mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-10-31 19:17:13 +00:00
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
GitNexus Index / index (push) Waiting to run
GitNexus Index / post-index (push) Blocked by required conditions
* 🧵 feat: Background Tool Calls for Agents & Model Specs Opt-in, poll-based background tool execution. The model marks an eligible tool call with `run_in_background: true`; the host executor registers a task, returns a handle immediately (so the graph turn resolves), runs the tool as a detached promise, and the model retrieves the result via a new `check_background_task` poll tool. Host-side only — no `@librechat/agents` change. - Opt-in mirrors `deferred_tools`: admin capability `run_in_background` (off by default) + per-tool `tool_options.run_in_background`. - Model specs / ephemeral agents: `TModelSpec.runInBackground` / `TEphemeralAgent.run_in_background` synthesize per-tool options; both paths converge at `initializeAgent`. - In-process task registry: scoped per user+conversation, idempotent by toolCallId (safe across resume/replay), capped, TTL-swept. - Excludes direct-path / host-special / code-session tools. Subagents and push notifications are deferred follow-ups. * 🩹 fix: Harden background tool calls (Codex review) - Reliable per-agent execution gate: thread the injected `run_in_background` tool names from `initializeAgent` through `configurable.backgroundToolNames` (`toolRegistry` only reaches the executor for PTC/tool_search), fixing the silent no-op + unstripped-arg leak for ordinary event-driven tools. - Enforce the per-tool opt-in at execution (`backgroundToolSet.has(name)`) so a non-opted-in tool can't be backgrounded via an extra arg. - Gate the `check_background_task` interception on the run actually enabling background, so a user tool sharing that name still executes. - Forward `backgroundToolsAvailable` to added-convo (multi-convo) agents. - Exclude `web_search`/`file_search` from eligibility — their results are turned into user-visible attachments/citations only by the foreground toolEndCallback. * 🩹 fix: Address Codex round 2 on background tool calls - Idempotency scoped to run+turn: provider tool-call ids repeat across turns (e.g. `call_0`), so key the dedupe map by `runId::toolCallId` and sweep orphaned mappings — a later turn no longer collides with a retained task. - Artifacts preserved: a backgrounded tool's artifact is processed through the same `toolEndCallback` as the foreground path (images/files/citations no longer silently dropped), best-effort/guarded. - Forward the `run_in_background` capability to connected-agent discovery and subagent `processAgent` init, so a child agent's own event-driven tools work the same as when it runs as primary. - Strip the injected flag on foreground calls of background-capable tools (the model may emit it as `false`) so strict MCP/action schemas don't reject. - `check_background_task` list path returns metadata only (result_available / result_chars), never full results — prevents context overflow; the full result is returned only when a specific id is requested. * 🩹 fix: Address Codex round 3 on background tool calls - Exclude background-capable tools from eager execution (run.ts): a speculative eager dispatch of a `run_in_background` call could launch the detached task with partial/stale args, and that side effect can't be canceled. - Reserve the `check_background_task` name: overwrite a colliding user/MCP tool with the host poll schema (with a warning) so the advertised schema matches the executor's interception instead of hijacking a mismatched tool. - Don't inject background schemas into pure subagents (spawn-tool child graphs) whose tools don't reach the host interceptor; keep it for primary/added/ connected agents. Subagent background is the durable follow-up. - Thread `backgroundToolsAvailable` + `backgroundToolNames` through the OpenAI-compatible and Responses agent routes (was chat-only), so the same agent/model spec behaves consistently across surfaces. - Exclude image-generation built-ins (dalle/flux/gemini_image_gen/image_gen_oai/ image_edit_oai) — artifact-first tools whose files can't reliably attach to an already-saved turn when backgrounded. * 🩹 fix: Address Codex round 4 on background tool calls - Sanitize self-spawn subagent inputs: strip `run_in_background` + the `check_background_task` def from the parent AgentInputs reused for self-spawn, so the isolated child (direct/child-graph path) doesn't advertise a background schema it can't honor. The SDK resolver keeps a provided `agentInputs` even with `self: true`. - Exclude `check_background_task` from PTC (`run_tools_with_code`) tool definitions — it's host-only and not callable from generated code. - Parse stringified JSON args before deciding background dispatch and before stripping the flag, so string-delivered `run_in_background` is honored and never