…r_edit

Fix grammar, hide tool_call from output

Add missing closing brace to terminate test_template_output_parsers() function. This resolves compilation errors that prevented successful build of the test-chat target.

Co-authored-by: Kashyap Jois <kjois@iprdgroup.com>

Co-authored-by: Kashyap Jois <kjois@iprdgroup.com>

Co-authored-by: Marcel de Vries <marceldev89@gmail.com>

Co-authored-by: Marcel de Vries <marceldev89@gmail.com>

…d84/llama.cpp into qwen3-coder_tool_call_parser

…ranches; add tests

- chat-parser: support schema.type as array (e.g. ["number","null"]) in convert_qwen3_param_value()
- chat: resolve $refs; allow unions including "string" as freeform; sanitize empty {"not":{}} in anyOf/oneOf before add_schema
- tests: add Qwen3-Coder regression ensuring grammar builds with unions and ignores {"not":{}}

See https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/chat_template.jinja

…gml-org#16751)

This commit add the trust_remote_code=True argument when loading models
using AutoConfig, AutoTokenizer, and AutoModelForCausalLM for the run
original model script.

The motivation for this is that some models require custom code to be
loaded properly, and setting trust_remote_code=True avoids a prompt
asking for user confirmation:
```console
(venv) $ make causal-run-original-model
The repository /path/to/model contains custom code which must be
executed to correctly load the model. You can inspect the repository
content at /path/to/model.

Do you wish to run the custom code? [y/N] N
```

Having this as the default seems like a safe choice as we have to clone
or download the models we convert and would be expecting to run any
custom code they have.

* webui: support q URL parameter

Fixes ggml-org#16722
I’ve checked that it works with Firefox’s AI tools

* webui: apply suggestions from code review

Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>

* chore: update webui static build

---------

Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>