Files
openclaw/src/agents/subagent-announce.ts
Tyler Yust b8f66c260d 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

618 lines
22 KiB
TypeScript

import crypto from "node:crypto";
import { resolveQueueSettings } from "../auto-reply/reply/queue.js";
import { loadConfig } from "../config/config.js";
import {
loadSessionStore,
resolveAgentIdFromSessionKey,
resolveMainSessionKey,
resolveStorePath,
} from "../config/sessions.js";
import { callGateway } from "../gateway/call.js";
import { normalizeMainKey } from "../routing/session-key.js";
import { defaultRuntime } from "../runtime.js";
import {
type DeliveryContext,
deliveryContextFromSession,
mergeDeliveryContext,
normalizeDeliveryContext,
} from "../utils/delivery-context.js";
import {
isEmbeddedPiRunActive,
queueEmbeddedPiMessage,
waitForEmbeddedPiRunEnd,
} from "./pi-embedded.js";
import { type AnnounceQueueItem, enqueueAnnounce } from "./subagent-announce-queue.js";
import { getSubagentDepthFromSessionStore } from "./subagent-depth.js";
import { readLatestAssistantReply } from "./tools/agent-step.js";
function formatDurationShort(valueMs?: number) {
if (!valueMs || !Number.isFinite(valueMs) || valueMs <= 0) {
return "n/a";
}
const totalSeconds = Math.round(valueMs / 1000);
const hours = Math.floor(totalSeconds / 3600);
const minutes = Math.floor((totalSeconds % 3600) / 60);
const seconds = totalSeconds % 60;
if (hours > 0) {
return `${hours}h${minutes}m`;
}
if (minutes > 0) {
return `${minutes}m${seconds}s`;
}
return `${seconds}s`;
}
function formatTokenCount(value?: number) {
if (typeof value !== "number" || !Number.isFinite(value) || value <= 0) {
return "0";
}
if (value >= 1_000_000) {
return `${(value / 1_000_000).toFixed(1)}m`;
}
if (value >= 1_000) {
return `${(value / 1_000).toFixed(1)}k`;
}
return String(Math.round(value));
}
async function buildCompactAnnounceStatsLine(params: {
sessionKey: string;
startedAt?: number;
endedAt?: number;
}) {
const cfg = loadConfig();
const agentId = resolveAgentIdFromSessionKey(params.sessionKey);
const storePath = resolveStorePath(cfg.session?.store, { agentId });
let entry = loadSessionStore(storePath)[params.sessionKey];
for (let attempt = 0; attempt < 3; attempt += 1) {
const hasTokenData =
typeof entry?.inputTokens === "number" ||
typeof entry?.outputTokens === "number" ||
typeof entry?.totalTokens === "number";
if (hasTokenData) {
break;
}
await new Promise((resolve) => setTimeout(resolve, 150));
entry = loadSessionStore(storePath)[params.sessionKey];
}
const input = typeof entry?.inputTokens === "number" ? entry.inputTokens : 0;
const output = typeof entry?.outputTokens === "number" ? entry.outputTokens : 0;
const ioTotal = input + output;
const promptCache = typeof entry?.totalTokens === "number" ? entry.totalTokens : undefined;
const runtimeMs =
typeof params.startedAt === "number" && typeof params.endedAt === "number"
? Math.max(0, params.endedAt - params.startedAt)
: undefined;
const parts = [
`runtime ${formatDurationShort(runtimeMs)}`,
`tokens ${formatTokenCount(ioTotal)} (in ${formatTokenCount(input)} / out ${formatTokenCount(output)})`,
];
if (typeof promptCache === "number" && promptCache > ioTotal) {
parts.push(`prompt/cache ${formatTokenCount(promptCache)}`);
}
return `Stats: ${parts.join(" • ")}`;
}
type DeliveryContextSource = Parameters<typeof deliveryContextFromSession>[0];
function resolveAnnounceOrigin(
entry?: DeliveryContextSource,
requesterOrigin?: DeliveryContext,
): DeliveryContext | undefined {
// requesterOrigin (captured at spawn time) reflects the channel the user is
// actually on and must take priority over the session entry, which may carry
// stale lastChannel / lastTo values from a previous channel interaction.
