# ElevenAgents: Test-specific tool mocks: Agent simulations and unit tests can now define…

By Steven Van · 2026-08-03

Test-specific tool mocks: Agent simulations and unit tests can now define tool\_mock\_overrides, keyed by tool ID, to replace shared mocks for one test.

[ElevenLabs](<https://creatorstoolbox.com/tools/elevenlabs>)'s ElevenAgents tools now let agent simulations and unit tests define tool\_mock\_overrides, a map keyed by tool ID that swaps in a mock for a single test instead of the shared one. Mock responses also gain an optional is\_error flag (default false), so a test can exercise a tool-failure path.

The same [August 3 changelog](<https://elevenlabs.io/docs/changelog/2026/8/3#elevenagents>) adds several other changes to ElevenAgents:

- Literal Say node messages can carry text\_translations, a map of language keys to translated strings.

- Listing conversations and searching conversation messages both accept a version\_id parameter to filter results by agent version.

- A new knowledge\_base system tool lets an agent's configuration set enabled retrieval strategies, and RAG queries can pass use\_agent\_defaults as false to use neutral retrieval settings while keeping the agent's embedding model.

- Agent configuration adds voice activity detection (VAD), currently supporting a background\_voice\_detection option.

- Custom LLM integrations can now use a websocket API type.

- Widget file-input configuration adds max\_files\_in\_memory (1-30, default 10); files beyond the limit are summarized and released from memory.

- DTMF input configuration adds redact\_input, which replaces caller keypad digits in transcripts, conversation logs and analysis, while digits repeated by the agent or passed to tools stay unchanged.

[![](<https://elevenlabs.io/docs/api/fern-docs/og?slug=docs%2Fchangelog%2F2026%2F8%2F3>)](<https://elevenlabs.io/docs/changelog/2026/8/3#elevenagents>)

![ElevenLabs](<https://elevenlabs.io/android-chrome-512x512.png>)

ElevenLabs

AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.

[View ElevenLabs →](<https://creatorstoolbox.com/tools/elevenlabs>)

Sources

[Original source](<https://elevenlabs.io/docs/changelog/2026/8/3#elevenagents>)

[Read ElevenAgents: Test-specific tool mocks: Agent simulations and unit tests can now define… on Creators Toolbox](<https://creatorstoolbox.com/blog/elevenlabs-elevenagents-test-specific-tool-mocks-agent-simulations-and-unit-test>)

---
Canonical source: https://creatorstoolbox.com/blog/elevenlabs-elevenagents-test-specific-tool-mocks-agent-simulations-and-unit-test