openclaw/src/plugins/commands.ts

331 lines
8.7 KiB
TypeScript
Raw Normal View History

/**
* Plugin Command Registry
*
* Manages commands registered by plugins that bypass the LLM agent.
* These commands are processed before built-in commands and before agent invocation.
*/
2026-01-30 03:15:10 +01:00
import type { OpenClawConfig } from "../config/config.js";
import { logVerbose } from "../globals.js";
import type {
2026-01-30 03:15:10 +01:00
OpenClawPluginCommandDefinition,
PluginCommandContext,
PluginCommandResult,
} from "./types.js";
2026-01-30 03:15:10 +01:00
type RegisteredPluginCommand = OpenClawPluginCommandDefinition & {
pluginId: string;
};
// Registry of plugin commands
const pluginCommands: Map<string, RegisteredPluginCommand> = new Map();
// Lock to prevent modifications during command execution
let registryLocked = false;
// Maximum allowed length for command arguments (defense in depth)
const MAX_ARGS_LENGTH = 4096;
/**
* Reserved command names that plugins cannot override.
* These are built-in commands from commands-registry.data.ts.
*/
const RESERVED_COMMANDS = new Set([
// Core commands
"help",
"commands",
"status",
"whoami",
"context",
// Session management
"stop",
"restart",
"reset",
"new",
"compact",
// Configuration
"config",
"debug",
"allowlist",
"activation",
// Agent control
"skill",
"subagents",
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
"kill",
"steer",
"tell",
"model",
"models",
"queue",
// Messaging
"send",
// Execution
"bash",
"exec",
// Mode toggles
"think",
"verbose",
"reasoning",
"elevated",
// Billing
"usage",
]);
/**
* Validate a command name.
* Returns an error message if invalid, or null if valid.
*/
export function validateCommandName(name: string): string | null {
const trimmed = name.trim().toLowerCase();
if (!trimmed) {
return "Command name cannot be empty";
}
// Must start with a letter, contain only letters, numbers, hyphens, underscores
// Note: trimmed is already lowercased, so no need for /i flag
if (!/^[a-z][a-z0-9_-]*$/.test(trimmed)) {
return "Command name must start with a letter and contain only letters, numbers, hyphens, and underscores";
}
// Check reserved commands
if (RESERVED_COMMANDS.has(trimmed)) {
return `Command name "${trimmed}" is reserved by a built-in command`;
}
return null;
}
export type CommandRegistrationResult = {
ok: boolean;
error?: string;
};
/**
* Register a plugin command.
* Returns an error if the command name is invalid or reserved.
*/
export function registerPluginCommand(
pluginId: string,
2026-01-30 03:15:10 +01:00
command: OpenClawPluginCommandDefinition,
): CommandRegistrationResult {
// Prevent registration while commands are being processed
if (registryLocked) {
return { ok: false, error: "Cannot register commands while processing is in progress" };
}
// Validate handler is a function
if (typeof command.handler !== "function") {
return { ok: false, error: "Command handler must be a function" };
}
if (typeof command.name !== "string") {
return { ok: false, error: "Command name must be a string" };
}
if (typeof command.description !== "string") {
return { ok: false, error: "Command description must be a string" };
}
const name = command.name.trim();
const description = command.description.trim();
if (!description) {
return { ok: false, error: "Command description cannot be empty" };
}
const validationError = validateCommandName(name);
if (validationError) {
return { ok: false, error: validationError };
}
const key = `/${name.toLowerCase()}`;
// Check for duplicate registration
if (pluginCommands.has(key)) {
const existing = pluginCommands.get(key)!;
return {
ok: false,
error: `Command "${name}" already registered by plugin "${existing.pluginId}"`,
};
}
pluginCommands.set(key, { ...command, name, description, pluginId });
logVerbose(`Registered plugin command: ${key} (plugin: ${pluginId})`);
return { ok: true };
}
/**
* Clear all registered plugin commands.
* Called during plugin reload.
*/
export function clearPluginCommands(): void {
pluginCommands.clear();
}
/**
* Clear plugin commands for a specific plugin.
*/
export function clearPluginCommandsForPlugin(pluginId: string): void {
for (const [key, cmd] of pluginCommands.entries()) {
if (cmd.pluginId === pluginId) {
pluginCommands.delete(key);
}
}
}
/**
* Check if a command body matches a registered plugin command.
* Returns the command definition and parsed args if matched.
*
* Note: If a command has `acceptsArgs: false` and the user provides arguments,
* the command will not match. This allows the message to fall through to
* built-in handlers or the agent. Document this behavior to plugin authors.
*/
export function matchPluginCommand(
commandBody: string,
): { command: RegisteredPluginCommand; args?: string } | null {
const trimmed = commandBody.trim();
if (!trimmed.startsWith("/")) {
return null;
}
// Extract command name and args
const spaceIndex = trimmed.indexOf(" ");
const commandName = spaceIndex === -1 ? trimmed : trimmed.slice(0, spaceIndex);
const args = spaceIndex === -1 ? undefined : trimmed.slice(spaceIndex + 1).trim();
const key = commandName.toLowerCase();
const command = pluginCommands.get(key);
if (!command) {
return null;
}
// If command doesn't accept args but args were provided, don't match
if (args && !command.acceptsArgs) {
return null;
}
return { command, args: args || undefined };
}
/**
* Sanitize command arguments to prevent injection attacks.
* Removes control characters and enforces length limits.
*/
function sanitizeArgs(args: string | undefined): string | undefined {
if (!args) {
return undefined;
}
// Enforce length limit
if (args.length > MAX_ARGS_LENGTH) {
return args.slice(0, MAX_ARGS_LENGTH);
}
// Remove control characters (except newlines and tabs which may be intentional)
let sanitized = "";
for (const char of args) {
const code = char.charCodeAt(0);
const isControl = (code <= 0x1f && code !== 0x09 && code !== 0x0a) || code === 0x7f;
if (!isControl) {
sanitized += char;
}
}
return sanitized;
}
/**
* Execute a plugin command handler.
*
* Note: Plugin authors should still validate and sanitize ctx.args for their
* specific use case. This function provides basic defense-in-depth sanitization.
*/
export async function executePluginCommand(params: {
command: RegisteredPluginCommand;
args?: string;
senderId?: string;
channel: string;
channelId?: PluginCommandContext["channelId"];
isAuthorizedSender: boolean;
commandBody: string;
2026-01-30 03:15:10 +01:00
config: OpenClawConfig;
from?: PluginCommandContext["from"];
to?: PluginCommandContext["to"];
accountId?: PluginCommandContext["accountId"];
messageThreadId?: PluginCommandContext["messageThreadId"];
}): Promise<PluginCommandResult> {
const { command, args, senderId, channel, isAuthorizedSender, commandBody, config } = params;
// Check authorization
const requireAuth = command.requireAuth !== false; // Default to true
if (requireAuth && !isAuthorizedSender) {
logVerbose(
`Plugin command /${command.name} blocked: unauthorized sender ${senderId || "<unknown>"}`,
);
return { text: "⚠️ This command requires authorization." };
}
// Sanitize args before passing to handler
const sanitizedArgs = sanitizeArgs(args);
const ctx: PluginCommandContext = {
senderId,
channel,
channelId: params.channelId,
isAuthorizedSender,
args: sanitizedArgs,
commandBody,
config,
from: params.from,
to: params.to,
accountId: params.accountId,
messageThreadId: params.messageThreadId,
};
// Lock registry during execution to prevent concurrent modifications
registryLocked = true;
try {
const result = await command.handler(ctx);
logVerbose(
`Plugin command /${command.name} executed successfully for ${senderId || "unknown"}`,
);
return result;
} catch (err) {
const error = err as Error;
logVerbose(`Plugin command /${command.name} error: ${error.message}`);
// Don't leak internal error details - return a safe generic message
return { text: "⚠️ Command failed. Please try again later." };
} finally {
registryLocked = false;
}
}
/**
* List all registered plugin commands.
* Used for /help and /commands output.
*/
export function listPluginCommands(): Array<{
name: string;
description: string;
pluginId: string;
}> {
return Array.from(pluginCommands.values()).map((cmd) => ({
name: cmd.name,
description: cmd.description,
pluginId: cmd.pluginId,
}));
}
/**
* Get plugin command specs for native command registration (e.g., Telegram).
*/
export function getPluginCommandSpecs(): Array<{
name: string;
description: string;
}> {
return Array.from(pluginCommands.values()).map((cmd) => ({
name: cmd.name,
description: cmd.description,
}));
}