@devries-cameron20 / composio-1 / commits / 14cb6b2e7
Fork 0

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

docs(openai): align responses demo on gpt-5 and print aggregated output

- Use gpt-5 like the rest of the repo's examples (getting-started.md, the pre-PR demo) instead of the gpt-5.2 id used nowhere else. - Print response.output_text instead of dumping the raw Response object, matching the final line of the demo.

jkomyno committed Sep 15, 2026 at 16:42 UTC 14cb6b2e75eae8a73a271c13041059c383d00cf0
1 file changed +3 -3
python/providers/openai/openai_responses_demo.py
+3 -3
@@ -21,11 +21,11 @@ tools = composio.tools.get(user_id="default", tools=["HACKERNEWS_GET_USER"])
21
22 # Get the first response from the LLM.
23 response = openai_client.responses.create(
24 - model="gpt-5.2",
24 + model="gpt-5",
25 tools=tools,
26 input=task,
27 )
28 -print(response)
28 +print(response.output_text)
29
30 # Execute tool calls until the model returns a final answer.
31 while True:
@@ -35,7 +35,7 @@ while True:
35
36 results = composio.provider.handle_tool_calls(response=response, user_id="default")
37 response = openai_client.responses.create(
38 - model="gpt-5.2",
38 + model="gpt-5",
39 tools=tools,
40 previous_response_id=response.id,
41 input=[