@tt-a1i/openpi 0.1.0

package/extensions/subagents/src/backend.ts

@@ -0,0 +1,63 @@
+/**
+ * The backend interface: one `SubagentBackend` per agent runtime, all
+ * producing the same `SubagentSession` shape. The interface survives the
+ * single-backend world because the manager, the UI, and the tests all depend
+ * on it rather than on the pi session directly.
+ *
+ * - pi (./backends/pi.ts): in-process `createAgentSession()` via the pi SDK.
+ * - stub (./backends/stub.ts): scripted sessions, test-only.
+ */
+
+import type { Effect, Scope, Stream } from "effect";
+import { Context } from "effect";
+import type {
+  BackendName,
+  SendError,
+  SpawnError,
+  SpawnTask,
+  SubagentEvent,
+  SubagentMeta,
+} from "./domain.ts";
+
+/**
+ * A live subagent session. The manager is the single consumer of `events`;
+ * it folds them into the `SubagentSnapshot` everything else reads.
+ */
+export interface SubagentSession {
+  /** Current metadata snapshot. Updates also arrive as MetaChanged events. */
+  readonly meta: Effect.Effect<SubagentMeta>;
+  /**
+   * All activity, normalized. Ends when the session's scope closes. Every
+   * run started within the session terminates with a RunSettled event.
+   */
+  readonly events: Stream.Stream<SubagentEvent>;
+  /**
+   * Steer the active run, or start a fresh run when idle (v1 `manager.send`
+   * semantics — the "is a run active" decision is backend-native state).
+   */
+  send(text: string): Effect.Effect<void, SendError>;
+  /**
+   * Interrupt the active run. Resolves once the backend acknowledges; the
+   * corresponding RunSettled(Interrupted) arrives on `events`. Callers bound
+   * this with a timeout and fall back to closing the session scope.
+   */
+  readonly interrupt: Effect.Effect<void>;
+}
+
+export interface SubagentBackend {
+  readonly name: BackendName;
+  /**
+   * Spawn a session. Scoped: closing the scope interrupts/kills the
+   * underlying session or process and ends `events`. Fire-and-forget
+   * semantics (background fibers, result delivery) live in the manager.
+   */
+  spawn(
+    task: SpawnTask,
+  ): Effect.Effect<SubagentSession, SpawnError, Scope.Scope>;
+}
+
+/** Registry of all wired backends, keyed by name. */
+export class BackendRegistry extends Context.Service<
+  BackendRegistry,
+  ReadonlyMap<BackendName, SubagentBackend>
+>()("subagents/BackendRegistry") {}

package/extensions/subagents/src/backends/pi.ts

@@ -0,0 +1,493 @@
+/**
+ * pi backend — real implementation over the pi SDK.
+ *
+ * Each subagent is an in-process `AgentSession` (a port of v1
+ * subagents/manager.ts, reusing the shared child-session helpers in
+ * extensions/shared/child-session.ts):
+ * - real session files visible in /resume, child resources loaded per-cwd
+ *   with trust gating, and the child tool denylist;
+ * - `session.subscribe()` events translated to normalized SubagentEvents;
+ * - send() steers a streaming run or starts a fresh prompt() when idle;
+ * - interrupt clears the queue and aborts; closing the session scope emits
+ *   the child session_shutdown hook and disposes the session.
+ */
+
+import type { AssistantMessage, Message, Model } from "@earendil-works/pi-ai";
+import type {
+  AgentSession,
+  AgentSessionEvent,
+} from "@earendil-works/pi-coding-agent";
+import {
+  createAgentSession,
+  SessionManager,
+} from "@earendil-works/pi-coding-agent";
+import type { Cause, Scope } from "effect";
+import { Effect, Queue, Stream } from "effect";
+import { resolveAgentModel } from "../agent-types.ts";
+import type { SubagentBackend, SubagentSession } from "../backend.ts";
+import type {
+  SpawnTask,
+  SubagentEvent,
+  SubagentMeta,
+  TranscriptPart,
+} from "../domain.ts";
+import { SendError, SpawnError } from "../domain.ts";
+import { createToolCallTimeoutGuard } from "../../../shared/tool-call-timeout.ts";
+import {
+  bindChildSessionExtensions,
+  CHILD_SHUTDOWN_TIMEOUT_MS,
+  childToolPolicy,
+  createChildResources,
+  shutdownAndDisposeChildSession,
+} from "../../../shared/child-session.ts";
+import { reclaimWorktree } from "../../../shared/worktree.ts";
+
+const DIRECT_WORKTREE_CLEANUP_TIMEOUT_MS = 4_000;
+
+// --- Model + effort resolution -----------------------------------------------
+
+type ThinkingLevel = NonNullable<
+  NonNullable<Parameters<typeof createAgentSession>[0]>["thinkingLevel"]
+>;
+
+// --- Event translation ----------------------------------------------------------
+
+function messageRole(msg: unknown): Message["role"] | undefined {
+  const role = (msg as { role?: string } | undefined)?.role;
+  if (role === "user" || role === "assistant" || role === "toolResult")
+    return role;
+  return undefined;
+}
+
+function lastAssistantMessage(