return mergeDeliveryContext(requesterOrigin, deliveryContextFromSession(entry));
}
async function sendAnnounce(item: AnnounceQueueItem) {
const requesterDepth = getSubagentDepthFromSessionStore(item.sessionKey);
const requesterIsSubagent = requesterDepth >= 1;
const origin = item.origin;
const threadId =
origin?.threadId != null && origin.threadId !== "" ? String(origin.threadId) : undefined;
await callGateway({
method: "agent",
params: {
sessionKey: item.sessionKey,
message: item.prompt,
channel: requesterIsSubagent ? undefined : origin?.channel,
accountId: requesterIsSubagent ? undefined : origin?.accountId,
to: requesterIsSubagent ? undefined : origin?.to,
threadId: requesterIsSubagent ? undefined : threadId,
deliver: !requesterIsSubagent,
idempotencyKey: crypto.randomUUID(),
},
timeoutMs: 15_000,
});
}
function resolveRequesterStoreKey(
cfg: ReturnType<typeof loadConfig>,
requesterSessionKey: string,
): string {
const raw = requesterSessionKey.trim();
if (!raw) {
return raw;
}
if (raw === "global" || raw === "unknown") {
return raw;
}
if (raw.startsWith("agent:")) {
return raw;
}
const mainKey = normalizeMainKey(cfg.session?.mainKey);
if (raw === "main" || raw === mainKey) {
return resolveMainSessionKey(cfg);
}
const agentId = resolveAgentIdFromSessionKey(raw);
return `agent:${agentId}:${raw}`;
}
function loadRequesterSessionEntry(requesterSessionKey: string) {
const cfg = loadConfig();
const canonicalKey = resolveRequesterStoreKey(cfg, requesterSessionKey);
const agentId = resolveAgentIdFromSessionKey(canonicalKey);
const storePath = resolveStorePath(cfg.session?.store, { agentId });
const store = loadSessionStore(storePath);
const entry = store[canonicalKey];
return { cfg, entry, canonicalKey };
}
async function maybeQueueSubagentAnnounce(params: {
requesterSessionKey: string;
triggerMessage: string;
summaryLine?: string;
requesterOrigin?: DeliveryContext;
}): Promise<"steered" | "queued" | "none"> {
const { cfg, entry } = loadRequesterSessionEntry(params.requesterSessionKey);
const canonicalKey = resolveRequesterStoreKey(cfg, params.requesterSessionKey);
const sessionId = entry?.sessionId;
if (!sessionId) {
return "none";
}
const queueSettings = resolveQueueSettings({
cfg,
channel: entry?.channel ?? entry?.lastChannel,
sessionEntry: entry,
});
const isActive = isEmbeddedPiRunActive(sessionId);
const shouldSteer = queueSettings.mode === "steer" || queueSettings.mode === "steer-backlog";
if (shouldSteer) {
const steered = queueEmbeddedPiMessage(sessionId, params.triggerMessage);
if (steered) {
return "steered";
}
}
const shouldFollowup =
queueSettings.mode === "followup" ||
queueSettings.mode === "collect" ||
queueSettings.mode === "steer-backlog" ||
queueSettings.mode === "interrupt";
if (isActive && (shouldFollowup || queueSettings.mode === "steer")) {
const origin = resolveAnnounceOrigin(entry, params.requesterOrigin);
enqueueAnnounce({
key: canonicalKey,
item: {
prompt: params.triggerMessage,
summaryLine: params.summaryLine,
enqueuedAt: Date.now(),
sessionKey: canonicalKey,
origin,
},
settings: queueSettings,
send: sendAnnounce,
});
return "queued";
}
return "none";
}
function loadSessionEntryByKey(sessionKey: string) {
const cfg = loadConfig();
const agentId = resolveAgentIdFromSessionKey(sessionKey);
const storePath = resolveStorePath(cfg.session?.store, { agentId });
const store = loadSessionStore(storePath);
return store[sessionKey];
}
async function readLatestAssistantReplyWithRetry(params: {
sessionKey: string;
initialReply?: string;
maxWaitMs: number;
}): Promise<string | undefined> {
const RETRY_INTERVAL_MS = 100;
let reply = params.initialReply?.trim() ? params.initialReply : undefined;
if (reply) {
return reply;
}
const deadline = Date.now() + Math.max(0, Math.min(params.maxWaitMs, 15_000));
while (Date.now() < deadline) {
await new Promise((resolve) => setTimeout(resolve, RETRY_INTERVAL_MS));
const latest = await readLatestAssistantReply({ sessionKey: params.sessionKey });
if (latest?.trim()) {
return latest;
}
}
return reply;
}
export function buildSubagentSystemPrompt(params: {
requesterSessionKey?: string;
requesterOrigin?: DeliveryContext;
