ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/studio/backend/tests
History
Daniel Han 67e371934c Enforce parallel_tool_calls=False client-side on local GGUF (PR #5711) 
Two related findings from round 12 reviewers:

1. The local GGUF tool loop in `generate_chat_completion_with_tools`
   iterates every entry of `tool_calls` returned by llama-server, even
   when the caller explicitly opted out of parallel tool calls. The
   `parallel_tool_calls` flag is forwarded to llama-server, but llama
   .cpp does not enforce it on every jinja template
   (https://github.com/ggml-org/llama.cpp/issues/22043), so a model
   that ignores the flag still ran multiple tools per turn. Cap
   `tool_calls` to the first entry when the flag is False so the
   client-side contract holds regardless of upstream behavior.

2. llama-server documents `parallel_tool_calls` as defaulting to FALSE
   (https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md),
   so the previous chat-adapter shape (forward only on explicit false)
   meant the UI's default-on state could never enable parallel tool
   calls there. Always forward the user's preference on the local
   path so the toggle actually does what it says. External providers
   default to true everywhere, so the external branch is unchanged.

Test pins the GGUF tool-loop cap by source-level assertion (the loop
itself is integration-only).
2026-05-24 17:35:05 +00:00
..
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
conftest.py Studio: Expose openai and anthropic compatible external API end points (#4956) 2026-04-13 21:08:11 +04:00
test_anthropic_cache_ttl.py Studio: support Anthropic 1h cache TTL via prompt_cache_ttl (#5685) 2026-05-22 06:03:32 -07:00
test_anthropic_code_execution.py Studio: per-model Anthropic server-side tool versions (#5679) 2026-05-22 06:03:27 -07:00
test_anthropic_compaction.py Studio: wire Anthropic server-side context compaction (#5686) 2026-05-22 06:19:09 -07:00
test_anthropic_messages.py Studio: Claude Code Anthropic API tool compatibility (#5390) 2026-05-21 16:45:05 +04:00
test_anthropic_thinking_translation.py studio: API external provider support for chat (OpenAI, Mistral, Gemini, Cohere, Anthropic, OpenRouter, DeepSeek, custom providers) (#4706) 2026-05-14 16:13:59 +04:00
test_anthropic_tool_versions.py Studio: per-model Anthropic server-side tool versions (#5679) 2026-05-22 06:03:27 -07:00
test_anthropic_web_fetch.py Studio: wire Anthropic server-side context compaction (#5686) 2026-05-22 06:19:09 -07:00
test_browse_folders_route.py Studio: add folder browser modal for Custom Folders (#5035) 2026-04-15 08:04:33 -07:00
test_cache_case_resolution.py Add tests for cache case resolution (from PR #4822) (#4823) 2026-04-03 13:58:26 -07:00
test_cached_gguf_routes.py Studio: support GGUF variant selection for non-suffixed repos (#5023) 2026-04-15 15:32:01 +04:00
test_chat_history_routes.py Studio: persist chat history in backend storage (#5272) 2026-05-22 06:18:05 -07:00
test_chat_history_storage.py Studio: persist chat history in backend storage (#5272) 2026-05-22 06:18:05 -07:00
test_cleanup_cancelled_checkpoints.py studio: scope cancel-cleanup to in-flight tmp dirs; walk back tool_call_id (#5488) 2026-05-18 00:01:48 -07:00
test_data_recipe_github_progress.py Studio: add github_repo seed reader and GitHub Support Bot recipe (#5169) 2026-04-24 12:02:03 -07:00
test_data_recipe_seed.py fix(seed): disable remote code execution in seed inspect dataset loads (#4275) 2026-03-13 19:37:43 +04:00
test_desktop_auth.py Studio: persist chat history in backend storage (#5272) 2026-05-22 06:18:05 -07:00
test_detect_mmproj_file.py fix(studio/mmproj): block cross-family projectors in flat local GGUF dirs (#5347) (#5350) 2026-05-14 20:31:20 -07:00
test_export_log_cursor.py studio: stream export worker output into the export dialog (#4897) 2026-04-14 08:55:43 -07:00
test_external_provider_usage_chunk.py Studio: surface prompt-cache token counts in /v1/chat/completions usage chunk (#5670) 2026-05-22 06:02:52 -07:00
test_gguf_metadata.py fix(studio/mmproj): block cross-family projectors in flat local GGUF dirs (#5347) (#5350) 2026-05-14 20:31:20 -07:00
test_gguf_reload_inheritance.py studio: add --spec-draft-n-max toggle for MTP speculative decoding (#5582) 2026-05-19 06:17:04 -07:00
test_gpu_selection.py Update VRAM estimator to cater to broader model configs (#5175) 2026-05-05 04:12:36 -07:00
test_gpu_selection_sandbox.py [Studio] multi gpu finetuning/inference via "balanced_low0/sequential" device_map (#4602) 2026-03-30 02:33:15 -07:00
test_host_defaults.py Default Studio host to 127.0.0.1 and prompt before auto-start (#5267) 2026-05-04 13:03:16 +04:00
test_inference_model_validation.py studio: scope cancel-cleanup to in-flight tmp dirs; walk back tool_call_id (#5488) 2026-05-18 00:01:48 -07:00
test_kv_cache_estimation.py studio: reserve VRAM headroom for the MTP draft cache in auto-fit (#5585) 2026-05-19 06:19:02 -07:00
test_llama_cpp_cache_aware_disk_check.py Studio: make GGUF disk-space preflight cache-aware (#5012) 2026-04-14 08:53:37 -07:00
test_llama_cpp_context_fit.py Studio: pin GPU at 95% headroom and warn on silent CPU fallback (#5323) 2026-05-13 04:48:15 -07:00
test_llama_cpp_freshness.py Studio: warn when llama.cpp prebuilt is at least 3 days behind (#5529) 2026-05-18 00:21:50 -07:00
test_llama_cpp_load_progress.py Studio: live model-load progress + rate/ETA on download and load (#5017) 2026-04-14 09:46:22 -07:00
test_llama_cpp_load_progress_live.py Studio: split model-load progress label across two rows (#5020) 2026-04-14 10:58:16 -07:00
test_llama_cpp_load_progress_matrix.py Studio: split model-load progress label across two rows (#5020) 2026-04-14 10:58:16 -07:00
test_llama_cpp_max_context_threshold.py fix KVCache estimates for gemma4 style sliding window models (#5225) 2026-05-05 04:06:46 -07:00
test_llama_cpp_mtp_detection.py studio: add --spec-draft-n-max toggle for MTP speculative decoding (#5582) 2026-05-19 06:17:04 -07:00
test_llama_cpp_no_context_shift.py Studio: hard-stop at n_ctx with a 'Context limit reached' toast (#5021) 2026-04-14 10:58:20 -07:00
test_llama_cpp_wait_for_health.py tests/studio: lock in Windows GPU detection fix (#5106) with a synthetic CI test (#5376) 2026-05-18 00:06:01 -07:00
test_llama_cpp_wait_for_vram_settle.py studio: settle GPU VRAM after killing llama-server before the next reload (#5693) 2026-05-22 05:50:39 -07:00
test_llama_cpp_windows_nvidia_path.py Studio: add torch's pip nvidia DLL dirs to PATH on Windows (#5324) 2026-05-11 05:42:09 -07:00
test_llama_server_args.py studio: emit one comma-chained --spec-type for CPU/Mac MTP path (#5575) 2026-05-19 03:16:05 -07:00
test_log_filter_no_truncation.py Studio: stop truncating long log lines as suspected base64 (#5335) 2026-05-08 13:07:18 +04:00
test_login_rate_limit.py studio: proxy-aware login rate-limit; allow google favicons in CSP (#5489) 2026-05-18 00:02:15 -07:00
test_middleware.py studio: proxy-aware login rate-limit; allow google favicons in CSP (#5489) 2026-05-18 00:02:15 -07:00
test_mlx_inference_backend.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
test_mlx_training_worker_config.py studio: skip flash-attn install on Blackwell GPUs (sm_100+) (#5420) 2026-05-14 18:13:50 +04:00
test_models_get_model_config_case_resolution.py Add tests for cache case resolution (from PR #4822) (#4823) 2026-04-03 13:58:26 -07:00
test_multimodal_document.py Studio: PDF / document attachments for Anthropic + OpenAI (#5689) 2026-05-22 06:22:57 -07:00
test_native_context_length.py Studio: Fix chat template disappearing after browser refresh (#5209) 2026-05-01 08:19:09 -07:00
test_offline_gguf_cache_fallback.py studio: load cached GGUF models when fully offline (#5505) 2026-05-17 21:25:39 -07:00
test_offline_inference_parent.py studio: extend offline DNS auto-detect to inference parent + training (#5512) 2026-05-18 00:31:33 -07:00
test_openai_code_execution.py fix(studio): handle expired OpenAI shell-tool containers without surfacing error in chat (#5547) 2026-05-18 05:47:57 -07:00
test_openai_compaction.py Studio: wire OpenAI Responses server-side context compaction (#5687) 2026-05-22 06:20:45 -07:00
test_openai_container_crud.py tests/openai: patch httpx.AsyncClient ctor so delete tests hit mock (#5469) 2026-05-15 15:53:54 -07:00
test_openai_image_generation.py Studio: wire OpenAI image_generation tool (#5688) 2026-05-22 06:03:38 -07:00
test_openai_responses_translation.py Studio: o3 reasoning summary payload (#5426) 2026-05-15 17:13:28 +04:00
test_openai_tool_passthrough.py Studio: assert promoted fields on attribute path in test_extra_fields_accepted 2026-05-23 15:33:14 +00:00
test_pricing.py Studio: per-session cost calculator + /api/providers/pricing endpoint (#5690) 2026-05-22 06:03:43 -07:00
test_providers_api.py studio: API external provider support for chat (OpenAI, Mistral, Gemini, Cohere, Anthropic, OpenRouter, DeepSeek, custom providers) (#4706) 2026-05-14 16:13:59 +04:00
test_pytorch_mirror.py Add configurable PyTorch mirror via UNSLOTH_PYTORCH_MIRROR env var (#5024) 2026-04-15 11:39:11 +04:00
test_recommended_folders_permission.py Fix /recommended-folders 500 on unreadable model directories (Python 3.12+) (#5523) 2026-05-18 00:16:14 +04:00
test_responses_api.py Studio: Expose openai and anthropic compatible external API end points (#4956) 2026-04-13 21:08:11 +04:00
test_responses_tool_passthrough.py Studio: forward standard OpenAI tools / tool_choice on /v1/responses (Codex compat) (#5122) 2026-04-21 13:17:20 +04:00
test_safetensors_capability_advertise.py Revert "studio: tool calling for Llama-3, Mistral, Gemma 4 on safetensors + MLX (#5615)" (#5619) 2026-05-19 07:26:39 -07:00
test_safetensors_tool_loop.py Revert "studio: tool calling for Llama-3, Mistral, Gemma 4 on safetensors + MLX (#5615)" (#5619) 2026-05-19 07:26:39 -07:00
test_sampling_params_routing.py Enforce parallel_tool_calls=False client-side on local GGUF (PR #5711) 2026-05-24 17:35:05 +00:00
test_sandbox_tools.py studio: tighten sandbox blocklist precision (bash, hf upload, NOFILE) (#5487) 2026-05-18 00:01:17 -07:00
test_studio_api.py Studio: forward standard OpenAI tools / tool_choice to llama-server (#5099) 2026-04-18 12:53:23 +04:00
test_studio_train_validation.py studio: security and hardening pass (auth rate-limit, sandbox, path containment, schema validation, headers) (#5375) 2026-05-13 06:12:18 -07:00
test_tool_policy_gates.py unsloth run: add --enable-tools/--disable-tools server-side tool policy (#5277) 2026-05-05 12:45:15 +04:00
test_tool_policy_state.py unsloth run: add --enable-tools/--disable-tools server-side tool policy (#5277) 2026-05-05 12:45:15 +04:00
test_tool_xml_strip.py Studio: strip orphan tool_call XML leaking into visible content (#5735) 2026-05-24 05:00:08 -07:00
test_trained_model_scan.py studio: security and hardening pass (auth rate-limit, sandbox, path containment, schema validation, headers) (#5375) 2026-05-13 06:12:18 -07:00
test_training_history_update.py Studio: Dark theme refactor, right sidebar redesign, and chat UI polish (#5150) 2026-05-07 14:33:31 +04:00
test_training_raw_support.py studio: drop unused max_grad_value schema + route plumbing (#5424) 2026-05-14 05:43:58 -07:00
test_training_worker_flash_attn.py studio: install flash-linear-attention and tilelang for Qwen3.5 family (#5434) 2026-05-18 03:49:06 -07:00
test_transformers_version.py split venv_t5 into tiered 5.3.0/5.5.0 and fix trust_remote_code (#4878) 2026-04-07 20:05:01 +04:00
test_utils.py Add AMD ROCm/HIP support across installer and hardware detection (#4720) 2026-04-10 01:56:12 -07:00
test_vision_cache.py Studio: split vision-cache exception test to match transient vs permanent (#5145) 2026-04-23 00:22:40 -07:00
test_vram_estimation.py Update VRAM estimator to cater to broader model configs (#5175) 2026-05-05 04:12:36 -07:00
test_windows_gpu_detection_mock.py tests/studio: lock in Windows GPU detection fix (#5106) with a synthetic CI test (#5376) 2026-05-18 00:06:01 -07:00