mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-08-04 14:57:42 +00:00
* 🎯 feat: Tool Intent Label Capability (tool_intents) Adds the fourth member of the per-tool capability family (defer_loading, allowed_callers, run_in_background): an admin capability AgentCapabilities.tool_intents plus a per-tool tool_options[name].describe_intent flag. Opted-in tools get an optional intent string injected as the FIRST property of their schema — one model-authored sentence per call, streamed to the client as the call's live status label (args already reach the client verbatim, so no new event plumbing). Native host tools (web_search, create_file/edit_file, set_memory/delete_memory, ask_user_question) default on while the capability is enabled; explicit false opts out. SDK-native intent schemas (@librechat/agents coding suite) are recognized and left alone. - packages/api/src/agents/intent.ts: structural sibling of background.ts — first-key non-mutating injection with registry parity (covers deferred/tool_search discovery), eligibility and PTC-only skips, arg read/strip helpers, self-spawn strip for defs and registry, ephemeral/model-spec synthesis with a tool_options merge so the background and intent toggles compose. - handlers.ts: intent runs BEFORE background injection so the label stays the first streamed key when a tool carries both (pinned by test); the arg is stripped before invocation unless the tool's own schema declares it, on both the foreground and background-dispatch paths; PTC target schemas are sanitized like background's. - Capability plumbing through all four routes (endpoint initialize, openai + responses controllers, the exported OpenAI-compatible service) plus handoff discovery and added-convo agents, and the intentToolNames execution channel via configurable. - describe_intent on toolOptionsSchema (all three written-out Zod annotations), ToolOptions, TEphemeralAgent, TModelSpec (+ zod), and data-schemas doc comments (tool_options is Mixed — no migration). - intent.spec.ts: 28 tests cloned from background.spec.ts structure, including the intent+background key-order composition. * 🧯 fix: Codex Review — Opt-Out Strips SDK-Native Intent, Skip mcp_all Placeholders - An explicit describe_intent: false now REMOVES an SDK-native intent property from the definition and registry entry, so the per-tool opt-out actually disables the arg's token cost for tools like web_search that carry the schema natively (SDK bodies tolerate its absence). Previously the early return left the property in place. - synthesizeIntentToolOptions skips lazily-expanded mcp_all placeholders instead of recording options under names that applyIntentLabels' exact-name matching can never match, and documents the limitation (parity with synthesizeBackgroundToolOptions). The P1 about the client not rendering the label is the documented slicing: the UI streaming-label PR follows once #14391's ToolCallGroup changes merge — args already reach the client, so that slice is purely rendering. * 🧯 fix: Codex Re-Review — Label Marker Guard, Capability Kill Switch, Late Defs, Service Threading - removeIntentParam is now marker-guarded (the label contract's opening instruction discriminates it), so an MCP/action tool's own business `intent` parameter is never stripped by an opt-out or the disabled path — previously an explicit false could remove a real, possibly required argument. - New sanitizeIntentLabels pass runs AFTER every registration step (the skill catalog appends its SDK definition post-injection): with tool_intents disabled it strips SDK-native intent labels from all definitions and registry entries, making the capability a real kill switch over their token cost; with it enabled it enforces explicit per-tool opt-outs on late-registered definitions. - ask_user_question removed from the native default-on set: its graph tool is rebuilt in run.ts from its own Zod schema (also the HITL card's wire shape), so definition-level injection never reached the model. Its intent support lands with the HITL slice, which threads the label into the interrupt payload deliberately. - The exported OpenAI-compatible service now threads intentToolNames into the run configurable, so the executor's PTC path can strip host-injected intent schemas on that route like the in-repo controllers do. * 🧯 fix: Codex Round 2 — Post-Skill Injection, PTC Native Strip, Service Boundary, Honest Docs - Intent injection now runs LAST in initializeAgent, after the skill catalog — which both appends its own definition and REPLACES upgraded ones (skill-aware read_file), clobbering an earlier injection while intentToolNames still listed the tool. Injection PREPENDS while background APPENDS, so intent stays the first schema property under the new ordering (pinned by a reverse-order composition test). - The PTC target-schema strip is now marker-guarded strip-ALL: SDK- native intent labels (which are deliberately never in intentToolNames) are removed from sandbox-advertised schemas alongside host-injected ones; business intent params survive. - toolIntentsAvailable on the exported service documents the loader boundary: a custom LoadToolsFn returning only structured instances bypasses definition/registry injection and sanitize by construction. - librechat.example.yaml describes tool_intents as backend groundwork with UI rendering in an upcoming release rather than promising a live label today. * 📦 chore: bump `@librechat/agents` to v3.3.6 Brings in the SDK half of tool intent labels (danny-avila/agents#347, #349): intent-first schemas on the coding suite across all three engines, plus web_search / subagent / skill / tool_search, and the outcome / outcome_patch result channel. Activates three host paths that were inert while no SDK tool shipped an `intent` property — verified against the real 3.3.6 schemas: - capability OFF now strips SDK-native labels (a real admin kill switch) - explicit `describe_intent: false` removes them per tool - host injection stays idempotent against an SDK schema, keeping `intent` first and never double-injecting * 🔬 test: Real-Provider Verification for Tool Intent Labels Adds the live check the unit tests structurally cannot perform: whether a real model actually authors the injected arg, places it FIRST, and gives sibling calls to one tool distinct labels. Reuses the existing real-provider harness (in-memory Mongo, seeded user, credential neutralizer) and the existing stdio MCP fixture as a genuine tool, so no external service is involved. - e2e/config/librechat.real.yaml: adds the e2e-memory MCP server and the tool_intents capability, giving the real model something to call. The sibling spec asserts only relative token growth, so the extra schemas do not perturb it. - e2e/playwright.config.real.ts: optional Langfuse passthrough. The LANGFUSE_* keys match the credential-neutralizer pattern and were being blanked before the server booted; they are preserved explicitly, read from the invoking environment only, and never written to the generated config. - e2e/specs/real/tool-intents.spec.ts: two facts stored in one turn, both through the same tool, asserting intent is the first key of each call and that the two labels differ. Args are read from persistence rather than the DOM deliberately — no UI renders the label yet, and persistence is what a reloaded conversation and the trace both read. First run against claude-haiku-4-5 produced 'Recording the location of the OAuth callback router' and 'Recording the location of the MCP connection pool configuration' — distinct, first-position, no tool name. Also updates tool-intent-spec.md: records the 3.3.7 removal of the tense verb map with the evidence that motivated it, the trimmed description and the marker's role as an API, and a new mandatory requirement that client-side label rendering be gated on a server-sent signal rather than the presence of an intent key (a tool's own business 'intent' parameter would otherwise render as a status label). * 📦 chore: bump `@librechat/agents` to v3.3.7 and dedupe the intent contract Picks up danny-avila/agents#353: the tense verb map is gone (a bare intent now displays unchanged, with completion carried by UI state), the model-facing description is trimmed 502 → 289 chars, and both the marker and the description are exported. Stops redeclaring the SDK contract here: - INTENT_LABEL_MARKER is imported instead of duplicated as a string literal. Every removal path in this module keys on it, and a local copy that drifted from the SDK's would make them all stop recognizing SDK-native labels — failing OPEN, with labels left in schemas and per-tool opt-outs silently inert. - INTENT_DESCRIPTION is imported too, so host-injected tools and SDK-native tools present the model with one identical instruction. Keeping the old local copy would also have meant host-injected tools still paying ~126 tokens per schema while SDK tools paid ~72. Verified live against real Anthropic after the trim: two sibling calls to one MCP tool produced 'Storing the OAuth callback router file location' and 'Storing the MCP connection pool configuration file location' — first-position and distinct, so the shorter description holds compliance.
1875 lines
61 KiB
JavaScript
1875 lines
61 KiB
JavaScript
const { logger, redactMessage } = require('@librechat/data-schemas');
|
|
const { tool: toolFn, DynamicStructuredTool } = require('@librechat/agents/langchain/tools');
|
|
const {
|
|
sleep,
|
|
createToolSearch,
|
|
createBashExecutionTool,
|
|
Constants: AgentConstants,
|
|
createBashProgrammaticToolCallingTool,
|
|
} = require('@librechat/agents');
|
|
const {
|
|
sendEvent,
|
|
getToolkitKey,
|
|
getUserMCPAuthMap,
|
|
loadToolDefinitions,
|
|
GenerationJobManager,
|
|
isActionDomainAllowed,
|
|
buildWebSearchContext,
|
|
buildImageToolContext,
|
|
buildToolClassification,
|
|
getMissingCustomUserVars,
|
|
buildWebSearchDynamicContext,
|
|
getCodeApiAuthHeaders,
|
|
getReplayablePendingMCPOAuthStart,
|
|
getMCPServerNamesFromTools,
|
|
buildMCPAuthToolCall,
|
|
buildMCPAuthStepId,
|
|
buildMCPAuthRunStepEvent,
|
|
buildMCPAuthRunStepDeltaEvent,
|
|
buildMCPAuthRunStepCompletedEvent,
|
|
isFileAuthoringToolDefinition,
|
|
ASK_USER_QUESTION_TOOL_NAME,
|
|
} = require('@librechat/api');
|
|
const {
|
|
Time,
|
|
Tools,
|
|
Constants,
|
|
CacheKeys,
|
|
ErrorTypes,
|
|
ContentTypes,
|
|
imageGenTools,
|
|
EModelEndpoint,
|
|
EToolResources,
|
|
isActionTool,
|
|
actionDelimiter,
|
|
ImageVisionTool,
|
|
openapiToFunction,
|
|
AgentCapabilities,
|
|
isEphemeralAgentId,
|
|
validateActionDomain,
|
|
actionDomainSeparator,
|
|
defaultAgentCapabilities,
|
|
validateAndParseOpenAPISpec,
|
|
} = require('librechat-data-provider');
|
|
const {
|
|
createActionTool,
|
|
legacyDomainEncode,
|
|
decryptMetadata,
|
|
loadActionSets,
|
|
domainParser,
|
|
} = require('./ActionService');
|
|
const {
|
|
getEndpointsConfig,
|
|
getMCPServerTools,
|
|
getCachedTools,
|
|
} = require('~/server/services/Config');
|
|
const { processFileURL, uploadImageBuffer } = require('~/server/services/Files/process');
|
|
const { primeFiles: primeSearchFiles } = require('~/app/clients/tools/util/fileSearch');
|
|
const { primeFiles: primeCodeFiles } = require('~/server/services/Files/Code/process');
|
|
const { manifestToolMap, toolkits } = require('~/app/clients/tools/manifest');
|
|
const { createOnSearchResults } = require('~/server/services/Tools/search');
|
|
const { reinitMCPServer } = require('~/server/services/Tools/mcp');
|
|
const { createMCPPermissionContext, resolveMcpServerContext } = require('~/server/services/MCP');
|
|
const { getMCPRequestContext } = require('~/server/services/MCPRequestContext');
|
|
const { recordUsage } = require('~/server/services/Threads');
|
|
const { loadTools } = require('~/app/clients/tools/util');
|
|
const { findPluginAuthsByKeys } = require('~/models');
|
|
const { getFlowStateManager, getMCPServersRegistry } = require('~/config');
|
|
const { getLogStores } = require('~/cache');
|
|
|
|
const domainSeparatorRegex = new RegExp(actionDomainSeparator, 'g');
|
|
|
|
/**
|
|
* Collapse every `actionDomainSeparator` sequence in the encoded-domain
|
|
* suffix of a fully-qualified action tool name to an underscore. Agents
|
|
* can store tool names in the raw `domainParser(..., true)` output,
|
|
* which for short hostnames is a `---`-separated string (e.g.
