Skip to content
This repository was archived by the owner on Jul 22, 2025. It is now read-only.
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -152,7 +152,7 @@ export default class BotSelector extends Component {
resetTargetRecipients() {
if (this.allowLLMSelector) {
const botUsername = this.currentUser.ai_enabled_chat_bots.find(
(bot) => bot.model_name === this.llm
(bot) => bot.id === this.llm
).username;
this.composer.set("targetRecipients", botUsername);
} else {
Expand All @@ -170,7 +170,7 @@ export default class BotSelector extends Component {

return availableBots.map((bot) => {
return {
id: bot.model_name,
id: bot.id,
name: bot.display_name,
};
});
Expand Down
6 changes: 5 additions & 1 deletion lib/completions/endpoints/base.rb
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,11 @@ class Base
attr_reader :partial_tool_calls

CompletionFailed = Class.new(StandardError)
TIMEOUT = 60
# 6 minutes
# Reasoning LLMs can take a very long time to respond, generally it will be under 5 minutes
# The alternative is to have per LLM timeouts but that would make it extra confusing for people
# configuring. Let's try this simple solution first.
TIMEOUT = 360

class << self
def endpoint_for(provider_name)
Expand Down