Files
openclaw/src/agents/pi-tools.policy.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

325 lines
10 KiB
TypeScript

import type { OpenClawConfig } from "../config/config.js";
import type { AnyAgentTool } from "./pi-tools.types.js";
import type { SandboxToolPolicy } from "./sandbox.js";
import { getChannelDock } from "../channels/dock.js";
import { resolveChannelGroupToolsPolicy } from "../config/group-policy.js";
import { resolveThreadParentSessionKey } from "../sessions/session-key-utils.js";
import { normalizeMessageChannel } from "../utils/message-channel.js";
import { resolveAgentConfig, resolveAgentIdFromSessionKey } from "./agent-scope.js";
import { compileGlobPatterns, matchesAnyGlobPattern } from "./glob-pattern.js";
import { expandToolGroups, normalizeToolName } from "./tool-policy.js";
function makeToolPolicyMatcher(policy: SandboxToolPolicy) {
const deny = compileGlobPatterns({
raw: expandToolGroups(policy.deny ?? []),
normalize: normalizeToolName,
});
const allow = compileGlobPatterns({
raw: expandToolGroups(policy.allow ?? []),
normalize: normalizeToolName,
});
return (name: string) => {
const normalized = normalizeToolName(name);
if (matchesAnyGlobPattern(normalized, deny)) {
return false;
}
if (allow.length === 0) {
return true;
}
if (matchesAnyGlobPattern(normalized, allow)) {
return true;
}
if (normalized === "apply_patch" && matchesAnyGlobPattern("exec", allow)) {
return true;
}
return false;
};
}
/**
* Tools always denied for sub-agents regardless of depth.
* These are system-level or interactive tools that sub-agents should never use.
*/
const SUBAGENT_TOOL_DENY_ALWAYS = [
// System admin - dangerous from subagent
"gateway",
"agents_list",
// Interactive setup - not a task
"whatsapp_login",
// Status/scheduling - main agent coordinates
"session_status",
"cron",
// Memory - pass relevant info in spawn prompt instead
"memory_search",
"memory_get",
// Direct session sends - subagents communicate through announce chain
"sessions_send",
];
/**
* Additional tools denied for leaf sub-agents (depth >= maxSpawnDepth).
* These are tools that only make sense for orchestrator sub-agents that can spawn children.
*/
const SUBAGENT_TOOL_DENY_LEAF = ["sessions_list", "sessions_history", "sessions_spawn"];
/**
* Build the deny list for a sub-agent at a given depth.
*
* - Depth 1 with maxSpawnDepth >= 2 (orchestrator): allowed to use sessions_spawn,
* subagents, sessions_list, sessions_history so it can manage its children.
* - Depth >= maxSpawnDepth (leaf): denied sessions_spawn and
* session management tools. Still allowed subagents (for list/status visibility).
*/
function resolveSubagentDenyList(depth: number, maxSpawnDepth: number): string[] {
const isLeaf = depth >= Math.max(1, Math.floor(maxSpawnDepth));
if (isLeaf) {
return [...SUBAGENT_TOOL_DENY_ALWAYS, ...SUBAGENT_TOOL_DENY_LEAF];
}
// Orchestrator sub-agent: only deny the always-denied tools.
// sessions_spawn, subagents, sessions_list, sessions_history are allowed.
return [...SUBAGENT_TOOL_DENY_ALWAYS];
}
export function resolveSubagentToolPolicy(cfg?: OpenClawConfig, depth?: number): SandboxToolPolicy {
const configured = cfg?.tools?.subagents?.tools;
const maxSpawnDepth = cfg?.agents?.defaults?.subagents?.maxSpawnDepth ?? 1;
const effectiveDepth = typeof depth === "number" && depth >= 0 ? depth : 1;
const baseDeny = resolveSubagentDenyList(effectiveDepth, maxSpawnDepth);
const deny = [...baseDeny, ...(Array.isArray(configured?.deny) ? configured.deny : [])];
const allow = Array.isArray(configured?.allow) ? configured.allow : undefined;
return { allow, deny };
}
export function isToolAllowedByPolicyName(name: string, policy?: SandboxToolPolicy): boolean {
if (!policy) {
return true;
}
return makeToolPolicyMatcher(policy)(name);
}
export function filterToolsByPolicy(tools: AnyAgentTool[], policy?: SandboxToolPolicy) {
if (!policy) {
return tools;
}
const matcher = makeToolPolicyMatcher(policy);
return tools.filter((tool) => matcher(tool.name));
}
type ToolPolicyConfig = {
allow?: string[];
alsoAllow?: string[];
deny?: string[];
profile?: string;
};
function unionAllow(base?: string[], extra?: string[]) {
if (!Array.isArray(extra) || extra.length === 0) {
return base;
}
// If the user is using alsoAllow without an allowlist, treat it as additive on top of
// an implicit allow-all policy.
if (!Array.isArray(base) || base.length === 0) {
return Array.from(new Set(["*", ...extra]));
}
return Array.from(new Set([...base, ...extra]));
}
function pickToolPolicy(config?: ToolPolicyConfig): SandboxToolPolicy | undefined {
if (!config) {
return undefined;
}
const allow = Array.isArray(config.allow)
? unionAllow(config.allow, config.alsoAllow)
: Array.isArray(config.alsoAllow) && config.alsoAllow.length > 0
? unionAllow(undefined, config.alsoAllow)
: undefined;
const deny = Array.isArray(config.deny) ? config.deny : undefined;
if (!allow && !deny) {
return undefined;
}
return { allow, deny };
}
function normalizeProviderKey(value: string): string {
return value.trim().toLowerCase();
}
function resolveGroupContextFromSessionKey(sessionKey?: string | null): {
channel?: string;
groupId?: string;
} {
const raw = (sessionKey ?? "").trim();
if (!raw) {
return {};
}
const base = resolveThreadParentSessionKey(raw) ?? raw;
const parts = base.split(":").filter(Boolean);
let body = parts[0] === "agent" ? parts.slice(2) : parts;
if (body[0] === "subagent") {
body = body.slice(1);
}
if (body.length < 3) {
return {};
}
const [channel, kind, ...rest] = body;
if (kind !== "group" && kind !== "channel") {
return {};
}
const groupId = rest.join(":").trim();
if (!groupId) {
return {};
}
return { channel: channel.trim().toLowerCase(), groupId };
}
function resolveProviderToolPolicy(params: {
byProvider?: Record<string, ToolPolicyConfig>;
modelProvider?: string;
modelId?: string;
}): ToolPolicyConfig | undefined {
const provider = params.modelProvider?.trim();
if (!provider || !params.byProvider) {
return undefined;
}
const entries = Object.entries(params.byProvider);
if (entries.length === 0) {
return undefined;
}
const lookup = new Map<string, ToolPolicyConfig>();
for (const [key, value] of entries) {
const normalized = normalizeProviderKey(key);
if (!normalized) {
continue;
}
lookup.set(normalized, value);
}
const normalizedProvider = normalizeProviderKey(provider);
const rawModelId = params.modelId?.trim().toLowerCase();
const fullModelId =
rawModelId && !rawModelId.includes("/") ? `${normalizedProvider}/${rawModelId}` : rawModelId;
const candidates = [...(fullModelId ? [fullModelId] : []), normalizedProvider];
for (const key of candidates) {
const match = lookup.get(key);
if (match) {
return match;
}
}
return undefined;
}
export function resolveEffectiveToolPolicy(params: {
config?: OpenClawConfig;
sessionKey?: string;
modelProvider?: string;
modelId?: string;
}) {
const agentId = params.sessionKey ? resolveAgentIdFromSessionKey(params.sessionKey) : undefined;
const agentConfig =
params.config && agentId ? resolveAgentConfig(params.config, agentId) : undefined;
const agentTools = agentConfig?.tools;
const globalTools = params.config?.tools;
const profile = agentTools?.profile ?? globalTools?.profile;
const providerPolicy = resolveProviderToolPolicy({
byProvider: globalTools?.byProvider,
modelProvider: params.modelProvider,
modelId: params.modelId,
});
const agentProviderPolicy = resolveProviderToolPolicy({
byProvider: agentTools?.byProvider,
modelProvider: params.modelProvider,
modelId: params.modelId,
});
return {
agentId,
globalPolicy: pickToolPolicy(globalTools),
globalProviderPolicy: pickToolPolicy(providerPolicy),
agentPolicy: pickToolPolicy(agentTools),
agentProviderPolicy: pickToolPolicy(agentProviderPolicy),
profile,
providerProfile: agentProviderPolicy?.profile ?? providerPolicy?.profile,
// alsoAllow is applied at the profile stage (to avoid being filtered out early).
profileAlsoAllow: Array.isArray(agentTools?.alsoAllow)
? agentTools?.alsoAllow
: Array.isArray(globalTools?.alsoAllow)
? globalTools?.alsoAllow
: undefined,
providerProfileAlsoAllow: Array.isArray(agentProviderPolicy?.alsoAllow)
? agentProviderPolicy?.alsoAllow
: Array.isArray(providerPolicy?.alsoAllow)
? providerPolicy?.alsoAllow
: undefined,
};
}
export function resolveGroupToolPolicy(params: {
config?: OpenClawConfig;
sessionKey?: string;
spawnedBy?: string | null;
messageProvider?: string;
groupId?: string | null;
groupChannel?: string | null;
groupSpace?: string | null;
accountId?: string | null;
senderId?: string | null;
senderName?: string | null;
senderUsername?: string | null;
senderE164?: string | null;
}): SandboxToolPolicy | undefined {
if (!params.config) {
return undefined;
}
const sessionContext = resolveGroupContextFromSessionKey(params.sessionKey);
const spawnedContext = resolveGroupContextFromSessionKey(params.spawnedBy);
const groupId = params.groupId ?? sessionContext.groupId ?? spawnedContext.groupId;
if (!groupId) {
return undefined;
}
const channelRaw = params.messageProvider ?? sessionContext.channel ?? spawnedContext.channel;
const channel = normalizeMessageChannel(channelRaw);
if (!channel) {
return undefined;
}
let dock;
try {
dock = getChannelDock(channel);
} catch {
dock = undefined;
}
const toolsConfig =
dock?.groups?.resolveToolPolicy?.({
cfg: params.config,
groupId,
groupChannel: params.groupChannel,
groupSpace: params.groupSpace,
accountId: params.accountId,
senderId: params.senderId,
senderName: params.senderName,
senderUsername: params.senderUsername,
senderE164: params.senderE164,
}) ??
resolveChannelGroupToolsPolicy({
cfg: params.config,
channel,
groupId,
accountId: params.accountId,
senderId: params.senderId,
senderName: params.senderName,
senderUsername: params.senderUsername,
senderE164: params.senderE164,
});
return pickToolPolicy(toolsConfig);
}
export function isToolAllowedByPolicies(
name: string,
policies: Array<SandboxToolPolicy | undefined>,
) {
return policies.every((policy) => isToolAllowedByPolicyName(name, policy));
}