Skip to content

Releases: evalstate/fast-agent

v0.4.49

07 Feb 17:38
@evalstate evalstate
v0.4.49
b0a810e

Choose a tag to compare

View all tags
v0.4.49 Latest
Latest

fast-agent 0.4.49

GPT-5.3-Codex and Opus 4.6

Use GPT-5.3-Codex with the codexplan model (e.g. fast-agent --model codexplan. Alias added for GPT-5.2-Codex codexplan52.

Use Opus 4.6 with Adaptive Reasoning and 1m Context Window support. Alias opus now points to Opus 4.6. Adaptive reasoning is on by default, use opus?reasoning=[off|low|med|high|max to set effort hints. Use [?|&]longcontext=1m to enable extended context window.

.agentskills support.

Includes .agentskills/skills as a default skills search location.

Open Telemetry and other fixes

Patches and library updates to restore OpenTelemetry for Anthropic and MCP. Thanks @yarisoy .

Numerous defect fixes thanks to the ever diligent @iqdoctor .

What's Changed

Full Changelog: v0.4.45...v0.4.49

Contributors

evalstate, iqdoctor, and 2 other contributors
Assets 2
Loading

v0.4.45

31 Jan 09:37
@evalstate evalstate
v0.4.45
47890cb

Choose a tag to compare

View all tags
v0.4.45

fast-agent 0.4.45

  • Full ACP Session List/Resume support (note - existing sessions will not be resumable from ACP)
  • Session pinning
  • Improvements to Agent Card live-reloading and history management (thanks @iqdoctor)
  • Kimi K2.5 max output token adjustment
  • Improve History Review mode for reloaded sessions
  • Custom Headers for Anthropic (thanks @floriafz23 )
  • Bedrock Tool Call errors fix (thanks @yarisoy)
  • Improvements to parallel tool call display

What's Changed

New Contributors

Full Changelog: v0.4.43...v0.4.45

Contributors

evalstate, dependabot, and 3 other contributors
Loading

v0.4.43

27 Jan 14:04
@evalstate evalstate
v0.4.43
5fa2a67

Choose a tag to compare

View all tags
v0.4.43

Changes

Screenshot 2026-01-27 120829

Validated Kimi-K2.5 with hugging face inference providers via novita. Structured, Vision, Tools and reasoning switch. Alias for "instant" added (moonshots term) -- use with kimi25?instant=on to disable thinking.

Contributors

evalstate
Loading

v0.4.42

27 Jan 00:04
@evalstate evalstate
v0.4.42
d756cad
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v0.4.42

fast-agent 0.4.42

  • OpenAI verbosity setting through model string and TUI/ACP (e.g. Gpt-5.2?verbosity=high&reasoning=low)
  • GLM 4.7 reasoning control (e.g. glm?reasoning=off)
  • Agent Lifecycle Hooks (see skill from /skills add)
  • Anthropic Structured Output support (supports reasoning with structured outputs. supply structured=tool_use to force legacy behaviour).
  • Fix #644 Azure headers.
  • Fix ruamel dependency for main package (from hf-inference-acp).
  • Improve error handling/logging for tool hooks.

What's Changed

Full Changelog: v0.4.40...v0.4.42

Contributors

evalstate and dependabot
Loading

fast-agent 0.4.40 (the self modifying version)

25 Jan 00:18
@evalstate evalstate
v0.4.40
b47dbfa
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
fast-agent 0.4.40 (the self modifying version)

fast-agent 0.4.40

This release note wraps up a huge number of features and improvements made over the last couple of weeks. I hope you enjoy them.

fast-agent skills

Skills for modifying and working with fast-agent are available by default through /skills add. Use /skills registry to add a registry or select preconfigured (Hugging Face / Anthropic). Repo is here

image

Tool Hooks and Agent Lifecycle Hooks

Extend Agents with simple Python code using the inbuilt hooks. They let you hook Agent/Subagent lifecycle and LLM Loop events,
intercepting and modifying commands, adjusting inputs and outputs, starting containers, designing your own compaction strategies.

The following hooks are supported, extendable with simple Python code that gives you access to the execution context.

Tool hooks:

  • before_llm_call
  • after_llm_call
  • before_tool_call
  • after_tool_call,
  • after_turn_complete

Agent Lifecycle hooks:

  • on_start
  • on_shutdown

When hooks are presented they are indicated with a ◆ next to the message or tool call.

image

Check the bundled skill to begin customising fast-agent! Switch on hot reloading with the --watch flag.

To create a subagent at runtime, simply use /agent <filename> --tool .

Example

Agent Card frontmatter:

name: dev-agent
model: codexplan
 tool_hooks:
   after_turn_complete: hooks.py:save_history

Python code

 from fast_agent.hooks.hook_context import HookContext
 from fast_agent.mcp.prompt_serialization import save_messages

 async def save_history(ctx: HookContext) -> None:
     save_messages(ctx.message_history, "history.json")

User Interface Improvements (a3 design)

fast-agent is unique in being CLI first - integrating perfectly with your terminal and preserving the scrollback buffer.  

fast-agent is has had a visual refresh, improving usability in long tool loops and workflows. Vertical space is much better used, and the stream is optimised for supervising LLM, Tool and subagent streams - highlighting important elements and actions, and enabling interventions where needed. Long gone are the days of monitoring single MCP tools calls!  Forms (human_input and MCP Elicitation) are also cleaner, with more content able to placed on the screen.

tool_stream.mp4

Of course, if you prefer a more refined front-end experience try Toad. Simply run toad acp "fast-agent-acp".

