codex: route OSS models through responses, not chat

Codex CLI dropped support for `wire_api = "chat"` (openai/codex
discussion 7782), so the OSS chat-completions route added for kimi/glm
now fails to load with "`wire_api = "chat"` is no longer supported".
Route every codex-harness model — including OSS families — through the
Responses gateway, matching what all other codex models already use.

Co-authored-by: Isaac

Author: lilly-luo

src/ucode/agents/codex.py

@@ -17,10 +17,8 @@
 )
 from ucode.databricks import (
     build_auth_token_argv,
-    build_oss_base_url,
     build_tool_base_url,
     get_databricks_token,
-    is_oss_model,
 )
 from ucode.launcher import exec_or_spawn
 from ucode.state import mark_tool_managed, save_state
@@ -109,14 +107,9 @@ def _provider_block(
     databricks_profile: str | None,
     use_pat: bool = False,
     provider: str | None = None,
-    model: str | None = None,
 ) -> dict:
     auth_argv = build_auth_token_argv(workspace, databricks_profile, use_pat=use_pat)
-    # OSS chat models (kimi/glm) don't speak the Responses API — they're served
-    # by the OpenAI-compatible MLflow chat-completions gateway. Route them there
-    # with `wire_api = "chat"`; everything else uses the codex Responses route.
-    oss = is_oss_model(model)
-    base_url = build_oss_base_url(workspace) if oss else build_tool_base_url("codex", workspace)
+    base_url = build_tool_base_url("codex", workspace)
     http_headers = {
         "User-Agent": f"ucode/{ucode_version()} codex/{agent_version('codex')}",
     }
@@ -127,7 +120,7 @@ def _provider_block(
     return {
         "name": "Databricks AI Gateway",
         "base_url": base_url,
-        "wire_api": "chat" if oss else "responses",
+        "wire_api": "responses",
         "http_headers": http_headers,
         # Run the `ucode auth-token` executable directly (not via `sh -c`) so the
         # helper works on Windows, where there is no POSIX shell (issue #116).
@@ -152,7 +145,7 @@ def render_overlay(
         overlay["model"] = model
     overlay["model_providers"] = {
         CODEX_MODEL_PROVIDER_NAME: _provider_block(
-            workspace, databricks_profile, use_pat, provider, model
+            workspace, databricks_profile, use_pat, provider
         ),
     }
     return overlay
@@ -178,7 +171,7 @@ def render_legacy_overlay(
         "profiles": {CODEX_PROFILE_NAME: profile_block},
         "model_providers": {
             CODEX_MODEL_PROVIDER_NAME: _provider_block(
-                workspace, databricks_profile, use_pat, provider, model
+                workspace, databricks_profile, use_pat, provider
             ),
         },
     }

tests/test_agent_codex.py

@@ -45,28 +45,6 @@ def test_provider_wire_api(self):
         provider = overlay["model_providers"]["ucode-databricks"]
         assert provider["wire_api"] == "responses"
 
-    def test_oss_model_routes_to_mlflow_chat(self):
-        overlay = codex.render_overlay(WS, "system.ai.kimi-k2")
-        provider = overlay["model_providers"]["ucode-databricks"]
-        assert provider["base_url"] == f"{WS}/ai-gateway/mlflow/v1"
-        assert provider["wire_api"] == "chat"
-
-    def test_oss_glm_model_routes_to_mlflow_chat(self):
-        overlay = codex.render_overlay(WS, "system.ai.glm-4-6")
-        provider = overlay["model_providers"]["ucode-databricks"]
-        assert provider["base_url"] == f"{WS}/ai-gateway/mlflow/v1"
-        assert provider["wire_api"] == "chat"
-
-    def test_oss_model_pinned_verbatim(self):
-        overlay = codex.render_overlay(WS, "system.ai.kimi-k2")
-        assert overlay["model"] == "system.ai.kimi-k2"
-
-    def test_gpt_model_still_uses_responses_route(self):
-        overlay = codex.render_overlay(WS, "system.ai.gpt-5")
-        provider = overlay["model_providers"]["ucode-databricks"]
-        assert provider["base_url"] == f"{WS}/ai-gateway/codex/v1"
-        assert provider["wire_api"] == "responses"
-
     def test_auth_runs_ucode_auth_token(self):
         # The auth command runs the `ucode auth-token` executable directly
         # (not `sh -c`), so it works on Windows where there is no POSIX shell.