> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/docs/_mcp/server.

# Changelog

## September 25, 2026

## New

* **[SQL editor](/docs/documentation/features/observe/sql-editor)**: added query previews and background CSV or JSONL exports.
* **[API keys](/docs/documentation/admin/respan-api-keys)**: added Read, Write, Gateway, and Admin permission scopes for more precise access control.

## Improved

* **[Playground](/docs/documentation/features/prompt-management/playground)**: made Run easier to access, improved tool controls, and added automatic restoration of your last Playground with an option to start fresh.
* **[Models](/docs/documentation/features/gateway/models-catalog)**: model details now lead with providers and pricing, with API examples in a separate tab. Added an All / Discounted toggle for easier price comparison.
* **[Saved views](/docs/documentation/features/observe/explore-spans)**: selected time ranges, visible columns, and sorting now persist in saved views.
* **[Logs](/docs/documentation/features/observe/explore-spans)**: added thread and trace aggregate filtering and restored grouped-view refresh, counts, exports, and shareable view state.
* **[Behaviors](/docs/documentation/features/pulse/behaviors)**: refined behavior definitions and detail views, improved breakdown charts and scrolling, and moved enable and disable controls into the list menu.
* **[Notifications](/docs/documentation/features/monitoring/monitors)**: notifications now support parallel delivery across multiple methods, with duplicate methods prevented during setup.

## Fixed

* **[Playground](/docs/documentation/features/prompt-management/playground)**: saved response schemas now remain intact across reruns, continuations, and restored sessions.
* **[Prompt variables](/docs/documentation/features/prompt-management/prompt-composition)**: long values now scroll correctly without clipping the first line.
* **[Threads](/docs/documentation/features/observe/view-debug-traces)**: fixed Customer ID and API key filters returning server errors.
* **[Logs](/docs/documentation/features/observe/explore-spans)**: provider service tiers are now recorded on passthrough requests.
* **[Provider settings](/docs/documentation/admin/llm-provider-keys)**: credential validation no longer creates duplicate internal API keys or splits activity across views.
* **Reliability**: requests in progress now finish during server replacements, reducing failures during deployments and restarts.
* **[Red Team](/docs/documentation/red-team/run-assessment)**: remote campaigns can resume from the last completed goal after a restart or interruption.

## September 21, 2026

## New

* **[SQL editor](/docs/documentation/features/observe/sql-editor)**: the SQL editor is now available to all platform users for querying and exploring their data.
* **[Custom ID](/docs/documentation/features/observe/custom-ids)**: the Custom ID page is now available to all platform users for exploring activity grouped by custom identifiers.

![SQL editor running a query for daily cost by top models, with the results charted below.](https://cdn.respan.ai/respan_docs/changelog/changelogs-09:21-sql-editor.png)

## Improved

* **[Billing](/docs/documentation/admin/credits-billing)**: reorganized the Usage tab so the billing period applies clearly to both usage and its breakdown, with a more consistent logs usage display.
* **[Red Team](/docs/documentation/red-team/results)**: confirmed findings now display directly from campaign events, and CLI scan and login commands provide clearer explanations when the server refuses a connection.
* **[Demo](https://demo.respan.ai/)**: product screenshots on the homepage now open the corresponding screen in the live demo.

## Fixed

* **[Gateway](/docs/documentation/features/gateway/responses-api)**: Responses API requests without a model now use your default model instead of returning a server error.
* **[Billing](/docs/documentation/admin/credits-billing)**: corrected cached-token pricing for OpenAI Flex, OpenAI Fast, and Gemini Priority so charges and spend-limit usage reflect the selected service tier.
* **[Project members](/docs/documentation/admin/collaborate)**: added typed-email confirmation before removing a member to help prevent accidental removal.
* **Log ingestion**: isolated retry queues by deployment so failed messages cannot be replayed into the wrong deployment.

## September 11, 2026

## New

* **[Simulation](/docs/documentation/features/prompt-management/prompt-management-quickstart)**: simulation is now available on the Prompts page, with scenario generation, runs, and results.
* **[Filters](/docs/documentation/features/observe/explore-logs)**: added full-text search to help users find matching content directly.

![Simulate prompt dialog on the Prompts page, set to generate three multi-turn scenarios for a support response prompt, with an optional focus describing the behaviors to emphasize and a toggle to ground generation in production traces.](https://cdn.respan.ai/respan_docs/changelog/changelogs-09:11-simulation.png)

## Improved

* **[Models](/docs/documentation/features/gateway/models-catalog)**: model details now show original and discounted prices together, including percentage savings for each provider.
* **[Simulation](/docs/documentation/features/prompt-management/prompt-management-quickstart)**: organized scenario details into Setup, Behavior, and Evaluation sections and improved scrolling to keep panel content stable.
* **Side panels**: standardized toolbar and content tooltips across the platform.
* **[Gateway](/docs/documentation/features/gateway/gateway-quickstart)**: organizations without credits or a provider key now receive a clear activation-required error.
* **[API](/docs/apis/gateway)**: retired the legacy `/api/generate` endpoint. Use `/api/chat/completions` for chat completion requests.
* **Log ingestion**: improved resilience against memory-related interruptions during heavy traffic.

![Model catalog showing DeepSeek V4 variants across providers with input and output prices, context sizes, and Save 10% badges on discounted entries.](https://cdn.respan.ai/respan_docs/changelog/changelogs-09:11-models.png)

## Fixed

* **[Prompts](/docs/documentation/features/prompt-management/prompt-management-quickstart)**: fixed prompt detail and version parameters causing unsupported filter errors when returning to prompt lists.
* **[Exports](/docs/documentation/features/observe/export-retention)**: corrected export time-range handling and filter mismatches so requests reflect the selected range and filters.
* **[Queries](/docs/documentation/resources/reference/error-handling)**: large queries that exceed resource limits now return clear errors instead of generic server failures, including during pagination.
* **[Playground](/docs/documentation/features/prompt-management/playground)**: new organizations now receive three free Playground calls to help them get started.

## September 4, 2026

## New

* **[PII redaction](/docs/documentation/pii-redaction)**: added organization-level redaction settings with separate controls for Gateway requests and stored telemetry, configurable categories, sensitivity controls, and previews.
* **[Model leaderboard](https://www.respan.ai/ai-gateway/leaderboard)**: added a Top models by spend chart to help users understand Gateway usage on the landing page.
* **[Observability](/docs/documentation/features/tracing/quickstart)**: combined Tracing and Observability into a single experience while preserving existing links and workflows.
* **[Simulation](/docs/documentation/features/evals/experiments)**: added a streamlined simulation flow where users can select a prompt and version directly, generate scenarios, run simulations, and inspect results.

![PII redaction settings showing separate controls for Gateway requests and stored telemetry, selectable redaction categories with sensitivity controls, and a preview of redacted output.](https://cdn.respan.ai/respan_docs/changelog/changelogs-09:04-pii-redaction.png)

## Improved

* **[Gateway](/docs/documentation/features/gateway/advanced)**: BYOK requests can now fall back to managed credits when provider credentials encounter rate limits.
* **[Model leaderboard](https://www.respan.ai/ai-gateway/leaderboard)**: legends now reflect the entire selected time range, model colors remain consistent, and individual models can be isolated for comparison.
* **[PII detection](/docs/documentation/pii-redaction)**: improved redaction reliability for short telemetry fields, Unicode content, street addresses, private IPv4 addresses, and loopback IPv6 addresses.
* **Tables**: the first column now remains consistently frozen, preventing alignment from shifting across views.
* **[Behavior classification](/docs/documentation/features/pulse/behaviors)**: improved processing reliability so behavior results remain current during traffic spikes.

![Stacked weekly chart of the models accounting for the most gateway spend over the past year, with a ranked legend showing each model's share.](https://cdn.respan.ai/respan_docs/changelog/changelogs-09:04-top-spend-chart.png)

## Fixed

* **[Exports](/docs/documentation/features/observe/export-retention#manage-export-jobs)**: partially completed exports now provide the rows successfully written, identify incomplete time ranges, and preserve failure reasons for later investigation. JSONL exports are also written as JSONL rather than JSON, which could cause downstream systems to count records twice.
* **[PII settings](/docs/documentation/pii-redaction)**: fixed saved settings losing an explicitly selected organization or the default category configuration.
* **[Slack integration](/docs/integrations/slack)**: fixed large channel lists causing setup requests to time out.
* **[Saved filters](/docs/documentation/features/observe/explore-spans)**: invalid filter requests now return actionable validation errors instead of server errors.
* **[Security](/docs/documentation/architecture_review)**: strengthened organization access controls and prevented duplicate cash-credit events from changing balances more than once.

