evals: SDK runner default Opus -> Sonnet (D1a)

agent-sdk-runner defaulted to Opus 4.7 while session-runner (the claude
-p path) defaulted to Sonnet — an inconsistency between the two runners,
not a decision anyone made. Unpinned tests were implicitly asserting the
expensive model. The 30+ tests that genuinely need Opus already pin it
via opts.model. Re-baselined by the periodic run in this branch's final
verification; regressors get explicit Opus pins.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

test/helpers/agent-sdk-runner.ts

@@ -299,7 +299,10 @@ export async function runAgentSdkTest(
   const sem = getApiSemaphore();
   const maxRetries = opts.maxRetries ?? 3;
   const queryImpl: QueryProvider = opts.queryProvider ?? query;
-  const model = opts.model ?? 'claude-opus-4-7';
+  // Default matches session-runner's Sonnet (D1a, 2026-08): the old Opus
+  // default was an inconsistency between the two runners, not a choice —
+  // tests that need Opus pin it via opts.model (30+ already do).
+  const model = opts.model ?? 'claude-sonnet-4-6';
 
   // NOTE on env: the SDK child gets the COMPLETE hermetic env (allowlist
   // scrub + ANTHROPIC_API_KEY + hermetic CLAUDE_CONFIG_DIR/GSTACK_HOME), with

test/helpers/auq-sdk-capture.ts

@@ -191,7 +191,7 @@ This is a capture test, not an interactive session. Skip any system-audit / envi
     timeout: 240_000,
     testName: opts.testName,
     runId: opts.runId,
-    model: opts.model ?? 'claude-opus-4-7',
+    model: opts.model ?? 'claude-sonnet-4-6', // D1a: align with session-runner default; Opus is opt-in
   });
 
   try {
@@ -253,7 +253,7 @@ Rules for this run:
     timeout: opts.timeout ?? 300_000,
     testName: opts.testName,
     runId: opts.runId,
-    model: opts.model ?? 'claude-opus-4-7',
+    model: opts.model ?? 'claude-sonnet-4-6', // D1a: align with session-runner default; Opus is opt-in
   });
 
   const readSections = new Set<string>();
@@ -334,7 +334,7 @@ Write the verbatim text of that AskUserQuestion (the full decision brief: title,
     timeout: 240_000,
     testName: opts.testName,
     runId: opts.runId,
-    model: opts.model ?? 'claude-opus-4-7',
+    model: opts.model ?? 'claude-sonnet-4-6', // D1a: align with session-runner default; Opus is opt-in
   });
 
   try {