v0.6.7

What's new

• Reduce Markdown streaming flickering
• Fix Opus/Sonnet 4.6 structured content API warning
• Display README files from card pack installs/updates (--pack) option
• Fix by @phucly95 to fix per-agent skill filtering
• Fix by @peachgabba22 to fix MCP connectivity for non-persistent Servers.
• Suppress uvloop / prompt_toolkit warnings on Python 3.14

New Contributors

• @phucly95 made their first contribution in #729
• @peachgabba22 made their first contribution in #737

Full Changelog: v0.6.1...v0.6.7

v0.6.1

What's Changed

• GPT-5.4-mini/nano support
• Remove SSE server support / migrate to FastMCP3 by @evalstate in #724

Full Changelog: v0.6.0...v0.6.1

v0.6.0 ❤️llama.cpp

fast-agent 0.6.0

llama.cpp support

• Added llama.cpp model discovery, import, and launch-oriented picker flows to make local model setup much easier. Use with fast-agent model llamacpp.
• Reads model settings (available context window size) and modalities, and creates a configuration file (model overlay). If you want to include sampling parameters from the server use --include-sampling-defaults.

Model Overlays

• Added local model overlays so teams can define reusable local model aliases and runtime settings outside the built-in catalog.
• Expanded model selection and switching UX across CLI, prompt UI, and ACP, with better cataloging, diagnostics, and reference handling.
• https://fast-agent.ai/models/model_overlays/

Anthropic 1M Context, Google Native Refresh

• Support for Anthropic 1M context window for 4.6 class models. Older models still require the extension flag e.g. claude-sonnet-4-5?context=1m
• Improved Google Gemini support and general Gemini provider behavior.
• Added support for Anthropic 1M-context workflows and broader Anthropic capability improvements.
• Introduced a dedicated skills CLI and reworked the skills subsystem into clearer service and operations layers.
• Improved ACP/MCP command handling, auth passthrough, session behavior, and command-surface parity.
• Upgraded prompt and interactive shell experiences, including better completions, tool display, history views, and input/runtime structure.
• Added more detailed history summaries, response telemetry, tool tracking, and streaming behavior coverage.
• Refactored core runtime, agent loading, validation, and model resolution code to support the newer workflows more cleanly.

⚠️WARNING

• Model Aliases are now known as Presets (e.g. kimi25).
• Configuration Aliases are now known as References (e.g. $system.default, $system.fast). Configuration files will need to be updated if they defined aliases.
• Large internal refactorings -- no major API changes but be careful upgrading regardless.

What's Changed

• Support local Codex auth.json override by @iqdoctor in #709
• Feat/acp registry by @evalstate in #711
• Dev/0.5.9 by @evalstate in #712
• Harden interrupted session tool-loop recovery by @evalstate in #713
• Upgrade and clean to ty 0.0.21. by @evalstate in #714
• Add skills CLI and extract standalone-ready skills core by @evalstate in #715
• Add history timing summaries and streaming telemetry by @evalstate in #716
• mcp: report lower-layer startup errors accurately by @iqdoctor in #717
• Fix/ty0.23 by @evalstate in #718
• Bump pyjwt from 2.10.1 to 2.12.0 by @dependabot[bot] in #720
• Dev/0.5.12 by @evalstate in #719
• Feat/model overlay by @evalstate in #722
• Feat/model overlay followup by @evalstate in #723

Full Changelog: v0.5.7...v0.6.0

v0.5.7

What's Changed

OpenAI Responses Improvements and gpt-5.4 support

• Support for gpt-5.4 (codexplan alias updated) and gpt-5.3-chat-instant (chatgpt alias)
• Support for assistant "phase"
• SDK version update
• Service Tier selection fast and flex for supported models (use Shift+TAB in UI for convenience)
• WebSocket is now the default transport - (use ?transport=sse for SSE connections) NB: OpenResponses remains SSE

Shell Improvements

• read_text_file and write_text_file are supplied with shell access (Qwen 3.5/ACP compatibility). Configurable with write_text_file_mode (auto|on|off|apply_patch)
• write_text_file is replaced with apply_patch for Responses models
• apply_patch output is coloured post streaming
• read_text_file previews enhanced and syntax highlight aware.
• Skill prompt generation now uses explicit read-tool naming (read_text_file vs read_skill) based on
  runtime capability.

