Adds everything needed to run a real multi-Gemini-model reactive agent
loop end-to-end on SynapBus.
internal/harness/subprocess/config.go:
* AgentConfig.GeminiMD — content of workdir/GEMINI.md
* MaterialiseAgentConfig writes GEMINI.md AND workdir/.gemini/settings.json
when gemini_md is set. The settings file carries the same mcp_servers
list as .mcp.json (so a Gemini child running from the workdir gets
the exact MCP surface the operator configured, not the user's
~/.gemini/settings.json).
* 2 new config_test cases: GEMINI.md + .gemini/settings.json round
trip, GEMINI.md with empty mcp_servers still writes the settings
file (explicitly clearing any inherited home config).
internal/harness/registry.go — BUG FIX:
Resolve() now honours agent.HarnessName (explicit selection) BEFORE
the inference chain, matching the reactor's own agentBackendKind
policy. Previously, when multiple backends were registered,
Resolve would pick "webhook" for every non-K8s agent — even when the
agent's HarnessName was "subprocess" — because the original fallback
chain put webhook first. This is why the first cold-topic-explainer
run failed with "webhook: agent has no webhook config". Discovered
during e2e testing.
internal/admin/socket.go + cmd/synapbus/admin.go:
New `messages.send` admin command (socket + CLI). Sends a DM as any
agent through the messaging service, bypassing the REST/MCP auth
layers. Local-only via the admin Unix socket, so the threat model is
"whoever can reach the socket is already admin".
CLI:
synapbus messages send --from X --to Y --body "..." [--priority N]
synapbus messages send --from X --to Y --body-file path
echo "..." | synapbus messages send --from X --to Y
Used by the harness shell wrappers (so Gemini subprocess agents can
DM each other) and by run_task.sh (to kick off a chain as a human
user without implementing the REST session flow).
examples/cold-topic-explainer/ (NEW):
Runnable 3-agent Gemini demo that exercises the subprocess harness,
reactive triggers, recursive update, and all the preconditions (depth,
budget, cooldown) end-to-end on a separate isolated synapbus instance.
Layout:
README.md — usage + troubleshooting + cost notes
start.sh — builds synapbus, launches on port 18088 with
./data, creates user + agents + harness configs,
marks agents reactive via sqlite3
run_task.sh — sends initial DM algis → decomposer-pro, polls
reactive_runs + messages for the FINAL: reply,
prints the result or dumps reactive_runs on
timeout for debugging
stop.sh — SIGTERM + 5s grace + SIGKILL fallback
wrapper.sh — shared subprocess local_command: reads
message.json + GEMINI.md, calls gemini headless
with --approval-mode yolo, strips the
"MCP issues detected" noise prefix, routes the
cleaned response to the next agent via
`synapbus messages send` over the admin socket
configs/
decomposer-pro.json — gemini-3.1-pro-preview
(gemini-2.5-pro is currently capacity-
exhausted on Google's side)
writer-flash.json — gemini-2.5-flash
critic-lite.json — gemini-2.5-flash-lite
.gitignore — data/, bin/, synapbus.log, .synapbus.pid
The wrapper does NOT rely on gemini's MCP tool-calling (which was
unreliable in testing). Gemini is used as a pure text generator; the
shell decides routing based on AGENT_ROLE:
- decomposer → NEXT_AGENT (writer)
- writer → NEXT_AGENT (critic)
- critic → OWNER_AGENT if response starts with FINAL:,
REVISE_AGENT otherwise
E2E VERIFICATION (real run, real Gemini, not a mock):
Topic: "how does SynapBus unify message delivery, reactive agent
triggers, and harness runs on a single SQLite database?"
Result (from data/synapbus.db after one successful run):
harness_runs:
#1 decomposer-pro subprocess success 106s
#2 writer-flash subprocess success 155s
#3 critic-lite subprocess success 10s
reactive_runs: 3 rows, all succeeded, trigger_from chain:
algis → decomposer-pro → writer-flash → critic-lite
messages:
#1 algis → decomposer-pro (topic)
#2 decomposer-pro → writer-flash (Q1/Q2/Q3 breakdown)
#3 writer-flash → critic-lite (3-paragraph draft)
#4 critic-lite → algis (FINAL: + polished 3-paragraph explainer)
Critic converged in one pass (all scores ≥ 8), so the writer↔critic
refinement loop didn't need to recurse — but the plumbing for it
(REVISE: branch in wrapper.sh, depth limit in reactor) is wired and
ready. Flipping the critic's acceptance bar exercises the recursion.
