mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-08-29 13:31:29 +00:00
* 🛠️ feat: Add registerCodeExecutionTools helper Idempotently registers `bash_tool` + `read_file` in the run's tool registry and tool-definition list via a registry `.has()` dedupe. Sets up the single code-execution tool path shared by: - `initializeAgent` (when an agent has `execute_code` in its tools and the capability is enabled for the run) - `injectSkillCatalog` (when skills are active; unconditional read_file, bash_tool follows `codeEnvAvailable`) Both callers reach the helper in the same initialization sequence, so the second call becomes a no-op and exactly one copy of each tool reaches the LLM — no more double registration for agents that combine `execute_code` capability with active skills. Unit-tested on a fresh run, idempotence (second call, overlap with prior tooldefs, partial overlap), and the no-registry variant. * 🔀 refactor: Route injectSkillCatalog bash_tool + read_file through registerCodeExecutionTools The `skill` tool is still registered inline (it's skill-path-specific), but `bash_tool` + `read_file` now flow through the shared idempotent helper so a prior registration from the execute_code path doesn't produce a duplicate copy later in the same run. Behavior preserved: - `read_file` always registers when any active skill is in scope — manually-primed `disable-model-invocation: true` skills still need it to load `references/*` from storage. - `bash_tool` follows `codeEnvAvailable` exactly as before. Adds a test pinning the cross-call dedupe: when `injectSkillCatalog` runs AFTER `registerCodeExecutionTools` has already seeded the registry + tool definitions with bash_tool/read_file, the resulting `toolDefinitions` still contains exactly one copy of each. * 🪄 feat: Expand `execute_code` tool name into bash_tool + read_file at initialize-time When an agent's `tools` include `execute_code` and the `execute_code` capability is enabled for the run, `initializeAgent` now registers `bash_tool` + `read_file` via `registerCodeExecutionTools` before `injectSkillCatalog`. The legacy `execute_code` tool definition is no longer handed to the LLM — `execute_code` remains on the agent document as a capability-trigger marker, but the runtime expands it into the skill-flavored tool pair. Call ordering matters: the `execute_code` registration runs BEFORE `injectSkillCatalog`, so the skill path's own `registerCodeExecutionTools` call inside `injectSkillCatalog` becomes a no-op via the registry's `.has()` check. Exactly one copy of each tool reaches the LLM whether the agent has: - only `execute_code` (legacy path) - only skills - both No data migration needed — `agent.tools: ['execute_code']` stays in the DB unchanged; the expansion is a runtime operation. Three tests cover the matrix: execute_code + capability on → bash_tool + read_file registered; execute_code + capability off → neither registered; no execute_code + capability on → neither registered. * 🗑️ refactor: Drop CodeExecutionToolDefinition from the builtin registry Removes the legacy `execute_code` entry from `agentToolDefinitions` and the corresponding import. With the initialize-time expansion in place, nothing consults `getToolDefinition('execute_code')` for a tool schema any more — the capability gate still filters on the string `execute_code`, but the actual tool definitions the LLM sees come from `registerCodeExecutionTools` (i.e. `bash_tool` + `read_file`). `loadToolDefinitions` in `packages/api/src/tools/definitions.ts` silently drops `execute_code` when it no longer resolves in the registry — that's the expected path and is now covered by an updated test. No caller of `getToolDefinition('execute_code')` expects a non-undefined result after this change. * 🔌 refactor: Read CODE_API_KEY from env for primeCodeFiles + PTC Finishes the Phase 4 server-env-keyed rollout on the two remaining `loadAuthValues({ authFields: [EnvVar.CODE_API_KEY] })` sites in `ToolService.js`: - `primeCodeFiles` (user-attached file priming on execute_code agents) - Programmatic Tool Calling (`createProgrammaticToolCallingTool`) Both now read `process.env[EnvVar.CODE_API_KEY]` directly, matching `bash_tool`'s pattern. The per-user plugin-auth path is no longer consulted for code-env credentials anywhere in the hot path — the agents library owns the actual tool-call execution and also reads the env var internally. Priming still fires for existing user-file workflows so the legacy `toolContextMap[execute_code]` hint ("files available at /mnt/data/...") stays in the prompt; only the key lookup changed. * 🔧 fix: Type the pre-seeded dedupe-test tools as LCTool CI TypeScript type checks caught `{ parameters: {} }` in the new cross-call dedupe test: `LCTool.parameters` is a `JsonSchemaType`, not `{}`. Use `{ type: 'object', properties: {} }` and type the local registry Map through the parameter-derived shape so the pre-seeded values match what `toolRegistry.set` expects. * 🛡️ fix: Run execute_code expansion before GOOGLE_TOOL_CONFLICT gate Codex review caught a latent regression: the original Phase 8 placement ran `registerCodeExecutionTools` after `hasAgentTools` was computed, so an execute-code-only agent on Google/Vertex with provider-specific `options.tools` populated would no longer trip `GOOGLE_TOOL_CONFLICT` — the legacy `CodeExecutionToolDefinition` used to populate `toolDefinitions` before the guard, but after dropping it from the registry, `toolDefinitions` stayed empty until my expansion ran downstream of the guard. Mixed provider + agent tools would silently flow through to the LLM. Fix moves the `execute_code` expansion to BEFORE `hasAgentTools` computation. `bash_tool` + `read_file` now contribute to the check the same way the legacy `execute_code` def did. Covered by a new test that pins the Google+execute_code+provider-tools scenario — the `rejects.toThrow(/google_tool_conflict/)` path would have silently passed on the prior placement. * 🔗 fix: Thread codeEnvAvailable through handoff sub-agents Round-2 codex review caught the other half of the execute_code expansion gap: `discoverConnectedAgents` omitted `codeEnvAvailable` from its forwarded `initializeAgent` params, so handoff sub-agents with `agent.tools: ['execute_code']` lost the `bash_tool` + `read_file` registration (pre-Phase 8 the legacy `CodeExecutionToolDefinition` would have landed in their `toolDefinitions` via the registry). - Add `codeEnvAvailable?` to `DiscoverConnectedAgentsParams` and forward it verbatim on every sub-agent `initializeAgent` call. - Update the three JS call sites that construct the primary's `codeEnvAvailable` (`services/Endpoints/agents/initialize.js`, `controllers/agents/openai.js`, `controllers/agents/responses.js`) to pass the same flag into `discoverConnectedAgents` — one authoritative source per request. - Two regression tests in `discovery.spec.ts` pin the true/false passthrough so a future refactor that drops the param-forwarding surfaces immediately. Left intentionally unchanged: `packages/api/src/agents/openai/service.ts` (public API helper with no in-repo caller). External consumers of `createAgentChatCompletion` who want code execution should pass a `codeEnvAvailable`-aware `initializeAgent` via `deps` — documenting the full public-API surface is out of scope for this Phase 8 PR. * 🔗 fix: Thread codeEnvAvailable through addedConvo + memory-agent paths Round-3 codex review caught the last two production `initializeAgent` callers missing the Phase-8 capability flag: - `api/server/services/Endpoints/agents/addedConvo.js` (multi-convo parallel agent execution). Added `codeEnvAvailable` to `processAddedConvo`'s destructured params and forwarded it into the per-added-agent `initializeAgent` call. Caller in `api/server/services/Endpoints/agents/initialize.js` passes the same `codeEnvAvailable` it computed for the primary. - `api/server/controllers/agents/client.js` (`useMemory` — memory extraction agent). Computes its own `codeEnvAvailable` from `appConfig?.endpoints?.[EModelEndpoint.agents]?.capabilities` and forwards into `initializeAgent`. Memory agents rarely list `execute_code`, but if one does, pre-Phase 8 they got the legacy `execute_code` tool registered unconditionally — the passthrough restores parity. With this, every production caller of `initializeAgent` explicitly resolves the capability: main chat flow (primary + handoff), OpenAI chat completions (primary + handoff), Responses API (primary + handoff), added convo parallel agents, and memory agents. The one remaining caller, `packages/api/src/agents/openai/service.ts::createAgentChatCompletion`, is a public API helper with no in-repo consumer (external callers must pass a capability-aware `initializeAgent` via `deps`). * 🪤 fix: Remove duplicate appConfig declaration causing TDZ ReferenceError The Responses API controller had TWO `const appConfig = req.config;` bindings inside `createResponse`: one at the top of the function (added by the Phase 4 `bash_tool` decouple) and one inside the try block (added by the polish PR #12760). Because `const` is block-scoped with a temporal dead zone, the inner redeclaration put `appConfig` in TDZ for the entire try block, so any earlier reference inside the try — notably `appConfig?.endpoints?.[EModelEndpoint.agents]?.allowedProviders` at line 348 — threw `ReferenceError: Cannot access 'appConfig' before initialization`. The error was silently swallowed by the outer try/catch, leaving `recordCollectedUsage` unreached and the six `responses.unit.spec.js` token-usage tests failing. Removing the inner redeclaration fixes the six failing tests (verified: 11/11 pass locally post-fix, 0 regressions elsewhere). The outer function-scoped binding already provides `appConfig` to every downstream reference. * 🔗 fix: Thread codeEnvAvailable through the OpenAI chat-completion public API Round-4 codex review (legitimate on the type-safety angle, even though the runtime concern was already covered): the `createAgentChatCompletion` helper defines its own narrower `InitializeAgentParams` interface locally, and the type was missing `codeEnvAvailable`. External consumers who supply a capability-aware `deps.initializeAgent` couldn't route `codeEnvAvailable` through without a type-cast workaround. - Widen the local `InitializeAgentParams` interface to include `codeEnvAvailable?: boolean` (matches the real `packages/api/src/agents/initialize.ts` type). - Derive `codeEnvAvailable` inside `createAgentChatCompletion` from `deps.appConfig?.endpoints?.agents?.capabilities` (the same source the in-repo controllers use) and forward to `deps.initializeAgent`. Uses a string literal `'execute_code'` lookup so this file stays free of a `librechat-data-provider` import — keeping the dependency surface of the public helper minimal. With this, external consumers of `createAgentChatCompletion` who pass `appConfig` with the agents capabilities get `bash_tool` + `read_file` registration automatically; consumers who don't pass `appConfig` retain the existing "explicit opt-in" semantics (the flag stays `undefined`, expansion is skipped). * 🧹 chore: Review-driven polish — observability log, JSDoc DRY, test gaps, no-op allocation Addresses the comprehensive review of PR #12767: - **Finding #1** (MINOR, observability): `initializeAgent` now emits a debug log when an agent lists `execute_code` in its tools but the runtime gate is off (`params.codeEnvAvailable` !== true). The event-driven `loadToolDefinitionsWrapper` path doesn't log capability-disabled warnings, so without this the tool silently vanishes from the LLM's definitions with zero trace. Operators debugging "why isn't code interpreter working?" now get a signal at the initialize layer. - **Finding #5** (NIT, allocation): `registerCodeExecutionTools` now returns the input `toolDefinitions` array by reference on the no-op path (both tools already registered by a prior caller in the same run) instead of allocating a fresh spread array every time. The common dual-call scenario — `initializeAgent` then `injectSkillCatalog` — saves one O(n) copy per request. - **Finding #4** (NIT, DRY): Collapsed the duplicated 6-line JSDoc comment in `openai.js`, `responses.js`, and `addedConvo.js` into either a one-line `@see DiscoverConnectedAgentsParams.codeEnvAvailable` pointer (the two JS call sites) or a compact 3-line block referring back to the canonical source (addedConvo's @param). - **Finding #2** (MINOR, test gap): Added `api/server/services/Endpoints/agents/addedConvo.spec.js` with three cases covering `codeEnvAvailable=true`, `codeEnvAvailable=false`, and omitted (undefined) passthrough. A future refactor that drops the param from destructuring now surfaces here instead of silently regressing multi-convo parallel agents with `execute_code`. - **Finding #3** (MINOR, test gap): Added `api/server/controllers/agents/__tests__/client.memory.spec.js` pinning the capability-flag derivation that `AgentClient::useMemory` uses — six cases covering present/absent/null/undefined config shapes plus an enum-literal pin (`'execute_code'` / `'agents'`). Catches enum renames or config-path shifts that would otherwise silently strip `bash_tool` + `read_file` from memory agents. Finding #7 (jest.mock scoping, confidence 40) left as-is: the reviewer's own risk assessment noted `buildToolSet` doesn't touch the mocked exports, and restructuring a file-level `jest.mock` to `jest.doMock` + dynamic `import()` introduces more complexity than the speculative risk justifies. The existing mock is scoped to the test file and contains the same stubs the adjacent `skills.test.ts` already uses. Finding #6 (PR description commit count) addressed out-of-band via PR description update. All existing tests pass, typecheck clean, lint clean across touched files. New tests: 9 cases across 2 new spec files. * 🧽 refactor: Replace hardcoded 'execute_code' string with AgentCapabilities enum in service.ts Follow-up review (conf 55) caught that `openai/service.ts`'s Phase 8 `codeEnvAvailable` derivation used the literal `'execute_code'` while every in-repo controller uses `AgentCapabilities.execute_code` from `librechat-data-provider`. The file deliberately uses local type interfaces to keep the public API helper's type surface small, but that pattern was never a ban on single-value imports from the data provider — `packages/api` already depends on it. Importing the enum value means a future rename of `AgentCapabilities.execute_code` propagates to this file automatically, matching the in-repo controllers' behavior. Other follow-up findings left as-is per the reviewer's own verdict: - #2 (memory spec mirrors the production expression rather than calling `AgentClient::useMemory` directly): reviewer flagged as "not blocking" / "design-philosophy observation." The test file's JSDoc already explicitly documents the tradeoff and pins the enum literals to catch the most likely drift vector. Standing up `AgentClient` + all its mocks for a one-line regression guard is disproportionate. - #3 (`addedConvo.spec.js` mock signature vs. underlying `loadAddedAgent` arity): reviewer's own confidence 25 noted the mock matches the wrapper's actual call pattern in the production file. Not a real gap. - #4 was self-retracted as a false alarm. * 🗑️ refactor: Fully deprecate CODE_API_KEY — remove all LibreChat-side references The code-execution sandbox no longer authenticates via a per-run `CODE_API_KEY` (frontend or backend). Auth moved server-side into the agents library / sandbox service, so LibreChat drops every reference: **Backend plumbing:** - `api/server/services/Files/Code/crud.js`: `getCodeOutputDownloadStream`, `uploadCodeEnvFile`, `batchUploadCodeEnvFiles` no longer accept `apiKey` or send the `X-API-Key` header. - `api/server/services/Files/Code/process.js`: `processCodeOutput`, `getSessionInfo`, `primeFiles` drop the `apiKey` param throughout. - `api/server/services/ToolService.js`: stop reading `process.env[EnvVar.CODE_API_KEY]` for `primeCodeFiles` and PTC; the agents library handles auth internally. Remove the now-dead `loadAuthValues` + `EnvVar` imports. Drop the misleading "LIBRECHAT_CODE_API_KEY" hint from the bash_tool error log. - `api/server/services/Files/process.js`: remove the `loadAuthValues` call around `uploadCodeEnvFile`. - `api/server/routes/files/files.js`: code-env file download no longer fetches a per-user key. - `api/server/controllers/tools.js`: `execute_code` is no longer a tool that needs verifyToolAuth with `[EnvVar.CODE_API_KEY]` — the endpoint always reports system-authenticated so the client skips the key-entry dialog. `processCodeOutput` called without `apiKey`. - `api/server/controllers/agents/callbacks.js`: `processCodeOutput` invoked without the loadAuthValues round trip, for both LegacyHandler and Responses-API handlers. - `api/app/clients/tools/util/handleTools.js`: `createCodeExecutionTool` called with just `user_id` + files. **packages/api:** - `packages/api/src/agents/skillFiles.ts`: `PrimeSkillFilesParams`, `PrimeInvokedSkillsDeps`, `primeSkillFiles`, `primeInvokedSkills` all drop the `apiKey` param; the gate is purely `codeEnvAvailable`. - `packages/api/src/agents/handlers.ts`: `handleSkillToolCall` drops the `process.env[EnvVar.CODE_API_KEY]` read; skill-file priming is now gated solely on `codeEnvAvailable`. `ToolExecuteOptions` signatures drop apiKey from `batchUploadCodeEnvFiles` and `getSessionInfo`. - `packages/api/src/agents/skillConfigurable.ts`: JSDoc no longer references the env var. - `packages/api/src/tools/classification.ts`: PTC creation no longer gated on `loadAuthValues`; `buildToolClassification` drops the `loadAuthValues` dep entirely (no LibreChat-side callers need it for this path anymore). - `packages/api/src/tools/definitions.ts`: `LoadToolDefinitionsDeps` drops the `loadAuthValues` field. **Frontend:** - Delete `client/src/hooks/Plugins/useAuthCodeTool.ts`, `useCodeApiKeyForm.ts`, and `client/src/components/SidePanel/Agents/Code/ApiKeyDialog.tsx` — the install/revoke dialogs for CODE_API_KEY are fully dead. - `BadgeRowContext.tsx`: drop `codeApiKeyForm` from the context type and provider. `codeInterpreter` toggle treated as always authenticated (sandbox auth is server-side). - `ToolsDropdown.tsx`, `ToolDialogs.tsx`, `CodeInterpreter.tsx`, `RunCode.tsx`, `SidePanel/Agents/Code/Action.tsx` +`Form.tsx`: all API-key dialog trigger refs, "Configure code interpreter" gear buttons, and auth-verification plumbing removed. The "Code Interpreter" toggle is now a plain `AgentCapabilities.execute_code` checkbox — no key-entry gate. - `client/src/locales/en/translation.json`: drop the three `com_ui_librechat_code_api*` keys and `com_ui_add_code_interpreter_api_key`. Other locales are externally automated per CLAUDE.md. **Config:** - `.env.example`: remove the `# LIBRECHAT_CODE_API_KEY=your-key` section and its header. **Tests:** - `crud.spec.js`: assertions flipped to pin "no X-API-Key header" and "no apiKey param". - `skillFiles.spec.ts`: removed env-var save/restore; tests now pin that the batch-upload path is gated solely on `codeEnvAvailable` and that no apiKey is threaded through. - `handlers.spec.ts`: same — just the `codeEnvAvailable` gate pins remain. - `classification.spec.ts`: remove the two tests that asserted `loadAuthValues` was (not) called for PTC. - `definitions.spec.ts`: drop every `loadAuthValues: mockLoadAuthValues` entry from the deps shape. - `process.spec.js`: strip the mock of `EnvVar.CODE_API_KEY`. **Comment hygiene:** - `tools.ts`, `initialize.ts`, `registry/definitions.ts`: shortened stale comment references to "legacy `execute_code` tool" without naming the retired env var. Tests verified: 678 packages/api tests pass, 836 backend api tests pass. Typecheck clean, lint clean. Only remaining CODE_API_KEY mentions in the code are two regression-guard assertions: - `crud.spec.js`: pins "no X-API-Key header" stays absent. - `skillConfigurable.spec.ts`: pins `configurable` never grows a `codeApiKey` field. * 🧹 chore: Remove the last two CODE_API_KEY name mentions in LibreChat Follow-up to the prior full deprecation commit: two tests still named the retired identifier in their regression-guard assertions. - `packages/api/src/agents/skillConfigurable.spec.ts`: drop the "does not inject a codeApiKey key" test. The `codeApiKey` field is gone from the production configurable shape, so an absence-assertion naming it re-introduces the retired identifier in code. - `api/server/services/Files/Code/crud.spec.js`: rename the "without an X-API-Key header" case back to "should request stream response from the correct URL" and drop the `expect(headers).not.toHaveProperty('X-API-Key')` assertion. The surrounding request-shape checks (URL, timeout, responseType) still pin the behavior; the explicit header-absence line was named-after the deprecated contract. Result: `grep -rn "CODE_API_KEY\|codeApiKey\|LIBRECHAT_CODE_API_KEY"` against the LibreChat source tree returns zero hits. The only remaining `X-API-Key` strings in this repo are on unrelated OpenAPI Action + MCP server auth configurations, where the string is user-facing config, not a LibreChat-owned identifier. Tests: 677 packages/api pass (2 pre-existing summarization e2e failures unrelated); 126 api-workspace controller/service tests pass. Typecheck and lint clean. * 🎯 fix: Narrow codeEnvAvailable to per-agent (admin cap AND agent.tools) Before this commit, `codeEnvAvailable` was computed in the three JS controllers as the admin-level capability flag only (`enabledCapabilities.has(AgentCapabilities.execute_code)`) and passed through `initializeAgent` → `injectSkillCatalog` / `primeInvokedSkills` / `enrichWithSkillConfigurable` unchanged. A skills-only agent whose `tools` array didn't include `execute_code` still got `bash_tool` registered (via `injectSkillCatalog`) and skill files re-primed to the sandbox on every turn — wrong, because the agent never opted in to code execution. **Fix:** `initializeAgent` now computes the per-agent effective value once as `params.codeEnvAvailable === true && agent.tools.includes(Tools.execute_code)`, reuses the same boolean for: 1. The `execute_code` → `bash_tool + read_file` expansion gate (previously already consulted `agent.tools`; now shares the single `effectiveCodeEnvAvailable` binding). 2. The `injectSkillCatalog` call (previously got the raw admin flag). 3. The returned `InitializedAgent.codeEnvAvailable` field (new, typed as required boolean). **Controllers (initialize.js, openai.js, responses.js):** store `primaryConfig.codeEnvAvailable` in `agentToolContexts.set(primaryId, ...)