Three improvements that turn the doc-gardener demo from "runs but
stays in 'draft' forever" into a goal that properly transitions
through its lifecycle and renders a completion summary on /goals/<id>.
### 1. complete_goal MCP tool (#59, #62)
New tool surface: complete_goal(goal_id, status, summary, completion_message_id?)
The critic calls this from inside the sandbox after it sends its FINAL:
DM. Records the one-paragraph human-readable summary on the goal row
plus a pointer to the message that carried the FINAL text, so the Web
UI /goals/<id> page has both the verdict and a deep link to the full
findings JSON.
Status parameter accepts completed | stuck | cancelled. Idempotent
when called with the current status. Rejects callers owned by a
different human than the goal owner.
Plumbing:
- New migration 026_goals_completion_summary.sql adds two columns
to goals: completion_summary TEXT, completion_message_id INTEGER
(FK messages.id, ON DELETE SET NULL).
- internal/goals/types.go: new CompletionSummary + CompletionMessageID
fields on Goal struct.
- internal/goals/store.go: Get/List Scan both new columns;
SetCompletion(goalID, status, summary, messageID) helper that
updates status+summary+message_id atomically and populates
completed_at for terminal states.
- internal/goals/service.go: Complete(ctx, goalID, status, summary,
messageID) wraps the store method with legalTransition gating.
legalTransition expanded so draft can jump straight to completed
(no mandatory "active" hop required).
- internal/mcp/goals_tools.go: completeGoalTool definition +
handleCompleteGoal handler. Tool count 6 → 7.
- internal/api/goals_handler.go: surfaces completion_summary,
completion_message_id, and completed_at on both list and detail
endpoints so the Svelte /goals UI can render them.
### 2. Draft → active auto-transition in propose_task_tree (#60)
handleProposeTaskTree now flips the goal from draft to active at the
end. Previously the coordinator would call create_goal +
propose_task_tree and dispatch inspector, but the goal stayed in
draft forever because nothing transitioned it. Now the mere fact
of having a task tree means the goal is active.
Safe: the transition is best-effort and ignores the legal-transition
error when the goal is already beyond draft.
### 3. REVISE round cap (#61)
Two-layer enforcement:
- Server-side: examples/doc-gardener/start.sh drops max_trigger_depth
from 8 to 4. Each REVISE round costs 2 hops (critic→inspector +
inspector→critic), so depth=4 caps the loop at roughly 2 rounds
before the reactor refuses further dispatches.
- Prompt-side: inspector now includes revision_round (starting at
0, incremented when it sees a REVISE: input) in its findings JSON.
Critic reads revision_round and force-FINALs when >= 1. Prompt
explicitly tells the critic to call complete_goal after sending
FINAL, so the goal row gets a proper completion_summary.
### 4. run_task.sh terminal-state detection
Rewrote the poll loop to watch goals.status/completion_summary as
the definitive "done" signal rather than parsing DM bodies. Keeps
a message-based fallback for TRIVIAL/CANNOT paths that don't create
a goal. Treats "Received system trigger..." and "Coalesced
trigger..." as informational (they're `__coalesced__` reactor
synthetic events leaking through the coordinator reply, not real
user-facing output). Bare coordinator replies are terminal only
when no goal was created.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New /api/goals + /api/goals/{id} endpoints serving list + task tree
+ cost rollup + billing breakdown + spawned agents + timeline.
- New Svelte /goals and /goals/[id] pages with sidebar link.
- goals.Service.EvaluateBudget returns a soft/hard verdict; agent
runner posts the 80% warning once and auto-pauses at 100%.
- Auto-quarantine: after each reputation append the agent runner
checks rolling score < 0.3 and writes quarantined_at; reactor
refuses new reactive dispatches to quarantined agents.
- Reactor exposes SetSecretProvider; main.go wires secrets.Store
so reactive subprocess runs inherit user/agent-scoped env vars.
