gsd-pi 2.37.1 → 2.38.0-dev.96dc7fb

package/src/resources/extensions/gsd/files.ts

@@ -15,6 +15,7 @@ import type {
   Summary, SummaryFrontmatter, SummaryRequires, FileModified,
   Continue, ContinueFrontmatter, ContinueStatus,
   RequirementCounts,
+  TaskIO,
   SecretsManifest, SecretsManifestEntry, SecretsManifestEntryStatus,
   ManifestStatus,
 } from './types.js';
@@ -724,6 +725,50 @@ export function countMustHavesMentionedInSummary(
   return count;
 }
 
+// ─── Task Plan IO Extractor ────────────────────────────────────────────────
+
+/**
+ * Extract input and output file paths from a task plan's `## Inputs` and
+ * `## Expected Output` sections. Looks for backtick-wrapped file paths on
+ * each line (e.g. `` `src/foo.ts` ``).
+ *
+ * Returns empty arrays for missing/empty sections — callers should treat
+ * tasks with no IO as ambiguous (sequential fallback trigger).
+ */
+export function parseTaskPlanIO(content: string): { inputFiles: string[]; outputFiles: string[] } {
+  const backtickPathRegex = /`([^`]+)`/g;
+
+  function extractPaths(sectionText: string | null): string[] {
+    if (!sectionText) return [];
+    const paths: string[] = [];
+    for (const line of sectionText.split("\n")) {
+      const trimmed = line.trim();
+      if (!trimmed || trimmed.startsWith("#")) continue;
+      let match: RegExpExecArray | null;
+      backtickPathRegex.lastIndex = 0;
+      while ((match = backtickPathRegex.exec(trimmed)) !== null) {
+        const candidate = match[1];
+        // Filter out things that look like code tokens rather than file paths
+        // (e.g. `true`, `false`, `npm run test`). A file path has at least one
+        // dot or slash.
+        if (candidate.includes("/") || candidate.includes(".")) {
+          paths.push(candidate);
+        }
+      }
+    }
+    return paths;
+  }
+
+  const [, body] = splitFrontmatter(content);
+  const inputSection = extractSection(body, "Inputs");
+  const outputSection = extractSection(body, "Expected Output");
+
+  return {
+    inputFiles: extractPaths(inputSection),
+    outputFiles: extractPaths(outputSection),
+  };
+}
+
 // ─── UAT Type Extractor ────────────────────────────────────────────────────
 
 /**

package/src/resources/extensions/gsd/observability-validator.ts

@@ -235,6 +235,33 @@ export function validateTaskPlanContent(file: string, content: string): Validati
     }
   }
 
+  // Rule: Inputs and Expected Output should contain backtick-wrapped file paths
+  const inputsSection = getSection(content, "Inputs", 2);
+  const outputSection = getSection(content, "Expected Output", 2);
+  const backtickPathPattern = /`[^`]*[./][^`]*`/;
+
+  if (outputSection === null || !backtickPathPattern.test(outputSection)) {
+    issues.push({
+      severity: "warning",
+      scope: "task-plan",
+      file,
+      ruleId: "missing_output_file_paths",
+      message: "Task plan `## Expected Output` is missing or has no backtick-wrapped file paths.",
+      suggestion: "List concrete output file paths in backticks (e.g. `src/types.ts`). These are machine-parsed to derive task dependencies.",
+    });
+  }
+
+  if (inputsSection !== null && inputsSection.trim().length > 0 && !backtickPathPattern.test(inputsSection)) {
+    issues.push({
+      severity: "info",
+      scope: "task-plan",
+      file,
+      ruleId: "missing_input_file_paths",
+      message: "Task plan `## Inputs` has content but no backtick-wrapped file paths.",
+      suggestion: "List input file paths in backticks (e.g. `src/config.json`). These are machine-parsed to derive task dependencies.",
+    });
+  }
+
   // ── Observability rules (gated by runtime relevance) ──
 
   const relevant = textSuggestsObservabilityRelevant(content);

package/src/resources/extensions/gsd/preferences-types.ts

@@ -18,6 +18,7 @@ import type {
   ParallelConfig,
   CompressionStrategy,
   ContextSelectionMode,
+  ReactiveExecutionConfig,
 } from "./types.js";
 import type { DynamicRoutingConfig } from "./model-router.js";
 
