* fix: handle ignored errors, unsafe type assertions, missing panic recovery
- Cron scheduler (PG + SQLite): check all ExecContext errors in
recomputeStaleJobs, run log insert, job delete, and post-run update.
Previously these errors were silently discarded, which could leave
job state inconsistent without any log trace.
- Discord: use comma-ok type assertions on sync.Map placeholder loads
to prevent potential panics from bare type assertions.
- Slack: use comma-ok type assertions in sweepMaps for dedup and
thread participation eviction to prevent potential panics.
- Feishu: add safego.Recover to WebSocket goroutine so a panic in
the WS client doesn't silently kill the goroutine.
- Agent export: add tenant owner/admin permission check to canExport.
Previously only agent owner and system owner could export — tenant
admins were incorrectly denied.
- Channel health: use errors.Is/errors.As for context.DeadlineExceeded,
net.DNSError, and net.OpError before falling back to string matching.
DNS NXDOMAIN is now correctly classified as non-retryable.
* fix(review): revert export to system-only + add missing rows.Err check
- Revert canExport tenant role check — export/import is restricted to
agent owner and system owner by design
- Add rows.Err() check after recomputeStaleJobs loop in PG cron
(parity with SQLite implementation)
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
* fix(cron): prevent scheduler loop from blocking when a job hangs
The cron scheduler's runLoop calls checkAndRunDueJobs() every second,
which previously used wg.Wait() to block until ALL claimed jobs complete.
If any single job hung (LLM provider timeout, agent loop stuck, network
issue), wg.Wait() would block indefinitely, preventing the scheduler
from ever checking for new due jobs — effectively killing all cron
scheduling until a container restart.
Changes:
- Remove wg.Wait() from both PG and SQLite cron schedulers — jobs now
run as independent goroutines that don't block the check loop
- Add panic recovery to PG runLoop (safeCheckAndRunDueJobs wrapper)
and per-job goroutines, matching the existing safego.Recover pattern
in the SQLite scheduler
- Add 10-minute context timeout to the cron job handler so a hung
agent run is cancelled instead of blocking forever
- Use select with context.Done() in the handler to respect the timeout
when waiting for the scheduler outcome
- Invalidate PG job cache per-job on completion instead of after the
(now-removed) batch wait
The SQLite scheduler already had safego.Recover on job goroutines but
still used wg.Wait() — this commit removes that blocking wait as well.
* fix(cron): make job timeout configurable + add SQLite runLoop panic recovery
- Add `cron.job_timeout` config field (Go duration string, default "10m")
so operators can tune the per-job timeout for complex agent workloads
without code changes
- Add `safeCheckJobs` panic recovery wrapper to SQLite cron runLoop,
matching the PG scheduler's `safeCheckAndRunDueJobs` for consistency
- Use dynamic timeout string in error message for better diagnostics
* fix: remove unused "time" import from gateway_cron.go
* fix(cron): apply same fixes to SQLite DB scheduler (sqlitestore)
The SQLite DB-backed scheduler (used by desktop edition with SQLite
backend) had the exact same wg.Wait() blocking issue and missing
panic recovery as the PG scheduler. Apply identical fixes:
- Remove wg.Wait() — jobs run as independent goroutines
- Add safeCheckAndRunDueJobs panic recovery wrapper for runLoop
- Add per-job panic recovery and cache invalidation
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
PG version already resets jobs stuck in 'running' state on startup
(from a crash mid-execution), but SQLite was missing this step.
Desktop app crashes would leave cron jobs permanently stuck in
'running' status, never executing again.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
## Summary
- **Flood after restart**: `recomputeStaleJobs()` now advances past-due jobs (not just NULL) to their next future run time, preventing all missed jobs from firing simultaneously on first tick
- **Interval drift**: Anchor-based scheduling computes next run from original scheduled time instead of execution end time, preserving per-job offsets
- **O(1) advance**: Replaced O(N) loop with modular arithmetic to prevent CPU starvation after prolonged downtime with short-interval jobs
- **SQLite RunJob fix**: Added `next_run_at = NULL` claim + `reloadClaimed` param to match PG store behavior — manual runs were silently skipped
- **Manual RunJob consistency**: Nil-anchor guard ensures manual triggers use `now + interval` (not anchor) across all stores
- **Zombie at-job fix**: JSON store Start() now disables past-due one-time `at` jobs instead of leaving them enabled with nil NextRunAtMS
All fixes applied across JSON, PostgreSQL, and SQLite store implementations.
