Files
openclaw/src/auto-reply/reply/get-reply.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

342 lines
8.9 KiB
TypeScript

import type { MsgContext } from "../templating.js";
import type { GetReplyOptions, ReplyPayload } from "../types.js";
import {
resolveAgentDir,
resolveAgentWorkspaceDir,
resolveSessionAgentId,
resolveAgentSkillsFilter,
} from "../../agents/agent-scope.js";
import { resolveModelRefFromString } from "../../agents/model-selection.js";
import { resolveAgentTimeoutMs } from "../../agents/timeout.js";
import { DEFAULT_AGENT_WORKSPACE_DIR, ensureAgentWorkspace } from "../../agents/workspace.js";
import { type OpenClawConfig, loadConfig } from "../../config/config.js";
import { applyLinkUnderstanding } from "../../link-understanding/apply.js";
import { applyMediaUnderstanding } from "../../media-understanding/apply.js";
import { defaultRuntime } from "../../runtime.js";
import { resolveCommandAuthorization } from "../command-auth.js";
import { SILENT_REPLY_TOKEN } from "../tokens.js";
import { resolveDefaultModel } from "./directive-handling.js";
import { resolveReplyDirectives } from "./get-reply-directives.js";
import { handleInlineActions } from "./get-reply-inline-actions.js";
import { runPreparedReply } from "./get-reply-run.js";
import { finalizeInboundContext } from "./inbound-context.js";
import { applyResetModelOverride } from "./session-reset-model.js";
import { initSessionState } from "./session.js";
import { stageSandboxMedia } from "./stage-sandbox-media.js";
import { createTypingController } from "./typing.js";
function mergeSkillFilters(channelFilter?: string[], agentFilter?: string[]): string[] | undefined {
const normalize = (list?: string[]) => {
if (!Array.isArray(list)) {
return undefined;
}
return list.map((entry) => String(entry).trim()).filter(Boolean);
};
const channel = normalize(channelFilter);
const agent = normalize(agentFilter);
if (!channel && !agent) {
return undefined;
}
if (!channel) {
return agent;
}
if (!agent) {
return channel;
}
if (channel.length === 0 || agent.length === 0) {
return [];
}
const agentSet = new Set(agent);
return channel.filter((name) => agentSet.has(name));
}
export async function getReplyFromConfig(
ctx: MsgContext,
opts?: GetReplyOptions,
configOverride?: OpenClawConfig,
): Promise<ReplyPayload | ReplyPayload[] | undefined> {
const isFastTestEnv = process.env.OPENCLAW_TEST_FAST === "1";
const cfg = configOverride ?? loadConfig();
const targetSessionKey =
ctx.CommandSource === "native" ? ctx.CommandTargetSessionKey?.trim() : undefined;
const agentSessionKey = targetSessionKey || ctx.SessionKey;
const agentId = resolveSessionAgentId({
sessionKey: agentSessionKey,
config: cfg,
});
const mergedSkillFilter = mergeSkillFilters(
opts?.skillFilter,
resolveAgentSkillsFilter(cfg, agentId),
);
const resolvedOpts =
mergedSkillFilter !== undefined ? { ...opts, skillFilter: mergedSkillFilter } : opts;
const agentCfg = cfg.agents?.defaults;
const sessionCfg = cfg.session;
const { defaultProvider, defaultModel, aliasIndex } = resolveDefaultModel({
cfg,
agentId,
});
let provider = defaultProvider;
let model = defaultModel;
let hasResolvedHeartbeatModelOverride = false;
if (opts?.isHeartbeat) {
// Prefer the resolved per-agent heartbeat model passed from the heartbeat runner,
// fall back to the global defaults heartbeat model for backward compatibility.