+  session: AgentSession,
+): AssistantMessage | undefined {
+  const messages = session.messages;
+  for (let i = messages.length - 1; i >= 0; i--) {
+    const msg = messages[i];
+    if (messageRole(msg) === "assistant") return msg as AssistantMessage;
+  }
+  return undefined;
+}
+
+/** Final assistant text output (last assistant message with text), v1 semantics. */
+function finalOutput(session: AgentSession): string {
+  const messages = session.messages;
+  for (let i = messages.length - 1; i >= 0; i--) {
+    const msg = messages[i];
+    if (messageRole(msg) !== "assistant") continue;
+    const text = (msg as AssistantMessage).content
+      .filter((part) => part.type === "text")
+      .map((part) => part.text)
+      .join("\n")
+      .trim();
+    if (text) return text;
+  }
+  return "";
+}
+
+function safeJson(value: unknown): string | undefined {
+  try {
+    const text = JSON.stringify(value);
+    return text === "{}" ? undefined : text.slice(0, 4_096);
+  } catch {
+    return undefined;
+  }
+}
+
+/** First non-empty line of a tool result-ish value (v1 liveToolPreview). */
+function toolPreview(value: unknown): string | undefined {
+  if (typeof value === "string") {
+    return value
+      .split("\n")
+      .find((line) => line.trim())
+      ?.trim();
+  }
+  if (!value || typeof value !== "object") return undefined;
+  const content = (value as { content?: unknown }).content;
+  if (!Array.isArray(content)) return undefined;
+  for (const part of content) {
+    if (!part || typeof part !== "object") continue;
+    const record = part as { type?: unknown; text?: unknown };
+    if (record.type !== "text" || typeof record.text !== "string") continue;
+    const firstLine = record.text.split("\n").find((line) => line.trim());
+    if (firstLine) return firstLine.trim();
+  }
+  return undefined;
+}
+
+function assistantParts(msg: AssistantMessage): TranscriptPart[] {
+  const parts: TranscriptPart[] = [];
+  for (const part of msg.content) {
+    if (part.type === "text") {
+      parts.push({ type: "text", text: part.text });
+    } else if (part.type === "thinking") {
+      parts.push({
+        type: "thinking",
+        text: part.redacted ? "" : part.thinking,
+        redacted: part.redacted,
+      });
+    } else if (part.type === "toolCall") {
+      parts.push({
+        type: "toolCall",
+        toolId: part.id,
+        name: part.name,
+        argsPreview: safeJson(part.arguments),
+      });
+    }
+  }
+  return parts;
+}
+
+function userText(msg: Message): string {
+  const content = (msg as { content: unknown }).content;
+  if (typeof content === "string") return content;
+  if (!Array.isArray(content)) return "";
+  return content
+    .filter(
+      (part): part is { type: "text"; text: string } =>
+        !!part &&
+        typeof part === "object" &&
+        (part as { type?: unknown }).type === "text",
+    )
+    .map((part) => part.text)
+    .join("\n");
+}
+
+// --- The session ------------------------------------------------------------------
+
+function boundedError(error: unknown) {
+  return (error instanceof Error ? error.message : String(error)).slice(
+    0,
+    4096,
+  );
+}
+
+const makePiSession = (
+  task: SpawnTask,
+): Effect.Effect<SubagentSession, SpawnError, Scope.Scope> =>
+  Effect.gen(function* () {
+    const registry = task.parent.modelRegistry;
+    if (!registry) {
+      return yield* new SpawnError({
+        message: "pi backend requires the parent session's model registry.",
+      });
+    }
+
+    const model = yield* Effect.try({
+      try: () =>
+        resolveAgentModel(registry, task.model, task.parent.inheritedModel),
+      catch: (error) => new SpawnError({ message: boundedError(error) }),
+    });
+    // pi's thinking levels ARE the shared reasoning-effort scale.
+    const thinkingLevel = (task.reasoningEffort ??
+      task.parent.inheritedThinkingLevel) as ThinkingLevel | undefined;
+
+    const session = yield* Effect.tryPromise({
+      try: async () => {
+        const { loader, settingsManager } = await createChildResources({
+          cwd: task.cwd,
+          projectTrusted: task.parent.projectTrusted,
+          ...(task.appendSystemPrompt
+            ? { appendSystemPrompt: [...task.appendSystemPrompt] }
+            : {}),
+        });
+        const { session } = await createAgentSession({
+          cwd: task.cwd,
+          sessionManager: SessionManager.create(task.cwd),
+          settingsManager,
+          resourceLoader: loader,
+          model,
+          thinkingLevel,
+          ...childToolPolicy(task.tools),
+        });
+        // Start child extension session hooks/resources in headless mode.
