Setting up a backend means guessing its numbers: Connect first, then fill the model's context, output reservation and effort from what the server reports #162
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
The Settings page asks for a backend's URL, model, context window, output reservation and reasoning effort all at once, before Braid has asked the server anything. For a new provider an operator has no idea what to enter: Anthropic's URL is always the same, and the window and output limits are published by the server itself.
What the servers report, read on 2026-10-08: Anthropic's
GET /v1/modelsgives each model'sdisplay_name,max_input_tokens(1,000,000 for the Claude 5.x models),max_tokens(128,000), the effort levels it supports, anddeprecated_at. vLLM's model list carriesmax_model_len(to confirm on trogdor). No server recommends a reasoning effort.What it needs
https://api.anthropic.com/v1. Self-hosted kinds keep a placeholder.max_input_tokens,max_model_len);min(its max output, 32,000), opencode's cap, andmedium.Done when
Adding the Claude API takes the kind, the key, Connect and a model pick, with every number filled from the model; and trogdor's profile fills its window from vLLM's model list.
Shipped in
649dc00(deployed; new boot id). Change archived asopenspec/changes/archive/2026-10-09-backend-connect.What shipped
src/osf/models.pyreads Anthropic's shape (max_input_tokens,max_tokens,capabilities.effort), vLLM'smax_model_len, and id-only lists. The answer keepsmodelsand addsmodel_details.https://api.anthropic.com/v1unless a URL was typed.medium;qwen3.8-27b: 20,480 andmedium), elsemin(max output, 32,000)andmedium. A field edited away shows the model's default; the effort offers only supported levels.Checked
medium; Sonnet 4.5, not in the table, filled the server's 200,000 and the rule's 32,000."max_model_len": 524288; Connect from production after the deploy read it as a 524,288 window with 20,480 andmedium.