Cherry-picked valuable changes from PR #206:
- hasReadImageProvider supports chain format {"providers":[...]} config
- create_image/video/audio verify file persistence after write with diagnostic logging
- HistoryEntry gains Media field + CollectMedia() for group media context on @mention
- Zalo extractContentAndMedia refactored: all media types via DetectMIMEType/BuildMediaTags, 20MB limit
- Discord/Zalo pass media paths to Record() and collect historical media on @mention
- Zalo send_helpers logs directory contents when checkFileSize stat fails
Allow users to be entered with commas or newlines in the channel
config textarea field. Previously only newlines were supported,
but the Enter key was not working in some browsers.
💘 Generated with Crush
Assisted-by: MiniMax-M2.5 via Crush <crush@charm.land>
Telegram:
- Fix context cancellation in reaction timer callbacks — use context.Background()
so emoji reactions still work after request context is cancelled
- Add comma-ok safety on sync.Map type assertions in OnReactionEvent/ClearReaction
Zalo:
- Add comma-ok safety on sync.Map type assertions for typing controllers
- Validate non-empty senderID before processing text/image messages
Feishu/Lark:
- Handle json.Unmarshal errors in all 7 LarkClient messaging methods instead of
silently returning empty values
- Add 30s HTTP timeout for WebSocket endpoint request (was using DefaultClient)
- Eliminate double decryption in webhook handler — cache first result
- Replace goroutine+sleep with time.AfterFunc for dedup cleanup
- Add comma-ok safety on pairing debounce type assertion
- Use json.Marshal instead of fmt.Sprintf for image/file key JSON construction
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The install script only copied the binary, so `goclaw migrate up` and
`goclaw onboard` failed when run from the installed location because the
migrations directory was missing.
- Include migrations/ in the release tarball
- Install migrations to /usr/local/share/goclaw/migrations
- Guide users to export GOCLAW_MIGRATIONS_DIR before onboard
- Align next-steps output with onboard's own instructions
* fix(telegram): thread transport policy into media downloads with SSRF guard
* fix(telegram): trust configured APIServer during media downloads
* fix(telegram): use proper download timeout and clone DefaultTransport
- Clone http.DefaultTransport when proxy is configured to preserve
connection pool, TLS handshake timeout, and keep-alive defaults
- Use dedicated 5-minute context timeout for media downloads instead
of the shared 30s client timeout, preventing large file timeouts
(local Bot API supports up to 200 MB)
---------
Co-authored-by: viettranx <viettranx@gmail.com>
- Read existing IDENTITY.md before overwriting to preserve emoji field
- Config tab: merge existing other_config to prevent wiping emoji on save
- Emoji input: validate single emoji only with extractSingleEmoji()
- Select-all on focus for easy emoji replacement
- Replace full-list-reload on WS events with delta patching
- Progress events: local patch with 1s debounce (no network call)
- Delete events: local remove (no network call)
- Created/status changes: debounced fetch-one per task_id (300ms)
- Add channel field to TeamTaskData type for scope-aware filtering
- Clear stale progress patches when fetch-one fires (race prevention)
The delegation system this depended on was previously removed,
leaving internal/hooks/ as dead code with zero imports. Remove
the entire hook engine, UI config section, protocol types, i18n
keys, and all documentation references.
Search now acquires the team create lock and marks listed, so leaders
can use search instead of list before creating tasks — reduces token
consumption by returning only matching tasks instead of the full board.
Flip write_file deliver param default from false to true so result files
(reports, articles, generated content) are automatically sent as document
attachments to chat channels without requiring explicit LLM opt-in.
Add .md MIME type to mimeFromExt for proper markdown file delivery.
Use existing usePagination hook (default 20/page) with Pagination
component. Select-all checkbox applies to current page only; selections
persist across pages.
Add checkbox column to task list view for selecting terminal-status
tasks (completed/failed/cancelled). Header checkbox supports select-all
with indeterminate state. Bulk action bar appears on selection with
delete button that opens ConfirmDeleteDialog requiring user to type
"delete" to confirm.
Backend: new teams.tasks.delete-bulk RPC method with DeleteTasks batch
SQL (DELETE ... WHERE id = ANY($1) RETURNING id). Broadcasts delete
event per task for real-time UI sync.
i18n: added bulk action keys for en/vi/zh.
Remove premature EventTeamTaskAssigned broadcast in executeCreate() that
caused duplicate "assigned to" Telegram notifications. Assignment
notification now only fires at actual dispatch (post-turn, fallback, or
unblocked).
Add TeamNotifyQueue (2s debounce, cap 20) to batch rapid-fire task
notifications per chat — reduces N messages to 1 when leader dispatches
multiple tasks at once. In leader mode this also reduces agent turns
from N to 1.
Also fix: ResetTaskStatus now clears progress_percent/progress_step on
retry, and retry broadcast includes TaskNumber/Subject for correct
notification formatting.
