Files
openclaw/src/cli/gateway-cli/run-loop.test.ts

143 lines
4.7 KiB
TypeScript
Raw Normal View History

import { describe, expect, it, vi } from "vitest";
const acquireGatewayLock = vi.fn(async () => ({
release: vi.fn(async () => {}),
}));
const consumeGatewaySigusr1RestartAuthorization = vi.fn(() => true);
const isGatewaySigusr1RestartExternallyAllowed = vi.fn(() => false);
const markGatewaySigusr1RestartHandled = vi.fn();
const getActiveTaskCount = vi.fn(() => 0);
const waitForActiveTasks = vi.fn(async () => ({ drained: true }));
const resetAllLanes = vi.fn();
const DRAIN_TIMEOUT_LOG = "drain timeout reached; proceeding with restart";
const gatewayLog = {
info: vi.fn(),
warn: vi.fn(),
error: vi.fn(),
};
vi.mock("../../infra/gateway-lock.js", () => ({
acquireGatewayLock: () => acquireGatewayLock(),
}));
vi.mock("../../infra/restart.js", () => ({
consumeGatewaySigusr1RestartAuthorization: () => consumeGatewaySigusr1RestartAuthorization(),
isGatewaySigusr1RestartExternallyAllowed: () => isGatewaySigusr1RestartExternallyAllowed(),
markGatewaySigusr1RestartHandled: () => markGatewaySigusr1RestartHandled(),
}));
Agents: add nested subagent orchestration controls and reduce subagent token waste (#14447) * Agents: add subagent orchestration controls * Agents: add subagent orchestration controls (WIP uncommitted changes) * feat(subagents): add depth-based spawn gating for sub-sub-agents * feat(subagents): tool policy, registry, and announce chain for nested agents * feat(subagents): system prompt, docs, changelog for nested sub-agents * fix(subagents): prevent model fallback override, show model during active runs, and block context overflow fallback Bug 1: When a session has an explicit model override (e.g., gpt/openai-codex), the fallback candidate logic in resolveFallbackCandidates silently appended the global primary model (opus) as a backstop. On reinjection/steer with a transient error, the session could fall back to opus which has a smaller context window and crash. Fix: when storedModelOverride is set, pass fallbacksOverride ?? [] instead of undefined, preventing the implicit primary backstop. Bug 2: Active subagents showed 'model n/a' in /subagents list because resolveModelDisplay only read entry.model/modelProvider (populated after run completes). Fix: fall back to modelOverride/providerOverride fields which are populated at spawn time via sessions.patch. Bug 3: Context overflow errors (prompt too long, context_length_exceeded) could theoretically escape runEmbeddedPiAgent and be treated as failover candidates in runWithModelFallback, causing a switch to a model with a smaller context window. Fix: in runWithModelFallback, detect context overflow errors via isLikelyContextOverflowError and rethrow them immediately instead of trying the next model candidate. * fix(subagents): track spawn depth in session store and fix announce routing for nested agents * Fix compaction status tracking and dedupe overflow compaction triggers * fix(subagents): enforce depth block via session store and implement cascade kill * fix: inject group chat context into system prompt * fix(subagents): always write model to session store at spawn time * Preserve spawnDepth when agent handler rewrites session entry * fix(subagents): suppress announce on steer-restart * fix(subagents): fallback spawned session model to runtime default * fix(subagents): enforce spawn depth when caller key resolves by sessionId * feat(subagents): implement active-first ordering for numeric targets and enhance task display - Added a test to verify that subagents with numeric targets follow an active-first list ordering. - Updated `resolveSubagentTarget` to sort subagent runs based on active status and recent activity. - Enhanced task display in command responses to prevent truncation of long task descriptions. - Introduced new utility functions for compacting task text and managing subagent run states. * fix(subagents): show model for active runs via run record fallback When the spawned model matches the agent's default model, the session store's override fields are intentionally cleared (isDefault: true). The model/modelProvider fields are only populated after the run completes. This left active subagents showing 'model n/a'. Fix: store the resolved model on SubagentRunRecord at registration time, and