@melihmucuk/pi-crew 1.0.19 → 1.0.20

package/README.md

@@ -34,7 +34,7 @@ Lists available subagent definitions and active subagents owned by the current s
 
 #### `crew_spawn`
 
-Spawns a subagent in an isolated session. The subagent runs in the background with its own context window, tools, and skills. When it finishes, the result is delivered to the session that spawned it as a steering message that triggers a new turn. If that session is not active, the result is queued until you switch back to it.
+Spawns a subagent in an isolated session. Each spawn includes a concise `brief` label for session lists and a full self-contained `task`. The subagent runs in the background with its own context window, tools, and skills. When it finishes, the result is delivered to the session that spawned it as a steering message that triggers a new turn. If that session is not active, the result is queued until you switch back to it.
 
 ```
 "spawn scout and find all API endpoints and their authentication methods"
@@ -100,14 +100,14 @@ A bundled orchestration skill that provides best practices for delegating work t
 
 pi-crew ships with six subagent definitions that cover common workflows:
 
-| Subagent             | Purpose                                                                                                                  | Tools                      | Model                       |
-| -------------------- | ------------------------------------------------------------------------------------------------------------------------ | -------------------------- | --------------------------- |
-| **scout**            | Investigates codebase and returns structured findings. Read-only. Use before planning or implementing to gather context. | read, grep, find, ls, bash | openai-codex/gpt-5.5        |
-| **planner**          | Analyzes requirements and produces a step-by-step implementation plan. Read-only. Does not write code. Interactive.      | read, grep, find, ls, bash | openai-codex/gpt-5.5        |
-| **oracle**           | Evaluates critical decisions, surfaces blind spots, and challenges assumptions. Read-only. Does not implement. Interactive. | read, grep, find, ls, bash | openai-codex/gpt-5.5        |
-| **code-reviewer**    | Reviews code changes for bugs, security issues, and correctness. Read-only. Does not fix issues.                         | read, grep, find, ls, bash | openai-codex/gpt-5.2        |
-| **quality-reviewer** | Reviews code structure for maintainability, duplication, and complexity. Read-only. Does not look for bugs.              | read, grep, find, ls, bash | openai-codex/gpt-5.2        |
-| **worker**           | Implements code changes, fixes, and refactors autonomously. Has full read-write access to the codebase.                  | all                        | openai-codex/gpt-5.5        |
+| Subagent             | Purpose                                                                                                                  | Tools                      | Model                       | Thinking |
+| -------------------- | ------------------------------------------------------------------------------------------------------------------------ | -------------------------- | --------------------------- | -------- |
+| **scout**            | Investigates codebase and returns structured findings. Read-only.                                                        | read, grep, find, ls, bash | openai-codex/gpt-5.5        | off      |
+| **planner**          | Produces deterministic implementation plans. Read-only. Does not write code.                                             | read, grep, find, ls, bash | openai-codex/gpt-5.5        | high     |
+| **oracle**           | Evaluates critical decisions, surfaces blind spots, and challenges assumptions. Read-only.                               | read, grep, find, ls, bash | openai-codex/gpt-5.5        | xhigh    |
+| **code-reviewer**    | Reviews scoped code for actionable bugs. Read-only.                                                                      | read, grep, find, ls, bash | openai-codex/gpt-5.5        | high     |
+| **quality-reviewer** | Reviews scoped code for maintainability, duplication, and complexity. Read-only.                                         | read, grep, find, ls, bash | openai-codex/gpt-5.5        | high     |
+| **worker**           | Implements scoped code changes safely and verifies them.                                                                 | all                        | openai-codex/gpt-5.5        | low      |
 
 Read-only bundled subagents still keep `bash` for inspection workflows like `git` and `ast-grep`. This is an instruction-level contract, not a sandbox boundary.
 

package/agents/code-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: code-reviewer
 description: Reviews scoped code for actionable bugs. Read-only.
-model: openai-codex/gpt-5.2
+model: openai-codex/gpt-5.5
 thinking: high
 tools: read, grep, find, ls, bash
 ---

package/agents/quality-reviewer.md

@@ -1,7 +1,7 @@
 ---
 name: quality-reviewer
 description: Reviews scoped code for maintainability, duplication, and complexity. Read-only.
-model: openai-codex/gpt-5.2
+model: openai-codex/gpt-5.5
 thinking: high
 tools: read, grep, find, ls, bash
 ---

package/extension/crew.ts