Clear progress_percent in DB on all terminal transitions (complete,
cancel, fail, approve, reject). Also hide progress bar in UI for
terminal statuses as a safety net (kanban, list, detail dialog).
* feat: Implement MCP manager for server connections, tool registration, and deferred tool loading for agents.
* feat: Add tests for deferred tool activation logic within the tool registry and agent loop.
* fix(mcp): prevent deny list bypass via lazy activation + fix idempotency race
- Add PolicyEngine.IsDenied() to check deny patterns (incl. group: expansion)
before allowing lazily-activated deferred tools to execute
- Check IsDenied() in both single-tool and parallel execution paths in loop.go
- Make ActivateToolIfDeferred idempotent by checking activatedTools before
returning false, preventing concurrent goroutines from being blocked
- Add tests for deny-on-first-call, group deny patterns, and idempotent
concurrent activation
---------
Co-authored-by: viettranx <viettranx@gmail.com>
* feat(telegram): implement robust message splitting and dynamic HTML retry logic
* fix(telegram): fix sendHTML error chain regression and add split depth limit
- Re-check err.Error() in thread-not-found handler instead of stale errStr,
restoring the original chained fallback behavior
- Add maxSplitDepth (5) to prevent unbounded recursion when Telegram
repeatedly rejects split chunks
- Rename misleading test case to reflect actual monolithic fallback behavior
---------
Co-authored-by: viettranx <viettranx@gmail.com>
- Fix progress event payload missing TaskNumber, Subject, OwnerAgentKey,
ProgressPercent, ProgressStep — notifications were rendering empty
- Fix progress notification format to include task name (consistent with
dispatched/failed) and guard empty ProgressStep
- Change percent tool schema from number to integer for clarity
- Add pre-run member task reminder injecting task context before LLM loop
- Add mid-loop progress nudge every 10 iterations with suggested percent
based on iteration ratio (handles maxIter=0 unlimited case)
- Enhance leader cross-session reminder to show progress % when available
- Strengthen TEAM.md member guidance: focus, result quality, progress rules
- Add progress bar to task list table view (matches kanban card pattern)
- Add ErrorBoundary wrapping routes (outer) and Outlet (inner with key reset)
- Replace lazy() with lazyWithRetry() to retry failed chunk loads + auto-reload
- Invalidate all queries on WS reconnect to prevent stale/empty data renders
- skill_manage builtin tool default Enabled: true (available in registry)
- When skill_evolve=false: filter skill_manage from both tool definitions
(API params) and system prompt tooling section — agent has zero awareness
- When skill_evolve=true: tool visible + system prompt guidance + nudges
- Update UI hints to reflect tool is available by default
- Move Self-Evolution + Skill Learning sections before LLM Config (right after Identity)
- Strip managed keys (emoji, self_evolve, description, skill_evolve, skill_nudge_interval)
from Other Config raw JSON editor so they don't leak as editable JSON
- Fix info text: remove hardcoded "5+ tool calls" — nudge threshold is configurable
sendMessageDraft causes "reply to deleted message" artifacts on some
Telegram clients (tdesktop#10315). Disable by default so content
streaming uses message transport (same as reasoning stream).
Extract announce logic from handleTeammateMessage into a dedicated
announce queue that batches concurrent task completions. Handles
failure reporting and deduplicates rapid-fire announces.
Predefined agents now retain all tools and system prompt sections when
BOOTSTRAP.md is present, instead of entering slim mode with only write_file.
Open agents keep the existing slim bootstrap mode.
- Gate tool filtering and IsBootstrap on agentType != "predefined"
- Add FIRST RUN reminder for predefined agents (without tool restriction)
- Skip bootstrap/user seeding for team-dispatched sessions (IsTeamSession)
- Group chats skip BOOTSTRAP.md entirely
- Track bootstrapWriteDetected + inject nudge after 2 turns without write_file
- Update templates: never reveal process, no capability listing, no "locked"
- Cache LoadContextFiles via existing agentCache/userCache (TTL 5min)
Remove fields the model doesn't need from tool response DTOs:
- owner_agent_id → model uses owner_agent_key
- created_by_agent_id → model uses created_by_agent_key
- task_number → model uses identifier (e.g. "T-018-5e65")
Reduces context token consumption. UI (WS API) unaffected —
uses separate TeamTaskData struct with all fields.
- Fix scope dropdown: cache scopes from initial "all" load so dropdown
stays stable when filtering by chatID
- Derive scopes from file chat_id when task scopes are empty
- Remove dead files: team-workspace-tab.tsx, team-tasks-tab.tsx
(replaced by board view and workspace dialog)
- Kanban: reorder columns (blocked after pending), show blocked-by info
on cards, clickable blocker links in task detail, framer-motion card
animation between columns
- Dialogs: standardize scroll pattern across all modals — header fixed,
scrollbar flush with outer edge via negative margin trick
- Remove delegation page, types, events, i18n, routes, and all references
- Fix activity_logs NULL jsonb scan error (COALESCE)
- Board header: show text labels on action buttons (desktop)