feat(deepseek): add DeepSeek instrumentation with R1 reasoning_content support

Adds opentelemetry-instrumentation-deepseek package for tracing DeepSeek API
calls. Closes #2597.

DeepSeek has no native tracing support in OpenLLMetry. Users calling
DeepSeek-R1 also lose visibility into reasoning_content (chain-of-thought
output) which is not captured by the existing OpenAI instrumentation.

- Patches openai.resources.chat.completions (DeepSeek is OpenAI-compatible)
- Only activates when base_url contains "deepseek" via _is_deepseek_client()
- Captures reasoning_content as gen_ai.deepseek.reasoning_content span attribute
- Accumulates reasoning_content across streaming chunks
- Follows the Groq instrumentation structure exactly

Author: CaringNihilistic

.cz.toml

@@ -10,6 +10,8 @@ version_files = [
     "packages/opentelemetry-instrumentation-mcp/opentelemetry/instrumentation/mcp/version.py",
     "packages/opentelemetry-instrumentation-groq/pyproject.toml:^version",
     "packages/opentelemetry-instrumentation-groq/opentelemetry/instrumentation/groq/version.py",
+    "packages/opentelemetry-instrumentation-deepseek/pyproject.toml:^version",
+    "packages/opentelemetry-instrumentation-deepseek/opentelemetry/instrumentation/deepseek/version.py",
     "packages/opentelemetry-instrumentation-agno/pyproject.toml:^version",
     "packages/opentelemetry-instrumentation-agno/opentelemetry/instrumentation/agno/version.py",
     "packages/opentelemetry-instrumentation-alephalpha/pyproject.toml:^version",

packages/opentelemetry-instrumentation-deepseek/.python-version

@@ -0,0 +1 @@
+3.10

packages/opentelemetry-instrumentation-deepseek/README.md

@@ -0,0 +1,53 @@
+# OpenTelemetry DeepSeek Instrumentation
+
+<a href="https://pypi.org/project/opentelemetry-instrumentation-deepseek/">
+    <img src="https://badge.fury.io/py/opentelemetry-instrumentation-deepseek.svg" alt="PyPI version">
+</a>
+
+This library allows tracing prompts and completions sent to [DeepSeek](https://platform.deepseek.com/) using the official [OpenAI SDK](https://github.com/openai/openai-python), since DeepSeek's API is OpenAI-compatible.
+
+## Installation
+
+```bash
+pip install opentelemetry-instrumentation-deepseek
+```
+
+## Example usage
+
+```python
+from opentelemetry.instrumentation.deepseek import DeepSeekInstrumentor
+
+DeepSeekInstrumentor().instrument()
+```
+
+This instrumentor patches `openai.resources.chat.completions.Completions.create` and `AsyncCompletions.create`, but only creates spans for requests made through a client configured with a DeepSeek `base_url`. Regular OpenAI clients are left untouched, so this instrumentation can be safely enabled alongside [opentelemetry-instrumentation-openai](https://pypi.org/project/opentelemetry-instrumentation-openai/).
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="<DEEPSEEK_API_KEY>",
+    base_url="https://api.deepseek.com",
+)
+
+response = client.chat.completions.create(
+    model="deepseek-chat",
+    messages=[{"role": "user", "content": "Hello!"}],
+)
+```
+
+## DeepSeek-R1 reasoning content
+
+The `deepseek-reasoner` model (DeepSeek-R1) returns its chain-of-thought in a `reasoning_content` field on the response message, in addition to the final `content`. This instrumentation captures `reasoning_content` as the `gen_ai.deepseek.reasoning_content` span attribute, for both streaming and non-streaming responses.
+
+## Privacy
+
+**By default, this instrumentation logs prompts, completions, and embeddings to span attributes**. This gives you a clear visibility into how your LLM application is working, and can make it easy to debug and evaluate the quality of the outputs.
+
+However, you may want to disable this logging for privacy reasons, as they may contain highly sensitive data from your users. You may also simply want to reduce the size of your traces.
+
+To disable logging, set the `TRACELOOP_TRACE_CONTENT` environment variable to `false`.
+
+```bash
+TRACELOOP_TRACE_CONTENT=false
+```