From f2fe3afae59431202e7d66c37ee0715db2e98947 Mon Sep 17 00:00:00 2001
From: "openclaw-docs-sync[bot]"
 <openclaw-docs-sync[bot]@users.noreply.github.com>
Date: Sun, 26 Apr 2026 03:38:33 +0000
Subject: [PATCH] chore(sync): mirror docs from
 openclaw/openclaw@b58223510c8134f4a91f6c289a4e8fe715dcb925

---
 .openclaw-sync/source.json    |  4 ++--
 docs/gateway/config-agents.md |  1 +
 docs/providers/zai.md         | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 686ed74ca..8fb5318da 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "2c8c79de5c778d25eba6a65c6fcbf38c107f42a9",
-  "syncedAt": "2026-04-26T03:29:14.078Z"
+  "sha": "b58223510c8134f4a91f6c289a4e8fe715dcb925",
+  "syncedAt": "2026-04-26T03:36:59.099Z"
 }
diff --git a/docs/gateway/config-agents.md b/docs/gateway/config-agents.md
index d5acd35f5..2586567c3 100644
--- a/docs/gateway/config-agents.md
+++ b/docs/gateway/config-agents.md
@@ -372,6 +372,7 @@ Time format in system prompt. Default: `auto` (OS preference).
 - `params` merge precedence (config): `agents.defaults.params` (global base) is overridden by `agents.defaults.models["provider/model"].params` (per-model), then `agents.list[].params` (matching agent id) overrides by key. See [Prompt Caching](/reference/prompt-caching) for details.
 - `params.extra_body`/`params.extraBody`: advanced pass-through JSON merged into `api: "openai-completions"` request bodies for OpenAI-compatible proxies. If it collides with generated request keys, the extra body wins; non-native completions routes still strip OpenAI-only `store` afterward.
 - `params.chat_template_kwargs`: vLLM/OpenAI-compatible chat-template arguments merged into top-level `api: "openai-completions"` request bodies. For `vllm/nemotron-3-*` with thinking off, OpenClaw automatically sends `enable_thinking: false` and `force_nonempty_content: true`; explicit `chat_template_kwargs` override those defaults, and `extra_body.chat_template_kwargs` still has final precedence.
+- `params.preserveThinking`: Z.AI-only opt-in for preserved thinking. When enabled and thinking is on, OpenClaw sends `thinking.clear_thinking: false` and replays prior `reasoning_content`; see [Z.AI thinking and preserved thinking](/providers/zai#thinking-and-preserved-thinking).
 - `embeddedHarness`: default low-level embedded agent runtime policy. Omitted runtime defaults to OpenClaw Pi. Use `runtime: "pi"` to force the built-in PI harness, `runtime: "auto"` to let registered plugin harnesses claim supported models, or a registered harness id such as `runtime: "codex"`. Set `fallback: "none"` to disable automatic PI fallback. Explicit plugin runtimes such as `codex` fail closed by default unless you set `fallback: "pi"` in the same override scope. Keep model refs canonical as `provider/model`; select Codex, Claude CLI, Gemini CLI, and other execution backends through runtime config instead of legacy runtime provider prefixes. See [Agent runtimes](/concepts/agent-runtimes) for how this differs from provider/model selection.
 - Config writers that mutate these fields (for example `/models set`, `/models set-image`, and fallback add/remove commands) save canonical object form and preserve existing fallback lists when possible.
 - `maxConcurrent`: max parallel agent runs across sessions (each session still serialized). Default: 4.
diff --git a/docs/providers/zai.md b/docs/providers/zai.md
index 114965543..43f45d7e8 100644
--- a/docs/providers/zai.md
+++ b/docs/providers/zai.md
@@ -132,6 +132,38 @@ GLM models are available as `zai/<model>` (example: `zai/glm-5`). The default bu
 
   </Accordion>
 
+  <Accordion title="Thinking and preserved thinking">
+    Z.AI thinking follows OpenClaw's `/think` controls. With thinking off,
+    OpenClaw sends `thinking: { type: "disabled" }` to avoid responses that
+    spend the output budget on `reasoning_content` before visible text.
+
+    Preserved thinking is opt-in because Z.AI requires the full historical
+    `reasoning_content` to be replayed, which increases prompt tokens. Enable it
+    per model:
+
+    ```json5
+    {
+      agents: {
+        defaults: {
+          models: {
+            "zai/glm-5.1": {
+              params: { preserveThinking: true },
+            },
+          },
+        },
+      },
+    }
+    ```
+
+    When enabled and thinking is on, OpenClaw sends
+    `thinking: { type: "enabled", clear_thinking: false }` and replays prior
+    `reasoning_content` for the same OpenAI-compatible transcript.
+
+    Advanced users can still override the exact provider payload with
+    `params.extra_body.thinking`.
+
+  </Accordion>
+
   <Accordion title="Image understanding">
     The bundled Z.AI plugin registers image understanding.