const heartbeatRaw =
opts.heartbeatModelOverride?.trim() ?? agentCfg?.heartbeat?.model?.trim() ?? "";
const heartbeatRef = heartbeatRaw
? resolveModelRefFromString({
raw: heartbeatRaw,
defaultProvider,
aliasIndex,
})
: null;
if (heartbeatRef) {
provider = heartbeatRef.ref.provider;
model = heartbeatRef.ref.model;
hasResolvedHeartbeatModelOverride = true;
}
}
const workspaceDirRaw = resolveAgentWorkspaceDir(cfg, agentId) ?? DEFAULT_AGENT_WORKSPACE_DIR;
const workspace = await ensureAgentWorkspace({
dir: workspaceDirRaw,
ensureBootstrapFiles: !agentCfg?.skipBootstrap && !isFastTestEnv,
});
const workspaceDir = workspace.dir;
const agentDir = resolveAgentDir(cfg, agentId);
const timeoutMs = resolveAgentTimeoutMs({ cfg, overrideSeconds: opts?.timeoutOverrideSeconds });
const configuredTypingSeconds =
agentCfg?.typingIntervalSeconds ?? sessionCfg?.typingIntervalSeconds;
const typingIntervalSeconds =
typeof configuredTypingSeconds === "number" ? configuredTypingSeconds : 6;
const typing = createTypingController({
onReplyStart: opts?.onReplyStart,
onCleanup: opts?.onTypingCleanup,
typingIntervalSeconds,
silentToken: SILENT_REPLY_TOKEN,
log: defaultRuntime.log,
});
opts?.onTypingController?.(typing);
const finalized = finalizeInboundContext(ctx);
if (!isFastTestEnv) {
await applyMediaUnderstanding({
ctx: finalized,
cfg,
agentDir,
activeModel: { provider, model },
});
await applyLinkUnderstanding({
ctx: finalized,
cfg,
});
}
const commandAuthorized = finalized.CommandAuthorized;
resolveCommandAuthorization({
ctx: finalized,
cfg,
commandAuthorized,
});
const sessionState = await initSessionState({
ctx: finalized,
cfg,
commandAuthorized,
});
let {
sessionCtx,
sessionEntry,
previousSessionEntry,
sessionStore,
sessionKey,
sessionId,
isNewSession,
resetTriggered,
systemSent,
abortedLastRun,
storePath,
sessionScope,
groupResolution,
isGroup,
triggerBodyNormalized,
bodyStripped,
} = sessionState;
await applyResetModelOverride({
cfg,
resetTriggered,
bodyStripped,
sessionCtx,
ctx: finalized,
sessionEntry,
sessionStore,
sessionKey,
storePath,
defaultProvider,
defaultModel,
aliasIndex,
});
const directiveResult = await resolveReplyDirectives({
ctx: finalized,
cfg,
agentId,
agentDir,
workspaceDir,
agentCfg,
sessionCtx,
sessionEntry,
sessionStore,
sessionKey,
storePath,
sessionScope,
groupResolution,
isGroup,
triggerBodyNormalized,
commandAuthorized,
defaultProvider,
defaultModel,
aliasIndex,
provider,
model,
hasResolvedHeartbeatModelOverride,
typing,
opts: resolvedOpts,
skillFilter: mergedSkillFilter,
});
if (directiveResult.kind === "reply") {
return directiveResult.reply;
}
let {
commandSource,
command,
allowTextCommands,
skillCommands,
directives,
cleanedBody,
elevatedEnabled,
elevatedAllowed,
elevatedFailures,
defaultActivation,
resolvedThinkLevel,
resolvedVerboseLevel,
resolvedReasoningLevel,
resolvedElevatedLevel,
execOverrides,
blockStreamingEnabled,
blockReplyChunking,
resolvedBlockStreamingBreak,
provider: resolvedProvider,
model: resolvedModel,
modelState,
contextTokens,
inlineStatusRequested,
directiveAck,
perMessageQueueMode,
perMessageQueueOptions,
} = directiveResult.result;
provider = resolvedProvider;
model = resolvedModel;
const inlineActionResult = await handleInlineActions({
ctx,
sessionCtx,
cfg,
agentId,
agentDir,
sessionEntry,
previousSessionEntry,
sessionStore,
sessionKey,
storePath,
sessionScope,
workspaceDir,
isGroup,
opts: resolvedOpts,
typing,
allowTextCommands,
inlineStatusRequested,
command,
skillCommands,
directives,
cleanedBody,
elevatedEnabled,
elevatedAllowed,
elevatedFailures,
defaultActivation: () => defaultActivation,
resolvedThinkLevel,
resolvedVerboseLevel,
resolvedReasoningLevel,
resolvedElevatedLevel,
resolveDefaultThinkingLevel: modelState.resolveDefaultThinkingLevel,
provider,
model,
contextTokens,
directiveAck,
abortedLastRun,
skillFilter: mergedSkillFilter,
});
if (inlineActionResult.kind === "reply") {
return inlineActionResult.reply;
}
directives = inlineActionResult.directives;
abortedLastRun = inlineActionResult.abortedLastRun ?? abortedLastRun;
await stageSandboxMedia({
ctx,
sessionCtx,
cfg,
sessionKey,
workspaceDir,
});
return runPreparedReply({
ctx,
sessionCtx,
cfg,
agentId,
agentDir,
agentCfg,
sessionCfg,
commandAuthorized,
command,
commandSource,
allowTextCommands,
directives,
defaultActivation,
resolvedThinkLevel,
resolvedVerboseLevel,
resolvedReasoningLevel,
resolvedElevatedLevel,
execOverrides,
elevatedEnabled,
elevatedAllowed,
blockStreamingEnabled,
blockReplyChunking,
resolvedBlockStreamingBreak,
modelState,
provider,
model,
perMessageQueueMode,
perMessageQueueOptions,
typing,
opts: resolvedOpts,
defaultProvider,
defaultModel,
timeoutMs,
isNewSession,
resetTriggered,
systemSent,
sessionEntry,
sessionStore,
sessionKey,
sessionId,
storePath,
workspaceDir,
abortedLastRun,
});
}