use it as a fallback in both display paths (subagents tool and /subagents command) when the session store entry has no model info. Changes: - SubagentRunRecord: add optional model field - registerSubagentRun: accept and persist model param - sessions-spawn-tool: pass resolvedModel to registerSubagentRun - subagents-tool: pass run record model as fallback to resolveModelDisplay - commands-subagents: pass run record model as fallback to resolveModelDisplay * feat(chat): implement session key resolution and reset on sidebar navigation - Added functions to resolve the main session key and reset chat state when switching sessions from the sidebar. - Updated the `renderTab` function to handle session key changes when navigating to the chat tab. - Introduced a test to verify that the session resets to "main" when opening chat from the sidebar navigation. * fix: subagent timeout=0 passthrough and fallback prompt duplication Bug 1: runTimeoutSeconds=0 now means 'no timeout' instead of applying 600s default - sessions-spawn-tool: default to undefined (not 0) when neither timeout param is provided; use != null check so explicit 0 passes through to gateway - agent.ts: accept 0 as valid timeout (resolveAgentTimeoutMs already handles 0 → MAX_SAFE_TIMEOUT_MS) Bug 2: model fallback no longer re-injects the original prompt as a duplicate - agent.ts: track fallback attempt index; on retries use a short continuation message instead of the full original prompt since the session file already contains it from the first attempt - Also skip re-sending images on fallback retries (already in session) * feat(subagents): truncate long task descriptions in subagents command output - Introduced a new utility function to format task previews, limiting their length to improve readability. - Updated the command handler to use the new formatting function, ensuring task descriptions are truncated appropriately. - Adjusted related tests to verify that long task descriptions are now truncated in the output. * refactor(subagents): update subagent registry path resolution and improve command output formatting - Replaced direct import of STATE_DIR with a utility function to resolve the state directory dynamically. - Enhanced the formatting of command output for active and recent subagents, adding separators for better readability. - Updated related tests to reflect changes in command output structure. * fix(subagent): default sessions_spawn to no timeout when runTimeoutSeconds omitted The previous fix (75a791106) correctly handled the case where runTimeoutSeconds was explicitly set to 0 ("no timeout"). However, when models omit the parameter entirely (which is common since the schema marks it as optional), runTimeoutSeconds resolved to undefined. undefined flowed through the chain as: sessions_spawn → timeout: undefined (since undefined != null is false) → gateway agent handler → agentCommand opts.timeout: undefined → resolveAgentTimeoutMs({ overrideSeconds: undefined }) → DEFAULT_AGENT_TIMEOUT_SECONDS (600s = 10 minutes) This caused subagents to be killed at exactly 10 minutes even though the user's intent (via TOOLS.md) was for subagents to run without a timeout. Fix: default runTimeoutSeconds to 0 (no timeout) when neither runTimeoutSeconds nor timeoutSeconds is provided by the caller. Subagent spawns are long-running by design and should not inherit the 600s agent-command default timeout. * fix(subagent): accept timeout=0 in agent-via-gateway path (second 600s default) * fix: thread timeout override through getReplyFromConfig dispatch path getReplyFromConfig called resolveAgentTimeoutMs({ cfg }) with no override, always falling back to the config default (600s). Add timeoutOverrideSeconds to GetReplyOptions and pass it through as overrideSeconds so callers of the dispatch chain can specify a custom timeout (0 = no timeout). This complements the existing timeout threading in agentCommand and the cron isolated-agent runner, which already pass overrideSeconds correctly. * feat(model-fallback): normalize OpenAI Codex model references and enhance fallback handling - Added normalization for OpenAI Codex model references, specifically converting "gpt-5.3-codex" to "openai-codex" before execution. - Updated the `resolveFallbackCandidates` function to utilize the new normalization logic. - Enhanced