> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Release 4.13

> Release 4.13 adds metric Alerts on traces, JSON response healing in the Router, a redesigned Smart Router page, and Advisor and Sidekick tools.

<Update label="Alerts" description="v4.13.0 Beta">
  Find out that production drifted from a notification, not from a customer. **[Alerts](https://docs.orq.ai/docs/ai-studio/observability/alerts)** watch a metric over a rolling window and notify a destination the moment a threshold is crossed, so a cost spike, a latency regression, or a burst of errors surfaces on its own.

  <img src="https://mintcdn.com/orqai/C9LJ4JMRsXLNWb25/images/alerts_4_13.png?fit=max&auto=format&n=C9LJ4JMRsXLNWb25&q=85&s=e4c69954f08613df6e0bba46e9bef81f" alt="Release 4.13 banner for Alerts in beta next to the alert list showing recent runs and threshold conditions" width="1200" height="627" data-path="images/alerts_4_13.png" />

  * **Five signals**: Start from Cost, Latency, Errors, or Guardrails, or pick Custom to alert on any metric in the catalogue.
  * **Rolling windows and check intervals**: Evaluate over 5 minutes to 1 day, and check as often as every 5 minutes.
  * **Notifiers**: Route to the same email, Slack, and webhook destinations already used by **Budgets**, so a destination is configured once and reused.
  * **Trigger view with drill-down**: See every firing on the alert detail page and open the event that caused it.
</Update>

<Update label="Smart Router" description="v4.13.0">
  The **Smart Router** has its own page in the **AI Gateway** that shows every configured router, which band each model lands in, and how to call the router from an application.

  <img src="https://mintcdn.com/orqai/wDGZBDRjJBffpWiX/images/smart_router_4_13.png?fit=max&auto=format&n=wDGZBDRjJBffpWiX&q=85&s=7e5b4d219047fe9b401007f7904b2f95" alt="Release 4.13 banner for the Smart Router next to the router list showing profiles and pool models" width="1200" height="627" data-path="images/smart_router_4_13.png" />

  * **Preview bands**: See which models sit in each band before traffic is sent, including Opus 4.8 and Fable 5 in the hard band.
  * **Invocation snippet**: Copy a working call straight from the router page, with tooltips explaining every column.
  * **[Model pool routing](https://docs.orq.ai/docs/ai-gateway/smart-router)**: The `route_pool` operation picks from N candidate models rather than only a strong and an economical pair.

  <Note>
    Set up intelligent routing from the [Smart Router guide](https://docs.orq.ai/docs/ai-gateway/smart-router).
  </Note>
</Update>

<Update label="Response healing" description="v4.13.0 Beta">
  Structured output that comes back wrapped in a markdown fence or carrying a trailing comma now parses instead of throwing. The `response_healing` **plugin** repairs malformed JSON before the response reaches the caller, so per-service JSON cleanup code can come out of the client.

  <img src="https://mintcdn.com/orqai/wDGZBDRjJBffpWiX/images/response_healing_4_13.png?fit=max&auto=format&n=wDGZBDRjJBffpWiX&q=85&s=6540cf8e44f798c18a65409758eeede2" alt="Release 4.13 banner announcing the Response Healing plugin next to the plugins list in settings" width="1200" height="627" data-path="images/response_healing_4_13.png" />

  * **[Six repair classes](https://docs.orq.ai/docs/ai-gateway/features/plugins/response-healing)**: Markdown code fences, JSON embedded in prose, missing closing brackets, trailing commas, unquoted keys, and single-quoted strings.
  * **Tool call arguments too**: Arguments are repaired whenever the plugin is enabled, with no `response_format` required.
  * **Workspace-wide switch**: Enable it for every request from **Settings** > **Plugins** instead of passing a `plugins` array on each call.

  <Note>
    Repairs apply to non-streaming requests only. See the [Response Healing plugin](https://docs.orq.ai/docs/ai-gateway/features/plugins/response-healing) page.
  </Note>
</Update>

<Update label="New features" description="v4.13.0">
  * **[Advisor and Sidekick tools](https://docs.orq.ai/docs/ai-studio/ai-engineering/build-agents#advisor-and-sidekick-tools)**: An **Agent** can consult a second model mid-turn. Advisor returns short guidance on the conversation so far, capped by `max_uses` and a transcript budget. Sidekick takes a discrete task and returns only the finished result, with its own instructions and output format. Both meter separately and nest their own spans, and a failed secondary call degrades to a message instead of failing the turn.
  * **Redesigned [Thread view](https://docs.orq.ai/docs/ai-studio/observability/threads)**: The conversation view in **Traces** is rebuilt around message blocks, with header stats, per-message avatars, granular navigation anchors, and a tool badge in the thread navigation so tool steps are easy to jump between.
  * **[Favourites in the sidebar](https://docs.orq.ai/docs/ai-studio/get-started/favorites)**: Star any entity to pin it to a Favourites section in the sidebar and a dedicated Favourites page. Stars are available on **Agents**, **Prompts**, **Datasets**, **Evaluators**, **Knowledge Bases**, **Memory Stores**, and MCPs.
</Update>

