fix(coding-agent): keep smoke-test fallback for uncovered UI surfaces

When a session has browser but not computer (or vice versa), the
behavioral/smoke-test fallback for UI changes was suppressed entirely,
leaving native-desktop (or web) verification guidance undefined. Render
the fallback whenever any visual runtime tool is missing.

Also strengthen the plan-mode tests per review: exercise the iterative
branch gating with iterative:true (previously passed trivially) and
restore a typed Overrides record for the render helper.

packages/coding-agent/src/prompts/system/system-prompt.md

@@ -214,9 +214,8 @@ EXECUTION WORKFLOW
     - **Native desktop UI** → drive it with `{{toolRefs.computer}}`; ground every claim in fresh screenshot or accessibility evidence.
 {{/has}}
     - **TUI/CLI** → launch the actual program and verify terminal interaction, output, or state.
-{{#ifAny (includes tools "browser") (includes tools "computer")}}
-{{else}}
-    - If no suitable runtime tool is available, verify with a behavioral test or smoke test and explicitly report when visual verification cannot be performed.
+{{#ifAny (not (includes tools "browser")) (not (includes tools "computer"))}}
+    - If no suitable runtime tool is available for the surface being changed, verify with a behavioral test or smoke test and explicitly report when visual verification cannot be performed.
 {{/ifAny}}
   - **Bug fix** → reproduce the bug, apply the fix, confirm the reproduction no longer triggers.
   - **Permanent feature / API change** → existing tests that cover the changed contract. Add a test only when the change introduces a new observable contract not already covered, or the user asked for one.

packages/coding-agent/test/plan-mode/reentry-prompt.test.ts

@@ -12,34 +12,42 @@ const BASE = {
 	askAvailable: true,
 	taskAvailable: true,
 	scoutAvailable: true,
+	reentry: false,
+	planExists: true,
 } as const;
 
-function render(overrides: Partial<Record<string, unknown>>): string {
+type Overrides = Partial<Record<keyof typeof BASE, boolean | string>>;
+
+function render(overrides: Overrides = {}): string {
 	return prompt.render(planModeActivePrompt, { ...BASE, ...overrides });
 }
 
 describe("plan-mode re-entry prompt", () => {
 	it("only emits the Re-entry section when re-entering", () => {
-		expect(render({ reentry: false, planExists: true })).not.toContain("## Re-entry");
-		expect(render({ reentry: true, planExists: true })).toContain("## Re-entry");
+		expect(render({ reentry: false })).not.toContain("## Re-entry");
+		expect(render({ reentry: true })).toContain("## Re-entry");
 	});
 });
 
 describe("plan-mode-active tool availability", () => {
 	it("omits ask-tool directives when ask is unavailable", () => {
-		const withoutAsk = render({ askAvailable: false });
+		const withoutAsk = render({ askAvailable: false, iterative: true });
 		expect(withoutAsk).not.toContain("`ask` with 2–4 mutually exclusive options");
 		expect(withoutAsk).not.toContain("use `ask` for preferences and tradeoffs");
 		expect(withoutAsk).not.toContain("Using `ask` to gather requirements");
 
-		const withAsk = render({ askAvailable: true });
+		const withAsk = render({ askAvailable: true, iterative: true });
 		expect(withAsk).toContain("`ask` with 2–4 mutually exclusive options");
+		expect(withAsk).toContain("use `ask` for preferences and tradeoffs");
 	});
 
 	it("provides a prose fallback for preference collection when ask is unavailable", () => {
-		const withoutAsk = render({ askAvailable: false });
-		expect(withoutAsk).toContain("present the candidates with a recommendation in prose");
-		expect(withoutAsk).toContain("surface any remaining preference questions with a recommendation in prose");
+		const iterativeWithoutAsk = render({ askAvailable: false, iterative: true });
+		expect(iterativeWithoutAsk).toContain("present the candidates with a recommendation in prose");
+		expect(iterativeWithoutAsk).not.toContain("`ask` for preferences and tradeoffs only");
+
+		const parallelWithoutAsk = render({ askAvailable: false, iterative: false });
+		expect(parallelWithoutAsk).toContain("surface any remaining preference questions with a recommendation in prose");
 	});
 
 	it("omits scout-via-task dispatch when the task tool is unavailable", () => {

packages/coding-agent/test/system-prompt-inventory.test.ts

@@ -724,6 +724,9 @@ describe("system prompt tool inventory", () => {
 		).systemPrompt.join("\n\n");
 
 		expect(withBrowser).toContain("drive it in `browser`");
+		// A browser-only session still needs the smoke-test fallback for
+		// native-desktop surfaces (no computer tool).
+		expect(withBrowser).toContain("behavioral test or smoke test");
 	});
 
 	it("omits todo workflow guidance when the todo tool is absent", async () => {