From aa9bea12b9f077b23edd8d46e042da71196480fb Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Fri, 27 Mar 2026 06:46:23 +0000
Subject: [PATCH] Address remaining reviewer findings: late tool_call IDs and
 XML speculation

1. Late-arriving tool_calls.id: when a provider sends the real ID on a
   later delta chunk (after the initial one with index and function
   name), the accumulator now updates the ID instead of keeping the
   synthetic "call_{idx}" placeholder. (P2, 2/10 reviewers)

2. XML speculation respects auto_heal_tool_calls: when auto_heal is
   explicitly disabled, _TOOL_XML_SIGNALS is empty so the BUFFERING
   state never speculatively holds content for XML prefix detection.
   Content starting with literal "<tool_call>" or "<function=" text
   flows straight through without delay. (P2, 1/10 reviewers)

Skipped: finish_reason="tool_calls" without delta.tool_calls fallback
(P1, 1/10 reviewers). llama-server always sends delta.tool_calls
fragments in streaming mode. A non-streaming fallback for this edge
case would add complexity for a scenario that does not occur in
practice with the supported backend.
---
 studio/backend/core/inference/llama_cpp.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py
index 746ab26abb..b3ed3124db 100644
--- a/studio/backend/core/inference/llama_cpp.py
+++ b/studio/backend/core/inference/llama_cpp.py
@@ -1725,8 +1725,12 @@ class LlamaCppBackend:
                 text = pat.sub("", text)
             return text.strip() if final else text
 
-        # XML prefixes that signal a tool call in content
-        _TOOL_XML_SIGNALS = ("<tool_call>", "<function=")
+        # XML prefixes that signal a tool call in content.
+        # Empty when auto_heal is disabled so the buffer never
+        # speculatively holds content for XML detection.
+        _TOOL_XML_SIGNALS = (
+            ("<tool_call>", "<function=") if auto_heal_tool_calls else ()
+        )
         _MAX_BUFFER_CHARS = 32
 
         for iteration in range(max_tool_iterations):
@@ -1871,6 +1875,12 @@ class LlamaCppBackend:
                                                         "arguments": "",
                                                     },
                                                 }
+                                            elif tc_d.get("id"):
+                                                # Update ID if real one
+                                                # arrives on a later delta
+                                                tool_calls_acc[idx]["id"] = (
+                                                    tc_d["id"]
+                                                )
                                             func = tc_d.get("function", {})
                                             if func.get("name"):
                                                 tool_calls_acc[idx]["function"][