Loading AI Observability Input/Output

Open

#2,878 opened on Oct 9, 2025 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty: 5/5
Estimated time: Over a week
Newbie friendliness: 20/100

Issue type: Feature
Clarity: Needs clarification
Activity status: Stale
Tech stack: python
Domain: api, observability-sre

Research direction

Start with the datadog-api-client Python API used to retrieve the traces, then compare its returned trace_ids with those shown in Datadog's AI Observability LLM Observability traces. Determine whether input/output content is exposed by an existing endpoint or requires a new feature; done means the supported retrieval path or its limitation is documented and verified.

Written by the indexing model from the issue text.

Description

kind/feature-request stale

I got some confused in using of the datadog-api-client-python.
What I tried to do is pulling the information that passed to datadog from my application that I can see on the AI Observability > LLM Observability > Monitor > Traces > CONTENT > Input/Output.

However, the things I pulled thru datadog-api-client, gave me the different trace_ids that I saw on the DATADOG Platform, and also I am only received the infrastructure log signals but unable to retrieve the content (input/output).

Could you please add the feature or tutorial teach me how to do that?

I cannot find any useful information from datadog doc itself, Chatbot AIs, or the tech blogs on the internet.

Dominant language: Python
Stars: 166
Forks: 55
Avg merge: 2d 17h
Merged PRs (30d): 73

Contributor guide

Open the contributing guide

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Similar issues

[essnmx] Fix typo in NXLauetof application definition Open

essnmx good first issue

Difficulty 1/5 Under an hour Newbie friendliness 95/100

scipp/ess#760 · Opened Sep 23, 2026
[Feature] 奇物选择添加优先级 Open

Difficulty 2/5 1-3 hours Newbie friendliness 65/100

syfoud/Simulated_Scepter#174 · Opened Sep 23, 2026
garak adapter grades a NaN detector score as PASS Open

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

Giskard-AI/giskard-oss#2840 · 1 comment · Opened Sep 23, 2026
A claim comment carrying the issue number is silently declined while the workflow reports success Open

area: repo bug perceived difficulty: 2

Difficulty 2/5 1-3 hours Newbie friendliness 70/100

Nitjsefnie-Harness-Commons/daedalus#926 · Opened Sep 23, 2026
`IOCExtractor` always fails: `ioc_analyzer.build()` takes 1 argument but the agent dispatcher passes 2 Open

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

yeti-platform/yeti#1380 · Opened Sep 23, 2026

More Python issues