Full `go test ./...` remained green through all changes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Makes the subprocess backend fully self-contained: each agent carries
its instructions, MCP servers, skills, and subagents in its
harness_config_json column, viewable in the Web UI, editable via CLI.
internal/harness/subprocess/config.go (NEW):
AgentConfig struct with optional fields:
- claude_md → workdir/CLAUDE.md
- agents_md → workdir/AGENTS.md
- mcp_servers → workdir/.mcp.json (Claude Code format)
- skills → workdir/.claude/skills/<name>/SKILL.md
- subagents → workdir/.claude/agents/<name>.md
- env → layered into child env (after k8s_env_json,
before caller overrides)
ParseAgentConfig tolerates empty / returns error on invalid JSON.
MaterialiseAgentConfig writes all artifacts into the workdir with
path-traversal sanitisation on skill/subagent names.
subprocess.Harness.Execute now calls Parse + Materialise before exec,
so an agent's declarative config is on disk by the time the child
CLI's cwd lookup fires. buildEnv takes the parsed config and overlays
cfg.Env on top of k8s_env_json.
Tests:
config_test.go — 6 cases: empty, invalid JSON, full round-trip,
materialise writes all artefacts, empty is a no-op, skill names
are sanitised against "../escape" / "/etc/passwd", mcp entries
without a name are dropped.
subprocess_test.go — 2 new e2e cases: agent with CLAUDE.md + mcp
servers + skills + env sees all of them from inside the child via
cat/echo; invalid harness_config_json surfaces as Execute error.
internal/agents/store.go:
AgentStore gains UpdateHarnessConfig(ctx, name, harnessName,
localCommand, harnessConfigJSON). Empty strings leave a field
unchanged; literal "-" clears (sets to NULL). Returns sql.ErrNoRows
on missing agent. AgentService exposes Store() so admin handlers
can reach it without adding a full service method for a
config-set-style operation.
store_test.go: 6-subcase test covers set-all, partial update, clear,
unknown agent, and no-field no-op.
internal/admin/socket.go:
Two new admin commands:
harness.config_get {agent_name} → {harness_name, local_command,
harness_config_json, harness_config (parsed), parse_error?}
harness.config_set {agent_name, harness_name?, local_command?,
harness_config_json?} → updated fields
config_set validates JSON shape before calling the store; null /
"-" literals clear the column.
cmd/synapbus/admin.go:
New top-level `harness config` command group:
synapbus harness config get --agent <name> [--raw]
synapbus harness config set --agent <name>
[--harness-name subprocess]
[--local-command '["claude","--print"]']
[--file config.json] # or pipe from stdin
[--clear]
synapbus harness config edit --agent <name>
# fetches current config, opens $VISUAL/$EDITOR/vi,
# validates JSON on save, writes back via config_set
web/src/routes/agents/[name]/+page.svelte:
New read-only "Harness" panel on the agent detail page:
- Resolved backend badge (explicit or inferred from k8s_image /
local_command / harness_config_json.url)
- Grid summary: CLAUDE.md size, AGENTS.md size, MCP server count,
skills count
- Collapsible details for CLAUDE.md, AGENTS.md, each MCP server
(name / type / url|command / header count), skill filenames,
subagent filenames, env vars
- Footer hint showing the CLI edit command
No edit controls — editing is CLI-only by design (safer, fits an
ops-heavy workflow).
Verified: full project test suite (40+ packages including integration
tests) plus `vite build` of the Svelte app all green; `go vet ./...`
clean; the existing TestSubprocess_Execute_MaterialisesHarnessConfig
e2e test proves the round-trip from harness_config_json → workdir →
child process works end-to-end.
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>
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>
Switch Docker runtime from scratch to alpine:3.19 so kubectl exec works
for admin CLI operations. Add `synapbus channels create` and
`synapbus channels join` CLI commands with corresponding admin socket
handlers. Change default socket path to /data/synapbus.sock (absolute).
Also add Helm envFrom support and NodePort configuration.
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>
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>