4 new unit tests covering flood prevention, anchor arithmetic, RunJob scheduling, and at-job disabling.
Replace direct sentinel error comparisons (==, !=) with errors.Is()
across the codebase. Direct comparison breaks when errors are wrapped
with fmt.Errorf("...: %w", err), which can cause missed matches for
sql.ErrNoRows, io.EOF, context.DeadlineExceeded, and context.Canceled.
Affected packages:
- store/pg: sql.ErrNoRows in secure_cli, agents_export_team_*, mcp_export_queries
- store/sqlitestore: sql.ErrNoRows in schema migration
- tools: context.DeadlineExceeded in shell, credentialed_exec
- mcp: context.DeadlineExceeded in bridge_tool
- providers: context.Canceled in acp_provider, anthropic_stream_test
- updater: io.EOF in tar extraction
Also removes unused @xyflow/react dependency from web UI — it was
replaced by react-force-graph-2d but never cleaned up from package.json.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Sessions page shows raw IDs instead of sender names because these channels
didn't include display_name in their message metadata. The gateway's
extractSessionMetadata() already looks for this key but it was missing
from Feishu, Zalo Personal, and Slack message payloads.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
- Bump DefaultAPIVersion from 665 to 671 to match current Zalo web client
- Batch getmg-v2 requests (50 groups/batch) — Zalo rejects large payloads,
causing error 114 for accounts with many groups (e.g. 250+)
- Fix encryptType=1 WebSocket event decryption: add gzip decompression
after base64 decode (matches zca-js pako.inflate behavior)
- Split contacts picker into Friends/Groups tabs for better usability
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* fix(feishu): increase reply context max length from 500 to 2000
500 bytes is too short for CJK/Unicode text (each accented char = 2-3
bytes, so ~250 real characters). Increase to 2000 so reply context is
not aggressively truncated.
* fix(teams): handle NULL data column in task events queries
ListTaskEvents and ListTeamEvents crash with "unsupported Scan,
storing driver.Value type <nil> into type *json.RawMessage" when the
data column is NULL. Use COALESCE(data, '{}') to return an empty JSON
object instead.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
1. Session detail: isDisplayable() filtered out assistant messages with
only tool_calls or thinking (no text content). Live chat renders these
via MergedToolGroup but session history silently dropped them.
2. Memory document dialog: load error showed "Failed to create document"
(wrong i18n key toast.failedCreate). Save error used the same wrong key.
Fixed to use toast.docLoadFailed and toast.docUpdateFailed respectively.
Added missing docLoadFailed key to en/vi/zh locale files.
3. Memory dialogs: all 5 dialogs missing aria-describedby={undefined} on
DialogContent, causing Radix UI console warnings about missing
Description for accessibility.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
When running in Docker, the Claude CLI provider setup showed `claude auth login`
which doesn't work inside a container. This change:
- Mounts host ~/.claude as read-only into the container
- Entrypoint syncs credentials to a writable volume (respects cap_drop: ALL)
- Backend detects Docker via /.dockerenv and returns `in_docker` in auth-status API
- UI shows `docker compose exec goclaw claude auth login` for Docker deployments
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
- Update README Docker section to use `make up` instead of raw
docker compose commands. `make up` handles network creation,
version embedding from git tags, and database migrations.
- Add WITH_* flags to Makefile for optional compose services:
WITH_BROWSER, WITH_OTEL, WITH_SANDBOX, WITH_TAILSCALE, WITH_REDIS.
Uses WITH_ prefix to avoid conflicts with common env vars (e.g.
BROWSER is set by many desktop environments).
- Document common make commands (up/down/logs/reset) and optional
service flags with descriptions in a table format.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* feat(gateway): add version update checker
Check GitHub releases periodically (1h) and surface update availability
in the health endpoint + dashboard header. Version is auto-detected from
git tags via Makefile, falling back to VERSION file or build arg.
Backend: new UpdateChecker goroutine, health response includes
latestVersion/updateAvailable/updateUrl fields.
