fix(agent): keep session scout notices live

packages/coding-agent/CHANGELOG.md

@@ -40,7 +40,7 @@
 - Fixed the vibe pre-init-kill test racing `registry.kill()` against the worker's job-body dispatch (the mock only registered its AgentRef after the abort signal landed, so a loaded runner could observe no registration); the test now waits for the worker to be mid-initialization before killing.
 ### Fixed
 
-- Removed hard-coded `scout` references from system and tool prompts that leaked into the model even when the scout agent was disabled (`task.disabledAgents`) or absent from the spawn list: the task tool description, delegation gates, plan-mode and workflowz notices, and the glob/grep/ast-grep guidance now only mention scout when it is actually spawnable ([#7313](https://github.com/can1357/oh-my-pi/issues/7313)).
+- Removed hard-coded `scout` references from agent, system, and tool prompts that leaked into the model even when the scout agent was disabled (`task.disabledAgents`) or absent from the spawn list: the init agent prompt, task tool description, delegation gates, plan-mode and workflowz notices, and glob/grep/ast-grep guidance no longer recommend an unavailable agent, including after live settings changes ([#7313](https://github.com/can1357/oh-my-pi/issues/7313)).
 
 ## [17.2.4] - 2026-08-01
 

packages/coding-agent/src/prompts/agents/init.md

@@ -4,7 +4,7 @@ description: Generate AGENTS.md for current codebase
 thinking-level: medium
 ---
 
-Generate AGENTS.md by launching multiple `scout` agents in parallel (via `task` tool) scanning different areas (core src, tests, configs/build, scripts/docs), then synthesize findings into a single file.
+Generate AGENTS.md by launching multiple research agents in parallel (via `task` tool) to scan different areas (core src, tests, configs/build, scripts/docs), then synthesize findings into a single file.
 
 <structure>
 - **Project Overview**: Brief description of project purpose

packages/coding-agent/src/sdk.ts

@@ -3347,10 +3347,7 @@ async function createAgentSessionScoped(options: CreateAgentSessionOptions): Pro
 			initialAdvisorCosts,
 			settings,
 			autoApprove: options.autoApprove,
-			scoutAvailable: isScoutSpawnable(
-				settings.get("task.disabledAgents") as string[] | undefined,
-				options.spawns ?? "*",
-			),
+			scoutAllowedBySpawnPolicy: isScoutSpawnable(undefined, options.spawns ?? "*"),
 			evalKernelOwnerId,
 			// Defined only for top-level sessions (creation is gated above).
 			// AgentSession uses this to decide whether it may dispose the global

packages/coding-agent/src/session/agent-session-types.ts

@@ -109,8 +109,8 @@ export interface AgentSessionConfig {
 	agent: Agent;
 	sessionManager: SessionManager;
 	settings: Settings;
-	/** Whether the read-only `scout` subagent is spawnable (not disabled, allowed by spawn policy). Defaults to true. */
-	scoutAvailable?: boolean;
+	/** Whether the session spawn policy permits the read-only `scout` subagent. Defaults to true. */
+	scoutAllowedBySpawnPolicy?: boolean;
 	/** Whether the caller explicitly requested yolo/auto-approve behavior for this session. */
 	autoApprove?: boolean;
 	/** Models to cycle through with Ctrl+P (from --models flag). */

