This PR primarily fixes#572 by enabling graceful shutdown without consuming self. While implementing this, I noticed delete_session() is spawned as a background task, which means close() may return before HTTP session cleanup completes. Since this is part of the same shutdown lifecycle and can cause resource leaks/races, I'm including a small, localized fix to ensure cleanup is completed before close() returns. If maintainers prefer, I can split the cleanup timing change into a follow-up PR.
Changes:
- Add close(&mut self) for graceful shutdown without consuming
- Add close_with_timeout() for bounded shutdown operations
- Add is_closed() to check connection state
- Move HTTP delete_session from background spawn to inline cleanup
- Add 5-second timeout on session cleanup to prevent indefinite hangs
- Add Drop impl with debug log if dropped without explicit close
Fixes#572
The JSON-RPC 2.0 specification allows the ID field to be any JSON number,
including negative integers and large values. The previous u32 implementation
was limited to 0-4,294,967,295 and couldn't handle negative IDs.
Changes:
- Changed NumberOrString::Number from u32 to i64 to support full JSON number range
- Updated deserializer to handle both signed and unsigned integers
- Modified AtomicU32Provider to use AtomicU64 internally with i64 conversion
- Fixed progress token handling in meta.rs for i64 values
- Added comprehensive test for negative and large request IDs
This ensures full compliance with the JSON-RPC 2.0 specification.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add prompt support with typed argument handling
- Implement #[prompt], #[prompt_router], and #[prompt_handler] macros
- Add automatic JSON schema generation from Rust types for arguments
- Support flexible async handler signatures with automatic adaptation
- Create PromptRouter for efficient prompt dispatch
- Include comprehensive tests and example implementation
This enables MCP servers to provide reusable prompt templates that
LLMs can discover and invoke with strongly-typed parameters, similar
to the existing tool system but optimized for prompt use cases.
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: unify parameter handling between tools and prompts
- Replace Arguments<T> with Parameters<T> for consistent API
- Create shared common module for tool/prompt utilities
- Modernize async handling with futures::future::BoxFuture
- Move cached_schema_for_type to common module for reuse
- Update error types from rmcp::Error to rmcp::ErrorData
- Add comprehensive trait implementations for parameter extraction
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: extract Parameters wrapper to shared module and unify trait usage
- Move Parameters type from common.rs to dedicated wrapper/parameters.rs module
- Unify extractor traits by using FromContextPart for both tools and prompts
- Remove duplicate FromToolCallContextPart and FromPromptContextPart traits
- Add structured output support to Json wrapper with IntoCallToolResult impl
- Improve error messages with more descriptive panic for schema serialization
- Update all imports across codebase to use new module path
- Clean up trailing whitespace and formatting inconsistencies
This consolidates parameter extraction logic and reduces code duplication
between tool and prompt handlers while maintaining backward compatibility.
* chore: remove committed .egg-info directory and update gitignore
* docs: fix documentation formatting
* feat: provide more context information
1. provide context for notification
2. allow extract more info from tool call
3. inject http request part for streamable http server
* docs: add document for getting peer from context
* feat: better http server support
1. allow user get extensions in tool call.
2. allow user serve sse service without initialization.
* fix: fix document test
* refactor: a transport trait and streamable http client
* test: test with js streamable http server
* refactor: separate sse stream connection
* fix(test): streamable http client test with js
* fix(test): wait longer time for js server startup
* feat(transport): support streamable http server
* refactor(transport): add common module for shared transport utilities
* perf(tracing): add more log for streamable http session
* fix(test): fix port conflict in test with js
* fix(transport): fix id generating and session management
1. cancel when deleting
2. use `wrapping` and `saturating` correctly
* chore(naming): rename sse server to streamable http server
When a running service is dropped, its connections should be closed and its resources should be
cleaned up.
This changes the default from leaving services running to closing them. Library users who want
their services to remain running should call `waiting` on their running service, in a new task
where necessary.
Co-authored-by: Paul Ellenbogen <pe5@cs.princeton.edu>
1. Suppot revision 2025-03-26 data types
2. Support meta, progress tokne, and extensions in request/notification,
3. Remove `Message`, use `JsonRpcMessage` directly