`, capture `config.codeEnvAvailable` in every handoff `onAgentInitialized` callback, and read it from the per-agent ctx inside the `toolExecuteOptions.loadTools` runtime closure. The hoisted `const codeEnvAvailable = enabledCapabilities.has(...)` locals in the two OpenAI-compat controllers are gone — they were shadowing the narrowed per-agent value. **primeInvokedSkills:** `handlePrimeInvokedSkills` in `services/Endpoints/agents/initialize.js` now uses `primaryConfig.codeEnvAvailable` (per-agent, narrowed) instead of the raw admin flag. A skills-only primary agent won't re-prime historical skill files to the sandbox even when the admin enabled the capability globally. **Efficiency:** one extra `&&` in `initializeAgent`. No runtime hot-path cost — the `includes()` scan on `agent.tools` was already happening for the `execute_code` expansion gate; it's now just bound to a local. Tool execution closures read `ctx.codeEnvAvailable === true` (property access + strict equality, O(1)). **Ephemeral-agent note:** per-agent narrowing is authoritative for both persisted and ephemeral flows. The ephemeral toggle (`ephemeralAgent.execute_code`) is reconciled into `agent.tools` upstream in `packages/api/src/agents/added.ts`, so `agent.tools.includes('execute_code')` is the single source of truth by the time `initializeAgent` runs. **Tests:** two new regression tests pin the narrowing contract: - `initialize.test.ts` — four-quadrant matrix on `InitializedAgent.codeEnvAvailable` (cap on × agent asks, cap on × doesn't ask, cap off × asks, neither). Catches future refactors that drop either half of the AND. - `skills.test.ts` — `injectSkillCatalog` with `codeEnvAvailable: false` against an active skill catalog must NOT register `bash_tool` even though it still registers `read_file` + `skill`. This is the state a skills-only agent gets post-narrowing. All 191 affected packages/api tests pass + 836 backend api tests pass. Typecheck clean, lint clean. * 🧽 refactor: Comprehensive-review polish — hoist tool defs, pin verifyToolAuth contract, doc appConfig Addresses the comprehensive review of Phase 8. Findings mapped: **#1 (MINOR): `verifyToolAuth` unconditional auth for execute_code** - Added doc comment explicitly stating the deployment contract (admin capability → reachable sandbox; no per-check health probe to keep UI-gate queries O(1)). - New `api/server/controllers/__tests__/tools.verifyToolAuth.spec.js` with 4 regression tests pinning the contract: 1. `authenticated: true` + `SYSTEM_DEFINED` for execute_code. 2. 404 for unknown tool IDs. 3. `loadAuthValues` is never consulted (catches a future revert that would resurface the per-user key-entry dialog). 4. Response `message` is never `USER_PROVIDED`. **#2 (MINOR): `openai/service.ts` undocumented `appConfig` dependency** - Expanded the `ChatCompletionDependencies.appConfig` JSDoc to spell out that omitting it silently disables code execution for agents with `execute_code` in their tools. External consumers of `createAgentChatCompletion` now have the contract documented at the type boundary. **#5 (NIT): `registerCodeExecutionTools` re-allocates tool defs** - Hoisted `READ_FILE_DEF` and `BASH_TOOL_DEF` to module-level `Object.freeze`d constants. The shapes derive entirely from static `@librechat/agents` exports, so a single frozen object per tool is safe to share across every agent init. Eliminates the ~4-property allocations on every call (including the common second-call no-op path). **#6 (NIT): Verbose history-priming comment in initialize.js** - Trimmed the 16-line `handlePrimeInvokedSkills` block to a 5-line summary with `@see InitializedAgent.codeEnvAvailable` pointer. The canonical narrowing explanation lives on the type; the controller comment is just the ACL-vs-capability rationale. **Skipped:** - #3 (memory spec tests a mirror function): reviewer self-dismissed as a design tradeoff; the enum-literal pin already catches the highest-risk drift vector. - #4 (cross-repo contract for `createCodeExecutionTool`): user will explicitly install the latest `@librechat/agents` dev version once the companion PR publishes, so the version pin will be authoritative. - #7 (migration/deprecation note for self-hosters): out of scope per user direction — release notes handle this. Tests verified: 679 packages/api + 840 backend api tests pass. Typecheck + lint clean. * 🔧 chore: Update @librechat/agents version to 3.1.68-dev.1 across package-lock and package.json files This commit updates the version of the `@librechat/agents` package from `3.1.68-dev.0` to `3.1.68-dev.1` in the `package-lock.json` and relevant `package.json` files. This change ensures consistency across the project and incorporates any updates or fixes from the new version.
1481 lines
47 KiB
JavaScript
1481 lines
47 KiB
JavaScript
const { logger } = require('@librechat/data-schemas');
|
|
const { tool: toolFn, DynamicStructuredTool } = require('@langchain/core/tools');
|
|
const {
|
|
sleep,
|
|
StepTypes,
|
|
GraphEvents,
|
|
createToolSearch,
|
|
Constants: AgentConstants,
|
|
createBashExecutionTool,
|
|
createProgrammaticToolCallingTool,
|
|
} = require('@librechat/agents');
|
|
const {
|
|
sendEvent,
|
|
getToolkitKey,
|
|
getUserMCPAuthMap,
|
|
loadToolDefinitions,
|
|
GenerationJobManager,
|
|
isActionDomainAllowed,
|
|
buildWebSearchContext,
|
|
buildImageToolContext,
|
|
buildToolClassification,
|
|
buildOAuthToolCallName,
|
|
} = 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 { resolveConfigServers } = require('~/server/services/MCP');
|
|
const { recordUsage } = require('~/server/services/Threads');
|
|
