diff --git a/docs/plugins/codex-harness-reference.md b/docs/plugins/codex-harness-reference.md
index a1a46beb5da4..dbf67e3cde88 100644
--- a/docs/plugins/codex-harness-reference.md
+++ b/docs/plugins/codex-harness-reference.md
@@ -50,7 +50,7 @@ Top-level fields:
 ## App-server transport
 
 By default OpenClaw starts the managed Codex binary shipped with the bundled
-plugin (currently `@openai/codex` `0.142.5`):
+plugin (currently `@openai/codex` `0.143.0`):
 
 ```bash
 codex app-server --listen stdio://
@@ -146,7 +146,7 @@ permission profile instead. Codex-managed network enforcement is sandboxed
 networking, so a full-access profile would not protect outbound traffic.
 
 The plugin blocks older or unversioned app-server handshakes: Codex app-server
-must report stable version `0.142.0` or newer.
+must report stable version `0.143.0` or newer.
 
 OpenClaw treats non-loopback WebSocket app-server URLs as remote and requires
 identity-bearing WebSocket auth through `appServer.authToken` or an
@@ -462,16 +462,17 @@ If discovery fails or times out, OpenClaw uses a bundled fallback catalog:
 | `gpt-5.4-mini` | GPT-5.4-Mini | low, medium, high, xhigh |
 
 <Note>
-The current bundled harness is `@openai/codex` `0.142.5`. A `model/list` probe
+The current bundled harness is `@openai/codex` `0.143.0`. A `model/list` probe
 against that bundled app-server returned these public picker rows beyond the
 fallback catalog:
 
-| Model id              | Input modalities | Reasoning efforts        |
-| --------------------- | ---------------- | ------------------------ |
-| `gpt-5.5`             | text, image      | low, medium, high, xhigh |
-| `gpt-5.4`             | text, image      | low, medium, high, xhigh |
-| `gpt-5.4-mini`        | text, image      | low, medium, high, xhigh |
-| `gpt-5.3-codex-spark` | text             | low, medium, high, xhigh |
+| Model id        | Input modalities | Reasoning efforts        |
+| --------------- | ---------------- | ------------------------ |
+| `gpt-5.5`       | text, image      | low, medium, high, xhigh |
+| `gpt-5.4`       | text, image      | low, medium, high, xhigh |
+| `gpt-5.4-mini`  | text, image      | low, medium, high, xhigh |
+| `gpt-5.3-codex` | text, image      | low, medium, high, xhigh |
+| `gpt-5.2`       | text, image      | low, medium, high, xhigh |
 
 Live picker rows are account-scoped and can change with the account, Codex
 catalog, or bundled version; run `/codex models` for the current list rather
diff --git a/docs/plugins/codex-harness.md b/docs/plugins/codex-harness.md
index da3ba73a860a..c99061f1b867 100644
--- a/docs/plugins/codex-harness.md
+++ b/docs/plugins/codex-harness.md
@@ -38,7 +38,7 @@ channel is the communication surface.
 
 - OpenClaw with the bundled `codex` plugin available. Include `codex` in
   `plugins.allow` if your config uses an allowlist.
-- Codex app-server `0.142.0` or newer. The plugin manages a compatible
+- Codex app-server `0.143.0` or newer. The plugin manages a compatible
   binary by default, so a `codex` command on `PATH` does not affect normal
   startup.
 - Codex auth through `openclaw models auth login --provider openai`, an
@@ -900,10 +900,10 @@ instead of a plain OpenAI API-key failure.
 Doctor rewrites legacy model refs to `openai/*`, removes stale session and
 whole-agent runtime pins, and preserves existing auth-profile overrides.
 
-**The app-server is rejected:** use Codex app-server `0.142.0` or newer.
+**The app-server is rejected:** use Codex app-server `0.143.0` or newer.
 Same-version prereleases or build-suffixed versions such as
-`0.142.0-alpha.2` or `0.142.0+custom` are rejected because OpenClaw tests
-the stable `0.142.0` protocol floor.
+`0.143.0-alpha.2` or `0.143.0+custom` are rejected because OpenClaw tests
+the stable `0.143.0` protocol floor.
 
 **`/codex status` cannot connect:** check that the bundled `codex` plugin
 is enabled, that `plugins.allow` includes it when an allowlist is