leaks to strict object-schema tools. - Skip injection for tools that already declare their own `run_in_background` param (would otherwise hijack/strip it), and for non-object (string-input) schemas (would otherwise rewrite the input contract). * 🩹 fix: Address Codex round 5 on background tool calls - check_background_task now parses stringified JSON args, so providers that deliver args as a string can retrieve a specific task by id (not just list). - Include agentId in the background dedupe key (`agentId::runId::toolCallId`): two agents in the same run emitting the same provider id (e.g. `call_0`) now launch independent tasks instead of colliding. - Self-spawn sanitization also strips the background entries from the reused toolRegistry (not just toolDefinitions), so a child using tool_search/deferred loading can't rediscover the host-only run_in_background / check_background_task. * 🩹 fix: Strip run_in_background from PTC target tool schemas (Codex round 6) The PTC path already filtered out the host-only check_background_task poll tool but still exposed target tool schemas with the injected `run_in_background` param (the shared toolRegistry entries were mutated by applyBackgroundToolCalls). PTC codegen doesn't go through the host background interceptor, so it could pass the flag to an MCP/action tool (strict-schema rejection or silent foreground with no poll). Sanitize the PTC toolDefs like the self-spawn path does. * 🩹 fix: Sanitize background from explicit subagent inputs (Codex round 7) A child agent reachable as a top-level/handoff agent is initialized WITH the background capability, then reused as an explicit subagent via buildSubagentConfigs. Round 4 only sanitized the self-spawn case; this now applies the same stripBackgroundFromToolDefinitions/Registry to explicit child agentInputs when `child.backgroundToolNames` is non-empty, so an isolated child graph doesn't advertise a run_in_background / check_background_task contract it can't honor. * 🩹 fix: Reap stuck/expired background tasks (Codex round 8) - get() now sweeps before returning, so repeatedly polling a known background_task_id can't keep an expired completed task (and its retained result, up to 100k chars) alive past the one-hour completed TTL. - sweep() now reaps `running` tasks older than a 30-min running TTL, marking them errored. Previously a detached call that never settled (hung network / lost MCP connection) held a running slot forever, exhausting the per-conversation cap and rejecting every later dispatch. * 🩹 fix: Evict oldest settled tasks instead of blocking at the cap (Codex round 9) Only the running-task cap gates dispatch now. The total-tasks cap (MAX_TASKS_PER_BUCKET) bounds memory but no longer rejects new background calls: when full, it evicts the oldest settled (completed/error) tasks to make room. Previously 200 quick background calls in one conversation would block all new dispatches for up to the completed-task TTL, since polling doesn't remove settled tasks. Running is already capped, so room always frees. * 📝 docs: Frame background tool calls as within-turn (Codex P1 contract) Codex escalated the request-lifecycle findings to P1 on the grounds that the advertised "poll later" contract can't be honored for genuinely long-running calls (request-scoped MCP connections + the run abort signal are torn down at turn end). Align the model-facing contract with what the same-run implementation actually delivers: the run_in_background param, check_background_task, and the dispatch handle now instruct the model to collect the result WITHIN THE SAME TURN (backgrounded work isn't guaranteed to survive past the turn). This is within-turn parallelism; cross-turn survival of long-running calls remains the deliberate durable subagent follow-up. Copy/comment-only; no behavior change. * ♻️ refactor: Cross-turn background tool calls, leak-free Extend background tool calls from within-turn to cross-turn on a single process, since the mechanism already supports it: the run's abort signal never reaches the detached invoke (the graph forwards only configurable/ metadata to the tool-execute handler), so the floating promise keeps running past turn completion and its result stays in the in-process registry for a later turn to poll (get/list key only on user::conversation + id, never the dispatch run/turn). Guarantee no connection leak: ephemeral request-scoped MCP tools (runtime {{LIBRECHAT_BODY_*}} placeholders) capture their request-scoped store at creation and fall back to it, so config manipulation can't redirect them; their connection is torn down at request end. Tag such tools in createToolInstance and run them in the foreground instead of backgrounding them. Pooled/app-level MCP and structured tools are unaffected and survive cross-turn via their managed pools. Reword the model-facing contract (run_in_background, check_background_task, handle message, fileoverview) from