feat(harness): GEMINI.md support + cold-topic-explainer example

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>
2026-04-13 22:01:36 +03:00
parent b8a70bfe66
commit 04e4e3ca37
14 changed files with 776 additions and 16 deletions
@@ -544,7 +544,70 @@ func addAdminCommands(rootCmd *cobra.Command) {
 	messagesPurgeCmd.Flags().StringVar(&messagesPurgeAgent, "agent", "", "Delete messages from/to this agent")
 	messagesPurgeCmd.Flags().StringVar(&messagesPurgeChannel, "channel", "", "Delete messages in this channel")

-	messagesCmd.AddCommand(messagesListCmd, messagesSearchCmd, messagesPurgeCmd)
+	// `messages send` — bypasses MCP/REST auth; used by harness shell
+	// wrappers and demo scripts to post DMs as a named agent.
+	var (
+		messagesSendFrom     string
+		messagesSendTo       string
+		messagesSendBody     string
+		messagesSendBodyFile string
+		messagesSendSubject  string
+		messagesSendPriority int
+	)
+	messagesSendCmd := &cobra.Command{
+		Use:   "send",
+		Short: "Send a DM as a given agent (admin — bypasses auth)",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			body := messagesSendBody
+			if messagesSendBodyFile != "" {
+				b, err := os.ReadFile(messagesSendBodyFile)
+				if err != nil {
+					return fmt.Errorf("read --body-file: %w", err)
+				}
+				body = string(b)
+			} else if body == "" {
+				// Read body from stdin if piped.
+				stat, _ := os.Stdin.Stat()
+				if (stat.Mode() & os.ModeCharDevice) == 0 {
+					b, err := io.ReadAll(os.Stdin)
+					if err != nil {
+						return fmt.Errorf("read stdin: %w", err)
+					}
+					body = string(b)
+				}
+			}
+			if body == "" {
+				return fmt.Errorf("--body, --body-file, or stdin is required")
+			}
+			reqArgs := map[string]any{
+				"from": messagesSendFrom,
+				"to":   messagesSendTo,
+				"body": body,
+			}
+			if messagesSendSubject != "" {
+				reqArgs["subject"] = messagesSendSubject
+			}
+			if messagesSendPriority > 0 {
+				reqArgs["priority"] = messagesSendPriority
+			}
+			resp, err := adminRequest("messages.send", reqArgs)
+			if err != nil {
+				return err
+			}
+			printJSON(resp["data"])
+			return nil
+		},
+	}
+	messagesSendCmd.Flags().StringVar(&messagesSendFrom, "from", "", "Sender agent name")
+	messagesSendCmd.Flags().StringVar(&messagesSendTo, "to", "", "Recipient agent name (for DMs)")
+	messagesSendCmd.Flags().StringVar(&messagesSendBody, "body", "", "Message body")
+	messagesSendCmd.Flags().StringVar(&messagesSendBodyFile, "body-file", "", "Read body from file")
+	messagesSendCmd.Flags().StringVar(&messagesSendSubject, "subject", "", "Optional conversation subject")
+	messagesSendCmd.Flags().IntVar(&messagesSendPriority, "priority", 5, "Priority 1-10")
+	_ = messagesSendCmd.MarkFlagRequired("from")
+	_ = messagesSendCmd.MarkFlagRequired("to")
+
+	messagesCmd.AddCommand(messagesListCmd, messagesSearchCmd, messagesPurgeCmd, messagesSendCmd)

 	// ----- channels commands -----
 	channelsCmd := &cobra.Command{