v0.1.3 (2025-04-18)

What's Changed

• Return last text parts on empty message by @samuelcolvin in #1408
• move prepare_env.py to Python file in mcp-run-python by @samuelcolvin in #1461
• Don't set non-recording span as current by @alexmojaki in #1527
• opentelemetry: add span event for instructions by @Kludex in #1529
• Add extra_body to ModelSettings by @Kludex in #1538
• Do not raise an error when no results are found by @bputzeys in #1536
• Add support for gemini-2.5-flash-preview-04-17 by @barapa in #1531
• fix: allow multiple BinaryContent in message_history by @arde100 in #1523
• fix: handle empty args for ToolCallPart by @arnaudstiegler in #1515

New Contributors

• @bputzeys made their first contribution in #1536
• @arde100 made their first contribution in #1523
• @arnaudstiegler made their first contribution in #1515

Full Changelog: v0.1.2...v0.1.3

v0.1.2 (2025-04-17)

What's Changed

• Fix max length handling by @dmontagu in #1510
• Do a better job of inferring openai strict mode by @dmontagu in #1511
• Properly validate serialized messages with BinaryContent by decoding base64 by @DouweM in #1513
• Expose the StdioServerParameters.cwd param by @timesler in #1514

New Contributors

• @DouweM made their first contribution in #1513
• @timesler made their first contribution in #1514

Full Changelog: v0.1.1...v0.1.2

v0.1.1 (2025-04-16)

What's Changed

• fix: Allow empty tool call args by @Wh1isper in #1407
• fix: add instructions on further requests besides UserPromptNode by @Kludex in #1503
• Fix handling of additionalProperties by gemini by @Kludex in #1506

Full Changelog: v0.1.0...v0.1.1

v0.1.0 (2025-04-15)

What's Changed

• feat(bedrock): add VideoUrl input for BedrockConverseModel by @leandrodamascena in #1435
• Add spans as an attribute on agent/graph runs/runresults by @dmontagu in #1415
• BREAKING CHANGE: rename result -> output by @samuelcolvin in #1248
• Bugfix: ensure parameters are customized when making streaming requests by @dmontagu in #1475
• Customize the parameters as appropriate for the model when using fallback model by @dmontagu in #1477
• Update min openai version by @dmontagu in #1479
• feat(BedrockConverseModel): add additional configuration fields to Bedrock Runtime API by @leandrodamascena in #1458
• Add support for gemini-2.5-pro-preview-03-25 model (paid version of gemini 2.5 pro) by @barapa in #1473
• BREAKING CHANGE (minor) move format_as_xml by @samuelcolvin in #1484
• Add Changelog by @samuelcolvin in #1487
• Add instructions parameter by @Kludex in #1360
• Generalize the JSON schema transformations by @dmontagu in #1481
• Switch gemini request to camelCase as required by API by @piercefreeman in #1456

New Contributors

• @VildMedPap made their first contribution in #1441
• @leandrodamascena made their first contribution in #1435
• @ehaca made their first contribution in #1389

Full Changelog: v0.0.55...v0.1.0

v0.0.55 2025-04-09

What's Changed

• Allow empty user_prompt in run_stream by @lfloeer in #1421
• fix: infer azure provider and environment for key by @Wh1isper in #1422
• Fix bug with JSON schema generation when using InstrumentedModel by @dmontagu in #1424
• Add PydanticAI User-Agent header by @Kludex in #1425

New Contributors

• @lfloeer made their first contribution in #1421

Full Changelog: v0.0.54...v0.0.55

v0.0.54 2025-04-09

What's Changed

• evals: error when opentelemetry-sdk is not installed by @Kludex in #1403
• bedrock: allow empty system prompt by @Kludex in #1405
• fix import for the bedrock model by @yilololo in #1410
• Yield initial node during Graph (and therefore Agent) iteration by @dmontagu in #1412
• Make user_prompt optional by @Kludex in #1406
• Add stop_sequences to ModelSettings by @Kludex in #1419

New Contributors

• @yilololo made their first contribution in #1410

Full Changelog: v0.0.53...v0.0.54

v0.0.53 2025-04-07

What's Changed

• Improve some error messages by @dmontagu in #1366
• Improve serialization of LLMJudge and custom evaluators by @dmontagu in #1367
• Use handle_stream.stream_output() in the CLI by @Kludex in #1376
• Feature/add openai strict mode by @mscherrmann in #1304

New Contributors

• @mscherrmann made their first contribution in #1304

Full Changelog: v0.0.52...v0.0.53

v0.0.52 2025-04-03

What's Changed

• Add dependencies to evals by @Kludex in #1358

Full Changelog: v0.0.51...v0.0.52

v0.0.51 2025-04-03

What's Changed

• Match OpenAI models in strictness by @Kludex in #1356
• Switch mcp-run-python server to use deno by @samuelcolvin in #1340

Full Changelog: v0.0.50...v0.0.51

v0.0.50 2025-04-03

What's Changed

• Fix some issues with non-serializable inputs in evals by @dmontagu in #1333
• Add expected output to logfire attributes for the evals task span by @dmontagu in #1334
• Drop exclusiveMaximum/exclusiveMinimum from Gemini by @Kludex in #1341
• Drop JSON schema url from schema on Gemini by @Kludex in #1342
• Add py.typed marker to pydantic_evals package by @t94j0 in #1349

New Contributors

• @mike-luabase made their first contribution in #1331
• @t94j0 made their first contribution in #1349

Full Changelog: v0.0.49...v0.0.50