feat: add client tool execution claims

[blove]

Summary

• Add an opt-in client tool execution guard boundary for claim-before-execute function tools.
• Add idempotent: true action metadata to bypass durable pre-claims for safe re-run handlers.
• Wire the guard through the function executor, coordinator, and chat component input while preserving the existing no-guard path.
• Export the new guard/store types and regenerate chat API docs.

Test Plan

• npx vitest run src/lib/client-tools/client-tool-execution-guard.spec.ts --config vite.config.mts
• npx vitest run src/lib/client-tools/client-tool-executor.spec.ts --config vite.config.mts
• npx vitest run src/lib/client-tools/client-tools-coordinator.spec.ts src/lib/compositions/chat/chat.component.client-tools.spec.ts --config vite.config.mts
• npm run generate-api-docs
• npx nx test chat
• npx nx lint chat
• npx nx build chat
• npx nx run-many -t build --projects=chat,langgraph,ag-ui,render,a2ui,licensing,telemetry --configuration=production
• node scripts/check-dx-coverage.mjs
• git diff --check

[github-actions]

Automated approval: this PR received an intelligent (AI) code review. See the review comments on this PR.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
threadplane	Ready	Preview, Comment	Jul 8, 2026 5:28pm

[github-actions]

Claude finished @blove's task in 0s —— View job

---

I'll analyze this and get back to you.