sdl-mcp 0.10.4 → 0.10.6

package/README.md

@@ -281,11 +281,11 @@ The sandboxed runtime execution tool (`sdl.runtime.execute`) has its own governa
 
 ### Agent Context — Task-Shaped Retrieval
 
-`sdl.agent.context` is SDL-MCP's task-shaped context engine. Give it a task type (`debug`, `review`, `implement`, `explain`), a description, and a budget — it selects the right Iris Gate rungs, collects evidence, and returns context tuned to the job. In Code Mode, `sdl.context` provides the same retrieval surface without dropping into `sdl.workflow`.
+`sdl.context` is SDL-MCP's task-shaped context engine. Give it a task type (`debug`, `review`, `implement`, `explain`), a description, and a budget — it selects the right Iris Gate rungs, collects evidence, and returns context tuned to the job. In Code Mode, `sdl.context` provides the same retrieval surface without dropping into `sdl.workflow`.
 
 The feedback loop (`sdl.agent.feedback`) records which symbols were useful and which were missing, improving future slice quality.
 
-`sdl.context.summary` generates portable, token-bounded context briefings in markdown, JSON, or clipboard format for use outside MCP environments.
+ generates portable, token-bounded context briefings in markdown, JSON, or clipboard format for use outside MCP environments.
 
 **Why it matters:**
 
@@ -440,7 +440,7 @@ Each gateway tool accepts an `action` discriminator field (e.g., `{ action: "sym
 <tr><td rowspan="3"><strong>Symbols</strong></td>
     <td><code>sdl.symbol.search</code></td><td>Search symbols by name (with optional semantic reranking)</td></tr>
 <tr><td><code>sdl.symbol.getCard</code></td><td>Get a symbol card with ETag-based conditional support</td></tr>
-<tr><td><code>sdl.symbol.getCards</code></td><td>Batch-fetch up to 100 cards in one round trip</td></tr>
+<tr><td><code>sdl.symbol.getCard</code></td><td>Batch-fetch up to 100 cards in one round trip</td></tr>
 
 <tr><td rowspan="3"><strong>Slices</strong></td>
     <td><code>sdl.slice.build</code></td><td>Build a task-scoped dependency subgraph</td></tr>
@@ -463,10 +463,10 @@ Each gateway tool accepts an `action` discriminator field (e.g., `{ action: "sym
     <td><code>sdl.pr.risk.analyze</code></td><td>Scored PR risk with findings and test recommendations</td></tr>
 
 <tr><td><strong>Context</strong></td>
-    <td><code>sdl.context.summary</code></td><td>Token-bounded portable briefing (markdown/JSON/clipboard) with conditional ETag fetch support</td></tr>
+    <td><code></code></td><td>Token-bounded portable briefing (markdown/JSON/clipboard) with conditional ETag fetch support</td></tr>
 
 <tr><td rowspan="3"><strong>Agent</strong></td>
-    <td><code>sdl.agent.context</code></td><td>Task-shaped context retrieval with budget-controlled rung planning and conditional ETag fetch support</td></tr>
+    <td><code>sdl.context</code></td><td>Task-shaped context retrieval with budget-controlled rung planning and conditional ETag fetch support</td></tr>
 <tr><td><code>sdl.agent.feedback</code></td><td>Record which symbols were useful or missing</td></tr>
 <tr><td><code>sdl.agent.feedback.query</code></td><td>Query aggregated feedback statistics</td></tr>
 

package/config/sdlmcp.config.example.json

@@ -5,12 +5,23 @@
       "repoId": "my-repo",
       "rootPath": ".",
       "ignore": [
-        "**/node_modules/**",
+        "**/.git/**",
         "**/dist/**",
-        "**/.next/**",
+        "**/dist-*/**",
         "**/build/**",
-        "**/.git/**",
-        "**/coverage/**"
+        "**/out/**",
+        "**/target/**",
+        "**/coverage/**",
+        "**/node_modules/**",
+        "**/vendor/**",
+        "**/.next/**",
+        "**/__pycache__/**",
+        "**/.venv/**",
+        "**/.tmp/**",
+        "**/.claude/**",
+        "**/.codex/**",
+        "**/.cursor/**",
+        "**/.sdl-memory/**"
       ],
       "languages": [
         "ts",
@@ -40,6 +51,7 @@
       }
     }
   ],
+  "performanceTier": "auto",
   "graphDatabase": {
     "path": "./data/sdl-mcp-graph.lbug"
   },
@@ -61,7 +73,8 @@
     "maxWatchedFiles": 25000,
     "workerPoolSize": null,
     "engine": "rust",
-    "watchDebounceMs": 300
+    "watchDebounceMs": 300,
+    "pass2Concurrency": 1
   },
   "liveIndex": {
     "enabled": true,
@@ -102,7 +115,7 @@
   "semantic": {
     "enabled": true,
     "provider": "local",
-    "model": "all-MiniLM-L6-v2",
+    "model": "jina-embeddings-v2-base-code",
     "modelCacheDir": null,
     "generateSummaries": false,
     "summaryProvider": null,
@@ -111,6 +124,7 @@
     "summaryApiBaseUrl": null,
     "summaryMaxConcurrency": 5,
     "summaryBatchSize": 20,
+    "embeddingConcurrency": 1,
     "retrieval": {
       "mode": "hybrid",
       "extensionsOptional": true,
@@ -124,10 +138,10 @@
         "enabled": true,
         "topK": 75,
         "efc": 200,
-              "efs": 200,
+        "efs": 200,
         "indexes": {
-          "all-MiniLM-L6-v2": {
-            "indexName": "symbol_vec_minilm_l6_v2"
+          "jina-embeddings-v2-base-code": {
+            "indexName": "symbol_vec_jina_code_v2"
           },
           "nomic-embed-text-v1.5": {
             "indexName": "symbol_vec_nomic_embed_v15"

package/config/sdlmcp.config.json

@@ -4,12 +4,24 @@
       "repoId": "my-repo",
       "rootPath": ".",
       "ignore": [
-        "**/node_modules/**",
+        "**/.git/**",
         "**/dist/**",
-        "**/.next/**",
+        "**/dist-*/**",
         "**/build/**",
-        "**/.git/**",
+        "**/out/**",
+        "**/target/**",
         "**/coverage/**",
+        "**/node_modules/**",
+        "**/vendor/**",
+        "**/.next/**",
+        "**/__pycache__/**",
+        "**/.venv/**",
+        "**/.tmp/**",
+        "**/.claude/**",
+        "**/.codex/**",
+        "**/.cursor/**",
+        "**/.sdl-memory/**",
+        "**/.sisyphus/**",
         "**/native/target/**"
       ],
       "languages": [
@@ -42,11 +54,7 @@
         "**/*.test.ts",
         "**/*.spec.ts"
       ],
-      "languages": [
-        "ts",
-        "tsx",
-        "js"
-      ]
+      "languages": ["ts", "tsx", "js"]
     },
     {
       "repoId": "preact-oss",
@@ -61,12 +69,7 @@
         "**/*.test.tsx",
         "**/*.spec.tsx"
       ],
-      "languages": [
-        "ts",
-        "tsx",
-        "js",
-        "jsx"
-      ]
+      "languages": ["ts", "tsx", "js", "jsx"]
     },
     {
       "repoId": "flask-oss",
@@ -81,9 +84,7 @@
         "**/*.pyc",
         "**/tests/**"
       ],
-      "languages": [
-        "py"
-      ]
+      "languages": ["py"]
     },
     {
       "repoId": "ansible-lint-oss",
@@ -100,10 +101,7 @@
         "**/tests/**",
         "**/.tox/**"
       ],
-      "languages": [
-        "py",
-        "sh"
-      ]
+      "languages": ["py", "sh"]
     }
   ],
   "graphDatabase": {
@@ -145,7 +143,7 @@
     "enabled": true,
     "alpha": 0.6,
     "provider": "mock",
-    "model": "all-MiniLM-L6-v2",
+    "model": "jina-embeddings-v2-base-code",
     "generateSummaries": false
   },
   "prefetch": {