@@ -27,6 +27,7 @@ export interface SubagentState {
 	id: string;
 	agentConfig: AgentConfig;
 	task: string;
+	brief: string;
 	status: SubagentStatus;
 	ownerSessionId: string;
 	session: AgentSession | null;
@@ -63,6 +64,7 @@ export interface SpawnContext {
 	agentDir: string;
 	parentSessionFile?: string;
 	onWarning?: (message: string) => void;
+	brief?: string;
 }
 
 type SettledSubagentStatus = Extract<SubagentStatus, "done" | "waiting" | "error" | "aborted">;
@@ -149,7 +151,7 @@ export class CrewRuntime {
 		ctx: SpawnContext,
 		extensionResolvedPath: string,
 	): string {
-		const state = this.createAgent(agentConfig, task, ownerSessionId);
+		const state = this.createAgent(agentConfig, task, ctx.brief ?? "", ownerSessionId);
 		this.refreshWidgetFor(ownerSessionId);
 		this.runner.start(state, {
 			cwd,
@@ -226,12 +228,13 @@ export class CrewRuntime {
 			.map(buildActiveAgentSummary);
 	}
 
-	private createAgent(agentConfig: AgentConfig, task: string, ownerSessionId: string): SubagentState {
+	private createAgent(agentConfig: AgentConfig, task: string, brief: string, ownerSessionId: string): SubagentState {
 		const id = generateId(agentConfig.name, new Set(this.agents.keys()));
 		const state: SubagentState = {
 			id,
 			agentConfig,
 			task,
+			brief,
 			status: "running",
 			ownerSessionId,
 			session: null,
@@ -371,7 +374,17 @@ export class CrewRuntime {
 	}
 }
 
+const CREW_RUNTIME_VERSION = 2;
 const crewRuntimeKey = Symbol.for("pi-crew.runtime");
-const globalWithCrewRuntime = globalThis as typeof globalThis & Record<symbol, CrewRuntime | undefined>;
+const globalWithCrewRuntime = globalThis as typeof globalThis & Record<symbol, (CrewRuntime & { __piCrewRuntimeVersion?: number }) | undefined>;
 
-export const crewRuntime = globalWithCrewRuntime[crewRuntimeKey] ??= new CrewRuntime();
+function createCrewRuntime(): CrewRuntime & { __piCrewRuntimeVersion?: number } {
+	const runtime = new CrewRuntime() as CrewRuntime & { __piCrewRuntimeVersion?: number };
+	runtime.__piCrewRuntimeVersion = CREW_RUNTIME_VERSION;
+	return runtime;
+}
+
+const existingRuntime = globalWithCrewRuntime[crewRuntimeKey];
+export const crewRuntime = existingRuntime?.__piCrewRuntimeVersion === CREW_RUNTIME_VERSION
+	? existingRuntime
+	: (globalWithCrewRuntime[crewRuntimeKey] = createCrewRuntime());

package/extension/subagent-session.ts

@@ -175,6 +175,16 @@ function isAborted(state: SubagentState): boolean {
 	return state.status === "aborted";
 }
 
+function normalizeSessionNamePart(value: string): string {
+	return value.replace(/[\u0000-\u001f\u007f]/g, " ").replace(/\s+/g, " ").trim();
+}
+
+export function formatSubagentSessionName(state: Pick<SubagentState, "agentConfig" | "brief" | "id">): string {
+	const agentName = normalizeSessionNamePart(state.agentConfig.name) || "subagent";
+	const brief = normalizeSessionNamePart(state.brief) || state.id;
+	return `crew: ${agentName} · ${brief}`;
+}
+
 export class SubagentSessionRunner implements SubagentRunner {
 	constructor(private readonly callbacks: SubagentRunnerCallbacks) {}
 
@@ -211,6 +221,7 @@ export class SubagentSessionRunner implements SubagentRunner {
 			return false;
 		}
 		state.session = session;
+		session.setSessionName(formatSubagentSessionName(state));
 		return true;
 	}
 

package/extension/tools.ts

@@ -175,24 +175,29 @@ export function registerCrewTools(pi: ExtensionAPI, crew: CrewRuntime, extension
 		},
 	});
 
-	registerActionTool<{ subagent: string; task: string }>(pi, {
+	registerActionTool<{ subagent: string; brief: string; task: string }>(pi, {
 		name: "crew_spawn",
 		label: "Spawn Crew",
 		description:
 			"Spawn a non-blocking subagent that runs in an isolated session. The subagent works independently while your session stays interactive. Results are delivered back to your session as steering messages.",
 		parameters: Type.Object({
 			subagent: Type.String({ description: "Subagent name from crew_list" }),
-			task: Type.String({ description: "Task to delegate to the subagent" }),
+			brief: Type.String({ description: "Concise task label for session lists, ideally under 80 characters. This is not the full task." }),
+			task: Type.String({ description: "Full self-contained task to delegate to the subagent" }),
 		}),
 		promptSnippet: "Spawn a non-blocking subagent. Use crew_list first to see available subagents.",
 		promptGuidelines: [
 			"crew_spawn: Spawn a discovered subagent for one clearly delegated, self-contained task.",
-			"crew_spawn: Include only needed context: constraints, relevant files, acceptance criteria, and expected output.",
+			"crew_spawn: Provide brief as a concise human-readable task label for session lists, ideally under 80 characters; do not put the full task there.",
+			"crew_spawn: Include only needed context in task: constraints, relevant files, acceptance criteria, and expected output.",
 			"crew_spawn: After spawning, ownership transfers to the subagent; do not work on that task yourself.",
 			"crew_spawn: Results arrive as steering messages; do not poll crew_list or fabricate results.",
 			"crew_spawn: Use the bundled pi-crew skill for detailed delegation patterns.",
 		],
 		action: (params, ctx) => {
+			const brief = params.brief.trim();
+			if (!brief) return toolError("brief is required and must not be empty.");
+
