Docker’s new agent stack combines pay-as-you-go microVM sandboxes with an OCI-based Kit format for declaring what an agent can use. Cloud sessions cost from $0.07 to $1.12 an hour, and Docker says it plans to take the Kit specification toward CNCF neutral governance.
The new AWS–Azure pairing is less about raw bandwidth than an operational boundary shift: each cloud provider now manages its side of the private cross-cloud connection, with prebuilt capacity and native provisioning instead of a bespoke interconnect stack.
SnapStart previously covered only selected managed runtimes; extending it to container images changes the latency-versus-packaging trade-off for teams shipping large dependencies or standard container bases, with regional exclusions and runtime-specific guidance still applying.
Memory-bound agents, retrieval systems and stateful services can now choose 2-, 4-, 8- and 12-CPU Render plans with much wider RAM ratios. Existing plan prices and legacy IDs stay compatible; the new choices change the cost trade-off for workloads that previously had to overbuy CPU to get enough memory.
Google’s September Search changes now form a broader migration story: legacy campaign-level Broad Match and standalone Automatically Created Assets settings will be converted into AI Max, while language targeting stops affecting Search delivery and related API mutations begin failing.
Eligible API organisation owners can now enable per-request data residency on a new Global project without a separate Zero Data Retention application. Regional endpoints remain subject to support and pricing restrictions.
The September inventory launch remains available, but the original REST list/get operations are marked for removal. Builders should start an export, poll its ID and validate the completed CSV rather than rely on cursor pagination or treat HTTP 202 as a finished inventory.
Vite's GHSA-p4f5-76q4-ffq7 affects network-exposed dev servers through unescaped virtual-module IDs. Patches span Vite 6–8, while older 4/5 users need a migration.
HTTP/3 QPACK decompression can exhaust server memory when decoded headers lack limits. Bun's 1.4.4 fix is confirmed; check exact runtime and bundled library versions.
Google’s Search generative AI setting separates AI-answer visibility from ordinary Search indexing and model-training preferences, with inherited settings and lost AI referrals to consider.
The JavaScript micro-app platform is winding down after four years. Billing has stopped, official migration guides are available, and open-sourcing is planned for February.
Demand Gen automation that writes target_content_network=false will fail after the migration. Google is moving the opt-out to ad groups and will backfill existing campaigns.
Modern Web Guidance 1.0 adds Baseline-aware agent skills and a limited legacy scanner. Independent tests show useful fixes alongside substantial blind spots and higher agent costs.
XChat now has a second address layer beyond the public @handle: a shareable, revocable code that can grant direct inbox access without opening message requests to everyone.
A previously preparatory compliance field is now an operative delivery gate. Builders automating Toll-Free onboarding need to collect, validate and submit policy URLs as part of registration rather than treating them as optional metadata.
Redis-compatible cache and queue costs have fallen across Render's 1GB-plus Key Value plans, with two new memory tiers and automatic repricing for existing customers.
Search Console now separates both generative-AI visibility and multimodal image-led searches, giving publishers a clearer first-party view of how content is discovered outside conventional typed queries.