Misc. bug: Symbol '\' is not escaped in the json schema literals. #17306
Description
Name and Version
$ ./build/bin/llama-cli --version
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
version: 7061 (e1fcf8b)
built with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-cli, llama-server
Command line
llama-cli -m ... --json-schema '{"properties":{"code":{"const":"auto s = \"000\";","description":"Generated code","title":"Code","type":"string"}},"required":["code"],"title":"DecoderResponse","type":"object"}'Problem description & steps to reproduce
When I ran the command, I received the following messages and the program terminates.
First Bad Commit
No response
Relevant log output
...
main: interactive mode on.
parse: error parsing grammar: expecting newline or end at \\";\"" space
code-kv ::= "\"code\"" space ":" space code
root ::= "{" space code-kv "}" space
space ::= | " " | "\n"{1,2} [ \t]{0,20}
code ::= "\"auto s = \\"000\\";\"" space
code-kv ::= "\"code\"" space ":" space code
root ::= "{" space code-kv "}" space
space ::= | " " | "\n"{1,2} [ \t]{0,20}
llama_grammar_init_impl: failed to parse grammar
main: failed to initialize sampling subsystem