Raw Prisma model objects serialise to JSON on cache write but deserialise
as plain dicts on read (Redis backend). Attribute-style access on a dict
raises AttributeError, silently breaking org MCP permission enforcement.
Fix: convert the Prisma result to LiteLLM_ObjectPermissionTable (Pydantic)
before writing to cache using .dict(), and reconstruct the Pydantic model
from the cached dict on read — matching the pattern used by get_end_user_object
and get_team_object in auth_checks.py.
Co-authored-by: Cursor <cursoragent@cursor.com>
Greptile: LITELLM_DEFAULT_EMBEDDING_ENCODING_FORMAT=none (case-insensitive)
strips encoding_format so OpenAI-compatible backends can use provider defaults.
Preserves optional_params passthrough when env is unset.
Co-authored-by: Cursor <cursoragent@cursor.com>
Stop forcing Gemini 3 thinkingLevel for Anthropic-style thinking params by default, and gate legacy low/minimal mapping behind an explicit feature flag to avoid provider-default confusion.
Made-with: Cursor
- Route publisher/model ids (e.g. xai/grok) to .../endpoints/openapi; keep model in JSON body
- Add model_prices keys for vertex_ai/openai/xai/grok-*
- Document xAI Grok on vertex_partner (aligned with GPT-OSS)
- Add tests for create_vertex_url and body-model heuristic
Made-with: Cursor
- Streaming example referenced Llama-3.1 instead of Llama-3.3
- Add supports_vision: true for gemma-3-12b-it in both JSON files,
matching other providers (bedrock, novita)
The previous example set CRUSOE_API_BASE via env var and also passed
api_base= in the same call, making it look like both were required.
They are independent alternatives.
Trailing slashes on custom API base examples cause double-slash in
get_complete_url. Also fixes inconsistent list indentation in
test_crusoe_models_configuration.
Crusoe's vLLM-based endpoint accepts max_tokens, not max_completion_tokens.
Without this mapping, callers using the OpenAI-standard param would get errors.
These are reasoning/thinking models but were missing the flag, causing
litellm.supports_reasoning() to return False and reasoning-token handling
to not activate.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The backup JSON was missing Crusoe model entries, causing
test_crusoe_model_list_populated to fail with AssertionError.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove trailing slash from docs Base URL to match providers.json
- Wrap model_cost mutations in try/finally to prevent test state leakage
- Add missing __init__.py to crusoe test package
Replace hand-written CrusoeChatConfig class and manual registrations
across constants.py, __init__.py, get_llm_provider_logic.py, and
_lazy_imports_registry.py with a single entry in
litellm/llms/openai_like/providers.json, consistent with the
recommended pattern for OpenAI-compatible providers.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
