v0.0.49 2025-04-01

What's Changed

• Add Gemini 2.5 pro and improve CLI by @samuelcolvin in #1317
• Add OpenAI built-in tools by @Kludex in #1327
• Add generate_summary and truncation to OpenAIResponsesModelSettings by @Kludex in #1328
• Move imports to try-except block by @Kludex in #1329
• Don't download content on ImageUrl and DocumentUrl for Anthropic Models by @jnishiyama in #1318

New Contributors

• @jnishiyama made their first contribution in #1318

Full Changelog: v0.0.48...v0.0.49

v0.0.48 2025-03-31

What's Changed

• Add OpenAI Responses API by @Kludex in #1256
• Add dynamic version on evals extras by @Kludex in #1315

Full Changelog: v0.0.47...v0.0.48

v0.0.47 2025-03-31

What's Changed

• Ensure model settings' prefixes are enforced by @Kludex in #1257
• Bump logfire by @Kludex in #1262
• improvements while playing with the CLI by @samuelcolvin in #1263
• add span around tool calls by @samuelcolvin in #1158
• Add pydantic-evals package by @dmontagu in #935
• remove "preparing model request params" span by @samuelcolvin in #1281
• Clean up SpanQuery and related APIs by @dmontagu in #1287
• Fix the default types of generic params to EvaluatorContext by @dmontagu in #1290
• More otel cleanup for evals by @dmontagu in #1291
• Clean up public evals API by @dmontagu in #1298
• [Bugfix] Unknown tool called by agent will cause response 400 by @BeautyyuYanli in #1255
• feat: Add read timeout and connect timeout for bedrock provider by @Wh1isper in #1259
• allow str as model, fix Groq models by @samuelcolvin in #1306
• CLI fixes and improvements by @dmontagu in #1299
• Allow use of PYTHONOPTIMIZE=1 by @Kludex in #1307
• disable cohere with emscripten by @samuelcolvin in #1296

New Contributors

• @yaswhar made their first contribution in #1224
• @sarunas-llm made their first contribution in #1280
• @BeautyyuYanli made their first contribution in #1255

Full Changelog: v0.0.46...v0.0.47

v0.0.46

What's Changed

• Use different HTTP clients based on providers by @Kludex in #1242
• Add headers, timeout, and sse_read_timeout to MCPServerHTTP by @JohnUiterwyk in #1218
• Revert "Use get_running_loop instead of get_event_loop" by @Kludex in #1252

New Contributors

• @JohnUiterwyk made their first contribution in #1218

Full Changelog: v0.0.45...v0.0.46

v0.0.45

What's Changed

• Generate tool call id if not present by @Kludex in #1229
• add user mapping in openai chat completion by @ovisek in #1174
• Remove non-provider parameters from models by @Kludex in #1239

New Contributors

• @ovisek made their first contribution in #1174

Full Changelog: v0.0.44...v0.0.45

v0.0.44

What's Changed

• Migrate OpenAI models away from max_tokens to max_completion_tokens by @barapa in #1206
• Add return docstring to the function description by @Kludex in #1207
• Add model_request_parameters attribute (containing tool definitions) to chat spans by @alexmojaki in #1177
• Use get_running_loop instead of get_event_loop by @Kludex in #1204
• Bump openai to 1.66.0 by @Kludex in #1202
• Use pydantic-ai-slim version on CLI instead of pydantic-ai by @samuelcolvin in #1213
• Drop system parameter from OpenAIModel by @Kludex in #1235
• Use provider on models inference by @Kludex in #1234
• Add cohere provider class by @hrahmadi71 in #1225

New Contributors

• @derekwsgray made their first contribution in #1227

Full Changelog: v0.0.43...v0.0.44

v0.0.43 2025-03-21

What's Changed

• Add timestamp to SystemPromptPart by @vricciardulli in #1154
• Recreate access token on 401 for Google Vertex provider by @Kludex in #1195

New Contributors

• @dsfaccini made their first contribution in #1181
• @vricciardulli made their first contribution in #1154

Full Changelog: v0.0.42...v0.0.43

v0.0.42 2025-03-19

What's Changed

• Add support for MCP servers by @Kludex in #1100
• Make it possible to override JSON schema generation for tools by @dmontagu in #1108
• MCP server to run Python code in a sandbox by @samuelcolvin in #1140
• change api_key check flow by @ChenghaoMou in #1164
• require 3.12 for development by @samuelcolvin in #1173
• improved MCP documentation by @samuelcolvin in #1171
• rename MCPServerSSE to MCPServerHTTP and more docs by @samuelcolvin in #1176
• uprev to 0.0.42 by @samuelcolvin in #1178

New Contributors

• @ChenghaoMou made their first contribution in #1164

Full Changelog: v0.0.41...v0.0.42

v0.0.41 2025-03-17

What's Changed

• Improve generic typehints in graph.py by @dmontagu in #1139
• Fix span attributes when instrumenting FallbackModel streaming by @alexmojaki in #1147
• Add Anthropic provider classes by @hrahmadi71 in #1120
• Add Mistral provider by @Viicos in #1118

Full Changelog: v0.0.40...v0.0.41

v0.0.40 2025-03-15

What's Changed

• Update OpenAIProvider to use environment variable for base URL by @hrahmadi71 in #1117
• Add AzureProvider by @Kludex in #1091
• State persistence by @samuelcolvin in #955
• InstrumentedModel and FallbackModel fixes by @alexmojaki in #1121
• Add PDF support to Anthropic by @camilovelezr in #1123

New Contributors

• @camilovelezr made their first contribution in #1123

Full Changelog: v0.0.39...v0.0.40