mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-06-23 15:13:18 +08:00
* feat(plugin): add ModelRouter before auth with single-slot routing targets ## Motivation Plugins that need to change execution based on the **original inbound request** (protocol format, raw body, headers, query, stream flag, metadata, etc.) often resorted to virtual/trampoline models or routing inside interceptors. This commit adds **ModelRouter**: a pluggable layer **before** model-to-provider resolution and AuthManager credential selection, so plugins can declare who executes a request without spoofing the client model name. This is a **new capability**, not a bugfix on the existing chain. With no ModelRouter plugins loaded, behavior matches upstream. ## Pipeline placement - `execute`, `stream`, and `count` (and image paths via AuthManager) call `applyModelRouter()` before building `coreexecutor.Request`. - Routing runs **before** the request interceptor (before auth), so routers see the client’s original context. After a plugin executor is chosen, the existing **after-auth interceptor → response/stream interceptor** chain still applies. - Internal `ExecuteModel` / `ExecuteModelStream` (host callbacks) support `SkipRouterPluginID` so nested calls do not re-enter the same router. ## Routing API (single slot, mutually exclusive) `ModelRouteResponse` uses **one target slot** to avoid ambiguity when both `TargetExecutorPluginID` and `TargetProvider` were set and the host ignored one: | Field | Meaning | |-------|---------| | `Handled` | `false`: this router declines; try the next router or default path | | `TargetKind` | `self` \| `executor` \| `provider` (pick one) | | `Target` | `self`/`executor`: plugin ID; `provider`: built-in provider key | | `TargetModel` | Optional on `provider` only; empty keeps client `RequestedModel` | | `Reason` | Optional diagnostic text | - **self**: the router plugin’s own executor (`Target` normalized to the router’s plugin ID). - **executor**: another plugin’s executor; host pre-checks with `executorPluginReady()` (executor declared and provider identifier resolvable) to avoid handled routes that 500 at execution. - **provider**: skip registry model resolution; fixed built-in AuthManager path; optional `TargetModel` for execution model only—**does not** change outward requested-model metadata. Routers run in **descending plugin priority** (tie-break: ascending plugin ID). Panic, error, invalid target, or unavailable executor/provider → log and **fall through to the next router**; if none handle, use the original provider+auth flow. ## Context exposed to routers `ModelRouteRequest` includes: - `SourceFormat`, `RequestedModel`, `Stream` - `Headers`, `Query`, `Body` (defensive copies) - `Metadata` (best-effort read-only context snapshot) - `AvailableProviders`: built-in provider keys with at least one **non-disabled** auth (`AuthManager.AvailableProviders()`). **Does not** reflect per-model cooldown or transient unavailability—treat as an optimistic snapshot. Adds `AuthManager.HasProviderAuth()` and `AvailableProviders()`, excluding `Disabled` and `StatusDisabled` auths consistently with credential selection. ## Host and RPC - Go plugins: `pluginapi.ModelRouter` + `RouteModel()`. - RPC plugins: `pluginabi.MethodModelRoute` (`model.route`), capability flag `model_router`. - `pluginhost.Host` implements `RouteModel` / `RouteModelExcept`; handlers use `SetModelRouterHost` or a `PluginHost` type assertion; **direct executor** paths use `ExecutePluginExecutor*` / `CountPluginExecutor`. - No bundled example ModelRouter plugin; capability is active only when a third-party plugin declares `model_router` and loads. ## Plugin RPC schema (policy A, upstream-aligned) - `pluginabi.SchemaVersion` stays **1**: capability additions (`model_router`, `model.route`) do not bump the number; increment only on breaking RPC JSON changes. - Host sends `schema_version` at register; reject only if the plugin declares a **higher** version than the host. - No unpublished “ModelRouter requires schema ≥ 3” gate (v3 single-slot API was never public). - Existing plugins and examples without `model_router` (`schema_version: 1`) need no changes. - RPC ModelRouter: `schema_version: 1` + `model_router: true` + implement `model.route`. ## Path consistency within this commit - Provider routes reuse image-only model checks (e.g. `gpt-image-2`) on the normalized model, same as the default AuthManager path. - `count` aligned with execute/stream: `SkipRouterPluginID`, query/headers injection, interceptor skip semantics. - Handlers: `modelRoutersEnabled` treats hosts without `HasModelRouters` as disabled (same as before ModelRouter existed); `pluginhost.Host` implements the detector. - API docs: `ModelRouter` explicitly includes built-in **provider** targets (in addition to plugin executors and the router’s own executor). ## Testing go test ./internal/pluginhost ./sdk/api/handlers ./sdk/pluginapi ./sdk/pluginabi ./sdk/cliproxy/auth go build -o test-output ./cmd/server && rm test-output go test ./... * fix(handlers): address ModelRouter review feedback - Use modelExecutionQuery for plugin executor and AuthManager paths so inbound URL query matches router/header behavior - Guard queryFromContext when gin Request.URL