ui: capitalize memory strategy labels; cap max_turns at 50

- Memory Strategy radio: Condenser (default) / Vanilla / Discard-all / Hide-tool-result
- Help text bolded names match
- Max Turns slider upper bound 100 -> 50

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

app.py

@@ -1914,26 +1914,26 @@ with gr.Blocks(
                 memory_strategy = gr.Radio(
                     label="Memory Strategy",
                     choices=[
-                        ("condenser (default)", "condenser"),
-                        ("vanilla", "vanilla"),
-                        ("discard-all", "discard_all"),
-                        ("hide-tool-result", "hide_tool_result"),
+                        ("Condenser (default)", "condenser"),
+                        ("Vanilla", "vanilla"),
+                        ("Discard-all", "discard_all"),
+                        ("Hide-tool-result", "hide_tool_result"),
                     ],
                     value="condenser",
                     elem_id="quest-memory-strategy",
                 )
                 gr.HTML(
                     '<div class="memory-help">'
-                    '<b>condenser</b> (default) — when context grows large, a State Summarizer LLM compresses earlier turns into a structured JSON of trusted/untrusted/uncertain claims, visited sources, and prior search queries; the agent continues with that compact state.<br>'
-                    '<b>vanilla</b> — memory management disabled; the full conversation history is kept.<br>'
-                    '<b>discard-all</b> — when context grows large, the entire message history is reset, restarting the agent from the original question with no accumulated context.<br>'
-                    '<b>hide-tool-result</b> — when context grows large, older tool responses are pruned; only the most recent tool result is kept.'
+                    '<b>Condenser</b> (default) — when context grows large, a State Summarizer LLM compresses earlier turns into a structured JSON of trusted/untrusted/uncertain claims, visited sources, and prior search queries; the agent continues with that compact state.<br>'
+                    '<b>Vanilla</b> — memory management disabled; the full conversation history is kept.<br>'
+                    '<b>Discard-all</b> — when context grows large, the entire message history is reset, restarting the agent from the original question with no accumulated context.<br>'
+                    '<b>Hide-tool-result</b> — when context grows large, older tool responses are pruned; only the most recent tool result is kept.'
                     '</div>'
                 )
                 max_turns = gr.Slider(
                     label="Max Turns",
                     minimum=2,
-                    maximum=100,
+                    maximum=50,
                     value=6,
                     step=1,
                     elem_id="quest-max-turns",