Fix old comment and document URL

Signed-off-by: Ed Snible <esnible@acm.org>

Author: esnible

a2a/git_issue_agent/.env.ollama

@@ -2,15 +2,16 @@
 #
 # Uses a local Ollama instance for LLM inference.
 # Prerequisite: Ollama must be running with the model pulled:
-#   ollama pull ibm/granite4:latest
+#   ollama pull gpt-oss:latest
 
 # LLM configuration
 TASK_MODEL_ID=gpt-oss:latest
 # Ollama API base URL. Required by litellm (used by crewai >=1.10).
 # For Docker Desktop / Kind: http://host.docker.internal:11434/v1
 # For in-cluster Ollama:     http://ollama.ollama.svc:11434/v1
+# (This line matches all the other LLM_API_BASE examples in this repo)
 LLM_API_BASE=http://host.docker.internal:11434/v1
-OLLAMA_API_BASE=http://host.docker.internal:11434/v1
+# The API key is a dummy; ollama doesn't use it
 LLM_API_KEY=ollama
 MODEL_TEMPERATURE=0