try developer tier

docs/stylesheets/extra.css

@@ -66,7 +66,7 @@
   padding: 1em;
   font-weight: 500;
   position: relative;
-  z-index: 1000;
+  z-index: 3;
   border: 2px solid #FFD15D;
   border-radius: 0.25em;
   margin-bottom: 2em;

examples/azure/README.md

@@ -1,8 +1,8 @@
 # Supervised Fine-tuning with Azure OpenAI
 
-This example walks through an end-to-end supervised fine-tuning loop on Azure OpenAI. The trainer runs a toy capital-lookup agent, collects traces with rewards, submits fine-tuning jobs using those traces, and deploys every successful checkpoint as a new Azure OpenAI deployment.
+[![azure CI status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-azure.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-azure.yml)
 
-**NOTE: The example is tested and compatible with Agent-lightning v0.2.x, but it's not yet maintained on CI due to the difficulty of maintaining a logged-in status in the testing environment.**
+This example walks through an end-to-end supervised fine-tuning loop on Azure OpenAI. The trainer runs a toy capital-lookup agent, collects traces with rewards, submits fine-tuning jobs using those traces, and deploys every successful checkpoint as a new Azure OpenAI deployment.
 
 ## Prerequisites
 

examples/azure/aoai_finetune.py

@@ -391,7 +391,7 @@ class AzureOpenAIFinetune(Algorithm):
                 suffix=f"v{next_iteration:02d}",
                 # NOTE: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning
                 # Other options are "GlobalStandard" and "Standard"
-                extra_body={"trainingType": "GlobalStandard"},
+                extra_body={"trainingType": "DeveloperTier"},
             )
             job_id = job.id
             self._log_info("Fine-tuning job %s created for base model %s.", job_id, base_model)

examples/tinker/README.md

@@ -1,8 +1,8 @@
 # Tinker + Agent-lightning Integration
 
-This example shows how to use [Tinker's reinforcement-learning infrastructure](https://tinker-docs.thinkingmachines.ai/) as a fine-tuning backend for agents written against Agent-lightning. You author the agent exactly the way you would for deployment, while the bridge code reconstructs Tinker-compatible trajectories from Agent-lightning traces.
+[![tinker CI status](https://github.com/microsoft/agent-lightning/actions/workflows/examples-tinker.yml/badge.svg)](https://github.com/microsoft/agent-lightning/actions/workflows/examples-tinker.yml)
 
-**NOTE: The example is tested and compatible with Agent-lightning v0.2.x, but it's not yet maintained on CI due to the cost of running the Tinker training service.**
+This example shows how to use [Tinker's reinforcement-learning infrastructure](https://tinker-docs.thinkingmachines.ai/) as a fine-tuning backend for agents written against Agent-lightning. You author the agent exactly the way you would for deployment, while the bridge code reconstructs Tinker-compatible trajectories from Agent-lightning traces.
 
 ## How this differs from the original Tinker Cookbook RL recipe