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

465 lines
16 KiB
TypeScript

import crypto from "node:crypto";
import type { ExecToolDefaults } from "../../agents/bash-tools.js";
import type { OpenClawConfig } from "../../config/config.js";
import type { MsgContext, TemplateContext } from "../templating.js";
import type { GetReplyOptions, ReplyPayload } from "../types.js";
import type { buildCommandContext } from "./commands.js";
import type { InlineDirectives } from "./directive-handling.js";
import type { createModelSelectionState } from "./model-selection.js";
import type { TypingController } from "./typing.js";
import { resolveSessionAuthProfileOverride } from "../../agents/auth-profiles/session-override.js";
import {
abortEmbeddedPiRun,
isEmbeddedPiRunActive,
isEmbeddedPiRunStreaming,
resolveEmbeddedSessionLane,
} from "../../agents/pi-embedded.js";
import {
resolveGroupSessionKey,
resolveSessionFilePath,
resolveSessionFilePathOptions,
type SessionEntry,
updateSessionStore,
} from "../../config/sessions.js";
import { logVerbose } from "../../globals.js";
import { clearCommandLane, getQueueSize } from "../../process/command-queue.js";
import { normalizeMainKey } from "../../routing/session-key.js";
import { isReasoningTagProvider } from "../../utils/provider-utils.js";
import { hasControlCommand } from "../command-detection.js";
import { buildInboundMediaNote } from "../media-note.js";
import {
type ElevatedLevel,
formatXHighModelHint,
normalizeThinkLevel,
type ReasoningLevel,
supportsXHighThinking,
type ThinkLevel,
type VerboseLevel,
} from "../thinking.js";
import { SILENT_REPLY_TOKEN } from "../tokens.js";
import { runReplyAgent } from "./agent-runner.js";
import { applySessionHints } from "./body.js";
import { buildGroupChatContext, buildGroupIntro } from "./groups.js";
import { buildInboundMetaSystemPrompt, buildInboundUserContextPrefix } from "./inbound-meta.js";
import { resolveQueueSettings } from "./queue.js";
import { routeReply } from "./route-reply.js";
import { BARE_SESSION_RESET_PROMPT } from "./session-reset-prompt.js";
import { ensureSkillSnapshot, prependSystemEvents } from "./session-updates.js";
import { resolveTypingMode } from "./typing-mode.js";
import { appendUntrustedContext } from "./untrusted-context.js";
type AgentDefaults = NonNullable<OpenClawConfig["agents"]>["defaults"];
type ExecOverrides = Pick<ExecToolDefaults, "host" | "security" | "ask" | "node">;
type RunPreparedReplyParams = {
ctx: MsgContext;
sessionCtx: TemplateContext;
cfg: OpenClawConfig;
agentId: string;
agentDir: string;
agentCfg: AgentDefaults;
sessionCfg: OpenClawConfig["session"];
commandAuthorized: boolean;
command: ReturnType<typeof buildCommandContext>;
commandSource: string;
allowTextCommands: boolean;
directives: InlineDirectives;
defaultActivation: Parameters<typeof buildGroupIntro>[0]["defaultActivation"];
resolvedThinkLevel: ThinkLevel | undefined;
resolvedVerboseLevel: VerboseLevel | undefined;
resolvedReasoningLevel: ReasoningLevel;
resolvedElevatedLevel: ElevatedLevel;
execOverrides?: ExecOverrides;
elevatedEnabled: boolean;
elevatedAllowed: boolean;
blockStreamingEnabled: boolean;
blockReplyChunking?: {
minChars: number;
maxChars: number;
breakPreference: "paragraph" | "newline" | "sentence";
flushOnParagraph?: boolean;
};
resolvedBlockStreamingBreak: "text_end" | "message_end";
modelState: Awaited<ReturnType<typeof createModelSelectionState>>;
provider: string;
model: string;
perMessageQueueMode?: InlineDirectives["queueMode"];
perMessageQueueOptions?: {
debounceMs?: number;
cap?: number;
dropPolicy?: InlineDirectives["dropPolicy"];
};
typing: TypingController;
opts?: GetReplyOptions;
defaultProvider: string;
defaultModel: string;
timeoutMs: number;
isNewSession: boolean;
resetTriggered: boolean;
systemSent: boolean;
sessionEntry?: SessionEntry;
sessionStore?: Record<string, SessionEntry>;
sessionKey: string;