Integrated Shell

Run shell commands by entering ! and the command. Shell completion is supported (CTRL+SPACE). Enter ! to start a new shell, and exit to return to fast-agent.

shell2.mp4

Agent Query

Use # to send a message to an agent, and have the result returned to your input buffer ready for editing. Perfect for getting different model/agents feedback on plans, or with the human_input tool to create an interactive experience - or simply to get concise inputs.

hash_one.mp4

Bash output truncation

By default, shell output is truncated to 5 lines (configurable with output_display_lines under shell_settings in config).

To review the complete output use the /history review command.

Sessions and History Management

/history rewind lets you go back to a previous user turn, and place the message at that point in to the input buffer for editing.

Sessions are saved automatically and resumable with the /session resume <sessionid> command or --resume cli flag, and can be forked with /session fork. Use /session title <title> to give them memorable names.

Screenshot 2026-01-24 225448

fast-agent environments

Agent environments (config, skills and agent cards) can be specified with the --env <directory> flag. They can also be deployed as MCP Servers (fast-agent serve or used with any ACP client (fast-agent-acp shortcut).

Reasoning Adjustment

Model reasoning effort can be adjusted with the /model reasoning command, and supplied as a request parameter on the model string.

For example:

model: opus?reasoning=1024
model: codexplan?reasoning=xhigh
fast-agent --model haiku?reasoning=0

Existing configuration options and formats work, but more model settings will be migrated to this format over time.

OpenAI Codex Plan support

Use fast-agent auth codexplan to log in to your Codex CLI plan, and then specify the codexplan model to use it (currently aliased to GPT-5.2-codex). Use of the plan is denoted by a $ symbol in the status bar. The apply_patch tool has been ported to Python from Codex - improving token efficiency when using this model.

<img width="640"  alt="image" src="https://github.com/user-attachments/assets/99463eac-6591-43e6-8b76-ab3e928e8b6e" />

Aliyun Improved Model Support

Qwen3-Max added -- more soon

Big thanks to @iqdoctor !

What's Changed

New Contributors

Full Changelog: v0.4.31...v0.4.40

Contributors

evalstate, dependabot, and iqdoctor
Loading

v0.4.31

15 Jan 22:17
@evalstate evalstate
v0.4.31
57e074c

Choose a tag to compare

View all tags
v0.4.31

Open Responses and GPT-5.2-codex.

fast-agent has Open Responses Client support. This is in beta until official SDKs etc. are launched. This was added by fast-agent using gpt-5.2-codex which was launched in 0.4.30. The codex alias now points to this model.

https://fast-agent.ai/models/llm_providers/

image

Join the fast-agent Discord here to discuss.

Contributors

evalstate
Loading

v0.4.29

12 Jan 22:51
@evalstate evalstate
v0.4.29
6c86caf

Choose a tag to compare

View all tags
v0.4.29

Responses and Hot Reload!

OpenAI Responses is now the default

Stateless Responses API (encrypted reasoning) is now the default for gpt-5 and o- series models. gpt-5.1-codex has been added as an alias.

Hot Reload of Agent Cards

By @iqdoctor -- hot reload of AgentCards (both Agents and Agents-as-Tools); completely dynamic, self-rewriting agents now possible. Available via TUI and ACP.

Other Changes

Full Changelog: v0.4.27...v0.4.29

Contributors

evalstate and iqdoctor
Loading

v0.4.27

11 Jan 11:52
@evalstate evalstate
v0.4.27
81239a6
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v0.4.27

What's Changed

Toad/Agent Card Examples

Added a new quickstart with hackable examples of Agents, Agents as Tools and Skills. Hot reload available (❤️ @iqdoctor ).

fast-agent: fast-agent quickstart toad-examples
From Toad: ctrl+o, Setup and /quickstart or use the wizard

Hash Commands

Send a message to an agent, and have it's result sent to the Input Buffer of the currently active agent.

MCP Client keep-alive

Client to Server ping healthcheck (thanks @Agent-Hellboy )

New Contributors

Full Changelog: v0.4.22...v0.4.27

Contributors

evalstate, Agent-Hellboy, and iqdoctor
Loading

v0.4.22

04 Jan 22:42
@evalstate evalstate
v0.4.22
047ce1b

Choose a tag to compare

View all tags
v0.4.22

Agent Cards

New feature - Agent Cards.

Read the article by @iqdoctor here: https://github.com/evalstate/fast-agent/blob/main/plan/agentcard-standards-mini-article.md.

Agents can be loaded as peers, or as tools (using --card / --card-tool or /card <filename> [--tool] from ACP/UI. Cards are also auto-loaded from .fast-agent/agent-cards or .fast-agent/tool-cards, and can reference Python function tools.

  • REPL. New AgentCard in md fromat and CLI loading/lazy hot swap with --agent-cards | --watch | --reload options. New workflow-md samples by @iqdoctor in #585
  • Add command line option for loading card as tool by @evalstate in #590
  • Feat/auto load by @evalstate in #593
  • Add decorator function_tools support and RAG example by @iqdoctor in #592

Hugging Face Space Deployment

Improved support for HF Spaces deployment (deployment skill to be follow) - use HF OAuth to use end-user token for inference.

What's Changed

Full Changelog: v0.4.17...v0.4.22

Contributors

evalstate and iqdoctor
Loading

v0.4.17

28 Dec 23:34
@github-actions github-actions
v0.4.17
d57a646

Choose a tag to compare

View all tags
v0.4.17

Sampling with Tools Release

  • SEP-1577 - Sampling with Tools. @evalstate (#578)
  • SEP-1036 - URL Elicitaitions.
  • SEP-991 - CIMD support for OAuth.

Notes

You may need to remove earlier DCR tokens before re-authorizing. Use fast-agent auth to manage saved tokens.

Contributors

evalstate
Loading