849 this month · 169 companies
A quiet day; the week: Databricks Data Intelligence Platform will retire DeepSeek V4 Flash (0731) on November 5, 2026. Google Cloud Gemini API deprecated deep-research-pro-preview-12-2025 with a shutdown on October 23, 2026, alongside gemini-3.7-flash, gemini-3.5-flash, and 1 other. CircleCI scheduled the retirement of ten legacy v1 and v1.1 Trigger and Rerun API endpoints for February 1, 2027. Anthropic Claude Platform reduced prompt cache read pricing on Claude Sonnet 5.5 to lower deployment expenses.
You can now use SQL to register, modify, and remove named workload identities for a service user. Each workload identity has its own name and provider settings. A user can have up to 10 workload identities by default.
Feature iwork: Read pictures placed on a Numbers sheet (88fbc05) Fix docx: Emit textboxes in table cells once inside their cell (6bc5770) jats: Parse ordered lists and list item labels (ad2e0e1) mlx: Pass the sampling temperature as temperature to mlx-vlm (fb0818e) odf: Move hidden ODP slides to the invisible content layer (807f6df) pptx: Move hidden shapes...
20.21.0 (2026-10-11) Features assign a random gradient to projects created by ingestion (8946f7a) cost-tracking: support Mistral AI model pricing (0e33736), closes #16878 Bug Fixes agents: upgrade pydantic-ai for CVE-2026-107286 (3cdb004) deps: update arize-phoenix-evals to 3.9.2 (e8aa1ea) playground: sync built-in model prices and model lists (35f86e5)...
MySQL 8.0.46 is now the default minor version for Cloud SQL for MySQL 8.0. For more information about minor version support in Cloud SQL for MySQL, see MySQL 8.0 .
This update brings more control over default models and MCP server in GitHub Copilot for JetBrains. It also makes diagnostics easier to address, improves chat navigation and account controls, and strengthens reliability across agent sessions, customizations, and worktrees.
The Cloudflare API MCP server now serves Cloudflare skills ↗︎ through the Skills over MCP extension ↗︎ . MCP clients that support the extension discover the skills with skills/list and read their files at skill://<name>/<path> . To use them, add https://mcp.cloudflare.com/mcp to an MCP client that supports the extension ↗︎ .
The BigQuery Data Engineering Agent is now available in the asia-northeast1 (Tokyo) regional endpoint and supports the gemini-3.5-flash model. For more information, see Where Gemini in BigQuery processes your data . This feature is Generally Available (GA).
Now available in preview , Conversational Analytics agentic workflows support scheduled agentic workflows in addition to triggered agentic workflows . You can use scheduled agentic workflows to schedule recurring deliveries of AI-generated insights summaries, data tables, visualizations, and PDF reports to email or Slack by using natural language.
When you enable Knowledge Catalog (formerly Dataplex Universal Catalog) integration on an eligible Cloud SQL for MySQL instance created before April 18, 2026 where the integration is currently turned off, the instance now syncs schema and metadata updates to Knowledge Catalog in near real-time instead of once a day (instances created on or after April 18...
The Catalog API now returns a merchant’s compare-at price as list_price on each product variant. Your app or agent can use list_price to tell when a product is marked down and by how much. The price field doesn’t change. No action is required. list_price is an optional field defined in the UCP catalog specification, version 2026-08-25 .
Deployment Storage and Functions Storage billing will begin for all Pro teams at $0.10 per GB-month. Check your email for details about when billing will start for your team. To keep storage costs low, the deployment retention window also changes to 30 days.
Liquid d1 is now available on AI Gateway . d1 is a decision model that evaluates shared state against typed questions for classification, routing, and scoring. It returns structured answers with probabilities without generating text tokens.
With this release, the Snowsight interface for tags and data protection policies is generally available. These areas require Enterprise Edition or higher .
Agentic Marketplace Discovery is now available in public preview. On the public Snowflake Marketplace Discover page in Snowsight, you can switch between Agentic discovery and Marketplace search . Describe what you need to CoCo to find and compare matching listings, or search for providers and listings directly.
This week’s updates make Copilot easier to use across accounts and environments, with more control over what agents can access and how you manage their work. GitHub Copilot Claude Haiku 5.5 is available to Copilot Pro, Pro+, Max, Business, and Enterprise users.
CodeQL 2.27.2 is now available, adding a C++ regular-expression parser and analysis improvements across several languages. CodeQL is the static analysis engine behind GitHub code scanning, which helps you find and remediate security issues in your code. The Default suite runs 498 security queries covering 170 CWEs.
You can now let a Claude Managed Agents agent use dynamic workflows, in beta with the managed-agents-2026-04-01 beta header. For work with many pieces, such as reviewing hundreds of documents, the agent can write a workflow. A workflow is a program that runs many agents in phases and combines their results.