- cli-verifier demonstrates the resource-request protocol: checks
MCPPROXY_API_KEY, posts to #requests + resource_requests row if
missing. New `synapbus secrets set/list` CLI (direct-DB) closes
the loop.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Makes the Web UI reflect what agents are actually doing: reactions
on DMs that trigger a subprocess run, a per-run detail page that
shows the exact prompt the model received and the raw response, and
cross-linked reactive_runs ↔ harness_runs data for a single composite
API call.
Migration 020 (internal/storage/schema/020_harness_run_detail.sql):
ALTER TABLE harness_runs ADD COLUMN reactive_run_id INTEGER;
ALTER TABLE harness_runs ADD COLUMN prompt TEXT;
ALTER TABLE harness_runs ADD COLUMN response TEXT;
CREATE INDEX idx_harness_runs_reactive ON harness_runs(reactive_run_id);
internal/harness:
* ExecRequest.ReactiveRunID — reactor pins the reactive_runs row id
so the observer can JOIN the two tables.
* ExecResult.Prompt / Response — the subprocess harness reads
prompt.txt / response.txt that wrappers write into the workdir,
and runs.Store persists them (capped at 32 KiB each).
* runs.Run struct now has JSON tags — previously the API returned
PascalCase field names that didn't match the Web UI's snake_case
TypeScript types.
* New runs.Store.GetByReactiveRunID for the composite API endpoint.
* Test schema updated to include the new columns.
internal/reactor:
* New ReactionNotifier interface + SetReactionNotifier.
* dispatchHarness now reacts `in_progress` on the triggering DM
before spawning the goroutine.
* runHarness reacts `done` on success, `reject` on failure. The
existing reactionPriority ordering means the terminal reaction
wins for badge display — no need to remove in_progress first.
* dispatchHarness sets ExecRequest.ReactiveRunID.
cmd/synapbus/main.go:
* reactorReactionAdapter: adapts reactions.Service.Toggle to the
reactor's one-shot AddReaction signature.
* HarnessRunsStore wired into the API router config.
internal/api/runs_handler.go — GetRun composite endpoint:
The GET /api/runs/{id} response now returns everything the Web UI
needs to render the run detail page in one call:
{
"run": <reactive_runs row>,
"harness_run": <linked harness_runs row with prompt/response>,
"agent": <current agent snapshot with harness_config_json>,
"trigger_message": <DM that started the run>,
"outgoing_message": <first DM the agent produced after startedAt>
}
The outgoing-message lookup wraps both sides of the created_at
comparison in datetime() so SQLite parses the stored 'YYYY-MM-DD
HH:MM:SS' and the Go-emitted RFC3339 into the same canonical form
before comparing — a raw string compare was silently returning no
rows.
internal/api/router.go: HarnessRunsStore field in RouterConfig, wired
through to NewRunsHandler.
examples/cold-topic-explainer/wrapper.sh:
Writes prompt.txt and response.txt alongside gemini.stdout.raw so
the subprocess harness can capture "what the model saw" and "what
the model said" post-hoc.
web/src/lib/components/MessageList.svelte:
New ReactionPills render below each message body when the message
carries a `reactions` array (already populated by
EnrichMessages/ReactionEnricher on the server side). Makes the
👀 in_progress / ✔ done / ❌ reject lifecycle visible in every DM
view and conversation.
web/src/routes/runs/[id]/+page.svelte (NEW):
New run detail page at /runs/:id with sections:
1. Header strip — agent, status pill, backend badge, trigger
info, duration, tokens in/out, cost, exit code, trace id.
2. Triggering message — body + sender.
3. What the model saw — GEMINI.md / CLAUDE.md from agent snapshot
+ the captured rendered prompt (byte count on each summary
bar, collapsible details).
4. What the model said — captured response, falling back to
logs_excerpt or error_log when unavailable.
5. Outgoing message — body + recipient + status.
6. Metadata — reactive_run.id, harness_run.run_id, backend,
session_id, tokens_cached, k8s_job, agent trigger config.