within-turn to cross-turn on this server (not across restart/replica, which stays the durable follow-up). Tests: cross-turn poll retrieval; ephemeral MCP tool runs foreground. * 🐛 fix: Guard ephemeral MCP tag against a null server config createToolInstance can be reached with a null/stale capturedServerConfig (cached availableTools + getServerConfig returns null, as several MCP unit tests construct tools). The new unconditional requiresEphemeralUserConnection call then dereferenced config.source and threw during tool construction (CI: Tests api shard 2/3). Guard with the same serverConfig ? ... : false pattern the other callers use; a missing config is not request-scoped. * 🎨 fix: Deliver backgrounded tool artifacts on the poll turn A slow backgrounded MCP/action tool resolves after its dispatch turn is finalized: createToolEndCallback only appends to that turn's artifactPromises (already awaited) and writes to a closed stream, so the artifact (file/citation/ UI resource) was silently dropped — check_background_task recorded only the hasArtifact boolean. The cross-turn contract made this the common case. Hold the artifact on the task and deliver it through the LIVE poll turn's toolEndCallback the first time check_background_task collects that id (once, then cleared to free memory), attributed to the original tool. Same-turn and cross-turn now share this path since the model must poll to collect any result. Tests: registry claim-once; artifact delivered on poll not dispatch, idempotent. * ✨ feat: Agent-builder toggle for background tool calls + cap tool descriptions Add a per-MCP-tool "run in background" toggle in the agent builder, mirroring the programmatic/deferred pattern: gated on the admin `run_in_background` capability via useAgentCapabilities, read/written on tool_options[id] .run_in_background through useMCPToolOptions (per-tool + bulk mark-all), and rendered as a Zap toggle in MCPToolItem and McpSection with new locale keys. Also cap the section tool/server descriptions (McpSection, ToolSection, SkillSection) with max-h-40 overflow-y-auto so a long description scrolls instead of overflowing the dialog, matching MCPToolItem's existing cap. Tests: MCPToolItem renders/toggles the background button only when enabled. * 🧪 fix: Mock new background hook functions in McpSection spec * 🎨 fix: Restore background artifact when poll-turn delivery fails * 🛡️ fix: Harden background tool call edges from review findings - Error immediately (matching foreground) when a background-requested tool failed to load, instead of returning a success handle for a dead task - Exclude ephemeral request-scoped MCP tools at injection time so the model never sees a run_in_background param the executor would silently downgrade; flip the execute-time tag to fail closed on a missing server config - Source image-tool background exclusions from the shared imageGenTools set (adds missing stable-diffusion, an artifact-first live tool) instead of a hand-copied list - Add check_background_task to the eager-execution exclusion list: artifact collection is a one-shot claim that must not fire from a speculative snapshot the SDK may discard - Strip an imitated run_in_background arg on tools the executing agent never opted in (multi-agent history bleed), unless the tool's own schema declares the parameter - Truncate oversized stored results with an explicit marker via the shared truncateMiddle (moved to utils/text) instead of a silent slice - Document the at-most-once artifact delivery semantics honestly (the callback's downstream persistence is fire-and-forget, as in foreground) * ♻️ refactor: Deduplicate background tool-call plumbing and tighten types - Use the SDK's JsonSchemaType instead of a local duplicate; drop all as-unknown casts and type the poll-tool serializer explicitly - Drop derivable BackgroundTask state (progress, hasArtifact) and the dead `enabled` param/return on applyBackgroundToolCalls (guarded at the call site), which also skips the defs pass when nothing opted in - Fold the enable expression into synthesizeBackgroundToolOptions so the three load/added call sites can't drift - Throttle the registry's all-buckets sweep and always sweep the accessed bucket, so a hot poll loop is no longer O(total tasks server-wide); bound retained artifact memory with a size cap - Single-pass stripBackgroundFromToolDefinitions; pass metadata through to the poll-turn callback instead of a no-op reconstruction - Collapse the client's copy-pasted boolean option families into a keyed factory (also removes the shared-object mutation in the bulk toggles) and the six toggle-button copies into one OptionToggle component * 🧪 test: e2e coverage for cross-turn background tool calls Proves the full contract through the real pipeline (mock harness): an agent opts an MCP tool in via tool_options.run_in_background, the model dispatches it detached and receives