We are excited to announce that __Access Token Scope Customization for Actions is now Generally Available__, and with this release we are __extending support to Post Login Actions__. Credentials Exchange Actions, which had these interfaces in Early Access, are now GA as well.
Starting today, you can upload brand templates in Amazon Quick, allowing you to create presentations and documents that match your approved visual identity. Brand managers set up a template once and everyone gets on-brand output, without hunting for the right file in each chat.
DigitalOcean MicroVMs are available in public preview in MKC1. MicroVMs are lightweight virtual machines that run a container image in its own kernel, pause automatically when idle, and resume on the next request with memory, files, and …
Genie One can now run code in a secure, isolated sandbox to take on work that goes beyond SQL, such as more advanced analyses. Code runs on your behalf using your existing permissions, so Unity Catalog governance and data access controls continue to apply. See Code execution in Genie One .
You can now select OpenJev (Qwen3.5 4B) as the evaluator model service of a custom LLM-as-a-judge service policy. OpenJev classifies content without generating output tokens, so it typically responds faster than a chat evaluator. See Use OpenJev as the evaluator .
The managed Google Workspace connector is now available in Beta in Databricks Lakeflow Connect. Use the connector to ingest audit activity from Google Workspace applications and services into Databricks. The connector uses OAuth user authorization and supports incremental ingestion.
All AI Gateway models now available with prepaid credits. You don't need to request access to frontier models in the Neon AI Gateway anymore. If you're on a pai...
The JavaScript SDKs now trace more AI frameworks, providers, and classifiers across Node.js, Bun, Cloudflare, and Deno, with more consistent data in traces.
Different readers need different things from a report. An executive may want clean pages that put the panels first, while a client expects your branding and page numbers throughout. Custom PDF headers and footers let you shape your reports around the people who read them.
Voice Insights now tags calls as HD Audio when they connect with the AMR-WB or Opus codec. Use the tag to confirm your endpoints negotiated what you configured, and to correlate HD usage with transcription accuracy, AI agent performance, and customer satisfaction.
Identity and Access Management now supports Identity Assertion JWT Authorization Grant (ID-JAG) token exchange. An ID-JAG is a short-lived, signed JSON Web Token (JWT) that enables identity handoff across trust domains. A source identity domain exchanges an ID token for an ID-JAG.
Cloudflare has improved how it handles and reports client-cancelled HTTP/3 requests across Free, Pro, Business, and Enterprise plans. Customers now get a clearer view of client behavior in Cloudflare analytics and, where available, logs. Previously, Cloudflare did not always stop an HTTP/3 request when the client cancelled its request stream.
AI Assistant in build mode: new capabilities In workbooks, Sigma Assistant in build mode now supports the following: Dynamic dashboard layouts : Design dashboards that default to a dynamic layout featuring a prominent hero chart or KPI alongside other elements of varied widths and height.
The PlanetScale MCP server can now check your database's metrics. planetscale_get_branch_metrics pulls CPU, memory, disk, replication lag, and connections into your AI assistant, so you can see those numbers without leaving your editor. It works for Vitess, Postgres, and Neki.
We just finished planning last week and the features will keep coming until morale improves. We hear that many of you want to bring more and more of your coding subscriptions into Railway and we have just that and more. Anyway, hold your laughter, these features are no joke.
Buildkite shipped 40 releases. Three themes. Diagnosis. Agents put blocking failures first and retry infrastructure failures. Desktop alerts and log summaries are more reliable. Compatibility. GitHub Actions workflows get hashFiles() in composite actions, Windows checkout fixes, and retries for temporary token failures. Control.
Keys now use permission presets instead of the ADMIN and API scopes. When you create a key, select one of seven presets: API , SERVERLESS , DEPLOY , COMPUTE , BILLING , READONLY , or FULL . If no preset matches your case, select the exact permissions the key needs. You can also limit a key to specific models and set it to expire.
Release Notes Released on 2026-10-09. The executables in our macOS and Windows release archives and ruff wheels are now code-signed. macOS executables are signed with an Apple Developer ID certificate and notarized by Apple. Windows executables have timestamped Authenticode signatures from Azure Artifact Signing.
Release Notes Released on 2026-10-09. uv 0.13.0 makes Python 3.15 the default stable Python version. We've also included several breaking changes to improve correctness, performance, and compatibility, described below. We expect most users to be able to upgrade without making changes.