childSessionKey: string;
label?: string;
task?: string;
/** Depth of the child being spawned (1 = sub-agent, 2 = sub-sub-agent). */
childDepth?: number;
/** Config value: max allowed spawn depth. */
maxSpawnDepth?: number;
}) {
const taskText =
typeof params.task === "string" && params.task.trim()
? params.task.replace(/\s+/g, " ").trim()
: "{{TASK_DESCRIPTION}}";
const childDepth = typeof params.childDepth === "number" ? params.childDepth : 1;
const maxSpawnDepth = typeof params.maxSpawnDepth === "number" ? params.maxSpawnDepth : 1;
const canSpawn = childDepth < maxSpawnDepth;
const parentLabel = childDepth >= 2 ? "parent orchestrator" : "main agent";
const lines = [
"# Subagent Context",
"",
`You are a **subagent** spawned by the ${parentLabel} for a specific task.`,
"",
"## Your Role",
`- You were created to handle: ${taskText}`,
"- Complete this task. That's your entire purpose.",
`- You are NOT the ${parentLabel}. Don't try to be.`,
"",
"## Rules",
"1. **Stay focused** - Do your assigned task, nothing else",
`2. **Complete the task** - Your final message will be automatically reported to the ${parentLabel}`,
"3. **Don't initiate** - No heartbeats, no proactive actions, no side quests",
"4. **Be ephemeral** - You may be terminated after task completion. That's fine.",
"5. **Trust push-based completion** - Descendant results are auto-announced back to you; do not busy-poll for status.",
"",
"## Output Format",
"When complete, your final response should include:",
`- What you accomplished or found`,
`- Any relevant details the ${parentLabel} should know`,
"- Keep it concise but informative",
"",
"## What You DON'T Do",
`- NO user conversations (that's ${parentLabel}'s job)`,
"- NO external messages (email, tweets, etc.) unless explicitly tasked with a specific recipient/channel",
"- NO cron jobs or persistent state",
`- NO pretending to be the ${parentLabel}`,
`- Only use the \`message\` tool when explicitly instructed to contact a specific external recipient; otherwise return plain text and let the ${parentLabel} deliver it`,
"",
];
if (canSpawn) {
lines.push(
"## Sub-Agent Spawning",
"You CAN spawn your own sub-agents for parallel or complex work using `sessions_spawn`.",
"Use the `subagents` tool to steer, kill, or do an on-demand status check for your spawned sub-agents.",
"Your sub-agents will announce their results back to you automatically (not to the main agent).",
"Default workflow: spawn work, continue orchestrating, and wait for auto-announced completions.",
"Do NOT repeatedly poll `subagents list` in a loop unless you are actively debugging or intervening.",
"Coordinate their work and synthesize results before reporting back.",
"",
);
} else if (childDepth >= 2) {
lines.push(
"## Sub-Agent Spawning",
"You are a leaf worker and CANNOT spawn further sub-agents. Focus on your assigned task.",
"",
);
}
lines.push(
"## Session Context",
...[
params.label ? `- Label: ${params.label}` : undefined,
params.requesterSessionKey
? `- Requester session: ${params.requesterSessionKey}.`
: undefined,
params.requesterOrigin?.channel
? `- Requester channel: ${params.requesterOrigin.channel}.`
: undefined,
`- Your session: ${params.childSessionKey}.`,
].filter((line): line is string => line !== undefined),
"",
);
return lines.join("\n");
}
export type SubagentRunOutcome = {
status: "ok" | "error" | "timeout" | "unknown";
error?: string;
};
export type SubagentAnnounceType = "subagent task" | "cron job";
function buildAnnounceReplyInstruction(params: {
remainingActiveSubagentRuns: number;
requesterIsSubagent: boolean;
announceType: SubagentAnnounceType;
}): string {
if (params.remainingActiveSubagentRuns > 0) {
const activeRunsLabel = params.remainingActiveSubagentRuns === 1 ? "run" : "runs";
return `There are still ${params.remainingActiveSubagentRuns} active subagent ${activeRunsLabel} for this session. If they are part of the same workflow, wait for the remaining results before sending a user update. If they are unrelated, respond normally using only the result above.`;
}
if (params.requesterIsSubagent) {