@@ -86,12 +87,13 @@ export const KNOWN_PREFERENCE_KEYS = new Set<string>([
   "compression_strategy",
   "context_selection",
   "widget_mode",
+  "reactive_execution",
 ]);
 
 /** Canonical list of all dispatch unit types. */
 export const KNOWN_UNIT_TYPES = [
   "research-milestone", "plan-milestone", "research-slice", "plan-slice",
-  "execute-task", "complete-slice", "replan-slice", "reassess-roadmap",
+  "execute-task", "reactive-execute", "complete-slice", "replan-slice", "reassess-roadmap",
   "run-uat", "complete-milestone",
 ] as const;
 export type UnitType = (typeof KNOWN_UNIT_TYPES)[number];
@@ -215,6 +217,8 @@ export interface GSDPreferences {
   context_selection?: ContextSelectionMode;
   /** Default widget display mode for auto-mode dashboard. "full" | "small" | "min" | "off". Default: "full". */
   widget_mode?: "full" | "small" | "min" | "off";
+  /** Reactive (graph-derived parallel) task execution within slices. Disabled by default. */
+  reactive_execution?: ReactiveExecutionConfig;
 }
 
 export interface LoadedGSDPreferences {

package/src/resources/extensions/gsd/preferences-validation.ts

@@ -496,6 +496,47 @@ export function validatePreferences(preferences: GSDPreferences): {
     }
   }
 
+  // ─── Reactive Execution ─────────────────────────────────────────────────
+  if (preferences.reactive_execution !== undefined) {
+    if (typeof preferences.reactive_execution === "object" && preferences.reactive_execution !== null) {
+      const re = preferences.reactive_execution as unknown as Record<string, unknown>;
+      const validRe: Record<string, unknown> = {};
+
+      if (re.enabled !== undefined) {
+        if (typeof re.enabled === "boolean") validRe.enabled = re.enabled;
+        else errors.push("reactive_execution.enabled must be a boolean");
+      }
+      if (re.max_parallel !== undefined) {
+        const mp = typeof re.max_parallel === "number" ? re.max_parallel : Number(re.max_parallel);
+        if (Number.isFinite(mp) && mp >= 1 && mp <= 8) {
+          validRe.max_parallel = Math.floor(mp);
+        } else {
+          errors.push("reactive_execution.max_parallel must be a number between 1 and 8");
+        }
+      }
+      if (re.isolation_mode !== undefined) {
+        if (re.isolation_mode === "same-tree") {
+          validRe.isolation_mode = "same-tree";
+        } else {
+          errors.push('reactive_execution.isolation_mode must be "same-tree"');
+        }
+      }
+
+      const knownReKeys = new Set(["enabled", "max_parallel", "isolation_mode"]);
+      for (const key of Object.keys(re)) {
+        if (!knownReKeys.has(key)) {
+          warnings.push(`unknown reactive_execution key "${key}" — ignored`);
+        }
+      }
+
+      if (Object.keys(validRe).length > 0) {
+        validated.reactive_execution = validRe as unknown as import("./types.js").ReactiveExecutionConfig;
+      }
+    } else {
+      errors.push("reactive_execution must be an object");
+    }
+  }
+
   // ─── Verification Preferences ───────────────────────────────────────────
   if (preferences.verification_commands !== undefined) {
     if (Array.isArray(preferences.verification_commands)) {

package/src/resources/extensions/gsd/prompts/plan-slice.md

@@ -61,13 +61,14 @@ Then:
    - a concrete, action-oriented title
    - the inline task entry fields defined in the plan.md template (Why / Files / Do / Verify / Done when)
    - a matching task plan file with description, steps, must-haves, verification, inputs, and expected output
+   - **Inputs and Expected Output must list concrete backtick-wrapped file paths** (e.g. `` `src/types.ts` ``). These are machine-parsed to derive task dependencies — vague prose without paths breaks parallel execution. Every task must have at least one output file path.
    - Observability Impact section **only if the task touches runtime boundaries, async flows, or error paths** — omit it otherwise
 6. Write `{{outputPath}}`
 7. Write individual task plans in `{{slicePath}}/tasks/`: `T01-PLAN.md`, `T02-PLAN.md`, etc.
 8. **Self-audit the plan.** Walk through each check — if any fail, fix the plan files before moving on:
     - **Completion semantics:** If every task were completed exactly as written, the slice goal/demo should actually be true.
     - **Requirement coverage:** Every must-have in the slice maps to at least one task. No must-have is orphaned. If `REQUIREMENTS.md` exists, every Active requirement this slice owns maps to at least one task.
-    - **Task completeness:** Every task has steps, must-haves, verification, inputs, and expected output — none are blank or vague.
+    - **Task completeness:** Every task has steps, must-haves, verification, inputs, and expected output — none are blank or vague. Inputs and Expected Output list backtick-wrapped file paths, not prose descriptions.
     - **Dependency correctness:** Task ordering is consistent. No task references work from a later task.
     - **Key links planned:** For every pair of artifacts that must connect, there is an explicit step that wires them.
     - **Scope sanity:** Target 2–5 steps and 3–8 files per task. 10+ steps or 12+ files — must split. Each task must be completable in a single fresh context window.