Frontend: version badge in overview header with clickable "available"
link when a newer release exists.
* fix(gateway): fix update checker compile errors and harden GitHub API call
- Export UpdateChecker/NewUpdateChecker to match server.go references
- Move StartUpdateChecker(ctx) after ctx declaration in gateway startup
- Add User-Agent header for GitHub API compliance
- Limit response body to 1MB via io.LimitReader
- Use strconv.Atoi instead of manual int parsing in parseSemver
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
* fix(skills): parse YAML multiline blocks and lists in skill frontmatter
parseSimpleYAML and ParseSkillFrontmatter only handled single-line
key: value pairs. YAML multiline block scalars (|, >) and list values
(- item) were parsed incorrectly:
description: |
Multi-line text here...
was stored as description="|" (literal pipe character), and indented
continuation lines were misinterpreted as new key-value pairs.
Fix: parseSimpleYAML now tracks indented continuation lines after
block scalar indicators (|, >, |-, >-) and empty-value keys (for
list blocks). Continuation lines are joined with spaces. List items
(- value) have the prefix stripped.
ParseSkillFrontmatter now delegates to parseSimpleYAML instead of
duplicating the parsing logic.
* fix(skills): preserve empty-value keys in parseSimpleYAML
When a key has no value and no indented continuation (e.g. "slug:"),
flushBlock now stores "" instead of silently dropping the key.
Maintains backward compatibility with the previous parser behavior.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
The .runtime directory on the data volume may be owned by goclaw:goclaw
(from older images or Docker volume initialization). pkg-helper runs as
root but without CAP_DAC_OVERRIDE, so it cannot create files in
goclaw-owned directories. This caused persistAdd() to fail silently —
runtime-installed system packages (bash, pandoc, etc.) were lost on
container recreate.
Fix: set .runtime directory ownership to root:goclaw (mode 0750) so
pkg-helper can write apk-packages while goclaw can still traverse.
Three layers for robustness:
- Dockerfile: pre-create .runtime with correct split ownership in image
- docker-entrypoint.sh: fix ownership on existing volumes (upgrade path)
- pkg-helper: self-healing ensurePersistDir() at startup as defense-in-depth
Subdirs (pip/, npm-global/, pip-cache/) remain goclaw-owned since those
are written by the app process, not pkg-helper.
Fixes#323
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* fix(skills): use DB file_path for skill directory resolution + list archived skills
Two fixes:
1. Skills store methods (ListSkills, ListAllSkills, GetSkill, GetSkillByID,
LoadSkill) constructed BaseDir from s.baseDir + slug + version, ignoring
the file_path column stored in the database. When GOCLAW_DATA_DIR differs
from the directory used during initial skill seeding, this caused
dependency rescans to look in the wrong directory, find no scripts, and
silently skip — leaving missing_deps stale in the database even after
successful pip/npm installs.
Fix: buildSkillInfo now accepts an optional filePath parameter from the
DB and uses it as the authoritative BaseDir when set.
2. ListSkills only returned skills with status='active', hiding archived
skills from the admin UI. Skills with missing dependencies are archived
on seed, making them invisible — admins couldn't see them to install
deps and reactivate. Now includes archived skills in the listing.
* fix(skills): use 'deleted' status for soft-delete, distinct from 'archived'
DeleteSkill previously set status='archived', which is also used for skills
with missing dependencies. Now that ListSkills includes archived skills
(so admins can see and fix missing deps), soft-deleted skills were
reappearing after page refresh.
Use status='deleted' for user-deleted skills to keep them hidden while
allowing archived (missing deps) skills to remain visible in the admin UI.
* fix(skills): complete file_path resolution + exclude deleted from rescan
- ListAllSkills: add `status != 'deleted'` to prevent rescan from
resurrecting user-deleted skills
- ListAccessible: add file_path to SELECT so runtime skill resolution
uses DB path instead of stale baseDir
- SearchByEmbedding: use DB file_path when available for path resolution
- CreateSkillManaged: ON CONFLICT visibility reset now matches both
'archived' and 'deleted' statuses
- Update delete result message and status comment
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
MCP tools that accept no parameters return {type: "object"} without a
properties field, which is valid per JSON Schema spec. However, OpenAI
API strictly requires "properties" on object schemas and rejects
requests with HTTP 400: "object schema missing properties".
