You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Complete Python SDK implementation with:
- Run context model with UUIDv7 run_id generation
- @botanu_use_case decorator for run span creation
- RunContextEnricher processor for baggage propagation
- LLM/GenAI tracking with OTel semantic conventions
- Data tracking (DB, storage, messaging operations)
- AttemptLedger for durable cost event logging
- Resource detection (K8s, AWS, GCP, Azure, container)
- FastAPI/Starlette middleware
- Bootstrap with auto-instrumentation for 20+ libraries
- Unit tests for run_context, decorators, and LLM tracking
Signed-off-by: Deborah Jacob <deborahjacob@botanu.ai>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
In the interest of fostering an open and welcoming environment, we as contributors and maintainers agree to abide by the Code of Conduct available at https://lfprojects.org/policies/code-of-conduct/
OpenTelemetry-native **run-level cost attribution** for AI workflows.
9
+
10
+
## Overview
11
+
12
+
Botanu adds **runs** on top of distributed tracing. A run represents a single business execution that may span multiple traces, retries, and services. By correlating all spans to a stable `run_id`, you get accurate cost attribution without sampling artifacts.
13
+
14
+
## Quick Start
15
+
16
+
```python
17
+
from botanu import enable, botanu_use_case, emit_outcome
Please upgrade to latest stable version of Botanu which will have know security issues addressed.
6
+
7
+
## Reporting a Vulnerability
8
+
9
+
Please report security vulnerabilities privately to the Botanu [maintainer team] (https://github.com/monocle2ai/monocle/blob/main/MAINTAINER.md). Please do not post security vulnerabilities to the public issue tracker.
0 commit comments