mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-21 00:21:49 +00:00
222f283c93
Some checks failed
ai-gateway image / ai-gateway release image (push) Waiting to run
LiteLLM Rust / rust-lint (push) Has been cancelled
LiteLLM Rust / rust-test (push) Has been cancelled
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Codex 0.130 and 0.145 require supports_reasoning_summaries and supports_parallel_tool_calls on every catalog entry, so a catalog written for 0.154 made those releases exit at startup with a parse error. Every field some release since 0.105.0 deserializes without a default is now written, with Codex's own fallback values, and the catalog is read back once through the installed binary (`codex debug models`) before launch. A Codex that rejects it, or one older than 0.130 with no such command, gets the skip notice and launches on its built-in catalog instead. |
||
|---|---|---|
| .. | ||
| autoroute | ||
| __init__.py | ||
| conftest.py | ||
| test_agents.py | ||
| test_auth_commands.py | ||
| test_claude_settings.py | ||
| test_codex_settings.py | ||
| test_config_commands.py | ||
| test_configure_commands.py | ||
| test_credentials_commands.py | ||
| test_debug_commands.py | ||
| test_encryption_commands.py | ||
| test_global_options.py | ||
| test_keys_commands.py | ||
| test_model_groups_commands.py | ||
| test_models_commands.py | ||
| test_pi.py | ||
| test_pkce_login.py | ||
| test_statusline_script.py | ||
| test_up_commands.py | ||
| test_users_commands.py | ||