Separate short review context from full supervisor orientation

test/native-intercom.test.ts

@@ -52,7 +52,7 @@ it("runs a forked Pi supervisor and receives its exact instruction in another Pi
 		let body = "";
 		for await (const chunk of request) body += chunk;
 		const input = JSON.parse(body);
-		const latest = input.messages.at(-1);
+		const latest = input.messages.filter((message: any) => !JSON.stringify(message.content).includes("Full active plan:")).at(-1);
 		const steer = latest.role === "user" && JSON.stringify(latest.content).includes("The worker stopped.");
 		if (steer) supervisorTools = input.tools.map((tool: any) => tool.function.name);
 		response.writeHead(200, { "content-type": "text/event-stream" });

test/plan-view.test.ts

@@ -0,0 +1,18 @@
+import { expect, it } from "vitest";
+import { planViews } from "../src/plan-view.js";
+
+it("keeps outcome, preferences and discriminators without tasks or history", () => {
+	const plan = "# Outcome\nBeat random, not just plot it.\n## User preferences\nKeep costs low.\n## Goals\n1. [ ] goal: repair\n  - discriminator: beats random\n  - subtle failure mode: plot exists but result fails\n  - tasks:\n    1. [x] draw plot\n  - evidence:\n    - old output\n2. [ ] goal: confirm\n## Task list\n- [ ] run it\n## Appendix\nunapproved idea";
+	const views = planViews(plan);
+	for (const text of ["Beat random", "Keep costs low", "goal: repair", "discriminator: beats random", "subtle failure mode", "goal: confirm"]) expect(views.short).toContain(text);
+	for (const text of ["draw plot", "old output", "run it", "unapproved idea"]) expect(views.short).not.toContain(text);
+	expect(views.long).toContain("draw plot");
+	expect(views.long).toContain("old output");
+	expect(views.long).not.toContain("unapproved idea");
+});
+
+it("stops at history and preserves a manual goal tick", () => {
+	const view = planViews("# Plan\n1. [x] goal: result\n## Log\n1. [ ] goal: historical");
+	expect(view.short).toContain("[x] goal: result");
+	expect(view.long).not.toContain("historical");
+});

test/supervisor-session.test.ts

@@ -133,19 +133,20 @@ describe("visible supervisor session", () => {
 		try {
 			writeFileSync(join(cwd, "plan.md"), "# Outcome\nBeat random\n1. [ ] goal: repair\n  - discriminator: beats random\n## Log\nold history");
 			const runtime = setup(cwd, join(cwd, "plan.md"));
-			const { systemPrompt } = await runtime.hooks.get("before_agent_start")({}, runtime.ctx);
+			const first = await runtime.hooks.get("before_agent_start")({}, runtime.ctx);
+			const systemPrompt = `${first.systemPrompt}\n${first.message.content}`;
 			expect(systemPrompt).toContain("brief visible recap");
 			expect(systemPrompt).toContain("discriminator: beats random");
 			expect(systemPrompt).not.toContain("old history");
-			expect(systemPrompt).toContain("Supervisor role reminder:");
-			const review = async () => (await runtime.hooks.get("before_agent_start")({}, runtime.ctx)).systemPrompt;
-			expect(await review()).not.toContain("Supervisor role reminder:");
-			for (let i = 0; i < 5; i++) await runtime.hooks.get("turn_end")({}, runtime.ctx);
-			expect(await review()).toContain("Supervisor role reminder:");
+			expect(first.message.customType).toBe("pi-goals-supervisor-role");
+			const review = async () => runtime.hooks.get("before_agent_start")({}, runtime.ctx);
+			const next = await review();
+			expect(next.message).toBeUndefined();
+			expect(next.systemPrompt).toContain("autonomously extending the user's agency");
 			await runtime.hooks.get("session_compact")({}, runtime.ctx);
-			expect(await review()).toContain("Supervisor role reminder:");
+			expect((await review()).message.content).toContain("Protect the user's epistemic autonomy");
 			writeFileSync(join(cwd, "plan.md"), "# Outcome\nBeat random\n1. [x] goal: repair\n  - discriminator: beats random\n");
-			expect(await review()).toContain("Supervisor role reminder:");
+			expect((await review()).systemPrompt).toContain("[x] goal: repair");
 			expect(systemPrompt).toContain("your judgment");
 			expect(systemPrompt).toContain("justified confidence, not certainty at any cost");
 			expect(systemPrompt).toContain('Treat "blocked", "waiting", "impossible", and "already done" as claims to investigate');