LLM Gateway rate-limit policies; dashboard gets P90/P95 queries

Observability and evaluations

Datasets and experiments

• GET /annotation-queues/{id}/items now returns THREAD queue items alongside RUN items, with an optional item_type filter.
• GET /annotation-queues/{id}/runs and related size endpoints exclude THREAD queue rows so mixed queues no longer return 500.
• Project settings now require a thread idle time of at least two minutes.
• Annotation queue item add requests now consistently enforce a 100-item limit for runs and threads.
• GET /annotation-queues/{id}/items returns Postgres membership metadata for RUN and THREAD items without hydrating nested run or thread payloads.
• When you bulk-add runs from a tracing project, its default dataset now appears first in the dataset picker.
• Annotation queue review lists now label unnamed run rows as Run <ID>.
• Opening the pairwise experiment comparison from a pairwise annotation queue no longer crashes the page.

Tracing

• The Insights reports pane can now be collapsed to give report details more space.
• Insights cluster summary columns can now expand to show more of each summary.
• LangSmith MCP's fetch_runs tool now returns first_token_time when that value is recorded.
• Legacy run URLs now resolve the run metadata and redirect to the SmithDB trace view.
• Trace usage limit banners now appear only for workspace members whose user-scoped limit has been exceeded.
• The Deployment button on tracing project pages now opens the deployment page within the app.
• Clicking the already-selected run or trace in a thread's trace tree now keeps it selected.
• Fixed two frontend call sites that could reach POST /runs/stats with an empty or missing session.
• MCP run query tools now return gateway timeout responses without retrying.
• Pressing Enter to confirm characters from an input method editor in LangSmith Chat now commits the composed text instead of prematurely sending the message.
• LangSmith Chat now surfaces a run's system prompt inline when reading a traced LLM run.
• LangSmith Chat traces now show the model you configured instead of mislabeling it as GPT-3.5-Turbo.
• The Run in Studio button is now hidden on public (shared) run pages.
• Navigating between traces now clears stale sharing state.
• The run, trace, and thread detail panels now enforce a minimum width when resized.
• Restore is_in_dataset on trace and run responses when the query is proxied to the V1 backend in ClickHouse-only mode.
• BYOC workspaces now avoid requesting trace table fields that older data planes do not support.
• Custom dashboard charts can now query summed latency and first-token time metrics through the runs analytics SmithDB path.
• Custom dashboard charts can now query minimum and maximum latency, time-to-first-token, token, and cost values.
• Custom dashboard charts can now query P90 and P95 for latency, first token time, tokens, and cost metrics.
• Custom dashboard charts can now aggregate feedback scores by sum, P50, P90, P95, and P99.
• The LangSmith homepage now provides clearer onboarding steps for coding agents and tracing.

Prompts and playground

• Editing agent and skill metadata in the Context Hub now shows save progress and reports actionable errors.
• Prompts with a repo readme now display it in a dedicated Readme section of the prompt view.
• Gemini 3.6 Flash and Gemini 3.5 Flash Lite are now available in Fleet, Agent Builder, and playground model selectors.
• Pasting content into rich-text editors now works reliably again.
• Previewing a single dataset row after running a full experiment now resolves the row's evaluator scores.
• LangSmith no longer keeps system-added top_p values when switching OpenAI prompts to reasoning models.

Engine

• The organization Engine usage page now lets you switch between a workspaces view and a projects view of month-to-date LCU spend.
• Engine no longer shows redundant hover tooltips on issue category badges or the default Fix action.
• Engine opens the Slack or webhook destination form immediately when no destinations are configured.
• Engine issue category labels now appear on a dedicated row below the title.
• Engine now shows a warning beside a linked repository when it cannot access it.
• On an Engine issue, navigating to the next or previous linked trace now stays in the conversation view for traces that belong to a thread.
• Engine now shows a clickable Paused status in the issues header when scheduled scanning is paused.
• Engine now works in supported self-hosted deployments without Eppo rollout configuration.
• Opening the project spend limit from the pause confirmation now scrolls the settings pane to the limit editor.
• Engine Overview now displays the current Engine package version.

Monitoring and alerting

• Self-hosted alert webhook delivery now honors SSRF_ALLOW_K8S_INTERNAL.

Automations

• Thread (grouped) evaluators now require a minimum idle time of 120 seconds.
• Leaving feedback on a run in a thread now makes the thread eligible for re-evaluation.
• Editing an online evaluator no longer intermittently fails when sandbox validation is slow.

Deployment

• Worker and API server CPU charts now plot a peak (max) series alongside the average.
• Worker and API server memory charts now plot a peak (max) series alongside the average.
• Creating a deployment with a name that's already in use within your workspace now returns a 409 Conflict.
• Hybrid deployments remain compatible with older listeners during control-plane upgrades.

Sandboxes

• A sandbox proxy configuration can now define environment variables that are applied to every command in the sandbox.
• Attach free-form key/value labels when creating a sandbox or snapshot.
• Sandbox network egress now tries every resolved IP for a destination instead of only the first.
• Creating a sandbox with only mem_bytes set now derives a matching CPU allocation automatically.

Administration

• Selecting All Workspaces on the Granular Billable Usage page now loads usage successfully for organizations with many workspaces.
• The Granular Usage page now shows a notice that long-lived trace usage isn't tracked in self-hosted deployments.

LLM Gateway

• Gateway Monitoring now shows spend for the workspace you're viewing rather than the whole organization.
• The Rate Limiting tab in Gateway Policies now supports creating, editing, deleting, and enabling/disabling request- and token-based rate-limit policies.
• Editing a materialized LLM Gateway policy now turns it into a standalone override.
• You can now call LangChain-managed models through the LLM gateway without configuring your own provider credentials.
• Selecting an entity filter on the LLM Gateway spend monitoring page no longer flips the breakdown to a different dimension.
• Selecting more than one entity in any Gateway Monitoring breakdown filter now returns spend for all chosen entities.
• The Gateway Monitoring spend chart now formats axis labels and tooltip ranges in UTC.
• The LLM Gateway spend chart and table now label spend from service keys as "Unaffiliated with any user".
• API-key-scoped LLM Gateway spend-cap and rate-limit policies can now add a custom X-Gateway-* header condition.
• Stat card and table headers in the LLM Gateway monitoring page's Spend tab now capitalize every word.
• When a specific start/end date is selected in the LLM Gateway monitoring page's date range picker, the button now shows the dates in UTC.
• The "Spend share" column on the LLM Gateway Monitoring spend dashboard no longer cuts off its header text.
• The LLM Gateway now lives in a dedicated top-level sidebar section instead of under Settings.
• A Home banner for LangSmith Cloud orgs with LLM Gateway enabled highlights how Gateway manages costs and improves runtime reliability.