docs(cookbook): use auto parser resolution for Granite 4.2 (#36342)

docs/cookbook/autoregressive/IBM/Granite-4.2.mdx

@@ -99,8 +99,8 @@ import { Playground } from "/src/snippets/_playground.jsx";
 
 - **Thinking is enabled by default.** Set `chat_template_kwargs.enable_thinking` to `false` for a direct answer. Set `enable_thinking` and `low_effort` to `true` for a shorter reasoning trace.
 - **Give thinking enough tokens.** At `temperature=1.0` the default thinking mode can run past 1,000 tokens on multi-step problems. Use a `max_tokens` of at least 2,048 for thinking requests so the answer is not cut off.
-- **Reasoning parser.** Launch with `--reasoning-parser nemotron_3` so OpenAI-compatible responses separate the trace into `message.reasoning_content` and the answer into `message.content`. Without a parser flag the reasoning markup stays inline in `message.content`. `--reasoning-parser auto` also resolves to `nemotron_3` for these checkpoints.
+- **Reasoning parser.** Launch with `--reasoning-parser auto`, which resolves to `nemotron_3` for these checkpoints, so OpenAI-compatible responses separate the trace into `message.reasoning_content` and the answer into `message.content`. Without a parser flag the reasoning markup stays inline in `message.content`.
-- **Tool-call parser.** Launch with `--tool-call-parser qwen3_coder` so tool requests are returned through `message.tool_calls`. Without it, raw `<tool_call>` markup stays in `message.content`. `--tool-call-parser auto` also resolves to `qwen3_coder` for these checkpoints.
+- **Tool-call parser.** Launch with `--tool-call-parser auto`, which resolves to `qwen3_coder` for these checkpoints, so tool requests are returned through `message.tool_calls`. Without it, raw `<tool_call>` markup stays in `message.content`.
 - **Single-GPU sizing.** All three BF16 checkpoints loaded and completed chat requests with `--tp 1 --mem-fraction-static 0.8` on one H200 and on one B200. Increase TP only after validating the new topology.
 - **Image selection.** The validated path uses `lmsysorg/sglang:dev`. A stable image tested during validation had an incompatible dependency set before model loading, so use the recipe's image until a newer tagged release is confirmed.
 

docs/src/snippets/configs/ibm-granite/granite-4.2.jsx

@@ -70,8 +70,8 @@ export const config = {
     },
     parsers: {
       items: [
-        { id: "reasoning", label: "Reasoning Parser", flag: "--reasoning-parser nemotron_3" },
+        { id: "reasoning", label: "Reasoning Parser", flag: "--reasoning-parser auto" },
-        { id: "toolCall", label: "Tool Call Parser", flag: "--tool-call-parser qwen3_coder" },
+        { id: "toolCall", label: "Tool Call Parser", flag: "--tool-call-parser auto" },
       ],
     },
     pdDisagg: {
@@ -112,8 +112,8 @@ export const config = {
         "--model-path {{MODEL_NAME}}",
         "--tp 1",
         "--mem-fraction-static 0.8",
-        "--reasoning-parser nemotron_3",
+        "--reasoning-parser auto",
-        "--tool-call-parser qwen3_coder",
+        "--tool-call-parser auto",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",
       ],
@@ -126,8 +126,8 @@ export const config = {
         "--model-path {{MODEL_NAME}}",
         "--tp 1",
         "--mem-fraction-static 0.8",
-        "--reasoning-parser nemotron_3",
+        "--reasoning-parser auto",
-        "--tool-call-parser qwen3_coder",
+        "--tool-call-parser auto",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",
       ],
@@ -140,8 +140,8 @@ export const config = {
         "--model-path {{MODEL_NAME}}",
         "--tp 1",
         "--mem-fraction-static 0.8",
-        "--reasoning-parser nemotron_3",
+        "--reasoning-parser auto",
-        "--tool-call-parser qwen3_coder",
+        "--tool-call-parser auto",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",
       ],
@@ -154,8 +154,8 @@ export const config = {
         "--model-path {{MODEL_NAME}}",
         "--tp 1",
         "--mem-fraction-static 0.8",
-        "--reasoning-parser nemotron_3",
+        "--reasoning-parser auto",
-        "--tool-call-parser qwen3_coder",
+        "--tool-call-parser auto",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",
       ],
@@ -168,8 +168,8 @@ export const config = {
         "--model-path {{MODEL_NAME}}",
         "--tp 1",
         "--mem-fraction-static 0.8",
-        "--reasoning-parser nemotron_3",
+        "--reasoning-parser auto",
-        "--tool-call-parser qwen3_coder",
+        "--tool-call-parser auto",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",
       ],
@@ -182,8 +182,8 @@ export const config = {
         "--model-path {{MODEL_NAME}}",
         "--tp 1",
         "--mem-fraction-static 0.8",
-        "--reasoning-parser nemotron_3",
+        "--reasoning-parser auto",
-        "--tool-call-parser qwen3_coder",
+        "--tool-call-parser auto",
         "--host {{HOST_IP}}",
         "--port {{PORT}}",
       ],