unsloth/studio/backend/routes
Ritwij Aryan Parmar 181288e118
fix(studio): handle empty Responses tool output (#6167)
• fix: handle empty responses tool output

Normalize empty Responses `function_call_output.output` values before converting them into Chat Completions `role="tool"` messages. Empty strings, whitespace-only strings, and empty arrays now use the existing no-output sentinel, while non-empty text and content arrays are preserved.

Add regression coverage for empty tool outputs, image payloads outside `output`, content-array serialization, validator round trips, and preserving non-empty text.

---------

Co-authored-by: wasimysaid <wasimysdev@gmail.com>
Co-authored-by: Tai An <antai12232931@outlook.com>
Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com>
2026-06-11 17:35:50 +02:00
..
data_recipe Studio: improve OpenAI- and Anthropic-compatible API spec compliance (#6010) 2026-06-09 17:13:25 +02:00
.gitkeep root studio folder 2026-02-02 09:13:49 +00:00
__init__.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
auth.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
chat_history.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
datasets.py Studio: training survives a non-writable HF datasets cache (#6148) 2026-06-10 08:22:47 -07:00
export.py fix: don't block the event loop with time.sleep in async load_checkpoint (#6135) 2026-06-11 14:38:35 +02:00
inference.py fix(studio): handle empty Responses tool output (#6167) 2026-06-11 17:35:50 +02:00
llama.py Studio: offer the in-app llama.cpp update for source-build (markerless) installs (#6188) 2026-06-11 02:45:12 -07:00
mcp_servers.py studio: show MCP "Import config" on the add-server form (#6030) 2026-06-11 16:17:22 +01:00
models.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
prompts.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
providers.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
rag.py Studio: clean-room compact RAG (knowledge bases, hybrid search, fast indexing) (#5910) 2026-06-09 21:17:04 -07:00
settings.py Studio: make Helper LLM startup pre-cache opt in (#6113) 2026-06-09 15:28:34 +02:00
training.py fix(studio): surface live step with null loss through the SSE progress stream (#6206) 2026-06-11 07:50:13 -07:00
training_history.py Formatting: ruff line-length 100, kwarg-spacing passes, drop blank after short local imports (#6079) 2026-06-08 04:24:13 -07:00