## August 28, 2026

## New

* **[Models](/docs/documentation/features/gateway/models-catalog)**: added Kimi K2.6, MiniMax M2.7, and DeepSeek V4 Flash 0731 with BYOK and managed-credit support.
* **[Experiments](/docs/documentation/features/evals/experiments)**: added editable experiment replication, earlier evaluator-result columns, and consistent aggregate results for completed and failed runs.

## Improved

* **[Models](/docs/documentation/features/gateway/models-catalog)**: improved model-detail layouts, search relevance, and provider matching. Model selectors also refresh after custom model or provider updates without clearing active searches and filters. Deployment-specific models now appear correctly when configuring BYOK provider credentials.
* **[Gateway](/docs/documentation/features/gateway/gateway-quickstart)**: provider timeouts now return a clearer timeout status, and connection-level provider failures return more accurate error responses.
* **[Gateway](/docs/documentation/features/gateway/routing-and-passthrough)**: improved Anthropic passthrough fidelity for errors, streaming responses, optional fields, and retry behavior.
* **[Responses API](/docs/documentation/features/gateway/responses-api)**: OpenRouter models can now be called through the Responses API.
* **[Logs](/docs/documentation/features/observe/explore-spans)**: object parameters such as metadata now appear as individual fields in the Config tab instead of a raw JSON object.
* **[Demo workspace](https://demo.respan.ai/)**: updated sample prompts and added introductory guidance throughout the demo experience.
* **[Settings](/docs/documentation/admin/projects)**: improved page rendering and migrated organization data loading to a more reliable query system.
* **Tables**: numeric values are now consistently right-aligned, with improved header spacing across product tables.

![Respan demo workspace for logs.](https://cdn.respan.ai/respan_docs/changelog/changelogs-08:28-demo.png)

## Fixed

* **[Experiments](/docs/documentation/features/evals/experiments)**: fixed columns becoming hidden after returning to the experiment list from a detail page.
* **[Scores](/docs/documentation/features/evals/evaluators/overview)**: fixed errors when opening evaluation-result details backed by PostgreSQL.
* **[Logs](/docs/documentation/features/observe/explore-spans)**: fixed the first and last time labels being clipped on events charts, and fixed an issue that prevented users from clearing the selected grouping.
* **[Models](/docs/documentation/features/gateway/models-catalog)**: fixed incorrect model filters being applied when reloading model-detail pages.
* **[Monitors and reports](/docs/documentation/features/monitoring/monitors)**: corrected breakdown values and removed duplicate data requests.
* **[Security](/docs/documentation/architecture_review)**: patched some security vulnerabilities.
* **Organization members**: fixed member updates failing when existing access-level information was included in the request.

## August 21, 2026

## New

* **[Response formats](/docs/documentation/features/prompt-management/structured-output)**: added a dedicated place to create, edit, and reuse saved response formats across model configurations.
* **[Online evaluations](/docs/documentation/features/evals/online-evals)**: added alerts for online evaluation results.

## Improved

* **[Experiments](/docs/documentation/features/evals/experiments)**: stabilized trace loading with clearer loading states, early row previews, and protection against stale results.
* **Experiment inference**: reasoning models can now use reasoning and tool calls together during a run.
* **[Models](/docs/documentation/features/gateway/models-catalog)**: updated model availability, pricing, context limits, recommended ordering, and BYOK filtering across the Platform and Enterprise catalogs.
* **[Behaviors](/docs/documentation/features/pulse/custom-behaviors)**: improved custom behavior creation with better candidate selection and related reliability fixes.
* **[Monitors and reports](/docs/documentation/features/monitoring/reports)**: standardized time, number, and unit formatting for clearer and more consistent results.
* **[Agent](/docs/documentation/agent)**: restored page context and skills, and corrected metric filter definitions.
* **[Gateway](/docs/documentation/features/gateway/routing-and-passthrough)**: responses now preserve the exact model name provided in the original request.
* **[Slack integration](/docs/documentation/features/monitoring/monitors#configure-notifications)**: improved channel caching and request handling to prevent rate-limit errors during setup.