|
|
* `medium---com`). The lookup maps below are always keyed with the
|
|
* `_`-collapsed domain, so every read must normalize that suffix or
|
|
* short-hostname tools silently fail to resolve.
|
|
*
|
|
* The operationId portion (everything before the last `actionDelimiter`)
|
|
* is deliberately left untouched: `openapiToFunction` preserves hyphens
|
|
* in generated operationIds, so two specs can legitimately produce
|
|
* operationIds that differ only in hyphens-vs-underscores (e.g.
|
|
* `get_foo---bar` vs `get_foo_bar`). Collapsing the operationId would
|
|
* merge those into a single map slot and silently drop one tool.
|
|
*/
|
|
const normalizeActionToolName = (toolName) => {
|
|
const delimiterIndex = toolName.lastIndexOf(actionDelimiter);
|
|
if (delimiterIndex === -1) {
|
|
return toolName;
|
|
}
|
|
const prefixEnd = delimiterIndex + actionDelimiter.length;
|
|
const encodedDomain = toolName.slice(prefixEnd);
|
|
return toolName.slice(0, prefixEnd) + encodedDomain.replace(domainSeparatorRegex, '_');
|
|
};
|
|
|
|
/**
|
|
* Populate a `toolToAction` map with one slot per fully-qualified tool
|
|
* name (`<operationId><actionDelimiter><encoded-domain>`). Both the new
|
|
* and the legacy encodings of the domain are registered for every
|
|
* function so agents whose stored tool names predate the current
|
|
* encoding still resolve correctly.
|
|
*
|
|
* Indexing on the full tool name instead of the encoded domain alone is
|
|
* what makes multi-action agents work when two actions share a hostname:
|
|
* the operationId disambiguates them, so neither overwrites the other.
|
|
*
|
|
* Two actions that additionally share the same operationId still
|
|
* collide (nothing in the key distinguishes them). That case is
|
|
* pathological — `sanitizeOperationId` plus OpenAPI's own uniqueness
|
|
* requirement make it very unlikely — but when it does happen we log
|
|
* a warning so the silent-overwrite mode from the original bug cannot
|
|
* reappear under a different disguise.
|
|
*/
|
|
const registerActionTools = ({
|
|
toolToAction,
|
|
functionSignatures,
|
|
normalizedDomain,
|
|
legacyNormalized,
|
|
makeEntry,
|
|
}) => {
|
|
const setKey = (key, entry) => {
|
|
if (toolToAction.has(key)) {
|
|
logger.warn(
|
|
`[Actions] operationId collision: "${key}" already registered; ` +
|
|
`action "${entry.action?.action_id}" overwrites the previous entry. ` +
|
|
`Two actions share both the operationId and the encoded hostname.`,
|
|
);
|
|
}
|
|
toolToAction.set(key, entry);
|
|
};
|
|
|
|
for (const sig of functionSignatures) {
|
|
const entry = makeEntry(sig);
|
|
// Use `sig.name` verbatim: `openapiToFunction` keeps hyphens in
|
|
// generated operationIds, so `get_foo---bar` and `get_foo_bar` are
|
|
// distinct operations on the same spec. `normalizeActionToolName`
|
|
// only touches the encoded-domain suffix at lookup time, so map
|
|
// keys and lookups stay consistent without merging distinct
|
|
// operationIds into the same slot.
|
|
setKey(`${sig.name}${actionDelimiter}${normalizedDomain}`, entry);
|
|
if (legacyNormalized !== normalizedDomain) {
|
|
setKey(`${sig.name}${actionDelimiter}${legacyNormalized}`, entry);
|
|
}
|
|
}
|
|
};
|
|
|
|
/**
|
|
* Resolves the set of enabled agent capabilities from endpoints config,
|
|
* falling back to app-level or default capabilities for ephemeral agents.
|
|
* @param {ServerRequest} req
|
|
* @param {Object} appConfig
|
|
* @param {string} agentId
|
|
* @returns {Promise<Set<string>>}
|
|
*/
|
|
async function resolveAgentCapabilities(req, appConfig, agentId) {
|
|
const endpointsConfig = await getEndpointsConfig(req);
|
|
let capabilities = new Set(endpointsConfig?.[EModelEndpoint.agents]?.capabilities ?? []);
|
|
if (capabilities.size === 0 && isEphemeralAgentId(agentId)) {
|
|
capabilities = new Set(
|
|
appConfig.endpoints?.[EModelEndpoint.agents]?.capabilities ?? defaultAgentCapabilities,
|
|
);
|
|
}
|
|
return capabilities;
|
|
}
|
|
|
|
/**
|
|
* Processes the required actions by calling the appropriate tools and returning the outputs.
|
|
* @param {OpenAIClient} client - OpenAI or StreamRunManager Client.
|
|
* @param {RequiredAction} requiredActions - The current required action.
|
|
* @returns {Promise<ToolOutput>} The outputs of the tools.
|
|
*/
|
|
const processVisionRequest = async (client, currentAction) => {
|
|
if (!client.visionPromise) {
|
|
return {
|
|
tool_call_id: currentAction.toolCallId,
|
|
output: 'No image details found.',
|
|
};
|
|
}
|
|
|
|
/** @type {ChatCompletion | undefined} */
|
|
const completion = await client.visionPromise;
|
|
if (completion && completion.usage) {
|
|
recordUsage({
|
|
user: client.req.user.id,
|
|
model: client.req.body.model,
|
|
conversationId: (client.responseMessage ?? client.finalMessage).conversationId,
|
|
...completion.usage,
|
|
});
|
|
}
|
|
const output = completion?.choices?.[0]?.message?.content ?? 'No image details found.';
|
|
return {
|
|
tool_call_id: currentAction.toolCallId,
|
|
output,
|
|
};
|
|
};
|
|
|
|
/**
|
|
* Processes return required actions from run.
|
|
* @param {OpenAIClient | StreamRunManager} client - OpenAI (legacy) or StreamRunManager Client.
|
|
* @param {RequiredAction[]} requiredActions - The required actions to submit outputs for.
|
|
* @returns {Promise<ToolOutputs>} The outputs of the tools.
|
|
*/
|
|
async function processRequiredActions(client, requiredActions) {
|
|
logger.debug(
|
|
`[required actions] user: ${client.req.user.id} | thread_id: ${requiredActions[0].thread_id} | run_id: ${requiredActions[0].run_id}`,
|
|
requiredActions,
|
|
);
|
|
const appConfig = client.req.config;
|
|
const toolDefinitions = (await getCachedTools()) ?? {};
|
|
const seenToolkits = new Set();
|
|
const tools = requiredActions
|
|
.map((action) => {
|
|
const toolName = action.tool;
|
|
const toolDef = toolDefinitions[toolName];
|
|
if (toolDef && !manifestToolMap[toolName]) {
|
|
for (const toolkit of toolkits) {
|
|
if (seenToolkits.has(toolkit.pluginKey)) {
|
|
return;
|
|
} else if (toolName.startsWith(`${toolkit.pluginKey}_`)) {
|
|
seenToolkits.add(toolkit.pluginKey);
|
|
return toolkit.pluginKey;
|
|
}
|
|
}
|
|
}
|
|
return toolName;
|
|
})
|
|
.filter((toolName) => !!toolName);
|
|
|
|
const { loadedTools } = await loadTools({
|
|
user: client.req.user.id,
|
|
model: client.req.body.model ?? 'gpt-4o-mini',
|
|
tools,
|
|
functions: true,
|
|
endpoint: client.req.body.endpoint,
|
|
options: {
|
|
processFileURL,
|
|
req: client.req,
|
|
uploadImageBuffer,
|
|
openAIApiKey: client.apiKey,
|
|
returnMetadata: true,
|
|
},
|
|
webSearch: appConfig.webSearch,
|
|
fileStrategy: appConfig.fileStrategy,
|
|
imageOutputType: appConfig.imageOutputType,
|
|
});
|
|
|
|
const ToolMap = loadedTools.reduce((map, tool) => {
|
|
map[tool.name] = tool;
|
|
return map;
|
|
}, {});
|
|
|
|
const promises = [];
|
|
|
|
let actionSetsData = null;
|
|
let isActionTool = false;
|
|
const ActionToolMap = {};
|
|
const ActionBuildersMap = {};
|
|
|
|
for (let i = 0; i < requiredActions.length; i++) {
|
|
const currentAction = requiredActions[i];
|
|
if (currentAction.tool === ImageVisionTool.function.name) {
|
|
promises.push(processVisionRequest(client, currentAction));
|
|
continue;
|
|
}
|
|
let tool = ToolMap[currentAction.tool] ?? ActionToolMap[currentAction.tool];
|
|
|
|
const handleToolOutput = async (output) => {
|
|
requiredActions[i].output = output;
|
|
|
|
/** @type {FunctionToolCall & PartMetadata} */
|
|
const toolCall = {
|
|
function: {
|
|
name: currentAction.tool,
|
|
arguments: JSON.stringify(currentAction.toolInput),
|
|
output,
|
|
},
|
|
id: currentAction.toolCallId,
|
|
type: 'function',
|
|
progress: 1,
|
|
action: isActionTool,
|
|
};
|
|
|
|
const toolCallIndex = client.mappedOrder.get(toolCall.id);
|
|
|
|
if (imageGenTools.has(currentAction.tool)) {
|
|
const imageOutput = output;
|
|
toolCall.function.output = `${currentAction.tool} displayed an image. All generated images are already plainly visible, so don't repeat the descriptions in detail. Do not list download links as they are available in the UI already. The user may download the images by clicking on them, but do not mention anything about downloading to the user.`;
|
|
|
|
// Streams the "Finished" state of the tool call in the UI
|
|
client.addContentData({
|
|
[ContentTypes.TOOL_CALL]: toolCall,
|
|
index: toolCallIndex,
|
|
type: ContentTypes.TOOL_CALL,
|
|
});
|
|
|
|
await sleep(500);
|
|
|
|
/** @type {ImageFile} */
|
|
const imageDetails = {
|
|
...imageOutput,
|
|
...currentAction.toolInput,
|
|
};
|
|
|
|
const image_file = {
|
|
[ContentTypes.IMAGE_FILE]: imageDetails,
|
|
type: ContentTypes.IMAGE_FILE,
|
|
// Replace the tool call output with Image file
|
|
index: toolCallIndex,
|
|
};
|
|
|
|
client.addContentData(image_file);
|
|
|
|
// Update the stored tool call
|
|
client.seenToolCalls && client.seenToolCalls.set(toolCall.id, toolCall);
|
|
|
|
return {
|
|
tool_call_id: currentAction.toolCallId,
|
|
output: toolCall.function.output,
|
|
};
|
|
}
|
|
|
|
client.seenToolCalls && client.seenToolCalls.set(toolCall.id, toolCall);
|
|
client.addContentData({
|
|
[ContentTypes.TOOL_CALL]: toolCall,
|
|
index: toolCallIndex,
|
|
type: ContentTypes.TOOL_CALL,
|
|
// TODO: to append tool properties to stream, pass metadata rest to addContentData
|
|
// result: tool.result,
|
|
});
|
|
|
|
return {
|
|
tool_call_id: currentAction.toolCallId,
|
|
output,
|
|
};
|
|
};
|
|
|
|
if (!tool) {
|
|
// throw new Error(`Tool ${currentAction.tool} not found.`);
|
|
|
|
if (!actionSetsData) {
|
|
/** @type {Action[]} */
|
|
const actionSets =
|
|
(await loadActionSets({
|
|
assistant_id: client.req.body.assistant_id,
|
|
})) ?? [];
|
|
|
|
// See registerActionTools for the key-shape rationale.