 			const toolCtx = getToolContext(ctx);
 			const { agents, warnings } = discoverAgents(toolCtx.cwd);
 			notifyDiscoveryWarnings(ctx, shownDiscoveryWarnings, warnings);
@@ -208,6 +213,7 @@ export function registerCrewTools(pi: ExtensionAPI, crew: CrewRuntime, extension
 				toolCtx.cwd,
 				toolCtx.callerSessionId,
 				{
+					brief,
 					model: ctx.model,
 					modelRegistry: ctx.modelRegistry,
 					agentDir: getAgentDir(),
@@ -218,11 +224,13 @@ export function registerCrewTools(pi: ExtensionAPI, crew: CrewRuntime, extension
 			);
 			return toolSuccess(
 				`Subagent '${subagent.name}' spawned as ${id}. Result will be delivered as a steering message when done.`,
-				{ id, agentName: subagent.name, task: params.task },
+				{ id, agentName: subagent.name, brief, task: params.task },
 			);
 		},
 		renderCall(args, theme, _context) {
-			return renderCrewCall(theme, "crew_spawn", args.subagent || "...", args.task);
+			const subagent = args.subagent || "...";
+			const title = args.brief ? `${subagent} · ${args.brief}` : subagent;
+			return renderCrewCall(theme, "crew_spawn", title, args.task);
 		},
 	});
 

package/extension/ui.ts

@@ -1,3 +1,4 @@
+import { pathToFileURL } from "node:url";
 import type { AgentToolResult } from "@earendil-works/pi-agent-core";
 import {
 	type ExtensionAPI,
@@ -144,6 +145,11 @@ function renderWarningMessage(content: unknown, theme: MessageRendererTheme): Bo
 	return box;
 }
 
+function linkFilePath(filePath: string): string {
+	const url = pathToFileURL(filePath).href;
+	return `\x1b]8;;${url}\x07${filePath}\x1b]8;;\x07`;
+}
+
 export function registerCrewMessageRenderers(pi: ExtensionAPI): void {
 	pi.registerMessageRenderer("crew-result", (message, { expanded }, theme) => {
 		const details = message.details as CrewResultMessageDetails | undefined;
@@ -158,7 +164,7 @@ export function registerCrewMessageRenderers(pi: ExtensionAPI): void {
 		box.addChild(new Text(header, 0, 0));
 
 		if (details?.sessionFile) {
-			box.addChild(new Text(theme.fg("muted", `📁 ${details.sessionFile}`), 0, 0));
+			box.addChild(new Text(theme.fg("muted", `📁 ${linkFilePath(details.sessionFile)}`), 0, 0));
 		}
 
 		if (body) {
@@ -242,7 +248,7 @@ function syncWidgetText(state: WidgetState, agents: ActiveAgentSummary[]): void
 }
 
 export function updateWidget(ctx: ExtensionContext, crew: CrewRuntime): void {
-	if (!ctx.hasUI) {
+	if (ctx.mode !== "tui") {
 		clearWidget();
 		return;
 	}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@melihmucuk/pi-crew",
-  "version": "1.0.19",
+  "version": "1.0.20",
   "type": "module",
   "description": "Non-blocking subagent orchestration for pi coding agent",
   "files": [
@@ -43,13 +43,13 @@
     "typebox": "*"
   },
   "devDependencies": {
-    "@earendil-works/pi-agent-core": "^0.76.0",
-    "@earendil-works/pi-ai": "^0.76.0",
-    "@earendil-works/pi-coding-agent": "^0.76.0",
-    "@earendil-works/pi-tui": "^0.76.0",
+    "@earendil-works/pi-agent-core": "^0.78.1",
+    "@earendil-works/pi-ai": "^0.78.1",
+    "@earendil-works/pi-coding-agent": "^0.78.1",
+    "@earendil-works/pi-tui": "^0.78.1",
     "@types/node": "^22.19.17",
     "tsx": "^4.22.3",
-    "typebox": "^1.1.39",
+    "typebox": "^1.2.1",
     "typescript": "^5.9.3"
   }
 }

package/skills/pi-crew/REFERENCE.md

@@ -2,7 +2,12 @@
 
 ## Delegation Checklist
 
-Before `crew_spawn`, ensure the brief is self-contained but not mechanically templated. Include only information that helps this specific subagent do this specific task:
+Before `crew_spawn`, provide:
+
+- `brief`: a concise human-readable task label for session lists, ideally under 80 characters. Use a few words for intent/outcome; do not include the full task, acceptance criteria, long paths, secrets, or mechanical repo state.
+- `task`: a self-contained delegated task body, not mechanically templated.
+
+In `task`, include only information that helps this specific subagent do this specific task:
 
 - Intent, expected outcome, and relevant user decisions.
 - User-provided references, plus a concise summary after reading them when practical.
@@ -76,7 +81,7 @@ If ownership overlaps, serialize the work.
 ## Tool Notes
 
 - `crew_list`: discovery before a new spawn decision or requested status snapshot; never completion polling.
-- `crew_spawn`: self-contained delegation; ownership transfers after spawn.
+- `crew_spawn`: provide `brief` plus a self-contained `task`; ownership transfers after spawn.
 - `crew_respond`: send a follow-up to a waiting interactive subagent; fire-and-forget.
 - `crew_done`: close a waiting interactive subagent when complete.
 - `crew_abort`: abort active owned subagents only when obsolete, wrong, or cancelled.

package/skills/pi-crew/SKILL.md

@@ -21,6 +21,11 @@ See [REFERENCE.md](REFERENCE.md) for examples and detailed handling patterns.
 
 ## Spawn Brief
 
+Every `crew_spawn` requires both `brief` and `task`:
+
+- `brief`: concise human-readable task label for session lists, ideally under 80 characters. Write the intent/outcome in a few words; do not include the full task, acceptance criteria, long paths, secrets, or mechanical repo state.
+- `task`: self-contained delegated work body with the context the subagent needs.
+
 Send a self-contained task, but do not fill a template mechanically. Use only sections that add task-specific value, for example:
 
