v0.4.3

What's Changed

General

• Model selection available through FAST_AGENT_MODEL environment variable, message on startup when used.
• Enhanced Tool Call / Transport instrumentation in timing channel
• Allow absolute paths to be specified for Skills. (NB - best results usually when skills are in a subdirectory).
• LLM Retry Logic (thank you @usamaJ17 !)
• MCP Session Termination retry (use reconnect_on_disconnect: False in config to disable)
• Enhanced support/testing for HF Reasoning models.
• Improve HF provider selection (and provider selection message on startup).

Agent Client Protocol

• Auth view/reset
• Improved Streaming and Permission updates.
• Improved Reasoning token streaming.

Auto-generated:

• fix: prompt template file resolution ordering by @evalstate in #521
• update tool timing saving, including transport channel by @evalstate in #523
• allow absolute paths for skills directories by @evalstate in #524
• Feat/model env option by @evalstate in #526
• Feat/reasoning streaming by @evalstate in #529
• Implement Agent Client Protocol tools for CLI by @evalstate in #528
• fix: Centralize robust API retry logic in FastAgentLLM & preserve context by @usamaJ17 in #517
• Dev/0.4.2 by @evalstate in #530
• Compare session termination handling implementations by @evalstate in #532
• Feat/auth status acp by @evalstate in #533
• Improve acp progress by @evalstate in #534
• Simplify status command when no errors exist by @evalstate in #535

New Contributors

• @usamaJ17 made their first contribution in #517

Full Changelog: v0.4.1...v0.4.3

v0.4.1

What's Changed

• Fix #518. Remove ESC key handling - ctrl+c still cleanly cancels generation.
• Opus 4.5 support (alias opus and opus45)

v0.4.0

fast-agent 0.4.0

Agent Client Protocol (ACP) Support

fast-agent now has support for Zed Industries Agent Client Protocol, allowing seamless integrations with editors like Zed and Toad.

Read more about the integration at https://fast-agent.ai/acp/.

Workflow agents and MCP Tool Calls deliver workflow and progress notifications, multimodal content, agent skills, model comparison and cancellation are all supported. The default system prompt loads AGENTS.md if present.

A new command line fast-agent-acp has been added for convenience, and a no-install package is on PyPi - use it with uvx fast-agent-acp@latest --model xxx.

Stateless LLM Providers

LLM Providers are now stateless, simplifying cross-model switching and history management. The load_history command now has completions to enable easy loading.

Other Changes

• ESC key cancellation is supported
• Hugging Face kimi kimithink and qwen3 aliases now use Together as their default provider.

What's Changed

• Stateless LLM Providers by @evalstate in #499
• Review and audit codebase by @evalstate in #503
• Refactor type hints to modern Python syntax by @evalstate in #502
• Add ESC key cancellation for LLM provider calls by @evalstate in #505
• Remove unnecessary getattr calls with type info by @evalstate in #506
• Review ACP cancellation token implementation by @evalstate in #507
• Use prompt toolkit completion for /load_history command by @evalstate in #509
• Add ESC key handler to cancel streaming messages by @evalstate in #510
• Add load slash command to Python SDK by @evalstate in #511
• Add telemetry to Chain and Iterative Planner agents by @evalstate in #512
• Dev/0.4.0 by @evalstate in #514

Full Changelog: v0.3.29...v0.4.0

v0.3.29

What's Changed

• gpt-5.1 support
• add kimithink alias for Hugging Face, clamp kimi and kimithink aliases to "together" provider.
• Improve System Prompt template handling https://fast-agent.ai/agents/instructions/

Review full changelog here:

Full Changelog: v0.3.23...v0.3.29

v0.3.23

Hugging Face Inference Providers Support 🤗

HF Inference Providers are now fully supported -- read the documentation here: https://fast-agent.ai/models/llm_providers/#hugging-face

NB The default alias for kimi now points to the hf provider, with kimigroq for the Groq direct provider.

The following aliases have been configured, and tested/configured with Structured Outputs and Tool Use:

Alias	Maps to
kimi	hf.moonshotai/Kimi-K2-Instruct-0905
gpt-oss	hf.openai/gpt-oss-120b
gpt-oss-20b	hf.openai/gpt-oss-20b
glm	hf.zai-org/GLM-4.6
qwen3	hf.Qwen/Qwen3-Next-80B-A3B-Instruct
deepseek31	hf.deepseek-ai/DeepSeek-V3.1
minimax	hf.MiniMaxAI/MiniMax-M2

To try simply use fast-agent --model kimi for HF Routing or fast-agent --model kimi:together to specify "Together AI" as the provider.

Package Changes

Bedrock and Tensorzero packages should now be installed as add-ons:

uv tool install fast-agent-mcp[bedrock] and uv tool install fast-agent-mcp[tensorzero] respecitvely.

Other Changes

• ConversationSummary is a new utility class that analyzes agent conversation history and provides computed statistics for easy monitoring, debugging and evaluations. It automatically extracts key metrics including tool call counts, error rates, per-tool breakdowns, and timing information (average response time, total elapsed time, conversation span). All statistics are accessible as properties. The class can be used with the load_history function to analyse saved conversations.
• Change Server-Tool separator from - to __.
• Improvements to History display
• save_history now uses a default filename if not specified.

What's Changed

• Feat/serve command by @evalstate in #445
• fix: remove unused tomli package by @danfimov in #448
• fix issue #447 by @evalstate in #449
• fix(common): Improve constant SEP from "-" to "__" for namespaced names by @codeboyzhou in #298
• Feat/tool naming display by @evalstate in #451
• Fix recent changes defect by @evalstate in #452
• Test agent job execution and performance metrics by @evalstate in #453
• fix: Prevent display freeze during tool call streaming by @evalstate in #454
• fix: Restore buffer truncation to enable continuous scrolling by @evalstate in #455
• docs: rename plantype references to plan_type by @iqdoctor in #456
• Add FAST_AGENT_TIMING channel for instrumentation by @evalstate in #457
• Reduce package dependencies in fast-agent by @evalstate in #459
• Fix save_history function bug by @evalstate in #460
• Feat/acp by @evalstate in #463
• Fix All Remaining Issues by @evalstate in #462
• Add ACP terminal support to agent implementation by @evalstate in #464
• Handle overlapping ACP prompt requests gracefully by @evalstate in #465
• Fix duplicate messages in ACP client connection by @evalstate in #466

New Contributors

• @danfimov made their first contribution in #448
• @iqdoctor made their first contribution in #456

Full Changelog: v0.3.17...v0.3.23

v0.3.17

fast-agent 0.3.17 skills'n'shells

Agent Skills

Support for Agent Skills - check the documentation here: https://fast-agent.ai/agents/skills

Shell Access

Agents can now access the shell. Use the -x or --shell command line option to enable. Use at your own risk!

Markdown Streaming (Experimental)

Markdown Streaming now enabled by default for all providers (including Google Gemini).

markdown_streaming_small.mp4

Switch to plain text or disable streaming by updating fastagent.config.yaml:

logger:
  # Streaming renderer for assistant responses: "markdown", "plain", or "none"
  streaming: markdown

(Note due to the nature of doing this in a standard Terminal, occasional scroll-back pollution may occur).

Tool Call Streaming (OpenAI Models)

OpenAI Models support streaming of Tool Call arguments, providing immediate feedback when generating large amounts of content:

trimmed_reencoded.mp4

Thank you

Huge thank you to all Users and Contributors who keep fast-agent focused on being a powertool. Join us in the Discord at https://discord.gg/Dw9gHejh

