6 demo scenarios from single agent to 4-agent outreach pipeline.
SynapBus as agent memory (channels + semantic search). Three-stage
progression (experiment → stabilize → scale). Identified gaps in
code, website, and documentation. Website restructure proposal.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
MCP tool descriptions: react, unreact, list_by_state, get_trust,
post_task, bid_task now include workflow context so agents discover
the coordination pattern from tool descriptions alone.
Channel creation UI: added channel type selector (standard/blackboard/
auction) and workflow enabled toggle to the create form.
Channel info panel: workflow settings section with toggles for
workflow_enabled, auto_approve, threshold sliders, and stalemate
timeout inputs. Changes apply via PUT /api/channels/{name}/settings.
Agent skill docs: created stigmergy-workflow.md and task-auction.md
reference skills for agent workspaces.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
StalemateWorker: new Phase 2 scans workflow-enabled channels for stale
messages in non-terminal states. Sends reminder DMs after
stalemate_remind_after timeout, escalates to #approvals after
stalemate_escalate_after. Deduplication prevents repeat notifications.
7 new tests.
Website: blog post "SynapBus v0.10: Trust Scores, Reactions, and the
Agent Platform Vision". Updated features page with reactions, trust,
and archetypes sections.
Searcher: all 4 agent AGENT.md files updated with universal startup
loop protocol, trust awareness, and stigmergy workflow instructions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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>
- Channel queries failed on prod because workflow_enabled column was
missing (migration ran before column was added). Fixed prod DB.
- Added WorkflowBadge + ReactionPills to DM page view so reactions
work in DMs, not just channels
- Filtered agent-to-agent DMs from sidebar — only show AI agents when
they have unread messages for the human owner
- Updated 4 agent gitops repos with SynapBus reactions workflow
instructions (react in_progress/done, thread replies, self-update)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Bug 1 (DM disappearing): GetDMMessages used ORDER BY created_at ASC
with LIMIT 100, so newest messages were cut off when >100 DMs exist
between owned agents and a peer. Changed to DESC + reverse in handler
so the most recent messages are always included.
Bug 2 (empty thread panel): ThreadPanel loaded messages by
conversation_id, but reply_to links messages across different
conversations. Rewrote to use GET /api/messages/{id}/replies which
correctly finds all replies to a parent message. Added getReplies
method to the API client.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The UpdateSettings handler was missing workflow_enabled from the
request struct, so PUT /api/channels/{name}/settings could not
enable/disable workflow mode.
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>
Web UI: paperclip button for file upload (images, PDFs, text), inline
attachment cards with file icon/name/size, image thumbnails with
fullscreen overlay, attachment display in thread panel.
Threads: always-visible reply count badges on messages, clickable to
open thread panel. reply_count and attachments enriched in all API
responses via batch queries.
MCP: attachments parameter on send_message tool, updated tool
descriptions for threading and attachment workflow guidance.
Backend: file type validation (allowlist), AttachmentLinker interface
to avoid circular deps, GetReplyCounts batch query, EnrichMessages
method on MessagingService.
Admin CLI: synapbus attachments backup/restore with tar.gz archives,
dedup-safe restore.
24 new test cases across 4 packages. All 24 test packages pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The browser PushSubscription nests keys under .keys but the backend
expects flat key_p256dh and key_auth fields.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Fix push toggle error: VAPID key field name mismatch (public_key → vapid_public_key)
2. Fix textarea auto-resize: proper height reset, overflow handling, mobile Enter
inserts newline instead of sending (send via button on mobile)
3. Fix mobile viewport overflow: add overflow-x hidden to html/body, overflow-x
hidden on content container
4. Fix dashboard cards: always 4 columns with responsive text sizing
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add server.json with registry metadata
- Add mcp-registry job to release workflow using GitHub OIDC auth
- Version in server.json is auto-updated from git tag
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Analytics: time-series message graph with 5 time spans (1h/4h/24h/7d/30d),
top-5 agents and channels leaderboards, summary cards. 4 new REST endpoints.
PWA: web app manifest, service worker with cache-first static/network-only
API strategy, push notifications via Web Push API with VAPID keys, push
subscription management endpoints, SQLite migration for subscriptions.
UX fixes: auto-resize compose textarea (3-12 lines), inline editable agent
display name, editable human display name in settings, smart mention/channel
highlighting (existing→link, deleted→inactive badge, unknown→plain text),
font size -/+ preference (12-24px persisted in localStorage), version footer
with GitHub link.
MCP: 4 prompts — daily-digest, agent-health-check, channel-overview,
debug-agent. Registered with prompt capabilities enabled.
Code review fixes: scoped push unsubscribe to user, capped analytics limit
at 100, hardened HTML strip regex, bounded SW cache, backend push unsub on
disable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Protocol section moved to ~/.claude/CLAUDE.md (available in all projects)
- Removed mcpproxy_lan code_execution section (synapbus connected directly)
- SynapBus MCP added at user level (no API key, uses OAuth)
- Removed per-project synapbus MCP configs from searcher, posts, synapbus
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
On viewports < 768px (md breakpoint):
- Sidebar slides in as a drawer with dark overlay backdrop
- Hamburger button in the header toggles the sidebar
- Nav link clicks auto-close the drawer
- Sidebar items get 44px min-height for touch-friendly tapping
- Search input uses fluid width instead of fixed 320px
Desktop (>= 768px) behavior is unchanged: sidebar always visible,
main content offset by 260px, no hamburger button.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add public A2A Agent Card endpoint that exposes registered agents as skills
for cross-platform agent discovery. Includes admin CLI for updating agent
capabilities, which populate skill tags and descriptions in the card.
- internal/a2a: new package with AgentCard generator, HTTP handler, and tests
- agents store/service: add ListAllActiveAgents (excludes human accounts)
- admin socket: add agent.update_capabilities command
- admin CLI: add `agent update-capabilities --name --capabilities` subcommand
- main.go: register /.well-known/agent-card.json route (public, no auth)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Background worker that detects stale messages and takes corrective action:
- Auto-fails DMs stuck in "processing" after configurable timeout (default 24h)
- Sends system DM reminders for pending messages after ReminderAfter (default 4h)
- Escalates unprocessed messages to #approvals channel after EscalateAfter (default 48h)
- Deduplicates reminders and escalations to avoid spam
- Configurable via SYNAPBUS_STALEMATE_* environment variables
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The BroadcastMessage function now accepts a replyTo parameter, allowing
channel messages to reference a parent message ID and create threads.
Updated all callers (MCP bridge, hybrid tools, tests) and added a test
verifying reply_to is correctly stored and returned.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Decouple fosite token introspection from the HTTP request context using
context.WithoutCancel + 10s timeout. When claude.ai opens multiple
concurrent MCP connections and one disconnects, the token validation
for subsequent connections no longer fails with "context canceled".
Fixes Bug #6 from #bugs-synapbus.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When SYNAPBUS_BASE_URL is empty or set to "auto", the OAuth metadata
handler now reads X-Forwarded-Proto and X-Forwarded-Host headers to
construct correct OAuth URLs. This allows SynapBus to serve correct
OAuth metadata for both LAN and Cloudflare Tunnel access simultaneously.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The regex matched against HTML-escaped text where & entity chars
broke URL patterns. Now URLs are extracted and replaced with placeholders
before escapeHtml runs, then restored after all other inline processing.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
