v0.5.0 (2025-08-04)

What's Changed

• Breaking Change: The EvaluationReport.print and EvaluationReport.console_table methods now require most arguments be passed by keyword. by @dmontagu in #2163
• Breaking Change: The source field of an EvaluationResult is now of type EvaluatorSpec rather than the actual source Evaluator instance, to help with serialization/deserialization by @dmontagu in #2388
• Let more BaseModels use OpenAI strict JSON mode by defaulting to additionalProperties=False by @DouweM in #2419
• Allow string format, pattern and others in OpenAI strict JSON mode by @DouweM in #2420
• Include default values in tool arguments JSON schema by @DouweM in #2418
• Fix ImageUrl, VideoUrl, AudioUrl and DocumentUrl not being serializable by @DouweM in #2422
• Fix test_download_item_no_content_type test failing on macOS by @strawgate in #2404
• Document performance implications of async vs sync tools by @GuillermoBlasco in #2298
• Document that tools become toolset internally by @HamzaFarhan in #2395
• docs: add missing optional packages in install.md by @Kludex in #2412

New Contributors

• @GuillermoBlasco made their first contribution in #2298

Full Changelog: v0.4.11...v0.5.0

v0.4.11 (2025-08-01)

What's Changed

• Add convenience functions to handle AG-UI requests with request-specific deps by @DouweM in #2397
• Support custom thinking tags specified on the model profile by @xjose97x in #2364
• Rename gemini-2.5-flash-lite-preview-06-17 to gemini-2.5-flash-lite as it's out of preview by @ethan01x in #2387
• Fix toggleable toolset example so toolset state is not shared across agent runs by @DouweM in #2396
• Docs: add an example of using RunContext to pass data among tools by @tonyxwz in #2316

New Contributors

• @tonyxwz made their first contribution in #2316
• @ethan01x made their first contribution in #2387
• @xjose97x made their first contribution in #2364

Full Changelog: v0.4.10...v0.4.11

v0.4.10 (2025-07-30)

What's Changed

• Fix parallel tool calling with tools returning ToolReturn with content by @DouweM in #2365
• Always enter Toolset context when running agent by @strawgate in #2361
• Add priority service_tier to OpenAIModelSettings and respect it in OpenAIResponsesModel by @akenarsari in #2368
• Add HTTP Referer request header to Vercel AI Gateway provider by @joshualipman123 in #2369

New Contributors

• @akenarsari made their first contribution in #2368

Full Changelog: v0.4.9...v0.4.10

v0.4.9 (2025-07-28)

What's Changed

• Ensure AG-UI state is isolated between requests by @DouweM in #2343
• Refine retry logic for parallel tool calling by @DouweM in #2317
• Fix AgentStream.stream_output and StreamedRunResult.stream_structured with output tools by @DouweM in #2314
• Allow default in tool schema with Gemini by @strawgate in #2309

Full Changelog: v0.4.8...v0.4.9

v0.4.8 (2025-07-28)

What's Changed

• Add tenacity utilities/integration for improved retry handling by @dmontagu in #2282
• fix: close initialized MCP server if any MCP server fails to initalize by @hartungstenio in #2312
• Adding thinkingpart to otel_events in ModelResponse by @adtyavrdhn in #2237
• Fix: TypeError in MCPServerSSE due to improper initialization by @tradeqvest in #2319
• Fix: AG-UI assistant text and tool call order by @ChuckJonas in #2328

New Contributors

• @hartungstenio made their first contribution in #2312
• @tradeqvest made their first contribution in #2319
• @ChuckJonas made their first contribution in #2328

Full Changelog: v0.4.7...v0.4.8

v0.4.7 (2025-07-24)

What's Changed

• Add MoonshotAI provider with Kimi-K2 model support by @zachmayer in #2211
• Add Vercel AI Gateway provider by @joshualipman123 in #2277
• Support passing files uploaded to Gemini Files API and setting custom media type by @dprov in #2270
• Parse '' tags in streamed text as thinking parts by @DouweM in #2290
• Rename MCPServer sse_read_timeout to read_timeout and pass to ClientSession by @AntSan813 in #2240
• Update cohere and MCP, add support for MCP ResourceLink returned from tools by @medaminezghal in #2094
• Ignore empty text alongside tool calls when streaming from Ollama by @DouweM in #2286
• Ignore leading whitespace when streaming text, fixing run_stream + Ollama + Qwen3 by @DouweM in #2294
• Fix AG-UI parallel tool calls by @DouweM in #2301
• Fix initial tool call args not being streamed with AG-UI by @DouweM in #2303
• Handle None created timestamp coming from OpenRouter API by @R0boji in #2247
• Update MCP docs to show you can pass ssl options via the http_client arg by @assadyousuf in #2214
• Include ThinkingPart in messages.md API documentation graph by @lfloeer in #2299