const { loadTools } = require('~/app/clients/tools/util');
|
|
const { redactMessage } = require('~/config/parsers');
|
|
const { findPluginAuthsByKeys } = require('~/models');
|
|
const { getFlowStateManager } = 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,
|
|
);
|
|
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;
|
|
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,
|
|
});
|
|
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>;
|
|
* 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]);
|
|
|
|
/** 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
|
|
* @returns {Promise<{
|
|
* toolDefinitions?: import('@librechat/api').LCTool[];
|
|
* toolRegistry?: Map<string, import('@librechat/api').LCTool>;
|
|
* userMCPAuthMap?: Record<string, Record<string, string>>;
|
|
* hasDeferredTools?: boolean;
|
|
* }>}
|
|
*/
|
|
async function loadToolDefinitionsWrapper({ req, res, agent, streamId = null, 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 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 (isActionTool(tool)) {
|
|
return actionsEnabled;
|
|
}
|
|
if (!areToolsEnabled) {
|
|
return false;
|
|
}
|
|
return true;
|
|
});
|
|
|
|
if (!filteredTools || filteredTools.length === 0) {
|
|
return { toolDefinitions: [] };
|
|
}
|
|
|
|
/** @type {Record<string, Record<string, string>>} */
|
|
let userMCPAuthMap;
|
|
if (agent.tools?.some((t) => t.includes(Constants.mcp_delimiter))) {
|
|
userMCPAuthMap = await getUserMCPAuthMap({
|
|
tools: agent.tools,
|
|
userId: req.user.id,
|
|
findPluginAuthsByKeys,
|
|
});
|
|
}
|
|
|
|
const flowsCache = getLogStores(CacheKeys.FLOWS);
|
|
const flowManager = getFlowStateManager(flowsCache);
|
|
const configServers = await resolveConfigServers(req);
|
|
const pendingOAuthServers = new Set();
|
|
|
|
const createOAuthEmitter = (serverName) => {
|
|
return async (authURL) => {
|
|
const flowId = `${req.user.id}:${serverName}:${Date.now()}`;
|
|
const stepId = 'step_oauth_login_' + serverName;
|
|
const toolCall = {
|
|
id: flowId,
|
|
name: buildOAuthToolCallName(serverName),
|
|
type: 'tool_call_chunk',
|
|
};
|
|
|
|
const runStepData = {
|
|
runId: Constants.USE_PRELIM_RESPONSE_MESSAGE_ID,
|
|
id: stepId,
|
|
type: StepTypes.TOOL_CALLS,
|
|
index: 0,
|
|
stepDetails: {
|
|
type: StepTypes.TOOL_CALLS,
|
|
tool_calls: [toolCall],
|
|
},
|
|
};
|
|
|
|
const runStepDeltaData = {
|
|
id: stepId,
|
|
delta: {
|
|
type: StepTypes.TOOL_CALLS,
|
|
tool_calls: [{ ...toolCall, args: '' }],
|
|
auth: authURL,
|
|
expires_at: Date.now() + Time.TWO_MINUTES,
|
|
},
|
|
};
|
|
|
|
const runStepEvent = { event: GraphEvents.ON_RUN_STEP, data: runStepData };
|
|
const runStepDeltaEvent = { event: GraphEvents.ON_RUN_STEP_DELTA, data: runStepDeltaData };
|
|
|
|
if (streamId) {
|
|
await GenerationJobManager.emitChunk(streamId, runStepEvent);
|
|
await GenerationJobManager.emitChunk(streamId, runStepDeltaEvent);
|
|
} else if (res && !res.writableEnded) {
|
|
sendEvent(res, runStepEvent);
|
|
sendEvent(res, runStepDeltaEvent);
|
|
} else {
|
|
logger.warn(
|
|
`[Tool Definitions] Cannot emit OAuth event for ${serverName}: no streamId and res not available`,
|
|
);
|
|
}
|
|
};
|
|
};
|
|
|
|
const getOrFetchMCPServerTools = async (userId, serverName) => {
|
|
const cached = await getMCPServerTools(userId, serverName);
|
|
if (cached) {
|
|
return cached;
|
|
}
|
|
|
|
const oauthStart = async () => {
|
|
pendingOAuthServers.add(serverName);
|
|
};
|
|
|
|
const result = await reinitMCPServer({
|
|
user: req.user,
|
|
oauthStart,
|
|
flowManager,
|
|
serverName,
|
|
configServers,
|
|
userMCPAuthMap,
|
|
});
|
|
|
|
return result?.availableTools || null;
|
|
};
|
|
|
|
const getActionToolDefinitions = async (agentId, actionToolNames) => {
|
|
const actionSets = (await loadActionSets({ agent_id: agentId })) ?? [];
|
|
if (actionSets.length === 0) {
|
|
return [];
|
|
}
|
|
|
|
const definitions = [];
|
|
const allowedDomains = appConfig?.actions?.allowedDomains;
|
|
const normalizedToolNames = new Set(
|
|
actionToolNames.map((n) => n.replace(domainSeparatorRegex, '_')),
|
|
);
|
|
|
|
for (const action of actionSets) {
|
|
const domain = await domainParser(action.metadata.domain, true);
|
|
const normalizedDomain = domain.replace(domainSeparatorRegex, '_');
|
|
|
|
const legacyDomain = legacyDomainEncode(action.metadata.domain);
|
|
const legacyNormalized = legacyDomain.replace(domainSeparatorRegex, '_');
|
|
|
|
const isDomainAllowed = await isActionDomainAllowed(action.metadata.domain, allowedDomains);
|
|
if (!isDomainAllowed) {
|
|
logger.warn(
|
|
`[Actions] Domain "${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,
|
|
},
|
|
{
|
|
isBuiltInTool,
|
|
getOrFetchMCPServerTools,
|
|
getActionToolDefinitions,
|
|
},
|
|
);
|
|
|
|
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) => {
|
|
try {
|
|
const result = await reinitMCPServer({
|
|
user: req.user,
|
|
serverName,
|
|
configServers,
|
|
userMCPAuthMap,
|
|
flowManager,
|
|
returnOnOAuth: false,
|
|
oauthStart: createOAuthEmitter(serverName),
|
|
connectionTimeout: Time.TWO_MINUTES,
|
|
});
|
|
|
|
if (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: ${successfulServers.join(', ')}`,
|
|
);
|
|
const reloadResult = await loadToolDefinitions(
|
|
{
|
|
userId: req.user.id,
|
|
agentId: agent.id,
|
|
tools: filteredTools,
|
|
toolOptions: agent.tool_options,
|
|
deferredToolsEnabled,
|
|
},
|
|
{
|
|
isBuiltInTool,
|
|
getOrFetchMCPServerTools,
|
|
getActionToolDefinitions,
|
|
},
|
|
);
|
|
toolDefinitions = reloadResult.toolDefinitions;
|
|
toolRegistry = reloadResult.toolRegistry;
|
|
hasDeferredTools = reloadResult.hasDeferredTools;
|
