[proxy] Add e2e cover for the gateway protocol changes

The routing and parser-selection fixes touch every provider surface, and
the unit tests only prove each side of a seam in isolation. Two suites
close that:

The provider matrix drives one request per wire shape over a single tunnel,
with a record per catalog surface behind it, and asserts the surface each
request was metered under together with the token counts that surface's own
usage block carries. A response read by the wrong provider's parser meters
zero, so a regression fails instead of passing on a coincidental non-zero.
It also covers the Bedrock and Vertex token-counting paths, the warm-up
probe, and the vendor error envelope on a refusal.

The discovery suite covers the configuration that broke: an account with a
model allowlist, where the listing carries no model and the gate failed
closed. It asserts the listing is served, that it is bounded to the
authorised model, and that inference outside the allowlist is still
refused, so the exemption cannot be read as a way around the gate.

The mock upstream grows the Anthropic, Bedrock and token-counting shapes so
one container stands in for every surface, and the client gains GET and
arbitrary-POST helpers for the endpoints that carry no chat body.

e2e/harness/client.go

@@ -7,6 +7,7 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"net/http"
 	"os/exec"
 	"strconv"
 	"strings"
@@ -322,10 +323,29 @@ func withSessionID(headers []string, sessionID string) []string {
 	return append(headers, "x-session-id: "+sessionID)
 }
 
-// post runs curl in a throwaway container sharing the client's network
-// namespace so the request traverses the WireGuard tunnel, pinning the endpoint
-// to the proxy IP. It returns the HTTP status and response body.
+// Get issues a GET to the agent-network endpoint over the client's tunnel.
+// Model discovery and the connection-warming probe are read-only endpoints
+// that carry no body, so they can't go through the chat helpers.
+func (cl *Client) Get(ctx context.Context, endpoint, proxyIP, path string, extraHeaders []string) (int, string, error) {
+	return cl.do(ctx, http.MethodGet, endpoint, proxyIP, path, "", extraHeaders)
+}
+
+// PostJSON issues an arbitrary JSON POST over the client's tunnel, for wire
+// shapes the typed helpers don't cover (token counting, say).
+func (cl *Client) PostJSON(ctx context.Context, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) {
+	return cl.do(ctx, http.MethodPost, endpoint, proxyIP, path, body, extraHeaders)
+}
+
+// post issues a JSON POST. Retained as the shorthand the chat helpers use.
 func (cl *Client) post(ctx context.Context, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) {
+	return cl.do(ctx, http.MethodPost, endpoint, proxyIP, path, body, extraHeaders)
+}
+
+// do runs curl in a throwaway container sharing the client's network
+// namespace so the request traverses the WireGuard tunnel, pinning the endpoint
+// to the proxy IP. It returns the HTTP status and response body. An empty body
+// sends no payload, which is what a GET needs.
+func (cl *Client) do(ctx context.Context, method, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) {
 	url := "https://" + endpoint + path
 	args := []string{
 		"run", "--rm",
@@ -334,13 +354,15 @@ func (cl *Client) post(ctx context.Context, endpoint, proxyIP, path, body string
 		"-sk", "--connect-timeout", "5", "--max-time", "90",
 		"--resolve", endpoint + ":443:" + proxyIP,
 		"-o", "/dev/stderr", "-w", "%{http_code}",
-		"-X", "POST", url,
+		"-X", method, url,
 		"-H", "Content-Type: application/json",
 	}
 	for _, h := range extraHeaders {
 		args = append(args, "-H", h)
 	}
-	args = append(args, "--data", body)
+	if body != "" {
+		args = append(args, "--data", body)
+	}
 	cmd := exec.CommandContext(ctx, "docker", args...)
 	// -w writes the status code to stdout; -o /dev/stderr writes the body to
 	// stderr so we can capture both separately.

