gitnexus 1.6.10-rc.65 → 1.6.10-rc.67

package/README.md

@@ -284,6 +284,7 @@ Set these env vars to use a remote OpenAI-compatible `/v1/embeddings` endpoint i
 export GITNEXUS_EMBEDDING_URL=http://your-server:8080/v1
 export GITNEXUS_EMBEDDING_MODEL=BAAI/bge-large-en-v1.5
 export GITNEXUS_EMBEDDING_DIMS=1024          # optional, default 384
+export GITNEXUS_EMBEDDING_REQUEST_DIMS=omit  # optional: omit "dimensions", or an integer to override it
 export GITNEXUS_EMBEDDING_API_KEY=your-key   # optional, default: "unused"
 export GITNEXUS_EMBEDDING_MAX_ATTEMPTS=3     # optional, total attempts (1-20)
 export GITNEXUS_EMBEDDING_RETRY_CAP_MS=5000  # optional, maximum retry delay
@@ -291,6 +292,15 @@ export GITNEXUS_EMBEDDING_MIN_INTERVAL_MS=0  # optional, minimum request spacing
 gitnexus analyze . --embeddings
 ```
 
+`GITNEXUS_EMBEDDING_REQUEST_DIMS` controls only the `dimensions` field sent in
+the request body, independently of `GITNEXUS_EMBEDDING_DIMS` (which still
+validates the returned vector's length):
+
+- `omit` (or `none`, `off`, `false`, `0`) — do not send `dimensions` at all, for
+  strict backends that return the right vector size but reject the field.
+- a positive integer — send that value instead of `GITNEXUS_EMBEDDING_DIMS`.
+- unset — send `GITNEXUS_EMBEDDING_DIMS` (the previous behavior).
+
 Works with Infinity, vLLM, TEI, llama.cpp, Ollama, LM Studio, or OpenAI. Retry and pacing settings are provider-neutral; provider-specific limits should be supplied through configuration. When unset, local embeddings are used unchanged.
 
 ## Multi-Repo Support

package/dist/core/embeddings/http-client.js

@@ -85,18 +85,24 @@ const paceHttpRequest = async (minIntervalMs, signal) => {
     await waitTurn;
 };
 /**
- * Stable lead of the {@link readConfig} malformed-`GITNEXUS_EMBEDDING_DIMS`
- * error. `readConfig` throws a plain `Error` (not an {@link HttpEmbeddingError})
- * because this is a *config* mistake, not an endpoint failure — so the CLI
- * recognizes it by this lead ({@link isHttpEmbeddingDimsError}) and prints a
- * clean config message instead of a raw stack dump. See #2385.
+ * Stable lead of a {@link readConfig} malformed dims-env error. `readConfig`
+ * throws a plain `Error` (not an {@link HttpEmbeddingError}) for a malformed
+ * `GITNEXUS_EMBEDDING_DIMS` or `GITNEXUS_EMBEDDING_REQUEST_DIMS` because it's a
+ * *config* mistake, not an endpoint failure — so the CLI recognizes it by this
+ * lead ({@link isHttpEmbeddingDimsError}) and prints a clean config message
+ * instead of a raw stack dump. Each var names itself so the message points the
+ * operator at the variable they actually set, not a sibling. See #2385.
  */
-const EMBEDDING_DIMS_ENV_ERROR_LEAD = 'GITNEXUS_EMBEDDING_DIMS must be a positive integer';
+const dimsEnvErrorLead = (name) => `${name} must be a positive integer`;
+const EMBEDDING_DIMS_ENV_ERROR_LEAD = dimsEnvErrorLead('GITNEXUS_EMBEDDING_DIMS');
+const EMBEDDING_REQUEST_DIMS_ENV_ERROR_LEAD = dimsEnvErrorLead('GITNEXUS_EMBEDDING_REQUEST_DIMS');
 /**
- * @internal Exported for the CLI analyze error handler. True when `message` is
- * the {@link readConfig} malformed-DIMS config error (a plain `Error`).
+ * @internal Exported for the CLI analyze error handler. True when `message` is a
+ * {@link readConfig} malformed dims-env config error (a plain `Error`) — for
+ * either `GITNEXUS_EMBEDDING_DIMS` or `GITNEXUS_EMBEDDING_REQUEST_DIMS`.
