* Add AnthropicSamplingHandler
Adds a sampling handler for the Anthropic API at
fastmcp.client.sampling.handlers.anthropic, alongside the existing
OpenAI handler. Includes full support for tool calling.
Install with: pip install fastmcp[anthropic]
* Update default model
* Update sampling docs to cover both OpenAI and Anthropic handlers
* Use AsyncAnthropic, fix falsy value handling, handle tool_choice none
* Propagate isError to Anthropic, join multiple text blocks, fix docs
* Unify SamplingHandler and promote OpenAI handler
Consolidates ServerSamplingHandler and ClientSamplingHandler into a single
SamplingHandler type alias. Moves OpenAISamplingHandler from experimental
to fastmcp.client.sampling.handlers.openai as the canonical location.
Backwards compatibility maintained for imports from experimental.
* Remove unreachable code paths in OpenAI handler
* Fix docstring and use elif for mutually exclusive branches
* MCP → SDK (vocab change only)
* WIP: Sampling API with SamplingResult[T] and result_type
* SEP-1577: Sampling with tools
- Add tools and result_type parameters to ctx.sample()
- Update OpenAI handler for tool content types
- Client advertises sampling.tools capability by default
- Collect tool results into single message with list content
* Fix tool result content handling in OpenAI handler
* Remove @sampling_tool decorator - pass functions directly to sample()
Functions passed to ctx.sample(tools=[...]) are now auto-converted
via SamplingTool.from_function(). Users can still use that method
directly for custom name/description overrides.
* Remove auto-conversion of MCP tools to sampling tools
Users want MCP tools passed to ctx.sample() to go through the full MCP
machinery (middleware, native responses) rather than being auto-converted
to direct function calls. Now only SamplingTool and plain callables are
accepted - passing a FastMCP Tool raises a clear TypeError.
Also bumps mcp dependency to >=1.24.0 for required sampling features.
* Refactor sampling API: replace sample_iter() with sample_step()
Replace the mutable SampleRun/sample_iter() pattern with a simpler stateless
sample_step() function. sample_step() makes a single LLM call and returns a
SampleStep with the response and history. sample() now loops sample_step()
internally.
Key changes:
- Add sample_step() for fine-grained control over the sampling loop
- Remove SampleRun class and sample_iter() method
- Structured output uses tool description only (no prompt modification)
- execute_tools parameter controls automatic vs manual tool execution
* Address CodeRabbit nitpicks
* Address CodeRabbit review feedback for sampling tools
- Fix temperature=0.0 being dropped due to falsy evaluation
- Add ToolChoice.name support for forcing specific tools
- Replace assert statements with explicit RuntimeError checks
- Add mask_error_details parameter to sample()/sample_step() with ToolError escape hatch
- Fix hasattr patterns with proper isinstance checks
- Document mask_error_details and add OpenAI prerequisites to docs
* Address additional CodeRabbit review feedback
- Catch ValidationError specifically instead of bare Exception
- Update result_type docs to mention dataclasses and basic types
- Raise ValueError for unknown tool_choice modes
- Validate sampling_handler_behavior to catch typos
- Remove ToolChoice.name handling (not part of MCP spec)
- Validate tool_choice string in sample_step()
* Review fixes for sampling tools PR
- Remove internal functions from sampling __init__.py exports
- Remove fragile is_text property, use not is_tool_use instead
- Inline call_client into context.py, remove from run.py
- Fix SamplingMessage docs to use TextContent
- Handle result.text being None in doc examples
- Simplify client sampling docs to recommend OpenAISamplingHandler
- Add sampling_capabilities override documentation
- Raise iteration limit from 50 to 100
- Remove _parse_model_preferences duplication
- Use AsyncOpenAI in OpenAISamplingHandler
- Fix tool_choice docstring
* Fix OpenAI handler tests to use AsyncOpenAI
* Address remaining CodeRabbit review comments
- Fix message ordering in OpenAI handler: tool results now correctly
follow assistant message with tool_calls
- sample_step() now always includes assistant message in history
- Raise ValueError on JSON parse errors instead of silent {}
- Add has_sampling capability check when behavior is None
- Raise RuntimeError when structured output receives text response
- Wrap primitive result_type schemas in object wrapper
- Fix docs example using invalid SamplingMessage construction
- Add comprehensive client_sampling_test.py example
* Add return type annotation to OpenAISamplingHandler.__init__
* Use explicit 'is not None' check for sampling_capabilities defaulting
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Bill Easton <strawgate@users.noreply.github.com>
* fix: skip TextIO log file test on Windows
Avoids PytestUnraisableExceptionWarning caused by ProactorEventLoop
cleanup timing issues with subprocess pipe transports.
* Use WindowsSelectorEventLoopPolicy to fix Windows test warnings
Re-add the SelectorEventLoop fix from bcd2e594 that was inadvertently
removed in cf101c2a. This fixes ProactorEventLoop cleanup warnings
on Windows CI without needing to skip individual tests.
* feat: add PromptResult as canonical internal type for prompts
Applies the same pattern as ResourceContent to prompts. PromptResult
wraps messages with description and meta. Public render() can return
either list[PromptMessage] or PromptResult (backwards compatible),
while private _render() always returns PromptResult.
* docs: fix incorrect PromptResult return type in example
* feat: add PromptResult canonical type with meta support
* fix: address PR #2600 review comments
Fixes test failures and code quality issues identified in PR review:
- Update 3 tests in test_server_interactions.py to access PromptResult.messages[0] instead of indexing directly
- Fix ProxyPromptManager to preserve meta field when converting GetPromptResult to PromptResult
- Fix ProxyPrompt.render() to return PromptResult instead of deprecated list[PromptMessage], preventing fastmcp tags from leaking into runtime meta
- Fix mask_error_details initialization to respect explicit False values
- Fix exception re-raising to preserve tracebacks (use bare raise instead of raise e)
- Update testing documentation to use pytest -n auto for parallel execution
* feat: make ResourceContent the canonical internal type for resources
Add Resource._read() private method that always returns ResourceContent,
maintaining backwards compatibility for custom resources returning str/bytes
from read(). Includes deprecation warning when str/bytes is returned.
* fix: address review feedback for ResourceContent
- Remove ResourceContent from root exports (import from fastmcp.resources)
- Fix FunctionResource.read() return type to str | bytes | ResourceContent
- Decode base64 blobs in proxy when receiving from remote servers
- Preserve meta in ProxyResource cached content
* fix: add empty result guards in proxy resource reads
When a prompt function returned `mcp.types.PromptMessage` objects directly
and was executed as a task, the result serialization failed with
"'PromptMessage' object has no attribute 'to_mcp'".
The task result converter was calling `.to_mcp()` on what it thought was a
FastMCP wrapper type, but the import actually pulls in `mcp.types.PromptMessage`
directly, which is already the final MCP type. Removed the unnecessary
conversion.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: handle error from the initialize middleware
In some situation, the initialize middleware can check the status of the
server and decide to raise an error.
Example use case: in a FastMCPProxy, an initialization middleware
overrides the on_initialize method and connect to the underlying proxied
client. When client respond with error, I want to pass this error to the
client.
* docs update
* test: use McpError assertions now that exception propagation is fixed
- Update tests to catch McpError specifically instead of generic Exception
- Remove commented-out code in low_level.py
---------
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
When upstream OAuth providers don't return expires_in (like GitHub OAuth
Apps), use smart defaults: 1 hour if refresh token available, 1 year if
not. Adds fallback_access_token_expiry_seconds parameter to override.
Tools, resources, and prompts from servers mounted more than 2 levels
deep failed to invoke even though they were correctly listed.
The bug was in the routing methods which used manager methods that only
search locally, not through nested mounted servers. Changed to use
server-level methods that search recursively.
Fixes#2583
Proxied tool results now properly forward the meta attribute from upstream servers through ProxyToolManager and ProxyTool.