Tool Result passthrough

• Option in request_params and model card to bypass LLM processing of tool outputs (intended for use with code-mode style subagents and MCP Servers).

Other UI/UX Improvements

• service_tier, reasoning, verbosity, web_search and web_fetch are toggled with Shift+TAB, F6-F9 keys)
• Added fast-agent model setup and fast-agent model doctor to manage model configuration and aliases
• Added Codex login link in the model picker
• fast-agent model setup now guides users through missing, invalid, and configured aliases
• fresh model setup now defaults to $system.default
• Use ##<agent> to send a message to an agent with silent return to the input buffer.
• Interactive UI toolbar/model chip was upgraded with service-tier, reasoning, verbosity, web-search, and
  web-fetch indicators.

New prompt shortcuts and controls:

• Shift+Tab service-tier cycle
• F6 reasoning cycle
• F7 verbosity cycle
• F8 web search toggle
• F9 web fetch toggle

Internal / Refactor / Tests

• Shared formatting and marketplace-argument parsing helpers for command handlers.
• Unified A3 header rendering utility used across CLI/command surfaces.
• Docs layout switched to a docs git submodule pointer.
• Broad test expansion for passthrough flow, filesystem runtime, apply_patch display/preview, quiet hash-
  send, display suppression, model controls, and ACP response-mode handling.
• Improved cancellation/interrupt handling across interactive, CLI runner, ACP prompt handling, and tool-
  loop history reconciliation.
• Better post-cancel recovery: stale progress row cleanup, clearer cancelled-turn messaging, and safer
  task cancellation state handling.
• Improved read_text_file and shell result display behavior (cleaner summaries, truncation behavior,
  display suppression integration).
• Refined MCP connection/reconnect handling and stream transport tracking hooks.
• Result export reliability improvements for one-shot message runs (including transient result history
  capture when needed).

v0.5.6

What's Changed

• Huge improvements to Markdown Streaming Performance
• Major WebSockets improvements for Responses API.
• Minimax M2.5 and Qwen 3.5 Support
• Model Picker
• MCP experimental sessions demonstrations
• Other display enhancements

• Dev/0.5.1 by @evalstate in #693
• Bump requests from 2.32.3 to 2.32.4 by @dependabot[bot] in #690
• Bump urllib3 from 2.3.0 to 2.6.3 in /docs by @dependabot[bot] in #688
• Dev/0.5.2 by @evalstate in #694
• fix websocket continuation, more geneourous shell token limits by @evalstate in #695
• Bump requests from 2.32.3 to 2.32.4 by @dependabot[bot] in #699
• migrate to new schema by @evalstate in #698
• markdown optimistic case improvements by @evalstate in #700
• Dev/0.5.4 by @evalstate in #697
• fix double print by @evalstate in #701
• Feat/model selector by @evalstate in #702

Full Changelog: v0.5.1...v0.5.6

fast-agent 0.5.1 codex and config

Codex and Config

• GPT-5.3-codex support via API Key
• All OpenAI Responses models can now be configured to use WebSocket (add ?transport=ws to the model string e.g. fast-agent -x --model responses.GPT-5.2?transport=ws)
• Improvements to WebSocket handling/planning
• fastagent.config.yaml and AgentCards can both use target style configuration for MCP
• MCP Experimental Sessions support and demos

Full Changelog: v0.5.0...v0.5.1

fast-agent `0.5.0`

fast-agent 0.5.0 series

• Support for "card packs" - adding, updating, publishing from command line and ACP/TUI. (fast-agent cards or /cards).

• Improved model handling with support for aliases (e.g. $system.code or $system.fast). New /models command and CLI option.

• Improved Smart Agent MCP functionality.

