fix(tests): retire dead model ids from the chat-pipeline integration suite (base-red #12581)

Three integration failures, one cause: the suite still routes two model
ids the vendor lifecycle registry marks `retired`, so the pipeline
correctly refuses them and the tests assert on the refusal.

  ❌ persists Codex responses cache and reasoning tokens → 410 !== 200
     "codex/gpt-5.1-codex" — retired 2026-07-23, successor gpt-5.6-sol
  ❌ translates OpenAI requests to Claude              → 410 !== 200
  ❌ falls back across combo models                    → 502 !== 200
     both on "claude/claude-3-5-sonnet-20241022" — the combo case fails
     with 502 because the retired id is its fallback target

Only the first reaches the release-green report, which prints the first
failing line, so the other two were invisible. All three had been hidden
for longer than that: the integration gate has been dying on its 2400s
ceiling, and a gate killed by its ceiling never reports an individual
test failure.

Replaces both with live ids — the successor named by the lifecycle record
for the Codex one, and the `claude-sonnet-4-6` this same file already
uses elsewhere for the Claude one. `buildOpenAIResponsesSSE` also echoed
the retired Codex id, and the call log derives its provider from the
model in the response, so leaving it made the row log `provider:
"openai"` for a request that correctly used the codex connection.

No assertion is changed or relaxed. Verified with the CI invocation
(setupPolyfill + isolateDataDir + --test-concurrency=1): 28/28 pass,
exit 0, from 25/28 before.

tests/integration/chat-pipeline.test.ts

@@ -170,7 +170,7 @@ function buildOpenAIToolCallResponse({
   );
 }
 
-function buildClaudeResponse(text = "ok", model = "claude-3-5-sonnet-20241022") {
+function buildClaudeResponse(text = "ok", model = "claude-sonnet-4-6") {
   return new Response(
     JSON.stringify({
       id: "msg_json",
@@ -286,7 +286,7 @@ function buildOpenAIStreamResponse(text = "streamed from openai") {
 
 function buildOpenAIResponsesSSE({
   text = "responses streamed from codex",
-  model = "gpt-5.1-codex",
+  model = "gpt-5.6-sol",
   usage = null,
 } = {}) {
   return new Response(
@@ -567,7 +567,7 @@ test("chat pipeline persists Codex responses cache and reasoning tokens to call
     buildRequest({
       url: "http://localhost/v1/responses",
       body: {
-        model: "codex/gpt-5.1-codex",
+        model: "codex/gpt-5.6-sol",
         stream: false,
         input: "Persist cache + reasoning usage",
       },
@@ -983,7 +983,7 @@ test("chat pipeline translates OpenAI requests to Claude and returns OpenAI-shap
   const response = await handleChat(
     buildRequest({
       body: {
-        model: "claude/claude-3-5-sonnet-20241022",
+        model: "claude/claude-sonnet-4-6",
         stream: false,
         messages: [{ role: "user", content: "Hello Claude" }],
       },
@@ -1566,7 +1566,7 @@ test("chat pipeline falls back across combo models when the first provider fails
     name: "combo-fallback",
     strategy: "priority",
     config: { maxRetries: 0, retryDelayMs: 0 },
-    models: ["openai/gpt-4o-mini", "claude/claude-3-5-sonnet-20241022"],
+    models: ["openai/gpt-4o-mini", "claude/claude-sonnet-4-6"],
   });
   const attempts = [];