What's Changed

• fix(google): handle const in tool schemas for Gemini (string=>enum; drop non-string const) by @xek in #421
• Fix/0.3.13 by @evalstate in #422
• Use DEFAULT_MAX_ITERATIONS as a fallback in tool calls by @mylux in #423
• Feat/apps sdk by @evalstate in #425
• configurable timeline! by @evalstate in #426
• Fix/apps sdk by @evalstate in #427
• Normalize tool call request params by @mylux in #424
• ElicitationForm: Add support for pattern matching in string fields by @pommfresser in #428
• [BUGFIX] Fix the agent dependencies by @ChrisW-priv in #430
• Provide tool error feedback agent by @mylux in #431
• Plain/Markdown Streaming Support [Experimental] by @evalstate in #433
• Add text navigation mode by @pommfresser in #437
• Feat/agent skills by @evalstate in #439
• Feat/improve tool stream by @evalstate in #442

New Contributors

• @xek made their first contribution in #421
• @mylux made their first contribution in #423
• @pommfresser made their first contribution in #428

Full Changelog: v0.3.12...v0.3.17

v0.3.12

Major Changes

• Sonnet 4.5 Support
• MCP Transport Diagnostics Command (/mcp)
• Show Agent History and Clear History Command (/history, /clear)
• Enhanced Display Handling
• Type clean-up

What's Changed

• README Update - Incorrect Example by @nicholasericksen in #402
• Feat/transport display/LLM Error Handling by @evalstate in #407
• stdio tracking, display tweak by @evalstate in #408
• icon and colour scheme fixes by @evalstate in #409
• improve notification handling, auto-cancel config, timeline display by @evalstate in #410
• [Mixed] Refactor + Fix + Example of McpAgent definition added by @ChrisW-priv in #411
• sonnet 45 model db update by @evalstate in #417
• feat: add an example of how to define a Tool Use agent that has direc… by @ChrisW-priv in #413
• Fix/deco types clean by @evalstate in #419
• feat: clear histories on the 'clear' special command by @ChrisW-priv in #414

New Contributors

• @nicholasericksen made their first contribution in #402

Full Changelog: v0.3.8...v0.3.12

v0.3.8

What's Changed

• Support for XAI grok-4-fast! 2M Context Window VLM - model aliases:

grok-4-fast = grok-4-fast-non-reasoning
grok-4-fast-reasoning = grok-4-fast-reasoning

• Added A2A example (@usamaJ17)

• grok-4-fast support, a2a example, docstrings by @evalstate in #400

Full Changelog: v0.3.7...v0.3.8

v0.3.7

Major Features

• mcp-ui support @idosal
• OAuth and Keyring Support added
• MCP Instructions support added
• Improvements to exported API layout
• Default serialization to PromptMessageExtended format
• Handle untokenizable content for models
• Code improvements thanks (@ChrisW-priv )

What's Changed

• Bedrock 0.3.0 refactor by @jdecker76 in #378
• Feat/check design by @evalstate in #380
• Feat/mcp UI by @evalstate in #382
• Fix/migration by @evalstate in #383
• Feat/save history command by @evalstate in #384
• Fix/exports by @evalstate in #385
• Fix/0.3.3 by @evalstate in #386
• FastAgent exported from fast_agent module by @evalstate in #387
• Feat/mcp UI output by @evalstate in #388
• Feat/oauth v1 by @evalstate in #389
• Fix/0.3.6 by @evalstate in #390
• chore: make a check for the length of the agent dict by @ChrisW-priv in #395
• Remove the boilerplate in the create_agents_in_dependency_order function by @ChrisW-priv in #396
• Fix/0.3.7 by @evalstate in #398

New Contributors

• @ChrisW-priv made their first contribution in #395

Full Changelog: v0.3.0...v0.3.7

v0.3.0

fast-agent 0.3.0

Warning

This release contains breaking API changes. Pin to 0.2.58 if necessary.

• mcp-ui support
• api enhancements and improvements
• migration to fast_agent package. some compatibility layer remains.
• augmented_llm deprecated; improved architecture

Changes

• Feat/save history command @evalstate (#384)
• Fix/migration @evalstate (#383)
• Feat/mcp UI @evalstate (#382)
• Feat/check design @evalstate (#380)
• Bedrock 0.3.0 refactor @jdecker76 (#378)
• Dev 0.3.0 @evalstate (#366)