• MCP Completion Support

• NB This does not break API compatibility but fast-agent setup is now fast-agent scaffold and other automations may need command line updates.

What's Changed

• Bump cryptography from 46.0.3 to 46.0.5 by @dependabot[bot] in #684
• Bump requests from 2.32.3 to 2.32.4 by @dependabot[bot] in #685
• Fix/markdown by @evalstate in #686
• Feat/OpenAI search by @evalstate in #687
• Bump pillow from 11.2.1 to 12.1.1 in /docs by @dependabot[bot] in #689
• Feat/model enhancements by @evalstate in #691

Full Changelog: v0.4.54...v0.5.0

v0.4.54

fast-agent 0.4.54

Sonnet 4.6 and Web Search/Web Fetch features

Support for claude-sonnet-46, as well as Web Search and Fetch features (all supported models). Enable with ?web_search=on&web_fetch=on.

NB The older web tools appear to perform better, I will continue testing and revert/fix as needed.

Agent Card MCP enhancements / Smart Agent improvements.

Specify url, npx or uvx MCP connections directly from the Agent Card:

mcp_connect:
  - target: "https://hf.co/mcp"
    name: "hf_hub"
  - target: "npx @modelcontextprotocol/server-everything"
    name: "everything"

Smart Agent instructions can be added to prompts with:

{{internal:smart_prompt}} for the default smart agent prompt, {{internal:smart_agent_cards}} for the description section. Read more at https://fast-agent.ai/agents/instructions/#template-variables for other new template vars.

Web Socket Improvements

Improved Web Socket handling for codexplan models.

What's Changed

• Dev/0.4.54 by @evalstate in #683

Full Changelog: v0.4.53...v0.4.54

v0.4.53

fast-agent 0.4.53 -- hot sockets and skills

What's Changed

• Experimental: Codex Spark support. Use model string codexspark
• Experimental: Websockets for OpenAI Plan - Use codexspark?transport=ws or codexplan?transport=ws to enable Web Socket connection.
• Skill Update mechanism -- uses a small manifest to track git source and allow updating without manifest/marketplace peeking.
• GLM-5 support via Hugging Face inference providers.
• Introduce --agent and --noenv flags to make use in evaluations/testing simpler
• ACP Registry compatibility and nested agent notifications (thanks @iqdoctor)
• /mcp connect command to allow dynamic loading/reloading of MCP Servers. This works similar to the command line so /mcp connect https://huggingface.co and /mcp connect npx @modelcontextprotocol/server-everything wrok.
• Improvements to URL Elicitation handling

• Bump protobuf from 6.33.2 to 6.33.5 by @dependabot[bot] in #675
• add --agent target and --noenv option. refactor CLI command handling. by @evalstate in #676
• acp: advertise authMethods + handle authenticate by @iqdoctor in #672
• ACP tool call tracking: stable IDs and nested grouping by @iqdoctor in #677
• Feat/hot mcp by @evalstate in #678
• chore(gitignore): replace examples/**/*.jsonl with *.jsonl by @iqdoctor in #680
• fix(mcp): reject non-finite or non-positive connect timeouts by @iqdoctor in #679
• Dev/0.4.52 by @evalstate in #681
• Dev/0.4.53 by @evalstate in #682

Full Changelog: v0.4.49...v0.4.53

v0.4.49

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

• default retries to 1 by @evalstate in #663
• Feat/compact strategies by @evalstate in #662
• Dev/0.4.48 by @evalstate in #665
• default skills dir, extraneous warning remove by @evalstate in #666
• fix: Bedrock Agents-As-Tools validation errors by @yarisoy in #668
• Dev/0.4.49 by @evalstate in #673
• examples: silence npm output for fetch server by @iqdoctor in #670
• fix: use app default agent for --message/--prompt-file by @iqdoctor in #669
• Add support for Anthropic Beta Streaming API with OpenTelemetry by @floriafz23 in #650
• fix(acp): prevent duplicated/stuck tool cards (stable tool_use_id + dedupe) by @iqdoctor in #674

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