Adding support for herdr - agents in new tabs

test/integration/harness.ts

@@ -2,9 +2,9 @@
  * Integration test harness for pi-interactive-subagents.
  *
  * Provides utilities to:
- * - Detect whether tmux is available
+ * - Detect the active terminal-surface backend
  * - Create isolated test environments with test agent definitions
- * - Start real pi sessions in tmux panes
+ * - Start real pi sessions in Herdr tabs or tmux panes
  * - Poll for file creation and screen output
  * - Clean up panes and temp files after tests
  */
@@ -18,12 +18,13 @@ import {
   existsSync,
   readFileSync,
   unlinkSync,
+  writeFileSync,
 } from "node:fs";
 import { join, resolve, dirname } from "node:path";
 import { fileURLToPath } from "node:url";
 import { tmpdir } from "node:os";
 import {
-  isMuxAvailable,
+  getMuxBackend,
   createSurface,
   createSurfaceSplit,
   sendCommand,
@@ -31,10 +32,13 @@ import {
   readScreen,
   readScreenAsync,
   closeSurface,
+  pollForExit,
   shellEscape,
-} from "../../pi-extension/subagents/tmux.ts";
+  wrapWithCompletionFile,
+  type MuxBackend,
+} from "../../pi-extension/subagents/surface.ts";
 
-// Re-export tmux primitives for tests
+// Re-export backend-neutral surface primitives for tests
 export {
   createSurface,
   createSurfaceSplit,
@@ -43,7 +47,9 @@ export {
   readScreen,
   readScreenAsync,
   closeSurface,
+  pollForExit,
   shellEscape,
+  wrapWithCompletionFile,
 };
 
 // ── Paths ──
@@ -68,27 +74,49 @@ const EXTENSION_SOURCE = join(PROJECT_ROOT, "pi-extension", "subagents", "index.
 // ── Configuration ──
 
 /** Model used for integration tests. Override with PI_TEST_MODEL env var. */
-export const TEST_MODEL = process.env.PI_TEST_MODEL ?? "anthropic/claude-haiku-4-5";
+const activePiModel =
+  process.env.PI_PROVIDER && process.env.PI_MODEL
+    ? `${process.env.PI_PROVIDER}/${process.env.PI_MODEL}`
+    : undefined;
+export const TEST_MODEL =
+  process.env.PI_TEST_MODEL ?? activePiModel ?? "anthropic/claude-haiku-4-5";
 
 /** Per-test timeout in ms. Override with PI_TEST_TIMEOUT env var. */
 export const PI_TIMEOUT = Number(process.env.PI_TEST_TIMEOUT ?? "120000");
 
 // ── Backend detection ──
 
-/**
- * Detect whether tmux is available in the current environment.
- * Returns ["tmux"] or [].
- */
-export function getAvailableBackends(): string[] {
-  return isMuxAvailable() ? ["tmux"] : [];
+/** Return the one backend selected automatically for this process. */
+export function getAvailableBackends(): MuxBackend[] {
+  const backend = getMuxBackend();
+  return backend ? [backend] : [];
+}
+
+function parseHerdrJson(command: string, args: string[]): any {
+  const output = execFileSync(command, args, { encoding: "utf8" });
+  return JSON.parse(output);
 }
 
 export function focusSurface(surface: string): void {
+  if (getMuxBackend() === "herdr") {
+    const pane = parseHerdrJson("herdr", ["pane", "get", surface]);
+    const tabId = pane.result?.pane?.tab_id;
+    if (!tabId) throw new Error(`Herdr pane ${surface} has no tab id`);
+    execFileSync("herdr", ["tab", "focus", tabId], { encoding: "utf8" });
+    return;
+  }
   execFileSync("tmux", ["select-pane", "-t", surface], { encoding: "utf8" });
 }
 
 export function getFocusedSurface(): string | null {
   try {
+    if (getMuxBackend() === "herdr") {
+      const workspace = process.env.HERDR_WORKSPACE_ID;
+      if (!workspace) return null;
+      const response = parseHerdrJson("herdr", ["pane", "list", "--workspace", workspace]);
+      return response.result?.panes?.find((pane: any) => pane.focused)?.pane_id ?? null;
+    }
+
     const panes = execFileSync("tmux", ["list-panes", "-F", "#{pane_id} #{pane_active}"], {
       encoding: "utf8",
     });
@@ -110,7 +138,7 @@ export async function waitForFocusedSurface(
   }
 
   throw new Error(
-    `Timeout (${timeout}ms) waiting for focused tmux pane ${surface}; ` +
+    `Timeout (${timeout}ms) waiting for focused terminal surface ${surface}; ` +
       `current focus is ${getFocusedSurface() ?? "unknown"}`,
   );
 }
@@ -139,7 +167,13 @@ export function createTestEnv(): TestEnv {
   if (existsSync(TEST_AGENTS_SRC)) {
     for (const file of readdirSync(TEST_AGENTS_SRC)) {
       if (file.endsWith(".md")) {
-        cpSync(join(TEST_AGENTS_SRC, file), join(agentsDir, file));
+        const destination = join(agentsDir, file);
+        cpSync(join(TEST_AGENTS_SRC, file), destination);
+        const definition = readFileSync(destination, "utf8").replace(
+          /^model:\s*.+$/m,
+          `model: ${TEST_MODEL}`,
+        );
+        writeFileSync(destination, definition);
       }
     }
   }
@@ -227,6 +261,9 @@ export function startPi(
     .filter(Boolean)
     .join(" ");
 
+  // Herdr does not retain terminal output for tabs that have never been shown.
+  // Focus the test runner surface so waitForScreen can observe its transcript.
+  focusSurface(surface);
   sendLongCommand(surface, `${cmd}; echo '__TEST_DONE_'$?'__'`, {
     scriptPath: join(testDir, `test-launch-${Date.now()}.sh`),
   });