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

262 lines
8.1 KiB
TypeScript

import type { OpenClawConfig } from "../../config/config.js";
import type { FinalizedMsgContext, MsgContext } from "../templating.js";
import { resolveSessionAgentId } from "../../agents/agent-scope.js";
import { abortEmbeddedPiRun } from "../../agents/pi-embedded.js";
import {
listSubagentRunsForRequester,
markSubagentRunTerminated,
} from "../../agents/subagent-registry.js";
import {
resolveInternalSessionKey,
resolveMainSessionAlias,
} from "../../agents/tools/sessions-helpers.js";
import {
loadSessionStore,
resolveStorePath,
type SessionEntry,
updateSessionStore,
} from "../../config/sessions.js";
import { logVerbose } from "../../globals.js";
import { parseAgentSessionKey } from "../../routing/session-key.js";
import { resolveCommandAuthorization } from "../command-auth.js";
import { normalizeCommandBody } from "../commands-registry.js";
import { stripMentions, stripStructuralPrefixes } from "./mentions.js";
import { clearSessionQueues } from "./queue.js";
const ABORT_TRIGGERS = new Set(["stop", "esc", "abort", "wait", "exit", "interrupt"]);
const ABORT_MEMORY = new Map<string, boolean>();
const ABORT_MEMORY_MAX = 2000;
export function isAbortTrigger(text?: string): boolean {
if (!text) {
return false;
}
const normalized = text.trim().toLowerCase();
return ABORT_TRIGGERS.has(normalized);
}
export function getAbortMemory(key: string): boolean | undefined {
const normalized = key.trim();
if (!normalized) {
return undefined;
}
return ABORT_MEMORY.get(normalized);
}
function pruneAbortMemory(): void {
if (ABORT_MEMORY.size <= ABORT_MEMORY_MAX) {
return;
}
const excess = ABORT_MEMORY.size - ABORT_MEMORY_MAX;
let removed = 0;
for (const entryKey of ABORT_MEMORY.keys()) {
ABORT_MEMORY.delete(entryKey);
removed += 1;
if (removed >= excess) {
break;
}
}
}
export function setAbortMemory(key: string, value: boolean): void {
const normalized = key.trim();
if (!normalized) {
return;
}
if (!value) {
ABORT_MEMORY.delete(normalized);
return;
}
// Refresh insertion order so active keys are less likely to be evicted.
if (ABORT_MEMORY.has(normalized)) {
ABORT_MEMORY.delete(normalized);
}
ABORT_MEMORY.set(normalized, true);
pruneAbortMemory();
}
export function getAbortMemorySizeForTest(): number {
return ABORT_MEMORY.size;
}
export function resetAbortMemoryForTest(): void {
ABORT_MEMORY.clear();
}
export function formatAbortReplyText(stoppedSubagents?: number): string {
if (typeof stoppedSubagents !== "number" || stoppedSubagents <= 0) {
return "⚙️ Agent was aborted.";
}
const label = stoppedSubagents === 1 ? "sub-agent" : "sub-agents";
return `⚙️ Agent was aborted. Stopped ${stoppedSubagents} ${label}.`;
}
function resolveSessionEntryForKey(
store: Record<string, SessionEntry> | undefined,
sessionKey: string | undefined,
) {
if (!store || !sessionKey) {
return {};
}
const direct = store[sessionKey];
if (direct) {
return { entry: direct, key: sessionKey };
}
return {};
}
function resolveAbortTargetKey(ctx: MsgContext): string | undefined {
const target = ctx.CommandTargetSessionKey?.trim();
if (target) {
return target;
}
const sessionKey = ctx.SessionKey?.trim();
return sessionKey || undefined;
}
function normalizeRequesterSessionKey(
cfg: OpenClawConfig,
key: string | undefined,
): string | undefined {
const cleaned = key?.trim();
if (!cleaned) {
return undefined;
}
const { mainKey, alias } = resolveMainSessionAlias(cfg);
return resolveInternalSessionKey({ key: cleaned, alias, mainKey });
}
export function stopSubagentsForRequester(params: {
cfg: OpenClawConfig;
requesterSessionKey?: string;
}): { stopped: number } {
const requesterKey = normalizeRequesterSessionKey(params.cfg, params.requesterSessionKey);
if (!requesterKey) {
return { stopped: 0 };
}
const runs = listSubagentRunsForRequester(requesterKey);
if (runs.length === 0) {
return { stopped: 0 };
}
const storeCache = new Map<string, Record<string, SessionEntry>>();
const seenChildKeys = new Set<string>();
let stopped = 0;
for (const run of runs) {
const childKey = run.childSessionKey?.trim();
if (!childKey || seenChildKeys.has(childKey)) {
continue;
}
seenChildKeys.add(childKey);
if (!run.endedAt) {
const cleared = clearSessionQueues([childKey]);
const parsed = parseAgentSessionKey(childKey);
const storePath = resolveStorePath(params.cfg.session?.store, { agentId: parsed?.agentId });
let store = storeCache.get(storePath);
if (!store) {
store = loadSessionStore(storePath);
storeCache.set(storePath, store);
}
const entry = store[childKey];
const sessionId = entry?.sessionId;
const aborted = sessionId ? abortEmbeddedPiRun(sessionId) : false;
const markedTerminated =
markSubagentRunTerminated({
runId: run.runId,
childSessionKey: childKey,
reason: "killed",
}) > 0;
if (markedTerminated || aborted || cleared.followupCleared > 0 || cleared.laneCleared > 0) {
stopped += 1;
}
}
// Cascade: also stop any sub-sub-agents spawned by this child.
