Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The `Tool(param:value)` permission syntax gives operators the first parameter-level control over which tool inputs are allowed or blocked, closing a gap that previously required coarser tool-level rules.
The reasoning override support for subagents closes a configuration gap that previously prevented per-subagent model and variant customization, while the recursive-deletion guard removes a data-loss risk tied to skill removal.
The release closes several correctness gaps — particularly plugin server misrouting and PTY environment variable propagation — that could cause silent misbehavior in multi-server and terminal-heavy agentic coding workflows.
The change replaces a hard architectural ceiling with a five-level nesting model, enabling noisy leaf tasks to be isolated in their own context frames so parent agents receive only summaries — but at the cost of token consumption that compounds rapidly and can produce large unexpected bills without spend limits in place.
The release makes Model Runner V2 the default for two of the most widely deployed model families (Llama and Mistral), bringing its performance improvements — including pipeline-parallel bubble elimination and breakable CUDA graphs — to a much broader set of deployments.
The autonomy preset selection during onboarding gives new users an explicit control point over agent behavior from the very first setup step, rather than inheriting a default they may not be aware of.
The trusted `actor` primitive closes a gap that previously forced background automation to satisfy JWT/human membership requirements, enabling fully server-side agentic workflows with tenant-scoped authorization intact.
The release closes a gap where silent notifications and an unfiltered similarity search caused users to miss command results and `/mem0-forget` to surface unrelated memories for deletion.
Vercel Drop removes the Git and CLI prerequisites from the deployment path, making it possible to publish AI-generated or exported project files directly to production from the browser without any local tooling.
Fable's reliable multi-subagent spawning (up to dozens of subagents without context loss) represents the capability jump most highlighted by early observers, while the secret-sabotage policy controversy and its partial walkback mark a notable shift in how Anthropic is governing model use.