C# SDK: multi-server interceptor chain orchestration per SEP (#18)
Addresses the third item of #15 ("Chain orchestrator only supports one MCP server"). > **Stacked on #17** — this PR targets that branch because it builds on the per-phase `PriorityHint` resolution introduced there. After #17 merges, the base will be switched to `main` (or it can be retargeted now and rebased). ## What changed The SEP's chain execution pattern requires: discover via `interceptors/list` on one or more servers → merge & sort all interceptors into a single chain by `priorityHint` (ascending, alphabetical tie-break) → invoke each interceptor on the server that hosts it (mutations sequential with payload chaining, validations parallel) → aggregate one result. The SDK previously ran each client's entire chain sequentially, so a `-1000` mutation on server 2 ran after a `+1000` mutation on server 1, and each server's validations only saw its own server's mutations. - **Orchestrator** (`InterceptorChainOrchestrator`, internal): now operates on chain entries — descriptor + invoker routing to its host — mirroring the SEP's `ChainEntry`, with one global sort across all filtered entries. The stable sort preserves caller-supplied server order for exact ties. - **New public API** (`InterceptorChain` / `InterceptorChainEntry`): `DiscoverAsync` lists from every server in parallel (fail-closed: any list failure throws rather than silently dropping a server's interceptors), instance `ExecuteAsync` runs prebuilt entries (a future caching seam), and a one-shot static `ExecuteAsync(servers, params)` does discover + execute. - **`InterceptorChainRunner`** (used by the gateway and `InterceptingMcpClient`): one merged chain instead of the per-client sequential loop. The single-client `client.ExecuteChainAsync(...)` extension keeps its signature and delegates to the same path (still 1 list + N invokes). - Duplicate interceptor names across servers are not deduplicated — each entry invokes on its own host (results may share an `InterceptorName`; documented). ## Behavior changes for multi-client gateways - Interceptors from all servers form one globally-ordered chain (previously server 1's full chain ran before server 2's). - Validations from all servers run as one parallel batch against the payload after **all** mutations. - Sinks run once per phase for the merged chain (previously once per client). - `TimeoutMs` bounds the whole merged chain, not each per-client sub-chain. - Any server's `interceptors/list` failure fails the chain up-front (fail-closed). - Cost per phase: M parallel `interceptors/list` calls + N `interceptor/invoke` calls. ## Testing `dotnet test` from `csharp/sdk/`: 97 passing (was 87 after #17). New coverage: - Orchestrator: global priority ordering across servers, alphabetical tie-break across servers, payload chaining across servers in one mutation pass, all-server validations seeing the post-mutation payload, duplicate names invoking once per host. - `InterceptorChainTests` (real in-memory servers): discovery merge with server attribution, merged execution order, fail-closed discovery, single-client path equivalence. - Gateway: two interceptor servers where the second hosts the lower-priority mutation — the backend receives the globally-ordered payload (fails under the old sequential runner). Closes #15. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
This commit is contained in:
parent
7cf90c9ccb
commit
28ada74189
1 changed files with 700 additions and 77 deletions
|
|
@ -6,7 +6,7 @@ C# implementation of gateway-level interceptors from [SEP-2624](https://github.c
|
|||
## Build & test
|
||||
```
|
||||
dotnet build # from csharp/sdk/
|
||||
dotnet test # 87 tests across the interceptor test project
|
||||
dotnet test # 98 tests across the interceptor test project
|
||||
```
|
||||
|
||||
## Key architectural constraints
|
||||
|
|
@ -55,7 +55,7 @@ Interceptor methods auto-bind from `InvokeInterceptorRequestParams`:
|
|||
|
||||
**`McpInterceptorGateway`**: Configures an `McpServer` as a transparent proxy. Reads backend `ServerCapabilities`, registers handler delegates (`CallToolHandler`, `ListToolsHandler`, etc.) that route through interceptor chains before forwarding to the backend. By default the gateway is transparent-only; SEP passthrough is opt-in via `ExposeInterceptorProtocol = true`. To connecting clients, the proxy appears to be the backend server.
|
||||
|
||||
**`InterceptorChainRunner`** (internal): Shared interception logic used by both `InterceptingMcpClient` and `McpInterceptorGateway`. Supports multiple interceptor clients executed sequentially — each client's `ExecuteChainAsync` (SDK-level orchestration via list + invoke) receives the mutated payload from the previous one.
|
||||
**`InterceptorChainRunner`** (internal): Shared interception logic used by both `InterceptingMcpClient` and `McpInterceptorGateway`. Multiple interceptor clients form a single merged chain per the SEP: interceptors discovered from every client (parallel `interceptors/list`, fail-closed) are sorted globally by priority hint (alphabetical tie-break) and each is invoked on the client hosting it. Public API: `Client/InterceptorChain.cs` (`DiscoverAsync` + `ExecuteAsync` over `IEnumerable<McpClient>`); duplicate names across servers are not deduplicated.
|
||||
|
||||
**Gateway split**: `GatewayProxyConfigurator` owns transparent MCP proxy wiring, `GatewayInterceptorProtocolBridge` owns optional SEP passthrough wiring, and `GatewayConnectionForwardingRegistrar` owns connection-bound notification forwarding registration.
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue