Your stack
You are
Mostly building
Your edition
16 items
Relevant to you · Agents & coding tools
OpenAI
Agents SDK now available in TypeScript with sandbox support
5 May · OpenAI released a TypeScript version of their Agents SDK with sandboxed execution, letting you run agents in isolated environments safely.
Anthropic
Dreams managed agent now supports Claude Opus 5
1 Aug · Anthropic's Dreams managed agent now supports their latest Claude Opus 5 model, giving you access to improved reasoning and capabilities in autonomous workflows.
Set effort levels on managed agents to control compute allocation
21 Jul · Managed agents now let you tune how hard Claude thinks on each task, balancing speed against answer quality without changing the model.
Thread-level event streams now support delta previews
21 Jul · Subagent output now streams token-by-token at the thread level, matching session-level streaming for consistent real-time visibility.
Seed managed agent sessions with initial events to start work immediately
21 Jul · You can now bootstrap a managed agent session with context and goals in one call, eliminating a separate send-events request.
Claude Code
Background sessions now commit, push, and report work location
4 Aug · Unattended background jobs now properly persist their work to git and tell you where to find it, respecting your git preferences.
Permission checks for parallel tool calls now cache-efficient
4 Aug · Parallel tool permission checks are now cheaper and more reliable; switching modes mid-check no longer applies stale results.
Sandbox credential masking on Linux and WSL
4 Aug · Sandboxed code can now safely read credential files without exposing secrets to the sandbox; the agent masks values on egress while letting commands see what they need.
Claude Opus 5 becomes default model with 1M context
24 Jul · Claude Opus 5 replaces 4.7 as the default model, offering 1M context window and faster inference at new pricing. Existing sessions can switch via `/model`.
Also waiting
OpenAI
GPT-5.6 Luna and Terra pricing drops
30 Jul · OpenAI reduced inference costs for two GPT-5.6 variants, making Luna especially attractive for cost-conscious applications.
Fast mode replaces Priority Processing for GPT-5.6 Sol
30 Jul · OpenAI replaced its Priority Processing with Fast mode, delivering faster inference for Sol at higher cost with automatic backward compatibility.
GPT-5.6 Luna and Terra pricing reduced
30 Jul · OpenAI reduced inference costs on two GPT-5.6 variants, making Luna competitive for cost-sensitive applications and Terra more efficient overall.
Vercel AI SDK
Video generation now supports async polling and webhooks
3 Aug · Video models can now handle asynchronous completion via polling or webhooks instead of blocking, letting you integrate with workflow systems and handle timeouts gracefully.
streamText and ToolLoopAgent now support experimental tool callers
31 Jul · Tool callers—a new experimental pattern for invoking tools—are now supported in streaming contexts and agent loops, expanding how you can structure tool use.
generateText warns on streaming-only timeout settings
31 Jul · If you pass streaming-specific timeouts to generateText (which doesn't stream), you'll now get a warning to help catch config mistakes.
Telemetry now correctly attributes calls to their actual response model
31 Jul · When you call a model that gets routed or remapped to a different model internally, telemetry now credits the actual model that responded instead of the one you asked for.
172 more waiting. Each tool contributes four items an edition, use-case matches first — the rest come in a later edition rather than being dropped.
Built from entries already ingested and shaped by the same code that builds the email. Your real editions also skip anything you have already been sent.