unsloth/studio/backend
danielhanchen 1e58c3707d Harden Gemma array parsing, XML-parameter guard, and stream teardown
Address five review findings on the Gemma tool-call and OpenAI passthrough
streaming paths:

- parse_tool_calls_from_text collected JSON and Gemma markers without the
  _inside_open_parameter guard, so a marker embedded in an existing
  <function=...><parameter=...> value was promoted to a separate tool call.
  Candidates that start inside an open XML parameter are now skipped, matching
  the guard the XML-style parser already applies.

- _quote_gemma_array_elements preserved array elements starting with { or [
  verbatim, so an array of objects (items:[{path:a}]) or a nested array failed
  json.loads and the whole call was dropped. Object and nested-array elements
  are now normalised recursively.

- _openai_passthrough_stream synthesized a finish chunk before a trailing
  usage-only chunk and set saw_finish_reason, which made the EOF guard skip the
  [DONE] sentinel. The EOF path now emits [DONE] whenever the upstream omitted
  it, even after a finish chunk was already synthesized.

- /generate/stream drove generation through asyncio.to_thread with no
  disconnect watcher, so a client disconnect during a long generation went
  unnoticed until the next send. It now runs _await_disconnect_then_cancel
  against the request, matching the other local streaming endpoints.

- _SameTaskStreamingResponse closed the body iterator with aclose() on a
  send-side disconnect, raising GeneratorExit so the generators' cancellation
  handlers (which finish the api_monitor entry) never ran. It now throws
  CancelledError, falling back to aclose() when athrow is unavailable.

Extends tests/test_gemma_tool_parse_edge_cases.py with array-of-objects,
nested-array, and marker-inside-XML-parameter cases.
2026-06-22 15:14:42 +00:00
..
assets feat(studio): expose provider_type selector in model provider dialog (#4277) 2026-06-15 15:07:06 +02:00
auth CLI: stop unsloth connect from leaking Studio credentials to unverified servers (#6479) 2026-06-21 21:28:38 -07:00
core Harden Gemma array parsing, XML-parameter guard, and stream teardown 2026-06-22 15:14:42 +00:00
hub Studio: add an Open button to reveal the models folder in the file manager (#6452) 2026-06-19 05:14:58 -07:00
loggers Studio: trim serving-log noise and surface llama-server engine stats (#6377) 2026-06-17 05:37:57 -07:00
models Merge branch 'main' into fix-gemma4-openai-api-streams 2026-06-22 04:58:22 +00:00
plugins Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
requirements studio: select torchao version from the installed torch (#6400) 2026-06-17 04:09:40 -07:00
routes Harden Gemma array parsing, XML-parameter guard, and stream teardown 2026-06-22 15:14:42 +00:00
state Studio: Add inline confirmation (Allow/Always allow/Deny) for tool calls (#5869) 2026-06-12 10:55:26 +02:00
storage feat: implement thread forking functionality with associated database… (#5810) 2026-06-15 14:57:39 +01:00
tests Harden Gemma array parsing, XML-parameter guard, and stream teardown 2026-06-22 15:14:42 +00:00
utils Studio: use an isolated Node.js for the frontend build instead of replacing the system Node/npm (#6533) 2026-06-21 21:17:29 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
_platform_compat.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
cloudflare_tunnel.py Reap Studio child processes when the parent dies abnormally (#6425) 2026-06-18 05:51:22 -07:00
colab.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
main.py Studio: pin CUDA_DEVICE_ORDER=PCI_BUS_ID and list GPUs at startup (#6353) 2026-06-17 22:40:04 -07:00
run.py Keep server-side tools enabled under --secure (#6403) 2026-06-18 05:52:40 -07:00
startup_banner.py Studio: enable stdio MCP servers on a loopback bind (#6295) 2026-06-15 03:02:32 +01:00