Google Gemini

Installation

pip
uv
npm
yarn
pnpm

pip install "pandaprobe[gemini]"

uv add "pandaprobe[gemini]"

npm install pandaprobe @google/genai

yarn add pandaprobe @google/genai

pnpm add pandaprobe @google/genai

Setup

Python
TypeScript

Python

from pandaprobe.wrappers import wrap_gemini
from google import genai

client = wrap_gemini(genai.Client())

TypeScript

import { GoogleGenAI } from "@google/genai";
import { wrapGemini } from "pandaprobe/wrappers/gemini";

const client = wrapGemini(new GoogleGenAI({ apiKey: process.env.GOOGLE_API_KEY }));

Generate content

Span name: "gemini-generate", SpanKind: LLM

Python

response = client.models.generate_content(
    model="gemini-3.1-flash-preview",
    contents="Explain quantum computing.",
    config={"temperature": 0.7},
)
print(response.text)

TypeScript

const response = await client.models.generateContent({
  model: "gemini-3.8-flash",
  contents: "Explain quantum computing.",
  config: { temperature: 0.7 },
});
console.log(response.text);

What gets traced

Input: contents plus system_instruction normalized to messages format (role "model" mapped to "assistant")
Output: answer text (non-thought parts)
Model name
Token usage
Model parameters: temperature, top_p, top_k, max_output_tokens, stop_sequences, and related fields
Thinking or reasoning parts stored in metadata as reasoning_summary

Streaming

Python

stream = client.models.generate_content_stream(
    model="gemini-3.1-flash-preview",
    contents="Hello!",
)
for chunk in stream:
    print(chunk.text, end="")

TypeScript streaming

const stream = await client.models.generateContentStream({
  model: "gemini-3.8-flash",
  contents: "Hello!",
});
for await (const chunk of stream) {
  process.stdout.write(chunk.text ?? "");
}

PandaProbe traces Python’s synchronous and asynchronous APIs and TypeScript’s Promise-based APIs with the same span fields.

Thinking mode

When using Gemini’s thinking mode, thought parts are automatically separated from answer parts. Thought content is stored in metadata as reasoning_summary, while the span output contains only the answer text.

Token usage mapping

Gemini Field	PandaProbe Field
`prompt_token_count`	`prompt_tokens`
`candidates_token_count`	`completion_tokens`
`total_token_count`	`total_tokens`
`thoughts_token_count`	`reasoning_tokens`
`cached_content_token_count`	`cache_read_tokens`

Get Started

Tracing

Installation

Setup

Generate content

Streaming

Thinking mode

Token usage mapping

​Installation

​Setup

​Generate content

​Streaming

​Thinking mode

​Token usage mapping

Installation

Setup

Generate content

Streaming

Thinking mode

Token usage mapping