the synthetic handle while the tool is still running (status=running in the rendered ack — the non-blocking guarantee without timing assertions), the tool completes after its turn finalized, and a later user turn recovers the task id from replayed history, polls check_background_task, and renders the collected result. - fake-mcp-server: slow_echo fixture tool (delayed echo) - fake-model: E2E_BACKGROUND_DISPATCH / E2E_BACKGROUND_COLLECT markers - e2e yaml: agents capabilities = defaults + run_in_background * 🔧 fix: Close two background capability gaps from review - Thread backgroundToolsAvailable through the OpenAI-compatible service (derived from app capabilities like codeEnvAvailable/statefulSessions), so agents with tool_options.run_in_background keep the feature on that route; fold the three capability derivations into one helper - Index ephemeral MCP servers by normalizeServerName when excluding tools from background injection: tool names embed the normalized server name while mcpConfig keys the original, so exotic server names previously escaped the injection-time exclusion * 🛂 fix: Fall back to configurable user identity for background task scoping The in-repo routes merge req into the tool-execute configurable, but external hosts of the exported OpenAI-compatible service inject their own loadTools and may not — tasks would then register under an empty user id, collapsing registry isolation to conversationId alone. Resolve the scoping id from req.user.id, then configurable.user_id / user, and cover the isolation with a foreign-user not_found test. * 🧹 chore: Apply repo import sorter to PR-touched files
232 lines
8.1 KiB
JavaScript
232 lines
8.1 KiB
JavaScript
const { logger } = require('@librechat/data-schemas');
|
|
const {
|
|
ADDED_AGENT_ID,
|
|
initializeAgent,
|
|
validateAgentModel,
|
|
resolveAgentScopedSkillIds,
|
|
resolveModelSpecSkillIds,
|
|
loadAddedAgent: loadAddedAgentFn,
|
|
} = require('@librechat/api');
|
|
const { isEphemeralAgentId } = require('librechat-data-provider');
|
|
const { filterFilesByAgentAccess } = require('~/server/services/Files/permissions');
|
|
const { getMCPServerTools } = require('~/server/services/Config');
|
|
const { canAuthorSkillFiles } = require('./skillDeps');
|
|
const db = require('~/models');
|
|
|
|
const loadAddedAgent = (params) =>
|
|
loadAddedAgentFn(params, { getAgent: db.getAgent, getMCPServerTools });
|
|
|
|
/**
|
|
* Process addedConvo for parallel agent execution.
|
|
* Creates a parallel agent config from an added conversation.
|
|
*
|
|
* When an added agent has no incoming edges, it becomes a start node
|
|
* and runs in parallel with the primary agent automatically.
|
|
*
|
|
* Edge cases handled:
|
|
* - Primary agent has edges (handoffs): Added agent runs in parallel with primary,
|
|
* but doesn't participate in the primary's handoff graph
|
|
* - Primary agent has agent_ids (legacy chain): Added agent runs in parallel with primary,
|
|
* but doesn't participate in the chain
|
|
* - Primary agent has both: Added agent is independent, runs parallel from start
|
|
*
|
|
* @param {Object} params
|
|
* @param {import('express').Request} params.req
|
|
* @param {import('express').Response} params.res
|
|
* @param {Object} params.endpointOption - The endpoint option containing addedConvo
|
|
* @param {Object} params.modelsConfig - The models configuration
|
|
* @param {Function} params.logViolation - Function to log violations
|
|
* @param {Function} params.loadTools - Function to load agent tools
|
|
* @param {Array} params.requestFiles - Request files
|
|
* @param {string} params.conversationId - The conversation ID
|
|
* @param {string} [params.parentMessageId] - The parent message ID for thread filtering
|
|
* @param {Set} params.allowedProviders - Set of allowed providers
|
|
* @param {Map} params.agentConfigs - Map of agent configs to add to
|
|
* @param {string} params.primaryAgentId - The primary agent ID
|
|
* @param {Object|undefined} params.userMCPAuthMap - User MCP auth map to merge into
|
|
* @param {Array} [params.accessibleSkillIds] - Full VIEW-accessible skill IDs for the user
|
|
* @param {Array} [params.editableSkillIds] - Full EDIT-accessible skill IDs for the user
|
|
* @param {boolean} [params.skillsCapabilityEnabled] - Whether endpoint Skills are enabled
|
|
* @param {boolean} [params.ephemeralSkillsToggle] - Per-request ephemeral Skills badge state
|
|
* @param {boolean} [params.skillCreateAllowed] - Whether the user can create Skills
|
|
* @param {Record<string, boolean>} [params.skillStates] - Per-user Skill active overrides
|
|
* @param {boolean} [params.defaultActiveOnShare] - Default active state for shared Skills
|
|
* @param {boolean} [params.codeEnvAvailable] - `execute_code` capability flag;
|
|
* forwarded verbatim to the added agent's `initializeAgent`. @see
|
|
* InitializeAgentParams.codeEnvAvailable for full semantics.
