Root cause: ConsolidatorWorker.tryDispatch / launchOne incremented
the per-(owner, day) `jobs_started` counter immediately after
JobsStore.Create, BEFORE the dispatch flip succeeded. When the
subsequent steps fail (token issue, agent lookup, dispatch flip
race) the job row is Completed as `failed` but `jobs_started`
remains incremented — and the error paths never call
RecordCompletion, so `jobs_failed` stays flat while `jobs_started`
drifts upward.
Over hours/days, owners whose dispatches fail consistently (e.g.
owner_id=2 in the kubic deployment, hitting one of the harness
failure modes from commit bfb2551) accumulate phantom
`jobs_started` until the default DreamDailyJobLimit=100 trips. From
that point every tick logs `circuit broken … reason=jobs_exceeded`
for all four job types, even though no real jobs ran — and the
counter never decays until midnight UTC.
Fix: move `usage.RecordStart(...)` to AFTER a successful
`jobs.Dispatch(...)` in both tryDispatch (consolidator.go:518)
and launchOne (consolidator.go:455). Now only dispatches that
actually transitioned a row to `dispatched` count against the
daily-job-limit gate.
Test: TestConsolidator_PreDispatchFailureDoesNotBurnJobsStarted
seeds DreamDailyJobLimit=2, makes the agent lookup fail, calls
ForceRun three times, asserts jobs_started stays 0 and the gate
still allows. Verified to fail without the fix
(jobs_started=2 / reason=jobs_exceeded) and pass with it.
Counterpart TestConsolidator_DispatchSuccessIncrementsJobsStarted
asserts jobs_started=1 on a real successful dispatch so the
counter still feeds the gate correctly.
Operational note: this prevents future inflation. Existing stuck
rows for owner_id=2 in today's `memory_dream_usage` bucket need a
one-shot SQL fix —
UPDATE memory_dream_usage
SET jobs_started = jobs_succeeded + jobs_failed
WHERE date = date('now')
AND owner_id = '2';
or simply wait for the next UTC-midnight reset.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drain-on-demand: SYNAPBUS_DREAM_PARALLEL (default 1) and
`synapbus memory dream-run --parallel N` fan out N concurrent
dream-agent k8s Jobs per (owner, job_type) in one shot. Set
high (e.g. 8) to drain backlog quickly, then back to 1 for normal
hourly operation.
Schema:
- migration 030_dream_parallelism: adds slot INTEGER NOT NULL DEFAULT 0
to memory_consolidation_jobs. Drops + recreates the partial unique
in-flight index as (owner, job_type, slot) so slots 0..N-1 each hold
one in-flight job independently.
Stores:
- JobsStore.CreateOnSlot + CreateNextAvailableSlot.
- ConsolidatorWorker.ForceRunN dispatches N parallel jobs through the
existing launchOne path (extracted from ForceRun).
- core_rewrite coerces to N=1 regardless of the knob — per-(owner,
agent) blob is wholesale-replace and concurrent rewrites would race.
Three bug fixes discovered while bringing the parallel path up on
kubic:
1. k8s Job names collided on rapid relaunch because runner.go used
"synapbus-<agent>-<msg_id>", and dream dispatches have msg_id=0.
Now appends a unique (timestamp%1e6, 4-byte random) suffix when
msg_id is zero; historical "synapbus-<agent>-<id>" prefix preserved.
2. memory_list_unprocessed didn't actually exclude already-refined
messages — the contract said it should, the implementation
returned the same oldest-50 every cycle. The dream agent kept
re-refining the same set: 221 refines links touched only 55
unique dst messages, so progress flat-lined. Added the
NOT IN (refines/duplicate_of/superseded_by) filter and a
from_agent NOT LIKE 'dream:%' clause so the agent never refines
its own reflections.
3. The k8sjob harness was constructed with nil Waiter in main.go,
so every dream dispatch failed instantly with "k8sjob: no Waiter
configured". Now builds a ClientsetWaiter from the in-cluster
clientset.
Plus admin/server.go gets DreamRunN closure + DefaultDreamParallel
(sourced from MemoryConfig.DreamParallel). admin/socket.go
handleMemoryDreamRun accepts `parallel` arg and returns job_ids[].
CLI admin command grows --parallel N flag.
Live evidence from kubic (image v0.21.0-amd64):
1 CLI call with --parallel 8 produced 8 job rows on slots 0..7,
spawned 8 distinct k8s Jobs with unique suffixes, retired ~86
unprocessed messages in <1 min (vs ~10/cycle for the buggy
serial version pre-fix-2).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Backend (Go, in this commit):
- migration 029_memory_dream_usage: per (date, owner) counters for
tokens_in/out, jobs_started/succeeded/failed/circuit_broken
- DreamUsageStore + UsageGate (internal/messaging/dream_usage.go).