Styled against the existing dark tailwind system — no design
overhaul, fits the current aesthetic (editorial sectioning,
monospace for code-like content, accent-blue for links,
accent-purple for system-instructions, accent-green for model
output, accent-red for errors).
web/src/routes/runs/+page.svelte: the inline expand panel now has
a "View full details →" link next to the Retry button.
E2E VERIFIED on a live subprocess run:
* Topic: "why does the subprocess harness materialise GEMINI.md
alongside .gemini/settings.json in the per-run workdir?"
* 3 subprocess runs + 3 reactive_runs + 3 harness_runs, all linked.
* message_reactions: 6 rows — in_progress + done for each hop.
* GET /api/runs/1 returns a composite with
harness_run.prompt=883 bytes, harness_run.response=550 bytes,
reactive_run_id=1, trigger_message populated, outgoing_message
populated (decomposer-pro → writer-flash), agent.gemini_md=747
bytes. All keys are snake_case as the Svelte types expect.
Full go test ./... green. `vite build` green. Demo instance still
running on port 18088 for browser verification.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The previous implementation only scanned inbox (pending messages),
so historical conversations with read/done messages were invisible.
New GetDMPartners() does a direct SQL query with window functions
to find all unique DM partners with most recent message preview
and unread count. Historical conversations now always show.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- New API: GET /api/dm/partners — returns DM conversation partners
ordered by most recent message, with unread counts
- Sidebar DM section now shows actual conversation partners (agents
you've exchanged messages with) instead of owned agents
- Each partner shows name, unread badge, clickable to /dm/{name}
- Fixes issue where all DMs were shown mixed in one view
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>
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 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>
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>
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>
Replace the Conversations page with a dedicated search page featuring:
- Large, prominent search input with autofocus
- Collapsible filter panel with time range presets (24h, week, month,
3 months, custom date range), channel filter (comma-separated,
- prefix to exclude), and agent filter (same syntax)
- Search-results-only display with helpful empty state when no search
has been performed
- Remove duplicate "Conversations" heading, rename to "Search"
- Update sidebar nav label and icon to match
Backend changes:
- Add channel, agent, after, before query parameters to
GET /api/messages/search endpoint
- Add Channels, ExcludeChannels, Agents, ExcludeAgents fields to
SearchOptions with SQL filter generation in store.go
- Support include/exclude semantics via - prefix for both channel
and agent filters
API client updated to pass new filter parameters.
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>
- Use human agent's perspective only for unread counts (avoids system agent inflation)
- Replace onDestroy + get() with $effect cleanup in channel/DM pages (Svelte 5 compat)
- Fix notification store to parse array-of-objects API response format
- Add last_read_message_id to DM messages endpoint
- Fix test agent type seeding for GetHumanAgentForUser
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Backend:
- GET /api/notifications/unread returns channel + DM unread counts
- POST /api/notifications/mark-read updates inbox_state for channels/DMs
- SSE broadcaster wired into message send for real-time push
- last_read_message_id added to channel/DM message responses
Frontend:
- Notification store tracks unread counts per channel/DM
- SSE listener for new_message and unread_update events
- Red circular badges in sidebar (Slack-style)
- "New messages" separator line in channel/DM views
- Auto mark-as-read after 2 seconds of viewing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add Offset, After, Before date filters to ReadOptions and SearchOptions.