|
|
const toolToAction = new Map();
|
|
|
|
for (const action of actionSets) {
|
|
const domain = await domainParser(action.metadata.domain, true);
|
|
const normalizedDomain = domain.replace(domainSeparatorRegex, '_');
|
|
const legacyDomain = legacyDomainEncode(action.metadata.domain);
|
|
const legacyNormalized = legacyDomain.replace(domainSeparatorRegex, '_');
|
|
|
|
const isDomainAllowed = await isActionDomainAllowed(
|
|
action.metadata.domain,
|
|
appConfig?.actions?.allowedDomains,
|
|
appConfig?.actions?.allowedAddresses,
|
|
);
|
|
if (!isDomainAllowed) {
|
|
continue;
|
|
}
|
|
|
|
// Validate and parse OpenAPI spec
|
|
const validationResult = validateAndParseOpenAPISpec(action.metadata.raw_spec);
|
|
if (!validationResult.spec || !validationResult.serverUrl) {
|
|
throw new Error(
|
|
`Invalid spec: user: ${client.req.user.id} | thread_id: ${requiredActions[0].thread_id} | run_id: ${requiredActions[0].run_id}`,
|
|
);
|
|
}
|
|
|
|
// SECURITY: Validate the domain from the spec matches the stored domain
|
|
// This is defense-in-depth to prevent any stored malicious actions
|
|
const domainValidation = validateActionDomain(
|
|
action.metadata.domain,
|
|
validationResult.serverUrl,
|
|
);
|
|
if (!domainValidation.isValid) {
|
|
logger.error(`Domain mismatch in stored action: ${domainValidation.message}`, {
|
|
userId: client.req.user.id,
|
|
action_id: action.action_id,
|
|
});
|
|
continue; // Skip this action rather than failing the entire request
|
|
}
|
|
|
|
// Process the OpenAPI spec
|
|
const { requestBuilders, functionSignatures } = openapiToFunction(validationResult.spec);
|
|
|
|
// Store encrypted values for OAuth flow
|
|
const encrypted = {
|
|
oauth_client_id: action.metadata.oauth_client_id,
|
|
oauth_client_secret: action.metadata.oauth_client_secret,
|
|
};
|
|
|
|
// Decrypt metadata
|
|
const decryptedAction = { ...action };
|
|
decryptedAction.metadata = await decryptMetadata(action.metadata);
|
|
|
|
registerActionTools({
|
|
toolToAction,
|
|
functionSignatures,
|
|
normalizedDomain,
|
|
legacyNormalized,
|
|
makeEntry: (sig) => ({
|
|
action: decryptedAction,
|
|
requestBuilder: requestBuilders[sig.name],
|
|
encrypted,
|
|
}),
|
|
});
|
|
|
|
// Store builders for reuse
|
|
ActionBuildersMap[action.metadata.domain] = requestBuilders;
|
|
}
|
|
|
|
actionSetsData = toolToAction;
|
|
}
|
|
|
|
const entry = actionSetsData.get(normalizeActionToolName(currentAction.tool));
|
|
if (!entry) {
|
|
continue;
|
|
}
|
|
|
|
const { action, requestBuilder, encrypted } = entry;
|
|
|
|
// We've already decrypted the metadata, so we can pass it directly
|
|
const _allowedDomains = appConfig?.actions?.allowedDomains;
|
|
const _allowedAddresses = appConfig?.actions?.allowedAddresses;
|
|
tool = await createActionTool({
|
|
userId: client.req.user.id,
|
|
res: client.res,
|
|
action,
|
|
requestBuilder,
|
|
// Note: intentionally not passing zodSchema, name, and description for assistants API
|
|
encrypted, // Pass the encrypted values for OAuth flow
|
|
useSSRFProtection: !Array.isArray(_allowedDomains) || _allowedDomains.length === 0,
|
|
allowedAddresses: _allowedAddresses,
|
|
});
|
|
if (!tool) {
|
|
logger.warn(
|
|
`Invalid action: user: ${client.req.user.id} | thread_id: ${requiredActions[0].thread_id} | run_id: ${requiredActions[0].run_id} | toolName: ${currentAction.tool}`,
|
|
);
|
|
throw new Error(`{"type":"${ErrorTypes.INVALID_ACTION}"}`);
|
|
}
|
|
isActionTool = !!tool;
|
|
ActionToolMap[currentAction.tool] = tool;
|
|
}
|
|
|
|
if (currentAction.tool === 'calculator') {
|
|
currentAction.toolInput = currentAction.toolInput.input;
|
|
}
|
|
|
|
const handleToolError = (error) => {
|
|
logger.error(
|
|
`tool_call_id: ${currentAction.toolCallId} | Error processing tool ${currentAction.tool}`,
|
|
error,
|
|
);
|
|
return {
|
|
tool_call_id: currentAction.toolCallId,
|
|
output: `Error processing tool ${currentAction.tool}: ${redactMessage(error.message, 256)}`,
|
|
};
|
|
};
|
|
|
|
try {
|
|
const promise = tool
|
|
._call(currentAction.toolInput)
|
|
.then(handleToolOutput)
|
|
.catch(handleToolError);
|
|
promises.push(promise);
|
|
} catch (error) {
|
|
const toolOutputError = handleToolError(error);
|
|
promises.push(Promise.resolve(toolOutputError));
|
|
}
|
|
}
|
|
|
|
return {
|
|
tool_outputs: await Promise.all(promises),
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Processes the runtime tool calls and returns the tool classes.
|
|
* @param {Object} params - Run params containing user and request information.
|
|
* @param {ServerRequest} params.req - The request object.
|
|
* @param {ServerResponse} params.res - The request object.
|
|
* @param {AbortSignal} params.signal
|
|
* @param {Pick<Agent, 'id' | 'provider' | 'model' | 'tools'} params.agent - The agent to load tools for.
|
|
* @param {string | undefined} [params.openAIApiKey] - The OpenAI API key.
|
|
* @returns {Promise<{
|
|
* tools?: StructuredTool[];
|
|
* toolContextMap?: Record<string, unknown>;
|
|
* dynamicToolContextMap?: Record<string, unknown>;
|
|
* userMCPAuthMap?: Record<string, Record<string, string>>;
|
|
* toolRegistry?: Map<string, import('~/utils/toolClassification').LCTool>;
|
|
* hasDeferredTools?: boolean;
|
|
* }>} The agent tools and registry.
|
|
*/
|
|
/** Native LibreChat tools that are not in the manifest */
|
|
const nativeTools = new Set([
|
|
Tools.execute_code,
|
|
Tools.file_search,
|
|
Tools.web_search,
|
|
Tools.memory,
|
|
]);
|
|
|
|
/** Checks if a tool name is a known built-in tool */
|
|
const isBuiltInTool = (toolName) =>
|
|
Boolean(
|
|
manifestToolMap[toolName] ||
|
|
toolkits.some((t) => t.pluginKey === toolName) ||
|
|
nativeTools.has(toolName),
|
|
);
|
|
|
|
/**
|
|
* Loads only tool definitions without creating tool instances.
|
|
* This is the efficient path for event-driven mode where tools are loaded on-demand.
