Fix the simulations CI job: lk agent simulate needs the text subcommand (#107)

Since livekit-cli v2.18, the root `lk agent simulate` command only prints help
and exits 0; the mode is a required subcommand (`text` or `audio`). The
simulations job has been running the old flat form, so it has been passing
without starting a single simulation. Switch the job and the four places that
show the command to `lk agent simulate text --scenarios scenarios.yaml`.

Text mode is the right mode for CI: it exercises the LLM, tools and
conversation logic without the audio pipeline, and is scheduled so it doesn't
compete with live sessions for inference.

Author: bcherry

.github/workflows/simulations.yml

@@ -1,7 +1,7 @@
 # Runs the scenarios in scenarios.yaml against your agent on LiveKit Cloud.
 # Simulations spend real inference, so this runs on merges to main and on demand
 # rather than on every pull request push. Run
-# `lk agent simulate --scenarios scenarios.yaml` locally while iterating.
+# `lk agent simulate text --scenarios scenarios.yaml` locally while iterating.
 name: Simulations
 
 on:
@@ -43,4 +43,4 @@ jobs:
       run: curl -sSL https://get.livekit.io/cli | bash
 
     - name: Run simulations
-      run: lk agent simulate --scenarios scenarios.yaml
+      run: lk agent simulate text --scenarios scenarios.yaml

AGENTS.md

@@ -42,7 +42,7 @@ Voice AI agents are highly sensitive to excessive latency. For this reason, it's
 
 ## Testing
 
-When possible, add tests for agent behavior. Add a scenario to `scenarios.yaml` and run it with `lk agent simulate --scenarios scenarios.yaml`. The scenarios run in CI on every merge to main; read the [simulations documentation](https://docs.livekit.io/agents/start/testing/simulations/) before editing them.
+When possible, add tests for agent behavior. Add a scenario to `scenarios.yaml` and run it with `lk agent simulate text --scenarios scenarios.yaml`. The scenarios run in CI on every merge to main; read the [simulations documentation](https://docs.livekit.io/agents/start/testing/simulations/) before editing them.
 
 For turn-level checks that don't need a live session, use the in-process [testing framework](https://docs.livekit.io/agents/start/testing/); `tests/test_agent.py` has a commented-out example. Run those with `uv run pytest`.
 

README.md

@@ -148,7 +148,7 @@ For advanced customization, see the [complete frontend guide](https://docs.livek
 Simulations run full multi-turn conversations between a simulated user and your agent on LiveKit Cloud, then judge each transcript. The scenarios live in [`scenarios.yaml`](scenarios.yaml). Run them locally with the [LiveKit CLI](https://docs.livekit.io/intro/basics/cli/):
 
 ```console
-lk agent simulate --scenarios scenarios.yaml
+lk agent simulate text --scenarios scenarios.yaml
 ```
 
 The `Simulations` workflow in `.github/workflows/simulations.yml` runs the same file on every merge to `main` and on demand from the Actions tab. It runs there rather than on every pull request push because each run spends real inference. See the [simulations guide](https://docs.livekit.io/agents/start/testing/simulations/) for how to write scenarios and read results.

scenarios.yaml

@@ -1,6 +1,6 @@
 # Simulation scenarios for the starter assistant. Each one is a conversation a
 # simulated user has with your agent, judged against agent_expectations. Run them
-# with `lk agent simulate --scenarios scenarios.yaml`; the Simulations workflow
+# with `lk agent simulate text --scenarios scenarios.yaml`; the Simulations workflow
 # runs them on every merge to main.
 #
 # Add a scenario whenever you change instructions or add a tool, and pin any dates