openclaw/src/agents/tools/sessions-spawn-tool.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

334 lines
12 KiB
TypeScript

import { Type } from "@sinclair/typebox";
import crypto from "node:crypto";
import type { GatewayMessageChannel } from "../../utils/message-channel.js";
import type { AnyAgentTool } from "./common.js";
import { formatThinkingLevels, normalizeThinkLevel } from "../../auto-reply/thinking.js";
import { loadConfig } from "../../config/config.js";
import { callGateway } from "../../gateway/call.js";
import { normalizeAgentId, parseAgentSessionKey } from "../../routing/session-key.js";
import { normalizeDeliveryContext } from "../../utils/delivery-context.js";
import { resolveAgentConfig } from "../agent-scope.js";
import { AGENT_LANE_SUBAGENT } from "../lanes.js";
import { resolveDefaultModelForAgent } from "../model-selection.js";
import { optionalStringEnum } from "../schema/typebox.js";
import { buildSubagentSystemPrompt } from "../subagent-announce.js";
import { getSubagentDepthFromSessionStore } from "../subagent-depth.js";
import { countActiveRunsForSession, registerSubagentRun } from "../subagent-registry.js";
import { jsonResult, readStringParam } from "./common.js";
import {
resolveDisplaySessionKey,
resolveInternalSessionKey,
resolveMainSessionAlias,
} from "./sessions-helpers.js";
const SessionsSpawnToolSchema = Type.Object({
task: Type.String(),
label: Type.Optional(Type.String()),
agentId: Type.Optional(Type.String()),
model: Type.Optional(Type.String()),
thinking: Type.Optional(Type.String()),
runTimeoutSeconds: Type.Optional(Type.Number({ minimum: 0 })),
cleanup: optionalStringEnum(["delete", "keep"] as const),
});
function splitModelRef(ref?: string) {
if (!ref) {
return { provider: undefined, model: undefined };
}
const trimmed = ref.trim();
if (!trimmed) {
return { provider: undefined, model: undefined };
}
const [provider, model] = trimmed.split("/", 2);
if (model) {
return { provider, model };
}
return { provider: undefined, model: trimmed };
}
function normalizeModelSelection(value: unknown): string | undefined {
if (typeof value === "string") {
const trimmed = value.trim();
return trimmed || undefined;
}
if (!value || typeof value !== "object") {
return undefined;
}
const primary = (value as { primary?: unknown }).primary;
if (typeof primary === "string" && primary.trim()) {
return primary.trim();
}
return undefined;
}
export function createSessionsSpawnTool(opts?: {
agentSessionKey?: string;
agentChannel?: GatewayMessageChannel;
agentAccountId?: string;
agentTo?: string;
agentThreadId?: string | number;
agentGroupId?: string | null;
agentGroupChannel?: string | null;
agentGroupSpace?: string | null;
sandboxed?: boolean;
/** Explicit agent ID override for cron/hook sessions where session key parsing may not work. */
requesterAgentIdOverride?: string;
}): AnyAgentTool {
return {
label: "Sessions",
name: "sessions_spawn",
description:
"Spawn a background sub-agent run in an isolated session and announce the result back to the requester chat.",
parameters: SessionsSpawnToolSchema,
execute: async (_toolCallId, args) => {
const params = args as Record<string, unknown>;
const task = readStringParam(params, "task", { required: true });
const label = typeof params.label === "string" ? params.label.trim() : "";
const requestedAgentId = readStringParam(params, "agentId");
const modelOverride = readStringParam(params, "model");
const thinkingOverrideRaw = readStringParam(params, "thinking");
const cleanup =
params.cleanup === "keep" || params.cleanup === "delete" ? params.cleanup : "keep";
const requesterOrigin = normalizeDeliveryContext({
channel: opts?.agentChannel,
accountId: opts?.agentAccountId,
to: opts?.agentTo,
threadId: opts?.agentThreadId,
});
// Default to 0 (no timeout) when omitted. Sub-agent runs are long-lived
// by default and should not inherit the main agent 600s timeout.
const runTimeoutSeconds =
typeof params.runTimeoutSeconds === "number" && Number.isFinite(params.runTimeoutSeconds)
? Math.max(0, Math.floor(params.runTimeoutSeconds))
: 0;
let modelWarning: string | undefined;
let modelApplied = false;
const cfg = loadConfig();
const { mainKey, alias } = resolveMainSessionAlias(cfg);
const requesterSessionKey = opts?.agentSessionKey;
const requesterInternalKey = requesterSessionKey
? resolveInternalSessionKey({
key: requesterSessionKey,
alias,
mainKey,
})
: alias;
const requesterDisplayKey = resolveDisplaySessionKey({
key: requesterInternalKey,
alias,
mainKey,
});
const callerDepth = getSubagentDepthFromSessionStore(requesterInternalKey, { cfg });
const maxSpawnDepth = cfg.agents?.defaults?.subagents?.maxSpawnDepth ?? 1;
if (callerDepth >= maxSpawnDepth) {
return jsonResult({
status: "forbidden",
error: `sessions_spawn is not allowed at this depth (current depth: ${callerDepth}, max: ${maxSpawnDepth})`,
});
}
const maxChildren = cfg.agents?.defaults?.subagents?.maxChildrenPerAgent ?? 5;
const activeChildren = countActiveRunsForSession(requesterInternalKey);
if (activeChildren >= maxChildren) {
return jsonResult({
status: "forbidden",
error: `sessions_spawn has reached max active children for this session (${activeChildren}/${maxChildren})`,
});
}
const requesterAgentId = normalizeAgentId(
opts?.requesterAgentIdOverride ?? parseAgentSessionKey(requesterInternalKey)?.agentId,
);
const targetAgentId = requestedAgentId
? normalizeAgentId(requestedAgentId)
: requesterAgentId;
if (targetAgentId !== requesterAgentId) {
const allowAgents = resolveAgentConfig(cfg, requesterAgentId)?.subagents?.allowAgents ?? [];
const allowAny = allowAgents.some((value) => value.trim() === "*");
const normalizedTargetId = targetAgentId.toLowerCase();
const allowSet = new Set(
allowAgents
.filter((value) => value.trim() && value.trim() !== "*")
.map((value) => normalizeAgentId(value).toLowerCase()),
);
if (!allowAny && !allowSet.has(normalizedTargetId)) {
const allowedText = allowAny
? "*"
: allowSet.size > 0
? Array.from(allowSet).join(", ")
: "none";
return jsonResult({
status: "forbidden",
error: `agentId is not allowed for sessions_spawn (allowed: ${allowedText})`,
});
}
}
const childSessionKey = `agent:${targetAgentId}:subagent:${crypto.randomUUID()}`;
const childDepth = callerDepth + 1;
const spawnedByKey = requesterInternalKey;
const targetAgentConfig = resolveAgentConfig(cfg, targetAgentId);
const runtimeDefaultModel = resolveDefaultModelForAgent({
cfg,
agentId: targetAgentId,
});
const resolvedModel =
normalizeModelSelection(modelOverride) ??