|
|
*
|
|
* @param {Object} params
|
|
* @param {ServerRequest} params.req - The request object
|
|
* @param {ServerResponse} [params.res] - The response object for SSE events
|
|
* @param {Object} params.agent - The agent configuration
|
|
* @param {string|null} [params.streamId] - Stream ID for resumable mode
|
|
* @param {number} [params.jobCreatedAt] - The generation epoch that owns emitted tool events
|
|
* @returns {Promise<{
|
|
* toolDefinitions?: import('@librechat/api').LCTool[];
|
|
* toolRegistry?: Map<string, import('@librechat/api').LCTool>;
|
|
* mcpAvailableTools?: Record<string, import('@librechat/api').LCAvailableTools>;
|
|
* userMCPAuthMap?: Record<string, Record<string, string>>;
|
|
* hasDeferredTools?: boolean;
|
|
* }>}
|
|
*/
|
|
async function loadToolDefinitionsWrapper({
|
|
req,
|
|
res,
|
|
agent,
|
|
streamId = null,
|
|
jobCreatedAt,
|
|
tool_resources,
|
|
}) {
|
|
if (!agent.tools || agent.tools.length === 0) {
|
|
return { toolDefinitions: [] };
|
|
}
|
|
|
|
if (
|
|
agent.tools.length === 1 &&
|
|
(agent.tools[0] === AgentCapabilities.context || agent.tools[0] === AgentCapabilities.ocr)
|
|
) {
|
|
return { toolDefinitions: [] };
|
|
}
|
|
|
|
const appConfig = req.config;
|
|
const enabledCapabilities = await resolveAgentCapabilities(req, appConfig, agent.id);
|
|
|
|
const checkCapability = (capability) => enabledCapabilities.has(capability);
|
|
const areToolsEnabled = checkCapability(AgentCapabilities.tools);
|
|
const actionsEnabled = checkCapability(AgentCapabilities.actions);
|
|
const deferredToolsEnabled = checkCapability(AgentCapabilities.deferred_tools);
|
|
const programmaticToolsEnabled = enabledCapabilities.has(AgentCapabilities.programmatic_tools);
|
|
const codeExecutionEnabled =
|
|
agent.tools?.includes(Tools.execute_code) === true &&
|
|
enabledCapabilities.has(AgentCapabilities.execute_code);
|
|
const hasMCPTools = agent.tools?.some((tool) => tool?.includes(Constants.mcp_delimiter));
|
|
const mcpPermissionContext = createMCPPermissionContext(req);
|
|
const canUseMCP = hasMCPTools ? await mcpPermissionContext.canUseServers(req.user) : true;
|
|
|
|
const filteredTools = agent.tools?.filter((tool) => {
|
|
if (tool === Tools.file_search) {
|
|
return checkCapability(AgentCapabilities.file_search);
|
|
}
|
|
if (tool === Tools.execute_code) {
|
|
return checkCapability(AgentCapabilities.execute_code);
|
|
}
|
|
if (tool === Tools.web_search) {
|
|
return checkCapability(AgentCapabilities.web_search);
|
|
}
|
|
if (tool === Tools.memory) {
|
|
return checkCapability(AgentCapabilities.memory);
|
|
}
|
|
if (tool === ASK_USER_QUESTION_TOOL_NAME) {
|
|
return checkCapability(AgentCapabilities.ask_user_question);
|
|
}
|
|
if (isActionTool(tool)) {
|
|
return actionsEnabled;
|
|
}
|
|
if (tool?.includes(Constants.mcp_delimiter)) {
|
|
return areToolsEnabled && canUseMCP;
|
|
}
|
|
if (!areToolsEnabled) {
|
|
return false;
|
|
}
|
|
return true;
|
|
});
|
|
|
|
if (!filteredTools || filteredTools.length === 0) {
|
|
return { toolDefinitions: [] };
|
|
}
|
|
|
|
/** Only MCP tool keys need the server context; a purely non-MCP agent should not
|
|
* pay an app-config lookup on startup. */
|
|
const hasFilteredMCPTools = filteredTools.some((t) => t.includes(Constants.mcp_delimiter));
|
|
const { configServers, serverNames: mcpServerNames } = hasFilteredMCPTools
|
|
? await resolveMcpServerContext(req)
|
|
: { configServers: {}, serverNames: [] };
|
|
|
|
/** @type {Record<string, Record<string, string>>} */
|
|
let userMCPAuthMap;
|
|
if (hasFilteredMCPTools) {
|
|
userMCPAuthMap = await getUserMCPAuthMap({
|
|
tools: filteredTools,
|
|
userId: req.user.id,
|
|
serverNames: mcpServerNames,
|
|
findPluginAuthsByKeys,
|
|
});
|
|
}
|
|
|
|
const flowsCache = getLogStores(CacheKeys.FLOWS);
|
|
const flowManager = getFlowStateManager(flowsCache);
|
|
const pendingOAuthServers = new Set();
|
|
const pendingOAuthStarts = new Map();
|
|
const emittedOAuthStarts = new Map();
|
|
const oauthToolCallIds = new Map();
|
|
const oauthStepIndexes = new Map();
|
|
/** @type {Record<string, import('@librechat/api').LCAvailableTools>} */
|
|
const mcpAvailableTools = {};
|
|
const requestScopedConnections = getMCPRequestContext(req, res);
|
|
const rememberMCPAvailableTools = (serverName, availableTools) => {
|
|
if (!availableTools || Object.keys(availableTools).length === 0) {
|
|
return;
|
|
}
|
|
mcpAvailableTools[serverName] = availableTools;
|
|
};
|
|
|
|
const createOAuthEmitter = (serverName, index) => {
|
|
return async (authURL, options) => {
|
|
if (emittedOAuthStarts.get(serverName) === authURL) {
|
|
return;
|
|
}
|
|
emittedOAuthStarts.set(serverName, authURL);
|
|
|
|
const flowId =
|
|
oauthToolCallIds.get(serverName) ?? `${req.user.id}:${serverName}:${Date.now()}`;
|
|
const stepId = buildMCPAuthStepId(serverName);
|
|
oauthToolCallIds.set(serverName, flowId);
|
|
oauthStepIndexes.set(serverName, index);
|
|
const toolCall = buildMCPAuthToolCall({
|
|
id: flowId,
|
|
serverName,
|
|
});
|
|
|
|
const runStepEvent = buildMCPAuthRunStepEvent({ stepId, toolCall, index });
|
|
const runStepDeltaEvent = buildMCPAuthRunStepDeltaEvent({
|
|
authURL,
|
|
stepId,
|
|
toolCall,
|
|
options,
|
|
});
|
|
|
|
if (streamId) {
|
|
await GenerationJobManager.emitChunk(streamId, runStepEvent, {
|
|
expectedCreatedAt: jobCreatedAt,
|
|
});
|
|
await GenerationJobManager.emitChunk(streamId, runStepDeltaEvent, {
|
|
expectedCreatedAt: jobCreatedAt,
|
|
});
|
|
} else if (res && !res.writableEnded) {
|
|
sendEvent(res, runStepEvent);
|
|
sendEvent(res, runStepDeltaEvent);
|
|
} else {
|
|
logger.warn(
|
|
`[Tool Definitions] Cannot emit OAuth event for ${serverName}: no streamId and res not available`,
|
|
);
|
|
}
|
|
};
|
|
};
|
|
|
|
const createOAuthEndEmitter = (serverName) => {
|
|
return async () => {
|
|
const stepId = buildMCPAuthStepId(serverName);
|
|
const toolCall = buildMCPAuthToolCall({
|
|
id: oauthToolCallIds.get(serverName),
|
|
args: '',
|
|
output: 'OAuth authentication completed',
|
|
serverName,
|
|
type: 'tool_call',
|
|
});
|
|
const runStepCompletedEvent = buildMCPAuthRunStepCompletedEvent({
|
|
stepId,
|
|
toolCall,
|
|
index: oauthStepIndexes.get(serverName) ?? 0,
|
|
});
|
|
|
|
if (streamId) {
|
|
await GenerationJobManager.emitChunk(streamId, runStepCompletedEvent, {
|
|
expectedCreatedAt: jobCreatedAt,
|
|
});
|
|
} else if (res && !res.writableEnded) {
|
|
sendEvent(res, runStepCompletedEvent);
|
|
} else {
|
|
logger.warn(
|
|
`[Tool Definitions] Cannot emit OAuth completion for ${serverName}: no streamId and res not available`,
|
|
);
|
|
}
|
|
};
|
|
};
|
|
|
|
const getPendingOAuthStartForEmit = async (serverName) => {
|
|
const cachedOAuthStart = pendingOAuthStarts.get(serverName);
|
|
if (cachedOAuthStart?.options?.expiresAt != null) {
|
|
return cachedOAuthStart;
|
|
}
|
|
|
|
const pendingOAuthStart = await getReplayablePendingMCPOAuthStart({
|
|
flowManager,
|
|
userId: req.user.id,
|
|
serverName,
|
|
});
|
|
if (!pendingOAuthStart) {
|
|
return cachedOAuthStart;
|
|
}
|
|
|
|
if (!cachedOAuthStart || pendingOAuthStart.authURL === cachedOAuthStart.authURL) {
|
|
pendingOAuthStarts.set(serverName, pendingOAuthStart);
|
|
return pendingOAuthStart;
|
|
}
|
|
|
|
return cachedOAuthStart;
|
|
};
|
|
|
|
const getOrFetchMCPServerTools = async (userId, serverName) => {
|
|
const addPendingOAuthServer = async () => {
|
|
const pendingOAuthStart = await getReplayablePendingMCPOAuthStart({
|
|
flowManager,
|
|
userId,
|
|
serverName,
|
|
});
|
|
if (!pendingOAuthStart) {
|
|
return false;
|
|
}
|
|
|
|
pendingOAuthServers.add(serverName);
|
|
pendingOAuthStarts.set(serverName, pendingOAuthStart);
|
|
return true;
|
|
};
|
|
|
|
let serverConfig;
|
|
try {
|
|
serverConfig =
|
|
configServers?.[serverName] ??
