use 5.2 for telegram instead of 5.3-codex; having issues for some reason

Author: matthewlouisbrockman

docs/agents/openclaw-telegram.mdx

@@ -37,7 +37,7 @@ const sandbox = await Sandbox.create('openclaw', {
   timeoutMs: 3600_000,
 })
 
-await sandbox.commands.run('openclaw config set agents.defaults.model.primary openai/gpt-5.3-codex')
+await sandbox.commands.run('openclaw config set agents.defaults.model.primary openai/gpt-5.2')
 
 // Enable the Telegram plugin (required before adding the channel)
 await sandbox.commands.run('openclaw config set plugins.entries.telegram.enabled true')
@@ -69,7 +69,7 @@ sandbox = Sandbox.create("openclaw", envs={
     "TELEGRAM_BOT_TOKEN": os.environ["TELEGRAM_BOT_TOKEN"],
 }, timeout=3600)
 
-sandbox.commands.run("openclaw config set agents.defaults.model.primary openai/gpt-5.3-codex")
+sandbox.commands.run("openclaw config set agents.defaults.model.primary openai/gpt-5.2")
 
 # Enable the Telegram plugin (required before adding the channel)
 sandbox.commands.run("openclaw config set plugins.entries.telegram.enabled true")
@@ -179,7 +179,7 @@ print(logs.stdout)
 - `OpenClaw: access not configured`
   - Pairing has not been approved yet. Run `openclaw pairing approve ...`.
 - `No API key found for provider ...`
-  - This guide uses `openai/gpt-5.3-codex`. Set `OPENAI_API_KEY` in sandbox envs.
+  - This guide uses `openai/gpt-5.2`. Set `OPENAI_API_KEY` in sandbox envs.
 - No pending pairing requests from `pairing list`
   - Send a fresh message to the bot first, then retry `pairing list --channel telegram`.