  */
-export const isHttpEmbeddingDimsError = (message) => message.includes(EMBEDDING_DIMS_ENV_ERROR_LEAD);
+export const isHttpEmbeddingDimsError = (message) => message.includes(EMBEDDING_DIMS_ENV_ERROR_LEAD) ||
+    message.includes(EMBEDDING_REQUEST_DIMS_ENV_ERROR_LEAD);
 /**
  * Build config from the current process.env snapshot.
  * Returns null when GITNEXUS_EMBEDDING_URL + GITNEXUS_EMBEDDING_MODEL are unset.
@@ -122,6 +128,23 @@ const readConfig = () => {
         }
         dimensions = parsed;
     }
+    const rawRequestDims = process.env.GITNEXUS_EMBEDDING_REQUEST_DIMS?.trim();
+    let requestDimensions = dimensions;
+    if (rawRequestDims) {
+        if (/^(omit|none|off|false|0)$/i.test(rawRequestDims)) {
+            requestDimensions = undefined;
+        }
+        else {
+            if (!/^\d+$/.test(rawRequestDims)) {
+                throw new Error(`${EMBEDDING_REQUEST_DIMS_ENV_ERROR_LEAD}, got "${rawRequestDims}"`);
+            }
+            const parsed = parseInt(rawRequestDims, 10);
+            if (parsed <= 0) {
+                throw new Error(`${EMBEDDING_REQUEST_DIMS_ENV_ERROR_LEAD}, got "${rawRequestDims}"`);
+            }
+            requestDimensions = parsed;
+        }
+    }
     return {
         baseUrl: baseUrl.replace(/\/+$/, ''),
         model,
@@ -130,6 +153,7 @@ const readConfig = () => {
         maxAttempts: parsePositiveIntegerEnv('GITNEXUS_EMBEDDING_MAX_ATTEMPTS', HTTP_MAX_RETRIES + 1, 20),
         retryCapMs: parsePositiveIntegerEnv('GITNEXUS_EMBEDDING_RETRY_CAP_MS', HTTP_RETRY_CAP_MS, 300_000),
         minIntervalMs: parseNonNegativeIntegerEnv('GITNEXUS_EMBEDDING_MIN_INTERVAL_MS', 0, 300_000),
+        requestDimensions,
     };
 };
 /**
@@ -236,9 +260,9 @@ const isEmbeddingItem = (item) => typeof item === 'object' &&
  *   the `dimensions` field in the request body. Endpoints that implement
  *   Matryoshka truncation (OpenAI text-embedding-3-*, Cohere embed-v3,
  *   Voyage) return a truncated vector at that size; endpoints that do not
- *   recognise the field may ignore it or return 400. Leave
- *   `GITNEXUS_EMBEDDING_DIMS` unset for strict backends that reject
- *   unknown fields.
+ *   recognise the field may ignore it or return 400. Set
+ *   `GITNEXUS_EMBEDDING_REQUEST_DIMS=omit` for strict backends while keeping
+ *   `GITNEXUS_EMBEDDING_DIMS` set to the returned vector size.
