@devries-cameron20 / composio Mirror · read-only / commits / 37ed26dcd
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.

Mirrored from https://github.com/Camo67/composio.git

Synced Nov 21, 08:30 UTC

docs: remove the answering later section

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Mukund committed Oct 15, 2026 at 17:55 UTC 37ed26dcdee9cf1ae94085fbcff86d9057142b14
1 file changed -11
docs/content/docs/approval-mode.mdx
-11
@@ -379,17 +379,6 @@ terminal.close();
379 </Tab>
380 </Tabs>
381
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:
385 -
386 -- the tool call: its ID, tool name and arguments
387 -- the error's `input_requests` and `request_state`
388 -
389 -Then send the questions to your frontend and end the request. When the user answers, call `session.execute()` again with the saved tool name and arguments, their answers in `input_responses`, and the saved `request_state`. Add the result to the conversation as that tool call's result, and continue the agent loop.
390 -
391 -Keep `request_state` on your server, not in the browser.
392 -
382 ## Using MCP
383
384 If your agent connects to the session [over MCP](/docs/sessions-via-mcp), clients that support elicitation, like Claude Code, ask the user for you. Clients that don't support it can't ask, so calls that need approval are denied by default. You can set `no_elicitation_support_fallback` to `"allow"` to run them without asking instead: