unsloth/studio/backend
danielhanchen b3e244d658 Harden Gemma tool-call parsing and stream-error detection
Address three issues in the Gemma-native tool-call path:

- _quote_gemma_object_keys stopped a bare (unquoted) string value at the
  first comma, so an argument like `location:New York, NY` was split
  mid-value and the synthesized JSON failed to parse, dropping the whole
  tool call. A bare value now ends only at `}` or a comma that begins the
  next `key:` pair.

- parse_tool_calls_from_text scanned the entire response for Gemma markers
  even inside a tool call already parsed from a `<tool_call>{...}` JSON
  block, so a marker-like string inside an argument (data) was promoted to
  a second, unintended tool call. Matches inside an already-consumed call
  span are now skipped.

- _openai_passthrough_stream relied on _monitor_openai_sse_line to flag a
  stream error, which returns early when monitor_id is None
  (skip_api_monitor), so an upstream error chunk left saw_stream_error
  unset and the synthetic-finish guard emitted a successful finish_reason
  after a failed stream. Error chunks are now detected independently of API
  monitoring.

Adds tests/test_gemma_tool_parse_edge_cases.py covering the comma and
marker-injection cases.
2026-06-22 11:03:21 +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 tool-call parsing and stream-error detection 2026-06-22 11:03:21 +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 tool-call parsing and stream-error detection 2026-06-22 11:03:21 +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 tool-call parsing and stream-error detection 2026-06-22 11:03:21 +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