|
|
(await getMCPServersRegistry().getServerConfig(serverName, userId, configServers));
|
|
} catch (err) {
|
|
logger.warn(
|
|
`[Tool Definitions] MCP registry unavailable while resolving '${serverName}': ${
|
|
err?.message ?? err
|
|
}. Skipping MCP tool exposure for this lookup.`,
|
|
);
|
|
return null;
|
|
}
|
|
|
|
if (!serverConfig) {
|
|
logger.warn(
|
|
`[Tool Definitions] Skipping MCP server '${serverName}': no server config found (server may have been removed).`,
|
|
);
|
|
return null;
|
|
}
|
|
|
|
const customUserVars = userMCPAuthMap?.[`${Constants.mcp_prefix}${serverName}`];
|
|
const missingUserVars = getMissingCustomUserVars(serverConfig, customUserVars);
|
|
if (missingUserVars.length > 0) {
|
|
logger.warn(
|
|
`[Tool Definitions] Skipping MCP server '${serverName}': required user-provided variable(s) not set: ${missingUserVars.join(
|
|
', ',
|
|
)}. Tools will not be exposed until the user configures them.`,
|
|
);
|
|
return null;
|
|
}
|
|
|
|
if (mcpAvailableTools[serverName]) {
|
|
return mcpAvailableTools[serverName];
|
|
}
|
|
|
|
const cached = await getMCPServerTools(userId, serverName, serverConfig);
|
|
if (cached) {
|
|
rememberMCPAvailableTools(serverName, cached);
|
|
await addPendingOAuthServer();
|
|
return cached;
|
|
}
|
|
|
|
if (await addPendingOAuthServer()) {
|
|
return null;
|
|
}
|
|
|
|
const oauthStart = async (authURL, options) => {
|
|
pendingOAuthServers.add(serverName);
|
|
if (typeof authURL === 'string' && authURL.length > 0) {
|
|
pendingOAuthStarts.set(serverName, { authURL, options });
|
|
}
|
|
};
|
|
|
|
const result = await reinitMCPServer({
|
|
user: req.user,
|
|
oauthStart,
|
|
flowManager,
|
|
serverName,
|
|
configServers,
|
|
userMCPAuthMap,
|
|
requestBody: req.body,
|
|
requestScopedConnections,
|
|
});
|
|
|
|
rememberMCPAvailableTools(serverName, result?.availableTools);
|
|
return result?.availableTools || null;
|
|
};
|
|
|
|
const getActionToolDefinitions = async (agentId, actionToolNames) => {
|
|
const actionSets = (await loadActionSets({ agent_id: agentId })) ?? [];
|
|
if (actionSets.length === 0) {
|
|
return [];
|
|
}
|
|
|
|
const definitions = [];
|
|
const allowedDomains = appConfig?.actions?.allowedDomains;
|
|
const allowedAddresses = appConfig?.actions?.allowedAddresses;
|
|
const normalizedToolNames = new Set(
|
|
actionToolNames.map((n) => n.replace(domainSeparatorRegex, '_')),
|
|
);
|
|
|
|
for (const action of actionSets) {
|
|
const domain = await domainParser(action.metadata.domain, true);
|
|
const normalizedDomain = domain.replace(domainSeparatorRegex, '_');
|
|
|
|
const legacyDomain = legacyDomainEncode(action.metadata.domain);
|
|
const legacyNormalized = legacyDomain.replace(domainSeparatorRegex, '_');
|
|
|
|
const isDomainAllowed = await isActionDomainAllowed(
|
|
action.metadata.domain,
|
|
allowedDomains,
|
|
allowedAddresses,
|
|
);
|
|
if (!isDomainAllowed) {
|
|
logger.warn(
|
|
`[Actions] Domain "${action.metadata.domain}" not in allowedDomains. ` +
|
|
`Add it to librechat.yaml actions.allowedDomains to enable this action.`,
|
|
);
|
|
continue;
|
|
}
|
|
|
|
const validationResult = validateAndParseOpenAPISpec(action.metadata.raw_spec);
|
|
if (!validationResult.spec || !validationResult.serverUrl) {
|
|
logger.warn(`[Actions] Invalid OpenAPI spec for domain: ${domain}`);
|
|
continue;
|
|
}
|
|
|
|
const { functionSignatures } = openapiToFunction(validationResult.spec, true);
|
|
|
|
for (const sig of functionSignatures) {
|
|
const toolName = `${sig.name}${actionDelimiter}${normalizedDomain}`;
|
|
const legacyToolName = `${sig.name}${actionDelimiter}${legacyNormalized}`;
|
|
if (!normalizedToolNames.has(toolName) && !normalizedToolNames.has(legacyToolName)) {
|
|
continue;
|
|
}
|
|
|
|
definitions.push({
|
|
name: toolName,
|
|
description: sig.description,
|
|
parameters: sig.parameters,
|
|
});
|
|
}
|
|
}
|
|
|
|
return definitions;
|
|
};
|
|
|
|
let { toolDefinitions, toolRegistry, hasDeferredTools } = await loadToolDefinitions(
|
|
{
|
|
userId: req.user.id,
|
|
agentId: agent.id,
|
|
tools: filteredTools,
|
|
toolOptions: agent.tool_options,
|
|
deferredToolsEnabled,
|
|
programmaticToolsEnabled,
|
|
codeExecutionEnabled,
|
|
provider: agent.provider,
|
|
mcpServerNames,
|
|
},
|
|
{
|
|
isBuiltInTool,
|
|
getOrFetchMCPServerTools,
|
|
getActionToolDefinitions,
|
|
},
|
|
);
|
|
|
|
for (const serverName of getMCPServerNamesFromTools(filteredTools, mcpServerNames)) {
|
|
if (pendingOAuthServers.has(serverName)) {
|
|
continue;
|
|
}
|
|
|
|
const pendingOAuthStart = await getReplayablePendingMCPOAuthStart({
|
|
flowManager,
|
|
userId: req.user.id,
|
|
serverName,
|
|
});
|
|
if (pendingOAuthStart) {
|
|
pendingOAuthServers.add(serverName);
|
|
pendingOAuthStarts.set(serverName, pendingOAuthStart);
|
|
}
|
|
}
|
|
|
|
if (pendingOAuthServers.size > 0 && (res || streamId)) {
|
|
const serverNames = Array.from(pendingOAuthServers);
|
|
logger.info(
|
|
`[Tool Definitions] OAuth required for ${serverNames.length} server(s): ${serverNames.join(', ')}. Emitting events and waiting.`,
|
|
);
|
|
|
|
const oauthWaitPromises = serverNames.map(async (serverName, index) => {
|
|
try {
|
|
const pendingOAuthStart = await getPendingOAuthStartForEmit(serverName);
|
|
const oauthStart = createOAuthEmitter(serverName, index);
|
|
if (pendingOAuthStart) {
|
|
await oauthStart(pendingOAuthStart.authURL, pendingOAuthStart.options);
|
|
}
|
|
|
|
const result = await reinitMCPServer({
|
|
user: req.user,
|
|
serverName,
|
|
configServers,
|
|
userMCPAuthMap,
|
|
flowManager,
|
|
requestBody: req.body,
|
|
returnOnOAuth: false,
|
|
oauthStart,
|
|
oauthEnd: createOAuthEndEmitter(serverName),
|
|
connectionTimeout: Time.TWO_MINUTES,
|
|
});
|
|
|
|
if (result?.availableTools) {
|
|
rememberMCPAvailableTools(serverName, result.availableTools);
|
|
logger.info(`[Tool Definitions] OAuth completed for ${serverName}, tools available`);
|
|
return { serverName, success: true };
|
|
}
|
|
return { serverName, success: false };
|
|
} catch (error) {
|
|
logger.debug(`[Tool Definitions] OAuth wait failed for ${serverName}:`, error?.message);
|
|
return { serverName, success: false };
|
|
}
|
|
});
|
|
|
|
const results = await Promise.allSettled(oauthWaitPromises);
|
|
const successfulServers = results
|
|
.filter((r) => r.status === 'fulfilled' && r.value.success)
|
|
.map((r) => r.value.serverName);
|
|
|
|
if (successfulServers.length > 0) {
|
|
logger.info(
|
|
`[Tool Definitions] Reloading tools after OAuth for: ${successfulServers.join(', ')}`,
|
|
);
|
|
const reloadResult = await loadToolDefinitions(
|
|
{
|
|
userId: req.user.id,
|
|
agentId: agent.id,
|
|
tools: filteredTools,
|
|
toolOptions: agent.tool_options,
|
|
deferredToolsEnabled,
|
|
programmaticToolsEnabled,
|
|
codeExecutionEnabled,
|
|
provider: agent.provider,
|
|
mcpServerNames,
|
|
},
|
|
{
|
|
isBuiltInTool,
|
|
getOrFetchMCPServerTools,
|
|
getActionToolDefinitions,
|
|
},
|
|
);
|
|
toolDefinitions = reloadResult.toolDefinitions;
|
|
toolRegistry = reloadResult.toolRegistry;
|
|
hasDeferredTools = reloadResult.hasDeferredTools;
|
|
}
|
|
}
|
|
|
|
/** @type {Record<string, string>} */
|
|
const toolContextMap = {};
|
|
/** @type {Record<string, string>} */
|
|
const dynamicToolContextMap = {};
|
|
const hasWebSearch = filteredTools.includes(Tools.web_search);
|
|
const hasFileSearch = filteredTools.includes(Tools.file_search);
|
|
const hasExecuteCode = filteredTools.includes(Tools.execute_code);
|
|
|
|
if (hasWebSearch) {
|
|
toolContextMap[Tools.web_search] = buildWebSearchContext();
|
|
dynamicToolContextMap[Tools.web_search] = buildWebSearchDynamicContext(
|
|
req.conversationCreatedAt,
|
|
);
|
|
}
|
|
|
|
/**
|
|
* `files` carry the upload session_ids; we surface them so client.js can
|
|
* seed `Graph.sessions[EXECUTE_CODE]` before run start. Without that seed,
|
|
* the agents-side `ToolNode.getCodeSessionContext` returns undefined on
|
|
* call #1, `_injected_files` is never set on the tool call, and the
|
|
* sandbox can't see the prior turn's generated artifacts on first read.
|
|
*/
|
|
let primedCodeFiles;
|
|
if (hasExecuteCode && tool_resources) {
|
|
try {
|
|
const { toolContext, files } = await primeCodeFiles({
|
|
req,
|
|
tool_resources,
|
|
agentId: agent.id,
|
|
});
|
|
if (toolContext) {
|
|
dynamicToolContextMap[Tools.execute_code] = toolContext;
|
|
}
|
|
if (files?.length) {
|
|
primedCodeFiles = files;
|
|
}
|
|
} catch (error) {
|
|
logger.error('[loadToolDefinitionsWrapper] Error priming code files:', error);
|
|
}
|
|
}
|
|
|
|
if (hasFileSearch && tool_resources) {
|
|
try {
|
|
const { toolContext } = await primeSearchFiles({
|
|
req,
|
|
tool_resources,
|
|
agentId: agent.id,
|
|
});
|
|
if (toolContext) {
|
|
dynamicToolContextMap[Tools.file_search] = toolContext;
|
|
}
|
|
} catch (error) {
|
|
logger.error('[loadToolDefinitionsWrapper] Error priming search files:', error);
|
|
}
|
|
}
|
|
|
|
const imageFiles = tool_resources?.[EToolResources.image_edit]?.files ?? [];
|
|
if (imageFiles.length > 0) {
|
|
const hasOaiImageGen = filteredTools.includes('image_gen_oai');
|
|
const hasGeminiImageGen = filteredTools.includes('gemini_image_gen');
|
|
|
|
if (hasOaiImageGen) {
|
|
const toolContext = buildImageToolContext({
|
|
imageFiles,
|
|
toolName: `${EToolResources.image_edit}_oai`,
|
|
contextDescription: 'image editing',
|
|
});
|
|
if (toolContext) {
|
|
dynamicToolContextMap.image_edit_oai = toolContext;
|
|
}
|
|
}
|
|
|
|
if (hasGeminiImageGen) {
|
|
const toolContext = buildImageToolContext({
|
|
imageFiles,
|
|
toolName: 'gemini_image_gen',
|
|
contextDescription: 'image context',
|
|
});
|
|
if (toolContext) {
|
|
dynamicToolContextMap.gemini_image_gen = toolContext;
|
|
}
|
|
}
|
|
}
|
|
|
|
return {
|
|
toolRegistry,
|
|
mcpAvailableTools,
|
|
requestScopedConnections,
|
|
userMCPAuthMap,
|
|
toolContextMap,
|
|
dynamicToolContextMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
primedCodeFiles,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Loads agent tools for initialization or execution.
|
|
* @param {Object} params
|
|
* @param {ServerRequest} params.req - The request object
|
|
* @param {ServerResponse} params.res - The response object
|
|
* @param {Object} params.agent - The agent configuration
|
|
* @param {AbortSignal} [params.signal] - Abort signal
|
|
* @param {Object} [params.tool_resources] - Tool resources
|
|
* @param {string} [params.openAIApiKey] - OpenAI API key
|
|
* @param {string|null} [params.streamId] - Stream ID for resumable mode
|
|
* @param {number} [params.jobCreatedAt] - The generation epoch that owns emitted tool events
|
|
* @param {boolean} [params.definitionsOnly=true] - When true, returns only serializable
|
|
* tool definitions without creating full tool instances. Use for event-driven mode
|
|
* where tools are loaded on-demand during execution.
|
|
*/
|
|
async function loadAgentTools({
|
|
req,
|
|
res,
|
|
agent,
|
|
signal,
|
|
tool_resources,
|
|
openAIApiKey,
|
|
streamId = null,
|
|
jobCreatedAt,
|
|
definitionsOnly = true,
|
|
}) {
|
|
if (definitionsOnly) {
|
|
return loadToolDefinitionsWrapper({
|
|
req,
|
|
res,
|
|
agent,
|
|
streamId,
|
|
jobCreatedAt,
|
|
tool_resources,
|
|
});
|
|
}
|
|
|
|
if (!agent.tools || agent.tools.length === 0) {
|
|
return { toolDefinitions: [] };
|
|
} else if (
|
|
agent.tools &&
|
|
agent.tools.length === 1 &&
|
|
/** Legacy handling for `ocr` as may still exist in existing Agents */
|
|
(agent.tools[0] === AgentCapabilities.context || agent.tools[0] === AgentCapabilities.ocr)
|
|
) {
|
|
return { toolDefinitions: [] };
|
|
}
|
|
|
|
const appConfig = req.config;
|
|
const enabledCapabilities = await resolveAgentCapabilities(req, appConfig, agent.id);
|
|
const checkCapability = (capability) => {
|
|
const enabled = enabledCapabilities.has(capability);
|
|
if (!enabled) {
|
|
const isToolCapability = [
|
|
AgentCapabilities.file_search,
|
|
AgentCapabilities.execute_code,
|
|
AgentCapabilities.web_search,
|
|
].includes(capability);
|
|
const suffix = isToolCapability ? ' despite configured tool.' : '.';
|
|
logger.warn(
|
|
`Capability "${capability}" disabled${suffix} User: ${req.user.id} | Agent: ${agent.id}`,
|
|
);
|
|
}
|
|
return enabled;
|
|
};
|
|
const areToolsEnabled = checkCapability(AgentCapabilities.tools);
|
|
const actionsEnabled = checkCapability(AgentCapabilities.actions);
|
|
const hasMCPTools = agent.tools?.some((tool) => tool?.includes(Constants.mcp_delimiter));
|
|
const mcpPermissionContext = createMCPPermissionContext(req);
|
|
const canUseMCP = hasMCPTools ? await mcpPermissionContext.canUseServers(req.user) : true;
|
|
|
|
let includesWebSearch = false;
|
|
const _agentTools = agent.tools?.filter((tool) => {
|
|
if (tool === Tools.file_search) {
|
|
return checkCapability(AgentCapabilities.file_search);
|
|
} else if (tool === Tools.execute_code) {
|
|
return checkCapability(AgentCapabilities.execute_code);
|
|
} else if (tool === Tools.web_search) {
|
|
includesWebSearch = checkCapability(AgentCapabilities.web_search);
|
|
return includesWebSearch;
|
|
} else if (tool === Tools.memory) {
|
|
return checkCapability(AgentCapabilities.memory);
|
|
} else if (tool === ASK_USER_QUESTION_TOOL_NAME) {
|
|
return checkCapability(AgentCapabilities.ask_user_question);
|
|
} else if (isActionTool(tool)) {
|
|
return actionsEnabled;
|
|
} else if (tool?.includes(Constants.mcp_delimiter)) {
|
|
return areToolsEnabled && canUseMCP;
|
|
} else if (!areToolsEnabled) {
|
|
return false;
|
|
}
|
|
return true;
|
|
});
|
|
|
|
if (!_agentTools || _agentTools.length === 0) {
|
|
return {};
|
|
}
|
|
/** @type {ReturnType<typeof createOnSearchResults>} */
|
|
let webSearchCallbacks;
|
|
if (includesWebSearch) {
|
|
webSearchCallbacks = createOnSearchResults(res, streamId, jobCreatedAt);
|
|
}
|
|
|
|
/** Resolved once and threaded into `loadTools` so the request app config is read once. */
|
|
const mcpServerContext = _agentTools?.some((t) => t.includes(Constants.mcp_delimiter))
|
|
? await resolveMcpServerContext(req)
|
|
: undefined;
|
|
|
|
/** @type {Record<string, Record<string, string>>} */
|
|
let userMCPAuthMap;
|
|
if (mcpServerContext) {
|
|
userMCPAuthMap = await getUserMCPAuthMap({
|
|
tools: _agentTools,
|
|
userId: req.user.id,
|
|
serverNames: mcpServerContext.serverNames,
|
|
findPluginAuthsByKeys,
|
|
});
|
|
}
|
|
|
|
const { loadedTools, toolContextMap, dynamicToolContextMap, primedCodeFiles } = await loadTools({
|
|
agent,
|
|
signal,
|
|
userMCPAuthMap,
|
|
functions: true,
|
|
user: req.user.id,
|
|
tools: _agentTools,
|
|
options: {
|
|
req,
|
|
res,
|
|
mcpServerContext,
|
|
jobCreatedAt,
|
|
openAIApiKey,
|
|
tool_resources,
|
|
processFileURL,
|
|
uploadImageBuffer,
|
|
returnMetadata: true,
|
|
mcpPermissionContext,
|
|
requestScopedConnections: getMCPRequestContext(req, res),
|
|
[Tools.web_search]: webSearchCallbacks,
|
|
},
|
|
webSearch: appConfig.webSearch,
|
|
fileStrategy: appConfig.fileStrategy,
|
|
imageOutputType: appConfig.imageOutputType,
|
|
});
|
|
|
|
/** Build tool registry from MCP tools and create PTC/tool search tools if configured */
|
|
const deferredToolsEnabled = checkCapability(AgentCapabilities.deferred_tools);
|
|
const programmaticToolsEnabled = enabledCapabilities.has(AgentCapabilities.programmatic_tools);
|
|
const codeExecutionEnabled =
|
|
agent.tools?.includes(Tools.execute_code) === true &&
|
|
enabledCapabilities.has(AgentCapabilities.execute_code);
|
|
const { toolRegistry, toolDefinitions, additionalTools, hasDeferredTools } =
|
|
await buildToolClassification({
|
|
loadedTools,
|
|
userId: req.user.id,
|
|
agentId: agent.id,
|
|
provider: agent.provider,
|
|
agentToolOptions: agent.tool_options,
|
|
deferredToolsEnabled,
|
|
programmaticToolsEnabled,
|
|
codeExecutionEnabled,
|
|
authHeaders: () => getCodeApiAuthHeaders(req),
|
|
});
|
|
|
|
const agentTools = [];
|
|
for (let i = 0; i < loadedTools.length; i++) {
|
|
const tool = loadedTools[i];
|
|
if (tool.name && (tool.name === Tools.execute_code || tool.name === Tools.file_search)) {
|
|
agentTools.push(tool);
|
|
continue;
|
|
}
|
|
|
|
if (!areToolsEnabled) {
|
|
continue;
|
|
}
|
|
|
|
if (tool.mcp === true) {
|
|
agentTools.push(tool);
|
|
continue;
|
|
}
|
|
|
|
if (tool instanceof DynamicStructuredTool) {
|
|
agentTools.push(tool);
|
|
continue;
|
|
}
|
|
|
|
const toolDefinition = {
|
|
name: tool.name,
|
|
schema: tool.schema,
|
|
description: tool.description,
|
|
};
|
|
|
|
if (imageGenTools.has(tool.name)) {
|
|
toolDefinition.responseFormat = 'content_and_artifact';
|
|
}
|
|
|
|
const toolInstance = toolFn(async (...args) => {
|
|
return tool['_call'](...args);
|
|
}, toolDefinition);
|
|
|
|
agentTools.push(toolInstance);
|
|
}
|
|
|
|
const ToolMap = loadedTools.reduce((map, tool) => {
|
|
map[tool.name] = tool;
|
|
return map;
|
|
}, {});
|
|
|
|
agentTools.push(...additionalTools);
|
|
|
|
const hasActionTools = _agentTools.some((t) => isActionTool(t));
|
|
if (!hasActionTools) {
|
|
return {
|
|
toolRegistry,
|
|
requestScopedConnections: getMCPRequestContext(req, res),
|
|
userMCPAuthMap,
|
|
toolContextMap,
|
|
dynamicToolContextMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
tools: agentTools,
|
|
primedCodeFiles,
|
|
};
|
|
}
|
|
|
|
const actionSets = (await loadActionSets({ agent_id: agent.id })) ?? [];
|
|
if (actionSets.length === 0) {
|
|
if (_agentTools.length > 0 && agentTools.length === 0) {
|
|
logger.warn(`No tools found for the specified tool calls: ${_agentTools.join(', ')}`);
|
|
}
|
|
return {
|
|
toolRegistry,
|
|
requestScopedConnections: getMCPRequestContext(req, res),
|
|
userMCPAuthMap,
|
|
toolContextMap,
|
|
dynamicToolContextMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
tools: agentTools,
|
|
primedCodeFiles,
|
|
};
|
|
}
|
|
|
|
// See registerActionTools for the key-shape rationale.
|
|
const toolToAction = new Map();
|
|
|
|
for (const action of actionSets) {
|
|
const domain = await domainParser(action.metadata.domain, true);
|
|
const normalizedDomain = domain.replace(domainSeparatorRegex, '_');
|
|
const legacyDomain = legacyDomainEncode(action.metadata.domain);
|
|
const legacyNormalized = legacyDomain.replace(domainSeparatorRegex, '_');
|
|
|
|
const isDomainAllowed = await isActionDomainAllowed(
|
|
action.metadata.domain,
|
|
appConfig?.actions?.allowedDomains,
|
|
appConfig?.actions?.allowedAddresses,
|
|
);
|
|
if (!isDomainAllowed) {
|
|
continue;
|
|
}
|
|
|
|
// Validate and parse OpenAPI spec once per action set
|
|
const validationResult = validateAndParseOpenAPISpec(action.metadata.raw_spec);
|
|
if (!validationResult.spec || !validationResult.serverUrl) {
|
|
continue;
|
|
}
|
|
|
|
// SECURITY: Validate the domain from the spec matches the stored domain
|
|
// This is defense-in-depth to prevent any stored malicious actions
|
|
const domainValidation = validateActionDomain(
|
|
action.metadata.domain,
|
|
validationResult.serverUrl,
|
|
);
|
|
if (!domainValidation.isValid) {
|
|
logger.error(`Domain mismatch in stored action: ${domainValidation.message}`, {
|
|
userId: req.user.id,
|
|
agent_id: agent.id,
|
|
action_id: action.action_id,
|
|
});
|
|
continue; // Skip this action rather than failing the entire request
|
|
}
|
|
|
|
const encrypted = {
|
|
oauth_client_id: action.metadata.oauth_client_id,
|
|
oauth_client_secret: action.metadata.oauth_client_secret,
|
|
};
|
|
|
|
// Decrypt metadata once per action set
|
|
const decryptedAction = { ...action };
|
|
decryptedAction.metadata = await decryptMetadata(action.metadata);
|
|
|
|
// Process the OpenAPI spec once per action set
|
|
const { requestBuilders, functionSignatures, zodSchemas } = openapiToFunction(
|
|
validationResult.spec,
|
|
true,
|
|
);
|
|
|
|
registerActionTools({
|
|
toolToAction,
|
|
functionSignatures,
|
|
normalizedDomain,
|
|
legacyNormalized,
|
|
makeEntry: (sig) => ({
|
|
action: decryptedAction,
|
|
requestBuilder: requestBuilders[sig.name],
|
|
zodSchema: zodSchemas[sig.name],
|
|
functionSignature: sig,
|
|
encrypted,
|
|
}),
|
|
});
|
|
}
|
|
|
|
// Now map tools to the processed action sets
|
|
const ActionToolMap = {};
|
|
|
|
for (const toolName of _agentTools) {
|
|
if (ToolMap[toolName]) {
|
|
continue;
|
|
}
|
|
|
|
const entry = toolToAction.get(normalizeActionToolName(toolName));
|
|
if (!entry) {
|
|
continue;
|
|
}
|
|
|
|
const { action, encrypted, zodSchema, requestBuilder, functionSignature } = entry;
|
|
const _allowedDomains = appConfig?.actions?.allowedDomains;
|
|
const _allowedAddresses = appConfig?.actions?.allowedAddresses;
|
|
const tool = await createActionTool({
|
|
userId: req.user.id,
|
|
res,
|
|
action,
|
|
requestBuilder,
|
|
zodSchema,
|
|
encrypted,
|
|
name: toolName,
|
|
description: functionSignature.description,
|
|
streamId,
|
|
jobCreatedAt,
|
|
useSSRFProtection: !Array.isArray(_allowedDomains) || _allowedDomains.length === 0,
|
|
allowedAddresses: _allowedAddresses,
|
|
});
|
|
|
|
if (!tool) {
|
|
logger.warn(
|
|
`Invalid action: user: ${req.user.id} | agent_id: ${agent.id} | toolName: ${toolName}`,
|
|
);
|
|
throw new Error(`{"type":"${ErrorTypes.INVALID_ACTION}"}`);
|
|
}
|
|
|
|
agentTools.push(tool);
|
|
ActionToolMap[toolName] = tool;
|
|
}
|
|
|
|
if (_agentTools.length > 0 && agentTools.length === 0) {
|
|
logger.warn(`No tools found for the specified tool calls: ${_agentTools.join(', ')}`);
|
|
return {};
|
|
}
|
|
|
|
return {
|
|
toolRegistry,
|
|
requestScopedConnections: getMCPRequestContext(req, res),
|
|
toolContextMap,
|
|
dynamicToolContextMap,
|
|
userMCPAuthMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
tools: agentTools,
|
|
primedCodeFiles,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Loads tools for event-driven execution (ON_TOOL_EXECUTE handler).
|
|
* This function encapsulates all dependencies needed for tool loading,
|
|
* so callers don't need to import processFileURL, uploadImageBuffer, etc.
|
|
*
|
|
* Handles both regular tools (MCP, built-in) and action tools.
|
|
*
|
|
* @param {Object} params
|
|
* @param {ServerRequest} params.req - The request object
|
|
* @param {ServerResponse} params.res - The response object
|
|
* @param {AbortSignal} [params.signal] - Abort signal
|
|
* @param {Object} params.agent - The agent object
|
|
* @param {string[]} params.toolNames - Names of tools to load
|
|
* @param {Map} [params.toolRegistry] - Tool registry
|
|
* @param {Record<string, import('@librechat/api').LCAvailableTools>} [params.mcpAvailableTools] - Run-scoped MCP tool definitions
|
|
* @param {import('@librechat/api').RequestScopedMCPConnectionStore} [params.requestScopedConnections] - Run-scoped MCP connections
|
|
* @param {Record<string, Record<string, string>>} [params.userMCPAuthMap] - User MCP auth map
|
|
* @param {Object} [params.tool_resources] - Tool resources
|
|
* @param {string|null} [params.streamId] - Stream ID for web search callbacks
|
|
* @param {number} [params.jobCreatedAt] - The generation epoch that owns emitted tool events
|
|
* @param {boolean} [params.actionsEnabled] - Whether the actions capability is enabled
|
|
* @returns {Promise<{ loadedTools: Array, configurable: Object }>}
|
|
*/
|
|
async function loadToolsForExecution({
|
|
req,
|
|
res,
|
|
signal,
|
|
agent,
|
|
toolNames,
|
|
toolRegistry,
|
|
backgroundToolNames,
|
|
intentToolNames,
|
|
mcpAvailableTools,
|
|
requestScopedConnections,
|
|
userMCPAuthMap,
|
|
tool_resources,
|
|
streamId = null,
|
|
jobCreatedAt,
|
|
actionsEnabled,
|
|
}) {
|
|
const appConfig = req.config;
|
|
const allLoadedTools = [];
|
|
const mcpRequestScopedConnections = requestScopedConnections ?? getMCPRequestContext(req, res);
|
|
const configurable = { userMCPAuthMap, requestScopedConnections: mcpRequestScopedConnections };
|
|
/** Per-agent set of tools that received the injected `run_in_background`
|
|
* param; the event-driven executor gates background dispatch and the
|
|
* `check_background_task` poll tool on this reliable per-agent channel. */
|
|
if (backgroundToolNames?.length) {
|
|
configurable.backgroundToolNames = backgroundToolNames;
|
|
}
|
|
/** Per-agent set of tools that received the host-injected `intent` label
|
|
* param; the executor strips the arg before invocation and removes the
|
|
* param from schemas the PTC sandbox sees. */
|
|
if (intentToolNames?.length) {
|
|
configurable.intentToolNames = intentToolNames;
|
|
}
|
|
|
|
const isToolSearch = toolNames.includes(AgentConstants.TOOL_SEARCH);
|
|
const ptcToolNames = [
|
|
AgentConstants.BASH_PROGRAMMATIC_TOOL_CALLING,
|
|
AgentConstants.PROGRAMMATIC_TOOL_CALLING,
|
|
].filter((name) => toolNames.includes(name));
|
|
const isPTCRequested = ptcToolNames.length > 0;
|
|
const isBashToolRequested = toolNames.includes(AgentConstants.BASH_TOOL);
|
|
const isLegacyExecuteCodeRequested = toolNames.includes(Tools.execute_code);
|
|
const isCodeExecutionToolRequested = isBashToolRequested || isLegacyExecuteCodeRequested;
|
|
|
|
let enabledCapabilities;
|
|
if (actionsEnabled === undefined || isPTCRequested || isCodeExecutionToolRequested) {
|
|
enabledCapabilities = await resolveAgentCapabilities(req, appConfig, agent?.id);
|
|
}
|
|
if (actionsEnabled === undefined) {
|
|
actionsEnabled = enabledCapabilities.has(AgentCapabilities.actions);
|
|
}
|
|
const codeExecutionEnabled =
|
|
enabledCapabilities?.has(AgentCapabilities.execute_code) === true &&
|
|
agent?.tools?.includes(Tools.execute_code) === true;
|
|
|
|
/**
|
|
* Opt bash_tool into the hedged stateful-session description. Gated on code
|
|
* execution being enabled AND the admin `stateful_code_sessions` capability
|
|
* AND the agent's own builder opt-in; off by default. Sets prompt text only
|
|
* (the wire hint is set at run config). PTC keeps its stateless prompt in
|
|
* v1. Older @librechat/agents ignore the param.
|
|
*/
|
|
const statefulCodeSessions =
|
|
codeExecutionEnabled &&
|
|
enabledCapabilities?.has(AgentCapabilities.stateful_code_sessions) === true &&
|
|
agent?.stateful_code_sessions === true;
|
|
|
|
const isPTC =
|
|
isPTCRequested &&
|
|
enabledCapabilities.has(AgentCapabilities.programmatic_tools) &&
|
|
codeExecutionEnabled;
|
|
|
|
logger.debug(
|
|
`[loadToolsForExecution] isToolSearch: ${isToolSearch}, toolRegistry: ${toolRegistry?.size ?? 'undefined'}`,
|
|
);
|
|
|
|
if (isToolSearch && toolRegistry) {
|
|
const toolSearchTool = createToolSearch({
|
|
mode: 'local',
|
|
toolRegistry,
|
|
});
|
|
allLoadedTools.push(toolSearchTool);
|
|
configurable.toolRegistry = toolRegistry;
|
|
}
|
|
|
|
if (isPTC && toolRegistry) {
|
|
configurable.toolRegistry = toolRegistry;
|
|
try {
|
|
/**
|
|
* LibreChat threads per-request Code API auth through the agents
|
|
* library so PTC calls share the same managed auth context.
