feat: as_anthropic_tools — Anthropic tool-runner export, both modes

Fills the last cell of the agent-connection matrix: users driving their
own anthropic tool_runner loop get runnable tools directly. Cloud wraps
the live MCP tool set with input schemas passing through verbatim (MCP
inputSchema is the Messages API schema shape); local exposes the same
set messages() runs internally. The beta_tool wrapping moves from
local_chat into integrations/anthropic_sdk.py, parallel to
openai_agents.py, and messages() now consumes the shared builder.
agent_tools grows _bridge_invoker/_read_only_tools so the plain-function
and beta_tool cloud paths share invocation containment and the
read-only gate.

pageindex/agent_tools.py

@@ -1220,18 +1220,11 @@ def _annotation_for(spec: dict) -> Any:
     return _SCHEMA_TYPE_MAP.get(schema_type, Any)
 
 
-def _make_bridge_function(bridge, meta: dict) -> Callable[..., str]:
-    """One plain function for a cloud tool: real signature and docstring from
-    the server's schema, invocation proxied over MCP, errors contained."""
-    import keyword
-
-    name = str(meta.get("name") or "")
-    schema = meta.get("inputSchema") or {}
-    properties: dict[str, Any] = schema.get("properties") or {}
-    required = set(schema.get("required") or [])
-
+def _bridge_invoker(bridge, name: str) -> Callable[[dict], str]:
+    """One cloud tool call proxied over MCP: None-valued arguments are
+    dropped (None ≡ omitted, matching the contract's "omit if ..."
+    semantics) and failures are contained in the error envelope."""
     def _invoke(arguments: dict[str, Any]) -> str:
-        # None ≡ omitted, matching the contract's "omit if ..." semantics.
         arguments = {key: value for key, value in arguments.items()
                      if value is not None}
         try:
@@ -1246,6 +1239,19 @@ def _make_bridge_function(bridge, meta: dict) -> Callable[..., str]:
                 "INTERNAL_ERROR",
             )
             return _dumps(payload)
+    return _invoke
+
+
+def _make_bridge_function(bridge, meta: dict) -> Callable[..., str]:
+    """One plain function for a cloud tool: real signature and docstring from
+    the server's schema, invocation proxied over MCP, errors contained."""
+    import keyword
+
+    name = str(meta.get("name") or "")
+    schema = meta.get("inputSchema") or {}
+    properties: dict[str, Any] = schema.get("properties") or {}
+    required = set(schema.get("required") or [])
+    _invoke = _bridge_invoker(bridge, name)
 
     params_usable = all(param.isidentifier() and not keyword.iskeyword(param)
                         and param != "_invoke"
@@ -1300,22 +1306,27 @@ def _cloud_bridge(client):
         return bridge
 
 
+def _read_only_tools(tools_meta: list[dict]) -> list[dict]:
+    """The management gate for consumers without a framework permission
+    layer: only tools the server marks read-only, guarded against a server
+    annotation regression silently disabling every tool."""
+    filtered = [meta for meta in tools_meta
+                if (meta.get("annotations") or {}).get("readOnlyHint") is True]
+    if tools_meta and not filtered:
+        raise PageIndexAPIError(
+            "The MCP server returned tools but none are annotated "
+            "read-only — a server annotation regression would otherwise "
+            "silently disable every tool. Pass include_management=True "
+            "to expose the unfiltered list."
+        )
+    return filtered
+
+
 def _build_cloud_agent_tools(client, include_management: bool) -> list[Callable[..., str]]:
     bridge = _cloud_bridge(client)
     tools_meta = bridge.list_tools()
     if not include_management:
-        # Plain functions have no framework permission layer, so the
-        # management gate lives here: only tools the server marks read-only.
-        filtered = [meta for meta in tools_meta
-                    if (meta.get("annotations") or {}).get("readOnlyHint") is True]
-        if tools_meta and not filtered:
-            raise PageIndexAPIError(
-                "The MCP server returned tools but none are annotated "
-                "read-only — a server annotation regression would otherwise "
-                "silently disable every tool. Pass include_management=True "
-                "to expose the unfiltered list."
-            )
-        tools_meta = filtered
+        tools_meta = _read_only_tools(tools_meta)
     return [_make_bridge_function(bridge, meta) for meta in tools_meta]
 
 

pageindex/client.py

@@ -618,6 +618,33 @@ class PageIndexClient:
         from .integrations.openai_agents import build_openai_tools
         return build_openai_tools(self, include_management, hosted)
 
