Trust scores: per (agent, action_type) pair, stored in agent_trust
table. Auto-adjusts when human reacts to AI agent messages (approve
+0.05, reject -0.1). Scores clamped [0.0, 1.0]. MCP get_trust action
+ REST API /api/trust/{agent}. Web UI shows trust progress bars on
agent detail pages.
Claim semantics: only one in_progress reaction per message enforced.
First agent to claim wins, duplicates rejected with clear error.
State-change webhooks: StateChangeNotifier interface fires
workflow.state_changed events through existing webhook infrastructure
when reactions change a message's derived workflow state.
Channel thresholds: publish_threshold and approve_threshold fields
on channels for configuring autonomy gates.
Migration 014_trust_claims.sql. 17 new test cases across trust
model + store.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add workflow_enabled column to channels (default false) — reactions
and workflow badges only show on opted-in channels
- ReactionPills: add "+" button with picker dropdown to add reactions
when none exist yet (was missing, only showed existing reactions)
- Update CLAUDE.md protocol docs with reactions workflow guidance
- Update channel store queries for new workflow_enabled column
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add typed reactions (approve/reject/in_progress/done/published) with
toggle semantics. Workflow state derived from highest-priority reaction.
New reactions package with model, SQLite store, and service layer.
REST API: POST/GET/DELETE /api/messages/{id}/reactions for toggle/query,
PUT /api/channels/{name}/settings for workflow config, GET by-state
endpoint for listing messages by workflow state.
MCP: react/unreact/get_reactions/list_by_state actions via bridge.
Web UI: WorkflowBadge (colored state pills) and ReactionPills (toggle
pills with agent names) components integrated into channel view.
Channel settings: auto_approve, stalemate_remind_after,
stalemate_escalate_after columns. CLI: channels update command.
Migration 013_reactions.sql adds message_reactions table and channel
workflow columns. 29+ new test cases across model and store.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Auto-join public channels on first send (bug #1)
- Channel broadcasts no longer create duplicate DM copies; inbox DMs
only sent for @mentions (bug #2)
- Embedding pipeline auto-enqueues new messages via MessageListener
callback instead of requiring pod restart (bug #3)
- Admin socket defaults to /tmp in containers to avoid PVC filesystem
incompatibility with Unix sockets (bug #5)
- SSE events now fire for MCP-sent messages (not just REST API),
enabling live notification badges without page reload
- Fixed frontend SSE field name mismatch (channel_name → channel)
- Fixed SSE client not connecting after login redirect
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- JS/TS execution engine (goja + esbuild) with sandboxed runtime and call() bridge
- BM25 action discovery index over 23 registered actions
- ServiceBridge mapping call() invocations to existing service methods
- Admin CLI subcommands for webhook/k8s/gc operations
- Pagination support (offset/limit) in read_inbox, search_messages, get_channel_messages
- Fixed test assertions for call() envelope structure {ok, result}
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace 5 separate tool registrars (messaging, channels, swarm,
attachments, webhooks) with a single HybridToolRegistrar exposing
4 tools: my_status, send_message, search, and execute.
New foundation packages:
- internal/actions: action registry (22 actions) + BM25 search index
- internal/jsruntime: lightweight call() expression parser with
concurrency-limited execution pool
The `execute` tool dispatches call() expressions through a
ServiceBridge that maps action names to existing service methods,
preserving all original handler logic. The `search` tool enables
agents to discover available actions by keyword. The `send_message`
tool merges DM and channel sending with mutual exclusion.
All unit tests, integration tests, build, and vet pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add `my_status` MCP tool: single call returns agent identity, pending
DMs, channel mentions, system notifications, channel summaries, and
stats with truncation for large inboxes
- Add embeddings CLI: `synapbus embeddings status|reindex|clear` for
managing vectors when switching embedding providers
- Add automatic message retention worker with configurable period
(--message-retention, default 12m), warning notifications 1 month
before deletion, cascade cleanup, and incremental vacuum
- Add manual purge: `synapbus messages purge --older-than --agent --channel`
and `synapbus db vacuum` for on-demand cleanup
- Add `synapbus retention status` CLI for admin visibility
- Create system agent at startup for sending retention warnings
- Filter system agent from discover_agents results
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
11 Go integration tests that start an in-process server with in-memory
SQLite, register agents with API keys, and make real JSON-RPC 2.0 calls
to /mcp. Tests cover: direct messages, channels, search, threads,
agent discovery, inbox filters, claim/mark-done, tool listing, auth
enforcement, private channels, and read-state tracking.
Run with: make test-e2e
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Major feature additions across backend and frontend:
Backend:
- Unix domain socket admin server with JSON-RPC protocol
- CLI subcommands: user/agent management, audit, backup, messages, channels
- Managed API keys (sb_ prefix) with permissions, channel limits, expiry
- Thread/reply support in messaging core (reply_to column)
- Context-based trace owner_id propagation for proper audit filtering
- Two-step auth middleware supporting both agent keys and managed API keys
Frontend:
- Complete Slack-like dark theme redesign with custom CSS properties
- Sidebar with Channels, Direct Messages, and Admin sections
- Thread panel (slide-in) for viewing message replies
- API key management page with create form, key display, and
ready-to-use MCP/Claude Code config snippets with copy-to-clipboard
- All pages restyled: login, dashboard, agents, conversations, settings
E2E Tests:
- Fixed test runner binary path resolution
- Added pyproject.toml for test dependencies
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Rewrite test to use 3-tier auth fallback (from dialog-engine pattern):
ANTHROPIC_API_KEY → CLAUDE_CODE_OAUTH_TOKEN → macOS Keychain.
No dedicated API key required — works with Claude subscription.
- Auto-start/stop SynapBus server (--auto-server flag)
- Dialog-engine tool loop pattern (max rounds + forced text termination)
- Token usage and cost tracking
- Add spec for E2E agent testing framework (011)
Tested: two Claude agents (Alice, Bob) autonomously exchange messages
through SynapBus MCP Streamable HTTP. Cost: ~$0.07 per run.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