+        // A rejection here would otherwise leak the freshly created session:
+        // the scope finalizer that owns cleanup is only registered later.
+        try {
+          await bindChildSessionExtensions(session, task.tools);
+        } catch (error) {
+          await shutdownAndDisposeChildSession(session);
+          throw error;
+        }
+        return session;
+      },
+      catch: (error) => new SpawnError({ message: boundedError(error) }),
+    });
+
+    const state = {
+      closed: false,
+      /** prompt() rejection for the active run; folded into RunSettled. */
+      runError: undefined as string | undefined,
+      /** One terminal event per run: lifecycle, prompt-rejection, and abort
+       * fallbacks can all race to settle; the first wins. */
+      settled: false,
+    };
+
+    const events = yield* Queue.make<SubagentEvent, Cause.Done>();
+    const emit = (event: SubagentEvent) => {
+      Queue.offerUnsafe(events, event);
+    };
+
+    const toolTimeout = createToolCallTimeoutGuard();
+    toolTimeout.apply(session);
+
+    const activeModel = (): Model<any> | undefined => {
+      const sessionModel = session.model;
+      const last = lastAssistantMessage(session);
+      if (!last) return sessionModel;
+      if (
+        sessionModel &&
+        (last.provider !== sessionModel.provider ||
+          last.model !== sessionModel.id)
+      ) {
+        // The session changed models after this assistant response.
+        return sessionModel;
+      }
+      return (
+        registry.find(last.provider, last.responseModel ?? last.model) ??
+        sessionModel
+      );
+    };
+
+    const currentMeta = (): SubagentMeta => {
+      const m = activeModel();
+      return {
+        backend: "pi",
+        modelLabel: m ? `${m.provider}/${m.id}` : undefined,
+        contextWindow: m?.contextWindow,
+        sessionFilePath: session.sessionFile,
+      };
+    };
+
+    const emitUsage = () => {
+      const usage = session.getContextUsage();
+      emit({
+        _tag: "UsageChanged",
+        tokens: usage?.tokens ?? undefined,
+        contextWindow: activeModel()?.contextWindow ?? usage?.contextWindow,
+      });
+    };
+
+    const settle = () => {
+      if (state.settled) return;
+      state.settled = true;
+      const last = lastAssistantMessage(session);
+      const partialText = finalOutput(session) || undefined;
+      if (last?.stopReason === "aborted") {
+        emit({
+          _tag: "RunSettled",
+          outcome: { _tag: "Interrupted", partialText },
+        });
+        return;
+      }
+      const errorText =
+        state.runError ??
+        (last?.stopReason === "error"
+          ? (last.errorMessage ?? "Run failed")
+          : undefined);
+      if (errorText !== undefined) {
+        emit({
+          _tag: "RunSettled",
+          outcome: {
+            _tag: "Failed",
+            errorText: boundedError(errorText),
+            partialText,
+          },
+        });
+        return;
+      }
+      emit({
+        _tag: "RunSettled",
+        outcome: { _tag: "Completed", finalText: finalOutput(session) },
+      });
+    };
+
+    const handleEvent = (event: AgentSessionEvent) => {
+      if (state.closed) return;
+      switch (event.type) {
+        case "agent_start":
+          // Extensions may register tools between runs; guard new ones too.
+          toolTimeout.apply(session);
+          state.settled = false;
+          emit({ _tag: "RunStarted" });
+          break;
+        case "message_update": {
+          const streamEvent = event.assistantMessageEvent;
+          if (streamEvent.type === "text_delta") {
+            emit({
+              _tag: "AssistantDelta",
+              kind: "text",
+              delta: streamEvent.delta,
+            });
+          } else if (streamEvent.type === "thinking_delta") {
+            emit({
+              _tag: "AssistantDelta",
+              kind: "thinking",
+              delta: streamEvent.delta,
+            });
+          }
+          break;
+        }
+        case "message_end": {
+          const role = messageRole(event.message);
+          if (role === "user") {
+            const text = userText(event.message as Message);
+            if (text.trim()) emit({ _tag: "UserMessage", text });
+          } else if (role === "assistant") {
+            emit({
+              _tag: "AssistantMessage",
+              parts: assistantParts(event.message as AssistantMessage),
+            });
+            emitUsage();
+            emit({ _tag: "MetaChanged", meta: currentMeta() });
+          }
+          // toolResult messages are covered by tool_execution_end.
