For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
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.
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.
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.
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.
New
- ‘vs previous interval’ thresholds for monitors. Compare alert conditions against the prior interval, not just absolute values.
- Cross-provider load balancing for flexible, layer-agnostic routing configurations.
- Public dashboard API endpoints with a new URL prefix. Docs updated.
- Audit logging and throttling on signup and activation endpoints to harden against abuse.
- ‘is not’ operator on the customer ID filter to exclude specific customers from results.
Improved
- Dashboard export and OpenAPI client endpoints polished for easier integration.
- API key quota and creation checks now exclude temporary keys from key-limit counts.
Fixed
- Rate limiting on authentication endpoints to prevent spam.
- Organization deletion no longer hangs. Chunked querysets are correctly ordered by primary key.
- Vercel instrumentation now populates customer info and classifies LLM spans correctly.
- Export pipeline reliability: unique workflow IDs and zombie-workflow termination.
- Token caching in the Responses API and Gemini now applies cost discounts correctly, preventing overcharging.
New
- CLI JS hooks — Claude Code, Codex CLI, and Gemini CLI integrations now use lightweight Node.js hooks instead of Python. 25KB per hook, no Python dependency needed. Send traces via OTLP v2 JSON.
- OpenAI Agents SDK (TypeScript) — auto-instrument agent, tool, generation, and handoff spans.
- Respan CLI —
@respan/cli v0.6.0 with JS hooks, --api-key auth default, and respan integrate for all 4 coding agents.
- 95+ integration overview — searchable integration page with filter pills for Agent Frameworks, LLM SDKs, Coding Agents, Vector Databases, and Model Providers.
- Monitor templates — automation template gallery with drag-and-drop workflow builder.
Improved
- OpenTelemetry integration page rewritten with full semantic convention mapping (GenAI, Traceloop, OpenInference)
- JS tracing SDK reliability improvements
- Docs migrated to new documentation platform
New
- GPT-5.4 model support — added gpt-5.4, gpt-5.4-mini, and gpt-5.4-nano models.
- Experiment seed field — set a seed for reproducible experiment runs.
- Dataset outcome spans — dataset evaluation tasks now emit outcome spans for observability.
- Payment methods management — manage payment methods directly from the billing page.
- Onboarding flow — improved onboarding with integration setup and Playwright-tested auth flows.
Improved
- Service tier promoted from metadata to top-level column
- Auto-create webhook mappings for request log events
- Filter infrastructure refactored for type safety and OpenAPI alignment
- Agent tool error responses sanitized
New
- OpenAI SDK TypeScript integration — auto-instrument OpenAI calls with
@respan/instrumentation-openai. Includes streaming, tool calls, multi-turn, structured output, and batch API examples.
- is_cached_by_model — new cache option to invalidate caches when switching models. Set
cache_options.is_cached_by_model: true.
- Span pinning — pin spans for infinite retention with
is_pinned: true. PATCH existing spans to pin them.
Improved
- Customer identifier now has 254 character limit with auto-truncation
- Properties field added for typed metadata (preserves native types unlike metadata)
New
- Claude Agent SDK integration — full tracing support for Anthropic’s Claude Agent SDK with auto-instrumented spans.
- Unified Python & TypeScript SDKs —
respan package with plugin system, propagate_attributes(), and log_batch_results().
- Pydantic AI integration — trace Pydantic AI agent runs with auto-instrumentation.
- Vercel AI SDK updates — provider tabs and gpt-5-mini support.
Improved
- RAG pipeline tracing cookbook added
- Updated docs URL structure with flat integration paths
New
- Prompt schema V2 — new merge strategy where prompt config always wins. Use
schema_version: 2 for all new integrations. Includes patch parameter for runtime overrides.
- Fallback models — add
fallback_models to any gateway request. The gateway automatically tries each model in order if the primary fails.
- Anthropic Agents SDK integration — trace agent runs, tool calls, and LLM generations for both Python and TypeScript.
- RubyLLM gateway integration — route RubyLLM requests through the Respan gateway.
- Enterprise MCP — dedicated endpoint at
mcp.respan.ai/mcp/enterprise with OAuth, JWT, and API key auth.
Improved
- Prompt version API endpoints cleaned up
- Trace delete endpoint added
