openclaw/src/agents/pi-embedded-runner/run.overflow-compaction.test.ts

import { describe, expect, it, vi, beforeEach } from "vitest";

vi.mock("./run/attempt.js", () => ({
  runEmbeddedAttempt: vi.fn(),
}));

vi.mock("./compact.js", () => ({
  compactEmbeddedPiSessionDirect: vi.fn(),
}));

vi.mock("./model.js", () => ({
  resolveModel: vi.fn(() => ({
    model: {
      id: "test-model",
      provider: "anthropic",
      contextWindow: 200000,
      api: "messages",
    },
    error: null,
    authStorage: {
      setRuntimeApiKey: vi.fn(),
    },
    modelRegistry: {},
  })),
}));

vi.mock("../model-auth.js", () => ({
  ensureAuthProfileStore: vi.fn(() => ({})),
  getApiKeyForModel: vi.fn(async () => ({
    apiKey: "test-key",
    profileId: "test-profile",
    source: "test",
  })),
  resolveAuthProfileOrder: vi.fn(() => []),
}));

vi.mock("../models-config.js", () => ({
  ensureClawdbotModelsJson: vi.fn(async () => {}),
}));

vi.mock("../context-window-guard.js", () => ({
  CONTEXT_WINDOW_HARD_MIN_TOKENS: 1000,
  CONTEXT_WINDOW_WARN_BELOW_TOKENS: 5000,
  evaluateContextWindowGuard: vi.fn(() => ({
    shouldWarn: false,
    shouldBlock: false,
    tokens: 200000,
    source: "model",
  })),
  resolveContextWindowInfo: vi.fn(() => ({
    tokens: 200000,
    source: "model",
  })),
}));

vi.mock("../../process/command-queue.js", () => ({
  enqueueCommandInLane: vi.fn((_lane: string, task: () => unknown) => task()),
}));

vi.mock("../../utils.js", () => ({
  resolveUserPath: vi.fn((p: string) => p),
}));

vi.mock("../../utils/message-channel.js", () => ({
  isMarkdownCapableMessageChannel: vi.fn(() => true),
}));

vi.mock("../agent-paths.js", () => ({
  resolveClawdbotAgentDir: vi.fn(() => "/tmp/agent-dir"),
}));

vi.mock("../auth-profiles.js", () => ({
  markAuthProfileFailure: vi.fn(async () => {}),
  markAuthProfileGood: vi.fn(async () => {}),
  markAuthProfileUsed: vi.fn(async () => {}),
}));

vi.mock("../defaults.js", () => ({
  DEFAULT_CONTEXT_TOKENS: 200000,
  DEFAULT_MODEL: "test-model",
  DEFAULT_PROVIDER: "anthropic",
}));

vi.mock("../failover-error.js", () => ({
  FailoverError: class extends Error {
    constructor(msg: string) {
      super(msg);
    }
  },
  resolveFailoverStatus: vi.fn(),
}));

vi.mock("../usage.js", () => ({
  normalizeUsage: vi.fn(() => undefined),
}));

vi.mock("./lanes.js", () => ({
  resolveSessionLane: vi.fn(() => "session-lane"),
  resolveGlobalLane: vi.fn(() => "global-lane"),
}));

vi.mock("./logger.js", () => ({
  log: {
    debug: vi.fn(),
    info: vi.fn(),
    warn: vi.fn(),
    error: vi.fn(),
  },
}));

vi.mock("./run/payloads.js", () => ({
  buildEmbeddedRunPayloads: vi.fn(() => []),
}));

vi.mock("./utils.js", () => ({
  describeUnknownError: vi.fn((err: unknown) => {
    if (err instanceof Error) return err.message;
    return String(err);
  }),
}));

vi.mock("../pi-embedded-helpers.js", async () => {
  return {
    isCompactionFailureError: (msg?: string) => {
      if (!msg) return false;
      const lower = msg.toLowerCase();
      return lower.includes("request_too_large") && lower.includes("summarization failed");
    },
    isContextOverflowError: (msg?: string) => {
      if (!msg) return false;
      const lower = msg.toLowerCase();
      return lower.includes("request_too_large") || lower.includes("request size exceeds");
    },
    isFailoverAssistantError: vi.fn(() => false),
    isFailoverErrorMessage: vi.fn(() => false),
    isAuthAssistantError: vi.fn(() => false),
    isRateLimitAssistantError: vi.fn(() => false),
    classifyFailoverReason: vi.fn(() => null),
    formatAssistantErrorText: vi.fn(() => ""),
    pickFallbackThinkingLevel: vi.fn(() => null),
    isTimeoutErrorMessage: vi.fn(() => false),
    parseImageDimensionError: vi.fn(() => null),
  };
});

import { runEmbeddedPiAgent } from "./run.js";
import { runEmbeddedAttempt } from "./run/attempt.js";
import { compactEmbeddedPiSessionDirect } from "./compact.js";
import { log } from "./logger.js";

import type { EmbeddedRunAttemptResult } from "./run/types.js";