![Span detail view for a streamed LLM request showing the model name and details.](https://cdn.respan.ai/respan_docs/changelog/changelogs-08:21-spans.png)

## Fixed

* **[Log privacy](/docs/documentation/features/observe/export-retention)**: requests with logging disabled no longer retain request or response content.
* **[Log filters](/docs/documentation/features/observe/explore-spans)**: fixed list-based filters causing server errors and prevented invalid filters from silently broadening results.
* **[Log exports](/docs/documentation/features/observe/export-retention#manage-export-jobs)**: large exports now complete more reliably, accurately report delivered rows, and fail clearly instead of returning incomplete files.
* **[Datasets](/docs/documentation/features/evals/datasets/overview)**: fixed trace imports and large row-removal operations failing on high-traffic accounts.
* **SQL editor**: prevented non-admin users from accessing internal system columns and metadata while preserving supported log filtering.
* **[Gateway](/docs/documentation/features/gateway/gateway-quickstart)**: fixed empty provider chunks ending streams early and ensured failed streamed responses still produce logs.
* **Gemini usage**: fixed responses incorrectly reporting zero token usage or cost.
* **[Monitors](/docs/documentation/features/monitoring/monitors)**: fixed high-volume rolling monitors missing scheduled evaluations or firing late.
* **[OAuth](/docs/documentation/mcp)**: fixed organization switching and authentication issues in MCP integrations.

## August 13, 2026

## New

* **[Gateway](/docs/integrations/gateway/openrouter)**: added a native OpenRouter chat completions endpoint, with reasoning and provider preferences passed through correctly.
* **[Agent search](/docs/documentation/agent)**: Respan Agent can now use full-text search to find relevant information.

## Improved

* **[Behaviors](/docs/documentation/features/pulse/behaviors#investigate-a-behavior)**: added LLM judging to improve behavior classification and analysis.
* **[Experiments](/docs/documentation/features/evals/experiments#results-and-analytics)**: experiment details now present grader names, outcomes, scores, latency, cost, tokens, and errors more clearly while hiding unnecessary metadata.
* **Experiment performance**: added early row previews, lighter list responses, and compression for large experiment APIs so results appear sooner and transfer less data.
* **[Model discovery](/docs/documentation/features/gateway/models-catalog#find-a-model)**: improved recommended-model ordering, [BYOK availability](/docs/documentation/features/gateway/models-catalog#understand-billing-labels) filtering, and model-detail layouts to make suitable models easier to find and compare.
* **[Model catalog](/docs/documentation/features/gateway/models-catalog)**: compressed model catalog responses to reduce loading time.
* **Workflows**: optimized workflow execution paths for substantially faster processing.
* **[Monitors](/docs/documentation/features/monitoring/monitors#configure-notifications)**: simplified monitor rendering for clearer, more consistent notifications.

![Completed experiment showing the evaluator, dataset, and prompt it ran against, a score distribution chart, and a results table with input, output, expected output, latency, cost, and expected-value columns.](https://cdn.respan.ai/respan_docs/changelog/2026-08-13-experiments.png)

## Fixed

* **[Log exports](/docs/documentation/features/observe/export-retention#manage-export-jobs)**: large exports now use stable ordering, recover from storage interruptions, and avoid silently dropping rows. Failed or incomplete exports also report accurate progress and no longer provide untrustworthy downloads.
* **Reliability**: brief cache interruptions no longer restart otherwise healthy web servers or turn into avoidable request failures.
* **[Models](/docs/documentation/features/gateway/routing-and-passthrough#unified-router)**: plain and provider-prefixed model names now resolve to the same catalog entry and behave consistently.
* **[Spans](/docs/documentation/features/observe/explore-spans#find-the-spans-that-matter)**: model icons remain readable when the Model column is narrow.
* **[Lists](/docs/documentation/resources/reference/error-handling)**: invalid sorting options now fall back safely instead of causing server errors.
* **[Dashboard metrics](/docs/documentation/features/monitoring/metrics#choose-the-right-percentile)**: fixed organization-filtered quantile requests that could return server errors.

## August 10, 2026

## New

* **[Evaluator results](/docs/documentation/features/evals/evaluators/overview#graders)**: LLM graders now provide a written rationale alongside each score, making it easier to understand why an evaluation passed or failed.

## Improved

* **[Model catalog](/docs/documentation/features/gateway/models-catalog)**: updated available and retired models, refreshed provider pricing, and expanded model capability details.
* **[Model catalog loading](/docs/documentation/features/gateway/models-catalog#find-a-model)**: models now load on demand for each organization, with retry handling and protection against stale responses.
* **Log ingestion**: very large log payloads are now captured reliably without stalling the ingestion pipeline.
* **[Search](/docs/documentation/features/observe/explore-spans#find-the-spans-that-matter)**: improved full-text search performance with a new ClickHouse text index.
* **[Request logs](/docs/documentation/resources/reference/error-handling)**: queries that exceed memory or time limits now return a clear, actionable response instead of a raw database error.

## Fixed

* **Workflows**: fixed an amplification issue that could cause workflows to perform unnecessary repeated work.

