feat(loop): integrate evolution, memory, and mid-loop critique

src/core/__tests__/trigger-auth.test.ts

@@ -19,7 +19,7 @@
 	let server: ReturnType<typeof Bun.serve>;
 	let baseUrl: string;
 
-	beforeAll(() => {
+	beforeAll(async () => {
 		// Back up the existing mcp.yaml so we can restore it after tests
 		if (existsSync(mcpConfigPath)) {
 			originalMcpYaml = readFileSync(mcpConfigPath, "utf-8");
@@ -38,11 +38,8 @@
 		mkdirSync("config", { recursive: true });
 		writeFileSync(mcpConfigPath, YAML.stringify(mcpConfig), "utf-8");
 
-		// Start server with a random port
-		server = startServer({ name: "test", port: 0, role: "base" } as never, Date.now());
-		baseUrl = `http://localhost:${server.port}`;
-
-		// Wire trigger deps with a mock runtime
+		// Wire trigger deps before starting the server so the /trigger
+		// handler is ready on the first request.
 		setTriggerDeps({
 			runtime: {
 				handleMessage: async () => ({
@@ -52,6 +49,15 @@
 				}),
 			} as never,
 		});
+
+		// Start server after deps are wired. Use server.url (Bun guarantees
+		// it is populated once serve() returns) instead of manually building
+		// the URL from server.port, which can race in CI environments.
+		server = startServer({ name: "test", port: 0, role: "base" } as never, Date.now());
+		baseUrl = server.url.origin;
+
+		// Ensure the server is accepting connections before tests run.
+		await fetch(`${baseUrl}/health`);
 	});
 
 	afterAll(() => {
@@ -70,7 +76,7 @@
 			headers: { "Content-Type": "application/json" },
 			body: triggerBody,
 		});
 		expect(res.status).toBe(401);
 		const json = (await res.json()) as { status: string; message: string };
 		expect(json.message).toContain("Missing");
 	});
@@ -84,7 +90,7 @@
 			},
 			body: triggerBody,
 		});
 		expect(res.status).toBe(401);
 	});
 
 	test("rejects read-only token (insufficient scope)", async () => {
@@ -96,7 +102,7 @@
 			},
 			body: triggerBody,
 		});
 		expect(res.status).toBe(403);
 		const json = (await res.json()) as { status: string; message: string };
 		expect(json.message).toContain("operator");
 	});
@@ -110,7 +116,7 @@
 			},
 			body: triggerBody,
 		});
 		expect(res.status).toBe(200);
 		const json = (await res.json()) as { status: string };
 		expect(json.status).toBe("ok");
 	});
@@ -124,6 +130,6 @@
 			},
 			body: triggerBody,
 		});
 		expect(res.status).toBe(200);
 	});
 });

src/db/__tests__/migrate.test.ts

@@ -36,7 +36,7 @@ describe("runMigrations", () => {
 		runMigrations(db);
 
 		const migrationCount = db.query("SELECT COUNT(*) as count FROM _migrations").get() as { count: number };
-		expect(migrationCount.count).toBe(12);
+		expect(migrationCount.count).toBe(13);
 	});
 
 	test("tracks applied migration indices", () => {
@@ -48,6 +48,6 @@ describe("runMigrations", () => {
 			.all()
 			.map((r) => (r as { index_num: number }).index_num);
 
-		expect(indices).toEqual([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]);
+		expect(indices).toEqual([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]);
 	});
 });

src/db/schema.ts

@@ -126,4 +126,6 @@ export const MIGRATIONS: string[] = [
 	// Appended, never inserted mid-array: existing deployments have already
 	// applied migrations 0–10, so the new column must land at index 11.
 	"ALTER TABLE loops ADD COLUMN trigger_message_ts TEXT",
+
+	"ALTER TABLE loops ADD COLUMN checkpoint_interval INTEGER",
 ];

src/evolution/judges/client.ts

@@ -10,6 +10,19 @@ import {
 	type VotingStrategy,
 } from "./types.ts";
 
+/** Thrown when the API call succeeds but structured output parsing fails. Carries token usage so cost can still be tracked. */
+export class JudgeParseError extends Error {
+	constructor(
+		message: string,
+		public readonly inputTokens: number,
+		public readonly outputTokens: number,
+		public readonly costUsd: number,
+	) {
+		super(message);
+		this.name = "JudgeParseError";
+	}
+}
+
 let _client: Anthropic | null = null;
 
 function getClient(): Anthropic {
@@ -58,14 +71,19 @@ export async function callJudge<T>(options: {
 	});
 
 	const parsed = message.parsed_output;
-	if (!parsed) {
-		throw new Error(`Judge returned no structured output (stop_reason: ${message.stop_reason})`);
-	}
-
 	const inputTokens = message.usage.input_tokens;
 	const outputTokens = message.usage.output_tokens;
 	const costUsd = estimateCost(options.model, inputTokens, outputTokens);
 
+	if (!parsed) {
+		throw new JudgeParseError(
+			`Judge returned no structured output (stop_reason: ${message.stop_reason})`,
+			inputTokens,
+			outputTokens,
+			costUsd,
+		);
+	}
+
 	// Extract verdict and confidence from the parsed data if present
 	const data = parsed as Record<string, unknown>;
 	const verdict = (data.verdict as "pass" | "fail") ?? "pass";

src/index.ts

@@ -116,8 +116,9 @@ async function main(): Promise<void> {
 		runtime.setRoleTemplate(activeRole);
 	}
 
+	let contextBuilder: MemoryContextBuilder | undefined;
 	if (memory.isReady()) {
-		const contextBuilder = new MemoryContextBuilder(memory, memoryConfig);
+		contextBuilder = new MemoryContextBuilder(memory, memoryConfig);
 		runtime.setMemoryContextBuilder(contextBuilder);
 	}
 
@@ -160,7 +161,17 @@ async function main(): Promise<void> {
 
 	let mcpServer: PhantomMcpServer | null = null;
 	let scheduler: Scheduler | null = null;
-	const loopRunner = new LoopRunner({ db, runtime });
+	const postLoopDeps =
+		evolution || memory.isReady()
+			? {
+					evolution: evolution ?? undefined,
+					memory: memory.isReady() ? memory : undefined,
+					onEvolvedConfigUpdate: evolution
+						? (config: ReturnType<EvolutionEngine["getConfig"]>) => runtime.setEvolvedConfig(config)
+						: undefined,
+				}
+			: undefined;
+	const loopRunner = new LoopRunner({ db, runtime, memoryContextBuilder: contextBuilder, postLoopDeps });
 	try {
 		mcpServer = new PhantomMcpServer({
 			config,