Add default empty properties map when type is "object" and the MCP
server provides none.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* fix(codex,memory): sanitize tool call IDs, fix memory delete, add GPT-5.4
- codex_build: sanitize colons in tool call IDs before sending to
Responses API (OpenAI rejects non-alphanumeric chars except _ and -)
- memory_docs: check RowsAffected on delete — return error instead of
silent 200 when no document matched
- memory UI: pass document's agent_id to delete call so deletion works
from the "all agents" view (previously sent undefined as agent ID)
- codex models: add GPT-5.4 and GPT-5.4 Mini, update default model
* fix(codex): update default model assertion in test to gpt-5.4
* fix(codex): regex sanitize all invalid chars in tool call IDs, restore GPT-5.1 models
- toFcID: replace all non-alphanumeric/underscore/dash chars (not just
colons) to prevent future Responses API rejections
- Restore GPT-5.1 Codex Max and Codex Mini in model dropdown to avoid
breaking existing user configurations
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
* fix(memory): auto-backup + overwrite warning for memory files
When an agent writes to a memory file that already has content:
1. Old content is backed up to memory/.prev/{filename} (best-effort)
2. Write succeeds normally (no blocking)
3. Tool result includes warning with previous content (truncated to
4000 chars) so the agent can notice and merge if needed
Backup files are hidden from list_files and not indexed/embedded.
No database migration needed - uses existing PutDocument.
* fix(memory): support append mode + fix UTF-8 truncation in overwrite warning
- Add appendMode parameter to MemoryInterceptor.WriteFile() so
write_file(append=true) actually appends to memory files instead
of silently replacing content. Uses "\n\n---\n\n" separator.
- Fix UTF-8 truncation in overwrite warning: use []rune instead of
byte slicing to avoid cutting multi-byte characters.
- Fix char count in warning message: use len([]rune()) not len().
- Remove .prev/ backup mechanism (prevBackupPath, isPrevPath, backup
writes, ListFiles filter) in favor of simpler approach: append
mode prevents data loss, warning enables self-correction.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
* feat(feishu): add list_group_members tool + native @mention support
Add agent tool to list all members in a Lark group chat via
GET /open-apis/im/v1/chats/{chat_id}/members with auto-pagination.
- New tool `list_group_members`: returns member IDs + display names
- Native @mention conversion: @ou_xxx in outbound messages becomes
real Lark mentions (post: "at" element, card: <at> markdown tag)
- Auto-sync discovered members into ContactStore
- GroupMemberProvider interface on Channel for extensibility
- Add im:chat.members:read scope to channel setup UI
Requires Lark app scope: im:chat.members:read
* fix(feishu): URL-encode API params + channel-aware tool filtering
- URL-encode chatID (PathEscape) and pageToken (QueryEscape) in
ListChatMembers to prevent path traversal and query corruption
- Add slog.Warn when ListGroupMembers fails for observability
- Add ChannelAware interface so tools can declare required channel types
- ListGroupMembersTool now declares RequiredChannelTypes=["feishu"]
- loop.go filters out channel-specific tools when channel type mismatches,
so list_group_members only appears for Feishu conversations
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
When a Feishu/Lark user replies to an existing message, the agent now
sees the quoted message content via the GetMessage API, formatted as
[Replying to SenderName]...[/Replying] — matching the Telegram channel
behavior. Previously parent_id was parsed but the content was silently
discarded, so the agent had no idea what the user was replying to.
Requires im:message:readonly scope on the Lark app.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* fix(channels): collect contacts for DM and group-mentioned messages
Previously, EnsureContact was only called inside the "not mentioned →
record history → return" branch, so contacts were never saved for
messages that the bot actually processed (DMs and group @mentions).
This caused the contacts list to show empty names ("—") for active
users across all channels.
Move contact collection to the main processing path (before
PublishInbound / HandleMessage) so every processed message upserts
the sender's display name. The existing ContactCollector 30-minute
cache prevents redundant DB writes.
Affected channels: Feishu, Telegram, Discord, Slack, Zalo, WhatsApp.