  */
 const httpEmbedBatch = async (url, batch, model, apiKey, batchIndex = 0, dimensions, requestOptions = {}, maxAttempts = HTTP_MAX_RETRIES + 1, retryCapMs = HTTP_RETRY_CAP_MS, minIntervalMs = 0) => {
     const requestBody = {
@@ -336,7 +360,7 @@ export const httpEmbed = async (texts, requestOptions = {}) => {
     for (let i = 0; i < texts.length; i += HTTP_BATCH_SIZE) {
         const batch = texts.slice(i, i + HTTP_BATCH_SIZE);
         const batchIndex = Math.floor(i / HTTP_BATCH_SIZE);
-        const items = await httpEmbedBatch(url, batch, config.model, config.apiKey, batchIndex, config.dimensions, requestOptions, config.maxAttempts, config.retryCapMs, config.minIntervalMs);
+        const items = await httpEmbedBatch(url, batch, config.model, config.apiKey, batchIndex, config.requestDimensions, requestOptions, config.maxAttempts, config.retryCapMs, config.minIntervalMs);
         if (items.length !== batch.length) {
             throw new HttpEmbeddingError(`Embedding endpoint returned ${items.length} vectors for ${batch.length} texts ` +
                 `(${safeUrl(url)}, batch ${batchIndex})`);
@@ -370,7 +394,7 @@ export const httpEmbedQuery = async (text, requestOptions = {}) => {
     if (!config)
         throw new Error('HTTP embedding not configured');
     const url = `${config.baseUrl}/embeddings`;
-    const items = await httpEmbedBatch(url, [text], config.model, config.apiKey, 0, config.dimensions, requestOptions, config.maxAttempts, config.retryCapMs, config.minIntervalMs);
+    const items = await httpEmbedBatch(url, [text], config.model, config.apiKey, 0, config.requestDimensions, requestOptions, config.maxAttempts, config.retryCapMs, config.minIntervalMs);
     if (!items.length) {
         throw new HttpEmbeddingError(`Embedding endpoint returned empty response (${safeUrl(url)})`);
     }

package/dist/core/ingestion/pipeline-phases/processes.d.ts

@@ -13,4 +13,12 @@ import { type ProcessDetectionResult } from '../process-processor.js';
 export interface ProcessesOutput {
     processResult: ProcessDetectionResult;
 }
+/**
+ * Compute the dynamic max-processes budget from the symbol count.
+ *
+ * Scales proportionally (symbolCount / 10) with a floor of 20.
+ * Prior to #2198 this was capped at 300 via `Math.min(300, …)`,
+ * silently truncating process detection on large repositories.
+ */
+export declare function computeDynamicMaxProcesses(symbolCount: number): number;
 export declare const processesPhase: PipelinePhase<ProcessesOutput>;

package/dist/core/ingestion/pipeline-phases/processes.js

@@ -14,6 +14,16 @@ import { generateId } from '../../../lib/utils.js';
 import { routeNodeKey } from '../route-extractors/route-path.js';
 import { isDev } from '../utils/env.js';
 import { logger } from '../../logger.js';
+/**
+ * Compute the dynamic max-processes budget from the symbol count.
+ *
+ * Scales proportionally (symbolCount / 10) with a floor of 20.
+ * Prior to #2198 this was capped at 300 via `Math.min(300, …)`,
+ * silently truncating process detection on large repositories.
+ */
+export function computeDynamicMaxProcesses(symbolCount) {
+    return Math.max(20, Math.round(symbolCount / 10));
+}
 export const processesPhase = {
     name: 'processes',
     // `structure` supplies `totalFiles` (progress counter) without the spurious
@@ -37,7 +47,7 @@ export const processesPhase = {
             if (n.label !== 'File')
                 symbolCount++;
         });
-        const dynamicMaxProcesses = Math.max(20, Math.min(300, Math.round(symbolCount / 10)));
+        const dynamicMaxProcesses = computeDynamicMaxProcesses(symbolCount);
         const processResult = await processProcesses(ctx.graph, communityResult.memberships, (message, progress) => {
             const processProgress = 99 + progress * 0.01;
             ctx.onProgress({

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "gitnexus",
-  "version": "1.6.10-rc.65",
+  "version": "1.6.10-rc.67",
   "description": "Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.",
   "author": "Abhigyan Patwari",
   "license": "PolyForm-Noncommercial-1.0.0",
@@ -70,7 +70,7 @@
     "graphology-indices": "^0.17.0",
     "graphology-utils": "^2.3.0",
     "ignore": "^7.0.5",
-    "js-yaml": "^5.0.0",
+    "js-yaml": "^4.1.1",
     "jsonc-parser": "^3.3.1",
     "mnemonist": "^0.40.3",
     "node-addon-api": "^8.0.0",
@@ -106,7 +106,7 @@
     "@types/cors": "^2.8.17",
     "@types/express": "^5.0.6",
     "@types/js-yaml": "^4.0.9",
-    "@types/node": "^25.6.0",
+    "@types/node": "^26.0.0",
     "@types/uuid": "^11.0.0",
     "@vitest/coverage-v8": "^4.0.18",
     "gitnexus-shared": "file:../gitnexus-shared",