Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
Mirrored from https://github.com/Camo67/composio.git
Synced Nov 21, 12:15 UTC
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=[