@functional-systems/lambdadb-mcp 0.1.4-dev.13 → 0.1.4-dev.15

package/CHANGELOG.md

@@ -16,12 +16,12 @@
 
 - Pin the LambdaDB TypeScript SDK to 0.7.0 and expose all 49 fixed lowercase
   analyzer presets in collection-tool guidance; preserve analyzer serialization.
-- Add optional per-query managed reranking to the MCP schema and SDK request path,
+- Add optional per-query native reranking to the MCP schema and SDK request path,
   preserving omission/null, distinct sizes, custom criteria, envelope scores and
   status metadata, including document downloads. Retain SDK validation and errors.
 - Extend local and installed-package contracts for analyzer expansion and reranking;
   update the opt-in live analyzer check to cover all 49 names.
-- Add a separate opt-in managed-reranking live suite for real default/custom
+- Add a separate opt-in native reranking live suite for real default/custom
   inference, empty candidates, omitted/null behavior and docsUrl envelope
   preservation, with owned-resource cleanup and no fixed relevance expectations.
 - Native SDK usage is unchanged; no Qdrant mapping exists in this server. Supporting

package/CONTRIBUTING.md

@@ -8,7 +8,7 @@ changes outside the PR. Use a dedicated worktree when another checkout is in use
 
 Use Node.js 22.14.0 or newer. CI verifies the exact minimum 22.14.0 and current
 22.x and 24.x LTS releases. Node 20 is end-of-life and is no longer supported.
-The runtime dependencies permit older Node versions (MCP SDK 1.29.0 declares
+The runtime dependencies permit older Node versions (MCP SDK 1.31.0 declares
 Node >=18), but that is not a promise to support end-of-life runtimes. The
 22.14.0 floor also aligns with the CLI and npm's OIDC publishing runtime floor.
 See the [Node release schedule](https://nodejs.org/en/about/previous-releases)

package/README.md

@@ -21,7 +21,7 @@ reproducibility or the default stable channel for initial setup. See
 
 [MCP 0.1.3](https://github.com/lambdadb/lambdadb-mcp/releases/tag/v0.1.3) is the
 published stable release with SDK 0.8.0, Bayesian hybrid search and native
-embedding configuration, alongside managed reranking and all 49 text analyzers.
+embedding configuration, alongside native reranking and all 49 text analyzers.
 This synchronization starts the next `0.1.4-dev.1` source base; check npm for the
 current published dev version. Use exact stable version `0.1.3` for reproducible
 installed execution.
@@ -55,7 +55,9 @@ configurations for reproducibility. `@dev`, `@rc` and unqualified (`latest`) res
 different release channels; installed copies do not update themselves.
 
 The server uses stdio: stdout contains only MCP JSON-RPC messages, diagnostics go
-to stderr, and stdin closure/SIGINT/SIGTERM ends the process. Running it without an
+to stderr, and stdin closure/SIGINT/SIGTERM ends the process. The MCP SDK limits
+the stdio receive buffer to 10 MiB and closes the transport if that limit is
+exceeded; keep incoming JSON-RPC messages below it. Running it without an
 MCP client waits for protocol input. See the [MCP transport specification](https://modelcontextprotocol.io/specification/2025-11-25/basic/transports).
 
 ## Project Structure
@@ -104,8 +106,8 @@ Optional write tools:
 
 ## API contract and tool inputs
 
-The LambdaDB SDK is pinned to `@functional-systems/lambdadb@0.8.0`, checked against
-the published package and [v0.8.0 release](https://github.com/lambdadb/lambdadb-typescript-client/releases/tag/v0.8.0).
+The LambdaDB SDK is pinned to `@functional-systems/lambdadb@0.8.1`, checked against
+the published package and [v0.8.1 release](https://github.com/lambdadb/lambdadb-typescript-client/releases/tag/v0.8.1).
 This dependency update applies to builds containing this change. Publishing the SDK
 alone does not update previously published or installed MCP packages.
 
@@ -230,7 +232,7 @@ integer candidate budgets unchanged, and leaves Bayesian structure, bounds and
 cross-field validation to the server, retaining service errors. No query defaults,
 weights or candidate counts are inserted by MCP. Bayesian scores are heuristic
 fusion scores; applied reranking preserves them in `retrievalScore` and retains
-all rerank status metadata, including through SDK-managed `docsUrl` downloads.
+all rerank status metadata, including when the SDK downloads documents from `docsUrl`.
 
