Change log for release 0.3.3

CHANGELOG.md

@@ -2,6 +2,42 @@
 
 ## 2025
 
+### 0.3.3 (Nov 25)
+
+General cleanup and fixes, and the following notable improvements:
+
+#### Docs
+- Document `AZURE_OPENAI_ENDPOINT_EMBEDDING` (Gwyneth Peña-Siguenza).
+- Add link to PyBay 2025 talk video.
+
+#### Core typeagent package
+- Simplify `load_dotenv()`.
+- Split embedding requests that are too large (Raphael Wirth).
+- Overhaul conversation metadata in storage providers.
+- Add extra optional keyword parameters to `create_conversation()`.
+- Add `Quantifier` to ingestion schema in addition to `Quantity`.
+- Extract knowledge concurrently (max 4 by default) (Kevin Turcios).
+- Fixes for `get_multiple()` implementations.
+- Tweak defaults in `ConversationSettings`.
+
+#### MCP server
+- Pass LLM requests to MCP client instead of calling the OpenAI API.
+- Add `--database` option to MCP server.
+
+#### Tools
+- The _tools/query.py_ tool now supports `@`-commands. Try `@help`.
+- Add _tools/ingest_podcast.py_ (a tool that ingests podcasts).
+
+#### Testing
+- Fix coverage support for MCP server test.
+- Use an updated "Adrian Tchaikovsky" podcast data dump (Rob Gruen).
+- Fix Windows testing issues. Run CI on Windows too (Raphael Wirth).
+- Run tests in CI using secrets stored in repo (Rob Gruen).
+
+#### Infrastructure
+- Migrate package build from _setuptools_ to _uv_build_.
+- Add `install-libatomic` target to `Makefile` (Bernhard Merkle).
+
 ### 0.3.2 (Oct 22)
 
 Brown bag release!

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "typeagent"
-version = "0.3.2"
+version = "0.3.3"
 description = "Incremental message indexing and querying pipelines using Structured RAG"
 readme = { file = "README.md", content-type = "text/markdown" }
 license = "MIT"