0.6.10 / Vertex / ACP Fix

README.md

@@ -7,10 +7,65 @@
 <a href="https://github.com/evalstate/fast-agent-mcp/blob/main/LICENSE"><img src="https://img.shields.io/pypi/l/fast-agent-mcp" /></a>
 </p>
 
-## Overview
+## Start Here
 
 > [!TIP]
-> Please see : https://fast-agent.ai for latest documentation. There is also an LLMs.txt [here](https://fast-agent.ai/llms.txt)
+> Please see https://fast-agent.ai for latest documentation.
+
+**`fast-agent`** is a flexible way to interact with LLMs, excellent for use as a Coding Agent, Development Toolkit, Evaluation or Workflow platform.
+
+To start an interactive session with shell support, install [uv](https://astral.sh/uv) and run
+
+```bash
+uvx fast-agent-mcp@latest -x
+```
+
+To start coding with Hugging Face inference providers or use your OpenAI Codex plan:
+
+```bash
+# Code with Hugging Face Inference Providers
+uvx fast-agent-mcp@latest --pack hf-dev
+
+# Code with Codex (agents optimized for OpenAI)
+uvx fast-agent-mcp@latest --pack codex
+```
+
+Enter a shell with `!`, or run shell commands e.g. `! cd web && npm run build`.
+
+Manage skills with the `/skills` command, and connect to MCP Servers with `/connect`. The default **`fast-agent`** registry contains skills to let you set up LSP, Agent and Tool Hooks, Compaction strategies, Automation and more.
+
+```bash
+# /connect supports stdio or streamable http (with OAuth)
+
+# Start a STDIO server
+/connect @modelcontextprotocol/server-everything
+
+# Connect to a Streamable HTTP Server
+/connect https://huggingface.co/mcp
+```
+
+It's recommended to install **`fast-agent`** to set up the shell aliases and other tooling.
+
+```bash
+# Install fast-agent
+uv tool install -U fast-agent-mcp
+
+# Run fast-agent with opus, shell support and subagent/smart mode
+fast-agent --model opus -x --smart
+```
+
+Use local models with the generic provider, or automatically create the correct configuration for `llama.cpp`:
+
+```bash
+fast-agent model llamacpp
+```
+
+Any **`fast-agent`** setup or program can be used with any ACP client - the simplest way is to use `fast-agent-acp`:
+
+```bash
+# Run fast-agent inside Toad
+toad acp "fast-agent-acp -x --model sonnet"
+```
 
 **`fast-agent`** enables you to create and interact with sophisticated multimodal Agents and Workflows in minutes. It is the first framework with complete, end-to-end tested MCP Feature support including Sampling and Elicitations.
 
@@ -23,32 +78,32 @@ The simple declarative syntax lets you concentrate on composing your Prompts and
 Model support is comprehensive with native support for Anthropic, OpenAI and Google providers as well as Azure, Ollama, Deepseek and dozens of others via TensorZero. Structured Outputs, PDF and Vision support is simple to use and well tested. Passthrough and Playback LLMs enable rapid development and test of Python glue-code for your applications.
 
 Recent features include:
- - Agent Skills (SKILL.md)
- - MCP-UI Support |
- - OpenAI Apps SDK (Skybridge)
- - Shell Mode
- - Advanced MCP Transport Diagnsotics
- - MCP Elicitations
 
-<img width="800"  alt="MCP Transport Diagnostics" src="https://github.com/user-attachments/assets/e26472de-58d9-4726-8bdd-01eb407414cf" />
+- Agent Skills (SKILL.md)
+- MCP-UI Support |
+- OpenAI Apps SDK (Skybridge)
+- Shell Mode
+- Advanced MCP Transport Diagnsotics
+- MCP Elicitations
 
+<img width="800"  alt="MCP Transport Diagnostics" src="https://github.com/user-attachments/assets/e26472de-58d9-4726-8bdd-01eb407414cf" />
 
 `fast-agent` is the only tool that allows you to inspect Streamable HTTP Transport usage - a critical feature for ensuring reliable, compliant deployments. OAuth is supported with KeyRing storage for secrets. Use the `fast-agent auth` command to manage.
 
