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: rename the agent loop section and drop its sample output
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Mukund committed
Oct 15, 2026 at 17:55 UTC
92dd281370fac15babce592801337b575c69c34f
1 file changed
+2
-13
docs/content/docs/approval-mode.mdx
+2
-13
@@ -194,9 +194,9 @@ If the user approves, the tool runs and `result_type` is `completed`. If they de
194
195
If the user picks **Always approve**, the tool runs, and later calls to the same tool on the same connected account run without asking for the rest of the session.
196
197
-## Adding approval to an agent loop
197
+## End-to-end example
198
199
-This agent sends an email over Gmail with Claude. Each tool call goes through `run_tool`, which runs it with `session.execute()`. When Composio needs the user's approval, `run_tool` asks in the terminal, then sends the call again with the answers.
199
+An agent loop with Claude that asks for approval in the terminal:
200
201
<Tabs groupId="language" items={['Python', 'TypeScript']} persist>
202
<Tab value="Python">
@@ -379,17 +379,6 @@ terminal.close();
379
</Tab>
380
</Tabs>
381
382
-When you run it, the agent asks to send the email, and you see:
383
-
384
-```txt
385
-Your agent wants to run the following tool:
386
-
387
-GMAIL_SEND_EMAIL({"recipient_email": "priya@acme.com", "subject": "Q3 numbers", ...})
388
-Decision (approve/always_approve/deny):
389
-```
390
-
391
-If you deny it, Claude gets the denial as the tool's error and can tell the user it didn't send the email.
392
-
382
### Answering later
383
384
In a web app, the user answers in your UI, perhaps minutes later, so you can't wait in a loop for their answer. When `session.execute()` raises, save these with the conversation: