DataDog/dd-trace-js
Dec 2025 – Dec 2025
1 Month active
Languages Used
JavaScript
Technical Skills
API integrationNode.jsfull stack developmenttesting
Xinyuan Guo
PROFILE
Xinyuan Guo
Over a two-month period, contributed to DataDog’s dd-trace-js and dd-trace-go repositories by building targeted observability features for large language model (LLM) integrations. Developed a reasoning output token metrics system for the OpenAI plugin in dd-trace-js, instrumenting code paths and integrating with reporting dashboards to provide visibility into token usage during reasoning tasks. In dd-trace-go, designed and implemented the llmobs.WithAnnotatedCostTagKeys API, enabling structured cost tag propagation and telemetry for LLM cost and token metrics. Leveraged Go, Node.js, and API design skills to enhance metric granularity, support cost attribution, and ensure robust, test-driven integration across both codebases.
Overall Statistics
Feature vs Bugs
100%Features
Repository Contributions
2Total
Bugs
0
Commits
2
Features
2
Lines of code
571
Activity Months2
Your Network
162 peopleShared Repositories
162
Work History
May 2026
1 Commits • 1 Features
May 1, 2026In May 2026, delivered a focused LLM Observability enhancement in DataDog/dd-trace-go: the new llmobs.WithAnnotatedCostTagKeys API enables propagation of annotated cost tag keys to LLM cost and token metrics, aligning behavior with DataDog’s other language tracers (dd-trace-py and dd-trace-js). The feature adds structured cost tagging on LLMObs spans, supports dedup across multiple annotations, and serializes cost tags into span events under metadata._dd.cost_tags. Telemetry counters for cost-tag usage were introduced to surface adoption and impact. The change reduces ambiguity in LLM cost attribution and enables finer granularity (e.g., by team, project, service line) for business decision-making.
1 Commits • 1 Features
May 1, 2026In May 2026, delivered a focused LLM Observability enhancement in DataDog/dd-trace-go: the new llmobs.WithAnnotatedCostTagKeys API enables propagation of annotated cost tag keys to LLM cost and token metrics, aligning behavior with DataDog’s other language tracers (dd-trace-py and dd-trace-js). The feature adds structured cost tagging on LLMObs spans, supports dedup across multiple annotations, and serializes cost tags into span events under metadata._dd.cost_tags. Telemetry counters for cost-tag usage were introduced to surface adoption and impact. The change reduces ambiguity in LLM cost attribution and enables finer granularity (e.g., by team, project, service line) for business decision-making.
May 2026
December 2025
1 Commits • 1 Features
Dec 1, 2025December 2025 monthly summary for DataDog/dd-trace-js. Delivered a new Reasoning Output Token Metrics feature for the OpenAI plugin to track token usage during reasoning tasks. Implemented instrumentation across relevant code paths, integrated with reporting, and added tests to verify metrics collection. This enhances observability, supports cost optimization, and improves reliability of LLM-powered flows.
December 2025
1 Commits • 1 Features
Dec 1, 2025December 2025 monthly summary for DataDog/dd-trace-js. Delivered a new Reasoning Output Token Metrics feature for the OpenAI plugin to track token usage during reasoning tasks. Implemented instrumentation across relevant code paths, integrated with reporting, and added tests to verify metrics collection. This enhances observability, supports cost optimization, and improves reliability of LLM-powered flows.
Activity
Loading activity data...
Quality Metrics
Correctness100.0%
Maintainability80.0%
Architecture90.0%
Performance80.0%
AI Usage50.0%
Skills & Technologies
Programming Languages
GoJavaScript
Technical Skills
API designAPI integrationGoNode.jsbackend developmentfull stack developmenttelemetrytesting
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline
DataDog/dd-trace-go
May 2026 – May 2026
1 Month active
Languages Used
Go
Technical Skills
API designGobackend developmenttelemetry