---
date: 2026-05-15
title: "Trace context on /api/public/v2/observations"
description: Fetch a trace's tags, release, and trace name directly on each observation row
author: Niklas
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com).

  `/api/public/v2/observations` is significantly faster than the v1 endpoint at scale — it uses cursor-based pagination and selective field retrieval so you only pay for the columns you actually need. See the [Langfuse v4 data model](/docs/v4) for the full picture of what changed.

The API `/api/public/v2/observations` now supports the `trace_context` field group. Add it to your `fields` query parameter and each observation comes back with `tags`, `release`, and `traceName` — denormalized from the parent trace, no extra `/traces/{id}` calls needed.

```
GET /api/public/v2/observations?fields=core,basic,trace_context
```

Common cases this simplifies:

- **Filter observations by trace tag** in a downstream pipeline without keeping a trace lookup table.
- **Group observations by release** for regression analysis directly on the observations response.
- **Render trace names** in an analytics view that paginates observations.

`trace_context` joins the existing groups (`core`, `basic`, `time`, `io`, `metadata`, `model`, `usage`, `prompt`, `metrics`) on the v2 endpoint. The full table is in the [Observations API v2 docs](/docs/api-and-data-platform/features/observations-api#v2).

`usagePricingTierName` also moved from `trace_context` to the `usage` group on the same endpoint — it's an observation-level pricing attribute, not parent-trace metadata.

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/changelog/2026-05-15-v2-observations-trace-context.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.