-
-
-
-
 > [!IMPORTANT]
 >
 > Documentation is included as a submodule. When cloning, use `--recurse-submodules` to get everything:
+>
 > ```bash
 > git clone --recurse-submodules https://github.com/evalstate/fast-agent.git
 > ```
+>
 > Or if you've already cloned:
+>
 > ```bash
 > git submodule update --init --recursive
 > ```
+>
 > The documentation source is also available at: https://github.com/evalstate/fast-agent-docs
 
 ### Agent Application Development

examples/hf-toad-cards/hooks/save_history.py

@@ -2,7 +2,7 @@
 
 from collections.abc import Iterable
 from datetime import datetime
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, cast
 
 from fast_agent.hooks import HookContext
 from fast_agent.mcp.prompt_serialization import save_messages
@@ -30,7 +30,7 @@ async def save_history_to_file(ctx: HookContext) -> None:
         # Fall back to runner's turn messages + final response
         runner_messages = getattr(ctx.runner, "delta_messages", None)
         if isinstance(runner_messages, Iterable):
-            messages = list(runner_messages)
+            messages = [cast("PromptMessageExtended", message) for message in runner_messages]
         else:
             messages = []
         if ctx.message and ctx.message not in messages:

examples/hf-toad-cards/skills/pr-writing-review/scripts/extract_pr_reviews.py

@@ -25,7 +25,7 @@
 import subprocess
 import sys
 from dataclasses import asdict, dataclass, field
-from typing import Optional
+from typing import Optional, cast
 from urllib.parse import quote, urlparse
 
 JsonValue = str | int | float | bool | None | list["JsonValue"] | dict[str, "JsonValue"]
@@ -120,12 +120,25 @@ def run_gh_jsonlines(args: list[str], check: bool = True) -> list[dict]:
     return out
 
 
+def _ensure_json_value(value: object, label: str) -> JsonValue:
+    if value is None or isinstance(value, str | int | float | bool):
+        return value
+    if isinstance(value, list):
+        return [_ensure_json_value(item, f"{label}[]") for item in value]
+    if isinstance(value, dict):
+        return _ensure_json_dict(value, label)
+    raise ValueError(f"Expected JSON-compatible value for {label}")
+
+
 def _ensure_json_dict(value: object, label: str) -> JsonDict:
     if not isinstance(value, dict):
         raise ValueError(f"Expected object for {label}")
     if not all(isinstance(key, str) for key in value.keys()):
         raise ValueError(f"Expected string keys for {label}")
-    return {str(key): val for key, val in value.items()}
+    return cast(
+        "JsonDict",
+        {str(key): _ensure_json_value(val, f"{label}.{key}") for key, val in value.items()},
+    )
 
 
 def _get_required_str(data: JsonDict, key: str) -> str:

publish/fast-agent-acp/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "fast-agent-acp"
-version = "0.4.7"
+version = "0.6.9"
 description = "Convenience launcher that pulls in fast-agent-mcp and exposes the ACP CLI entrypoint."
 readme = "README.md"
 license = { text = "Apache-2.0" }
@@ -18,7 +18,7 @@ classifiers = [
 ]
 requires-python = ">=3.13.5,<3.15"
 dependencies = [
-    "fast-agent-mcp==0.4.7",
+    "fast-agent-mcp==0.6.9",
 ]
 
 [project.urls]

publish/hf-inference-acp/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "hf-inference-acp"
-version = "0.4.31"
+version = "0.6.9"
 description = "Hugging Face inference agent with ACP support, powered by fast-agent-mcp"
 readme = "README.md"
 license = { text = "Apache-2.0" }
@@ -18,7 +18,7 @@ classifiers = [
 ]
 requires-python = ">=3.13.5,<3.15"
 dependencies = [
-    "fast-agent-mcp==0.5.7",
+    "fast-agent-mcp==0.6.9",
     "huggingface_hub>=1.3.4",
 ]
 