sessionId?: string;
storePath?: string;
workspaceDir: string;
abortedLastRun: boolean;
};
export async function runPreparedReply(
params: RunPreparedReplyParams,
): Promise<ReplyPayload | ReplyPayload[] | undefined> {
const {
ctx,
sessionCtx,
cfg,
agentId,
agentDir,
agentCfg,
sessionCfg,
commandAuthorized,
command,
commandSource,
allowTextCommands,
directives,
defaultActivation,
elevatedEnabled,
elevatedAllowed,
blockStreamingEnabled,
blockReplyChunking,
resolvedBlockStreamingBreak,
modelState,
provider,
model,
perMessageQueueMode,
perMessageQueueOptions,
typing,
opts,
defaultProvider,
defaultModel,
timeoutMs,
isNewSession,
resetTriggered,
systemSent,
sessionKey,
sessionId,
storePath,
workspaceDir,
sessionStore,
} = params;
let {
sessionEntry,
resolvedThinkLevel,
resolvedVerboseLevel,
resolvedReasoningLevel,
resolvedElevatedLevel,
execOverrides,
abortedLastRun,
} = params;
let currentSystemSent = systemSent;
const isFirstTurnInSession = isNewSession || !currentSystemSent;
const isGroupChat = sessionCtx.ChatType === "group";
const wasMentioned = ctx.WasMentioned === true;
const isHeartbeat = opts?.isHeartbeat === true;
const typingMode = resolveTypingMode({
configured: sessionCfg?.typingMode ?? agentCfg?.typingMode,
isGroupChat,
wasMentioned,
isHeartbeat,
});
const shouldInjectGroupIntro = Boolean(
isGroupChat && (isFirstTurnInSession || sessionEntry?.groupActivationNeedsSystemIntro),
);
// Always include persistent group chat context (name, participants, reply guidance)
const groupChatContext = isGroupChat ? buildGroupChatContext({ sessionCtx }) : "";
// Behavioral intro (activation mode, lurking, etc.) only on first turn / activation needed
const groupIntro = shouldInjectGroupIntro
? buildGroupIntro({
cfg,
sessionCtx,
sessionEntry,
defaultActivation,
silentToken: SILENT_REPLY_TOKEN,
})
: "";
const groupSystemPrompt = sessionCtx.GroupSystemPrompt?.trim() ?? "";
const inboundMetaPrompt = buildInboundMetaSystemPrompt(
isNewSession ? sessionCtx : { ...sessionCtx, ThreadStarterBody: undefined },
);
const extraSystemPrompt = [inboundMetaPrompt, groupChatContext, groupIntro, groupSystemPrompt]
.filter(Boolean)
.join("\n\n");
const baseBody = sessionCtx.BodyStripped ?? sessionCtx.Body ?? "";
// Use CommandBody/RawBody for bare reset detection (clean message without structural context).
const rawBodyTrimmed = (ctx.CommandBody ?? ctx.RawBody ?? ctx.Body ?? "").trim();
const baseBodyTrimmedRaw = baseBody.trim();
if (
allowTextCommands &&
(!commandAuthorized || !command.isAuthorizedSender) &&
!baseBodyTrimmedRaw &&
hasControlCommand(commandSource, cfg)
) {
typing.cleanup();
return undefined;
}
const isBareNewOrReset = rawBodyTrimmed === "/new" || rawBodyTrimmed === "/reset";
const isBareSessionReset =
isNewSession &&
((baseBodyTrimmedRaw.length === 0 && rawBodyTrimmed.length > 0) || isBareNewOrReset);
const baseBodyFinal = isBareSessionReset ? BARE_SESSION_RESET_PROMPT : baseBody;
const inboundUserContext = buildInboundUserContextPrefix(
isNewSession
? {
...sessionCtx,
...(sessionCtx.ThreadHistoryBody?.trim()
? { InboundHistory: undefined, ThreadStarterBody: undefined }
: {}),
}
: { ...sessionCtx, ThreadStarterBody: undefined },
);
const baseBodyForPrompt = isBareSessionReset
? baseBodyFinal
: [inboundUserContext, baseBodyFinal].filter(Boolean).join("\n\n");
const baseBodyTrimmed = baseBodyForPrompt.trim();
const hasMediaAttachment = Boolean(
sessionCtx.MediaPath || (sessionCtx.MediaPaths && sessionCtx.MediaPaths.length > 0),
);
if (!baseBodyTrimmed && !hasMediaAttachment) {
await typing.onReplyStart();
logVerbose("Inbound body empty after normalization; skipping agent run");
typing.cleanup();
return {
text: "I didn't receive any text in your message. Please resend or add a caption.",
};
}
// When the user sends media without text, provide a minimal body so the agent
// run proceeds and the image/document is injected by the embedded runner.
const effectiveBaseBody = baseBodyTrimmed
? baseBodyForPrompt
: "[User sent media without caption]";
let prefixedBodyBase = await applySessionHints({
baseBody: effectiveBaseBody,
abortedLastRun,
sessionEntry,
sessionStore,
sessionKey,
storePath,
abortKey: command.abortKey,
});
const isGroupSession = sessionEntry?.chatType === "group" || sessionEntry?.chatType === "channel";
const isMainSession = !isGroupSession && sessionKey === normalizeMainKey(sessionCfg?.mainKey);
prefixedBodyBase = await prependSystemEvents({
cfg,
sessionKey,
isMainSession,
isNewSession,
prefixedBodyBase,
});
prefixedBodyBase = appendUntrustedContext(prefixedBodyBase, sessionCtx.UntrustedContext);
const threadStarterBody = ctx.ThreadStarterBody?.trim();
const threadHistoryBody = ctx.ThreadHistoryBody?.trim();
const threadContextNote =
isNewSession && threadHistoryBody
? `[Thread history - for context]\n${threadHistoryBody}`
: isNewSession && threadStarterBody
? `[Thread starter - for context]\n${threadStarterBody}`
: undefined;
const skillResult = await ensureSkillSnapshot({
sessionEntry,
sessionStore,
sessionKey,
storePath,
sessionId,
isFirstTurnInSession,
workspaceDir,
cfg,
skillFilter: opts?.skillFilter,
});
sessionEntry = skillResult.sessionEntry ?? sessionEntry;
currentSystemSent = skillResult.systemSent;
const skillsSnapshot = skillResult.skillsSnapshot;
const prefixedBody = [threadContextNote, prefixedBodyBase].filter(Boolean).join("\n\n");
const mediaNote = buildInboundMediaNote(ctx);
const mediaReplyHint = mediaNote
? "To send an image back, prefer the message tool (media/path/filePath). If you must inline, use MEDIA:https://example.com/image.jpg (spaces ok, quote if needed) or a safe relative path like MEDIA:./image.jpg. Avoid absolute paths (MEDIA:/...) and ~ paths — they are blocked for security. Keep caption in the text body."
: undefined;
let prefixedCommandBody = mediaNote
? [mediaNote, mediaReplyHint, prefixedBody ?? ""].filter(Boolean).join("\n").trim()
: prefixedBody;
if (!resolvedThinkLevel && prefixedCommandBody) {
const parts = prefixedCommandBody.split(/\s+/);
const maybeLevel = normalizeThinkLevel(parts[0]);
if (maybeLevel && (maybeLevel !== "xhigh" || supportsXHighThinking(provider, model))) {
resolvedThinkLevel = maybeLevel;
prefixedCommandBody = parts.slice(1).join(" ").trim();
}
}
if (!resolvedThinkLevel) {
resolvedThinkLevel = await modelState.resolveDefaultThinkingLevel();
}
if (resolvedThinkLevel === "xhigh" && !supportsXHighThinking(provider, model)) {
const explicitThink = directives.hasThinkDirective && directives.thinkLevel !== undefined;
if (explicitThink) {
typing.cleanup();
return {
text: `Thinking level "xhigh" is only supported for ${formatXHighModelHint()}. Use /think high or switch to one of those models.`,
};
}
resolvedThinkLevel = "high";
if (sessionEntry && sessionStore && sessionKey && sessionEntry.thinkingLevel === "xhigh") {
sessionEntry.thinkingLevel = "high";
sessionEntry.updatedAt = Date.now();
sessionStore[sessionKey] = sessionEntry;
if (storePath) {
await updateSessionStore(storePath, (store) => {
store[sessionKey] = sessionEntry;
});
}
}
}
if (resetTriggered && command.isAuthorizedSender) {
// oxlint-disable-next-line typescript/no-explicit-any
const channel = ctx.OriginatingChannel || (command.channel as any);
const to = ctx.OriginatingTo || command.from || command.to;
if (channel && to) {
const modelLabel = `${provider}/${model}`;
const defaultLabel = `${defaultProvider}/${defaultModel}`;
const text =
modelLabel === defaultLabel
? `✅ New session started · model: ${modelLabel}`
: `✅ New session started · model: ${modelLabel} (default: ${defaultLabel})`;
await routeReply({
payload: { text },
channel,
to,
sessionKey,
accountId: ctx.AccountId,
threadId: ctx.MessageThreadId,