+    def as_anthropic_tools(self, include_management: bool = False) -> list:
+        """
+        Runnable tools for the Anthropic SDK's tool runner — pass to
+        ``client.beta.messages.tool_runner(tools=...)``.
+
+        Cloud: the full live read tool set (search, folders, images — as
+        enabled for your key), discovered from the PageIndex MCP server
+        and executed from your process; the server's input schemas pass
+        through verbatim (MCP and the Messages API share the schema
+        shape). The Messages API's MCP connector (``mcp_servers=``
+        pointing at ``{BASE_URL}/mcp``) is the server-side alternative
+        with no client-side tools involved. Local: the in-process tools —
+        the same set ``messages()`` runs internally.
+
+        Requires ``anthropic>=0.68.0``
+        (``pip install 'pageindex[anthropic]'``), imported only when this
+        method is called.
+
+        Args:
+            include_management (bool): Also expose tools that modify the
+                library. Local: adds ``remove_document``. Cloud: by default
+                only tools the server marks read-only are exposed; True
+                exposes the server's complete list (upload, delete, ...).
+        """
+        from .integrations.anthropic_sdk import build_anthropic_tools
+        return build_anthropic_tools(self, include_management)
+
     def as_claude_mcp(self, include_management: bool = False):
         """
         ``mcp_servers`` entry for the Claude Agent SDK.

pageindex/integrations/anthropic_sdk.py

@@ -0,0 +1,60 @@
+"""Anthropic SDK adapter for the tool runner's tools=... slot.
+
+Cloud clients get one runnable tool per live cloud MCP tool — the server's
+input schemas pass through verbatim (MCP inputSchema and Messages API
+input_schema are the same shape), calls proxied over MCP. Local clients get
+the in-process tools — the same set messages() runs internally.
+"""
+from __future__ import annotations
+
+from typing import Any
+
+from ..errors import PageIndexAPIError
+
+
+def build_anthropic_tools(client, include_management: bool = False) -> list:
+    try:
+        from anthropic import beta_tool
+    except ImportError as exc:
+        raise PageIndexAPIError(
+            "as_anthropic_tools requires the Anthropic SDK tool runner "
+            "(anthropic>=0.68.0) — pip install -U anthropic (or pip install "
+            "'pageindex[anthropic]')."
+        ) from exc
+
+    if getattr(client, "api_key", None):
+        from ..agent_tools import (_bridge_invoker, _cloud_bridge,
+                                   _read_only_tools)
+        bridge = _cloud_bridge(client)
+        tools_meta = bridge.list_tools()
+        if not include_management:
+            tools_meta = _read_only_tools(tools_meta)
+
+        def make_cloud(meta: dict):
+            name = str(meta.get("name") or "tool")
+            invoke = _bridge_invoker(bridge, name)
+
+            def _fn(**kwargs: Any) -> str:
+                return invoke(kwargs)
+
+            _fn.__name__ = name
+            return beta_tool(
+                _fn, name=name, description=meta.get("description", ""),
+                input_schema=meta.get("inputSchema")
+                or {"type": "object", "properties": {}},
+            )
+
+        return [make_cloud(meta) for meta in tools_meta]
+
+    from ..agent_tools import (_local_description, _local_schema, call_tool,
+                               tool_names)
+
+    def make_local(name: str):
+        def _fn(**kwargs: Any) -> str:
+            return call_tool(client, name, kwargs)[0]
+
+        _fn.__name__ = name
+        return beta_tool(_fn, name=name, description=_local_description(name),
+                         input_schema=_local_schema(name))
+
+    return [make_local(name) for name in tool_names(include_management)]

pageindex/local_chat.py

@@ -26,9 +26,7 @@ import time
 import uuid
 from typing import Any, Iterator, Optional, Union
 
-from .agent_tools import (AGENT_INSTRUCTIONS, _local_description,
-                          _local_schema, call_tool, doc_targeting_block,
-                          tool_names)
+from .agent_tools import AGENT_INSTRUCTIONS, doc_targeting_block
 from .errors import PageIndexAPIError
 
 CHAT_HEADER = (
@@ -506,20 +504,6 @@ def _anthropic_client():
     return anthropic.Anthropic()
 
 
-def _runnable_tools(client) -> list:
-    from anthropic import beta_tool
-
-    def make(name: str):
-        def _fn(**kwargs: Any) -> str:
-            return call_tool(client, name, kwargs)[0]
-
-        _fn.__name__ = name
-        return beta_tool(_fn, name=name, description=_local_description(name),
-                         input_schema=_local_schema(name))
-
-    return [make(name) for name in tool_names()]
-
-
 def _anthropic_system(extra_system, block: Optional[str]) -> list[dict]:
     """System blocks: cache_control marks the stable managed prefix only
     (the API allows 4 breakpoints total — the varying doc block and caller
@@ -580,6 +564,8 @@ def run_messages(client, messages, model: str, max_tokens: int,
                  stop_sequences: Optional[list[str]] = None,
                  max_turns: Optional[int] = None,
                  ) -> Union[dict, Iterator[Any]]:
+    from .integrations.anthropic_sdk import build_anthropic_tools
+
     _require_anthropic()
     _validate_max_turns(max_turns)
     if (not isinstance(messages, list) or not messages
@@ -596,7 +582,7 @@ def run_messages(client, messages, model: str, max_tokens: int,
         max_tokens=max_tokens,
         messages=prepared,
         model=model,
-        tools=_runnable_tools(client),
+        tools=build_anthropic_tools(client),
         system=_anthropic_system(system, block),
         stream=stream,
         # Bounded like the OpenAI surfaces (their framework default is 10).

