Switch to zai-glm-4.7: gpt-oss-120b's daily quota is exhausted

Confirmed via Cerebras dashboard: gpt-oss-120b hit 1.07M/1M tokens today. Each free-tier model has its own separate daily quota; switch to zai-glm-4.7 for an untouched budget.

app.py

@@ -101,7 +101,11 @@ class MemoryTrimmer:
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        model_id = os.getenv("AGENT_MODEL_ID", "cerebras/gpt-oss-120b")
+        # gpt-oss-120b's daily token quota (1M, separate per model on
+        # Cerebras) got fully used up mid-session. zai-glm-4.7 has its own
+        # untouched 1M/day quota, so switch there rather than waiting ~24h
+        # for gpt-oss-120b's to reset.
+        model_id = os.getenv("AGENT_MODEL_ID", "cerebras/zai-glm-4.7")
         api_key = os.getenv("CEREBRAS_API_KEY")
         if not api_key:
             print("Warning: CEREBRAS_API_KEY is not set - the agent will fail to call the model.")
@@ -323,7 +327,7 @@ with gr.Blocks() as demo:
         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
         This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
 
-        **Setup:** This agent calls Cerebras (gpt-oss-120b) via `smolagents`. Get a free key at https://cloud.cerebras.ai and set it as the `CEREBRAS_API_KEY` secret in this Space's settings before running.
+        **Setup:** This agent calls Cerebras (zai-glm-4.7) via `smolagents`. Get a free key at https://cloud.cerebras.ai and set it as the `CEREBRAS_API_KEY` secret in this Space's settings before running.
         """
     )