cfg,
});
}
}
const sessionIdFinal = sessionId ?? crypto.randomUUID();
const sessionFile = resolveSessionFilePath(
sessionIdFinal,
sessionEntry,
resolveSessionFilePathOptions({ agentId, storePath }),
);
const queueBodyBase = [threadContextNote, effectiveBaseBody].filter(Boolean).join("\n\n");
const queuedBody = mediaNote
? [mediaNote, mediaReplyHint, queueBodyBase].filter(Boolean).join("\n").trim()
: queueBodyBase;
const resolvedQueue = resolveQueueSettings({
cfg,
channel: sessionCtx.Provider,
sessionEntry,
inlineMode: perMessageQueueMode,
inlineOptions: perMessageQueueOptions,
});
const sessionLaneKey = resolveEmbeddedSessionLane(sessionKey ?? sessionIdFinal);
const laneSize = getQueueSize(sessionLaneKey);
if (resolvedQueue.mode === "interrupt" && laneSize > 0) {
const cleared = clearCommandLane(sessionLaneKey);
const aborted = abortEmbeddedPiRun(sessionIdFinal);
logVerbose(`Interrupting ${sessionLaneKey} (cleared ${cleared}, aborted=${aborted})`);
}
const queueKey = sessionKey ?? sessionIdFinal;
const isActive = isEmbeddedPiRunActive(sessionIdFinal);
const isStreaming = isEmbeddedPiRunStreaming(sessionIdFinal);
const shouldSteer = resolvedQueue.mode === "steer" || resolvedQueue.mode === "steer-backlog";
const shouldFollowup =
resolvedQueue.mode === "followup" ||
resolvedQueue.mode === "collect" ||
resolvedQueue.mode === "steer-backlog";
const authProfileId = await resolveSessionAuthProfileOverride({
cfg,
provider,
agentDir,
sessionEntry,
sessionStore,
sessionKey,
storePath,
isNewSession,
});
const authProfileIdSource = sessionEntry?.authProfileOverrideSource;
const followupRun = {
prompt: queuedBody,
messageId: sessionCtx.MessageSidFull ?? sessionCtx.MessageSid,
summaryLine: baseBodyTrimmedRaw,
enqueuedAt: Date.now(),
// Originating channel for reply routing.
originatingChannel: ctx.OriginatingChannel,
originatingTo: ctx.OriginatingTo,
originatingAccountId: ctx.AccountId,
originatingThreadId: ctx.MessageThreadId,
originatingChatType: ctx.ChatType,
run: {
agentId,
agentDir,
sessionId: sessionIdFinal,
sessionKey,
messageProvider: sessionCtx.Provider?.trim().toLowerCase() || undefined,
agentAccountId: sessionCtx.AccountId,
groupId: resolveGroupSessionKey(sessionCtx)?.id ?? undefined,
groupChannel: sessionCtx.GroupChannel?.trim() ?? sessionCtx.GroupSubject?.trim(),
groupSpace: sessionCtx.GroupSpace?.trim() ?? undefined,
senderId: sessionCtx.SenderId?.trim() || undefined,
senderName: sessionCtx.SenderName?.trim() || undefined,
senderUsername: sessionCtx.SenderUsername?.trim() || undefined,
senderE164: sessionCtx.SenderE164?.trim() || undefined,
senderIsOwner: command.senderIsOwner,
sessionFile,
workspaceDir,
config: cfg,
skillsSnapshot,
provider,
model,
authProfileId,
authProfileIdSource,
thinkLevel: resolvedThinkLevel,
verboseLevel: resolvedVerboseLevel,
reasoningLevel: resolvedReasoningLevel,
elevatedLevel: resolvedElevatedLevel,
execOverrides,
bashElevated: {
enabled: elevatedEnabled,
allowed: elevatedAllowed,
defaultLevel: resolvedElevatedLevel ?? "off",
},
timeoutMs,
blockReplyBreak: resolvedBlockStreamingBreak,
ownerNumbers: command.ownerList.length > 0 ? command.ownerList : undefined,
extraSystemPrompt: extraSystemPrompt || undefined,
...(isReasoningTagProvider(provider) ? { enforceFinalTag: true } : {}),
},
};
return runReplyAgent({
commandBody: prefixedCommandBody,
followupRun,
queueKey,
resolvedQueue,
shouldSteer,
shouldFollowup,
isActive,
isStreaming,
opts,
typing,
sessionEntry,
sessionStore,
sessionKey,
storePath,
defaultModel,
agentCfgContextTokens: agentCfg?.contextTokens,
resolvedVerboseLevel: resolvedVerboseLevel ?? "off",
isNewSession,
blockStreamingEnabled,
blockReplyChunking,
resolvedBlockStreamingBreak,
sessionCtx,
shouldInjectGroupIntro,
typingMode,
});
}