From: Piotr <redacted>
Date: Sat, 14 Jun 2025 16:25:15 +0000 (+0200)
Subject: llama-chat : Do not throw when tool parsing fails (#14012)
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=3cb203c89f60483e349f841684173446ed23c28f;p=pkg%2Fggml%2Fsources%2Fllama.cpp

llama-chat : Do not throw when tool parsing fails (#14012)

Currently when a model generates output which looks like a tool call,
but is invalid an exception is thrown and not handled, causing the cli
or llama-server to bail. Instead, handle the chat parser exception and
simply return the generated text in such cases.

Signed-off-by: Piotr Stankiewicz <redacted>
---

diff --git a/common/chat-parser.cpp b/common/chat-parser.cpp
index 65b664cb..18a30e49 100644
--- a/common/chat-parser.cpp
+++ b/common/chat-parser.cpp
@@ -49,6 +49,7 @@ bool common_chat_msg_parser::add_tool_call(const std::string & name, const std::
 
     // LOG_DBG("Tool call arguments:\n\traw: %s\n\tresult: %s\n", arguments.c_str(), tool_call.arguments.c_str());
     result_.tool_calls.emplace_back(tool_call);
+
     return true;
 }
 bool common_chat_msg_parser::add_tool_call(const json & tool_call) {
@@ -378,3 +379,7 @@ std::optional<common_chat_msg_parser::consume_json_result> common_chat_msg_parse
         /* .is_partial = */ found_healing_marker,
     };
 }
+
+void common_chat_msg_parser::clear_tools() {
+    result_.tool_calls.clear();
+}
diff --git a/common/chat-parser.h b/common/chat-parser.h
index 7ee35505..0e64c341 100644
--- a/common/chat-parser.h
+++ b/common/chat-parser.h
@@ -115,4 +115,6 @@ class common_chat_msg_parser {
         const std::vector<std::vector<std::string>> & args_paths = {},
         const std::vector<std::vector<std::string>> & content_paths = {}
     );
+
+    void clear_tools();
 };
diff --git a/common/chat.cpp b/common/chat.cpp
index 1d6974a8..0dad14fb 100644
--- a/common/chat.cpp
+++ b/common/chat.cpp
@@ -1921,7 +1921,9 @@ common_chat_msg common_chat_parse(const std::string & input, bool is_partial, co
     } catch (const common_chat_msg_partial_exception & ex) {
         LOG_DBG("Partial parse: %s\n", ex.what());
         if (!is_partial) {
-            throw std::runtime_error(ex.what());
+            builder.clear_tools();
+            builder.move_to(0);
+            common_chat_parse_content_only(builder);
         }
     }
     auto msg = builder.result();