const mockedRunEmbeddedAttempt = vi.mocked(runEmbeddedAttempt);
const mockedCompactDirect = vi.mocked(compactEmbeddedPiSessionDirect);

function makeAttemptResult(
  overrides: Partial<EmbeddedRunAttemptResult> = {},
): EmbeddedRunAttemptResult {
  return {
    aborted: false,
    timedOut: false,
    promptError: null,
    sessionIdUsed: "test-session",
    assistantTexts: ["Hello!"],
    toolMetas: [],
    lastAssistant: undefined,
    messagesSnapshot: [],
    didSendViaMessagingTool: false,
    messagingToolSentTexts: [],
    messagingToolSentTargets: [],
    cloudCodeAssistFormatError: false,
    ...overrides,
  };
}

const baseParams = {
  sessionId: "test-session",
  sessionKey: "test-key",
  sessionFile: "/tmp/session.json",
  workspaceDir: "/tmp/workspace",
  prompt: "hello",
  timeoutMs: 30000,
  runId: "run-1",
};

describe("overflow compaction in run loop", () => {
  beforeEach(() => {
    vi.clearAllMocks();
  });

  it("retries after successful compaction on context overflow promptError", async () => {
    const overflowError = new Error("request_too_large: Request size exceeds model context window");

    mockedRunEmbeddedAttempt
      .mockResolvedValueOnce(makeAttemptResult({ promptError: overflowError }))
      .mockResolvedValueOnce(makeAttemptResult({ promptError: null }));

    mockedCompactDirect.mockResolvedValueOnce({
      ok: true,
      compacted: true,
      result: {
        summary: "Compacted session",
        firstKeptEntryId: "entry-5",
        tokensBefore: 150000,
      },
    });

    const result = await runEmbeddedPiAgent(baseParams);

    expect(mockedCompactDirect).toHaveBeenCalledTimes(1);
    expect(mockedCompactDirect).toHaveBeenCalledWith(
      expect.objectContaining({ authProfileId: "test-profile" }),
    );
    expect(mockedRunEmbeddedAttempt).toHaveBeenCalledTimes(2);
    expect(log.warn).toHaveBeenCalledWith(
      expect.stringContaining("context overflow detected; attempting auto-compaction"),
    );
    expect(log.info).toHaveBeenCalledWith(expect.stringContaining("auto-compaction succeeded"));
    // Should not be an error result
    expect(result.meta.error).toBeUndefined();
  });

  it("returns error if compaction fails", async () => {
    const overflowError = new Error("request_too_large: Request size exceeds model context window");

    mockedRunEmbeddedAttempt.mockResolvedValue(makeAttemptResult({ promptError: overflowError }));

    mockedCompactDirect.mockResolvedValueOnce({
      ok: false,
      compacted: false,
      reason: "nothing to compact",
    });

    const result = await runEmbeddedPiAgent(baseParams);

    expect(mockedCompactDirect).toHaveBeenCalledTimes(1);
    expect(mockedRunEmbeddedAttempt).toHaveBeenCalledTimes(1);
    expect(result.meta.error?.kind).toBe("context_overflow");
    expect(result.payloads?.[0]?.isError).toBe(true);
    expect(log.warn).toHaveBeenCalledWith(expect.stringContaining("auto-compaction failed"));
  });

  it("returns error if overflow happens again after compaction", async () => {
    const overflowError = new Error("request_too_large: Request size exceeds model context window");

    mockedRunEmbeddedAttempt
      .mockResolvedValueOnce(makeAttemptResult({ promptError: overflowError }))
      .mockResolvedValueOnce(makeAttemptResult({ promptError: overflowError }));

    mockedCompactDirect.mockResolvedValueOnce({
      ok: true,
      compacted: true,
      result: {
        summary: "Compacted",
        firstKeptEntryId: "entry-3",
        tokensBefore: 180000,
      },
    });

    const result = await runEmbeddedPiAgent(baseParams);

    // Compaction attempted only once
    expect(mockedCompactDirect).toHaveBeenCalledTimes(1);
    // Two attempts: first overflow -> compact -> retry -> second overflow -> return error
    expect(mockedRunEmbeddedAttempt).toHaveBeenCalledTimes(2);
    expect(result.meta.error?.kind).toBe("context_overflow");
    expect(result.payloads?.[0]?.isError).toBe(true);
  });

  it("does not attempt compaction for compaction_failure errors", async () => {
    const compactionFailureError = new Error(
      "request_too_large: summarization failed - Request size exceeds model context window",
    );

    mockedRunEmbeddedAttempt.mockResolvedValue(
      makeAttemptResult({ promptError: compactionFailureError }),
    );

    const result = await runEmbeddedPiAgent(baseParams);

    expect(mockedCompactDirect).not.toHaveBeenCalled();
    expect(mockedRunEmbeddedAttempt).toHaveBeenCalledTimes(1);
    expect(result.meta.error?.kind).toBe("compaction_failure");
  });
});