is nil - Read plugin executor stream chunks via nextStreamChunk to exit on cancel - Drop redundant clonePluginMetadata on capability record meta Tests cover query propagation, stream cancel, and nil URL safety. * feat(plugin): add Claude web search router example Add a Claude Code web_search ModelRouter example that can route matching Claude requests through Antigravity, Codex, xAI, or Tavily. The plugin includes executor orchestration, backend fallback/penalty handling, Tavily API key support, Claude-compatible response assembly, stream forwarding, and focused unit coverage for detection, fallback routing, model resolution, penalties, stream forwarding, and Tavily behavior. Verification: go test -count=1 ./... in examples/plugin/claude-web-search-router/go; go build -buildmode=c-shared for the plugin; go build ./cmd/server; live local CPA curl coverage for plugin load, four explicit routes, fallback, and Codex spark routing. * fix(pluginhost): validate executor routes before fallback * fix(pluginhost): skip oauth-only executor routes
139 lines
3.8 KiB
Go
139 lines
3.8 KiB
Go
package main
|
|
|
|
import (
|
|
"encoding/json"
|
|
"testing"
|
|
|
|
"github.com/router-for-me/CLIProxyAPI/v7/internal/registry"
|
|
"github.com/router-for-me/CLIProxyAPI/v7/sdk/pluginapi"
|
|
)
|
|
|
|
func claudeWebSearchRouteBody(t *testing.T) []byte {
|
|
t.Helper()
|
|
body := []byte(`{
|
|
"tools":[{"type":"web_search_20250305","name":"web_search","max_uses":5}],
|
|
"system":[{"type":"text","text":"You have access to the web search tool use."}],
|
|
"messages":[{"role":"user","content":[{"type":"text","text":"Perform a web search for the query: test"}]}]
|
|
}`)
|
|
return body
|
|
}
|
|
|
|
func decodeModelRouteResponse(t *testing.T, raw []byte) pluginapi.ModelRouteResponse {
|
|
t.Helper()
|
|
var env envelope
|
|
if err := json.Unmarshal(raw, &env); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
var resp pluginapi.ModelRouteResponse
|
|
if err := json.Unmarshal(env.Result, &resp); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
return resp
|
|
}
|
|
|
|
func TestRouteWithFallbackAntigravityFirst(t *testing.T) {
|
|
reg := registry.GetGlobalRegistry()
|
|
const clientID = "test-fallback-antigravity"
|
|
reg.RegisterClient(clientID, "antigravity", []*registry.ModelInfo{
|
|
{ID: "gem-fallback-test", SupportsWebSearch: true},
|
|
})
|
|
t.Cleanup(func() { reg.UnregisterClient(clientID) })
|
|
|
|
currentConfig.Store(pluginConfig{
|
|
Enabled: true,
|
|
Route: string(backendFallback),
|
|
})
|
|
raw, err := routeModel(mustJSON(t, rpcModelRouteRequest{
|
|
ModelRouteRequest: pluginapi.ModelRouteRequest{
|
|
SourceFormat: "claude",
|
|
Body: claudeWebSearchRouteBody(t),
|
|
RequestedModel: "claude-sonnet-4-6",
|
|
AvailableProviders: []string{"antigravity", "codex", "xai"},
|
|
},
|
|
}))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
resp := decodeModelRouteResponse(t, raw)
|
|
if !resp.Handled || resp.TargetKind != pluginapi.ModelRouteTargetSelf {
|
|
t.Fatalf("resp = %#v", resp)
|
|
}
|
|
}
|
|
|
|
func TestRouteWithFallbackSkipsAntigravityToCodex(t *testing.T) {
|
|
currentConfig.Store(pluginConfig{
|
|
Enabled: true,
|
|
Route: string(backendFallback),
|
|
})
|
|
raw, err := routeModel(mustJSON(t, rpcModelRouteRequest{
|
|
ModelRouteRequest: pluginapi.ModelRouteRequest{
|
|
SourceFormat: "claude",
|
|
Body: claudeWebSearchRouteBody(t),
|
|
RequestedModel: "claude-sonnet-4-6",
|
|
AvailableProviders: []string{"codex", "xai"},
|
|
},
|
|
}))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
resp := decodeModelRouteResponse(t, raw)
|
|
if !resp.Handled || resp.TargetKind != pluginapi.ModelRouteTargetSelf {
|
|
t.Fatalf("resp = %#v", resp)
|
|
}
|
|
}
|
|
|
|
func TestRouteWithFallbackToTavily(t *testing.T) {
|
|
currentConfig.Store(pluginConfig{
|
|
Enabled: true,
|
|
Route: string(backendFallback),
|
|
TavilyAPIKeys: []string{"tvly-test"},
|
|
})
|
|
raw, err := routeModel(mustJSON(t, rpcModelRouteRequest{
|
|
ModelRouteRequest: pluginapi.ModelRouteRequest{
|
|
SourceFormat: "claude",
|
|
Body: claudeWebSearchRouteBody(t),
|
|
AvailableProviders: []string{},
|
|
},
|
|
}))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
resp := decodeModelRouteResponse(t, raw)
|
|
if !resp.Handled || resp.TargetKind != pluginapi.ModelRouteTargetSelf {
|
|
t.Fatalf("resp = %#v", resp)
|
|
}
|
|
}
|
|
|
|
func TestRouteWithFallbackExhausted(t *testing.T) {
|
|
currentConfig.Store(pluginConfig{
|
|
Enabled: true,
|
|
Route: string(backendFallback),
|
|
})
|
|
raw, err := routeModel(mustJSON(t, rpcModelRouteRequest{
|
|
ModelRouteRequest: pluginapi.ModelRouteRequest{
|
|
SourceFormat: "claude",
|
|
Body: claudeWebSearchRouteBody(t),
|
|
AvailableProviders: []string{},
|
|
},
|
|
}))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
resp := decodeModelRouteResponse(t, raw)
|
|
if resp.Handled {
|
|
t.Fatalf("expected declined, got %#v", resp)
|
|
}
|
|
if resp.Reason == "" || resp.Reason[:len("web_search_fallback_exhausted")] != "web_search_fallback_exhausted" {
|
|
t.Fatalf("reason = %q", resp.Reason)
|
|
}
|
|
}
|
|
|
|
func mustJSON(t *testing.T, v any) []byte {
|
|
t.Helper()
|
|
raw, err := json.Marshal(v)
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
return raw
|
|
}
|