v0.2.51

TensorZero Updated Support and QuickStart

Read the updated documentation here: https://fast-agent.ai/models/llm_providers/#tensorzero-integration

• Migrate tensorzero implementation from native inference to OpenAI, and add quickstart by @aaronpolhamus in #308 -

gpt-oss support on Groq

Added support for groq.openai/gpt-oss-120b and groq.openai/gpt-oss-20b, tested with Tools and Structured Output. Aliases added for quick access : gpt-oss and gpt-oss-20b. so you can access with:

fast-agent --model gpt-oss

• Fix TypeError when Google Gemini returns None content.parts by @HarshLit in #328

New Contributors

• @HarshLit made their first contribution in #328

Full Changelog: v0.2.50...v0.2.51

v0.2.50

Groq Provider Support

Groq Provider support now added! Structured Outputs and Tool calling tested with moonshotai/kimi-k2-instruct, qwen/qwen3-32b and deepseek-r1-distill-llama-70b. Use the kimi is supported a model alias.

Get started with fast-agent --model kimi.

by @evalstate in #325

Also fixes usage of model database for OpenAI derivatives.

Tool Progress Notifications

• tool progress notifications by @evalstate in #323

Full Changelog: v0.2.49...v0.2.50

v0.2.49

Experimental Groq Support

• "kimi" added as a model alias for "groq.moonshotai/kimi-k2-instruct". More models being validated soon.

Other Changes

• Fix/issue 314 OpenAI tool validation by @ksrpraneeth in #320
• client implementation spoofing, progress display tweaks by @evalstate in #321

New Contributors

• @ksrpraneeth made their first contribution in #320

Full Changelog: v0.2.47...v0.2.49

v0.2.47

New! Mermaid Diagram Support and Iterative Planner

• NEW - Iterative Planner (replacing Orchestrator) by @evalstate in #313
• mermaid diagram support by @evalstate in #315

There is a new iterative_planner agent which paves the way to replace the old Orchestrator and open the path for Dynamic Agents. (@storlien). The original Orchestrator is in place, but will be migrated based on feedback/tuning of the new iterative_planner.

Mermaid diagram support also added - detected diagrams appear in links beneath the assistant message. Enjoy 😎

Full Changelog: v0.2.46...v0.2.47

v0.2.46

Instruction Templating and Loading Improvements

Lots of great new features to make working with agents smoother (fetching prompts and templates from files/urls and embedded urls).
PLEASE READ https://fast-agent.ai/agents/instructions/
This introduces a breaking change (the --instructions argument for fast-agent go has changed).

What's Changed

• Improve Agent instruction handling/templating. (@storlien 👀)
• Bump MCP SDK to 1.12.1
• Add py.typed into pyproject.toml packaging by @chughtapan in #305
• Improve type exports, make Elicitation Form easy to use via API. Including defaults (@chughtapan)

New Contributors

• @chughtapan made their first contribution in #305

Full Changelog: v0.2.45...v0.2.46

v0.2.45

Changes

• Improve JSON Printing for Assistant Responses
• Use JSON Mode for Anthropic Structured Outputs @evalstate (#302)
• Update models in Evaluator example @evalstate (#301)
• Feat/display update @evalstate (#300)
• Update default model in Router.py
• Improve handling of System Prompt/Default Prompt for Router Simplify Eval/Optimizer
• Feat/display update by @evalstate in #300

Full Changelog: v0.2.44...v0.2.45

v0.2.44

Visual Update

This release refreshes the Console Display to use a new style (trialled with the new fast-agent go multi-model feature). If this is causing you issues then update the logger config to use_legacy_display: true.

What's Changed

• Fix/resource display by @evalstate in #294
• Adjust the lifetime of event queue for listeners in AsyncEventBus by @ufownl in #285
• Fix ResourceLinks for OpenAI
• Standardize on ContentBlock
• Bump SDK to MCP 1.12.0

Full Changelog: v0.2.42...v0.2.44

v0.2.42

What's Changed

MCP Tool, Resource, Prompt filtering selection:

Powerful filtering for MCP primitives per-agent so you can configure the precise tools, prompts and resources you need. See https://fast-agent.ai/mcp/#mcp-filtering for instructions

• MCP filtering by @jdecker76 in #282

AWS Bedrock Provider Native Support

Another huge contribution! https://fast-agent.ai/models/llm_providers/#aws-bedrock

• AWS Bedrock provider native support by @jdecker76 in #274

Small changes

• fix o4 and adjust hf space auth token @evalstate in #293 (solves #279 - thanks for raising @storlien

New Contributors

• @jdecker76 made their first contribution in #282

Full Changelog: v0.2.41...v0.2.42

v0.2.41

What's Changed (fast-agent users please read!)

Auto-Parallel, NPX and UVX from Command Line

Auto-Parallel FEEDBACK REQUESTED

You can now specify multiple models for fast-agent, and get a formatted response for each model. This is perfect for comparing model outputs side-by-side or MCP Server behaviour. Comma delimit the models like so:

fast-agent --models gpt-4.1,grok-3,haiku

You can also specify a message to automatically prompt with (-m "hello, world" or a prompt file --prompt-file "testing.md").

The parallel output in this mode is styled differently to the normal fast-agent output - no side bars (easy copy/paste) and markdown rendering enabled. There is also a "tree" style view for Router and Parallel agents. I am thinking about deploying this style more widely - please let me know what you think by trying the multi-model feature.

You can now run fast-agent to specify an NPX or UVX MCP Server directly:
fast-agent --npx @llmindset/mcp-webcam.
To pass arguments:
fast-agent --npx "@llmindset/mcp-webcam --arg1 --arg2

• allow npx/uvx from command line by @evalstate in #269
• "tree display" for router and parallel.
• fix azure api key environment variable handling (thanks for raising #270 @storlien)

xAI Grok 3 and Grok 4 support

• Add xAI (Grok 3 and 4) support by @Craftzman7 in #276

Show MCP Prompts / Tools

• Display MCP prompt and tool title in the [Available MCP Prompts/Tools] table by @codeboyzhou in #271

Set API key per-agent

• Add api_key argument to specify API KEY when creating agents by @ufownl in #268

New Contributors

• @Craftzman7 made their first contribution in #276

Full Changelog: v0.2.40...v0.2.41

v0.2.38

fast-agent: MCP Elicitation Support

Tip

Read the Quick Start guide here https://fast-agent.ai/mcp/elicitations/ to get up and running with fully working MCP Client/Server demonstrations.

fast-agent now has comprehensive support for the MCP Elicitations feature, providing compliant, interactive forms that allow full preview and validation before submission. It supports all data types and validations (including email, uri, date and date-time) with fully interactive forms.

There is an cancel-all option (easily navigable with ← + Enter) for safety that automatically cancels further Elicitations from the MCP Server.

For MCP Server developers, the form is fast and easy to navigate to facilitating iterative development. You can also specify your own custom Elicitation handlers.

What's Changed

• Feat/elicitation by @evalstate in #261
• Fix the issue of google native when use_history=False by @ufownl in #257
• Fix: Pass include_request parameter to ParallelAgent constructor by @gwburg in #265
• Fix/build res other by @evalstate in #262

New Contributors

• @gwburg made their first contribution in #265

Full Changelog: v0.2.36...v0.2.38

Thanks to @gwburg and @ufownl for their contributions in this release.