|
|
*/
|
|
for (const name of ptcToolNames) {
|
|
const ptcTool = createBashProgrammaticToolCallingTool({
|
|
authHeaders: () => getCodeApiAuthHeaders(req),
|
|
});
|
|
ptcTool.name = name;
|
|
allLoadedTools.push(ptcTool);
|
|
}
|
|
} catch (error) {
|
|
logger.error('[loadToolsForExecution] Error creating PTC tool:', error);
|
|
}
|
|
}
|
|
|
|
const isBashTool =
|
|
isBashToolRequested &&
|
|
codeExecutionEnabled &&
|
|
toolRegistry?.has(AgentConstants.BASH_TOOL) === true;
|
|
if (isBashToolRequested && !isBashTool) {
|
|
logger.warn(
|
|
`[loadToolsForExecution] Skipping unregistered or unauthorized ${AgentConstants.BASH_TOOL}. ` +
|
|
`User: ${req.user.id} | Agent: ${agent?.id ?? 'unknown'}`,
|
|
);
|
|
}
|
|
if (isBashTool) {
|
|
try {
|
|
const bashTool = createBashExecutionTool({
|
|
authHeaders: () => getCodeApiAuthHeaders(req),
|
|
statefulSessions: statefulCodeSessions,
|
|
});
|
|
allLoadedTools.push(bashTool);
|
|
} catch (error) {
|
|
logger.error('[loadToolsForExecution] Failed to create bash_tool', error);
|
|
}
|
|
}
|
|
|
|
const fileAuthoringToolNames = new Set(
|
|
toolRegistry
|
|
? Array.from(toolRegistry.values())
|
|
.filter((definition) => isFileAuthoringToolDefinition(definition))
|
|
.map((definition) => definition.name)
|
|
: [],
|
|
);
|
|
const specialToolNames = new Set([
|
|
AgentConstants.TOOL_SEARCH,
|
|
AgentConstants.PROGRAMMATIC_TOOL_CALLING,
|
|
AgentConstants.BASH_PROGRAMMATIC_TOOL_CALLING,
|
|
AgentConstants.BASH_TOOL,
|
|
AgentConstants.SKILL_TOOL,
|
|
AgentConstants.READ_FILE,
|
|
...fileAuthoringToolNames,
|
|
]);
|
|
|
|
let ptcOrchestratedToolNames = [];
|
|
if (isPTC && toolRegistry) {
|
|
ptcOrchestratedToolNames = Array.from(toolRegistry.keys()).filter(
|
|
(name) => !specialToolNames.has(name),
|
|
);
|
|
}
|
|
|
|
const requestedNonSpecialToolNames = toolNames.filter((name) => !specialToolNames.has(name));
|
|
const allowedNonSpecialToolNames = requestedNonSpecialToolNames.filter((name) => {
|
|
if (name !== Tools.execute_code) {
|
|
return true;
|
|
}
|
|
const allowed = codeExecutionEnabled && toolRegistry?.has(Tools.execute_code) === true;
|
|
if (!allowed) {
|
|
logger.warn(
|
|
`[loadToolsForExecution] Skipping unregistered or unauthorized ${Tools.execute_code}. ` +
|
|
`User: ${req.user.id} | Agent: ${agent?.id ?? 'unknown'}`,
|
|
);
|
|
}
|
|
return allowed;
|
|
});
|
|
const allToolNamesToLoad = isPTC
|
|
? [...new Set([...allowedNonSpecialToolNames, ...ptcOrchestratedToolNames])]
|
|
: allowedNonSpecialToolNames;
|
|
|
|
const actionToolNames = [];
|
|
const regularToolNames = [];
|
|
for (const name of allToolNamesToLoad) {
|
|
(isActionTool(name) ? actionToolNames : regularToolNames).push(name);
|
|
}
|
|
|
|
if (regularToolNames.length > 0) {
|
|
const includesWebSearch = regularToolNames.includes(Tools.web_search);
|
|
const webSearchCallbacks = includesWebSearch
|
|
? createOnSearchResults(res, streamId, jobCreatedAt)
|
|
: undefined;
|
|
|
|
const { loadedTools } = await loadTools({
|
|
agent,
|
|
signal,
|
|
userMCPAuthMap,
|
|
functions: true,
|
|
tools: regularToolNames,
|
|
user: req.user.id,
|
|
options: {
|
|
req,
|
|
res,
|
|
jobCreatedAt,
|
|
tool_resources,
|
|
processFileURL,
|
|
uploadImageBuffer,
|
|
returnMetadata: true,
|
|
mcpAvailableTools,
|
|
requestScopedConnections: mcpRequestScopedConnections,
|
|
[Tools.web_search]: webSearchCallbacks,
|
|
},
|
|
webSearch: appConfig?.webSearch,
|
|
fileStrategy: appConfig?.fileStrategy,
|
|
imageOutputType: appConfig?.imageOutputType,
|
|
});
|
|
|
|
if (loadedTools) {
|
|
allLoadedTools.push(...loadedTools);
|
|
}
|
|
}
|
|
|
|
if (actionToolNames.length > 0 && agent && actionsEnabled) {
|
|
const actionTools = await loadActionToolsForExecution({
|
|
req,
|
|
res,
|
|
agent,
|
|
appConfig,
|
|
streamId,
|
|
jobCreatedAt,
|
|
actionToolNames,
|
|
});
|
|
allLoadedTools.push(...actionTools);
|
|
} else if (actionToolNames.length > 0 && agent && !actionsEnabled) {
|
|
logger.warn(
|
|
`[loadToolsForExecution] Capability "${AgentCapabilities.actions}" disabled. ` +
|
|
`Skipping action tool execution. User: ${req.user.id} | Agent: ${agent.id} | Tools: ${actionToolNames.join(', ')}`,
|
|
);
|
|
}
|
|
|
|
if (isPTC && allLoadedTools.length > 0) {
|
|
const ptcToolMap = new Map();
|
|
for (const tool of allLoadedTools) {
|
|
if (
|
|
tool.name &&
|
|
tool.name !== AgentConstants.PROGRAMMATIC_TOOL_CALLING &&
|
|
tool.name !== AgentConstants.BASH_PROGRAMMATIC_TOOL_CALLING
|
|
) {
|
|
ptcToolMap.set(tool.name, tool);
|
|
}
|
|
}
|
|
configurable.ptcToolMap = ptcToolMap;
|
|
}
|
|
|
|
return {
|
|
configurable,
|
|
loadedTools: allLoadedTools,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Loads action tools for event-driven execution.
|
|
* @param {Object} params
|
|
* @param {ServerRequest} params.req - The request object
|
|
* @param {ServerResponse} params.res - The response object
|
|
* @param {Object} params.agent - The agent object
|
|
* @param {Object} params.appConfig - App configuration
|
|
* @param {string|null} params.streamId - Stream ID
|
|
* @param {number} [params.jobCreatedAt] - The generation epoch that owns emitted tool events
|
|
* @param {string[]} params.actionToolNames - Action tool names to load
|
|
* @returns {Promise<Array>} Loaded action tools
|
|
*/
|
|
async function loadActionToolsForExecution({
|
|
req,
|
|
res,
|
|
agent,
|
|
appConfig,
|
|
streamId,
|
|
jobCreatedAt,
|
|
actionToolNames,
|
|
}) {
|
|
const loadedActionTools = [];
|
|
|
|
const actionSets = (await loadActionSets({ agent_id: agent.id })) ?? [];
|
|
if (actionSets.length === 0) {
|
|
return loadedActionTools;
|
|
}
|
|
|
|
// See registerActionTools for the key-shape rationale.
|
|
const toolToAction = new Map();
|
|
const allowedDomains = appConfig?.actions?.allowedDomains;
|
|
const allowedAddresses = appConfig?.actions?.allowedAddresses;
|
|
|
|
for (const action of actionSets) {
|
|
const domain = await domainParser(action.metadata.domain, true);
|
|
const normalizedDomain = domain.replace(domainSeparatorRegex, '_');
|
|
const legacyDomain = legacyDomainEncode(action.metadata.domain);
|
|
const legacyNormalized = legacyDomain.replace(domainSeparatorRegex, '_');
|
|
|
|
const isDomainAllowed = await isActionDomainAllowed(
|
|
action.metadata.domain,
|
|
allowedDomains,
|
|
allowedAddresses,
|
|
);
|
|
if (!isDomainAllowed) {
|
|
logger.warn(
|
|
`[Actions] Domain "${action.metadata.domain}" not in allowedDomains. ` +
|
|
`Add it to librechat.yaml actions.allowedDomains to enable this action.`,
|
|
);
|
|
continue;
|
|
}
|
|
|
|
const validationResult = validateAndParseOpenAPISpec(action.metadata.raw_spec);
|
|
if (!validationResult.spec || !validationResult.serverUrl) {
|
|
logger.warn(`[Actions] Invalid OpenAPI spec for domain: ${domain}`);
|
|
continue;
|
|
}
|
|
|
|
const domainValidation = validateActionDomain(
|
|
action.metadata.domain,
|
|
validationResult.serverUrl,
|
|
);
|
|
if (!domainValidation.isValid) {
|
|
logger.error(`Domain mismatch in stored action: ${domainValidation.message}`, {
|
|
userId: req.user.id,
|
|
agent_id: agent.id,
|
|
action_id: action.action_id,
|
|
});
|
|
continue;
|
|
}
|
|
|
|
const encrypted = {
|
|
oauth_client_id: action.metadata.oauth_client_id,
|
|
oauth_client_secret: action.metadata.oauth_client_secret,
|
|
};
|
|
|
|
const decryptedAction = { ...action };
|
|
decryptedAction.metadata = await decryptMetadata(action.metadata);
|
|
|
|
const { requestBuilders, functionSignatures, zodSchemas } = openapiToFunction(
|
|
validationResult.spec,
|
|
true,
|
|
);
|
|
|
|
registerActionTools({
|
|
toolToAction,
|
|
functionSignatures,
|
|
normalizedDomain,
|
|
legacyNormalized,
|
|
makeEntry: (sig) => ({
|
|
action: decryptedAction,
|
|
requestBuilder: requestBuilders[sig.name],
|
|
zodSchema: zodSchemas[sig.name],
|
|
functionSignature: sig,
|
|
encrypted,
|
|
}),
|
|
});
|
|
}
|
|
|
|
for (const toolName of actionToolNames) {
|
|
const entry = toolToAction.get(normalizeActionToolName(toolName));
|
|
if (!entry) {
|
|
continue;
|
|
}
|
|
|
|
const { action, encrypted, zodSchema, requestBuilder, functionSignature } = entry;
|
|
const tool = await createActionTool({
|
|
userId: req.user.id,
|
|
res,
|
|
action,
|
|
streamId,
|
|
jobCreatedAt,
|
|
zodSchema,
|
|
encrypted,
|
|
requestBuilder,
|
|
name: toolName,
|
|
description: functionSignature.description,
|
|
useSSRFProtection: !Array.isArray(allowedDomains) || allowedDomains.length === 0,
|
|
allowedAddresses,
|
|
});
|
|
|
|
if (!tool) {
|
|
logger.warn(`[Actions] Failed to create action tool: ${toolName}`);
|
|
continue;
|
|
}
|
|
|
|
loadedActionTools.push(tool);
|
|
}
|
|
|
|
return loadedActionTools;
|
|
}
|
|
|
|
module.exports = {
|
|
loadTools,
|
|
isBuiltInTool,
|
|
getToolkitKey,
|
|
loadAgentTools,
|
|
loadToolsForExecution,
|
|
processRequiredActions,
|
|
resolveAgentCapabilities,
|
|
};
|