publish/hf-inference-acp/src/hf_inference_acp/cli.py

@@ -28,6 +28,7 @@
 from fast_agent.cli.commands.server_helpers import add_servers_to_config, generate_server_name
 from fast_agent.cli.commands.url_parser import generate_server_configs, parse_server_urls
 from fast_agent.core.agent_card_validation import collect_agent_card_names, find_loaded_agent_issues
+from fast_agent.llm.model_database import ModelDatabase
 from fast_agent.llm.model_factory import ModelFactory
 from fast_agent.llm.provider_key_manager import ProviderKeyManager
 from fast_agent.llm.provider_types import Provider
@@ -43,8 +44,26 @@
 )
 from hf_inference_acp.wizard import WizardSetupLLM
 
-# Register wizard-setup model locally
-ModelFactory.register_runtime_model("wizard-setup", provider=Provider.FAST_AGENT, llm_class=WizardSetupLLM)
+
+def _register_wizard_setup_model() -> None:
+    """Register the local wizard model across fast-agent versions."""
+    register_runtime_model = getattr(ModelFactory, "register_runtime_model", None)
+    if callable(register_runtime_model):
+        register_runtime_model(
+            "wizard-setup",
+            provider=Provider.FAST_AGENT,
+            llm_class=WizardSetupLLM,
+        )
+        return
+
+    ModelFactory.MODEL_SPECIFIC_CLASSES["wizard-setup"] = WizardSetupLLM
+    ModelDatabase.register_runtime_model_params(
+        "wizard-setup",
+        ModelDatabase.FAST_AGENT_STANDARD.model_copy(),
+    )
+
+
+_register_wizard_setup_model()
 
 app = typer.Typer(
     help="Run the Hugging Face Inference ACP agent over stdio.",

pyproject.toml

@@ -22,8 +22,8 @@ dependencies = [
     "pyyaml>=6.0.2",
     "rich>=14.3.3",
     "typer>=0.24.1",
-    "anthropic>=0.84.0",
-    "openai[aiohttp]>=2.28.0",
+    "anthropic[vertex]>=0.86.0",
+    "openai[aiohttp]>=2.29.0",
     "prompt-toolkit>=3.0.52",
     "aiohttp>=3.13.2",
     "opentelemetry-distro==0.60b1",
@@ -40,11 +40,12 @@ dependencies = [
     "keyring>=24.3.1",
     "python-frontmatter>=1.1.0",
     "watchfiles>=1.1.0",
-    "agent-client-protocol>=0.8.1",
+    "agent-client-protocol==0.9.0",
     "tiktoken>=0.12.0",
     "uvloop>=0.22.1; platform_system != 'Windows'",
     "multilspy>=0.0.15",
     "ruamel.yaml>=0.18.16",
+    "mslex>=1.3.0",
 ]
 
 [project.optional-dependencies]

src/fast_agent/acp/__init__.py

@@ -1,11 +1,15 @@
 """Agent Client Protocol (ACP) support for fast-agent."""
 
+from typing import TYPE_CHECKING, Any
+
 from fast_agent.acp.acp_aware_mixin import ACPAwareMixin, ACPCommand, ACPModeInfo
 from fast_agent.acp.acp_context import ACPContext, ClientCapabilities, ClientInfo
 from fast_agent.acp.filesystem_runtime import ACPFilesystemRuntime
-from fast_agent.acp.server.agent_acp_server import AgentACPServer
 from fast_agent.acp.terminal_runtime import ACPTerminalRuntime
 
+if TYPE_CHECKING:  # pragma: no cover - type checking only
+    from fast_agent.acp.server.agent_acp_server import AgentACPServer as AgentACPServer
+
 __all__ = [
     "ACPCommand",
     "ACPModeInfo",
@@ -17,3 +21,12 @@
     "ACPFilesystemRuntime",
     "ACPTerminalRuntime",
 ]
+
+
+def __getattr__(name: str) -> Any:
+    if name == "AgentACPServer":
+        from fast_agent.acp.server.agent_acp_server import AgentACPServer
+
+        return AgentACPServer
+
+    raise AttributeError(f"module '{__name__}' has no attribute '{name}'")