## August 6, 2026

## New

* **[Error Tracking](/docs/documentation/features/pulse/errors#investigate-an-incident)**: added an incident-first investigation experience with impact summaries, timelines, contributing error groups, occurrence evidence, acknowledgements, and notes.
* **Spans**: the "Aggregate into" control is now available to all Spans users, making it easier to investigate activity by supported groups.
* **[Reports](/docs/documentation/features/monitoring/reports#choose-the-contents)**: reports now include Pulse metrics, and existing customer reports have been migrated to the updated format.
* **[Agent chat](/docs/documentation/agent)**: agent responses can now render charts, tables, and lists for clearer, more structured results.
* **[Model catalog](/docs/documentation/features/gateway/models-catalog#understand-billing-labels)**: added BYOK-only billing labels across the catalog and model selectors.

![Errors page showing an error timeline stacked by provider and status code, a list of incidents with recovery status and error counts, and the contributing error groups below.](https://cdn.respan.ai/respan_docs/changelog/2026-08-06-errors.png)

## Improved

* **[Experiments](/docs/documentation/features/evals/experiments#compare-and-iterate)**: refined evaluation analytics and comparison views while reducing unnecessary trace loading, and added backend status visibility and automatic refreshes for active experiments.
* **[Evaluator editor](/docs/documentation/features/evals/evaluators/overview#graders)**: added expanded editors for LLM prompts and Python code, with immediate synchronization and smoother keyboard interactions.
* **[Error Tracking](/docs/documentation/features/pulse/errors#read-the-error-timeline)**: improved how errors are classified into incidents for more accurate investigation.
* **[Model discovery](/docs/documentation/features/gateway/models-catalog#find-a-model)**: models now default to newest-first ordering, with clearer release dates and lifecycle information.
* **[Model pages](/docs/documentation/features/gateway/models-catalog)**: improved layouts across compact, expanded, sparse, and data-rich views.
* **Experiment performance**: compressed large experiment-log responses to reduce loading time and transferred data.
* **Hosted MCP**: improved sign-in continuity for hosted MCP connections with a dedicated OAuth session flow.
* **[Logs API](/docs/apis/spans)**: removed internal platform fields from log, trace, and span API responses.

## Fixed

* **[Experiments](/docs/documentation/features/evals/experiments#results-and-analytics)**: fixed evaluator scoring so model, cost, and token metrics come from the experiment run instead of the source dataset row.

## July 30, 2026

## New

* **[Microsoft Teams](/docs/integrations/microsoft-teams)**: Microsoft Teams is now available as a [notification integration](/docs/documentation/features/monitoring/monitors#configure-notifications).
* **[Reports](/docs/documentation/features/monitoring/reports#choose-the-contents)**: reports can now include Pulse summaries for richer incident and behavior reporting.
* **[Logs](/docs/documentation/features/observe/view-debug-traces#choose-the-right-level)**: request activity can now be grouped by Threads or Traces directly from Logs, with filtering, sorting, refreshing, and detail panels available in each grouped view.
* **[Experiments](/docs/documentation/features/evals/experiments#results-and-analytics)**: experiment lists now include evaluator scores and model details, making results easier to compare without opening each experiment.
* **[Behaviors](/docs/documentation/features/pulse/behaviors#enable-behaviors)**: Behaviors is now available to regular platform users, with a complete draft, training, and review workflow.
* **Home**: added a recently visited section for quickly returning to prompts and datasets.

![Behaviors page showing the total behaviors detected over a two-week range, a stacked area chart of detections by day, and a list of behaviors with trend sparklines, positive or negative type, and match counts.](https://cdn.respan.ai/respan_docs/changelog/2026-07-30-behaviors.png)