+          break;
+        }
+        case "tool_execution_start":
+          emit({
+            _tag: "ToolStart",
+            toolId: event.toolCallId,
+            name: event.toolName,
+            argsPreview: safeJson(event.args),
+          });
+          break;
+        case "tool_execution_update":
+          emit({
+            _tag: "ToolUpdate",
+            toolId: event.toolCallId,
+            outputPreview: toolPreview(event.partialResult),
+          });
+          break;
+        case "tool_execution_end":
+          emit({
+            _tag: "ToolEnd",
+            toolId: event.toolCallId,
+            name: event.toolName,
+            isError: event.isError,
+            outputPreview: toolPreview(event.result),
+          });
+          break;
+        case "queue_update":
+          emit({
+            _tag: "QueueChanged",
+            queued: [
+              ...event.steering.map((text) => ({
+                text,
+                kind: "steer" as const,
+              })),
+              ...event.followUp.map((text) => ({
+                text,
+                kind: "follow-up" as const,
+              })),
+            ],
+          });
+          break;
+        case "agent_settled":
+          settle();
+          break;
+      }
+    };
+    const unsubscribe = session.subscribe(handleEvent);
+
+    yield* Effect.addFinalizer(() =>
+      Effect.promise(async () => {
+        state.closed = true;
+        unsubscribe();
+        try {
+          session.clearQueue();
+        } catch {
+          // Continue with abort/dispose.
+        }
+        await shutdownAndDisposeChildSession(session, {
+          abort: true,
+          timeoutMs: CHILD_SHUTDOWN_TIMEOUT_MS,
+        });
+        // A direct child can run multiple turns, so its worktree lives until
+        // this session scope closes. Cleanup is fail-closed and shares a hard
+        // deadline; unknown/dirty/ignored/detached work is preserved.
+        if (task.worktree) {
+          await reclaimWorktree(task.worktree.repoCwd, task.worktree, {
+            timeoutMs: DIRECT_WORKTREE_CLEANUP_TIMEOUT_MS,
+          }).catch(() => {});
+        }
+        Queue.endUnsafe(events);
+      }),
+    );
+
+    /** Start a fresh run (v1 manager.run): fire-and-forget, errors -> events. */
+    const startRun = (text: string) => {
+      state.runError = undefined;
+      state.settled = false;
+      emit({ _tag: "RunStarted" });
+      void session.prompt(text).catch((error) => {
+        state.runError = boundedError(error);
+        // Preflight failures may never start the agent lifecycle, so no
+        // agent_settled will arrive for them.
+        if (!session.isStreaming) settle();
+      });
+    };
+
+    // Session naming is best-effort.
+    const kind =
+      task.origin === "btw"
+        ? "btw"
+        : task.agentTypeName
+          ? `subagent[${task.agentTypeName}]`
+          : "subagent";
+    yield* Effect.try(() =>
+      session.sessionManager.appendSessionInfo(`${kind}: ${task.title}`),
+    ).pipe(Effect.ignore);
+
+    emit({ _tag: "MetaChanged", meta: currentMeta() });
+    startRun(task.prompt);
+
+    return {
+      meta: Effect.sync(currentMeta),
+      events: Stream.fromQueue(events),
+      send: (text) =>
+        Effect.suspend((): Effect.Effect<void, SendError> => {
+          if (state.closed) {
+            return new SendError({ message: "Subagent session is closed." });
+          }
+          if (session.isStreaming) {
+            // Steer the active run via the SDK's queue; queue_update events
+            // render it, message_end(user) lands it in the transcript. A
+            // rejected steer is a real send failure, not a diagnostic.
+            return Effect.tryPromise({
+              try: () => session.steer(text),
+              catch: (error) => new SendError({ message: boundedError(error) }),
+            }).pipe(Effect.asVoid);
+          }
+          return Effect.sync(() => startRun(text));
+        }),
+      interrupt: Effect.promise(async () => {
+        if (state.closed) return;
+        try {
+          session.clearQueue();
+        } catch {
+          // Abort regardless.
+        }
+        await session.abort().catch(() => undefined);
+        // Only resolve once streaming has actually stopped: reporting the
+        // interrupt as complete while the run keeps working would let the
+        // manager settle a run that is still mutating the workspace. The
+        // manager bounds this effect at 5s and force-disposes on timeout.
+        while (!state.closed && session.isStreaming) {
+          await new Promise((resolve) => setTimeout(resolve, 50));
+        }
+        // No streaming run means no agent_settled will arrive; emit the
+        // terminal event (once) so the run cannot look running forever.
+        if (!state.closed && !state.settled) {
+          state.settled = true;
+          emit({ _tag: "RunSettled", outcome: { _tag: "Interrupted" } });
+        }
+      }),
+    } satisfies SubagentSession;
+  });
+
+export const piBackend: SubagentBackend = {
+  name: "pi",
+  spawn: makePiSession,
+};