mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-07 04:01:37 +00:00
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)
This commit is contained in:
Tyler Yust
@@ -28,7 +28,12 @@ import { runEmbeddedPiAgent } from "../../agents/pi-embedded.js";
|
||||
import { buildWorkspaceSkillSnapshot } from "../../agents/skills.js";
|
||||
import { getSkillsSnapshotVersion } from "../../agents/skills/refresh.js";
|
||||
import { runSubagentAnnounceFlow } from "../../agents/subagent-announce.js";
|
||||
import {
|
||||
countActiveDescendantRuns,
|
||||
listDescendantRunsForRequester,
|
||||
} from "../../agents/subagent-registry.js";
|
||||
import { resolveAgentTimeoutMs } from "../../agents/timeout.js";
|
||||
import { readLatestAssistantReply } from "../../agents/tools/agent-step.js";
|
||||
import { deriveSessionTotalTokens, hasNonzeroUsage } from "../../agents/usage.js";
|
||||
import { ensureAgentWorkspace } from "../../agents/workspace.js";
|
||||
import {
|
||||
@@ -36,6 +41,7 @@ import {
|
||||
normalizeVerboseLevel,
|
||||
supportsXHighThinking,
|
||||
} from "../../auto-reply/thinking.js";
|
||||
import { SILENT_REPLY_TOKEN } from "../../auto-reply/tokens.js";
|
||||
import { createOutboundSendDeps, type CliDeps } from "../../cli/outbound-send-deps.js";
|
||||
import {
|
||||
resolveAgentMainSessionKey,
|
||||
@@ -94,6 +100,152 @@ function resolveCronDeliveryBestEffort(job: CronJob): boolean {
|
||||
return false;
|
||||
}
|
||||
|
||||
const CRON_SUBAGENT_WAIT_POLL_MS = 500;
|
||||
const CRON_SUBAGENT_WAIT_MIN_MS = 30_000;
|
||||
const CRON_SUBAGENT_FINAL_REPLY_GRACE_MS = 5_000;
|
||||
|
||||
function isLikelyInterimCronMessage(value: string): boolean {
|
||||
const text = value.trim();
|
||||
if (!text) {
|
||||
return true;
|
||||
}
|
||||
const normalized = text.toLowerCase().replace(/\s+/g, " ");
|
||||
const words = normalized.split(" ").filter(Boolean).length;
|
||||
const interimHints = [
|
||||
"on it",
|
||||
"pulling everything together",
|
||||
"give me a few",
|
||||
"give me a few min",
|
||||
"few minutes",
|
||||
"let me compile",
|
||||
"i'll gather",
|
||||
"i will gather",
|
||||
"working on it",
|
||||
"retrying now",
|
||||
"should be about",
|
||||
"should have your summary",
|
||||
"subagent spawned",
|
||||
"spawned a subagent",
|
||||
"it'll auto-announce when done",
|
||||
"it will auto-announce when done",
|
||||
"auto-announce when done",
|
||||
"both subagents are running",
|
||||
"wait for them to report back",
|
||||
];
|
||||
return words <= 45 && interimHints.some((hint) => normalized.includes(hint));
|
||||
}
|
||||
|
||||
function expectsSubagentFollowup(value: string): boolean {
|
||||
const normalized = value.trim().toLowerCase().replace(/\s+/g, " ");
|
||||
if (!normalized) {
|
||||
return false;
|
||||
}
|
||||
const hints = [
|
||||
"subagent spawned",
|
||||
"spawned a subagent",
|
||||
"auto-announce when done",
|
||||
"both subagents are running",
|
||||
"wait for them to report back",
|
||||
];
|
||||
return hints.some((hint) => normalized.includes(hint));
|
||||
}
|
||||
|
||||
async function readDescendantSubagentFallbackReply(params: {
|
||||
sessionKey: string;
|
||||
runStartedAt: number;
|
||||
}): Promise<string | undefined> {
|
||||
const descendants = listDescendantRunsForRequester(params.sessionKey)
|
||||
.filter(
|
||||
(entry) =>
|
||||
typeof entry.endedAt === "number" &&
|
||||
