{{define "content"}}
Providers are cognitive service suppliers. Roles decide which model does which job; minds keep their identity whatever you change here.
| Name | Kind | Endpoint | Key | Status | Last test | |
|---|---|---|---|---|---|---|
| {{.Name}} | {{.Kind}} | {{.Endpoint}} | {{.KeyDescribed}} | {{if .Enabled}}enabled{{else}}disabled{{end}}{{if .AllowPrivate}} private ok{{end}} | {{if .LastTestAt}}{{if deref .LastTestOK}}ok{{else}}failed{{end}} {{trunc .LastTestMsg 60}}{{else}}never{{end}} |
No providers yet. Add one on the right; local Ollama needs “allow private addresses”.
{{end}}| Provider | Model | Kind | Context | Cost in/out per M | State | |
|---|---|---|---|---|---|---|
| {{.Provider}} | {{.Name}} | {{.Kind}}{{if .Dims}} ({{.Dims}}d){{end}} | {{if .ContextWindow}}{{.ContextWindow}}{{else}}—{{end}} | ${{.InputCostPerM}} / ${{.OutputCostPerM}} | {{if .Enabled}}on{{else}}off{{end}} | {{if $admin}}{{end}} |
No models yet.
{{end}} {{if and $admin .Data.Providers}} {{end}}| Role | Purpose | Primary | Fallbacks | Temp | Max tokens | {{if $admin}}{{end}} |
|---|---|---|---|---|---|---|
| Provider | Model | Role | Calls | Errors | Tokens in | Tokens out | Cost | Avg ms |
|---|---|---|---|---|---|---|---|---|
| {{.Provider}} | {{.Model}} | {{.Role}} | {{.Calls}} | {{.Errors}} | {{.PromptTokens}} | {{.OutputTokens}} | ${{printf "%.4f" .Cost}} | {{printf "%.0f" .AvgLatencyMS}} |
No calls yet.
{{end}} {{if .Data.Errors}}Per-mind budgets are in each mind's configuration. When a budget is exhausted, deterministic cognition continues and model-assisted steps are skipped.