## Improved

* **[Red Team](/docs/documentation/red-team/run-assessment)**: improved campaign setup, engine performance, CLI presentation, documentation, and error handling.
* **[Experiments](/docs/documentation/features/evals/experiments#results-and-analytics)**: conditional evaluator results can now return N/A. Aggregate scores exclude unscored rows and show the number of scored results, while histograms display N/A separately.
* **[Evaluators](/docs/documentation/features/evals/evaluators/overview#graders)**: refined the grader editor, expanded [Code evaluation](/docs/documentation/features/evals/evaluators/code) access, and improved how LLM and Code configurations are displayed and saved.
* **[Behaviors](/docs/documentation/features/pulse/behaviors#investigate-a-behavior)**: improved classification accuracy, reduced false positives, added controls for flagging incorrect matches, and made behavior charts clearer across time ranges.
* **[Error tracking](/docs/documentation/features/pulse/errors#investigate-an-error-group)**: improved error classification and added automatic clustering for errors occurring around the same time.
* **[Model catalog](/docs/documentation/features/gateway/models-catalog#find-a-model)**: improved model information and catalog performance, including richer descriptions, release dates, and coding benchmark scores.
* **[Request logs](/docs/documentation/features/user-analytics/customer-identifier)**: customer names and email addresses are now preserved in request-log lists, and nearby-request navigation more accurately follows the selected event's timestamp.
* **Dashboard sessions**: bookmarked dashboards now refresh expired sessions automatically instead of unexpectedly returning users to sign-in.
* **[Metrics](/docs/documentation/features/monitoring/metrics)**: empty breakdown charts now remain in a stable no-data state without flashing.
* **[Prompts](/docs/documentation/features/prompt-management/advanced#deployment--versioning)**: new drafts are created only after an edit, keeping prompt version history cleaner.
* **[Dataset imports](/docs/documentation/features/evals/datasets/overview#add-rows-to-a-dataset)**: imported message histories now appear as conversations, and expected outputs are stored and displayed as formatted JSON.

## Fixed

* **[Experiments](/docs/documentation/features/evals/experiments#troubleshooting)**: boolean evaluator results now display false values correctly, and multi-turn prompt experiments retain the complete conversation history.
* **[Experiment workflows](/docs/documentation/features/evals/experiments)**: added task validation and made configured evaluator execution more consistent.
* **[Prompts](/docs/documentation/features/prompt-management/advanced#deployment--versioning)**: fixed commit detection and redeployment behavior across all behavior-affecting settings. [Load-balancing](/docs/documentation/features/gateway/load-balancing) configuration is now preserved during JSON editing, and dropped parameters are persisted so they no longer reappear.
* **[Evaluators](/docs/documentation/features/evals/evaluators/overview)**: fixed commit messages overwriting evaluator descriptions and ensured each version displays its own commit message.
* **Security**: closed an unauthorized live-event stream vulnerability and resolved an additional high-severity security issue.

## July 17, 2026

## New

* **[Red Team](/docs/documentation/red-team/run-assessment)**: Red Team is now available online, with tools to create and run assessments, [review results, and generate reports](/docs/documentation/red-team/results). The open-source Red Team engine is also available on PyPI.
* **[Experiments](/docs/documentation/features/evals/experiments)**: added filters for datasets, prompts, evaluators, and models, along with model, prompt, and evaluator details directly in experiment lists.
* **Dataset automation**: automatic insert workflows now support trace datasets.
* **Dashboard autosave**: named dashboard views now save automatically, making it easier to preserve dashboard changes as you work.

![Red Team campaign report showing an overall grade of F, counts for confirmed findings, resistance rate, tested rounds, and duration, and a findings list with critical severity labels.](https://cdn.respan.ai/respan_docs/changelog/2026-07-17-red-team.png)

## Improved

* **[Experiments](/docs/documentation/features/evals/experiments)**: added starring, provider icons for models, and server-side table sorting for more useful experiment management at scale.
* **[Dashboards](/docs/documentation/features/monitoring/metrics#choose-the-investigation-window)**: improved synced chart-hover markers and comparison labels so tooltips and date ticks consistently respect the selected timezone.
* **[Home dashboard](/docs/documentation/features/monitoring/metrics)**: metrics refresh automatically in the background and update more reliably when returning to the page or changing the time range.
* **Metrics**: charts now support copy-to-clipboard.
* **[Behaviors](/docs/documentation/features/pulse/behaviors)**: improved behavior detection accuracy and reduced false positives.

## Fixed

* **[Traces](/docs/documentation/features/observe/view-debug-traces#follow-a-session-with-threads)**: span-level filters are now preserved when viewing grouped traces and threads, so results remain accurate.
* **Security**: strengthened protections.

## July 9, 2026

## New

* **[Dashboard ranges](/docs/documentation/features/monitoring/metrics#choose-the-investigation-window)**: added 5-minute, 15-minute, 30-minute, 1-hour, 4-hour, and 12-hour dashboard time ranges for closer inspection of recent activity.
* **[Trace datasets](/docs/documentation/features/evals/datasets/agents)**: datasets can now use complete traces as rows, not only individual spans.
* **[Trace experiments](/docs/documentation/features/evals/experiments)**: evaluators can now score [trace datasets](/docs/documentation/features/evals/datasets/agents) using the full trace context, enabling more representative experiment results.
* **[Online evaluation](/docs/documentation/features/evals/online-evals)**: launched Online Eval.
* **[Recurring exports](/docs/documentation/features/observe/export-retention#create-a-recurring-export)**: launched recurring exports.