entry.endedAt >= params.runStartedAt &&
|
||||
entry.childSessionKey.trim().length > 0,
|
||||
)
|
||||
.toSorted((a, b) => (a.endedAt ?? 0) - (b.endedAt ?? 0));
|
||||
if (descendants.length === 0) {
|
||||
return undefined;
|
||||
}
|
||||
|
||||
const latestByChild = new Map<string, (typeof descendants)[number]>();
|
||||
for (const entry of descendants) {
|
||||
const childKey = entry.childSessionKey.trim();
|
||||
if (!childKey) {
|
||||
continue;
|
||||
}
|
||||
const current = latestByChild.get(childKey);
|
||||
if (!current || (entry.endedAt ?? 0) >= (current.endedAt ?? 0)) {
|
||||
latestByChild.set(childKey, entry);
|
||||
}
|
||||
}
|
||||
|
||||
const replies: string[] = [];
|
||||
const latestRuns = [...latestByChild.values()]
|
||||
.toSorted((a, b) => (a.endedAt ?? 0) - (b.endedAt ?? 0))
|
||||
.slice(-4);
|
||||
for (const entry of latestRuns) {
|
||||
const reply = (await readLatestAssistantReply({ sessionKey: entry.childSessionKey }))?.trim();
|
||||
if (!reply || reply.toUpperCase() === SILENT_REPLY_TOKEN.toUpperCase()) {
|
||||
continue;
|
||||
}
|
||||
replies.push(reply);
|
||||
}
|
||||
if (replies.length === 0) {
|
||||
return undefined;
|
||||
}
|
||||
if (replies.length === 1) {
|
||||
return replies[0];
|
||||
}
|
||||
return replies.join("\n\n");
|
||||
}
|
||||
|
||||
async function waitForDescendantSubagentSummary(params: {
|
||||
sessionKey: string;
|
||||
initialReply?: string;
|
||||
timeoutMs: number;
|
||||
observedActiveDescendants?: boolean;
|
||||
}): Promise<string | undefined> {
|
||||
const initialReply = params.initialReply?.trim();
|
||||
const deadline = Date.now() + Math.max(CRON_SUBAGENT_WAIT_MIN_MS, Math.floor(params.timeoutMs));
|
||||
let sawActiveDescendants = params.observedActiveDescendants === true;
|
||||
let drainedAtMs: number | undefined;
|
||||
while (Date.now() < deadline) {
|
||||
const activeDescendants = countActiveDescendantRuns(params.sessionKey);
|
||||
if (activeDescendants > 0) {
|
||||
sawActiveDescendants = true;
|
||||
drainedAtMs = undefined;
|
||||
await new Promise((resolve) => setTimeout(resolve, CRON_SUBAGENT_WAIT_POLL_MS));
|
||||
continue;
|
||||
}
|
||||
if (!sawActiveDescendants) {
|
||||
return initialReply;
|
||||
}
|
||||
if (!drainedAtMs) {
|
||||
drainedAtMs = Date.now();
|
||||
}
|
||||
const latest = (await readLatestAssistantReply({ sessionKey: params.sessionKey }))?.trim();
|
||||
if (
|
||||
latest &&
|
||||
latest.toUpperCase() !== SILENT_REPLY_TOKEN.toUpperCase() &&
|
||||
(latest !== initialReply || !isLikelyInterimCronMessage(latest))
|
||||
) {
|
||||
return latest;
|
||||
}
|
||||
if (Date.now() - drainedAtMs >= CRON_SUBAGENT_FINAL_REPLY_GRACE_MS) {
|
||||
return undefined;
|
||||
}
|
||||
await new Promise((resolve) => setTimeout(resolve, CRON_SUBAGENT_WAIT_POLL_MS));
|
||||
}
|
||||
const latest = (await readLatestAssistantReply({ sessionKey: params.sessionKey }))?.trim();
|
||||
if (
|
||||
latest &&
|
||||
latest.toUpperCase() !== SILENT_REPLY_TOKEN.toUpperCase() &&
|
||||
(latest !== initialReply || !isLikelyInterimCronMessage(latest))
|
||||
) {
|
||||
return latest;
|
||||
}
|
||||
return undefined;
|
||||
}
|
||||
|
||||
export type RunCronAgentTurnResult = {
|
||||
status: "ok" | "error" | "skipped";
|
||||
summary?: string;
|
||||
@@ -507,11 +659,11 @@ export async function runCronIsolatedAgentTurn(params: {
|
||||
await persistSessionEntry();
|
||||
}
|
||||