New Contributors

• @R0boji made their first contribution in #2247
• @AntSan813 made their first contribution in #2240
• @joshualipman123 made their first contribution in #2277
• @dprov made their first contribution in #2270

Full Changelog: v0.4.6...v0.4.7

v0.4.6 (2025-07-23)

What's Changed

• Enable URL and binary PDF for Mistral by @pintaf in #2267
• Fix pydantic-evals panel rendering with evaluators by @dmontagu in #2274
• Fix mp3 handling by @dmontagu in #2279
• Handle built-in tool errors better in tool registration by @fswair in #2252
• fix: use FileUrl.format to find the extension by @Kludex in #2280
• Correct code snippet for native output by @minhduc0711 in #2271
• chore: simplify output function call with model retry by @bitnahian in #2273
• Reduce duplication between StreamedRunResult and AgentStream by @DouweM in #2275
• chore: add CLAUDE.md by @Kludex in #2281
• Speed up function _estimate_string_tokens by @misrasaurabh1 in #2156

New Contributors

• @minhduc0711 made their first contribution in #2271
• @pintaf made their first contribution in #2267

Full Changelog: v0.4.5...v0.4.6

v0.4.5 (2025-07-22)

What's Changed

• Add async with self in agent_to_a2a by @Kludex in #2266
• Fix include_content not working as expected by @adtyavrdhn in #2206
• Support streamable HTTP in mcp-run-python by @Kigstn in #2230
• change format_as_xml defaults by @samuelcolvin in #2228
• Fix LLMJudge input handling to preserve BinaryContent as separate message part instead of stringifying by @adtyavrdhn in #2173
• validate OpenAI responses by @samuelcolvin in #2226
• Remove duplicate field on GeminiModelSettings by @strawgate in #2269
• Fix AG-UI shared state example by @stevenh in #2272

New Contributors

• @Kigstn made their first contribution in #2230
• @strawgate made their first contribution in #2269

Full Changelog: v0.4.4...v0.4.5

v0.4.4 (2025-07-18)

What's Changed

• Add Toolsets and Deferred Tools by @DouweM in #2024
• Support AG-UI protocol for frontend-agent communication by @stevenh in #2223
• Add identifier field to BinaryContent class by @GDaamn in #2231
• Add OpenAI models o1-pro, o3-pro, o3-deep-research, computer-use by @zachmayer in #2234
• Add grok-4 and groq kimi-k2 models by @zachmayer in #2235
• Remove old Google models by @DouweM in #2220
• Change clai default model to gpt-4.1 by @samuelcolvin in #2227
• Fix VertexAI Empty Model Parts Error by @caesarnine in #2203
• Remove incorrect tool call id from OpenAI tool call delta by @naveen-corpusant in #2210
• Speed up method AgentRunResult._set_output_tool_return by 18798% by @misrasaurabh1 in #2196
• Speed up method Usage.opentelemetry_attributes by 85% by @misrasaurabh1 in #2198
• Nicer errors under the capture_run_messages context by @alonme in #2219

New Contributors

• @naveen-corpusant made their first contribution in #2210
• @caesarnine made their first contribution in #2203
• @GSemikozov made their first contribution in #2193
• @alonme made their first contribution in #2219
• @GDaamn made their first contribution in #2231

Full Changelog: v0.4.3...v0.4.4

v0.4.3 (2025-07-16)

What's Changed

• Include content.1571 by @adtyavrdhn in #2180
• duckduckgo-search is renamed to ddgs by @basnijholt in #2172
• Add base64 encoding to tool_return_ta by @adtyavrdhn in #2186
• Bugfix: avoid race condition when refreshing google token by @JadHADDAD92 in #2100
• feat: Add output function tracing by @bitnahian in #2191
• Add Hugging Face as a provider by @hanouticelina in #1911

New Contributors

• @mmabrouk made their first contribution in #2192
• @basnijholt made their first contribution in #2172
• @JadHADDAD92 made their first contribution in #2100
• @bitnahian made their first contribution in #2191
• @hanouticelina made their first contribution in #1911

Full Changelog: v0.4.2...v0.4.3