![Evaluators page showing a scores over time chart for the last 24 hours with one line per evaluator, above a list of evaluators with IDs, tags, last updated dates, and owners.](https://cdn.respan.ai/respan_docs/changelog/2026-07-09-online-evals.png)

## Improved

* **[Dashboard charts](/docs/documentation/features/monitoring/metrics#customize-chart-display)**: chart cards now stay above neighboring tiles when hovered or keyboard-focused, keeping chart controls accessible in dense dashboards.
* **Command palette**: aliases now resolve during search, and the favorites action is now labeled "Pin."
* **Onboarding**: added a sign-out option during onboarding so users can switch accounts without getting stuck.

## July 7, 2026

## Improved

* **Dashboard charts**: restored chart spacing, grid behavior, refresh controls, timezone selector behavior, and full-window calendar presets for daily, weekly, monthly, and compare-period views.
* **Onboarding**: improved checklist steps, migrated onboarding variables, and fixed cases where users could get stuck or see visual flashes during onboarding.
* **Logs display**: tool call usage and tool call results are now displayed more clearly in the Spans and Threads pages.
* **Limits and webhooks settings**: improved cache and typing behavior, and fixed schema mismatch issues.

## Fixed

* **Prompts**: fixed an issue where prompt commit messages could be missing.
* **Playground**: fixed opening request logs in Playground so log handoff works reliably from log views.

## June 28, 2026

## New

* **Playground**: all users can now switch between the current and new Playground experiences.
* **Cache visibility**: cache tables now show last used time, expiry, and hit count columns.
* **Dataset row deletion**: users can now delete individual dataset records from the logs table with a confirmation flow.
* **Reports**: reports now include an activity panel and inspector for easier review of report-related changes.

## Improved

* **Dashboard charts**: improved metrics controls with timezone-aware ranges, chart expansion, drag-to-zoom, synced hover, layout reset behavior, and graph customizations.
* **Experiments**: improved the creation flow, model preset selection, log table wrapping, running indicators, and live result refresh while traces are still being written.
* **Prompt and Playground navigation**: prompt identity is now driven by URL parameters for more reliable sharing, reloads, and navigation.
* **Tables**: added infinite scrolling support, column reordering, better timestamp formatting, and improved table preview behavior.
* **Logs and traces**: improved preview table sizing and paused live streaming during bulk selection so selected rows stay stable.
* **Views and preferences**: scoped display preferences are now preserved more reliably after reloads.

## Fixed

* **Dataset uploads and experiment results**: fixed a regression where dataset uploads could silently fail and experiment runs could complete without results.
* **OAuth login**: fixed a rate-limiting issue that could break OAuth or social login.
* **Gateway prompt variables**: prompt variables now resolve with consistent precedence across Chat and Responses APIs.
* **Logging reliability**: streaming logs now retry failed batch writes and route undeliverable batches to a recoverable queue instead of dropping them.
* **Streaming reliability**: stalled streaming consumers now recover automatically, reducing delayed logs and background processing gaps.
* **Gateway credentials**: dedicated deployments for one model no longer block shared credentials for other models under the same provider.

## June 21, 2026

## New

* **Model status filtering**: the Models page now supports filtering models by Active or Deprecated status.

## Improved

* **Models page**: improved infinite scrolling, backend sorting, load performance, smart truncation, discount pricing, and cached table data for faster navigation.
* **Dashboard performance**: dashboards now load more quickly.
* **Prompt bulk updates**: polished the bulk update flow for a cleaner prompt editing experience.

## Fixed

* **Logs**: fixed rendering and performance issues in span and trace views that could make the page jump while navigating.
* **Reports**: fixed report page debounce behavior.
* **Datasets and graders**: fixed sort-by alignment issues in dataset and grader pages.
* **Display panels**: fixed cases where panel default state reset unexpectedly.
* **Evaluators**: fixed the Grader/New evaluations view switcher disappearing after the last evaluator or grader was deleted.

## June 14, 2026

## New

* **Dataset import UX**: CSV imports now support smarter header auto-mapping, drag-and-drop destination sections, and live import previews.
* **Prompt bulk updates**: multiple prompts can now be edited and updated at once, with model configuration and commit message support.
* **Organization logo upload**: organizations can now upload and manage a custom logo from settings and the profile menu.

