mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-31 12:07:45 -04:00
6a80e23733
Add a routing middleware stack and a cloud-proxy backend. * cloud-proxy: a Go gRPC backend that forwards OpenAI- and Anthropic-shaped chat requests to upstream providers, with an optional translate mode (OpenAI request -> Anthropic /v1/messages -> OpenAI response) and full tool-calling support. * routing: admission control, content-aware model routing (embedding cache + classifier + rerank + Arch-Router score), PII detection/redaction (regex + NER) with streaming filter and OpenAI/Anthropic adapters, and a per-user/per-key billing recorder backed by GORM or in-memory storage. * middleware: UsageMiddleware records usage via the billing recorder, plus admission, route-model, usage-stamp and trace middlewares. * observability: BackendTrace ring buffer stores full request bodies (capped), MITM proxy emits structured trace events, and router classifier decisions surface at /api/router/decide. * gallery: Arch-Router-1.5B (Q4_K_M and Q8_0). * UI: cloud-proxy model-editor fields, classifier system-prompt and score-normalization config, and a Traces page rendering request bodies. Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash] Signed-off-by: Richard Palethorpe <io@richiejp.com>
23 lines
807 B
Go
23 lines
807 B
Go
package localaitools
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/modelcontextprotocol/go-sdk/mcp"
|
|
)
|
|
|
|
func registerUsageTools(s *mcp.Server, client LocalAIClient, _ Options) {
|
|
mcp.AddTool(s, &mcp.Tool{
|
|
Name: ToolGetUsageStats,
|
|
Description: "Return aggregated token usage. Defaults to the calling user's own usage over the last month. " +
|
|
"Use period=day|week|month|all to change the window. Set all=true for a cluster-wide admin view " +
|
|
"(only meaningful when auth is on and the caller is admin; in single-user mode there is only one user).",
|
|
}, func(ctx context.Context, _ *mcp.CallToolRequest, args UsageStatsQuery) (*mcp.CallToolResult, any, error) {
|
|
stats, err := client.GetUsageStats(ctx, args)
|
|
if err != nil {
|
|
return errorResult(err), nil, nil
|
|
}
|
|
return jsonResult(stats), nil, nil
|
|
})
|
|
}
|