packages/coding-agent/src/session/agent-session.ts

@@ -518,7 +518,7 @@ export class AgentSession {
 	// Agent identity (registry id) used for IRC routing and job ownership.
 	#agentId: string | undefined;
 	#agentKind: "main" | "sub" = "main";
-	#scoutAvailable = true;
+	#scoutAllowedBySpawnPolicy = true;
 	#providerSessionId: string | undefined;
 	#freshProviderSessionId: string | undefined;
 	#inheritedProviderPromptCacheKey: string | undefined;
@@ -1238,7 +1238,7 @@ export class AgentSession {
 		this.#loopGuards = new LoopGuards(streamGuardsHost);
 		this.#agentId = config.agentId;
 		this.#agentKind = config.agentKind ?? "main";
-		this.#scoutAvailable = config.scoutAvailable ?? true;
+		this.#scoutAllowedBySpawnPolicy = config.scoutAllowedBySpawnPolicy ?? true;
 		this.#providerSessionId = config.providerSessionId;
 		this.#inheritedProviderPromptCacheKey =
 			config.providerPromptCacheKeySource === "fork" ? this.agent.promptCacheKey : undefined;
@@ -4637,6 +4637,11 @@ export class AgentSession {
 		};
 	}
 
+	#isScoutAvailable(): boolean {
+		const disabledAgents = this.settings.get("task.disabledAgents") as string[] | undefined;
+		return this.#scoutAllowedBySpawnPolicy && !disabledAgents?.includes("scout");
+	}
+
 	async #buildPlanModeMessage(): Promise<CustomMessage | null> {
 		const state = this.#planModeState;
 		if (!state?.enabled) return null;
@@ -4660,7 +4665,7 @@ export class AgentSession {
 			isHashlineEditMode: this.#resolveActiveEditMode() === "hashline",
 			reentry: state.reentry ?? false,
 			iterative: state.workflow === "iterative",
-			scoutAvailable: this.#scoutAvailable,
+			scoutAvailable: this.#isScoutAvailable(),
 		});
 
 		return {
@@ -4794,7 +4799,7 @@ export class AgentSession {
 					customType: "workflow-notice",
 					content: renderWorkflowNotice({
 						taskBatch: this.settings.get("task.batch"),
-						scoutAvailable: this.#scoutAvailable,
+						scoutAvailable: this.#isScoutAvailable(),
 					}),
 					display: false,
 					attribution: "user",

packages/coding-agent/test/agent-session-magic-keywords.test.ts

@@ -144,6 +144,21 @@ describe("AgentSession magic keyword settings", () => {
 		expect(notice?.content).toContain("**JavaScript (`eval`, JavaScript backend):**");
 	});
 
+	it("updates the workflowz notice when scout is disabled during the session", async () => {
+		const created = await createMagicKeywordSession(root);
+		session = created.session;
+		authStorage = created.authStorage;
+		created.settings.set("task.disabledAgents", ["scout"]);
+		const promptSpy = vi.spyOn(session.agent, "prompt").mockResolvedValue(undefined);
+
+		await session.prompt("please workflowz this");
+
+		const promptMessages = promptSpy.mock.calls[0]![0] as unknown as Array<{ content?: string; customType?: string }>;
+		const notice = promptMessages.find(message => message.customType === "workflow-notice")?.content ?? "";
+		expect(notice.toLowerCase()).not.toContain("scout");
+		expect(notice).toContain("Explore inline FIRST");
+	});
+
 	it("skips workflowz notice when the task tool is inactive", async () => {
 		const created = await createMagicKeywordSession(root, []);
 		session = created.session;

packages/coding-agent/test/task/spawn-policy.test.ts

@@ -1,5 +1,6 @@
 import { afterEach, describe, expect, it, vi } from "bun:test";
 import { Settings } from "../../src/config/settings";
+import initAgentPrompt from "../../src/prompts/agents/init.md" with { type: "text" };
 import * as taskDiscovery from "../../src/task/discovery";
 import { TaskTool } from "../../src/task/index";
 import { isScoutSpawnable } from "../../src/task/spawn-policy";
@@ -130,3 +131,10 @@ describe("task tool description scout gating", () => {
 		expect(description).toContain("### reviewer");
 	});
 });
+
+describe("bundled agent prompt scout gating", () => {
+	it("does not hard-code scout in the init agent prompt", () => {
+		expect(initAgentPrompt.toLowerCase()).not.toContain("scout");
+		expect(initAgentPrompt).toContain("multiple research agents");
+	});
+});