Telemetry ingest — Observra & OpenTelemetry

Cognisafe is the scoring and governance destination for your agent telemetry. If your agents already emit telemetry — via Observra or any OpenTelemetry pipeline — you can route it straight into Cognisafe and get OWASP LLM Top 10 scoring, dashboards, alerts, and audit evidence on that traffic, without touching your application code. Both endpoints authenticate with a normal Cognisafe API key and go through the same pipeline as first-party traffic: tier rate limits, retention settings (including zero content retention), safety scoring, and alerting all apply.

Observra

Observra is an open-source agent telemetry SDK (Apache 2.0) covering Google ADK, Claude Agent SDK, OpenAI Agents SDK, LangChain/LangGraph, and Pydantic AI. Point its webhook backend at Cognisafe:

from observra import initialize

initialize(
    backends=["webhook"],
    webhook_url="https://api.cognisafe.uk/ingest/observra",
    webhook_headers={"X-Cognisafe-Key": "csk_your_key"},
)

That’s it — every agent framework Observra supports now feeds Cognisafe.

How events map

Observra event	What Cognisafe does
`user_message`	Holds the prompt text briefly (10 min), keyed by `session_id`
`model_response` / `turn`	Creates a request, merging the held prompt from the same session — model, tokens, agent name, and prompt all land on one scored row
`model_error`	Creates a request carrying the error
Everything else (sessions, tool calls, handoffs)	Accepted and ignored (`202`, counted in `ignored`)

Because Observra redacts PII before events leave your process, what Cognisafe scores is the redacted text — a good pairing with zero content retention if you want no raw content persisted anywhere.

Request format

POST /ingest/observra accepts a single event object or a JSON array (max 500). Auth via X-Cognisafe-Key: csk_... or Authorization: Bearer csk_....

{"accepted": 1, "ignored": 3, "ids": ["<request uuid>"]}

OpenTelemetry

POST /ingest/otel accepts OTLP/HTTP JSON traces. Any span carrying GenAI semantic conventions becomes a scored Cognisafe request; other spans are ignored. Attributes read (first match wins):

Cognisafe field	GenAI attributes
model	`gen_ai.request.model`, `gen_ai.response.model`, `gen_ai.system`
prompt	`gen_ai.prompt`, `gen_ai.content.prompt`
response	`gen_ai.completion`, `gen_ai.content.completion`
tokens	`gen_ai.usage.input_tokens` / `output_tokens` (and the older `prompt_tokens` / `completion_tokens`)
agent	`gen_ai.agent.name`
latency	span start/end timestamps

Point an OTel Collector at it with an otlphttp exporter:

exporters:
  otlphttp/cognisafe:
    traces_endpoint: https://api.cognisafe.uk/ingest/otel
    headers:
      X-Cognisafe-Key: csk_your_key
    encoding: json

Spans without prompt/completion content still produce metadata rows (model, tokens, latency, cost) — useful for cost attribution even when your pipeline strips content. Scoring runs when content is present.

Choosing an integration path

You have	Use
Direct OpenAI/Anthropic/Mistral/Cohere calls	The Cognisafe SDK or proxy — richest capture
Agents on ADK / Claude Agent SDK / OpenAI Agents / LangChain / Pydantic AI	Observra → `/ingest/observra`
An existing OTel pipeline with GenAI spans	Collector → `/ingest/otel`

Getting Started

SDKs

LLM Providers

Self-hosted Models

Self-hosting

Integrations

Reference Architectures

Deployment Blueprints

Safety & Scoring

Telemetry ingest — Observra & OpenTelemetry

Observra

How events map

Request format

OpenTelemetry

Choosing an integration path

​Observra

​How events map

​Request format

​OpenTelemetry

​Choosing an integration path

Observra

How events map

Request format

OpenTelemetry

Choosing an integration path