> ## Documentation Index > Fetch the complete documentation index at: https://wb-21fd5541-new-articles-log.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # New articles > A weekly log of new articles published to the W&B documentation site. This page lists new articles as they are published to the W\&B documentation site, with the newest articles at the top. It is updated automatically every Friday. Articles published in previous years are collapsed under a heading for that year. Within each month, articles are grouped by the part of the documentation they belong to, such as **Models**, **Weave**, or **Support**. Auto-generated reference pages and localized content are not included. {/* new-articles:start */} ## July 2026 ### Models Track, version, and manage your AI prompts in the W\&B Registry by linking Weave prompt objects to a collection. When you create an Eval Table, specify which columns contain inputs, outputs, and scores. Learn how to create an Eval Table in W\&B. Use Eval Tables to compare inputs, outputs, and scores across multiple runs. Learn how to create, compare, and visualize Eval Tables in W\&B. ### Weave Visually compare two or more evaluations to spot regressions, improvements, and scoring differences across runs Render images and video that live in your own cloud bucket in Weave traces by logging their URIs, without importing the bytes into Weave. Render images and video that live in your own cloud bucket in the Weave Agents view by returning their URIs from agent tool spans, without importing the bytes into Weave. Keep only a share of incoming traces to control storage and LLM scoring costs on a self-managed Weave instance Trace Amazon Bedrock Agents invocations with Weave, capturing agent inputs, foundation model usage, and completion output. ## June 2026 ### Models Explore and compare local W\&B runs from the terminal with the LEET (Lightweight Experiment Exploration Tool) TUI. ### Weave Use W\&B Weave's Agents view to understand what your agent did, how much it cost, and exactly where things went right or wrong. Use Weave's sub-agent span to trace sub-agent delegations and view nested agent invocations. Use the Weave SDK to instrument multi-turn agentic applications and view them in the Agents tab. Manually log agent traces for frameworks that have already completed the LLM call and need to record it. Trace Pi agentic sessions, LLM calls, and tool executions in Weave. Track OpenClaw agent sessions in W\&B Weave for observability and debugging. Trace an agent built with the OpenAI Agents SDK using Weave. Trace an agent built with Google's Agent Development Kit (ADK) using Weave. Trace Codex agentic sessions, LLM calls, and tool executions in W\&B Weave. Track Claude Code sessions in W\&B Weave for observability and debugging. Trace an agent built with the Claude Agent SDK using Weave. ### ARIA ARIA, W\&B's AI Research and Iteration Agent, is your personalized research assistant that helps you analyze and run experiments, explain results, identify patterns across runs, recommend next steps, build visualizations and reports, and more in W\&B. Learn how W\&B Admins can control how your organization's data is used by W\&B's AI features like ARIA. The following page describes how to start a new chat, view your chat history, delete previous conversations, undock the chat window, reference a specific run in your prompt, add an image to a conversation, and provide feedback on ARIA's responses. Learn how to use ARIA, W\&B's AI Research and Iteration Agent, to analyze results and run experiments. ### HiveMind A shared dashboard for AI coding sessions. Track activity, spend, and outcomes across Claude Code, Cursor, Codex, Gemini CLI, and more with leaderboards, team views, and efficiency insights. ### Support Weave displays cost and token usage estimates based on data captured from your LLM calls, and discrepancies between Weave's numbers and your provider's invoice can be caused by the following issues. Slow wandb.init() or sluggish metric uploads are usually caused by network latency, large media payloads, high logging frequency, or slow startup of the W\&B service process. If your sweep agent starts but does not receive new run configurations, or receives one run and then idles, there are several common causes. W\&B marks a run as Crashed when it stops receiving heartbeats from the process that called wandb.init(), without the process having called wandb.finish(). W\&B captures your script's stdout and stderr and stores it as output.log on the run's Files tab. W\&B now issues longer API keys (about 86 characters). Workspace layout (panels, filters, grouping) persists only when you save a view. If metrics logged with wandb.log() are not appearing in the W\&B UI, there are several common causes. When you sign up for W\&B, the platform automatically creates a personal team with the same name as your username. W\&B has no JAX-specific integration. The parallel coordinates chart shows how hyperparameters relate to metrics across many runs. After a run finishes, use the Public API guide to edit config, display name, tags, and notes without re-running the experiment. You can set up alerts in and notifications using the W\&B Settings page. You can page through API result using the standard lazy-iterator pattern and perpage parameter. You can log corpus-level NLP scores (BLEU, ROUGE, perplexity) with wandb.log() and per-example outputs with wandb.Table. wandb.watch() hooks into a PyTorch model's parameters and gradients and logs histograms of their values at regular intervals. Only team admins can send invitations. W\&B stores your script's stdout and stderr as output.log (or multipart chunks under logs/). Teams are the primary unit of collaboration in W\&B. W\&B Self-Managed is a self-hosted deployment that runs in your infrastructure. Run resumption is not supported inside a W\&B sweep. Invalid