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
* [feat] expose get_session_id callback
* [test] add test for session id callback
* [fix] add test for uninitialized case and default to None
* [fix] add in changes based on reviewers
* SEP-1330 enum schema support for elicitation
* Add version badges for 2.14.0 elicitation features
* Fix Context.elicit() to handle SEP-1330 enum syntaxes
* Guard against empty list in elicit response_type
* Add guards for empty dict/list edge cases in elicit
* Refactor elicit: extract parsing and response handling to elicitation.py
Addresses code review feedback:
- Extract `get_task_capabilities()` to avoid duplicating the SEP-1686
capability structure across transports
- Add `_should_enable_component()` check before task routing for tools,
resources, and prompts to respect enable/tag filtering
- Simplify tasks/__init__.py to avoid circular import issues
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add EventStore and SSE polling support (SEP-1699)
* Add close_sse_stream() method to Context
* Add SSE polling documentation
* Fix missing Context import in docs example
* Remove EventStore from root __init__.py, update docs imports
- Removed EventStore import and export from src/fastmcp/__init__.py
- Updated docs to import EventStore from fastmcp.server.event_store
- Resolves merge conflict by not exporting EventStore from root package
The task protocol (SEP-1686) is now always enabled - server always
registers task handlers and advertises task capabilities. Users still
opt into background execution at the server level (tasks=True) or
component level (task=True on tools, prompts, resources).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The base Tool class now has an optional `execution` field for storing
task execution metadata (SEP-1686). This lets gateways/proxies preserve
execution info when forwarding tools from backends - previously this
metadata was lost because Tool had no way to store it.
FunctionTool continues to derive execution from task_config as before.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
When multiple servers with task-enabled tools are mounted into a parent,
their functions were all registered with Docket using `fn.__name__`. This
meant two mounted servers each having a function named `add` would both
register under `"add"`, with the second overwriting the first.
Now mounted functions use prefixed names matching their client-facing tool
names (e.g., `c1_add`, `c2_add`). Root server functions still use their
original names with no prefix.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Simplifies the task support story for proxies and mounts:
- Mounts get full SEP-1686 task support (unchanged)
- Proxies explicitly forbid task execution
The cross-session task forwarding for proxies turned out to be complex
since each client connection creates a new server lifespan with a new
Docket context, and task keys include session_id. Rather than introduce
that complexity, proxies now explicitly refuse task-augmented execution.
Key changes:
- All proxy components (ProxyTool, ProxyPrompt, ProxyResource,
ProxyTemplate) now have task_config.mode="forbidden"
- Proxy tests verify forbidden behavior (sync execution works,
task=True returns error/raises McpError)
- Fixed prompt task handler to check hasattr(prompt, "task_config")
instead of isinstance(prompt, FunctionPrompt) so it applies to
ProxyPrompt too
- Added test suites for both proxy and mount task behavior
Also includes minor fixes:
- Fixed result.meta_ -> result.meta in ProxyTool.run()
- Fixed client handling of returned_immediately without taskId
- Bumped pydocket>=0.15.2
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Follow-up to PR #2563 which fixed the signature handling in
create_function_without_params. These tests ensure the fix
works end-to-end for all object types that support Context injection.
* Fix: Include signature modification in create_function_without_params
When excluding parameters via create_function_without_params(), only
__annotations__ was being updated but not __signature__. This caused
Pydantic's _arguments_schema() to fail when it iterated over signature
parameters that didn't exist in the type hints dictionary.
The fix adds proper signature reconstruction matching the pattern used
in without_injected_parameters().
Fixes KeyError: 'ctx' when using @mcp.tool() with Context parameters.
* fix: add regression tests for create_function_without_params
The test_pydantic_typeadapter_compatibility test specifically reproduces the issue from #2562 and verifies the fix.
* fix: linter for test function
---------
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
* Fix type errors for ty 0.0.1-alpha.31 upgrade
Add type ignores and fixes for ty's stricter checking:
- Path(None) guards in cli.py
- isinstance checks for ElicitRequestFormParams (URL elicitation support)
- TODO(ty) comments for match/isinstance narrowing bugs
- Method override type ignores for generic covariance
- Starlette Middleware typing workarounds
- Dynamic type construction ignores in json_schema_type.py
* Fix remaining type errors for ty 0.0.1-alpha.31
- Add asserts for optional attribute access in tests
- Add type ignores for dynamic httpx transport internals
- Add TODO(ty) comments for `in` operator on str|bytes
- Add TODO(ty) comments for Starlette Middleware typing
- Use cast for prompt.fn async validation in server.py
* Upgrade ty to 0.0.1-alpha.31
Fixes additional test file type errors discovered after upgrade.