e2e/harness/vllm.go

@@ -22,14 +22,42 @@ const (
 	// matches a real small model commonly served by vLLM so the provider's
 	// enumerated model and the client's request line up.
 	VLLMModel = "Qwen/Qwen2.5-0.5B-Instruct"
+	// VLLMUnlistedModel is a second id the mock's model listing advertises but
+	// no test provider enumerates, so a filtered listing is observably shorter
+	// than the upstream's own.
+	VLLMUnlistedModel = "Qwen/Qwen2.5-7B-Instruct"
+)
+
+// Token counts the mock reports per wire shape. Tests assert on these rather
+// than on "> 0" so a response parsed with the wrong provider's parser (which
+// would read a different field, or none) fails loudly instead of passing on
+// a coincidental non-zero.
+const (
+	// VLLMChatInputTokens / VLLMChatOutputTokens ride the OpenAI usage block.
+	VLLMChatInputTokens  = 11
+	VLLMChatOutputTokens = 2
+	// VLLMMessagesInputTokens / VLLMMessagesOutputTokens ride the Anthropic
+	// usage block, whose field names the OpenAI parser cannot read.
+	VLLMMessagesInputTokens  = 17
+	VLLMMessagesOutputTokens = 3
 )
 
 // vllmNginxConf emulates a vLLM OpenAI-compatible server over plain HTTP (vLLM's
-// default: no TLS, port 8000). It answers /v1/models with a one-model list and
-// any chat/completions path with a canned OpenAI-shaped chat completion carrying
-// a non-zero usage block, so the proxy's OpenAI parser records real token
-// consumption. Running actual vLLM in CI is infeasible (GPU + multi-GB model
+// default: no TLS, port 8000), and additionally answers the wire shapes the
+// other catalog surfaces speak so one mock can stand in for every provider the
+// proxy routes to. Running actual vLLM in CI is infeasible (GPU + multi-GB model
 // download), so this stands in for the wire contract the proxy depends on.
+//
+// Each shape answers with its own vendor's usage block, so a response parsed
+// under the wrong surface meters zero rather than passing by accident:
+//
+//   - /v1/chat/completions (and any unmatched path): OpenAI chat completion.
+//   - /v1/messages: Anthropic Messages, snake_case usage plus a cache bucket.
+//   - /model/{id}/invoke: Bedrock InvokeModel, which carries the Anthropic body.
+//   - the token-counting endpoints: a count, with no usage block at all.
+//
+// The model listing advertises two models so a policy that authorises one
+// produces an observably shorter list than the upstream's own.
 const vllmNginxConf = `pid /tmp/nginx.pid;
 events {}
 http {
@@ -37,7 +65,26 @@ http {
     listen 8000;
     location = /v1/models {
       default_type application/json;
-      return 200 '{"object":"list","data":[{"id":"Qwen/Qwen2.5-0.5B-Instruct","object":"model","owned_by":"vllm"}]}';
+      return 200 '{"object":"list","data":[{"id":"Qwen/Qwen2.5-0.5B-Instruct","object":"model","owned_by":"vllm"},{"id":"Qwen/Qwen2.5-7B-Instruct","object":"model","owned_by":"vllm"}]}';
+    }
+    location = /v1/messages {
+      default_type application/json;
+      return 200 '{"id":"msg_e2e","type":"message","role":"assistant","model":"claude-sonnet-5","content":[{"type":"text","text":"pong"}],"stop_reason":"end_turn","usage":{"input_tokens":17,"output_tokens":3,"cache_read_input_tokens":5}}';
+    }
+    location = /v1/messages/count_tokens {
+      default_type application/json;
+      return 200 '{"input_tokens":7}';
+    }
+    location ~ ^/model/.+/invoke$ {
+      default_type application/json;
+      return 200 '{"id":"msg_e2e_bedrock","type":"message","role":"assistant","content":[{"type":"text","text":"pong"}],"stop_reason":"end_turn","usage":{"input_tokens":17,"output_tokens":3,"cache_read_input_tokens":5}}';
+    }
+    location ~ ^/model/.+/count-tokens$ {
+      default_type application/json;
+      return 200 '{"inputTokens":9}';
+    }
+    location = /api/hello {
+      return 200;
     }
     location / {
       default_type application/json;