|
}
|
|
}
|
|
|
|
/** @type {Record<string, string>} */
|
|
const toolContextMap = {};
|
|
const hasWebSearch = filteredTools.includes(Tools.web_search);
|
|
const hasFileSearch = filteredTools.includes(Tools.file_search);
|
|
const hasExecuteCode = filteredTools.includes(Tools.execute_code);
|
|
|
|
if (hasWebSearch) {
|
|
toolContextMap[Tools.web_search] = buildWebSearchContext();
|
|
}
|
|
|
|
if (hasExecuteCode && tool_resources) {
|
|
try {
|
|
const { toolContext } = await primeCodeFiles({ req, tool_resources, agentId: agent.id });
|
|
if (toolContext) {
|
|
toolContextMap[Tools.execute_code] = toolContext;
|
|
}
|
|
} catch (error) {
|
|
logger.error('[loadToolDefinitionsWrapper] Error priming code files:', error);
|
|
}
|
|
}
|
|
|
|
if (hasFileSearch && tool_resources) {
|
|
try {
|
|
const { toolContext } = await primeSearchFiles({
|
|
req,
|
|
tool_resources,
|
|
agentId: agent.id,
|
|
});
|
|
if (toolContext) {
|
|
toolContextMap[Tools.file_search] = toolContext;
|
|
}
|
|
} catch (error) {
|
|
logger.error('[loadToolDefinitionsWrapper] Error priming search files:', error);
|
|
}
|
|
}
|
|
|
|
const imageFiles = tool_resources?.[EToolResources.image_edit]?.files ?? [];
|
|
if (imageFiles.length > 0) {
|
|
const hasOaiImageGen = filteredTools.includes('image_gen_oai');
|
|
const hasGeminiImageGen = filteredTools.includes('gemini_image_gen');
|
|
|
|
if (hasOaiImageGen) {
|
|
const toolContext = buildImageToolContext({
|
|
imageFiles,
|
|
toolName: `${EToolResources.image_edit}_oai`,
|
|
contextDescription: 'image editing',
|
|
});
|
|
if (toolContext) {
|
|
toolContextMap.image_edit_oai = toolContext;
|
|
}
|
|
}
|
|
|
|
if (hasGeminiImageGen) {
|
|
const toolContext = buildImageToolContext({
|
|
imageFiles,
|
|
toolName: 'gemini_image_gen',
|
|
contextDescription: 'image context',
|
|
});
|
|
if (toolContext) {
|
|
toolContextMap.gemini_image_gen = toolContext;
|
|
}
|
|
}
|
|
}
|
|
|
|
return {
|
|
toolRegistry,
|
|
userMCPAuthMap,
|
|
toolContextMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* 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 {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,
|
|
definitionsOnly = true,
|
|
}) {
|
|
if (definitionsOnly) {
|
|
return loadToolDefinitionsWrapper({ req, res, agent, streamId, 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);
|
|
|
|
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 (isActionTool(tool)) {
|
|
return actionsEnabled;
|
|
} 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);
|
|
}
|
|
|
|
/** @type {Record<string, Record<string, string>>} */
|
|
let userMCPAuthMap;
|
|
if (agent.tools?.some((t) => t.includes(Constants.mcp_delimiter))) {
|
|
userMCPAuthMap = await getUserMCPAuthMap({
|
|
tools: agent.tools,
|
|
userId: req.user.id,
|
|
findPluginAuthsByKeys,
|
|
});
|
|
}
|
|
|
|
const { loadedTools, toolContextMap } = await loadTools({
|
|
agent,
|
|
signal,
|
|
userMCPAuthMap,
|
|
functions: true,
|
|
user: req.user.id,
|
|
tools: _agentTools,
|
|
options: {
|
|
req,
|
|
res,
|
|
openAIApiKey,
|
|
tool_resources,
|
|
processFileURL,
|
|
uploadImageBuffer,
|
|
returnMetadata: true,
|
|
[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 { toolRegistry, toolDefinitions, additionalTools, hasDeferredTools } =
|
|
await buildToolClassification({
|
|
loadedTools,
|
|
userId: req.user.id,
|
|
agentId: agent.id,
|
|
agentToolOptions: agent.tool_options,
|
|
deferredToolsEnabled,
|
|
});
|
|
|
|
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,
|
|
userMCPAuthMap,
|
|
toolContextMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
tools: agentTools,
|
|
};
|
|
}
|
|
|
|
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,
|
|
userMCPAuthMap,
|
|
toolContextMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
tools: agentTools,
|
|
};
|
|
}
|
|
|
|
// 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,
|
|
);
|
|
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 tool = await createActionTool({
|
|
userId: req.user.id,
|
|
res,
|
|
action,
|
|
requestBuilder,
|
|
zodSchema,
|
|
encrypted,
|
|
name: toolName,
|
|
description: functionSignature.description,
|
|
streamId,
|
|
useSSRFProtection: !Array.isArray(_allowedDomains) || _allowedDomains.length === 0,
|
|
});
|
|
|
|
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,
|
|
toolContextMap,
|
|
userMCPAuthMap,
|
|
toolDefinitions,
|
|
hasDeferredTools,
|
|
actionsEnabled,
|
|
tools: agentTools,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* 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, 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 {boolean} [params.actionsEnabled] - Whether the actions capability is enabled
|
|
* @returns {Promise<{ loadedTools: Array, configurable: Object }>}
|
|
*/
|
|
async function loadToolsForExecution({
|
|
req,
|
|
res,
|
|
signal,
|
|
agent,
|
|
toolNames,
|
|
toolRegistry,
|
|
userMCPAuthMap,
|
|
tool_resources,
|
|
streamId = null,
|
|
actionsEnabled,
|
|
}) {
|
|
const appConfig = req.config;
|
|
const allLoadedTools = [];
|
|
const configurable = { userMCPAuthMap };
|
|
|
|
if (actionsEnabled === undefined) {
|
|
const enabledCapabilities = await resolveAgentCapabilities(req, appConfig, agent?.id);
|
|
actionsEnabled = enabledCapabilities.has(AgentCapabilities.actions);
|
|
}
|
|
|
|
const isToolSearch = toolNames.includes(AgentConstants.TOOL_SEARCH);
|
|
const isPTC = toolNames.includes(AgentConstants.PROGRAMMATIC_TOOL_CALLING);
|
|
|
|
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 {
|
|
/**
|
|
* PTC auth is handled by the agents library / sandbox service
|
|
* directly; LibreChat no longer threads a per-run credential.
