From d1f2f8fae12bfb2bbe3b31889bbb2fb2af1759c2 Mon Sep 17 00:00:00 2001
From: Rohith Pariki <rohithpariki@gmail.com>
Date: Fri, 4 Sep 2026 05:01:39 +0530
Subject: [PATCH] fix(docs): clarify claude_code_exec and codex_exec optimizer
 support

---
 docs/guide/configuration.md |  4 ++--
 docs/reference/cli.md       | 24 ++++++++++++++++++++++++
 docs/reference/config.md    |  4 ++--
 3 files changed, 28 insertions(+), 4 deletions(-)

diff --git a/docs/guide/configuration.md b/docs/guide/configuration.md
index 7cc5479b..43467b22 100644
--- a/docs/guide/configuration.md
+++ b/docs/guide/configuration.md
@@ -44,8 +44,8 @@ model:
 | `qwen_chat` | ✓ | ✓ | Qwen served through an OpenAI-compatible endpoint (self-hosted vLLM/SGLang or a hosted gateway) |
 | `minimax_chat` | ✓ | ✓ | MiniMax API |
 | `copilot_chat` | ✓ | ✓ | GitHub Copilot CLI (`copilot -p`); alias `copilot` |
-| `codex_exec` | — | ✓ | Codex CLI execution harness |
-| `claude_code_exec` | — | ✓ | Claude Code CLI execution harness |
+| `codex_exec` | ✓ | ✓ | Codex CLI execution harness |
+| `claude_code_exec` | ✓ | ✓ | Claude Code CLI execution harness |
 | `cursor_exec` | — | ✓ | Cursor Agent CLI execution harness |
 | `copilot_exec` | — | ✓ | GitHub Copilot CLI execution harness |
 
diff --git a/docs/reference/cli.md b/docs/reference/cli.md
index 6aefbb20..ff972443 100644
--- a/docs/reference/cli.md
+++ b/docs/reference/cli.md
@@ -115,6 +115,30 @@ disabled. Read-only Ask-mode rollouts may explicitly disable it. Override the
 executable or sandbox through `model.cursor_exec_path` and
 `model.cursor_exec_sandbox`.
 
+To train or evaluate with the Claude Code CLI execution harness (`claude_code_exec`):
+
+```bash
+# Target-only rollout through Claude Code (optimizer defaults to configured chat backend):
+python scripts/train.py \
+  --config configs/searchqa/default.yaml \
+  --backend claude_code_exec
+
+# Explicitly drive both target and optimizer roles with Claude Code:
+python scripts/train.py \
+  --config configs/searchqa/default.yaml \
+  --cfg-options \
+    model.optimizer_backend=claude_code_exec \
+    model.target_backend=claude_code_exec
+```
+
+When `claude_code_exec` is selected as the target backend, SkillOpt streams SDK
+messages from the Claude Code process and parses text, tool calls, and tool
+results into structured trace steps (`claude_trace_steps.txt`). When
+`model.claude_trace_to_optimizer` is enabled (`true` by default), these trace
+steps are injected into the reflection prompt so the optimizer can inspect the
+agent's intermediate actions.
+
+
 ## SkillOpt-Sleep
 
 ```bash
diff --git a/docs/reference/config.md b/docs/reference/config.md
index e7111430..6371f69d 100644
--- a/docs/reference/config.md
+++ b/docs/reference/config.md
@@ -18,7 +18,7 @@ selecting the generic OpenAI-compatible backend.
 | `minimax_chat` | ✓ | ✓ |
 | `copilot_chat` | ✓ | ✓ |
 | `codex_exec` | ✓ | ✓ |
-| `claude_code_exec` | — | ✓ |
+| `claude_code_exec` | ✓ | ✓ |
 | `cursor_exec` | — | ✓ |
 | `copilot_exec` | — | ✓ |
 
@@ -34,7 +34,7 @@ resolves to `https://api.minimax.io/v1` and `cn_zh` resolves to
 | `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 plus `codex_exec` |
+| `model.optimizer_backend` | str | `openai_chat` | Optimizer client path; chat backends plus `codex_exec` and `claude_code_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 |