fix(codex): support exec optimizer backend

docs/guideline.html

@@ -394,7 +394,7 @@ <h2>Research model backends</h2>
           <tr><td><code>claude_chat</code></td><td>Yes</td><td>Yes</td><td>Runs an installed, authenticated Claude Code CLI via <code>claude -p</code>; not a direct Anthropic API client.</td></tr>
           <tr><td><code>qwen_chat</code></td><td>Yes</td><td>Yes</td><td>Local or hosted Qwen-compatible server.</td></tr>
           <tr><td><code>minimax_chat</code></td><td>Yes</td><td>Yes</td><td>MiniMax chat endpoint.</td></tr>
-          <tr><td><code>codex_exec</code></td><td>No</td><td>Supported adapters only</td><td>Executes Codex as a target agent.</td></tr>
+          <tr><td><code>codex_exec</code></td><td>Yes</td><td>Supported adapters only</td><td>Executes Codex for optimizer calls and as a target agent where supported.</td></tr>
           <tr><td><code>claude_code_exec</code></td><td>No</td><td>Supported adapters only</td><td>Executes Claude Code as a target agent.</td></tr>
         </tbody>
       </table>

docs/reference/api.md

@@ -190,7 +190,7 @@ not via a base class subclass. Supported values (as of this writing):
 | `qwen_chat` | ✓ | ✓ |
 | `minimax_chat` | ✓ | ✓ |
 | `openai_compatible` | ✓ | ✓ |
-| `codex_exec` | — | ✓ |
+| `codex_exec` | ✓ | ✓ |
 | `claude_code_exec` | — | ✓ |
 
 See `skillopt/model/backend_config.py` for the live whitelist and

docs/reference/config.md

@@ -16,7 +16,7 @@ selecting the generic OpenAI-compatible backend.
 | `claude_chat` | ✓ | ✓ |
 | `qwen_chat` | ✓ | ✓ |
 | `minimax_chat` | ✓ | ✓ |
-| `codex_exec` | — | ✓ |
+| `codex_exec` | ✓ | ✓ |
 | `claude_code_exec` | — | ✓ |
 
 MiniMax currently has one shared deployment. `model.minimax_model` is applied
@@ -28,7 +28,7 @@ MiniMax optimizer model and a different target model.
 | `model.backend` | str | `azure_openai` | Backward-compatible high-level run label |
 | `model.optimizer` | str | `gpt-5.5` | Optimizer deployment/model |
 | `model.target` | str | `gpt-5.5` | Target deployment/model |
-| `model.optimizer_backend` | str | `openai_chat` | Optimizer client path; chat backends only |
+| `model.optimizer_backend` | str | `openai_chat` | Optimizer client path; chat backends plus `codex_exec` |
 | `model.target_backend` | str | `openai_chat` | Target client path; chat or exec backend |
 | `model.reasoning_effort` | str | `medium` | Shared reasoning effort |
 | `model.rewrite_reasoning_effort` | str | empty | Optional full-rewrite effort override |

scripts/eval_only.py

@@ -320,8 +320,10 @@ def _has_model_override(dotted_key: str, legacy_key: str) -> bool:
             cfg.setdefault("optimizer_backend", "claude_chat")
             cfg.setdefault("target_backend", "claude_chat")
         elif backend in {"codex", "codex_exec"}:
-            cfg.setdefault("optimizer_backend", "openai_chat")
-            cfg.setdefault("target_backend", "codex_exec")
+            if not _has_model_override("model.optimizer_backend", "optimizer_backend"):
+                cfg["optimizer_backend"] = "codex_exec"
+            if not _has_model_override("model.target_backend", "target_backend"):
+                cfg["target_backend"] = "codex_exec"
         elif backend == "claude_code_exec":
             cfg.setdefault("optimizer_backend", "openai_chat")
             cfg.setdefault("target_backend", "claude_code_exec")

scripts/train.py

@@ -438,8 +438,10 @@ def _has_model_override(dotted_key: str, legacy_key: str) -> bool:
             flat.setdefault("optimizer_backend", "claude_chat")
             flat.setdefault("target_backend", "claude_chat")
         elif backend in {"codex", "codex_exec"}:
-            flat.setdefault("optimizer_backend", "openai_chat")
-            flat.setdefault("target_backend", "codex_exec")
+            if not _has_model_override("model.optimizer_backend", "optimizer_backend"):
+                flat["optimizer_backend"] = "codex_exec"
+            if not _has_model_override("model.target_backend", "target_backend"):
+                flat["target_backend"] = "codex_exec"
         elif backend == "claude_code_exec":
             flat.setdefault("optimizer_backend", "openai_chat")
             flat.setdefault("target_backend", "claude_code_exec")

