From 5546c8e01c014a1a3e6769fc8e2184919eb506dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Tue, 5 Aug 2025 11:46:28 -0700
Subject: [PATCH] scripts(evals): update to use new runner function

---
 scripts/evals/README.md | 6 +++---
 scripts/evals/eval.py   | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/scripts/evals/README.md b/scripts/evals/README.md
index b67d5d75b..74f1b2e27 100644
--- a/scripts/evals/README.md
+++ b/scripts/evals/README.md
@@ -32,7 +32,7 @@ also explains why it thinks the answer is valid or invalid.
 To run the release evals:
 
 ```sh
-python run-release-evals.py -a -v
+uv run run-release-evals.py -a -v
 ```
 
 This runs all the evals and stores logs and audio (`-a`) for each test.
@@ -41,7 +41,7 @@ You can also specify which tests to run. For example, to run all `07` series
 tests:
 
 ```sh
-python run-release-evals.py -p 07 -a -v
+uv run run-release-evals.py -p 07 -a -v
 ```
 
 ## Script Evals
@@ -49,7 +49,7 @@ python run-release-evals.py -p 07 -a -v
 You can also run evals for a single example (not part of the release set):
 
 ```sh
-python run-eval.py -p "A simple math addition" -a -v YOUR_EXAMPLE_SCRIPT
+uv run run-eval.py -p "A simple math addition" -a -v YOUR_EXAMPLE_SCRIPT
 ```
 
 Your script needs to follow any of the foundation examples pattern.
diff --git a/scripts/evals/eval.py b/scripts/evals/eval.py
index 71d5c9e9e..fba701f9c 100644
--- a/scripts/evals/eval.py
+++ b/scripts/evals/eval.py
@@ -176,7 +176,7 @@ async def run_example_pipeline(script_path: Path):
         ),
     )
 
-    await module.run_example(transport, argparse.Namespace(), True)
+    await module.run_bot(transport)
 
 
 async def run_eval_pipeline(