanent messages at tool call boundaries and on final event
- Reset buffer atomically in StreamEventFinal to prevent duplicate
messages when multiple final events fire (one per assistant output)
* test(telegram): improve draft mode test assertions
Add sendTextForTest hook for sendTelegramTextReturnMessage to enable
direct assertion of send calls. Clean up residual unused variables
and replace indirect assertions with explicit mock-based verification.
Allow configuring a custom Telegram Bot API base URL (`apiBaseURL`) per
channel, enabling users behind restricted networks to route requests
through a reverse proxy (e.g. Nginx, Cloudflare Workers).
Both API calls and file downloads respect the configured endpoint.
When omitted, the official https://api.telegram.org is used.
Closes#159
Add ProcessingStatusNotifier implementation: show 👀 reaction while
processing, remove on completion/failure. Fix isReplyToBot to match
only the current bot (bot.Self.ID) instead of any bot, preventing
multiple bots from responding to the same reply. Add rune-safe text
truncation for Telegram message length limit.
Strip invalid UTF-8 byte sequences in sendTelegramTextReturnMessage and
editTelegramMessageText to prevent "text must be encoded in UTF-8" errors
that abort the stream mid-response.
Increase edit throttle from 250ms to 1500ms to respect Telegram per-chat limits,
remove newline bypass that effectively disabled throttling, add dedicated
editStreamMessageFinal with retry for final message delivery, and simplify
editTelegramMessageText by removing blocking sleep in favor of caller-level retry.
- Treat 400 "message is not modified" as success to avoid user-facing error
- On 429: sleep retry_after and retry once in editTelegramMessageText;
stream backs off lastEditedAt and returns nil
- Require error code 400 for message-not-modified check; add production
error string to unit tests
- Lower base throttle to 250ms; add test hooks and tests for 429 retry
and stream backoff
Merge upstream fx refactor and adapt all services to use go.uber.org/fx
for dependency injection. Resolve conflicts in main.go, server.go,
and service constructors while preserving our domain model changes.
- Fix telegram adapter panic on shutdown (double close channel)
- Fix feishu adapter processing messages after stop
- Increase directory lookup timeout from 2s to 5s
- 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.
- 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 Liu