return "Convert this completion into a concise internal orchestration update for your parent agent in your own words. Keep this internal context private (don't mention system/log/stats/session details or announce type). If this result is duplicate or no update is needed, reply ONLY: NO_REPLY.";
}
return `A completed ${params.announceType} is ready for user delivery. Convert the result above into your normal assistant voice and send that user-facing update now. Keep this internal context private (don't mention system/log/stats/session details or announce type), and do not copy the system message verbatim. Reply ONLY: NO_REPLY if this exact result was already delivered to the user in this same turn.`;
}
export async function runSubagentAnnounceFlow(params: {
childSessionKey: string;
childRunId: string;
requesterSessionKey: string;
requesterOrigin?: DeliveryContext;
requesterDisplayKey: string;
task: string;
timeoutMs: number;
cleanup: "delete" | "keep";
roundOneReply?: string;
waitForCompletion?: boolean;
startedAt?: number;
endedAt?: number;
label?: string;
outcome?: SubagentRunOutcome;
announceType?: SubagentAnnounceType;
}): Promise<boolean> {
let didAnnounce = false;
let shouldDeleteChildSession = params.cleanup === "delete";
try {
let targetRequesterSessionKey = params.requesterSessionKey;
let targetRequesterOrigin = normalizeDeliveryContext(params.requesterOrigin);
const childSessionId = (() => {
const entry = loadSessionEntryByKey(params.childSessionKey);
return typeof entry?.sessionId === "string" && entry.sessionId.trim()
? entry.sessionId.trim()
: undefined;
})();
const settleTimeoutMs = Math.min(Math.max(params.timeoutMs, 1), 120_000);
let reply = params.roundOneReply;
let outcome: SubagentRunOutcome | undefined = params.outcome;
// Lifecycle "end" can arrive before auto-compaction retries finish. If the
// subagent is still active, wait for the embedded run to fully settle.
if (childSessionId && isEmbeddedPiRunActive(childSessionId)) {
const settled = await waitForEmbeddedPiRunEnd(childSessionId, settleTimeoutMs);
if (!settled && isEmbeddedPiRunActive(childSessionId)) {
// The child run is still active (e.g., compaction retry still in progress).
// Defer announcement so we don't report stale/partial output.
// Keep the child session so output is not lost while the run is still active.
shouldDeleteChildSession = false;
return false;
}
}
if (!reply && params.waitForCompletion !== false) {
const waitMs = settleTimeoutMs;
const wait = await callGateway<{
status?: string;
startedAt?: number;
endedAt?: number;
error?: string;
}>({
method: "agent.wait",
params: {
runId: params.childRunId,
timeoutMs: waitMs,
},
timeoutMs: waitMs + 2000,
});
const waitError = typeof wait?.error === "string" ? wait.error : undefined;
if (wait?.status === "timeout") {
outcome = { status: "timeout" };
} else if (wait?.status === "error") {
outcome = { status: "error", error: waitError };
} else if (wait?.status === "ok") {
outcome = { status: "ok" };
}
if (typeof wait?.startedAt === "number" && !params.startedAt) {
params.startedAt = wait.startedAt;
}
if (typeof wait?.endedAt === "number" && !params.endedAt) {
params.endedAt = wait.endedAt;
}
if (wait?.status === "timeout") {
if (!outcome) {
outcome = { status: "timeout" };
}
}
reply = await readLatestAssistantReply({ sessionKey: params.childSessionKey });
}
if (!reply) {
reply = await readLatestAssistantReply({ sessionKey: params.childSessionKey });
}
if (!reply?.trim()) {
reply = await readLatestAssistantReplyWithRetry({
sessionKey: params.childSessionKey,
initialReply: reply,
maxWaitMs: params.timeoutMs,
});
}
if (!reply?.trim() && childSessionId && isEmbeddedPiRunActive(childSessionId)) {
// Avoid announcing "(no output)" while the child run is still producing output.
shouldDeleteChildSession = false;
return false;
}
if (!outcome) {
outcome = { status: "unknown" };
}
let activeChildDescendantRuns = 0;
try {
const { countActiveDescendantRuns } = await import("./subagent-registry.js");
activeChildDescendantRuns = Math.max(0, countActiveDescendantRuns(params.childSessionKey));
} catch {
// Best-effort only; fall back to direct announce behavior when unavailable.