Add Channel name filter to SearchOptions. Introduce PaginatedMessages,
PaginatedChannels, and PaginatedTasks types with total counts. Update
ReadInbox, SearchMessages, and GetChannelMessages to return paginated
results. Add CountInboxMessages, CountSearchMessages, CountChannelMessages,
and CountTasks store methods. Update all callers in MCP tools, REST API
handlers, and search service. Add comprehensive tests for offset
pagination, date filtering, channel name filtering, and combined
filters with pagination.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix OAuth agent identity: add GetAgentName/GetUserID methods to fositeSession
so the introspection type assertion succeeds and MCP uses the selected agent
(e.g., "Alice Bot") instead of the human username ("alice")
- Fix channel broadcast: create a proper channel message (with channel_id) so
messages sent via MCP send_channel_message appear in the Web UI channel view
- Fix thread replies: pass conversation_id from thread panel so replies go into
the same conversation instead of creating a new one
- Fix OAuth token exchange: normalize localhost→127.0.0.1 in redirect_uri to
match what was stored during authorization (fixes Gemini CLI callback timeout)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix leave channel: handle ErrOwnerCannotLeave with error display, remove
all owned agents from channel
- Close thread panel when navigating between channels/DMs
- Remove Type dropdown from agent registration (agents are always AI;
human accounts created via CLI)
- Fix dashboard showing "Untitled conversation" — now shows last agent name
- Fix "1 msgs" → "1 msg" singular form on dashboard
- Fix conversation detail "-- N messages" → "— N message(s)" with em-dash
- Hide "done" status badge in MessageList and conversation detail
(consistent with DM view behavior)
- Add thread reply buttons and reply count to channel and DM messages
- Add agent selector for multi-agent users in channel and DM compose
- Add "Join Channel" prompt for non-members in channel compose area
- Show "(you)" indicator on channel member list for owned agents
- Add agent detail page with messages endpoint
- Improve release workflow and Dockerfile
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Channel pages now show message feed with compose bar instead of
just member lists. Messages display with agent avatars, names,
and timestamps. Collapsible info panel shows channel details.
- New /dm/[name] route for direct message conversations between
agents with from→to indicators and status badges.
- Sidebar DM links now navigate to /dm/{name} instead of agent
edit forms.
- Backend: add GetChannelMessages and GetDMMessages store/service
methods with corresponding API handlers and routes.
- Makefile: build target now depends on web target so binary
always embeds latest UI assets.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move module path from github.com/smart-mcp-proxy/synapbus to
github.com/synapbus/synapbus across all Go imports (47 files).
Add constellation logo options generated via FLUX 1.1 Pro.
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>
Add complete Web UI infrastructure:
Go backend:
- REST API handlers for messages, agents, channels (internal/api/)
- SSE hub for real-time event streaming
- Session-to-owner middleware bridging auth sessions to API context
- SPA file server with go:embed for static assets
- GetMessageByID on MessagingService, RevokeKey on AgentService
- Updated router with RouterConfig for full service wiring
Svelte 5 SPA (web/):
- SvelteKit with static adapter for SPA mode
- Tailwind CSS with dark mode (class-based, localStorage persisted)
- API client with auto-redirect on 401
- SSE client with exponential backoff reconnect
- Pages: Login, Dashboard, Conversations, Channels, Agents, Settings
- Components: Sidebar, Header, MessageList, ComposeForm, AgentCard, TraceViewer
- Responsive layout with mobile sidebar toggle
Build:
- Placeholder index.html in internal/web/dist/ for go:embed compilation
- Updated Makefile web target to copy build output
- All existing Go tests pass, CGO_ENABLED=0
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add file attachment support with SHA-256 content-addressable storage,
automatic deduplication, MIME detection, and garbage collection for
orphaned files. Includes MCP tools (upload_attachment, download_attachment,
gc_attachments), REST API endpoints for Web UI, and comprehensive tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add comprehensive trace logging and observability features:
- Enhanced trace store with owner-scoped queries, filtering (agent, action,
time range), pagination, streaming export, and retention cleanup
- REST API endpoints: GET /api/traces (list with filters), GET /api/traces/export
(streaming JSON/CSV), GET /api/traces/stats (action counts)
- Owner isolation enforced at every layer (store, API, tests)
- Hand-rolled Prometheus metrics (pure Go, zero CGO): traces_total,
traces_by_action, errors_total, active_agents at GET /metrics
- Configurable slog JSON handler with --log-level flag
- Request ID middleware for cross-referencing logs and traces
- Batch trace writing (64 entries or 100ms flush interval)
- Background retention cleanup via --trace-retention flag
- SQL migration 002 adds owner_id column and composite indexes
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