pyproject.toml

@@ -42,8 +42,9 @@ claude-agent-sdk = { version = ">=0.1.0", optional = true }
 # 0.8.0 offloads sync tools to a thread; older versions run them inline and
 # a blocking bridge call would freeze the agent event loop.
 openai-agents = { version = ">=0.8.0", optional = true }
-# messages() drives the SDK's beta tool runner; 0.68.0 is the first release
-# with tool_runner(stream/system/max_iterations) and beta_tool(input_schema).
+# messages() and as_anthropic_tools() need the SDK's beta tool runner;
+# 0.68.0 is the first release with tool_runner(stream/system/max_iterations)
+# and beta_tool(input_schema).
 anthropic = { version = ">=0.68.0", optional = true }
 
 [tool.poetry.extras]

tests/test_agent_tools.py

@@ -484,9 +484,73 @@ def test_as_claude_mcp_local_when_installed(client):
         assert server.get("type") != "http"
 
 
+def test_as_anthropic_tools_missing_dependency(client, monkeypatch):
+    monkeypatch.setitem(sys.modules, "anthropic", None)
+    with pytest.raises(PageIndexAPIError, match="anthropic"):
+        client.as_anthropic_tools()
+
+
+def test_as_anthropic_tools_local_in_process(client, store_path):
+    pytest.importorskip("anthropic")
+    from pageindex.agent_tools import _local_description, _local_schema
+    tools = client.as_anthropic_tools()
+    assert [tool.name for tool in tools] == list(tool_names())
+    browse = {tool.name: tool for tool in tools}["browse_documents"]
+    assert browse.input_schema == _local_schema("browse_documents")
+    assert browse.description == _local_description("browse_documents")
+    seed_doc(store_path, "pi-a", "report.pdf")
+    assert "report.pdf" in browse.call({})
+
+
+def test_as_anthropic_tools_local_management_opt_in(client):
+    pytest.importorskip("anthropic")
+    names = [tool.name
+             for tool in client.as_anthropic_tools(include_management=True)]
+    assert names == list(tool_names(include_management=True))
+    assert "remove_document" in names
+
+
+def test_as_anthropic_tools_cloud_schemas_pass_through(cloud_with_fake_bridge):
+    pytest.importorskip("anthropic")
+    cloud, created = cloud_with_fake_bridge
+    tools = cloud.as_anthropic_tools()
+    assert [tool.name for tool in tools] == ["search_documents", "get_document"]
+    bridge = created["bridge"]
+    assert tools[0].input_schema == bridge.tools[0]["inputSchema"]
+    assert tools[0].description == bridge.tools[0]["description"]
+    # Calls route over the bridge; None-valued arguments mean "omitted".
+    out = tools[1].call({"doc_name": "x.pdf", "folder_id": None})
+    assert bridge.calls == [("get_document", {"doc_name": "x.pdf"})]
+    assert json.loads(out)["success"] is True
+
+
+def test_as_anthropic_tools_cloud_management_opt_in(cloud_with_fake_bridge):
+    pytest.importorskip("anthropic")
+    cloud, _ = cloud_with_fake_bridge
+    names = [tool.name
+             for tool in cloud.as_anthropic_tools(include_management=True)]
+    assert names == ["search_documents", "get_document",
+                     "remove_document", "unannotated_tool"]
+
+
+def test_as_anthropic_tools_cloud_contains_bridge_errors(cloud_with_fake_bridge):
+    pytest.importorskip("anthropic")
+    cloud, created = cloud_with_fake_bridge
+    tools = cloud.as_anthropic_tools()
+
+    def boom(name, arguments):
+        raise RuntimeError("bridge down")
+
+    created["bridge"].call_tool = boom
+    payload = json.loads(tools[0].call({"query": "q"}))
+    assert payload["errorCode"] == "INTERNAL_ERROR"
+    assert "bridge down" in payload["error"]
+
+
 def test_agent_tools_work_without_frameworks(client, store_path, monkeypatch):
     monkeypatch.setitem(sys.modules, "agents", None)
     monkeypatch.setitem(sys.modules, "claude_agent_sdk", None)
+    monkeypatch.setitem(sys.modules, "anthropic", None)
     seed_doc(store_path, "pi-a", "report.pdf")
     browse = client.agent_tools()[0]
     assert "report.pdf" in browse()