 The [Bayesian contract](https://github.com/lambdadb/lambdadb-typescript-client/blob/v0.8.0/docs/bayesian-search.md)
 and native embedding additions below are pinned to backend
@@ -274,8 +276,8 @@ Bayesian example above. For example, call `lambdadb_query_collection` with:
 }
 ```
 
-Native dimensions and similarity are optional and belong inside `embedding`.
-MCP does not infer a flag, provider, model or native dimensions/similarity default.
+Native embedding dimensions and similarity are optional and belong inside `embedding`.
+MCP does not infer a flag, provider, model or native embedding dimensions/similarity default.
 The SDK rejects `managedEmbedding: false` with `embedding`, and native embedding
 with top-level dimensions/similarity. Caller-provided vectors continue to use
 top-level dimensions/similarity. Free-form nested object configurations retain
@@ -283,12 +285,14 @@ server validation. For older servers, explicitly add `managedEmbedding: true`
 beside `type`; it is preserved. Normalized collection metadata may still contain
 that true flag. See the [native embedding contract](https://github.com/lambdadb/lambdadb-typescript-client/blob/v0.8.0/docs/native-embeddings.md).
 
-### Optional managed reranking
+<a id="optional-managed-reranking"></a>
+
+### Optional native reranking
 
 `lambdadb_query_collection` accepts per-query `rerank`; omission or `null`
 preserves existing searches. Collection creation has no rerank setting.
-LambdaDB manages provider credentials; only the existing project API key is needed.
-See the [managed reranking contract](https://github.com/lambdadb/lambdadb-typescript-client/blob/v0.7.0/docs/managed-reranking.md).
+LambdaDB supplies provider credentials; only the existing project API key is needed.
+See the [native reranking contract](https://github.com/lambdadb/lambdadb-typescript-client/blob/v0.7.0/docs/managed-reranking.md).
 
 ```json
 {
@@ -433,7 +437,7 @@ temporary collection in cleanup, and verifies that the collection is absent.
 Branch/Tag/Alias setup and collection cleanup use the SDK directly because these
 operations are not exposed as MCP tools. This test is separate from `npm run check`.
 
-Managed reranking has a separate live suite because it requires an enabled
+Native reranking has a separate live suite because it requires an enabled
 `typesafe` / `jev-1.13.0` model and can incur inference cost. Use the same explicitly
 authorized development project and write opt-in, with an additional inference opt-in:
 
@@ -454,8 +458,8 @@ suite does not deliberately induce failures or verify search quality, load,
 production deployment or billing readiness. These live suites are outside default
 checks and credential-free CI.
 
