v0.2.30

What's Changed

HF_TOKEN mode

HF_TOKEN environment variable is used when accessing HuggingFace hosted MCP Servers either at hf.co/mcp or .hf.spaces. Can be overriden with Auth headers or fastagent.config.yaml.

Use external prompt editor with Ctrl+E

Use CTRL+E to open an external editor for Prompt editing. See #218 for more details.

Aliyun support

Aliyun Bailian, which provides APIs for the Qwen series of models—widely used across mainland China. @yeahdongcn informs me that "Qwen3 is gaining a lot of popularity, and Aliyun is currently offering free tokens for developers"!

Other fixes

• fix(#208): Fix wrong prompt description displayed in the [Available MCP Prompts] table by @codeboyzhou in #209
• Support Deepseek json_format by @Zorro30 in #182
• fix(#226): Error in tool list changed callback by @codeboyzhou in #227

New Contributors

• @codeboyzhou made their first contribution in #209
• @Zorro30 made their first contribution in #182
• @yeahdongcn made their first contribution in #224

Full Changelog: v0.2.29...v0.2.30

v0.2.29

Changes

• Add HF_TOKEN mode @evalstate (#223)
• Support Deepseek json_format @Zorro30 (#182)
• fix(#208): Fix wrong prompt description displayed in the [Available MCP Prompts] table @codeboyzhou (#209)
• Made sure that empty content.parts will not anymore cause bugs when u… @janspoerer (#220)
• adding deprecated to fix missing dependency error @jjwall (#216)
• added slow llm to test parallel sampling @wreed4 (#197)
• ensure tool names are < 64 characters
• fix opentelemetry (the MCP instrumentation isn't compatible with 1.9)
• Update MCP package to 1.9.3

New Contributors

• @jjwall made their first contribution in #216
• @janspoerer made their first contribution in #220

Full Changelog: v0.2.28...v0.2.29

v0.2.28

Release 0.2.28

Gemini Native Support

This release switches to the native Google API as the default for google models. Thanks to @monotykamary and @janspoerer for this work 🍾. If you run in to issues the old provider is accessible as googleoai -> but you will need to update your API key to match.

Autosampling

Servers are now offered Sampling capability as default, provided by the Agents model (or system default if not specified). Switch auto_sampling: false in the config.py file to switch off this behaviour.

Other Changes

• added slow llm to test parallel sampling @wreed4 (#197)
• fix(177): Fix prompt listing across agents @wreed4 (#178)

New Contributors

• @monotykamary made their first contribution in #134

Full Changelog: v0.2.27...v0.2.28

v0.2.27

What's Changed

• Update to MCP1.9.1 -> fix #187
• Implementation Details on Init correct

Full Changelog: v0.2.25...v0.2.27

v0.2.25

What's Changed

• Fix: Remove parallel_tool_calls from OpenAI model provider for 'o' model compatibility by @kikiya in #164
• feat: Add Azure OpenAI Service Support to FastAgent by @pablotoledo in #160

New Contributors

• @kikiya made their first contribution in #164
• @pablotoledo made their first contribution in #160

Full Changelog: v0.2.24...v0.2.25

v0.2.24

What's Changed

• bug fix: system prompt repeats in multiple rounds of conversations by @skyduy in #159
• MCP OpenTelemetry
• Tool Discovery Support

New Contributors

• @skyduy made their first contribution in #159

Full Changelog: v0.2.23...v0.2.24

v0.2.23

HTTP Streaming Support

fast-agent now has HTTP Streaming support.

Configure MCP Servers with the http transport type.
Run agents as MCP Servers with the --transport=http option - e.g. uv run agent.py --server --transport=http
prompt-server supports the transport=http option.
fast-agent go allows specifying urls and auth token from the command line - e.g. fast-agent go url=http://localhost:8080/mcp auth=<token>

What's Changed

• Add Streaming HTTP Support for Client, Server and prompt-server. by @evalstate in #158
• Renaming max_steps_reached to max_iterations_reached on PlanResult by @theobjectivedad in #157
• Enable markup based on user config by @alpeshvas in #155

New Contributors

• @alpeshvas made their first contribution in #155

Full Changelog: v0.2.22...v0.2.23

v0.2.22

What's Changed

• Feat/add tensorzero inference by @aaronpolhamus in #125
• Minor improvements to TensorZero provider by @GabrielBianconi in #147
• Improvements in error messages for SSE Server Startup/masking issues
• Bump MCP SDK to 1.8.0
• Mitigation for #143

New Contributors

• @aaronpolhamus made their first contribution in #125
• @GabrielBianconi made their first contribution in #147

Full Changelog: v0.2.21...v0.2.22

v0.2.21

Changes

• allow mcp versions >=1.7.0, <1.8.0 @mpereira (#138)
• prompt-server sse port configuration @evalstate (#141)

New Contributors

• @mpereira made their first contribution in #138

Full Changelog: v0.2.20...v0.2.21

v0.2.20

What's Changed

• LiteLLM+LangFuse Support: Enhancing how request_params are overridden by @theobjectivedad in #129
• Add more checks for when args parsing is disabled by @kahkeng in #133
• Added MCP server cwd setting by @jpeirson in #131
• Fix/misc by @evalstate in #137...
• otel instance id set
• allow hyphens in tool/server names, namespace refactor (llm) #135
• windows sse server startup fix #121
• increase max_iterations for tool call/llm loop
• add cwd functionality test

New Contributors

• @theobjectivedad made their first contribution in #129
• @kahkeng made their first contribution in #133
• @jpeirson made their first contribution in #131
  Thanks to
• @lizzy-0323 for raising hyphen in server defect
• @wowok-ai for raising windows sse server issue

Full Changelog: v0.2.19...v0.2.20