tests to verify the correct behavior of model normalization and fallback mechanisms. - Introduced a new test case to ensure that the normalization process works as expected for various input formats. * feat(tests): add unit tests for steer failure behavior in openclaw-tools - Introduced a new test file to validate the behavior of subagents when steer replacement dispatch fails. - Implemented tests to ensure that the announce behavior is restored correctly and that the suppression reason is cleared as expected. - Enhanced the subagent registry with a new function to clear steer restart suppression. - Updated related components to support the new test scenarios. * fix(subagents): replace stop command with kill in slash commands and documentation - Updated the `/subagents` command to replace `stop` with `kill` for consistency in controlling sub-agent runs. - Modified related documentation to reflect the change in command usage. - Removed legacy timeoutSeconds references from the sessions-spawn-tool schema and tests to streamline timeout handling. - Enhanced tests to ensure correct behavior of the updated commands and their interactions. * feat(tests): add unit tests for readLatestAssistantReply function - Introduced a new test file for the `readLatestAssistantReply` function to validate its behavior with various message scenarios. - Implemented tests to ensure the function correctly retrieves the latest assistant message and handles cases where the latest message has no text. - Mocked the gateway call to simulate different message histories for comprehensive testing. * feat(tests): enhance subagent kill-all cascade tests and announce formatting - Added a new test to verify that the `kill-all` command cascades through ended parents to active descendants in subagents. - Updated the subagent announce formatting tests to reflect changes in message structure, including the replacement of "Findings:" with "Result:" and the addition of new expectations for message content. - Improved the handling of long findings and stats in the announce formatting logic to ensure concise output. - Refactored related functions to enhance clarity and maintainability in the subagent registry and tools. * refactor(subagent): update announce formatting and remove unused constants - Modified the subagent announce formatting to replace "Findings:" with "Result:" and adjusted related expectations in tests. - Removed constants for maximum announce findings characters and summary words, simplifying the announcement logic. - Updated the handling of findings to retain full content instead of truncating, ensuring more informative outputs. - Cleaned up unused imports in the commands-subagents file to enhance code clarity. * feat(tests): enhance billing error handling in user-facing text - Added tests to ensure that normal text mentioning billing plans is not rewritten, preserving user context. - Updated the `isBillingErrorMessage` and `sanitizeUserFacingText` functions to improve handling of billing-related messages. - Introduced new test cases for various scenarios involving billing messages to ensure accurate processing and output. - Enhanced the subagent announce flow to correctly manage active descendant runs, preventing premature announcements. * feat(subagent): enhance workflow guidance and auto-announcement clarity - Added a new guideline in the subagent system prompt to emphasize trust in push-based completion, discouraging busy polling for status updates. - Updated documentation to clarify that sub-agents will automatically announce their results, improving user understanding of the workflow. - Enhanced tests to verify the new guidance on avoiding polling loops and to ensure the accuracy of the updated prompts. * fix(cron): avoid announcing interim subagent spawn acks * chore: clean post-rebase imports * fix(cron): fall back to child replies when parent stays interim * fix(subagents): make active-run guidance advisory * fix(subagents): update announce flow to handle active descendants and enhance test coverage - Modified the announce flow to defer announcements when active descendant runs are present, ensuring accurate status reporting. - Updated tests to verify the new behavior, including scenarios where no fallback requester is available and ensuring proper handling of finished