fix(antigravity): opus 4.6 forward-compat model + thinking signature sanitization bypass (#14218)

Two fixes for Google Antigravity (Cloud Code Assist) reliability:

1. Forward-compat model fallback: pi-ai's model registry doesn't include
   claude-opus-4-6-thinking. Add resolveAntigravityOpus46ForwardCompatModel()
   that clones the opus-4-5 template so the correct api ("google-gemini-cli")
   and baseUrl are preserved. Fixes #13765.

2. Fix thinking.signature rejection: The API returns Claude thinking blocks
   without signatures, then rejects them on replay. The existing sanitizer
   strips unsigned blocks, but the orphaned-user-message path in attempt.ts
   bypassed it by reading directly from disk. Now applies
   sanitizeAntigravityThinkingBlocks at that code path.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/agents/pi-embedded-runner/run/attempt.ts

@@ -67,6 +67,7 @@ import { buildEmbeddedExtensionPaths } from "../extensions.js";
 import { applyExtraParamsToAgent } from "../extra-params.js";
 import {
   logToolSchemasForGoogle,
+  sanitizeAntigravityThinkingBlocks,
   sanitizeSessionHistory,
   sanitizeToolsForGoogle,
 } from "../google.js";
@@ -770,7 +771,10 @@ export async function runEmbeddedAttempt(
             sessionManager.resetLeaf();
           }
           const sessionContext = sessionManager.buildSessionContext();
-          activeSession.agent.replaceMessages(sessionContext.messages);
+          const sanitizedOrphan = transcriptPolicy.normalizeAntigravityThinkingBlocks
+            ? sanitizeAntigravityThinkingBlocks(sessionContext.messages)
+            : sessionContext.messages;
+          activeSession.agent.replaceMessages(sanitizedOrphan);
           log.warn(
             `Removed orphaned user message to prevent consecutive user turns. ` +
               `runId=${params.runId} sessionId=${params.sessionId}`,