From 9774dea8951e93b8db050b340f4323a8fb631636 Mon Sep 17 00:00:00 2001
From: Story Crater Bot <19826264+Riotpiaole@users.noreply.github.com>
Date: Tue, 18 Aug 2026 20:50:21 -0700
Subject: [PATCH] fix(llm-serving): enable tool calling on homelab-reasoning

pi sends tool_choice="auto" for every session (Read/Bash/etc.) -- vLLM 400s on that without --enable-auto-tool-choice and a --tool-call-parser. Verified this deployed vLLM v0.11.0's registered parsers directly; deepseek_v3 matches, same family as the deepseek_r1 reasoning-parser already set (this Qwen-base distillation still emits DeepSeek's own tool-call format).
---
 k8s/apps/llm-serving/reasoning.yaml | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/k8s/apps/llm-serving/reasoning.yaml b/k8s/apps/llm-serving/reasoning.yaml
index 44f091c..66dfb0e 100644
--- a/k8s/apps/llm-serving/reasoning.yaml
+++ b/k8s/apps/llm-serving/reasoning.yaml
@@ -24,6 +24,16 @@ spec:
       - --enable-chunked-prefill
       - --enable-prefix-caching
       - --reasoning-parser=deepseek_r1
+      # Without these, any client sending tool_choice="auto" (pi does, for
+      # Read/Bash/etc.) gets a 400: "auto" tool choice requires
+      # --enable-auto-tool-choice and --tool-call-parser to be set. Verified
+      # against this exact deployed vLLM v0.11.0's registered parsers
+      # (ToolParserManager.tool_parsers) -- deepseek_v3 matches, same family
+      # as the deepseek_r1 reasoning-parser already set above (this model
+      # emits DeepSeek's own special-token format, not Qwen's Hermes-style,
+      # despite being a Qwen-base distillation).
+      - --enable-auto-tool-choice
+      - --tool-call-parser=deepseek_v3
       - --host=0.0.0.0
       - --port=8080
       env: