Discord: include sender's mention format in [From:] annotation so models
use the correct user ID, and strip the bot's own @mention from message
content to prevent the model from echoing it back.
Summoning modal: remove AGENTS.md from progress list since backend only
generates SOUL.md and IDENTITY.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add tool loop detection (toolloop.go): tracks repeated no-progress tool calls
using SHA256 hashing of args+results. Warning at 5 identical calls, force stop
at 10. Prevents Gemini models from burning tokens in infinite loops.
- Inject AVAILABILITY.md negative context when agent has no team/delegation
targets, so models don't waste iterations probing unavailable capabilities.
- Fix Dockerfile: create /app/.goclaw directory so Docker volume initializes
with correct goclaw:goclaw ownership instead of root:root.
- Update collapseToolCallsWithoutSig comments for clarity.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gemini 2.5 flash doesn't return thought_signature, causing
collapseToolCallsWithoutSig to convert tool_calls to "(Used tool ...)"
text that Gemini imitates instead of making real tool calls.
Now strips tool_calls and folds results into plain user messages
so the model retains context without an imitable pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Gemini 2.5 flash doesn't return thought_signature in OpenAI-compat responses,
causing collapseToolCallsWithoutSig to convert ALL tool_calls to "(Used tool ...)"
text. Gemini then imitates this pattern instead of making actual tool calls.
Now drops tool_call cycles entirely, preserving only the assistant's text content.
Also fixes word-wrap in trace detail dialog (break-words instead of break-all)
and uses <pre> with whitespace-pre-wrap for trace-level input/output previews.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Implement `probeBotInfo()` to fetch bot's `open_id` via `/open-apis/bot/v3/info`, fixing group mention detection that was always false due to empty `botOpenID`.
- Add group pending history support to Feishu channel (record/build context/clear) matching Discord pattern.
- Fix Discord placeholder edit to chunk long responses instead of truncating at 2000 chars.
- Implement DM pairing flow for Discord and WhatsApp (checkDMPolicy, sendPairingReply with debounce)
- Add "pairing" case to BaseChannel.CheckPolicy() to reject instead of falling through to "open"
- Add group pending history tracking to Discord (record when not mentioned, prepend context when mentioned)
- Resolve Discord display names with priority: server nickname > global name > username
- Fix Gemini collapse format to prevent model from imitating tool call patterns
- Fix formatTokens crash on null/undefined input
In managed mode, multiple agents share a single tool registry. The spawn
and subagent tools were constructed with a hardcoded parentID of "default",
which does not exist as an agent in managed mode deployments. This caused
subagent announces to fail with "agent default not found" when any
non-default agent (e.g. a secondary agent) tried to spawn a subagent.
Fix: add ctxAgentKey to tool context keys (same pattern as channel/chatID),
inject the calling agent's key from the loop, and read it in spawn/subagent
tools with a fallback to the construction-time default for backward
compatibility with standalone mode.
MCP servers that don't implement the `ping` method return a "method not
found" error. The health loop previously treated this as a failure,
triggering exponential backoff reconnects and making tools temporarily
unavailable.
Now uses case-insensitive matching to detect "method not found" responses
and treats the server as healthy (it did respond, just doesn't support
ping). Resets reconnect attempts and clears error state.
- Add cmd.Version variable set at build time via -ldflags
- Fix Dockerfile ldflags path to use cmd.Version instead of main.version
- Add Makefile with auto-detection from git tags (git describe)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Wire AgentToolPolicy from agent spec through loop creation and resolver, passing it to PolicyEngine.FilterTools for per-agent tool restrictions (nil = no restrictions). Set RestrictToWorkspace=true for default agent in managed mode seeding. Clean up thinking/placeholder messages in Discord and Telegram when agent suppresses empty/NO_REPLY responses by publishing empty outbound and deleting placeholders without sending messages.
Remove env/printenv from safe bins list and add deny patterns for bare env/printenv/set/export commands that dump all environment variables including secrets. Expand credential scrubbing to detect connection strings (PostgreSQL, MySQL, MongoDB, Redis, AMQP), generic KEY=/SECRET=/CREDENTIAL= environment variables, DSN/DATABASE_URL patterns, and long hex strings (64+ chars) that may be encryption keys or hashes.
Implement pagination across sessions.list, usage.get, and traces HTTP endpoints with limit/offset/total response fields. Add ListPaged method to SessionStore with SessionListOpts struct. Optimize PostgreSQL session queries using jsonb_array_length to avoid loading full message arrays. Add CountTraces method to TracingStore with shared WHERE clause builder. Create reusable Pagination component with page
Extend CronJob model with UserID field for multi-tenant isolation. Add agentID and userID filter parameters to ListJobs across all store implementations (file, pg). Support agent lookup by UUID in resolver for cron jobs that store agent_id as UUID. Change cron job handler signature to return CronJobResult struct with content, token usage (input/output tokens), and duration. Track execution metrics
Check Docker availability before enabling sandbox and gracefully disable with warning if unavailable. Add resolveAgentUUID helper in Telegram to support both agent keys and direct UUIDs. Expose sandbox config via environment variables for docker-compose overlay. Add compact redirect cards in config UI for Providers and Channels sections when in managed mode, directing users to dedicated management pages.
Implement group file writer allowlist system with Telegram commands (/addwriter, /removewriter, /writers) for managing who can edit protected files in group chats. Wire AgentStore through Telegram factory, inject SenderID context for permission checks, and auto-bootstrap first group member as writer. Only existing writers can manage the list, preventing removal of the last writer.
Apply security best practices to goclaw service: drop all capabilities, enable no-new-privileges, set read-only root filesystem with tmpfs for /tmp, limit PIDs to 200, and cap memory at 1G with 2 CPU cores.
Register edit tool (sandboxed + non-sandboxed variants) with context file and memory interceptors in managed mode. Add cron tool for agent-facing job management. Register session tools (list, status, history, send) and message tool with proper SessionStoreAware, BusAware, and ChannelSenderAware wiring. Harden exec approval system to always be active with deny patterns + safe bins, defaulting to full
