release: 0.5.0-alpha.3

[stainless-app]

Automated Release PR

0.5.0-alpha.3 (2026-02-19)

Full Changelog: v0.5.0-alpha.2...v0.5.0-alpha.3

⚠ BREAKING CHANGES

• improve consistency of post-training API endpoints

Features

• Add prompt_cache_key parameter support (6b45699)
• add support for /responses background parameter (4f8bf45)
• Add truncation parameter support (7501365)
• improve consistency of post-training API endpoints (99057fd)
• vector_io: Implement Contextual Retrieval for improved RAG search quality (89ec5a7)

Bug Fixes

• align chat completion usage schema with OpenAI spec (3974d5d)
• Enabled models list works (#314) (acd5e64)
• inference: use flat response message model for chat/completions (e58e2e4)
• vector_io: align Protocol signatures with request models (ea58fd8)

Chores

• api: minor updates (17a2705)
• format all api.md files (0e3e262)
• internal: bump dependencies (612291e)
• internal: fix lint error on Python 3.14 (a0f6975)
• update mock server docs (92cb087)

---

This pull request is managed by Stainless's GitHub App.

The semver version number is based on included commit messages. Alternatively, you can manually set the version number in the title of this pull request.

For a better experience, it is recommended to use either rebase-merge or squash-merge when merging this pull request.

🔗 Stainless website
📚 Read the docs
🙋 Reach out for help or questions

[stainless-app]

🧪 Testing

To try out this version of the SDK, run:

pip install 'https://pkg.stainless.com/s/llama-stack-client-python/92cb087355ffa1fd50e3a35b8e888853784c9fe9/llama_stack_client-0.5.0a2-py3-none-any.whl'

Expires at: Sat, 21 Mar 2026 18:26:42 GMT
Updated at: Thu, 19 Feb 2026 18:26:42 GMT