|
|
* @param {boolean} [params.statefulSessionsAvailable] - `stateful_code_sessions`
|
|
* capability flag; forwarded verbatim alongside `codeEnvAvailable`.
|
|
* @returns {Promise<{userMCPAuthMap: Object|undefined}>} The updated userMCPAuthMap
|
|
*/
|
|
const processAddedConvo = async ({
|
|
req,
|
|
res,
|
|
endpointOption,
|
|
modelsConfig,
|
|
logViolation,
|
|
loadTools,
|
|
requestFiles,
|
|
conversationId,
|
|
parentMessageId,
|
|
allowedProviders,
|
|
agentConfigs,
|
|
primaryAgentId,
|
|
primaryAgent,
|
|
userMCPAuthMap,
|
|
accessibleSkillIds = [],
|
|
editableSkillIds = [],
|
|
skillsCapabilityEnabled = false,
|
|
ephemeralSkillsToggle = false,
|
|
skillCreateAllowed = false,
|
|
skillStates,
|
|
defaultActiveOnShare,
|
|
codeEnvAvailable,
|
|
backgroundToolsAvailable,
|
|
statefulSessionsAvailable,
|
|
memoryAvailable,
|
|
}) => {
|
|
const addedConvo = endpointOption.addedConvo;
|
|
if (addedConvo == null) {
|
|
return { userMCPAuthMap };
|
|
}
|
|
|
|
logger.debug('[processAddedConvo] Processing added conversation', {
|
|
model: addedConvo.model,
|
|
agentId: addedConvo.agent_id,
|
|
endpoint: addedConvo.endpoint,
|
|
});
|
|
|
|
try {
|
|
const addedAgent = await loadAddedAgent({ req, conversation: addedConvo, primaryAgent });
|
|
if (!addedAgent) {
|
|
return { userMCPAuthMap };
|
|
}
|
|
|
|
const addedValidation = await validateAgentModel({
|
|
req,
|
|
res,
|
|
modelsConfig,
|
|
logViolation,
|
|
agent: addedAgent,
|
|
});
|
|
|
|
if (!addedValidation.isValid) {
|
|
logger.warn(
|
|
`[processAddedConvo] Added agent validation failed: ${addedValidation.error?.message}`,
|
|
);
|
|
return { userMCPAuthMap };
|
|
}
|
|
|
|
const selectedModelSpec =
|
|
addedConvo.spec && Array.isArray(req.config?.modelSpecs?.list)
|
|
? req.config.modelSpecs.list.find((modelSpec) => modelSpec.name === addedConvo.spec)
|
|
: null;
|
|
|
|
if (
|
|
addedAgent &&
|
|
isEphemeralAgentId(addedAgent.id) &&
|
|
selectedModelSpec &&
|
|
Object.hasOwn(selectedModelSpec, 'skills')
|
|
) {
|
|
if (selectedModelSpec.skills === true) {
|
|
addedAgent.skills_enabled = true;
|
|
delete addedAgent.skills;
|
|
} else if (selectedModelSpec.skills === false) {
|
|
addedAgent.skills_enabled = false;
|
|
addedAgent.skills = [];
|
|
} else if (Array.isArray(selectedModelSpec.skills)) {
|
|
const resolvedSkillIds = await resolveModelSpecSkillIds({
|
|
names: selectedModelSpec.skills,
|
|
accessibleSkillIds,
|
|
getSkillByName: db.getSkillByName,
|
|
});
|
|
addedAgent.skills_enabled = true;
|
|
addedAgent.skills = resolvedSkillIds.map((id) => id.toString());
|
|
}
|
|
}
|
|
|
|
const scopedSkillIds = resolveAgentScopedSkillIds({
|
|
agent: addedAgent,
|
|
accessibleSkillIds,
|
|
skillsCapabilityEnabled,
|
|
ephemeralSkillsToggle,
|
|
});
|
|
const scopedEditableSkillIds = resolveAgentScopedSkillIds({
|
|
agent: addedAgent,
|
|
accessibleSkillIds: editableSkillIds,
|
|
skillsCapabilityEnabled,
|
|
ephemeralSkillsToggle,
|
|
});
|
|
|
|
const addedConfig = await initializeAgent(
|
|
{
|
|
req,
|
|
res,
|
|
loadTools,
|
|
requestFiles,
|
|
conversationId,
|
|
parentMessageId,
|
|
agent: addedAgent,
|
|
endpointOption,
|
|
allowedProviders,
|
|
accessibleSkillIds: scopedSkillIds,
|
|
skillAuthoringAvailable: canAuthorSkillFiles({
|
|
agent: addedAgent,
|
|
scopedEditableSkillIds,
|
|
skillCreateAllowed,
|
|
skillsCapabilityEnabled,
|
|
ephemeralSkillsToggle,
|
|
}),
|
|
codeEnvAvailable,
|
|
backgroundToolsAvailable,
|
|
statefulSessionsAvailable,
|
|
memoryAvailable,
|
|
skillStates,
|
|
defaultActiveOnShare,
|
|
},
|
|
{
|
|
getFiles: db.getFiles,
|
|
getUserKey: db.getUserKey,
|
|
getMessages: db.getMessages,
|
|
getConvoFiles: db.getConvoFiles,
|
|
updateFilesUsage: db.updateFilesUsage,
|
|
getUserCodeFiles: db.getUserCodeFiles,
|
|
getUserKeyValues: db.getUserKeyValues,
|
|
getToolFilesByIds: db.getToolFilesByIds,
|
|
getCodeGeneratedFiles: db.getCodeGeneratedFiles,
|
|
filterFilesByAgentAccess,
|
|
listSkillsByAccess: db.listSkillsByAccess,
|
|
listAlwaysApplySkills: db.listAlwaysApplySkills,
|
|
getSkillByName: db.getSkillByName,
|
|
},
|
|
);
|
|
|
|
if (userMCPAuthMap != null) {
|
|
Object.assign(userMCPAuthMap, addedConfig.userMCPAuthMap ?? {});
|
|
} else {
|
|
userMCPAuthMap = addedConfig.userMCPAuthMap;
|
|
}
|
|
|
|
const addedAgentId = addedConfig.id || ADDED_AGENT_ID;
|
|
agentConfigs.set(addedAgentId, addedConfig);
|
|
|
|
// No edges needed - agent without incoming edges becomes a start node
|
|
// and runs in parallel with the primary agent automatically.
|
|
// This is independent of any edges/agent_ids the primary agent has.
|
|
|
|
logger.debug(
|
|
`[processAddedConvo] Added parallel agent: ${addedAgentId} (primary: ${primaryAgentId}, ` +
|
|
`primary has edges: ${!!endpointOption.edges}, primary has agent_ids: ${!!endpointOption.agent_ids})`,
|
|
);
|
|
|
|
return { userMCPAuthMap };
|
|
} catch (err) {
|
|
logger.error('[processAddedConvo] Error processing addedConvo for parallel agent', err);
|
|
return { userMCPAuthMap };
|
|
}
|
|
};
|
|
|
|
module.exports = {
|
|
processAddedConvo,
|
|
ADDED_AGENT_ID,
|
|
};
|