normalizeModelSelection(targetAgentConfig?.subagents?.model) ??
normalizeModelSelection(cfg.agents?.defaults?.subagents?.model) ??
normalizeModelSelection(cfg.agents?.defaults?.model?.primary) ??
normalizeModelSelection(`${runtimeDefaultModel.provider}/${runtimeDefaultModel.model}`);
const resolvedThinkingDefaultRaw =
readStringParam(targetAgentConfig?.subagents ?? {}, "thinking") ??
readStringParam(cfg.agents?.defaults?.subagents ?? {}, "thinking");
let thinkingOverride: string | undefined;
const thinkingCandidateRaw = thinkingOverrideRaw || resolvedThinkingDefaultRaw;
if (thinkingCandidateRaw) {
const normalized = normalizeThinkLevel(thinkingCandidateRaw);
if (!normalized) {
const { provider, model } = splitModelRef(resolvedModel);
const hint = formatThinkingLevels(provider, model);
return jsonResult({
status: "error",
error: `Invalid thinking level "${thinkingCandidateRaw}". Use one of: ${hint}.`,
});
}
thinkingOverride = normalized;
}
try {
await callGateway({
method: "sessions.patch",
params: { key: childSessionKey, spawnDepth: childDepth },
timeoutMs: 10_000,
});
} catch (err) {
const messageText =
err instanceof Error ? err.message : typeof err === "string" ? err : "error";
return jsonResult({
status: "error",
error: messageText,
childSessionKey,
});
}
if (resolvedModel) {
try {
await callGateway({
method: "sessions.patch",
params: { key: childSessionKey, model: resolvedModel },
timeoutMs: 10_000,
});
modelApplied = true;
} catch (err) {
const messageText =
err instanceof Error ? err.message : typeof err === "string" ? err : "error";
const recoverable =
messageText.includes("invalid model") || messageText.includes("model not allowed");
if (!recoverable) {
return jsonResult({
status: "error",
error: messageText,
childSessionKey,
});
}
modelWarning = messageText;
}
}
if (thinkingOverride !== undefined) {
try {
await callGateway({
method: "sessions.patch",
params: {
key: childSessionKey,
thinkingLevel: thinkingOverride === "off" ? null : thinkingOverride,
},
timeoutMs: 10_000,
});
} catch (err) {
const messageText =
err instanceof Error ? err.message : typeof err === "string" ? err : "error";
return jsonResult({
status: "error",
error: messageText,
childSessionKey,
});
}
}
const childSystemPrompt = buildSubagentSystemPrompt({
requesterSessionKey,
requesterOrigin,
childSessionKey,
label: label || undefined,
task,
childDepth,
maxSpawnDepth,
});
const childIdem = crypto.randomUUID();
let childRunId: string = childIdem;
try {
const response = await callGateway<{ runId: string }>({
method: "agent",
params: {
message: task,
sessionKey: childSessionKey,
channel: requesterOrigin?.channel,
to: requesterOrigin?.to ?? undefined,
accountId: requesterOrigin?.accountId ?? undefined,
threadId:
requesterOrigin?.threadId != null ? String(requesterOrigin.threadId) : undefined,
idempotencyKey: childIdem,
deliver: false,
lane: AGENT_LANE_SUBAGENT,
extraSystemPrompt: childSystemPrompt,
thinking: thinkingOverride,
timeout: runTimeoutSeconds,
label: label || undefined,
spawnedBy: spawnedByKey,
groupId: opts?.agentGroupId ?? undefined,
groupChannel: opts?.agentGroupChannel ?? undefined,
groupSpace: opts?.agentGroupSpace ?? undefined,
},
timeoutMs: 10_000,
});
if (typeof response?.runId === "string" && response.runId) {
childRunId = response.runId;
}
} catch (err) {
const messageText =
err instanceof Error ? err.message : typeof err === "string" ? err : "error";
return jsonResult({
status: "error",
error: messageText,
childSessionKey,
runId: childRunId,
});
}
registerSubagentRun({
runId: childRunId,
childSessionKey,
requesterSessionKey: requesterInternalKey,
requesterOrigin,
requesterDisplayKey,
task,
cleanup,
label: label || undefined,
model: resolvedModel,
runTimeoutSeconds,
});
return jsonResult({
status: "accepted",
childSessionKey,
runId: childRunId,
modelApplied: resolvedModel ? modelApplied : undefined,
warning: modelWarning,
});
},
};
}