acess to ml-agent-explorers

namespace fix

removed avatars and made ui improvements

debug

fixing inference token

inference token

Move model selector below chat input

Fix: model selector dropdown bg, get_max_tokens None fallback

Migrate to client-side OAuth via @huggingface/hub

Comprehensive frontend/backend overhaul: unified tool system, responsive UI, code quality

frontend update

Merge branch 'main' into feature/web-frontend

plan tool bottom right

log streaming

hf jobs desc update

added code panel, tool approval, tool calls logging

added whooooshing to api spec

fix

deleted search code

ruff

Merge branch 'main' into dataset_tool_improved

file refactor, still works

pre simple impl

adding token counts

whoosh impl for docs search

smol cleanup

adding whoami to system prompt

small modif

limit in rows displaying

better data shape + small change in tool desc

Added tool to go from draft to open PR, enabling merging + minor improvements

Add approval display details for hf_repo_files and hf_repo_git

Show file contents in hf_repo_files approval request

Add hf_repo_files and hf_repo_git tools

Cleaning up tools

Remove utils_tools and disable private_hf_repo_tool

Fix: look for hardware_flavor at top level of tool_args, not nested

Simplify yolo_mode: use config instead of runtime variable

Merge configurable-permissions: add confirm_cpu_jobs, auto_file_upload, keep yolo mode

Merge branch 'dataset_tools'

Fix example message selection and show as JSON with all keys

Prefer tool_calls or assistant message for example structure

Unify dataset tools into single comprehensive hf_inspect_dataset tool

jobs tool timeout errors;

fixing logs

Add yolo mode for auto-approving tool calls

job-streaming-retry

Add retry logic for job log streaming to handle connection drops

Show full job script in CLI instead of truncated snippet

Remove unused prompt files