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

197 lines
6.7 KiB
TypeScript
Raw Normal View History

2026-01-14 01:08:15 +00:00
import type { startGatewayServer } from "../../gateway/server.js";
2026-01-21 22:46:19 +00:00
import { acquireGatewayLock } from "../../infra/gateway-lock.js";
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
import { restartGatewayProcessWithFreshPid } from "../../infra/process-respawn.js";
import {
consumeGatewaySigusr1RestartAuthorization,
isGatewaySigusr1RestartExternallyAllowed,
markGatewaySigusr1RestartHandled,
} from "../../infra/restart.js";
import { createSubsystemLogger } from "../../logging/subsystem.js";
import {
getActiveTaskCount,
resetAllLanes,
waitForActiveTasks,
} from "../../process/command-queue.js";
import { createRestartIterationHook } from "../../process/restart-recovery.js";
import type { defaultRuntime } from "../../runtime.js";
2026-01-14 01:08:15 +00:00
const gatewayLog = createSubsystemLogger("gateway");
type GatewayRunSignalAction = "stop" | "restart";
export async function runGatewayLoop(params: {
start: () => Promise<Awaited<ReturnType<typeof startGatewayServer>>>;
runtime: typeof defaultRuntime;
lockPort?: number;
2026-01-14 01:08:15 +00:00
}) {
let lock = await acquireGatewayLock({ port: params.lockPort });
2026-01-14 01:08:15 +00:00
let server: Awaited<ReturnType<typeof startGatewayServer>> | null = null;
let shuttingDown = false;
let restartResolver: (() => void) | null = null;
const cleanupSignals = () => {
process.removeListener("SIGTERM", onSigterm);
process.removeListener("SIGINT", onSigint);
process.removeListener("SIGUSR1", onSigusr1);
};
const exitProcess = (code: number) => {
cleanupSignals();
params.runtime.exit(code);
};
const releaseLockIfHeld = async (): Promise<boolean> => {
if (!lock) {
return false;
}
await lock.release();
lock = null;
return true;
};
const reacquireLockForInProcessRestart = async (): Promise<boolean> => {
try {
lock = await acquireGatewayLock({ port: params.lockPort });
return true;
} catch (err) {
gatewayLog.error(`failed to reacquire gateway lock for in-process restart: ${String(err)}`);
exitProcess(1);
return false;
}
};
const handleRestartAfterServerClose = async () => {
const hadLock = await releaseLockIfHeld();
// Release the lock BEFORE spawning so the child can acquire it immediately.
const respawn = restartGatewayProcessWithFreshPid();
if (respawn.mode === "spawned" || respawn.mode === "supervised") {
const modeLabel =
respawn.mode === "spawned"
? `spawned pid ${respawn.pid ?? "unknown"}`
: "supervisor restart";
gatewayLog.info(`restart mode: full process restart (${modeLabel})`);
exitProcess(0);
return;
}
if (respawn.mode === "failed") {
gatewayLog.warn(
`full process restart failed (${respawn.detail ?? "unknown error"}); falling back to in-process restart`,
);
} else {
gatewayLog.info("restart mode: in-process restart (OPENCLAW_NO_RESPAWN)");
}
if (hadLock && !(await reacquireLockForInProcessRestart())) {
return;
}
shuttingDown = false;
restartResolver?.();
};
const handleStopAfterServerClose = async () => {
await releaseLockIfHeld();
exitProcess(0);
};
2026-01-14 01:08:15 +00:00
const DRAIN_TIMEOUT_MS = 30_000;
const SHUTDOWN_TIMEOUT_MS = 5_000;
2026-01-14 01:08:15 +00:00
const request = (action: GatewayRunSignalAction, signal: string) => {
if (shuttingDown) {
gatewayLog.info(`received ${signal} during shutdown; ignoring`);
return;
}
shuttingDown = true;
const isRestart = action === "restart";
gatewayLog.info(`received ${signal}; ${isRestart ? "restarting" : "shutting down"}`);
2026-01-14 01:08:15 +00:00
// Allow extra time for draining active turns on restart.
const forceExitMs = isRestart ? DRAIN_TIMEOUT_MS + SHUTDOWN_TIMEOUT_MS : SHUTDOWN_TIMEOUT_MS;
2026-01-14 01:08:15 +00:00
const forceExitTimer = setTimeout(() => {
gatewayLog.error("shutdown timed out; exiting without full cleanup");
exitProcess(0);
}, forceExitMs);
2026-01-14 01:08:15 +00:00
void (async () => {
try {
// On restart, wait for in-flight agent turns to finish before
// tearing down the server so buffered messages are delivered.
if (isRestart) {
const activeTasks = getActiveTaskCount();
if (activeTasks > 0) {
gatewayLog.info(
`draining ${activeTasks} active task(s) before restart (timeout ${DRAIN_TIMEOUT_MS}ms)`,
);
const { drained } = await waitForActiveTasks(DRAIN_TIMEOUT_MS);
if (drained) {
gatewayLog.info("all active tasks drained");
} else {
gatewayLog.warn("drain timeout reached; proceeding with restart");
}
}
}
2026-01-14 01:08:15 +00:00
await server?.close({
reason: isRestart ? "gateway restarting" : "gateway stopping",
restartExpectedMs: isRestart ? 1500 : null,
});
} catch (err) {
gatewayLog.error(`shutdown error: ${String(err)}`);
} finally {
clearTimeout(forceExitTimer);
server = null;
if (isRestart) {
await handleRestartAfterServerClose();
2026-01-14 01:08:15 +00:00
} else {
await handleStopAfterServerClose();
2026-01-14 01:08:15 +00:00
}
}
})();
};
const onSigterm = () => {
gatewayLog.info("signal SIGTERM received");
request("stop", "SIGTERM");
};
const onSigint = () => {
gatewayLog.info("signal SIGINT received");
request("stop", "SIGINT");
};
const onSigusr1 = () => {
gatewayLog.info("signal SIGUSR1 received");
const authorized = consumeGatewaySigusr1RestartAuthorization();
if (!authorized && !isGatewaySigusr1RestartExternallyAllowed()) {
gatewayLog.warn(
"SIGUSR1 restart ignored (not authorized; commands.restart=false or use gateway tool).",
);
return;
}
markGatewaySigusr1RestartHandled();
2026-01-14 01:08:15 +00:00
request("restart", "SIGUSR1");
};
process.on("SIGTERM", onSigterm);
process.on("SIGINT", onSigint);
process.on("SIGUSR1", onSigusr1);
try {
const onIteration = createRestartIterationHook(() => {
// After an in-process restart (SIGUSR1), reset command-queue lane state.
// Interrupted tasks from the previous lifecycle may have left `active`
// counts elevated (their finally blocks never ran), permanently blocking
// new work from draining. This must happen here — at the restart
// coordinator level — rather than inside individual subsystem init
// functions, to avoid surprising cross-cutting side effects.
resetAllLanes();
});
2026-01-14 01:08:15 +00:00
// Keep process alive; SIGUSR1 triggers an in-process restart (no supervisor required).
// SIGTERM/SIGINT still exit after a graceful shutdown.
// eslint-disable-next-line no-constant-condition
while (true) {
onIteration();
2026-01-14 01:08:15 +00:00
server = await params.start();
await new Promise<void>((resolve) => {
restartResolver = resolve;
});
}
} finally {
await releaseLockIfHeld();
2026-01-14 01:08:15 +00:00
cleanupSignals();
}
}