-Bayesian/native embedding verification also requires explicit managed inference
-opt-in for OpenAI embeddings and TypeSafe reranking:
+Bayesian/native embedding verification also requires explicit inference
+opt-in for native embedding with OpenAI and native reranking with TypeSafe:
 
 ```bash
 LAMBDADB_RUN_LIVE_TESTS=1 LAMBDADB_RUN_LIVE_RERANK_TESTS=1 LAMBDADB_LIVE_CONFIRM_PROJECT=YOUR_DEV_PROJECT npm run test:live:bayesian

package/RELEASING.md

@@ -34,7 +34,7 @@ A downloaded stable tarball matched registry integrity, source commit and SDK
 0.7.0 and passed 31 clean-consumer stdio tests. Provenance statement repository,
 workflow, tag, source commit and subject digest matched the publication.
 
-SDK 0.7.0 adds 49 fixed text analyzer presets and optional per-query managed
+SDK 0.7.0 adds 49 fixed text analyzer presets and optional per-query native
 reranking. Read-only defaults and explicit write opt-in remain. See
 `docs/validation/2026-10-04-0.1.2.md` for separate candidate, authorized
 source-build live, published dev and published stable evidence. Do not repeat the
@@ -46,7 +46,7 @@ while `latest` stays on 0.1.2 until an explicitly authorized stable release.
 Do not merge stable version metadata directly into develop.
 
 Live suites require explicit designation of a development project. Reranking
-also requires managed inference opt-in; no Jev API key is required. Live contract
+also requires native reranking inference opt-in; no Jev API key is required. Live contract
 checks do not establish production deployment, search quality, load/failure
 coverage or billing readiness. Supporting backend deployment/model availability
 and keyword-index requirements remain; existing collections/indexes are not migrated.

package/dist/tools/read.js

@@ -23,7 +23,7 @@ const rerankSchema = z.strictObject({
         .describe("Omitted/null defaults to error. returnOriginal covers only eligible provider failures."),
     criteria: z.array(z.string().min(1)).min(2).max(10).meta({ uniqueItems: true }).nullable().optional()
         .describe("Distinct nonblank descriptions from lowest to highest relevance, at most 2 KiB each and 8 KiB total UTF-8. Omitted/null uses defaults.")
-}).nullable().optional().describe("Optional per-query managed reranking; requires a scoring query and positive size, forbids sort. LambdaDB manages provider credentials.");
+}).nullable().optional().describe("Optional per-query native reranking; requires a scoring query and positive size, forbids sort. LambdaDB supplies provider credentials.");
 export function registerReadTools(server, config) {
     server.registerTool("lambdadb_list_collections", {
         title: "List Collections",
@@ -68,7 +68,7 @@ export function registerReadTools(server, config) {
     });
     server.registerTool("lambdadb_query_collection", {
         title: "Query Collection",
-        description: "Search documents with optional Bayesian hybrid search, managed reranking and keyword facet counts across all matches. Omit query for match-all; size: 0 requires facets and forbids reranking. Reranking requires a scoring query and forbids sort; it does not enable vector/hybrid facets. Applied envelope score is an evaluation score, retrievalScore preserves search score, and rerank metadata reports status. Features require a supporting server; facets require newly built keyword indexes.",
+        description: "Search documents with optional Bayesian hybrid search, native reranking and keyword facet counts across all matches. Omit query for match-all; size: 0 requires facets and forbids reranking. Reranking requires a scoring query and forbids sort; it does not enable vector/hybrid facets. Applied envelope score is an evaluation score, retrievalScore preserves search score, and rerank metadata reports status. Features require a supporting server; facets require newly built keyword indexes.",
         annotations: {
             readOnlyHint: true,
             openWorldHint: false

package/dist/tools/write.js

@@ -6,13 +6,13 @@ import { jsonResult, nameSchema, partitionFilterSchema } from "./shared.js";
 export function registerWriteTools(server, config) {
     server.registerTool("lambdadb_create_collection", {
         title: "Create Collection",
-        description: `Create a new collection in the configured project. Fixed lowercase text analyzer presets: ${Object.values(Analyzer).join(", ")}. Omitted analyzers uses standard; custom pipelines/options are unsupported. The keyword text analyzer is distinct from the keyword field type. Keyword indexes built on a supporting server support facets. Native vector fields accept embedding without managedEmbedding; explicit managedEmbedding: true remains supported for older servers.`,
+        description: `Create a new collection in the configured project. Fixed lowercase text analyzer presets: ${Object.values(Analyzer).join(", ")}. Omitted analyzers uses standard; custom pipelines/options are unsupported. The keyword text analyzer is distinct from the keyword field type. Keyword indexes built on a supporting server support facets. Native embedding vector fields accept embedding without managedEmbedding; explicit managedEmbedding: true remains supported for older servers.`,
         annotations: {
             openWorldHint: false
         },
         inputSchema: z.strictObject({
             collectionName: nameSchema,
-            indexConfigs: z.record(z.string(), z.any()).refine((value) => Object.keys(value).length > 0, "indexConfigs must contain at least one field.").describe("Field configurations validated by the SDK/server. Native vectors: {type: 'vector', embedding: {provider, model, sourceField, dimensions?, similarity?}}; declare sourceField as text. Native dimensions/similarity belong inside embedding, never at the field top level. Do not combine embedding with managedEmbedding: false. Legacy true is preserved; no provider/model or native defaults are inferred. Caller-provided vectors retain top-level dimensions/similarity."),
+            indexConfigs: z.record(z.string(), z.any()).refine((value) => Object.keys(value).length > 0, "indexConfigs must contain at least one field.").describe("Field configurations validated by the SDK/server. Native embedding vectors: {type: 'vector', embedding: {provider, model, sourceField, dimensions?, similarity?}}; declare sourceField as text. Native embedding dimensions/similarity belong inside embedding, never at the field top level. Do not combine embedding with managedEmbedding: false. Legacy true is preserved; no provider/model or native embedding defaults are inferred. Caller-provided vectors retain top-level dimensions/similarity."),
             description: z.string().max(255).optional(),
             tags: z.record(z.string().regex(/^[A-Za-z0-9_.-]{1,63}$/), z.string().min(1).max(127).regex(/^[^:#,]+$/))
                 .refine((value) => Object.keys(value).length <= 5, "At most five tags are allowed.")

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@functional-systems/lambdadb-mcp",
-  "version": "0.1.4-dev.13",
+  "version": "0.1.4-dev.15",
   "private": false,
   "description": "MCP server for LambdaDB data plane",
   "type": "module",
@@ -24,8 +24,8 @@
     "test:package": "node scripts/test-package.mjs"
   },
   "dependencies": {
-    "@functional-systems/lambdadb": "0.8.0",
-    "@modelcontextprotocol/sdk": "1.29.0",
+    "@functional-systems/lambdadb": "0.8.1",
+    "@modelcontextprotocol/sdk": "1.31.0",
     "zod": "^4.1.12"
   },
   "devDependencies": {
@@ -62,5 +62,5 @@
     "access": "public",
     "registry": "https://registry.npmjs.org"
   },
-  "gitHead": "f61b3a9a3b8ce34001292d21e5fdce301534c940"
+  "gitHead": "752fd825480556305f2a89025a0d87f5126b4d1b"
 }