strix/strix
0xallam a55797f729 Hint at provider prefix when bare model 401s against OpenAI
A bare model name without a provider prefix routes through the SDK's
default OpenAI provider, so configuring STRIX_LLM=deepseek-v4-pro with
LLM_API_KEY=<deepseek key> sends that key to api.openai.com and
surfaces a confusing "Incorrect API key" error pointing at the OpenAI
dashboard.

When warm-up fails with an OpenAI-shaped error AND the configured
model is still unprefixed after normalize_model_name, append a hint
that points the user at the '<provider>/<model>' form with concrete
examples.
2026-06-07 17:36:19 -07:00
..
agents fix: reasoning models reject tool_choice=required; bump to 1.0.2 (closes #503, #505) (#508) 2026-05-28 11:55:10 -07:00
config Use validate_environment to resolve provider env var 2026-06-07 17:36:19 -07:00
core fix: gate reasoning_effort by LiteLLM model registry (closes #517) (#523) 2026-06-07 12:24:48 -07:00
interface Hint at provider prefix when bare model 401s against OpenAI 2026-06-07 17:36:19 -07:00
report Add Scarf telemetry alongside PostHog 2026-05-25 23:22:01 -07:00
runtime Strip narrative comments and module/helper docstrings 2026-05-26 14:02:40 -07:00
skills Merge origin/main into harness-migration 2026-05-26 14:30:30 -07:00
telemetry Strip narrative comments and module/helper docstrings 2026-05-26 14:02:40 -07:00
tools Strip narrative comments and module/helper docstrings 2026-05-26 14:02:40 -07:00
utils fix(agent): fix tool schemas not retrieved on pyinstaller binary and validate tool call args 2026-01-14 10:57:32 -08:00
__init__.py Open-source release for Alpha version 2025-08-08 20:36:44 -07:00