* fix(sequentialthinking): restore nextThoughtNeeded in the advertised inputSchema required array
commit 1cdf806d (#3533) wrapped nextThoughtNeeded in a z.preprocess-based
coercedBoolean to fix a real footgun (string "false" coercing to true).
zod's toJSONSchema(..., { io: "input" }) treats a z.preprocess()-wrapped
field's input type as unknown, so it silently drops that field from the
emitted required array, even though it carries no .optional(). A client
that builds its call arguments from the advertised schema then omits
nextThoughtNeeded and gets a -32602 Invalid params from the runtime
validator, which still requires it.
Rebuild coercedBoolean as a transform on an explicit z.union([z.boolean(),
z.string()]) instead of z.preprocess. The union gives toJSONSchema a
concrete input type to report, so nextThoughtNeeded stays in required,
while parse behavior (including the case-insensitive string coercion
#3533 added) is unchanged.
Fixes#4651
* test(sequentialthinking): pin nextThoughtNeeded in required and string coercion
Runs against the built server so it checks the schema the SDK emits.
Skips when dist/ is absent, matching server-version.test.ts.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018Wo28CHPXyM3DHoLWvKnCK
---------
Co-authored-by: olaservo <olahungerford@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* fix(sequentialthinking): read server version from package.json
Replace the hardcoded 0.2.0 so initialize serverInfo tracks the
package version (0.6.2 in-tree; CalVer after release), matching the
approach used for memory server version sync.
Skip the dist-layout assertion when dist/ is absent so CI's
test-before-build job (and local runs without prepare) still pass.
* test(sequentialthinking): smoke stdio initialize serverInfo.version
Spawn the built server over stdio and assert getServerVersion() matches
package.json (and is not the old hardcoded 0.2.0). Skip when dist/ is
absent so test-before-build CI still passes.
fix(sequential-thinking): use z.coerce for number and safe preprocess for boolean params
Uses z.coerce.number() for number fields and a z.preprocess() helper for boolean fields to handle string-typed parameters from LLM clients. The preprocess approach correctly handles "false" → false, avoiding the z.coerce.boolean() footgun where Boolean("false") === true.
Fixes#3428
feat(sequential-thinking): add tool annotations
Adds MCP ToolAnnotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to the sequential-thinking tool, bringing it in line with the annotation pattern established by the filesystem server.
Fixes#3403
* fix(sequential-thinking): convert to modern TypeScript SDK APIs
Convert the sequential-thinking server to use the modern McpServer API
instead of the low-level Server API.
Key changes:
- Replace Server with McpServer from @modelcontextprotocol/sdk/server/mcp.js
- Use registerTool() method instead of manual request handlers
- Use Zod schemas directly in inputSchema/outputSchema
- Add structuredContent to tool responses
- Fix type literals to use 'as const' assertions
The modern API provides:
- Less boilerplate code
- Better type safety with Zod
- More declarative tool registration
- Cleaner, more maintainable code
* fix: exclude test files from TypeScript build
Add exclude for test files and vitest.config.ts to tsconfig
* refactor: remove redundant validation now handled by Zod
Zod schema already validates all required fields and types. Removed
validateThoughtData() method and kept only business logic validation
(adjusting totalThoughts if needed).
* fix(sequentialthinking): add Zod validation to processThought method
The modern API migration removed manual validation from processThought(),
but tests call this method directly, bypassing the Zod validation in the
tool registration layer. This commit adds Zod validation directly in the
processThought() method to ensure validation works both when called via
MCP and when called directly (e.g., in tests).
Also improves error message formatting to match the expected error
messages in the tests.
* refactor: simplify by removing redundant validation
Since processThought() is only called through the tool registration in
production, validation always happens via Zod schemas at that layer.
Removed redundant validation logic from processThought() and updated
tests to reflect this architectural decision.
Changes:
- Remove Zod validation from processThought() method
- Accept ThoughtData type instead of unknown
- Remove 10 validation tests that are now handled at tool registration
- Add comment explaining validation approach
Models are confused about the case of the variables, which results into random validation errors. Keeping them the same helps to remove back and forth.
Update thoughtNumber and totalThoughts parameter descriptions to use positive-only examples that guide LLMs toward correct numeric type usage. This addresses the issue where LLMs sometimes generate string values (e.g. "1") instead of numeric values (e.g. 1) for integer parameters.
Co-authored-by: Ola Hungerford <olaservo@users.noreply.github.com>
