chore: Align example config keys and env vars with new naming (#29)

Author: jsonbailey

features/create_agent/.env.example

@@ -0,0 +1,8 @@
+# Your LaunchDarkly server-side SDK key
+LAUNCHDARKLY_SDK_KEY=
+
+# Provider API key(s) for the provider your agent config uses
+OPENAI_API_KEY=
+
+# Override to use a different AI Config
+LAUNCHDARKLY_AGENT_KEY=sample-agent

features/create_agent/README.md

@@ -13,14 +13,12 @@ This example demonstrates how to use LaunchDarkly's `create_agent` method, which
 
 1. Create the following config in your LaunchDarkly project. You can use a different key by setting the environment variable in your `.env`.
 
-   - [Create an AI Agent Config](https://launchdarkly.com/docs/home/ai-configs/agents) with a model and agent instructions. Default key: `sample-agent-config`.
+   - [Create an AI Agent Config](https://launchdarkly.com/docs/home/ai-configs/agents) with a model and agent instructions. Default key: `sample-agent`.
 
-1. Create a `.env` file in this directory with the following variables:
+1. Copy `.env.example` to `.env` and fill in your keys:
 
-   ```
-   LAUNCHDARKLY_SDK_KEY=your-launchdarkly-sdk-key
-   LAUNCHDARKLY_AGENT_CONFIG_KEY=sample-agent-config
-   OPENAI_API_KEY=your-openai-api-key
+   ```bash
+   cp .env.example .env
    ```
 
 1. Install the required dependencies:

features/create_agent/create_agent_example.py

@@ -17,7 +17,7 @@
 sdk_key = os.getenv('LAUNCHDARKLY_SDK_KEY')
 
 # Set agent_config_key to the AI Agent Config key you want to evaluate.
-agent_config_key = os.getenv('LAUNCHDARKLY_AGENT_CONFIG_KEY', 'sample-agent-config')
+agent_config_key = os.getenv('LAUNCHDARKLY_AGENT_KEY', 'sample-agent')
 
 
 def get_weather(city: str) -> str:
@@ -110,6 +110,7 @@ async def async_main():
             print("\nNo judge evaluations were performed.")
 
     except Exception as err:
+        # In production, sanitize before logging — provider errors may include credentials.
         print("Error:", err)
     finally:
         # Flush pending events and close the client.

features/create_agent_graph/.env.example

@@ -0,0 +1,8 @@
+# Your LaunchDarkly server-side SDK key
+LAUNCHDARKLY_SDK_KEY=
+
+# Provider API key(s) for the provider(s) your agent graph uses
+OPENAI_API_KEY=
+
+# Override to use a different AI Config
+LAUNCHDARKLY_AGENT_GRAPH_KEY=sample-agent-graph

features/create_agent_graph/README.md

@@ -16,12 +16,10 @@ This example demonstrates how to use LaunchDarkly's `create_agent_graph` method,
    - [Create AI Agent Configs](https://launchdarkly.com/docs/home/ai-configs/agents) for each node in your graph. Configure each with a model and agent instructions. Add tools (e.g. `search_flights`, `search_hotels`, `get_weather`) to the agents that need them.
    - [Create an Agent Graph](https://launchdarkly.com/docs/home/ai-configs/create) that connects your agent configs as nodes with edges defining the workflow. Default key: `sample-agent-graph`.
 
-1. Create a `.env` file in this directory with the following variables:
+1. Copy `.env.example` to `.env` and fill in your keys:
 
-   ```
-   LAUNCHDARKLY_SDK_KEY=your-launchdarkly-sdk-key
-   LAUNCHDARKLY_AGENT_GRAPH_KEY=sample-agent-graph
-   OPENAI_API_KEY=your-openai-api-key
+   ```bash
+   cp .env.example .env
    ```
 
 1. Install the required dependencies:

features/create_agent_graph/create_agent_graph_example.py

@@ -128,6 +128,7 @@ async def async_main():
                 print(f"  reasoning: {eval_result.reasoning}")
 
     except Exception as err:
+        # In production, sanitize before logging — provider errors may include credentials.
         print("Error:", err)
     finally:
         # Flush pending events and close the client.

features/create_judge/.env.example

@@ -0,0 +1,8 @@
+# Your LaunchDarkly server-side SDK key
+LAUNCHDARKLY_SDK_KEY=
+
+# Provider API key(s) for the provider your judge config uses
+OPENAI_API_KEY=
+
+# Override to use a different AI Config
+LAUNCHDARKLY_JUDGE_KEY=sample-judge

features/create_judge/README.md

@@ -13,14 +13,12 @@ This example demonstrates how to use LaunchDarkly's `create_judge` method to eva
 
 1. Create the following config in your LaunchDarkly project. You can use a different key by setting the environment variable in your `.env`.
 
-   - [Create a Judge Config](https://launchdarkly.com/docs/home/ai-configs/judges) for evaluation. Default key: `sample-ai-judge`.
+   - [Create a Judge Config](https://launchdarkly.com/docs/home/ai-configs/judges) for evaluation. Default key: `sample-judge`.
 
-1. Create a `.env` file in this directory with the following variables:
+1. Copy `.env.example` to `.env` and fill in your keys:
 
-   ```
-   LAUNCHDARKLY_SDK_KEY=your-launchdarkly-sdk-key
-   LAUNCHDARKLY_AI_JUDGE_KEY=sample-ai-judge
-   OPENAI_API_KEY=your-openai-api-key
+   ```bash
+   cp .env.example .env
    ```
 
 1. Install the required dependencies:

features/create_judge/create_judge_example.py

@@ -17,7 +17,7 @@
 sdk_key = os.getenv('LAUNCHDARKLY_SDK_KEY')
 
 # Set judge_key to the Judge key you want to use.
-judge_key = os.getenv('LAUNCHDARKLY_AI_JUDGE_KEY', 'sample-ai-judge')
+judge_key = os.getenv('LAUNCHDARKLY_JUDGE_KEY', 'sample-judge')
 
 
 async def async_main():
@@ -95,6 +95,7 @@ async def async_main():
 
         print("\nDone!")
     except Exception as err:
+        # In production, sanitize before logging — provider errors may include credentials.
         print("Error:", err)
     finally:
         # Flush pending events and close the client.

features/create_model/.env.example

@@ -0,0 +1,8 @@
+# Your LaunchDarkly server-side SDK key
+LAUNCHDARKLY_SDK_KEY=
+
+# Provider API key(s) for the provider your AI config uses
+OPENAI_API_KEY=
+
+# Override to use a different AI Config
+LAUNCHDARKLY_COMPLETION_KEY=sample-completion