 ```md
@@ -35,7 +40,7 @@ Omit sections that would only restate the selected subagent’s role, default sc
 
 Include only information that helps this specific subagent do this specific task: intent, expected outcome, relevant decisions, exact errors/output, unusual constraints, and file paths or entry points that genuinely clarify the task. Use short Markdown sections and bullets when they improve scanability, especially for multi-part intent, constraints, observations, requirements, or acceptance criteria; avoid dense paragraphs.
 
-For repeated workflows, make each spawn brief independent. Do not assume a new subagent knows earlier loop results, owner-session discussion, or what another subagent saw. If prior findings, fixes, decisions, or verification matter, summarize the concrete facts or point to durable artifacts the subagent can inspect. Avoid vague references like “we fixed the first review findings” unless you also state what those findings/fixes were or define the current review target without relying on that history.
+For repeated workflows, make each task independent. Do not assume a new subagent knows earlier loop results, owner-session discussion, or what another subagent saw. If prior findings, fixes, decisions, or verification matter, summarize the concrete facts or point to durable artifacts the subagent can inspect. Avoid vague references like “we fixed the first review findings” unless you also state what those findings/fixes were or define the current review target without relying on that history.
 
 Do not restate boilerplate implied by the selected subagent’s role, name, or description. Avoid repeating default scope, output format, edit permissions, or repo guidance. Subagents run in the same cwd as the orchestrator, so do not include mechanical Git state they can inspect themselves, such as full changed-file lists, staged/unstaged/untracked inventories, branch/cwd details, or generic project constraints, unless those details define a non-default scope or prevent ambiguity.