Gate inspects today's usage against new env knobs:
- SYNAPBUS_DREAM_RECENT_WINDOW (default 336h / 14d)
- SYNAPBUS_DREAM_DAILY_TOKEN_LIMIT_IN (default 1M)
- SYNAPBUS_DREAM_DAILY_TOKEN_LIMIT_OUT (default 200k)
- SYNAPBUS_DREAM_DAILY_JOB_LIMIT (default 100)
- Consolidator now bounds watermarks + core_rewrite eligibility by the
recency window. core_rewrite skipped for owners with no in-window
activity. ForceRun honors the breaker.
- Recency fallback in BuildContextPacket + memory_list_unprocessed now
accept RecentWindowDays so injection and dream queries see the same
14d slice.
- Prometheus metrics registered (internal/metrics/metrics.go):
synapbus_dream_jobs_total{owner,job_type,status},
synapbus_dream_tokens_total{owner,direction},
synapbus_dream_job_duration_seconds{owner,job_type},
synapbus_dream_circuit_broken_total{owner,reason},
synapbus_injection_packets_total{tool},
synapbus_injection_memories_per_packet{tool},
synapbus_injection_packet_chars{tool},
synapbus_injection_skipped_total{tool,reason}.
- deploy/kubic/deployment.yaml: liveness/readiness timeoutSeconds: 1→5
(root-causes the "connection refused" mcpproxy errors at 13:02 today —
/readyz occasionally exceeded 1s under dream-worker tick load, so the
pod fell out of the Service endpoints intermittently).
Dream-claude agent (Python, in /dream-agent/):
- dream_runner.py uses claude-agent-sdk 0.1.48 to drive Claude Code
against SynapBus's MCP server. MCP transport carries
Authorization: Bearer <api_key> AND X-Synapbus-Dispatch-Token from env
via the SDK's McpHttpServerConfig.headers field — confirmed supported.
- Tools restricted via allowed_tools to mcp__synapbus__memory_*.
- Final JSON envelope reports tokens_in/out so harness.Usage stays
populated and the circuit breaker can count consumption.
- Dockerfile builds linux/amd64 at 189 MB, mirroring searcher's
agents/universal recipe.
- k8s-job-template.yaml: backoffLimit 0, ttl 600s, 512Mi/1CPU,
Anthropic credentials via secret-ref.
Grafana dashboard (deploy/kubic/grafana/):
- dream-dashboard.json — 14 panels across 5 rows (dream activity,
token usage vs limit, circuit breaker, injection layer, MCP
transport health), all templated to ${DS_PROMETHEUS}.
- import.sh: resolves the cluster's Prometheus DS uid and POSTs the
dashboard via Grafana API.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Background ConsolidatorWorker dispatches consolidation work to a Claude
Code agent through harness.Harness.Execute (NOT via system DMs — per
feedback_system_dm_no_trigger.md) with a one-time 15m dispatch token.
The dispatched agent uses six new MCP tools, all token-gated and
recording every action to memory_consolidation_jobs.actions JSON.
Stores:
- memory_links.go (+ test): typed edges with actor-prefix reserved-type
guard; AddConsolidationLink bypass for memory_mark_duplicate /
memory_supersede (their contractual writers).
- memory_pins.go (+ test): owner pin overlay, bypasses score floor.
- memory_status.go: queries the memory_status view.
- consolidation_jobs.go: Create / Dispatch / Lease / AppendAction /
Complete with ErrJobAlreadyInFlight via partial unique index.
- auto_links.go: MessageListener generating mention / reply_to /
channel_cooccurrence links automatically on send.
Worker:
- consolidator.go (+ test): ticker pattern modeled on StalemateWorker.
Watermark trigger for link_gen / dedup_contradiction; daily 03:00
UTC for sleep-time core rewrite. Wallclock budget via harness Budget.
Global semaphore gates concurrent owners. Mocked-harness test asserts
no system DM is ever sent.
- consolidator_prompts.go: four job-type prompts passed via env to the
dispatched agent.
MCP tools (internal/mcp/memory_tools.go + test):
- memory_list_unprocessed, memory_write_reflection, memory_rewrite_core,
memory_mark_duplicate, memory_supersede, memory_add_link.
- Full error-code matrix tested per contracts/mcp-memory-tools.md.
- Registered only when SYNAPBUS_DREAM_ENABLED=1.
Injection extensions:
- search/injection.go: pin overlay applied after retrieval; status
filter drops soft_deleted / superseded unless pinned. New
PinProvider, StatusProvider, MessageLookup hooks on InjectionOpts.
Wiring:
- cmd/synapbus/main.go: stores constructed, AutoLinkListener attached
to MessagingService, mcpSrv.SetDream wired, ConsolidatorWorker
start/stop, admin DreamRun closure.
- cmd/synapbus/admin.go: synapbus memory dream-run --owner --job
socket-RPC command (forces a single job bypassing trigger).
Cycle workarounds (documented in code):
- messaging.DreamAgent / HarnessDispatcher are local interfaces (the
agents and harness packages import messaging, not the reverse).
main.go wraps the real types via adapter structs.
Stubbed:
- Cron expression parsing (DreamDeepCron). Hardcoded daily 03:00 UTC.