parameters on chat completion requests often surface as HTTP 422 (Unprocessable Entity) or HTTP 400 (Bad Request) depending on where validation runs. A 404 response from the W\&B Inference API means the server could not find the model or resource you asked for. To authenticate to a W\&B Self-Managed instance, point the CLI and SDK at your instance URL before you log in: It depends on what you're building: @weave.op traces individual Python functions and surfaces results in the Traces tab. ## May 2026 ### Models Learn to build a project run-failure alert or a registry alias automation. Build an automation that runs a webhook when a Registry artifact gets a specific alias like "production". Build a run-failure alert that sends a Slack notification when a run in your project fails. Programmatic automation management with the Python API. Create and update may be affected on some client versions. Prefer the W\&B App until the SDK fix ships. ## April 2026 ### Weave Trace Deepset Haystack pipelines with W\&B Weave using the WeaveConnector integration. Improve the resilience of W\&B Weave trace data capture with the write-ahead log Trace Vercel AI SDK calls in Weave using OpenTelemetry Create event-driven automations that trigger actions based on monitor metrics and trace activity. ### Platform Understand how W\&B uses object storage, how deletion maps to bucket bytes, and how to reduce storage usage and costs. ### Sandboxes Learn how to manage secrets in Serverless Sandboxes. Learn how to run commands in a sandbox environment and read output and exit codes. Learn how to train a PyTorch model in a Serverless Sandbox environment with this step-by-step tutorial. Learn about the lifecycle of a Serverless Sandbox, including its states, how to wait for state changes, and how to stop a sandbox. Learn how to invoke an OpenAI agent within a Serverless Sandbox environment Learn how to read, write, and mount files in Serverless Sandboxes. Create W\&B Serverless Sandboxes that run code in isolated containers with their own filesystem, network, and process space. On-demand, isolated compute environments that you can create, use, and discard from Python with W\&B Serverless Sandboxes. ### Support By default, Weave's .call() method captures exceptions and stores them in call.exception instead of raising them. Workspaces can load slowly when a project has many metrics, runs, or panels. This article helps you resolve training hangs when you use W\&B with distributed training frameworks, so your runs can start and finish without stalling. When you use a service account to automate W\&B workflows, you might encounter authorization errors or find that runs don't appear where you expect them. If you receive an HTTP 429 Rate limit exceeded error when you call wandb.log(), you're exceeding the rate limit quota for your project. This page explains how to resolve unresponsive processes that occur when you start a process with Hydra alongside W\&B. This page helps administrators of W\&B enterprise deployments diagnose common issues when W\&B doesn't recognize an enterprise license or its features are unavailable after you set the license. If you see Cuda out of memory during a sweep, refactor your code to use process-based execution. If you see both CommError, Run does not exist and ERROR Error uploading during a sweep, the most likely cause is that you're setting a run ID manually in your code: If you can't link an artifact to a W\&B Registry, the most common cause is that the artifact was logged with a personal entity instead of a team entity. An anaconda 400 error during a sweep often means you didn't log the metric you're optimizing. ## March 2026 ### Models Learn how W\&B Sweeps handle UNIX signals, exit codes, and preemption in sweep runs. ### Weave Use Weave to automatically trace your calls to the OpenAI Realtime API. Retrieve and manage versions of your prompts for LLM applications Evaluate trace items and submit structured feedback using a simplified review interface. Create annotation queues, route traces to domain experts, and export structured feedback. ### Platform Track training runs, review console logs, view line plots and system metrics, and explore W\&B Models projects from your iPhone or iPad. Install W\&B Skills to teach your coding agent how to train models, build agents, and analyze experiments using W\&B's AI development platform. Optional rate limits on Self-Managed instances for stability View all supported AWS, Google Cloud, and Azure regions available for W\&B Dedicated Cloud instances. Default rate limits on Dedicated Cloud and how to request changes Export runs, metrics, artifacts, and reports from a W\&B Dedicated Cloud instance using the Python SDK API. ### Inference > ## February 2026 ### Weave Use Weave projects to organize related assets like traces, prompts, evaluations, models, and dashboards. ### Platform Connect your IDE or AI agent to the W\&B Model Context Protocol (MCP) server to query and analyze your W\&B data and documentation in natural language. ### Inference > ## January 2026 ### Models Learn how to use pinned and baseline runs to keep track of important runs and efficiently evaluate model experiments. ### Weave Dynamic Leaderboards let you configure, customize, save, and update Leaderboard views directly from an evaluation. Map columns in datasets to different names. This helps you align the column names in your dataset with the column names expected by the scorer. ### Inference > ### December 2025 #### Models View the execution history of your W\&B Automations to check status, triggering events, and action results. > Evaluate a VLLM-compatible model checkpoint using infrastructure managed by CoreWeave Evaluate a hosted API model using infrastructure managed by CoreWeave Evaluate model checkpoints or hosted API models within W\&B and analyze the results using automatically generated leaderboards.