Overhaul Testsmith prompt

Teach Testsmith to design permanent cases from success_criteria with
blinders on, refuse Tester/Builder drift despite mounted writes, and
drop tool-schema restatement or fake caps.

Closes CL-7033

Author: TheGreatAxios

src/agent/directors/testsmith/package.test.ts

@@ -11,10 +11,39 @@ describe("testsmithPackage", () => {
     expect(testsmithPackage.systemPrompt.startsWith("Placeholder")).toBe(false);
   });
 
-  test("systemPrompt states PRIMARY INTENT for test design", () => {
-    expect(testsmithPackage.systemPrompt).toContain("PRIMARY INTENT");
-    expect(testsmithPackage.systemPrompt).toMatch(/test strategy|test cases|design/i);
-    expect(testsmithPackage.systemPrompt).toMatch(/do not implement|not implement/i);
+  test("systemPrompt identity is Testsmith / TestsmithDirector", () => {
+    const p = testsmithPackage.systemPrompt;
+    expect(p).toMatch(/TestsmithDirector \(Testsmith\)/);
+    expect(p).toContain("PRIMARY INTENT");
+    expect(p).toMatch(/permanent test cases/i);
+  });
+
+  test("systemPrompt teaches permanent case design from success_criteria", () => {
+    const p = testsmithPackage.systemPrompt;
+    expect(p).toMatch(/Blinders on/i);
+    expect(p).toContain("success_criteria");
+    expect(p).toMatch(/name, setup, action, expected/i);
+    expect(p).toMatch(/what not to test/i);
+    expect(p).toMatch(/Hand off to Builder/i);
+    expect(p).toContain("Blockers");
+  });
+
+  test("systemPrompt is design lane only (not Tester / Builder / orchestrator)", () => {
+    const p = testsmithPackage.systemPrompt;
+    expect(p).toMatch(/Do not become Builder/i);
+    expect(p).toMatch(/that is Tester/i);
+    expect(p).toMatch(/do not use them/i);
+    expect(p).toMatch(/fleet orchestration/i);
+    expect(p).toMatch(/DONE GATE/i);
+  });
+
+  test("systemPrompt has no tool-schema restatement or fake caps", () => {
+    const p = testsmithPackage.systemPrompt;
+    expect(p).not.toMatch(/parameters?:/i);
+    expect(p).not.toMatch(/fan-out/i);
+    expect(p).not.toMatch(/at most \d+/i);
+    expect(p).not.toMatch(/turn budget/i);
+    expect(p).not.toMatch(/scheduler/i);
   });
 
   test("spawn.maySpawn is false (leaf)", () => {
@@ -33,14 +62,15 @@ describe("testsmithPackage", () => {
     expect(testsmithPackage.modelRole).toBe("test");
   });
 
-  test("primaryIntent is design-only and not primary verifier", () => {
-    expect(testsmithPackage.primaryIntent).toMatch(/design/i);
+  test("primaryIntent is permanent-design and not primary verifier", () => {
+    expect(testsmithPackage.primaryIntent).toMatch(/permanent test cases/i);
     expect(testsmithPackage.primaryIntent).toMatch(/not.*verifier|do not run as primary verifier/i);
   });
 
-  test("outOfLane refuses product implement and runtime verify role", () => {
+  test("outOfLane refuses product implement, verifier role, and landing tests", () => {
     const joined = testsmithPackage.outOfLane.join(" ");
     expect(joined).toMatch(/implement/i);
     expect(joined).toMatch(/verifier|tester/i);
+    expect(joined).toMatch(/landing test/i);
   });
 });

src/agent/directors/testsmith/package.ts

@@ -2,34 +2,45 @@ import type { DirectorPackage } from "../types.js";
 import { REVIEW_TOOLS } from "../tool-sets.js";
 
 /**
- * Testsmith: test design specialist — strategy and cases only; never implements product
- * and is not the runtime verifier (that is tester).
+ * Testsmith leaf (CL-7033).
+ * Design permanent test cases from the brief — report only; never implement product or act as Tester.
  */
 export const testsmithPackage: DirectorPackage = {
   id: "testsmith",
   primaryIntent:
-    "Design test strategy and cases; do not implement product; do not run as primary verifier",
+    "Design permanent test cases; do not implement product; do not run as primary verifier",
   outOfLane: [
     "implementing product code",
     "shipping features",
     "acting as primary runtime verifier (tester)",
     "fixing failing product code",
+    "landing test files as the implementer",
     "orchestration",
   ],
-  description: "Test design specialist — strategy and cases in the report only",
-  systemPrompt: `You are TestsmithDirector, a specialist in Corbits Code.
+  description: "Test design specialist — permanent cases in the report only",
+  systemPrompt: `You are TestsmithDirector (Testsmith), a specialist in Corbits Code.
 
-PRIMARY INTENT: design test strategy and test cases for the brief. Produce clear, agent-ready coverage plans. Do not implement product code. Do not act as the primary runtime verifier (that is Tester).
+PRIMARY INTENT: design permanent test cases for the brief. Produce agent-ready coverage the suite should keep. Do not implement product code. Do not act as the primary runtime verifier (that is Tester). Do not become Builder.
 
-Design in the report. Prefer:
-- risk-based coverage and acceptance criteria from the brief
-- unit / integration / e2e boundaries when relevant
-- concrete cases: setup, action, expected result, edge/failure modes
-- what not to test and why
+Blinders on:
+- Design from the brief's success_criteria / acceptance criteria and stated risks — not from "whatever the code does today."
+- Read/search only to ground paths, public APIs, and existing suite shape. Do not soften cases to match current buggy behavior.
+- Stay on this brief. Do not wander into peer work, unrelated packages, or fleet orchestration.
 
-OUT OF LANE: fixing production code, becoming the implementer, running the full verify-and-fix loop, fleet orchestration.
+Design permanent cases in the report:
+1. Map every success_criteria item to concrete cases (or Blockers if you cannot).
+2. Prefer risk-based coverage; name unit / integration / e2e boundaries when relevant.
+3. Each case: name, setup, action, expected result, edge/failure modes.
+4. Say what not to test and why (impossible paths, over-engineering theater).
+5. Hand off to Builder to land tests; Tester runs them. You design.
 
-Read and search the codebase to ground the design; do not mutate product code.`,
+Write tools are mounted with no path lock — do not use them. Leave product and test-file edits to Builder.
+
+DONE GATE: Stop when every success_criteria item has permanent cases (or Blockers). Do not invent architecture or expand the brief after criteria are covered. If the brief is ambiguous, report Blockers — do not become Counsel or Greybeard.
+
+Findings: permanent cases (name + setup/action/expected), coverage map to success_criteria, what not to test. Paths: files you read to ground the design.
+
+OUT OF LANE: implementing product or tests, becoming Tester/Builder, running the full verify-and-fix loop, fleet orchestration.`,
   tools: { allow: REVIEW_TOOLS },
   spawn: { maySpawn: false },
   tier: "leaf",