fix(compression): pass provider to context length resolver in feasibility check

_check_compression_model_feasibility calls get_model_context_length
without provider=, so Codex OAuth users get 1,050,000 (from models.dev
for 'openai') instead of the actual 272,000 limit. This happens because
_infer_provider_from_url maps chatgpt.com → 'openai' (not 'openai-codex'),
skipping the Codex-specific resolution branch entirely.

Result: compression threshold set at 85% of 1.05M = 892K — conversations
never trigger compression, the context grows unbounded, and when gateway
hygiene eventually forces compression, the Codex endpoint drops the
oversized streaming request ('peer closed connection without sending
complete message body').

Fix: forward self.provider to get_model_context_length so provider-
specific resolution branches (Codex OAuth 272K, Copilot live /models,
Nous suffix-match) fire correctly.

Reported by user on GPT 5.5 via Codex OAuth Pro (paste.rs/vsra3).

tests/run_agent/test_compression_feasibility.py

@@ -184,6 +184,7 @@ def test_feasibility_check_passes_config_context_length(mock_get_client, mock_ct
         base_url="http://custom-endpoint:8080/v1",
         api_key="sk-custom",
         config_context_length=1_000_000,
+        provider="openrouter",
     )
 
 
@@ -206,6 +207,7 @@ def test_feasibility_check_ignores_invalid_context_length(mock_get_client, mock_
         base_url="http://custom:8080/v1",
         api_key="sk-test",
         config_context_length=None,
+        provider="openrouter",
     )
 
 
@@ -258,6 +260,7 @@ def test_init_feasibility_check_uses_aux_context_override_from_config():
         base_url="http://custom-endpoint:8080/v1",
         api_key="sk-custom",
         config_context_length=1_000_000,
+        provider="",
     )