Fix release_radar version extraction and customer-support voice model (#1020)

- release_radar_agent/radar.py: _extract_version returned matches[-1], the
  exclusive upper bound of a version range (e.g. '>=1.10.0,<2.0.0' -> '2.0.0'),
  so build_release_candidates saw no delta and suppressed every alert. Use
  matches[0] (the pinned/lower bound). Exact pins/tags give a single match, so
  the 5 shipped unit tests still pass.
- customer_support_voice_agent.py: the Text-to-Speech Agent is invoked via
  Runner.run (chat endpoint) but was built with model='gpt-4o-mini-tts', a
  speech-only model, so every query errored. Use 'gpt-4o' (matching the sibling
  voice_rag_openaisdk app); the real speech call at line 288 keeps gpt-4o-mini-tts.

Fixes #1019

Co-authored-by: thejesh23 <thejesh23@users.noreply.github.com>

always_on_agents/release_radar_agent/radar.py

@@ -64,7 +64,9 @@ def _normalize_name(name: str) -> str:
 
 def _extract_version(specifier: str) -> str | None:
     matches = VERSION_PATTERN.findall(specifier)
-    return matches[-1] if matches else None
+    # Specifiers put the pinned/lower bound first ("==1.2.3", ">=1.2.3,<2.0.0"),
+    # so the last match is the exclusive upper bound, not the installed version.
+    return matches[0] if matches else None
 
 
 def _github_repo_from_spec(specifier: str) -> str | None:

voice_ai_agents/customer_support_voice_agent/customer_support_voice_agent.py

@@ -237,7 +237,7 @@ def setup_agents(openai_api_key: str):
         4. Keep the tone professional but friendly
         5. Use appropriate pauses for better comprehension
         6. Ensure the speech is clear and well-articulated""",
-        model="gpt-4o-mini-tts"
+        model="gpt-4o"
     )
     
     return processor_agent, tts_agent