package/src/resources/extensions/gsd/prompts/reactive-execute.md

@@ -0,0 +1,41 @@
+# Reactive Task Execution — Parallel Dispatch
+
+**Working directory:** `{{workingDirectory}}`
+**Milestone:** {{milestoneId}} — {{milestoneTitle}}
+**Slice:** {{sliceId}} — {{sliceTitle}}
+
+## Mission
+
+You are executing **multiple tasks in parallel** for this slice. The task graph below shows which tasks are ready for simultaneous execution based on their input/output dependencies.
+
+**Critical rule:** Use the `subagent` tool in **parallel mode** to dispatch all ready tasks simultaneously. Each subagent gets a self-contained execute-task prompt. After all subagents return, verify each task's outputs and write summaries.
+
+## Task Dependency Graph
+
+{{graphContext}}
+
+## Ready Tasks for Parallel Dispatch
+
+{{readyTaskCount}} tasks are ready for parallel execution:
+
+{{readyTaskList}}
+
+## Execution Protocol
+
+1. **Dispatch all ready tasks** using `subagent` in parallel mode. Each subagent prompt is provided below.
+2. **Wait for all subagents** to complete.
+3. **Verify each task's outputs** — check that expected files were created/modified and that verification commands pass.
+4. **Write task summaries** for each completed task using the task-summary template.
+5. **Mark completed tasks** as done in the slice plan (checkbox `[x]`).
+6. **Commit** all changes with a clear message covering the parallel batch.
+
+If any subagent fails:
+- Write a summary for the failed task with `blocker_discovered: true`
+- Continue marking the successful tasks as done
+- The orchestrator will handle re-dispatch on the next iteration
+
+## Subagent Prompts
+
+{{subagentPrompts}}
+
+{{inlinedTemplates}}