skillopt/engine/trainer.py

@@ -670,12 +670,14 @@ def _build_eval_env(split: str, env_num: int, seed: int):
         optimizer_backend = cfg.get("optimizer_backend")
         target_backend = cfg.get("target_backend")
         if not optimizer_backend or not target_backend:
-            if backend in {"claude", "claude_chat"}:
-                optimizer_backend = optimizer_backend or "claude_chat"
-                target_backend = target_backend or "claude_chat"
-            elif backend in {"codex", "codex_exec"}:
-                optimizer_backend = optimizer_backend or "openai_chat"
-                target_backend = target_backend or "codex_exec"
+            if backend in {"claude", "claude_chat"}:
+                optimizer_backend = optimizer_backend or "claude_chat"
+                target_backend = target_backend or "claude_chat"
+            elif backend in {"codex", "codex_exec"}:
+                if optimizer_backend in (None, "", "openai_chat"):
+                    optimizer_backend = "codex_exec"
+                if target_backend in (None, "", "openai_chat"):
+                    target_backend = "codex_exec"
             elif backend == "claude_code_exec":
                 optimizer_backend = optimizer_backend or "openai_chat"
                 target_backend = target_backend or "claude_code_exec"

skillopt/envs/_template/config_template.yaml

@@ -50,6 +50,6 @@ evaluation:
 # ── Model ────────────────────────────────────────
 # Override only what differs from the inherited defaults.
 model:
-  optimizer_backend: openai_chat  # openai_chat | claude_chat | qwen_chat | minimax_chat
-  target_backend: openai_chat     # … plus codex_exec / claude_code_exec for target only
+  optimizer_backend: openai_chat  # openai_chat | claude_chat | qwen_chat | minimax_chat | codex_exec
+  target_backend: openai_chat     # chat backends plus codex_exec / claude_code_exec
   reasoning_effort: medium

skillopt/model/__init__.py

@@ -6,6 +6,7 @@
 
 from skillopt.model import azure_openai as _openai
 from skillopt.model import claude_backend as _claude
+from skillopt.model import codex_backend as _codex
 from skillopt.model import minimax_backend as _minimax
 from skillopt.model import openai_compatible_backend as _openai_compat
 from skillopt.model import qwen_backend as _qwen
@@ -41,10 +42,14 @@ def set_backend(name: str | None) -> str:
         set_target_backend("claude_chat")
         return "claude_chat"
     if normalized == "codex":
-        set_optimizer_backend("openai_chat")
+        set_optimizer_backend("codex_exec")
         set_target_backend("codex_exec")
         return "codex"
-    if normalized in {"codex_exec", "claude_code_exec"}:
+    if normalized == "codex_exec":
+        set_optimizer_backend("codex_exec")
+        set_target_backend("codex_exec")
+        return normalized
+    if normalized == "claude_code_exec":
         set_optimizer_backend("openai_chat")
         set_target_backend(normalized)
         return normalized
@@ -73,7 +78,7 @@ def get_backend_name() -> str:
         return "qwen_chat"
     if optimizer == "openai_chat" and target == "openai_chat":
         return "azure_openai"
-    if optimizer == "openai_chat" and target == "codex_exec":
+    if optimizer == "codex_exec" and target == "codex_exec":
         return "codex"
     if optimizer == "openai_chat" and target == "qwen_chat":
         return "qwen_chat"
@@ -132,6 +137,15 @@ def chat_optimizer(
             reasoning_effort=reasoning_effort,
             timeout=timeout,
         )
+    if get_optimizer_backend() == "codex_exec":
+        return _codex.chat_optimizer(
+            system=system,
+            user=user,
+            max_completion_tokens=max_completion_tokens,
+            retries=retries,
+            stage=stage,
+            timeout=timeout,
+        )
     return _openai.chat_optimizer(
         system=system,
         user=user,
@@ -265,6 +279,17 @@ def chat_optimizer_messages(
             return_message=return_message,
             timeout=timeout,
         )
+    if get_optimizer_backend() == "codex_exec":
+        return _codex.chat_optimizer_messages(
+            messages=messages,
+            max_completion_tokens=max_completion_tokens,
+            retries=retries,
+            stage=stage,
+            tools=tools,
+            tool_choice=tool_choice,
+            return_message=return_message,
+            timeout=timeout,
+        )
     return _openai.chat_optimizer_messages(
         messages=messages,
         max_completion_tokens=max_completion_tokens,
@@ -449,6 +474,17 @@ def get_token_summary() -> dict:
         summary[stage]["prompt_tokens"] += values["prompt_tokens"]
         summary[stage]["completion_tokens"] += values["completion_tokens"]
         summary[stage]["total_tokens"] += values["total_tokens"]
+    codex_summary = _codex.get_token_summary()
+    for stage, values in codex_summary.items():
+        if stage == "_total":
+            continue
+        if stage not in summary:
+            summary[stage] = values
+            continue
+        summary[stage]["calls"] += values["calls"]
+        summary[stage]["prompt_tokens"] += values["prompt_tokens"]
+        summary[stage]["completion_tokens"] += values["completion_tokens"]
+        summary[stage]["total_tokens"] += values["total_tokens"]
     total = {
         "calls": 0,
         "prompt_tokens": 0,
@@ -472,6 +508,7 @@ def reset_token_tracker() -> None:
     _qwen.reset_token_tracker()
     _minimax.reset_token_tracker()
     _openai_compat.reset_token_tracker()
+    _codex.reset_token_tracker()
 
