Skip to content
AI NEWS JOURNAL
ONE EVENT. MANY PERSPECTIVES.

llama.cpp · b11871

chat : reject JSON nested more than 128 levels before walking it (#30242) * chat : reject JSON nested more than 128 levels before walking it The schema builder, the jinja engine and the decision code walk request JSON with recursion. A request nested deep enough overflows the stack of the HTTP thread and llama-server dies (SIGBUS on macOS, SIGSEGV on Linux): for a tool schema from a few hundred levels on macOS and about 10000 on Linux. Check the depth first and answer 400 past 128 levels: the chat inputs in common_chat_templates_apply (tools, tool-call arguments, chat_template_kwargs, json_schema), the json_schema of /completion, and the whole /v1/systemone body. A gemma4 tool result that is too deep stays text. * fix the root, not the call side --------- Co-authored-by: Xuan Son Nguyen **

1 independent sources · 1 reportsOldest first ↕
Newest first

llama.cpp · b11871

chat : reject JSON nested more than 128 levels before walking it (#30242) * chat : reject JSON nested more than 128 levels before walking it The schema builder, the jinja engine and the decision code walk request JSON with recursion. A request nested deep enough overflows the stack of the HTTP thread and llama-server dies (SIGBUS on macOS, SIGSEGV on Linux): for a tool schema from a few hundred levels on macOS and about 10000 on Linux. Check the depth first and answer 400 past 128 levels: the chat inputs in common_chat_templates_apply (tools, tool-call arguments, chat_template_kwargs, json_schema), the json_schema of /completion, and the whole /v1/systemone body. A gemma4 tool result that is too deep stays text. * fix the root, not the call side --------- Co-authored-by: Xuan Son Nguyen **

Why it matters:按信源设置仅收录,不参与自动精选

Timeline and related coverage