feat(runtime): OpenAI-compatible transport for cloud-pinned operator execution

Merges prototype/openai-compat-transport (7b268e1). The operator's execution
substrate had exactly one transport (OllamaChatTransport, localhost:11434) —
send_task(model='<Provider>/<model>') posted cloud model names to Ollama's
/api/chat and 400'd (observed live: Verboo Code/glm-5.3-flash, 0.2s). The
supported model= override could not execute ANY cloud provider.

OpenAICompatTransport speaks the OpenAI wire format (/chat/completions) and
returns Ollama-shaped responses (LocalToolRuntime loop unchanged). Selection
is deterministic on routing_mode=='cloud' — no router, ladder, or escalation
change. Provider config resolved from the same source of truth the mimo CLI
uses (mimocode.jsonc baseURL + auth.json key).

Translation unit tests (6) + live smoke against the real Verboo API
(TRANSPORT-SMOKE-OK). Umbrella manifest updated. Stray experiment files
removed. 1295 tests green; ratchet 352/80; henxels clean.

config/umbrellas.json

@@ -118,6 +118,7 @@
         "tool_executor",
         "tool_protocol",
         "local_tool_runtime",
+        "openai_compat_transport",
         "forge_client",
         "message_queue",
         "connection_pool",

docs/wr-fail-marker.py

@@ -1 +0,0 @@
-def broken(:

wr_failure_fixture.py

@@ -1 +0,0 @@
-def broken(: