Elvean_v1.2.28.dmg (latest release) only supplies Apple Silicon only binary
Upon downloading Elvean_v1.2.28.dmg, I was greeted by a file that showed only one .app, which lists as "Kind: Application (Apple Silicon)” rather than a universal binary as the website would suggest. Elvean_v1.2.28.dmg SHA-256 Checksum for file validation: 6500eaf1841cd5028e266421fd65ab58564cbfc0305bc279494084dc586ed50a
Tyler Barney about 2 hours ago
Elvean_v1.2.28.dmg (latest release) only supplies Apple Silicon only binary
Upon downloading Elvean_v1.2.28.dmg, I was greeted by a file that showed only one .app, which lists as "Kind: Application (Apple Silicon)” rather than a universal binary as the website would suggest. Elvean_v1.2.28.dmg SHA-256 Checksum for file validation: 6500eaf1841cd5028e266421fd65ab58564cbfc0305bc279494084dc586ed50a
Tyler Barney about 2 hours ago
Bug: Bug: `max_tokens` is not forwarded to Custom (OpenAI-compatible) Providers
Elvean does construct a full parameter payload — sampling parameters (`temperature`, top_p) and tool definitions are forwarded correctly. Only max_tokens is omitted, so the slider value never reaches the API. Row 2 reproduces the behaviour exactly. Row 1 shows the backend handles long generations without issue when the parameter is present. ## Controlled A/B through a logging proxy Elvean was pointed at a small proxy in front of mlx_lm.server. The proxy logs the incoming payload and can optionally inject max_tokens. Nothing in Elvean was changed between the two runs — same conversation settings, same Max Tokens slider value, same prompt. Run A — proxy passes through unchanged: ``` keys : ['messages', 'model', 'stream', 'stream_options', 'temperature', 'tool_choice', 'tools', 'top_p'] max_tokens : ABSENT ``` Result: output stops mid-sentence inside the reasoning block.
Nathan about 6 hours ago
Bug: Bug: `max_tokens` is not forwarded to Custom (OpenAI-compatible) Providers
Elvean does construct a full parameter payload — sampling parameters (`temperature`, top_p) and tool definitions are forwarded correctly. Only max_tokens is omitted, so the slider value never reaches the API. Row 2 reproduces the behaviour exactly. Row 1 shows the backend handles long generations without issue when the parameter is present. ## Controlled A/B through a logging proxy Elvean was pointed at a small proxy in front of mlx_lm.server. The proxy logs the incoming payload and can optionally inject max_tokens. Nothing in Elvean was changed between the two runs — same conversation settings, same Max Tokens slider value, same prompt. Run A — proxy passes through unchanged: ``` keys : ['messages', 'model', 'stream', 'stream_options', 'temperature', 'tool_choice', 'tools', 'top_p'] max_tokens : ABSENT ``` Result: output stops mid-sentence inside the reasoning block.
Nathan about 6 hours ago
Ability to choose which messages are included in a conversation
the ability to choose which messages are included in a conversation to save tokens and exclude “unwanted” messages.
AxelPOG about 2 months ago
Ability to choose which messages are included in a conversation
the ability to choose which messages are included in a conversation to save tokens and exclude “unwanted” messages.
AxelPOG about 2 months ago
Completed
Switch between multiple API keys with the same service
I would like to be able to have different “workspaces” saving chats for each and having a different API key for each. I’m currently using Claude and would like to be able to switch between my different API keys for different projects/clients.
cgriffin about 2 months ago
Completed
Switch between multiple API keys with the same service
I would like to be able to have different “workspaces” saving chats for each and having a different API key for each. I’m currently using Claude and would like to be able to switch between my different API keys for different projects/clients.
cgriffin about 2 months ago
Completed
Access / Import my chats in Open Ai's ChatGPT
Hello there, I just downloaded your app and I have searched your “Help” section but I cannot find a way to access mi very long ChatGPT chats. I was hoping I could import them into Elvean and continue working with them. Can this be done? Apologies if this is covered somewhere else ind detailed. Many thanks in advance.
LolaBerwoots about 2 months ago
Completed
Access / Import my chats in Open Ai's ChatGPT
Hello there, I just downloaded your app and I have searched your “Help” section but I cannot find a way to access mi very long ChatGPT chats. I was hoping I could import them into Elvean and continue working with them. Can this be done? Apologies if this is covered somewhere else ind detailed. Many thanks in advance.
LolaBerwoots about 2 months ago
In Progress
Repeatable tasks
Add support for repeatable tasks with ability to execute at certain intervals in the background, send notification when ready.
Nathan 4 months ago
In Progress
Repeatable tasks
Add support for repeatable tasks with ability to execute at certain intervals in the background, send notification when ready.
Nathan 4 months ago