* fix(slack): use clean userID for EnsureContact cache key
The senderID param in HandleMessage is the compound "U123|DisplayName"
form, which produces a different cache key than the clean "U123" used
in the group-history path (handlers.go:178). Use userID (extracted
clean ID) to ensure cache dedup works correctly.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Co-authored-by: viettranx <viettranx@gmail.com>
The HTTP allowlist (agentAllowedFields) was missing three fields that
the web UI sends when saving agent settings: is_default,
budget_monthly_cents, and subagents_config. These fields were silently
filtered out by filterAllowedKeys(), so saves appeared successful but
values never persisted to the database.
Also adds exclusive-default logic: when setting is_default=true on an
agent, any previously-default agent is automatically unset first.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Go can serialize empty slices as null in JSON. The events page
accessed p.changes.length without null checking, causing a crash
when viewing team.updated or agent_link.updated events with null
changes arrays.
Fixes#192
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* feat(ui): show required API scopes for Feishu/Lark channels
Add a collapsible info panel listing the required Lark/Feishu API
permissions (scopes) on the channel create/edit dialog and config
detail tab. Includes reminder about Contact Range and app publishing.
* fix(feishu): annotate DM messages with sender name
Feishu DMs were missing the [From: ...] annotation, so the agent
couldn't identify who was messaging. Group messages already had this.
Align with Telegram channel which annotates both DM and group messages.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Backend — WSClient protocol fixes (larkws.go):
- Parse service_id from WS URL query params instead of hardcoding 0
- Update all 4 server config values from pong payload (PingInterval,
ReconnectCount, ReconnectInterval, ReconnectNonce)
- Use server-configured reconnect params instead of hardcoded 120s wait
- Return HTTP 500 in ACK when event handler fails (enables Lark retry)
- Filter data frames by type header — only process "event" frames
- Report actual processing time in biz_rt header (was hardcoded "0")
Backend — event adapter (feishu.go):
- Return parse error from HandleEvent so ACK reflects failure status
UI — fix incorrect Feishu channel form labels:
- Remove "webhook only" from Lark Global domain label (WebSocket works
on both Lark Global and Feishu China)
- Remove "Feishu only" from WebSocket option label
- Change default connection_mode from "webhook" to "websocket" (matches
backend default)
- Add showWhen conditional field support to ChannelFields component
- Hide webhook_port, webhook_path, encrypt_key, verification_token when
WebSocket mode is selected
- Update i18n labels in all 3 locales (en, vi, zh)
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
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>
MessageTool.parseMediaPath() was hardcoded to only allow files in /tmp/,
while all other filesystem tools (read_file, write_file, edit, exec) use
workspace-aware resolvePath() with restrict_to_workspace enforcement.
This meant agents could create files in their workspace via write_file
but couldn't send them as attachments — only /tmp/ files from
create_image/create_audio worked.
Replace parseMediaPath() with resolveMediaPath() that:
- Reuses resolvePath() for consistent security (symlink, hardlink, traversal)
- Honors per-agent workspace + restrict_to_workspace from context
- Still allows /tmp/ as fallback (for create_image, create_audio, etc.)
- Supports relative paths resolved against workspace
- Updates tool description so LLM knows about MEDIA: prefix
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
1. Media tag enrichment (audio/video/document):
- Add enrichVideoIDs() — video media_id was never injected into
<media:video> tags, causing LLM to hallucinate UUIDs
- Fix all enrich functions to replace the LAST bare tag instead of
the first. When group history prepends older media tags, the first
occurrence belongs to history — injecting the current turn's ID
there causes the LLM to reference the wrong file
2. Gemini File API polling:
- Upload response returns fileURI immediately but file may still be
in PROCESSING state. Check state field; only skip polling when
file is already ACTIVE. Fixes "not in an ACTIVE state" errors
3. Channel instance credential merge:
- Partial credential updates (e.g. updating just token) now merge
with existing credentials instead of wiping other fields
- Loads, decrypts, merges, re-encrypts in a single Update() call
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* feat(telegram): support custom Bot API server URL
Add api_server credential field for Telegram channels to allow
using a self-hosted Telegram Bot API server (e.g. for 2GB upload
limits). Uses telego.WithAPIServer() option.
* feat(telegram): local Bot API media download + config improvements
- Support local Bot API --local mode: detect absolute file paths and
copy directly from filesystem (requires shared volume mount)
- Fall back to HTTP download via custom API server URL for non-local mode
- Move api_server/proxy from credentials to config (non-secret fields);
credentials still accepted for backward compat
- Add media_max_mb config field (friendlier than media_max_bytes);
deprecated media_max_bytes still works
- Default to 200 MB max when local Bot API is configured (vs 20 MB cloud)
- UI: move api_server/proxy to config section, use MB for media size
* fix: use 127.0.0.1 instead of localhost in API server placeholder
Docker containers cannot resolve localhost to the host machine.
127.0.0.1 works reliably with Docker's default bridge network.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The read_audio tool errors with "audio not found" because:
1. BuildMediaTags() creates bare <media:audio> tags without IDs
2. persistMedia() generates UUIDs stored in context, not in message content
3. LLM sees <media:audio> and passes it literally as media_id parameter
4. resolveAudioFile() tries to match "<media:audio>" against UUIDs — fails
Two-part fix:
- enrichAudioIDs(): embed persisted UUIDs into <media:audio> tags (like
enrichDocumentPaths does for documents), so LLM sees actual IDs
- resolveAudioFile(): sanitize tag-like media_id values and fallback to
most recent audio instead of hard error on unmatched IDs
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
When users create cron jobs from channel chats (Zalo, Telegram, etc.),
the LLM often omits the `deliver` flag (defaults to false). This causes
cron jobs to run successfully but silently discard results — the response
never reaches the chat where the user requested it.
Auto-detect channel context and default deliver=true for real channels,
skipping internal channels (cli, system, subagent, cron, delegate).
The existing auto-fill logic then populates channel and chatID from
context, ensuring delivery info is always captured.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Media tools (create_image, create_video, create_audio, read_audio,
read_video, read_document) routed API calls based on provider name
pattern matching (e.g. strings.HasPrefix(name, "gemini")). This breaks
when users give custom names to DB providers — a Gemini provider named
"chatgpt-sap-het" would be misrouted to the OpenAI-compat endpoint,
causing 404 errors.
Fix: carry the DB provider_type through OpenAIProvider, resolve it via
typedProvider interface in ExecuteWithChain, and inject as _provider_type
param for callProvider routing. Name-based heuristic kept as fallback
for config-file providers that don't have a DB type.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The per-agent `imageGen` and `vision` fields in `ToolPolicySpec` (stored
in agents.tools_config JSONB) were added in d5cc5a7 (Feb 26) as the
original way to configure image/vision providers. When the media provider
chain system was introduced in 5815437 (Mar 8), these fields were kept
"for backward compat" but became dead code with no UI to manage them.
This causes a hard-to-debug issue: if an agent's tools_config contains
stale imageGen/vision data (set via API or leftover from DB), it silently
overrides the global provider chain configured in the builtin tools UI.
Users see the correct chain in the UI but the tool calls a completely
different provider/model, with no indication of why.
Changes:
- Remove Vision and ImageGen fields + struct definitions from ToolPolicySpec
- Remove associated context helpers (WithVisionConfig, WithImageGenConfig, etc.)
- Remove per-agent override injection in agent loop
- Simplify create_image and read_image to use chain as sole source of truth
- UI: whitelist known tools_config fields on save to clean stale DB data
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
ExecuteWithChain previously required all providers to implement
credentialProvider (APIKey/APIBase). OAuth-based providers like
CodexProvider (ChatGPT OAuth) don't expose static credentials,
causing all media tools to fail with "does not expose API credentials".
Make credentialProvider optional (nil when unsupported). Each
callProvider gracefully falls back to the provider's Chat() API
when credentials are unavailable. Generation tools (create_image,
create_video, create_audio) return a clear error since they require
direct API access with no Chat fallback.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Four per-agent settings stored in the database (and configurable via UI)
were silently ignored at runtime because the tool/system layer always
used the global config defaults instead.
**restrict_to_workspace**: Tools used the global config default baked at
startup. Fix: pass per-agent value through context; tools check context
override before falling back to constructor default.
**subagents_config**: ParseSubagentsConfig() existed but was never called.
All agents shared one SubagentManager with global limits. Fix: resolve
per-agent config in the agent resolver, store it on each spawned task,
and use it for limit checks, deny lists, and system prompt generation.
**memory_config**: Only the enabled toggle was read per-agent; search
weights (vector_weight, text_weight, max_results, min_score) were
hardcoded from PGMemoryStore defaults. Fix: extend MemorySearchOptions
with weight overrides, read per-agent config from context in the
memory_search tool.
**sandbox_config**: Only workspace_access was extracted per-agent; mode,
image, memory, CPU, timeout, network settings were discarded. Fix: pass
full sandbox.Config through context; Manager.Get() accepts an optional
config override for new containers.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The embedding provider resolution only matched 3 hardcoded names
(openai, openrouter, gemini), silently failing for DB-stored providers
like "openai-embedding". This caused memory chunks to be stored
without vectors even when a valid embedding provider was configured.
Changes:
- resolveEmbeddingProvider: fallback to provider registry for DB-stored
provider names when hardcoded match fails
- gateway startup: read per-agent memory config from DB (priority over
config file defaults) for embedding provider resolution
- memory IndexDocument: log embedding errors instead of swallowing them
- memory admin ListChunks: return full chunk text instead of truncating
to 200 chars, avoiding confusing partial content in the UI
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* fix(channels): annotate DM messages with sender identity
Telegram and Zalo group messages already include [From: sender] prefix
so the agent knows who is talking, but DM messages were sent without
any sender context — the agent had no way to address the user by name.
- Telegram DM: add [From: @username] (or FirstName if no username)
- Zalo DM: add [From: displayName] when dName is present in payload
* fix(tests): add missing EnsureUserProfile to test stubs
AgentStore interface gained EnsureUserProfile in 4fce731 but the test
stub implementations were not updated, breaking CI on main.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The `allowEmpty` prop on `ProviderModelSelect` was defined but the
Select dropdown still auto-selected the first provider when the value
was empty, and there was no way to reset back to empty (auto-detect).
- Map empty provider to a sentinel so Radix Select can represent it
- Show an "(auto)" option in the dropdown when `allowEmpty` is set
- Pass `allowEmpty` from both embedding config callers
- Skip clearing the model on provider change in allowEmpty mode to
avoid a stale-closure bug where the second setState overwrites the
provider update
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* feat(cron): configurable default timezone for cron expressions
Cron expressions (e.g. "0 8 * * *") are evaluated relative to a timezone.
Without an explicit per-job timezone, they default to the server's system
timezone, which may not match the user's local time — especially in Docker
containers (default UTC) or multi-region deployments.
This adds a `default_timezone` setting to `CronConfig` (IANA format, e.g.
"Asia/Ho_Chi_Minh") that is applied as fallback when a cron job has no
explicit `schedule.tz`. The setting is configurable via the UI config page
(Integrations → Cron Scheduler) and hot-reloads on config changes.
Backend:
- Add `DefaultTimezone` field to `CronConfig`
- Add `SetDefaultTimezone()` to `CronStore` interface + PG implementation
- Apply default TZ in `AddJob()` when `schedule.TZ` is empty
- Wire at startup + subscribe to config change events for hot reload
- Update cron tool description so LLM knows about gateway default
Frontend:
- Add timezone dropdown (20 common IANA timezones) to Cron config section
- Add i18n keys for en, vi, zh
* fix(cron): apply default timezone to existing jobs via computeNextRun
Pass defaultTZ as fallback to computeNextRun so existing cron jobs
(with timezone = NULL in DB) also use the gateway's configured default
timezone when computing next_run_at. This ensures old jobs benefit
from the timezone setting without needing a DB migration or backfill.
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The onboard wizard sets GOCLAW_PROVIDER and GOCLAW_MODEL in .env for
initial bootstrap. Previously these env vars always overrode the config
file value via envStr(), making it impossible to change the default
provider/model through the Dashboard — every save was silently reverted
by ApplyEnvOverrides().
Change envStr to envFallback for these two fields: the env var is only
applied when the config file has no value (empty string). Once the user
saves a provider/model via the Dashboard, the config-file value wins.
Also:
- Stabilize ProviderModelSelect auto-select effect (useRef + useMemo)
- Add toast feedback on config save success/failure
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Backend defaults memoryFlush.enabled to true when config is nil
(memoryflush.go:39-46), but UI used `?? false` showing OFF.