const firstText = payloads[0]?.text ?? "";
|
||||
const summary = pickSummaryFromPayloads(payloads) ?? pickSummaryFromOutput(firstText);
|
||||
const outputText = pickLastNonEmptyTextFromPayloads(payloads);
|
||||
const synthesizedText = outputText?.trim() || summary?.trim() || undefined;
|
||||
let summary = pickSummaryFromPayloads(payloads) ?? pickSummaryFromOutput(firstText);
|
||||
let outputText = pickLastNonEmptyTextFromPayloads(payloads);
|
||||
let synthesizedText = outputText?.trim() || summary?.trim() || undefined;
|
||||
const deliveryPayload = pickLastDeliverablePayload(payloads);
|
||||
const deliveryPayloads =
|
||||
let deliveryPayloads =
|
||||
deliveryPayload !== undefined
|
||||
? [deliveryPayload]
|
||||
: synthesizedText
|
||||
@@ -609,9 +761,56 @@ export async function runCronIsolatedAgentTurn(params: {
|
||||
typeof params.job.name === "string" && params.job.name.trim()
|
||||
? params.job.name.trim()
|
||||
: `cron:${params.job.id}`;
|
||||
const initialSynthesizedText = synthesizedText.trim();
|
||||
let activeSubagentRuns = countActiveDescendantRuns(agentSessionKey);
|
||||
const expectedSubagentFollowup = expectsSubagentFollowup(initialSynthesizedText);
|
||||
const hadActiveDescendants = activeSubagentRuns > 0;
|
||||
if (activeSubagentRuns > 0 || expectedSubagentFollowup) {
|
||||
let finalReply = await waitForDescendantSubagentSummary({
|
||||
sessionKey: agentSessionKey,
|
||||
initialReply: initialSynthesizedText,
|
||||
timeoutMs,
|
||||
observedActiveDescendants: activeSubagentRuns > 0 || expectedSubagentFollowup,
|
||||
});
|
||||
activeSubagentRuns = countActiveDescendantRuns(agentSessionKey);
|
||||
if (
|
||||
!finalReply &&
|
||||
activeSubagentRuns === 0 &&
|
||||
(hadActiveDescendants || expectedSubagentFollowup)
|
||||
) {
|
||||
finalReply = await readDescendantSubagentFallbackReply({
|
||||
sessionKey: agentSessionKey,
|
||||
runStartedAt,
|
||||
});
|
||||
}
|
||||
if (finalReply && activeSubagentRuns === 0) {
|
||||
outputText = finalReply;
|
||||
summary = pickSummaryFromOutput(finalReply) ?? summary;
|
||||
synthesizedText = finalReply;
|
||||
deliveryPayloads = [{ text: finalReply }];
|
||||
}
|
||||
}
|
||||
if (activeSubagentRuns > 0) {
|
||||
// Parent orchestration is still in progress; avoid announcing a partial
|
||||
// update to the main requester.
|
||||
return withRunSession({ status: "ok", summary, outputText });
|
||||
}
|
||||
if (
|
||||
(hadActiveDescendants || expectedSubagentFollowup) &&
|
||||
synthesizedText.trim() === initialSynthesizedText &&
|
||||
isLikelyInterimCronMessage(initialSynthesizedText) &&
|
||||
initialSynthesizedText.toUpperCase() !== SILENT_REPLY_TOKEN.toUpperCase()
|
||||
) {
|
||||
// Descendants existed but no post-orchestration synthesis arrived, so
|
||||
// suppress stale parent text like "on it, pulling everything together".
|
||||
return withRunSession({ status: "ok", summary, outputText });
|
||||
}
|
||||
if (synthesizedText.toUpperCase() === SILENT_REPLY_TOKEN.toUpperCase()) {
|
||||
return withRunSession({ status: "ok", summary, outputText });
|
||||
}
|
||||
try {
|
||||
const didAnnounce = await runSubagentAnnounceFlow({
|
||||
childSessionKey: runSessionKey,
|
||||
childSessionKey: agentSessionKey,
|
||||
childRunId: `${params.job.id}:${runSessionId}`,
|
||||
requesterSessionKey: announceSessionKey,
|
||||
requesterOrigin: {
|
||||
|
||||
Reference in New Issue
Block a user