OpenAI’s Assistants API has shut down
The Assistants API shutdown date has passed. OpenAI’s deprecation documentation lists August 26, 2026 as the removal date and directs developers to Responses and Conversations for replacement workloads.
Find published research by company, product, platform or technology.
Showing 201–220 of 308 dossiers
The Assistants API shutdown date has passed. OpenAI’s deprecation documentation lists August 26, 2026 as the removal date and directs developers to Responses and Conversations for replacement workloads.
Railway now patches and redeploys affected workloads for known CVEs and refreshes dependent services after credential rotation—but only when those credentials use Railway variable references.
GitHub's multi-model coding orchestration is now GA, with admin-controlled model pools and per-model charges. Local routing remains experimental and cloud-dependent.
Self-hosted Coolify operators need to check their exact v4 branch: patched versions are 4.0.1, 4.1.3, 4.2.1, 4.3.24 and 4.4.7, but maintainers recommend 4.4.7 for fuller coverage.
16.4 fills gaps in the new navigation/caching model and adds ensureStatic checks, while preserving a separate migration path for existing routes.
The important shift is that agent orchestration itself becomes a managed API surface: context compaction, tool discovery, programmatic tool calls and subagent coordination can now come from OpenAI’s maintained Codex harness rather than an application team rebuilding those layers.
Vercel Agent now works in Slack as well as the Vercel dashboard, combining logs, metrics, deployments and repository context with team conversation before proposing approved actions such as pull requests, rollbacks, configuration changes and cache purges.
Fin Releases and Evals are now generally available across Intercom workspaces, giving support teams a repeatable preview, test and staged-rollout process for changing AI agent behaviour.
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.
Shopify partners are now represented by platform-verified project history rather than customer reviews. That changes discovery and credibility signals, particularly for smaller agencies.
Postmark’s new IP Allowlisting creates an extra sending boundary around API credentials: trusted infrastructure can send normally, while requests from outside configured ranges fail even if the token itself is valid. SMTP is not covered.
OpenSSH 10.6p2 and Alpine backports address a critical musl/no-PAM password bypass; operators must restart sshd after upgrading.
Computer Use is now GA in both Gemini APIs, but it is an action-planning tool, not a hosted remote desktop: clients execute clicks and keystrokes and must handle safety decisions.
A graph, an HTML Preview and a trusted virtual-keyboard message listener combined to bypass ChatGPT's iframe boundary. The fix is reported shipped, but the incident offers a practical warning to anyone embedding untrusted interactive content.
ChatGPT Ads' new default-on AI creative system can adapt ad copy and landing-page destinations using conversation context. Advertisers should audit account and campaign settings and ensure pages remain accurate.
Old third-party JavaScript includes can become a live supply-chain attack when their domains expire. DeadTag shows why removing abandoned tags and monitoring what scripts load is operational security, not housekeeping.
PostgreSQL Anonymizer 3.3 fixes a dozen privacy and privilege flaws. Its migration is unusually sensitive: no ALTER EXTENSION UPDATE, possible salt exposure, and new restrictions on masking functions.
GitHub Apps can now authenticate Copilot SDK workloads without a user's credentials. Organisation admins control installation permissions, usage attribution and budgets.
The coordinated Nix/Lix advisory now lists five CVE identifiers, three shared across Nix and Lix and two Nix-specific. The privilege-escalation and sandbox exposure, affected versions and operational patch guidance remain central.
Tailscale's new MagicRoute beta lets eligible organisations choose priority-based routes per client rather than regional grouping. It affects multi-region subnet access, service hosts and exit-node recommendations.