 
 def configure_azure_openai(
@@ -622,6 +659,7 @@ def set_reasoning_effort(effort: str | None) -> None:
     _qwen.set_reasoning_effort(effort)
     _minimax.set_reasoning_effort(effort)
     _openai_compat.set_reasoning_effort(effort)
+    _codex.set_reasoning_effort(effort)
 
 
 def set_target_deployment(deployment: str) -> None:
@@ -630,10 +668,12 @@ def set_target_deployment(deployment: str) -> None:
     _qwen.set_target_deployment(deployment)
     _minimax.set_target_deployment(deployment)
     _openai_compat.set_target_deployment(deployment)
+    _codex.set_target_deployment(deployment)
 
 
 def set_optimizer_deployment(deployment: str) -> None:
     _openai.set_optimizer_deployment(deployment)
     _claude.set_optimizer_deployment(deployment)
     _qwen.set_optimizer_deployment(deployment)
     _openai_compat.set_optimizer_deployment(deployment)
+    _codex.set_optimizer_deployment(deployment)

skillopt/model/backend_config.py

@@ -49,10 +49,18 @@ def _parse_int(value: str | None, default: int) -> int:
 def set_optimizer_backend(backend: str) -> None:
     global OPTIMIZER_BACKEND
     OPTIMIZER_BACKEND = normalize_backend_name(backend or "openai_chat")
-    if OPTIMIZER_BACKEND not in {"openai_chat", "claude_chat", "qwen_chat", "minimax_chat", "openai_compatible"}:
+    if OPTIMIZER_BACKEND not in {
+        "openai_chat",
+        "claude_chat",
+        "qwen_chat",
+        "minimax_chat",
+        "openai_compatible",
+        "codex_exec",
+    }:
         raise ValueError(
             f"Unsupported optimizer backend: {OPTIMIZER_BACKEND!r}. "
-            "Supported values are 'openai_chat', 'claude_chat', 'qwen_chat', 'minimax_chat', and 'openai_compatible'."
+            "Supported values are 'openai_chat', 'claude_chat', 'qwen_chat', 'minimax_chat', "
+            "'openai_compatible', and 'codex_exec'."
         )
     os.environ["OPTIMIZER_BACKEND"] = OPTIMIZER_BACKEND
 
@@ -81,7 +89,14 @@ def is_target_exec_backend() -> bool:
 
 
 def is_optimizer_chat_backend() -> bool:
-    return OPTIMIZER_BACKEND in {"openai_chat", "claude_chat", "qwen_chat", "minimax_chat", "openai_compatible"}
+    return OPTIMIZER_BACKEND in {
+        "openai_chat",
+        "claude_chat",
+        "qwen_chat",
+        "minimax_chat",
+        "openai_compatible",
+        "codex_exec",
+    }
 
 
 def is_target_chat_backend() -> bool:

skillopt/model/codex_backend.py

@@ -18,6 +18,7 @@
     CompatToolFunction,
     tracker,
 )
+from skillopt.model.backend_config import get_codex_exec_config
 
 
 CODEX_BIN = os.environ.get("CODEX_CLI_BIN", "codex")
@@ -286,20 +287,21 @@ def _run_codex_exec(
     timeout: int | None,
 ) -> tuple[str, dict[str, int]]:
     with tempfile.TemporaryDirectory(prefix="skillopt_codex_") as temp_dir:
+        config = get_codex_exec_config()
         output_path = os.path.join(temp_dir, "last_message.txt")
         image_paths = _materialize_attachments(attachments, temp_dir)
+        profile = str(config.get("profile") or os.environ.get("CODEX_PROFILE", "")).strip()
+        reasoning_effort = str(REASONING_EFFORT or config.get("reasoning_effort") or "").strip()
 
         command = [
-            CODEX_BIN,
+            str(config.get("path") or CODEX_BIN),
             "exec",
             "--json",
             "--ephemeral",
-            "--profile",
-            CODEX_PROFILE,
             "-c",
-            "approval_policy=\"never\"",
+            f"approval_policy={json.dumps(str(config.get('approval_policy') or 'never'))}",
             "--sandbox",
-            CODEX_SANDBOX_MODE,
+            str(config.get("sandbox") or CODEX_SANDBOX_MODE),
             "--skip-git-repo-check",
             "--cd",
             _default_working_directory(),
@@ -309,8 +311,11 @@ def _run_codex_exec(
             output_path,
         ]
 
-        if REASONING_EFFORT:
-            command.extend(["-c", f"model_reasoning_effort={json.dumps(REASONING_EFFORT)}"])
+        if profile:
+            command.extend(["--profile", profile])
+
+        if reasoning_effort and reasoning_effort != "none":
+            command.extend(["-c", f"model_reasoning_effort={json.dumps(reasoning_effort)}"])
 
         schema_path = None
         if output_schema is not None: