From 1b2bb43f34029c0461d313b1fabd1b4edf7a8dd6 Mon Sep 17 00:00:00 2001
From: Andrew Kent <andrew@braintrustdata.com>
Date: Tue, 20 Jan 2026 16:12:13 -0800
Subject: [PATCH 1/2] remove outdated docs

---
 README.md | 59 -------------------------------------------------------
 1 file changed, 59 deletions(-)

diff --git a/README.md b/README.md
index 7bd307f..0d33aaa 100644
--- a/README.md
+++ b/README.md
@@ -82,65 +82,6 @@ var request =
 var response = openAIClient.chat().completions().create(request);
 ```
 
-### LangChain4j Instrumentation
-
-```java
-var braintrust = Braintrust.get();
-var openTelemetry = braintrust.openTelemetryCreate();
-
-// Wrap the chat model to trace LLM calls
-ChatModel model = BraintrustLangchain.wrap(
-    openTelemetry,
-    OpenAiChatModel.builder()
-        .apiKey(System.getenv("OPENAI_API_KEY"))
-        .modelName("gpt-4o-mini")
-        .temperature(0.0));
-
-var response = model.chat("What is the capital of France?");
-```
-
-#### Tool Wrapping
-
-Use `BraintrustLangchain.wrapTools()` to automatically trace tool executions in your LangChain4j agents:
-
-```java
-// Create your tool class
-public class WeatherTools {
-    @Tool("Get current weather for a location")
-    public String getWeather(String location) {
-        return "The weather in " + location + " is sunny.";
-    }
-}
-
-// Wrap tools to create spans for each tool execution
-WeatherTools tools = new WeatherTools();
-WeatherTools instrumentedTools = BraintrustLangchain.wrapTools(openTelemetry, tools);
-
-// Use instrumented tools in your AI service
-Assistant assistant = AiServices.builder(Assistant.class)
-    .chatModel(model)
-    .tools(instrumentedTools)
-    .build();
-```
-
-Each tool call will automatically create an OpenTelemetry span in Braintrust with:
-- Tool name and parameters
-- Execution duration
-- Return values
-- Any exceptions thrown
-
-**Note:** For proper display in the Braintrust UI, ensure parent spans (conversation, turn, etc.) also set the required Braintrust attributes:
-```java
-var span = tracer.spanBuilder("my-span").startSpan();
-span.setAttribute("braintrust.span_attributes", "{\"type\":\"task\",\"name\":\"my-span\"}");
-span.setAttribute("braintrust.input_json", "{\"user_message\":\"...\"}");
-// ... do work ...
-span.setAttribute("braintrust.output_json", "{\"result\":\"...\"}");
-span.end();
-```
-
-See [LangchainToolWrappingExample.java](./examples/src/main/java/dev/braintrust/examples/LangchainToolWrappingExample.java) for a complete example with proper span hierarchy.
-
 ## Running Examples
 
 Example source code can be found [here](./examples/src/main/java/dev/braintrust/examples)

From 82710328bbe91664803a159ef9ed9ad8e098f7c2 Mon Sep 17 00:00:00 2001
From: Andrew Kent <andrew@braintrustdata.com>
Date: Tue, 20 Jan 2026 16:17:14 -0800
Subject: [PATCH 2/2] update contributing docs

---
 CONTRIBUTING.md | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index e347c5b..c1e4620 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -2,6 +2,8 @@
 
 This file documents developing the SDK itself. If you simply wish to use the SDK or run examples, see [README.md](./README.md)
 
+Because the SDK is new and under active development, third-party contribution best-practices are still being established. If you wish to contribute please open a github issue explaining what you'd like to achieve and a developer will follow-up with you.
+
 ## Setup
 
 - Install JDK 17
@@ -15,7 +17,9 @@ This file documents developing the SDK itself. If you simply wish to use the SDK
   - These hooks automatically run common checks for you but CI also runs the same checks before merging to the main branch is allowed
   - NOTE: this will overwrite existing hooks. Take backups before running
 
-## Running a local OpenTelemetry collector
+## Misc Tips
+
+### Running a local OpenTelemetry collector
 
 OpenTelemetry provides a local collector with a debug exporter which logs all traces, logs, and metrics to stdout.