feat(codex-bridge): split into a splitter and a separate bridge process

bridge.py is now a small splitter with no features: a request for one of
Codex's own models goes to chatgpt.com byte for byte, a request for an added
model goes to kopru.py, which runs as its own process. Codex's own models no
longer pass through the feature code at all, and restarting or losing the
bridge process does not touch them.

Measured with real Codex on spare ports: own model answers; forced compaction
on the own model completes (twice) while the bridge process is restarted;
added model answers; no own-model request reaches the bridge process.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

apps/desktop/assets/codex-bridge/test_access_programs.py

@@ -10,7 +10,7 @@ import urllib.request
 
 # Load only the actual adapter and routing method: no catalog/network/thread
 # startup or credential loading is needed to exercise the production code.
-source = ast.parse(Path(__file__).with_name("bridge.py").read_text(encoding="utf-8"))
+source = ast.parse(Path(__file__).with_name("kopru.py").read_text(encoding="utf-8"))
 flatten = next(n for n in source.body if isinstance(n, ast.FunctionDef) and n.name == "flatten_request")
 claude_sonu = next(n for n in source.body if isinstance(n, ast.FunctionDef) and n.name == "claude_sonu_duzelt")
 handler = next(n for n in source.body if isinstance(n, ast.ClassDef) and n.name == "H")