package/src/resources/extensions/gsd/reactive-graph.ts

@@ -0,0 +1,289 @@
+/**
+ * Reactive Task Graph — derives dependency edges from task plan IO signatures.
+ *
+ * Pure functions that build a DAG from task IO intersections and resolve
+ * which tasks are currently ready for parallel dispatch. Used by the
+ * reactive-execute dispatch path (ADR-004).
+ *
+ * Graph derivation and resolution functions are pure (no filesystem access).
+ * The `loadSliceTaskIO` loader at the bottom is the only async/IO function.
+ */
+
+import type { TaskIO, DerivedTaskNode, ReactiveExecutionState } from "./types.js";
+import { loadFile, parsePlan, parseTaskPlanIO } from "./files.js";
+import { resolveTasksDir, resolveTaskFiles } from "./paths.js";
+import { join } from "node:path";
+import { loadJsonFileOrNull, saveJsonFile } from "./json-persistence.js";
+import { existsSync, unlinkSync } from "node:fs";
+
+// ─── Graph Construction ───────────────────────────────────────────────────
+
+/**
+ * Build a dependency graph from task IO signatures.
+ *
+ * A task T_b depends on T_a when any of T_b's inputFiles appear in T_a's
+ * outputFiles. Self-references are excluded.
+ *
+ * Tasks are returned in the same order as the input array.
+ */
+export function deriveTaskGraph(tasks: TaskIO[]): DerivedTaskNode[] {
+  // Build output → producer lookup
+  const outputToProducer = new Map<string, string[]>();
+  for (const task of tasks) {
+    for (const outFile of task.outputFiles) {
+      const existing = outputToProducer.get(outFile);
+      if (existing) {
+        existing.push(task.id);
+      } else {
+        outputToProducer.set(outFile, [task.id]);
+      }
+    }
+  }
+
+  return tasks.map((task) => {
+    const deps = new Set<string>();
+    for (const inFile of task.inputFiles) {
+      const producers = outputToProducer.get(inFile);
+      if (producers) {
+        for (const pid of producers) {
+          if (pid !== task.id) deps.add(pid);
+        }
+      }
+    }
+    return {
+      ...task,
+      dependsOn: [...deps].sort(),
+    };
+  });
+}
+
+// ─── Ready Set Resolution ─────────────────────────────────────────────────
+
+/**
+ * Return task IDs whose dependencies are all in `completed`.
+ * Excludes tasks that are already done or in-flight.
+ */
+export function getReadyTasks(
+  graph: DerivedTaskNode[],
+  completed: Set<string>,
+  inFlight: Set<string>,
+): string[] {
+  return graph
+    .filter((node) => {
+      if (node.done || completed.has(node.id) || inFlight.has(node.id)) return false;
+      return node.dependsOn.every((dep) => completed.has(dep));
+    })
+    .map((node) => node.id);
+}
+
+// ─── Conflict-Free Subset Selection ──────────────────────────────────────
+
+/**
+ * Greedy selection of non-conflicting tasks up to `maxParallel`.
+ *
+ * Two tasks conflict if they share any outputFile. We also exclude tasks
+ * whose outputs overlap with `inFlightOutputs` (files being written by
+ * tasks currently in progress).
+ */
+export function chooseNonConflictingSubset(
+  readyIds: string[],
+  graph: DerivedTaskNode[],
+  maxParallel: number,
+  inFlightOutputs: Set<string>,
+): string[] {
+  const nodeMap = new Map(graph.map((n) => [n.id, n]));
+  const claimed = new Set(inFlightOutputs);
+  const selected: string[] = [];
+
+  for (const id of readyIds) {
+    if (selected.length >= maxParallel) break;
+    const node = nodeMap.get(id);
+    if (!node) continue;
+
+    // Check for output overlap with already-selected or in-flight
+    const conflicts = node.outputFiles.some((f) => claimed.has(f));
+    if (conflicts) continue;
+
+    // Claim this task's outputs
+    for (const f of node.outputFiles) claimed.add(f);
+    selected.push(id);
+  }
+
+  return selected;
+}
+
+// ─── Graph Quality Checks ─────────────────────────────────────────────────
+
+/**
+ * Returns true if any incomplete task has 0 inputFiles AND 0 outputFiles.
+ *
+ * An ambiguous graph means IO annotations are too sparse to derive reliable
+ * edges — the dispatcher should fall back to sequential execution.
+ */
+export function isGraphAmbiguous(graph: DerivedTaskNode[]): boolean {
+  return graph.some(
+    (node) =>
+      !node.done &&
+      node.inputFiles.length === 0 &&
+      node.outputFiles.length === 0,
+  );
+}
+
+/**
+ * Detect deadlock: no tasks are ready and none are in-flight, yet incomplete
+ * tasks remain. This indicates a circular dependency or impossible state.
+ */
+export function detectDeadlock(
+  graph: DerivedTaskNode[],