<Update label="Improvements" description="v4.13.0">
  * **Renaming**: **Chat** is now **Playground** in the platform toggle.
  * **Higher token ceilings**: OpenAI-compatible providers accept a max tokens value above 128k, up to 10M.
  * **Cleaner Router errors**: Error envelopes are consistent across providers so OpenAI and Vercel AI SDK error parsing works, and rate-limited requests return `Retry-After`.
  * **[Guardrail](https://docs.orq.ai/docs/ai-gateway/configuration/guardrail-rules#system-guardrails) sampling**: System guardrails support non-blocking mode and sampling, matching what user guardrails already allowed.
  * **Reset a conversation in the Agent Playground**: Clear conversation history without leaving the playground.
  * **API key expiry at a glance**: The API Keys table gains an expiration date column.
  * **Annotation queues API**: The **Annotation Queues** API is public and documented in the OpenAPI spec.
  * **`store: false` on Responses**: Callers can opt out of persistence on `/v1/responses`.
  * **Entity context in search**: Search results show which project an entity belongs to.
  * **Jump from a span to its source**: **Trace** spans link straight to the **Agent** or **Prompt** that produced them.
</Update>

<Update label="New models" description="v4.13.0">
  New additions to the **Model Garden**, plus two new providers: **Fireworks** and **Baseten**. Browse details on the [Supported Models](https://docs.orq.ai/docs/ai-gateway/supported-models) page.

  | Provider        | Models                                                                                                                                                       |
  | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
  | **Alibaba**     | `qwen3.8-max`                                                                                                                                                |
  | **OpenAI**      | `gpt-transcribe`, `gpt-live-transcribe`, plus EU regional offerings across the OpenAI catalogue                                                              |
  | **Mistral**     | `mistral-ocr-4-0`, billed per page                                                                                                                           |
  | **Moonshot AI** | `kimi-k3`, `kimi-k3-fast`                                                                                                                                    |
  | **Fireworks**   | `kimi-k3`, `kimi-k2.7-code`, `minimax-m3`, `qwen3.7-plus`, `deepseek-v4-pro`, `glm-5.2`                                                                      |
  | **Baseten**     | `kimi-k3`, `kimi-k2.6`, `kimi-k2.7-code`, `minimax-m3`, `glm-5.2`, `glm-5.2-fast`, `glm-4.7`, `deepseek-v4-pro`, `gpt-oss-120b`, `nemotron-ultra`, `inkling` |
  | **AWS Bedrock** | Claude Opus 4.8 in the EU region                                                                                                                             |

  Model metadata also gained an intelligence index, which is what the **Smart Router** bands read from.
</Update>

<Update label="Bug fixes" description="v4.13.0">
  * **Tool schemas reach the model intact**: `$defs` and `$ref` are no longer stripped from `tools[].function.parameters` on the **Anthropic** and **Google** paths, and the `required` array survives on **Anthropic** chat completions.
  * **Tool choice is honored**: Anthropic-native `tool_choice` respects `required` instead of downgrading to `auto`, and `disable_parallel_tool_use` is no longer dropped.
  * **Provider errors stay truthful**: Upstream 4xx and 404 responses pass through instead of being remapped to 500, including the **Google** and **Vertex** paths, and a thinking model that spends its whole budget on reasoning no longer returns an empty 500.
  * **Streaming completes on tool calls**: A Router `/responses` stream that carries a tool call now ends with `response.completed`, so OpenAI-compatible clients no longer hang waiting for the terminal event.
  * **Pre-flight validation**: Unsupported `response_format` and `service_tier` values are rejected before the provider call rather than surfacing as a provider 400.
  * **Image endpoints**: `gpt-image-1` accepts `response_format`, which unblocks Vercel AI SDK image calls, and non-streaming image responses report standard usage including `total_tokens`.
  * **Reasoning token billing**: `gemini-2.5-pro` reasoning tokens are metered separately instead of being counted inside output tokens, which had overstated cost significantly.
  * **Embedding spend is attributed**: Embedding calls from **Knowledge Bases** and **Memory Stores** record spend and reach **Budgets**.
  * **Traces accuracy**: The name filter is project scoped, spans show display names for private models instead of raw provider ids, Azure AI Inference tool-call output is stored rather than dropped, and span and agent-run counts match what **Traces** shows.
  * **Knowledge reliability**: Chunk metadata updates persist to the search index, `rerank_config` on the search API is applied instead of being accepted and ignored, Jina reranking succeeds, and multi-chunk ingestion with `google/gemini-embedding-2` completes.
  * **Evaluators**: A PATCH no longer discards `model` and other arm fields when `mode` is omitted, `dataset_id` round-trips on `llm_eval`, and output evaluators read the correct turn when an **Agent** ends on a tool call.
  * **SDKs**: `/v2/deployments/stream` returns `text/event-stream`, `agents.list()` accepts a null model parameters object, `refreshKeyCard()` works without a request body, and `POST /v2/files` keeps the filename and returns `object_name`.
  * **Sign-in**: OIDC sign-in lands on the workspace instead of onboarding or a missing page.
</Update>