## Improved

* **Views and display settings**: centralized sorting helpers, display defaults, and column definitions so saved views and tables behave more consistently.
* **Filter system**: optimized filter context values by grouping them, improving performance across filtered views.
* **Prompt and Playground performance**: optimized prompt and playground data loading, reducing redundant fetching and unnecessary page re-renders.
* **Onboarding**: connected the sidebar checklist to the home steps flow and fixed cases where users could see onboarding more than once.
* **Invitations**: improved pending invitation state and actions so invite flows behave more reliably.
* **Models page**: added discount badges, smarter model-name truncation, and cleaner list actions.

## Fixed

* **Logs**: fixed an empty-output UI issue and aligned span chart counts with request-log summary counts.
* **Projects**: deleting a project now logs the user out cleanly, preventing broken UI state after removal.
* **Monitors**: fixed monitor workflow issues and improved task list behavior.
* **Home charts**: fixed broken chart redirects from the home page into spans and related views.
* **Inputs and caches**: removed native number-input spinners and fixed cache typography issues.

## June 7, 2026

## New

* **Reports**: released the Reports feature with API key limit breach details and updated report metrics.
* **Prompt activity**: prompt activity now uses the shared activity feed experience.

## Improved

* **Filter system**: added grouped filters, saved-view persistence, cleaner display names, and more reliable filter URL behavior.
* **Dashboard**: added storage metrics, deployment breakdowns, and improved chart axes.
* **Playground**: prompt loading now supports infinite scrolling.
* **Slack channel picker**: Slack channel selection now supports infinite loading.
* **Signup and onboarding**: improved signup validation messages.

## Fixed

* API key total counts in paginator now display correctly.
* Monitor aggregation windows can now support up to 7 days.

## May 31, 2026

## New

* **Dashboard custom charts**: added cost-by-key charts, custom SQL charts, metrics views, and resizable chart grids.
* **Theme customization**: added new theme options and accent color customization.

## Improved

* **Billing and credits**: improved credit purchase flows, auto top-up settings, budget duration controls, and credit adjustment handling.
* **Dashboard charts**: improved chart bucket alignment, layouts, and custom chart behavior.
* **Reports preview**: improved report preview rendering and fixed report toggle behavior.
* **Logs**: opening logs in a new tab now preserves the current view state.
* **Provider and model icons**: added model family fallbacks and improved provider icon handling.
* **Model ID copy action**: model IDs are now easier to copy from the Models page.

## Fixed

* API key notifications are preserved correctly.
* Report notification methods no longer regress when edited.
* Tag filter labels now preserve the correct “has any of” operator text.

## May 24, 2026

## New

* **Metrics views**: added a workflow for creating and managing dashboard metric views.
* **Multi-value filters**: filter chips now support clearer “is any of” behavior for multi-value inputs.
* **Prompt filter submenu**: prompt filters are now grouped into a submenu for easier navigation.

## Improved

* **Models page**: model search persists more reliably, and model detail rows open correctly.
* **Prompts reliability**: fixed prompt creation and log prompt failure cases.
* **Logs, traces, and threads**: selected rows are now cleared automatically when changing pages.
* **Experiments**: improved loading states and pagination behavior for experiment summaries.

## Fixed

* Trace Thread ID filtering now uses the correct underlying session identifier.
* API key success toasts no longer leave excessive empty spacing.
* Cache hit origin is now shown correctly in side panels.
* Playground tool call outputs and tool call classification are restored correctly.

## May 17, 2026

## New

* **Reworked API Keys page**: manage API keys from a dedicated product area with filters, labels, creation flows, save confirmations, and activity history.
* **Custom model response format support**: configure response format settings when creating or editing custom models.
* **Monitor alert variables**: monitor templates now support request count variables for clearer alert messages.

## Improved

* **Billing controls**: improved credit settings, auto top-off, low balance warnings, and billing page layout.
* **Usage limits**: recurring limit usage and budget panels now show more accurate usage state.
* **Dashboard charts**: improved chart spacing, grid details, and drag behavior.
* **Trace side panels**: trace filters now map to the correct fields when drilling into side-panel rows.

## Fixed

* Exported logs now include input and output fields correctly.
* URL handling was hardened to reduce unsafe redirect and script risks.
* API key lifetime policies now stay in sync with configured limits.

_Showing the 20 most recent of 36 entries. Append `/llms.txt` to the changelog URL for the complete index._