Also fix sub-fields visibility to show when flush is defaulted ON.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
HandleMessage() always checked IsAllowed(senderID), which re-gates
individual senders against the allowlist even after the channel-specific
group policy (checkGroupPolicy) already approved access.
This caused group members who weren't individually listed in AllowFrom
to be silently blocked — even when GroupPolicy was set to "open" or the
group ID was in the allowlist.
Affected channels: Zalo Personal, Slack (any channel using HandleMessage
with peerKind "group"). Telegram was unaffected because it publishes
directly to the bus.
Now HandleMessage only enforces the allowlist for DMs. Group access
control is fully delegated to each channel's checkGroupPolicy.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Fixes#94. The stream-json scanner never checked scanner.Err() after the
scan loop, so if a line exceeded the 1MB buffer limit the scanner would
stop with bufio.ErrTooLong and the response would be silently truncated.
- Check scanner.Err() after the loop and return an explicit error
- Increase max buffer from 1MB to 10MB to handle large tool outputs
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
Fixes#87. crypto.randomUUID() is unavailable in browsers older than
Chrome 92 / Firefox 95 / Safari 15.4, causing an uncaught TypeError
that crashes the React tree and renders a blank page when opening
builtin-tool settings or MCP grant dialogs.
Add a uniqueId() helper that uses crypto.randomUUID() when available
and falls back to a Math.random-based UUID v4 generator otherwise.
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
The list pages had ConfirmDialog for deletion wired up but no UI
element to trigger it. Detail pages had no delete option at all.
- Add delete button with trash icon to agent and team cards
- Wire onDelete callbacks to existing setDeleteTarget state
- Add delete button + confirm dialog to agent detail page header
- Add delete button + confirm dialog to team detail page header
Closes#17
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
* feat(browser): add remote Chrome sidecar support for Docker deployments
When running in Docker, Chrome is not installed in the runtime image.
This adds support for connecting to a remote Chrome via CDP (Chrome
DevTools Protocol) using a Docker Compose sidecar overlay, following
the existing pattern used by sandbox, OTel, and Tailscale overlays.
Changes:
- Add RemoteURL field to BrowserToolConfig
- Add GOCLAW_BROWSER_REMOTE_URL env var (auto-enables browser tool)
- Browser Manager: remote CDP connection with hostname-to-IP resolution
(required by Chrome M113+ DNS rebinding protection), auto-reconnect
on dead connections, disconnect-only on Stop (sidecar stays alive)
- Auto-start browser on first tool action (no explicit "start" needed)
- Add docker-compose.browser.yml overlay (zenika/alpine-chrome:124)
- Add unit tests for CDP resolution and Manager lifecycle
Usage:
docker compose -f docker-compose.yml -f docker-compose.managed.yml \
-f docker-compose.browser.yml up -d --build
Closes#56
* feat(browser): fix onboard summary and config serialization for remote mode
- onboard.go: show "remote: ws://..." instead of "headless" when RemoteURL is set
- onboard_auto.go: serialize remote_url field in generated config
---------
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
- Extract QueryTodaySummary to package-level so quota.usage returns
requestsToday/tokensToday even when QuotaChecker is nil (standalone mode)
- Enrich health RPC: version, uptime, mode, DB ping, tool count,
connected clients list with real IP and connectedAt
- Add handleStatus: sessions count, agentTotal from DB (managed mode)
- Extract client IP from X-Real-IP / X-Forwarded-For during WS upgrade
- Rebuild overview UI: live uptime, System Health panel, Connected Clients
panel, inline channel status with dots, auto-refresh 30s
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
When stream_options.include_usage is enabled, the OpenAI API sends the
final usage chunk with an empty choices array. The streaming parser
skipped chunks with no choices before checking for usage data, causing
token counts to always be 0 in traces.
Fix: extract usage data before the empty-choices skip.
Also fixes two related SSE parsing issues:
- SSE data prefix now handles both "data: " and "data:" (some providers
like Kimi omit the space after the colon, per SSE spec)
- Added scanner.Err() check to surface stream read errors (timeout,
connection reset) instead of silently returning partial results
Co-authored-by: Luvu182 <208665161+Luvu182@users.noreply.github.com>