Docket stores a shared FakeServer as a class attribute (_memory_server).
When many tests run in parallel, shared state can cause issues on Windows.
Add autouse fixture to reset the shared server before each test.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fakeredis doesn't implement blocking xread properly - it returns
immediately instead of waiting. This causes Docket._monitor_strikes
to busy-loop, overwhelming pytest-xdist workers on Windows.
Mock the method to just sleep, since strike coordination isn't useful
with in-memory backends anyway.
See: https://github.com/cunla/fakeredis-py/issues/274🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Windows ProactorEventLoop has known memory corruption issues that cause
pytest-xdist worker crashes with "node down: Not properly terminated".
Setting WindowsSelectorEventLoopPolicy in conftest.py avoids this issue.
See: https://github.com/python/cpython/issues/116773🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Docket provides background task execution and is now always available
for all FastMCP servers. Only `enable_tasks` remains to control the
SEP-1686 task protocol support.
Changes:
- Remove `enable_docket` setting and related validation
- Docket/Worker lifecycle is always active in server lifespan
- CurrentDocket and CurrentWorker dependencies work without config
- Add server readiness signaling via `_started` event
- Fix test timing issues with proper port probing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Raise ValueError when sync functions have task=True
Move validation from server.py decorators to the from_function() class
methods on FunctionTool, FunctionPrompt, FunctionResource, and
FunctionResourceTemplate. This ensures the check runs regardless of how
the objects are created.
* Fix async check for callable classes and staticmethods
Move the task=True async validation to run AFTER callable classes and
staticmethods are unwrapped, preventing false positives for async
callable classes with sync-looking signatures.
* Implement MCP background tasks (SEP-1686) using Docket
Adds support for background task execution via the MCP task protocol,
powered by Docket for task queue management.
- Tools, resources, and prompts can be marked with `task=True` to run async
- Progress dependency for tracking task progress
- CurrentDocket and CurrentWorker dependencies for advanced use cases
- Client API with `.call_tool(..., task=True)` returns task handles
- Task status notifications via subscriptions
- CLI worker command for distributed task processing
Configuration via environment:
- FASTMCP_ENABLE_DOCKET=true
- FASTMCP_ENABLE_TASKS=true
- FASTMCP_DOCKET_URL=redis://... (or memory:// for single-process)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix tasks example import (TaskStatusResponse → GetTaskResult)
The example was using a non-existent TaskStatusResponse type.
Updated to use mcp.types.GetTaskResult which is what the
on_status_change callback actually receives.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix env var name in Docket error messages
The error messages referenced FASTMCP_EXPERIMENTAL_ENABLE_DOCKET but the
actual setting is FASTMCP_ENABLE_DOCKET.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Remove deprecated code re-added from pre-#2329 branch
- Remove ExtendedEnvSettingsSource (FASTMCP_SERVER_ prefix support)
- Remove dependencies parameter from FastMCP.__init__
* Replace fakeredis git pin with PyPI release
* Remove redundant fakeredis dev dep (pulled via pydocket)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jeremiah Lowin <153965+jlowin@users.noreply.github.com>
When GitHub's API rate limits cause asyncio shutdown issues, the test
times out rather than failing with the underlying 429 error. Updated the
detection logic to check for 429 indicators in the captured output when
a timeout occurs.
Also increased the per-test timeout from 15s to 30s to give remote API
calls more breathing room.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
All OAuth providers now return correct invalid_client error codes
instead of unauthorized_client for auth failures. Previously only
OAuthProxy had this fix; now OAuthProvider (and InMemoryOAuthProvider)
also benefit.
The pytest-retry plugin was causing teardown crashes due to a bug with
pytest's tmp_path fixture stash. Removing `@pytest.mark.flaky` and instead
improving the rate limit detection to properly skip tests on 429 errors.
Also fixed a brittle error message regex - GitHub changed their error
format from "tool not found" to "unknown tool".
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* Fix RFC 8414 path-aware authorization server metadata discovery
Override get_well_known_routes() in OAuthProvider to rewrite the
authorization server metadata route to be path-aware based on issuer_url,
matching how protected resource metadata already works.
Closes#2527
* Update readme