|
|
*/
|
|
const ptcTool = createProgrammaticToolCallingTool({});
|
|
allLoadedTools.push(ptcTool);
|
|
} catch (error) {
|
|
logger.error('[loadToolsForExecution] Error creating PTC tool:', error);
|
|
}
|
|
}
|
|
|
|
const isBashTool = toolNames.includes(AgentConstants.BASH_TOOL);
|
|
if (isBashTool) {
|
|
try {
|
|
const bashTool = createBashExecutionTool({});
|
|
allLoadedTools.push(bashTool);
|
|
} catch (error) {
|
|
logger.error('[loadToolsForExecution] Failed to create bash_tool', error);
|
|
}
|
|
}
|
|
|
|
const specialToolNames = new Set([
|
|
AgentConstants.TOOL_SEARCH,
|
|
AgentConstants.PROGRAMMATIC_TOOL_CALLING,
|
|
AgentConstants.BASH_TOOL,
|
|
AgentConstants.SKILL_TOOL,
|
|
AgentConstants.READ_FILE,
|
|
]);
|
|
|
|
let ptcOrchestratedToolNames = [];
|
|
if (isPTC && toolRegistry) {
|
|
ptcOrchestratedToolNames = Array.from(toolRegistry.keys()).filter(
|
|
(name) => !specialToolNames.has(name),
|
|
);
|
|
}
|
|
|
|
const requestedNonSpecialToolNames = toolNames.filter((name) => !specialToolNames.has(name));
|
|
const allToolNamesToLoad = isPTC
|
|
? [...new Set([...requestedNonSpecialToolNames, ...ptcOrchestratedToolNames])]
|
|
: requestedNonSpecialToolNames;
|
|
|
|
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) : undefined;
|
|
|
|
const { loadedTools } = await loadTools({
|
|
agent,
|
|
signal,
|
|
userMCPAuthMap,
|
|
functions: true,
|
|
tools: regularToolNames,
|
|
user: req.user.id,
|
|
options: {
|
|
req,
|
|
res,
|
|
tool_resources,
|
|
processFileURL,
|
|
uploadImageBuffer,
|
|
returnMetadata: true,
|
|
[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,
|
|
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: ${actionToolNames.join(', ')}`,
|
|
);
|
|
}
|
|
|
|
if (isPTC && allLoadedTools.length > 0) {
|
|
const ptcToolMap = new Map();
|
|
for (const tool of allLoadedTools) {
|
|
if (tool.name && tool.name !== AgentConstants.PROGRAMMATIC_TOOL_CALLING) {
|
|
ptcToolMap.set(tool.name, tool);
|
|
}
|
|
}
|
|
configurable.ptcToolMap = ptcToolMap;
|
|
}
|
|
|
|
return {
|
|
configurable,
|
|
loadedTools: allLoadedTools,
|
|
};
|
|
}
|
|
|
|
/**
|
|
* Loads action tools for event-driven execution.
|
|
* @param {Object} params
|
|
* @param {ServerRequest} params.req - The request object
|
|
* @param {ServerResponse} params.res - The response object
|
|
* @param {Object} params.agent - The agent object
|
|
* @param {Object} params.appConfig - App configuration
|
|
* @param {string|null} params.streamId - Stream ID
|
|
* @param {string[]} params.actionToolNames - Action tool names to load
|
|
* @returns {Promise<Array>} Loaded action tools
|
|
*/
|
|
async function loadActionToolsForExecution({
|
|
req,
|
|
res,
|
|
agent,
|
|
appConfig,
|
|
streamId,
|
|
actionToolNames,
|
|
}) {
|
|
const loadedActionTools = [];
|
|
|
|
const actionSets = (await loadActionSets({ agent_id: agent.id })) ?? [];
|
|
if (actionSets.length === 0) {
|
|
return loadedActionTools;
|
|
}
|
|
|
|
// See registerActionTools for the key-shape rationale.
|
|
const toolToAction = new Map();
|
|
const allowedDomains = appConfig?.actions?.allowedDomains;
|
|
|
|
for (const action of actionSets) {
|
|
const domain = await domainParser(action.metadata.domain, true);
|
|
const normalizedDomain = domain.replace(domainSeparatorRegex, '_');
|
|
const legacyDomain = legacyDomainEncode(action.metadata.domain);
|
|
const legacyNormalized = legacyDomain.replace(domainSeparatorRegex, '_');
|
|
|
|
const isDomainAllowed = await isActionDomainAllowed(action.metadata.domain, allowedDomains);
|
|
if (!isDomainAllowed) {
|
|
logger.warn(
|
|
`[Actions] Domain "${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,
|
|
zodSchema,
|
|
encrypted,
|
|
requestBuilder,
|
|
name: toolName,
|
|
description: functionSignature.description,
|
|
useSSRFProtection: !Array.isArray(allowedDomains) || allowedDomains.length === 0,
|
|
});
|
|
|
|
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,
|
|
};
|