feat(ollama): allow Custom model ID in the CLI dropdown

Users with other models pulled via `ollama pull` (beyond the three
suggested defaults) can now select "Custom model ID" and type any
model name. Matches the same pattern used for DeepSeek, GLM, Qwen,
and MiniMax — the existing _prompt_custom_model_id flow handles the
"custom" value generically, so this is a one-row catalog addition
plus regression coverage.

tradingagents/llm_clients/model_catalog.py

@@ -159,16 +159,20 @@ MODEL_OPTIONS: ProviderModeOptions = {
     # apply whether the user runs ollama-serve on localhost or against a
     # remote host. The actual resolved endpoint is surfaced separately by
     # cli.utils.confirm_ollama_endpoint() right after provider selection.
+    # "Custom model ID" lets users pick any model they have pulled via
+    # `ollama pull` beyond the three suggested defaults.
     "ollama": {
         "quick": [
             ("Qwen3:latest (8B)", "qwen3:latest"),
             ("GPT-OSS:latest (20B)", "gpt-oss:latest"),
             ("GLM-4.7-Flash:latest (30B)", "glm-4.7-flash:latest"),
+            ("Custom model ID", "custom"),
         ],
         "deep": [
             ("GLM-4.7-Flash:latest (30B)", "glm-4.7-flash:latest"),
             ("GPT-OSS:latest (20B)", "gpt-oss:latest"),
             ("Qwen3:latest (8B)", "qwen3:latest"),
+            ("Custom model ID", "custom"),
         ],
     },
 }