subagents. - Enhanced the announce formatting to include an `expectFinal` flag for better clarity in the announcement process. * fix(subagents): enhance announce flow and formatting for user updates - Updated the announce flow to provide clearer instructions for user updates based on active subagent runs and requester context. - Refactored the announcement logic to improve clarity and ensure internal context remains private. - Enhanced tests to verify the new message expectations and formatting, including updated prompts for user-facing updates. - Introduced a new function to build reply instructions based on session context, improving the overall announcement process. * fix: resolve prep blockers and changelog placement (#14447) (thanks @tyler6204) * fix: restore cron delivery-plan import after rebase (#14447) (thanks @tyler6204) * fix: resolve test failures from rebase conflicts (#14447) (thanks @tyler6204) * fix: apply formatting after rebase (#14447) (thanks @tyler6204)
2026-02-14 22:03:45 -08:00
vi.mock("../../infra/process-respawn.js", () => ({
restartGatewayProcessWithFreshPid: () => ({ mode: "skipped" }),
}));
vi.mock("../../process/command-queue.js", () => ({
getActiveTaskCount: () => getActiveTaskCount(),
waitForActiveTasks: (timeoutMs: number) => waitForActiveTasks(timeoutMs),
resetAllLanes: () => resetAllLanes(),
}));
vi.mock("../../logging/subsystem.js", () => ({
createSubsystemLogger: () => gatewayLog,
}));
function removeNewSignalListeners(
signal: NodeJS.Signals,
existing: Set<(...args: unknown[]) => void>,
) {
for (const listener of process.listeners(signal)) {
const fn = listener as (...args: unknown[]) => void;
if (!existing.has(fn)) {
process.removeListener(signal, fn);
}
}
}
describe("runGatewayLoop", () => {
it("restarts after SIGUSR1 even when drain times out, and resets lanes for the new iteration", async () => {
vi.clearAllMocks();
getActiveTaskCount.mockReturnValueOnce(2).mockReturnValueOnce(0);
waitForActiveTasks.mockResolvedValueOnce({ drained: false });
type StartServer = () => Promise<{
close: (opts: { reason: string; restartExpectedMs: number | null }) => Promise<void>;
}>;
const closeFirst = vi.fn(async () => {});
const closeSecond = vi.fn(async () => {});
const start = vi.fn<StartServer>();
let resolveFirst: (() => void) | null = null;
const startedFirst = new Promise<void>((resolve) => {
resolveFirst = resolve;
});
start.mockImplementationOnce(async () => {
resolveFirst?.();
return { close: closeFirst };
});
let resolveSecond: (() => void) | null = null;
const startedSecond = new Promise<void>((resolve) => {
resolveSecond = resolve;
});
start.mockImplementationOnce(async () => {
resolveSecond?.();
return { close: closeSecond };
});
start.mockRejectedValueOnce(new Error("stop-loop"));
const beforeSigterm = new Set(
process.listeners("SIGTERM") as Array<(...args: unknown[]) => void>,
);
const beforeSigint = new Set(
process.listeners("SIGINT") as Array<(...args: unknown[]) => void>,
);
const beforeSigusr1 = new Set(
process.listeners("SIGUSR1") as Array<(...args: unknown[]) => void>,
);
const { runGatewayLoop } = await import("./run-loop.js");
const loopPromise = runGatewayLoop({
start,
runtime: {
exit: vi.fn(),
} as { exit: (code: number) => never },
});
try {
await startedFirst;
expect(start).toHaveBeenCalledTimes(1);
await new Promise<void>((resolve) => setImmediate(resolve));
process.emit("SIGUSR1");
await startedSecond;
expect(start).toHaveBeenCalledTimes(2);
await new Promise<void>((resolve) => setImmediate(resolve));
expect(waitForActiveTasks).toHaveBeenCalledWith(30_000);
expect(gatewayLog.warn).toHaveBeenCalledWith(DRAIN_TIMEOUT_LOG);
expect(closeFirst).toHaveBeenCalledWith({
reason: "gateway restarting",
restartExpectedMs: 1500,
});
expect(markGatewaySigusr1RestartHandled).toHaveBeenCalledTimes(1);
expect(resetAllLanes).toHaveBeenCalledTimes(1);
process.emit("SIGUSR1");
await expect(loopPromise).rejects.toThrow("stop-loop");
expect(closeSecond).toHaveBeenCalledWith({
reason: "gateway restarting",
restartExpectedMs: 1500,
});
expect(markGatewaySigusr1RestartHandled).toHaveBeenCalledTimes(2);
expect(resetAllLanes).toHaveBeenCalledTimes(2);
} finally {
removeNewSignalListeners("SIGTERM", beforeSigterm);
removeNewSignalListeners("SIGINT", beforeSigint);
removeNewSignalListeners("SIGUSR1", beforeSigusr1);
}
});
});