Adding robfig/cron deferred to keep no-new-deps.
Pre-existing reactor test failures (5) are unchanged; confirmed
pre-020 via stash check.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wraps eligible MCP tool handlers (my_status, send_message, search,
execute; get_replies excluded as pure metadata) with a middleware that
appends relevant_context to the JSON response. Retrieval reuses the
existing search.Service hybrid pipeline; owner scoping filters out
memories from other owners' agents (SC-008). Pin overlay is a marked
TODO for US3.
Components:
- internal/search/injection.go (+ test): BuildContextPacket with token
budget greedy fill, score floor, truncation flag, CoreMemoryProvider
interface stubbed for US2.
- internal/mcp/injection_wrap.go (+ test): WrapInjection middleware,
registered via SetInjection on the existing handler.
- internal/mcp/injection_e2e_test.go: adversarial cross-owner test
asserts H1 cannot see H2's memories on any wrapped tool.
- internal/messaging/memory_injections.go (+ test): 24h audit ring,
hourly cleanup tick wired into stalemate worker.
Discovery during impl: claim_messages/read_inbox/read_channel live as
actions inside the execute bridge, not as registered top-level MCP
tools. They inherit injection through the execute wrapper.
This commit also bundles pre-existing working-tree changes for the
027 "remove approval noise" cleanup (migration 027, design doc,
removal of reminder/escalate logic from stalemate worker, related
trims in goals_tools.go and tools_hybrid.go). The two changes touch
the same files (stalemate.go, tools_hybrid.go) and bundling them
keeps history readable.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds the SQL substrate (6 tables + memory_status view) and the helpers
every user story depends on:
- migration 028_memory_consolidation.sql + smoke test
- internal/messaging/memory_config.go (env-flag plumbing)
- internal/messaging/dispatch_tokens.go (32-byte rand, 15m TTL, single-job-bound)
- internal/messaging/memory_channels.go (open-brain / reflections-* / is_memory flag)
- internal/agents/owner.go (OwnerFor with sentinel errors)
Deviations from spec, all documented in code:
- owner_id is stored as INTEGER FK to users; OwnerFor converts to the
string scope-key the new tables use.
- MemoryChannel is a local struct to avoid an import cycle between
internal/channels and internal/messaging.
- channels.metadata column does not exist yet; IsMemoryChannel honors
it conditionally so MemoryChannelIDs can extend trivially when added.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
read_inbox now requires explicit MarkRead (default false). Worker-queue callers
opt in. Resolves bugs-synapbus #30674 where consecutive identical calls returned
0 the second time and produced inconsistent views with the claim/process/done
loop and StalemateWorker.
failTimedOutProcessing UPDATE now re-checks claimed_at < cutoff so a fresh
re-claim between SELECT and UPDATE can't be stomped to failed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Words like "to", "from", "and", "or", "not", "near" are FTS5 operators
and caused SQL errors (e.g. "no such column: to") when passed as search
queries. sanitizeFTS5Query() wraps each token in double quotes so they
are treated as literal phrase tokens by SQLite's FTS5 MATCH operator.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Removed the 'peer NOT IN (owned)' filter that excluded all owned agents.
Since all agents (algis, research-*, social-commenter) are owned by the
same user, the filter was hiding all inter-agent DMs. Now shows all
unique DM partners regardless of ownership.
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>
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>
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>
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>
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>
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>
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>
- 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>
Parse @agentname patterns in channel message body. Mentioned agents
(who are channel members, excluding sender) get mention=true flag in
their inbox notification metadata. Channel message metadata includes
mentioned_agents list for all recipients.
- mentions.go: regex parser with email exclusion, dedup, 22 test cases
- BroadcastMessage: metadata now uses json.Marshal, includes mentions
- Tests verify mention flag, self-mention exclusion, non-member skip
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Agents could send channel messages but had no MCP tool to read them.
Also, search_messages only searched DMs (to/from agent), missing channel
messages entirely. Now SearchMessages includes channel messages where
the agent is a member.
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>
Implements the foundational layer that all SynapBus features depend on:
- internal/storage: SQLite connection manager (WAL mode, busy_timeout,
foreign_keys) and embedded migration runner using modernc.org/sqlite
- internal/messaging: MessagingService with send, read inbox, claim,
mark done/failed, and FTS5 search. SQLite-backed MessageStore with
conversation auto-creation and read/unread tracking via inbox_state.
- internal/agents: AgentService with register, authenticate (bcrypt),
update, deregister, discover by capability. HTTP auth middleware.
- internal/mcp: MCP server using mark3labs/mcp-go with 9 registered
tools (send_message, read_inbox, claim_messages, mark_done,
search_messages, register_agent, discover_agents, update_agent,
deregister_agent). SSE transport, health endpoint, connection manager.
- internal/trace: Async trace recorder with buffered channel for
recording agent actions to SQLite traces table.
- cmd/synapbus: Updated main.go wiring storage, migrations, services,
MCP server, chi router, and graceful shutdown.
All code compiles with CGO_ENABLED=0. Full test suite passes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