Features - feat(web): design-system CodeSection replaces CodeView - feat(sessions): Add syntax highlighting to session tool previews - feat(billing): send spend alerts for ClickHouse-billed organizations - feat(web): ask new users what they will use Langfuse for - feat(topics): add adaptive map exploration and compact workspace - feat(evals): revamp...
prime-agent 0.10.0
For installation instructions check out the getting started guide. Added sftp: SFTP credentials now support an advanced opt-in block to enable additional SSH key exchange algorithms, ciphers, and MACs beyond the x/crypto/ssh defaults.
Minor release off the new release-1.5.x branch. 108 commits since v1.4.0. Breaking changes Serve conversations and prompts with responses, or when explicitly listed An explicit apis: list is now authoritative, even when empty Raise the FastAPI floor to 0.137.2 and drop legacy route collection Allow an empty choices list in the OpenAI legacy completions...
Minor Changes b52cd30: Add mode: 'full' | 'filesystem' (exported as the SnapshotMode type) to createSnapshot / create_snapshot. With 'filesystem', only the filesystem is persisted: the snapshot is smaller and faster to take, and sandboxes created from it cold-boot (start fresh from disk) instead of restoring memory.
20.20.0 (2026-10-08) Features harbor: prompt hill-climb task on a text-to-SQL dataset (bd78550) mcp/sql: allowlist the annotation, evaluator, prompt, split and job tables (a37b841) mcp: add GraphQL schema, query, and mutation tools (9351580) playground: add claude-haiku-5-5 and remove retired Anthropic models (b978e7c) pxi: make PXI's MCP code mode...
gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. All requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash) and review the Gemini 3.6 Flash guide.
A preview release of OCI Kubernetes Engine now provides support for Kubernetes version 1.37.0 for early access testing and validation purposes. This preview release is not intended for production workloads, is only available in the OC1 realm, and might contain issues without known workarounds.
The Compliance API can now download Claude Docs documents as Word files, in beta. See Retrieve files and artifacts.
Stable egress IP addresses are now generally available on Azure and are no longer in Preview . You can generate Snowflake egress IP address ranges (as CIDR addresses) and add them to an external server's allowlist so that Snowflake can make requests to that server.
This release adds new billing and license controls for Copilot code review admins: Billing: Organization owners can bill Copilot code reviews from members with a Copilot license to the organization’s cost center instead of using up those members’ Copilot quotas.
Maintainers are seeing more low-quality contributions in their repositories and need better ways to manage them. You can now configure pull request limits to also include draft pull requests. Previously, draft pull requests didn’t count toward a user’s limit.
File upload in Genie One now supports plaintext files, including text ( .txt ) and Markdown ( .md ) files, in addition to CSV, Excel, PDF, image, Word, and PowerPoint files. See Upload a file .
The Discover page and domains are now generally available. Discover is a curated browsing experience that helps users find assets across Databricks without requiring deep knowledge of catalog hierarchies.
Stacked pull requests are now displayed in Linear Diffs. Move through a stack and see review, CI, and merge status at a glance. Related PRs are grouped into a single collapsible row in Reviews, alongside their issue and project context. For GitHub-native stacks, you can preview every affected PR before merging the current PR and those below from Linear.
Step 5 Preview , StepFun's flagship model, is now available on AI Gateway . It's built for agentic coding, professional knowledge work, and financial analysis, from building apps and debugging code to research and analytical reports.
You can now skip sending client request bodies to Routing Middleware with skipMiddlewareRequestBody . This reduces incoming Fast Origin Transfer usage for middleware invocations and can improve time to first byte, especially for requests with large bodies. Enable this option only if your Routing Middleware doesn’t read request bodies.
Grafana Cloud Synthetic Monitoring now integrates with the knowledge graph, available in public preview. When a check fails or slows down, you can see the service it monitors, explore its dependencies, and compare check results with service health to narrow down where to investigate. Synthetic checks show how your application behaves from the outside.
The integration between Microsoft Agent 365 and Azure API Management is now available in public preview, helping organizations connect centralized governance with runtime enforcement for MCP servers and tools.With this integration, organizations can:Disco
Now you can deploy Azure Database for PostgreSQL flexible server in the East US 3 Azure region. Learn more.
Configure monitoring and alerts for device posture (beta) to help admins and end-users diagnose connectivity problems caused by failing posture. New: Badges can be shown on the Machines page of the admin console when a device is failing a posture (beta) . New: The Failing Posture filter on the Machines page shows devices that are failing selected postures.
Prompt caching for DigitalOcean-hosted models is now in general availability. All DigitalOcean-hosted models cache context automatically, with no code changes and no cache-write charge. Cache affinity routes requests with matching prefixes …
Performance Risks Inbox is GA Performance Risks Inbox is now generally available (GA). It finds the performance anti-patterns that quietly slow your application down, such as N+1 queries and inefficient database calls, and groups them in one place so your team can fix them before they become incidents.
Releasesby Ibis
Shopify
AWS