unsloth/studio/backend
Daniel Han 2874abbfec Studio: fail closed when Codex SDK cannot enforce safety pins
Round 6 reviewer noted that the warn-and-proceed path in
`_start_thread_with_system` is "failing open" on a server-side
chat surface: an SDK rev that does not expose ApprovalMode or
SandboxMode would log a warning then call `thread_start(model=...)`
with NO safety kwargs, letting the model run under the SDK's
`auto_review` default. For a route that takes a user-controlled
prompt and can spawn shell commands or file writes, that is the
wrong tradeoff.

Now fails closed: when `_safe_thread_safety_kwargs()` returns the
empty dict the helper raises `CodexUnavailableError`, which the
route layer translates to a 503 with a clear error message telling
the operator to upgrade `openai_codex` (or set the explicit
override env var). The error message names the override so users
who hit this on a pre-release alpha can opt in with eyes open
rather than discovering the unsafe default after the fact.

`UNSLOTH_CODEX_ALLOW_UNSAFE_DEFAULTS=1` is the deliberately-verbose
escape hatch. Variable name long and explicit so it does not creep
into production environments by accident, kept on the codex
subprocess safe-list so the round 6 SDK env-scrub wrapper does not
delete it before the gate sees it.

Tests: 50 cases total (was 49). The previous old-SDK test was
renamed and replaced by two new ones:
- `test_thread_start_fails_closed_when_safety_unavailable` asserts
  the raise fires and `thread_start` is never called.
- `test_thread_start_allows_unsafe_defaults_with_explicit_opt_in`
  asserts the override env var lets the request through and
  `thread_start` runs without the safety kwargs (with a logged
  warning).
The `_install_fake_codex_sdk` helper now injects fake ApprovalMode
and SandboxMode by default so the general translation tests do
not need to opt into the override; the two round-6b tests above
pass `with_safety_enums=False` to exercise the fail-closed branch.
2026-05-24 17:45:20 +00:00
..
assets Add Qwen3.6 inference defaults for Studio (#5065) 2026-04-16 11:42:42 -07:00
auth studio: security and hardening pass (auth rate-limit, sandbox, path containment, schema validation, headers) (#5375) 2026-05-13 06:12:18 -07:00
core Studio: fail closed when Codex SDK cannot enforce safety pins 2026-05-24 17:45:20 +00:00
loggers Studio: stop truncating long log lines as suspected base64 (#5335) 2026-05-08 13:07:18 +04:00
models Studio: round 5e Codex hardening (4 follow-ups) 2026-05-24 16:59:46 +00:00
plugins fix(gh_client): fail fast on 401/403 auth errors instead of retrying forever (#5325) (#5329) 2026-05-08 21:57:41 +04:00
requirements ci: broaden Linux + narrow Windows llama.cpp runtime patterns + trim #5741 comments (#5746) 2026-05-23 21:48:12 -07:00
routes Merge branch 'main' into feat/codex-provider 2026-05-24 14:25:41 +00:00
state unsloth run: add --enable-tools/--disable-tools server-side tool policy (#5277) 2026-05-05 12:45:15 +04:00
storage Studio: persist chat history in backend storage (#5272) 2026-05-22 06:18:05 -07:00
tests Studio: fail closed when Codex SDK cannot enforce safety pins 2026-05-24 17:45:20 +00:00
utils Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
_platform_compat.py Fix Studio crash on Anaconda/conda-forge Python (#4484) 2026-03-22 05:36:55 -07:00
colab.py Fix/studio colab button message: Add fallback message for Colab Studio button when proxy URL fails (#4866) 2026-04-05 21:57:45 -07:00
main.py Studio: add Codex SDK as a chat provider with parallel-calls fan-out 2026-05-23 14:00:31 +00:00
run.py Studio: stop hint, Uvicorn log rename, reachability check + Mac UI CI retry hardening (#5503) 2026-05-17 07:44:06 -07:00
startup_banner.py Studio: stop hint, Uvicorn log rename, reachability check + Mac UI CI retry hardening (#5503) 2026-05-17 07:44:06 -07:00