}
if (activeChildDescendantRuns > 0) {
// The finished run still has active descendant subagents. Defer announcing
// this run until descendants settle so we avoid posting in-progress updates.
shouldDeleteChildSession = false;
return false;
}
// Build status label
const statusLabel =
outcome.status === "ok"
? "completed successfully"
: outcome.status === "timeout"
? "timed out"
: outcome.status === "error"
? `failed: ${outcome.error || "unknown error"}`
: "finished with unknown status";
// Build instructional message for main agent
const announceType = params.announceType ?? "subagent task";
const taskLabel = params.label || params.task || "task";
const announceSessionId = childSessionId || "unknown";
const findings = reply || "(no output)";
let triggerMessage = "";
let requesterDepth = getSubagentDepthFromSessionStore(targetRequesterSessionKey);
let requesterIsSubagent = requesterDepth >= 1;
// If the requester subagent has already finished, bubble the announce to its
// requester (typically main) so descendant completion is not silently lost.
if (requesterIsSubagent) {
const { isSubagentSessionRunActive, resolveRequesterForChildSession } =
await import("./subagent-registry.js");
if (!isSubagentSessionRunActive(targetRequesterSessionKey)) {
const fallback = resolveRequesterForChildSession(targetRequesterSessionKey);
if (!fallback?.requesterSessionKey) {
// Without a requester fallback we cannot safely deliver this nested
// completion. Keep cleanup retryable so a later registry restore can
// recover and re-announce instead of silently dropping the result.
shouldDeleteChildSession = false;
return false;
}
targetRequesterSessionKey = fallback.requesterSessionKey;
targetRequesterOrigin =
normalizeDeliveryContext(fallback.requesterOrigin) ?? targetRequesterOrigin;
requesterDepth = getSubagentDepthFromSessionStore(targetRequesterSessionKey);
requesterIsSubagent = requesterDepth >= 1;
}
}
let remainingActiveSubagentRuns = 0;
try {
const { countActiveDescendantRuns } = await import("./subagent-registry.js");
remainingActiveSubagentRuns = Math.max(
0,
countActiveDescendantRuns(targetRequesterSessionKey),
);
} catch {
// Best-effort only; fall back to default announce instructions when unavailable.
}
const replyInstruction = buildAnnounceReplyInstruction({
remainingActiveSubagentRuns,
requesterIsSubagent,
announceType,
});
const statsLine = await buildCompactAnnounceStatsLine({
sessionKey: params.childSessionKey,
startedAt: params.startedAt,
endedAt: params.endedAt,
});
triggerMessage = [
`[System Message] [sessionId: ${announceSessionId}] A ${announceType} "${taskLabel}" just ${statusLabel}.`,
"",
"Result:",
findings,
"",
statsLine,
"",
replyInstruction,
].join("\n");
const queued = await maybeQueueSubagentAnnounce({
requesterSessionKey: targetRequesterSessionKey,
triggerMessage,
summaryLine: taskLabel,
requesterOrigin: targetRequesterOrigin,
});
if (queued === "steered") {
didAnnounce = true;
return true;
}
if (queued === "queued") {
didAnnounce = true;
return true;
}
// Send to the requester session. For nested subagents this is an internal
// follow-up injection (deliver=false) so the orchestrator receives it.
let directOrigin = targetRequesterOrigin;
if (!requesterIsSubagent && !directOrigin) {
const { entry } = loadRequesterSessionEntry(targetRequesterSessionKey);
directOrigin = deliveryContextFromSession(entry);
}
await callGateway({
method: "agent",
params: {
sessionKey: targetRequesterSessionKey,
message: triggerMessage,
deliver: !requesterIsSubagent,
channel: requesterIsSubagent ? undefined : directOrigin?.channel,
accountId: requesterIsSubagent ? undefined : directOrigin?.accountId,
to: requesterIsSubagent ? undefined : directOrigin?.to,
threadId:
!requesterIsSubagent && directOrigin?.threadId != null && directOrigin.threadId !== ""
? String(directOrigin.threadId)
: undefined,
idempotencyKey: crypto.randomUUID(),
},
expectFinal: true,
timeoutMs: 15_000,
});
didAnnounce = true;
} catch (err) {
defaultRuntime.error?.(`Subagent announce failed: ${String(err)}`);
// Best-effort follow-ups; ignore failures to avoid breaking the caller response.
} finally {
// Patch label after all writes complete
if (params.label) {
try {
await callGateway({
method: "sessions.patch",
params: { key: params.childSessionKey, label: params.label },
timeoutMs: 10_000,
});
} catch {
// Best-effort
}
}
if (shouldDeleteChildSession) {
try {
await callGateway({
method: "sessions.delete",
params: { key: params.childSessionKey, deleteTranscript: true },
timeoutMs: 10_000,
});
} catch {
// ignore
}
}
}
return didAnnounce;
}