mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-06-23 14:15:03 +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
108 lines
3.8 KiB
Go
108 lines
3.8 KiB
Go
package main
|
|
|
|
import (
|
|
"strings"
|
|
|
|
"github.com/router-for-me/CLIProxyAPI/v7/sdk/pluginapi"
|
|
)
|
|
|
|
// defaultWebSearchFallbackChain is the ordered backend try list when route=fallback.
|
|
func defaultWebSearchFallbackChain() []routeBackend {
|
|
return []routeBackend{
|
|
backendAntigravityGoogle,
|
|
backendCodexWebSearch,
|
|
backendXAIWebSearch,
|
|
backendTavily,
|
|
}
|
|
}
|
|
|
|
func isFallbackRoute(route string) bool {
|
|
r := strings.ToLower(strings.TrimSpace(route))
|
|
return r == "" || r == string(backendFallback)
|
|
}
|
|
|
|
// tryRouteBackend returns a handled ModelRouteResponse and true when this backend can serve the request.
|
|
func tryRouteBackend(backend routeBackend, cfg pluginConfig, req pluginapi.ModelRouteRequest) (pluginapi.ModelRouteResponse, bool) {
|
|
switch backend {
|
|
case backendTavily:
|
|
client := newTavilyClient(cfg.TavilyAPIKeys)
|
|
if !client.available() {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "tavily_unavailable"}, false
|
|
}
|
|
return pluginapi.ModelRouteResponse{
|
|
Handled: true,
|
|
TargetKind: pluginapi.ModelRouteTargetSelf,
|
|
Reason: "claude_code_web_search_tavily",
|
|
}, true
|
|
case backendAntigravityGoogle:
|
|
if !hasProvider(req.AvailableProviders, "antigravity") {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "antigravity_unavailable"}, false
|
|
}
|
|
targetModel := resolveAntigravityWebSearchTargetModel(cfg.AntigravityModel, req.RequestedModel)
|
|
if targetModel == "" {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "antigravity_web_search_model_unresolved"}, false
|
|
}
|
|
return pluginapi.ModelRouteResponse{
|
|
Handled: true,
|
|
TargetKind: pluginapi.ModelRouteTargetProvider,
|
|
Target: "antigravity",
|
|
TargetModel: targetModel,
|
|
Reason: "claude_code_web_search_antigravity_google",
|
|
}, true
|
|
case backendCodexWebSearch:
|
|
if !hasProvider(req.AvailableProviders, "codex") {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "codex_unavailable"}, false
|
|
}
|
|
targetModel := resolveCodexWebSearchTargetModel(cfg.CodexModel)
|
|
return pluginapi.ModelRouteResponse{
|
|
Handled: true,
|
|
TargetKind: pluginapi.ModelRouteTargetProvider,
|
|
Target: "codex",
|
|
TargetModel: targetModel,
|
|
Reason: "claude_code_web_search_codex",
|
|
}, true
|
|
case backendXAIWebSearch:
|
|
if !hasProvider(req.AvailableProviders, "xai") {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "xai_unavailable"}, false
|
|
}
|
|
targetModel := resolveXAIWebSearchTargetModel(cfg.XAIModel)
|
|
return pluginapi.ModelRouteResponse{
|
|
Handled: true,
|
|
TargetKind: pluginapi.ModelRouteTargetProvider,
|
|
Target: "xai",
|
|
TargetModel: targetModel,
|
|
Reason: "claude_code_web_search_xai",
|
|
}, true
|
|
case backendDefaultProvider:
|
|
provider := cfg.DefaultProvider
|
|
if provider == "" || !hasProvider(req.AvailableProviders, provider) {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "default_provider_unavailable"}, false
|
|
}
|
|
return pluginapi.ModelRouteResponse{
|
|
Handled: true,
|
|
TargetKind: pluginapi.ModelRouteTargetProvider,
|
|
Target: provider,
|
|
TargetModel: cfg.DefaultProviderModel,
|
|
Reason: "claude_code_web_search_default_provider",
|
|
}, true
|
|
default:
|
|
return pluginapi.ModelRouteResponse{Handled: false}, false
|
|
}
|
|
}
|
|
|
|
func routeWithFallback(cfg pluginConfig, req pluginapi.ModelRouteRequest) pluginapi.ModelRouteResponse {
|
|
return routeWithExecutionOrchestration(cfg, req, string(backendFallback))
|
|
}
|
|
|
|
func routeWithExecutionOrchestration(cfg pluginConfig, req pluginapi.ModelRouteRequest, route string) pluginapi.ModelRouteResponse {
|
|
plans := executionPlansForRoute(cfg, req, route)
|
|
if len(plans) == 0 {
|
|
return pluginapi.ModelRouteResponse{Handled: false, Reason: "web_search_fallback_exhausted"}
|
|
}
|
|
return pluginapi.ModelRouteResponse{
|
|
Handled: true,
|
|
TargetKind: pluginapi.ModelRouteTargetSelf,
|
|
Reason: "claude_code_web_search_orchestrated",
|
|
}
|
|
}
|