+  completed: Set<string>,
+  inFlight: Set<string>,
+): boolean {
+  const incomplete = graph.filter(
+    (n) => !n.done && !completed.has(n.id) && !inFlight.has(n.id),
+  );
+  if (incomplete.length === 0) return false; // all done
+  if (inFlight.size > 0) return false; // something is running, wait for it
+
+  // Nothing in flight, but incomplete tasks remain — check if any are ready
+  const ready = getReadyTasks(graph, completed, inFlight);
+  return ready.length === 0;
+}
+
+// ─── Graph Metrics ────────────────────────────────────────────────────────
+
+/** Compute summary metrics for logging. */
+export function graphMetrics(graph: DerivedTaskNode[]): {
+  taskCount: number;
+  edgeCount: number;
+  readySetSize: number;
+  ambiguous: boolean;
+} {
+  const completed = new Set(graph.filter((n) => n.done).map((n) => n.id));
+  const ready = getReadyTasks(graph, completed, new Set());
+  const edgeCount = graph.reduce((sum, n) => sum + n.dependsOn.length, 0);
+
+  return {
+    taskCount: graph.length,
+    edgeCount,
+    readySetSize: ready.length,
+    ambiguous: isGraphAmbiguous(graph),
+  };
+}
+
+// ─── IO Loader (async, filesystem) ────────────────────────────────────────
+
+/**
+ * Load TaskIO for all tasks in a slice by reading the slice plan (for done
+ * status and task IDs) and individual task plan files (for IO sections).
+ *
+ * Returns [] when the slice plan or tasks directory doesn't exist.
+ */
+export async function loadSliceTaskIO(
+  basePath: string,
+  mid: string,
+  sid: string,
+): Promise<TaskIO[]> {
+  const { resolveSliceFile } = await import("./paths.js");
+  const slicePlanPath = resolveSliceFile(basePath, mid, sid, "PLAN");
+  const planContent = slicePlanPath ? await loadFile(slicePlanPath) : null;
+  if (!planContent) return [];
+
+  const plan = parsePlan(planContent);
+  const tDir = resolveTasksDir(basePath, mid, sid);
+  if (!tDir) return [];
+
+  const results: TaskIO[] = [];
+
+  for (const taskEntry of plan.tasks) {
+    const planFiles = resolveTaskFiles(tDir, "PLAN");
+    const taskFileName = planFiles.find((f) =>
+      f.toUpperCase().startsWith(taskEntry.id.toUpperCase() + "-"),
+    );
+    if (!taskFileName) {
+      // Task plan file missing — include with empty IO (will trigger ambiguous)
+      results.push({
+        id: taskEntry.id,
+        title: taskEntry.title,
+        inputFiles: [],
+        outputFiles: [],
+        done: taskEntry.done,
+      });
+      continue;
+    }
+
+    const taskContent = await loadFile(join(tDir, taskFileName));
+    if (!taskContent) {
+      results.push({
+        id: taskEntry.id,
+        title: taskEntry.title,
+        inputFiles: [],
+        outputFiles: [],
+        done: taskEntry.done,
+      });
+      continue;
+    }
+
+    const io = parseTaskPlanIO(taskContent);
+    results.push({
+      id: taskEntry.id,
+      title: taskEntry.title,
+      inputFiles: io.inputFiles,
+      outputFiles: io.outputFiles,
+      done: taskEntry.done,
+    });
+  }
+
+  return results;
+}
+
+// ─── State Persistence ────────────────────────────────────────────────────
+
+function reactiveStatePath(basePath: string, mid: string, sid: string): string {
+  return join(basePath, ".gsd", "runtime", `${mid}-${sid}-reactive.json`);
+}
+
+function isReactiveState(data: unknown): data is ReactiveExecutionState {
+  if (!data || typeof data !== "object") return false;
+  const d = data as Record<string, unknown>;
+  return typeof d.sliceId === "string" && Array.isArray(d.completed) && Array.isArray(d.dispatched);
+}
+
+/**
+ * Load persisted reactive execution state for a slice.
+ * Returns null when no state file exists or the file is invalid.
+ */
+export function loadReactiveState(
+  basePath: string,
+  mid: string,
+  sid: string,
+): ReactiveExecutionState | null {
+  return loadJsonFileOrNull(reactiveStatePath(basePath, mid, sid), isReactiveState);
+}
+
+/**
+ * Save reactive execution state to disk.
+ */
+export function saveReactiveState(
+  basePath: string,
+  mid: string,
+  sid: string,
+  state: ReactiveExecutionState,
+): void {
+  saveJsonFile(reactiveStatePath(basePath, mid, sid), state);
+}
+
+/**
+ * Remove the reactive state file when a slice completes.
+ */
+export function clearReactiveState(
+  basePath: string,
+  mid: string,
+  sid: string,
+): void {
+  const path = reactiveStatePath(basePath, mid, sid);
+  try {
+    if (existsSync(path)) unlinkSync(path);
+  } catch {
+    // Non-fatal
+  }
+}

package/src/resources/extensions/gsd/templates/task-plan.md

@@ -42,11 +42,19 @@ estimated_files: {{estimatedFiles}}
 
 ## Inputs
 
+<!-- Every input MUST be a backtick-wrapped file path. These paths are machine-parsed to
+     derive task dependencies — vague descriptions without paths break dependency detection.
+     For the first task in a slice with no prior task outputs, list the existing source files
+     this task reads or modifies. -->
+
 - `{{filePath}}` — {{whatThisTaskNeedsFromPriorWork}}
-- {{priorTaskSummaryInsight}}
 
 ## Expected Output
 
-<!-- This task should produce a real increment toward making the slice goal/demo true. A full slice plan should not be able to mark every task complete while the claimed slice behavior still does not work at the stated proof level. -->
+<!-- Every output MUST be a backtick-wrapped file path — the specific files this task creates
+     or modifies. These paths are machine-parsed to derive task dependencies.
+     This task should produce a real increment toward making the slice goal/demo true. A full
+     slice plan should not be able to mark every task complete while the claimed slice behavior
+     still does not work at the stated proof level. -->
 
-- `{{filePath}}` — {{whatThisTaskShouldProduceOrModify}}
+- `{{filePath}}` — {{whatThisTaskCreatesOrModifies}}

package/src/resources/extensions/gsd/tests/cmux.test.ts

@@ -100,6 +100,99 @@ test("buildCmuxStatusLabel and progress prefer deepest active unit", () => {
   assert.deepEqual(buildCmuxProgress(state), { value: 0.4, label: "2/5 tasks" });
 });
 
+describe("createGridLayout", () => {
+  // Create a mock CmuxClient that tracks createSplitFrom calls
+  function makeMockClient() {
+    let nextId = 1;
+    const calls: Array<{ source: string | undefined; direction: string }> = [];
+
+    const client = {
+      calls,
+      async createGridLayout(count: number) {
+        // Simulate the grid layout logic with a fake client
+        if (count <= 0) return [];
+        const surfaces: string[] = [];
+
+        const createSplitFrom = async (source: string | undefined, direction: string) => {
+          calls.push({ source, direction });
+          return `surface-${nextId++}`;
+        };
+
+        const rightCol = await createSplitFrom("gsd-surface", "right");
+        surfaces.push(rightCol);
+        if (count === 1) return surfaces;
+
+        const bottomRight = await createSplitFrom(rightCol, "down");
+        surfaces.push(bottomRight);
+        if (count === 2) return surfaces;
+
+        const bottomLeft = await createSplitFrom("gsd-surface", "down");
+        surfaces.push(bottomLeft);
+        if (count === 3) return surfaces;
+
+        let lastSurface = bottomRight;
+        for (let i = 3; i < count; i++) {
+          const next = await createSplitFrom(lastSurface, "down");
+          surfaces.push(next);
+          lastSurface = next;
+        }
+
+        return surfaces;
+      },
+    };
+    return client;
+  }
+
+  test("1 agent creates single right split", async () => {
+    const mock = makeMockClient();
+    const surfaces = await mock.createGridLayout(1);
+    assert.equal(surfaces.length, 1);
+    assert.deepEqual(mock.calls, [
+      { source: "gsd-surface", direction: "right" },
+    ]);
+  });
+
+  test("2 agents creates right column then splits it down", async () => {
+    const mock = makeMockClient();
+    const surfaces = await mock.createGridLayout(2);
+    assert.equal(surfaces.length, 2);
+    assert.deepEqual(mock.calls, [
+      { source: "gsd-surface", direction: "right" },
+      { source: "surface-1", direction: "down" },
+    ]);
+  });
+
+  test("3 agents creates 2x2 grid (gsd + 3 agent surfaces)", async () => {
+    const mock = makeMockClient();
+    const surfaces = await mock.createGridLayout(3);
+    assert.equal(surfaces.length, 3);
+    assert.deepEqual(mock.calls, [
+      { source: "gsd-surface", direction: "right" },
+      { source: "surface-1", direction: "down" },
+      { source: "gsd-surface", direction: "down" },
+    ]);
+  });
+
+  test("4 agents creates 2x2 grid with extra split", async () => {
+    const mock = makeMockClient();
+    const surfaces = await mock.createGridLayout(4);
+    assert.equal(surfaces.length, 4);
+    assert.deepEqual(mock.calls, [
+      { source: "gsd-surface", direction: "right" },
+      { source: "surface-1", direction: "down" },
+      { source: "gsd-surface", direction: "down" },
+      { source: "surface-2", direction: "down" },
+    ]);
+  });
+
+  test("0 agents returns empty", async () => {
+    const mock = makeMockClient();
+    const surfaces = await mock.createGridLayout(0);
+    assert.equal(surfaces.length, 0);
+    assert.equal(mock.calls.length, 0);
+  });
+});
+
 describe("cmux extension discovery opt-out", () => {
   test("cmux directory has package.json with pi manifest to prevent auto-discovery as extension", () => {
     const cmuxDir = path.resolve(