const cascadeResult = stopSubagentsForRequester({
cfg: params.cfg,
requesterSessionKey: childKey,
});
stopped += cascadeResult.stopped;
}
if (stopped > 0) {
logVerbose(`abort: stopped ${stopped} subagent run(s) for ${requesterKey}`);
}
return { stopped };
}
export async function tryFastAbortFromMessage(params: {
ctx: FinalizedMsgContext;
cfg: OpenClawConfig;
}): Promise<{ handled: boolean; aborted: boolean; stoppedSubagents?: number }> {
const { ctx, cfg } = params;
const targetKey = resolveAbortTargetKey(ctx);
const agentId = resolveSessionAgentId({
sessionKey: targetKey ?? ctx.SessionKey ?? "",
config: cfg,
});
// Use RawBody/CommandBody for abort detection (clean message without structural context).
const raw = stripStructuralPrefixes(ctx.CommandBody ?? ctx.RawBody ?? ctx.Body ?? "");
const isGroup = ctx.ChatType?.trim().toLowerCase() === "group";
const stripped = isGroup ? stripMentions(raw, ctx, cfg, agentId) : raw;
const normalized = normalizeCommandBody(stripped);
const abortRequested = normalized === "/stop" || isAbortTrigger(stripped);
if (!abortRequested) {
return { handled: false, aborted: false };
}
const commandAuthorized = ctx.CommandAuthorized;
const auth = resolveCommandAuthorization({
ctx,
cfg,
commandAuthorized,
});
if (!auth.isAuthorizedSender) {
return { handled: false, aborted: false };
}
const abortKey = targetKey ?? auth.from ?? auth.to;
const requesterSessionKey = targetKey ?? ctx.SessionKey ?? abortKey;
if (targetKey) {
const storePath = resolveStorePath(cfg.session?.store, { agentId });
const store = loadSessionStore(storePath);
const { entry, key } = resolveSessionEntryForKey(store, targetKey);
const sessionId = entry?.sessionId;
const aborted = sessionId ? abortEmbeddedPiRun(sessionId) : false;
const cleared = clearSessionQueues([key ?? targetKey, sessionId]);
if (cleared.followupCleared > 0 || cleared.laneCleared > 0) {
logVerbose(
`abort: cleared followups=${cleared.followupCleared} lane=${cleared.laneCleared} keys=${cleared.keys.join(",")}`,
);
}
if (entry && key) {
entry.abortedLastRun = true;
entry.updatedAt = Date.now();
store[key] = entry;
await updateSessionStore(storePath, (nextStore) => {
const nextEntry = nextStore[key] ?? entry;
if (!nextEntry) {
return;
}
nextEntry.abortedLastRun = true;
nextEntry.updatedAt = Date.now();
nextStore[key] = nextEntry;
});
} else if (abortKey) {
setAbortMemory(abortKey, true);
}
const { stopped } = stopSubagentsForRequester({ cfg, requesterSessionKey });
return { handled: true, aborted, stoppedSubagents: stopped };
}
if (abortKey) {
setAbortMemory(abortKey, true);
}
const { stopped } = stopSubagentsForRequester({ cfg, requesterSessionKey });
return { handled: true, aborted: false, stoppedSubagents: stopped };
}