package/config/sdlmcp.config.schema.json

@@ -29,10 +29,21 @@
               "type": "string"
             },
             "default": [
-              "**/node_modules/**",
+              "**/.git/**",
               "**/dist/**",
+              "**/dist-*/**",
+              "**/build/**",
+              "**/out/**",
+              "**/target/**",
+              "**/coverage/**",
+              "**/node_modules/**",
+              "**/vendor/**",
               "**/.next/**",
-              "**/build/**"
+              "**/__pycache__/**",
+              "**/.venv/**",
+              "**/.tmp/**",
+              "**/.claude/**",
+              "**/.sdl-memory/**"
             ]
           },
           "languages": {
@@ -142,6 +153,12 @@
         }
       }
     },
+    "performanceTier": {
+      "type": "string",
+      "description": "CPU performance tier for auto-tuning concurrency defaults. 'auto' (default) detects hardware at startup. 'mid' = 1-8 cores (conservative), 'high' = 9-20 cores (moderate), 'extreme' = 21+ cores (aggressive). Presets only affect fields not explicitly set by the user.",
+      "enum": ["mid", "high", "extreme", "auto"],
+      "default": "auto"
+    },
     "policy": {
       "type": "object",
       "description": "Code access policy settings",
@@ -241,7 +258,7 @@
           "type": "integer",
           "description": "Number of concurrent indexing workers",
           "minimum": 1,
-          "maximum": 10,
+          "maximum": 32,
           "default": 8
         },
         "enableFileWatching": {
@@ -259,7 +276,7 @@
           "type": "integer",
           "description": "Optional cap for the indexing worker pool size",
           "minimum": 1,
-          "maximum": 16
+          "maximum": 32
         },
         "engine": {
           "type": "string",
@@ -273,6 +290,13 @@
           "minimum": 50,
           "maximum": 5000,
           "default": 300
+        },
+        "pass2Concurrency": {
+          "type": "integer",
+          "description": "Number of files to resolve concurrently in Pass 2 cross-file call resolution. Default 1 (sequential). Increase on multi-core systems to overlap CPU parse work with read I/O.",
+          "minimum": 1,
+          "maximum": 16,
+          "default": 1
         }
       },
       "default": {
@@ -280,7 +304,8 @@
         "enableFileWatching": true,
         "maxWatchedFiles": 25000,
         "engine": "rust",
-        "watchDebounceMs": 300
+        "watchDebounceMs": 300,
+        "pass2Concurrency": 1
       }
     },
     "liveIndex": {
@@ -317,7 +342,7 @@
           "type": "integer",
           "description": "Reserved concurrency cap for background reconciliation work",
           "minimum": 1,
-          "maximum": 8,
+          "maximum": 16,
           "default": 1
         },
         "clusterRefreshThreshold": {
@@ -522,12 +547,8 @@
         },
         "model": {
           "type": "string",
-          "enum": [
-            "all-MiniLM-L6-v2",
-            "nomic-embed-text-v1.5",
-            "jina-embeddings-v2-base-code"
-          ],
-          "default": "all-MiniLM-L6-v2"
+          "enum": ["jina-embeddings-v2-base-code", "nomic-embed-text-v1.5"],
+          "default": "jina-embeddings-v2-base-code"
         },
         "modelCacheDir": {
           "type": "string",
@@ -558,7 +579,7 @@
           "type": "integer",
           "description": "Maximum concurrent LLM requests for summary generation",
           "minimum": 1,
-          "maximum": 20,
+          "maximum": 32,
           "default": 5
         },
         "summaryBatchSize": {
@@ -568,6 +589,13 @@
           "maximum": 50,
           "default": 20
         },
+        "embeddingConcurrency": {
+          "type": "integer",
+          "description": "Number of embedding batches to process concurrently during refreshSymbolEmbeddings(). Defaults to 1 (sequential). Increasing this can improve throughput on multi-core machines but ONNX Runtime's internal thread pool is shared across concurrent calls; consider reducing intraOpNumThreads proportionally when raising above 1. Maximum 4.",
+          "minimum": 1,
+          "maximum": 4,
+          "default": 1
+        },
         "ann": {
           "type": "object",
           "description": "Deprecated — removed in v0.10.1. Silently ignored. Use retrieval.vector instead.",
@@ -668,8 +696,8 @@
                     }
                   },
                   "default": {
-                    "all-MiniLM-L6-v2": {
-                      "indexName": "symbol_vec_minilm_l6_v2"
+                    "jina-embeddings-v2-base-code": {
+                      "indexName": "symbol_vec_jina_code_v2"
                     },
                     "nomic-embed-text-v1.5": {
                       "indexName": "symbol_vec_nomic_embed_v15"
@@ -682,8 +710,8 @@
                 "topK": 75,
                 "efs": 200,
                 "indexes": {
-                  "all-MiniLM-L6-v2": {
-                    "indexName": "symbol_vec_minilm_l6_v2"
+                  "jina-embeddings-v2-base-code": {
+                    "indexName": "symbol_vec_jina_code_v2"
                   },
                   "nomic-embed-text-v1.5": {
                     "indexName": "symbol_vec_nomic_embed_v15"
@@ -734,7 +762,9 @@
               "topK": 75,
               "efs": 200,
               "indexes": {
-                "all-MiniLM-L6-v2": { "indexName": "symbol_vec_minilm_l6_v2" },
+                "jina-embeddings-v2-base-code": {
+                  "indexName": "symbol_vec_jina_code_v2"
+                },
                 "nomic-embed-text-v1.5": {
                   "indexName": "symbol_vec_nomic_embed_v15"
                 }
@@ -751,11 +781,12 @@
       "default": {
         "enabled": true,
         "provider": "local",
-        "model": "all-MiniLM-L6-v2",
+        "model": "jina-embeddings-v2-base-code",
         "generateSummaries": false,
         "summaryModel": "claude-haiku-4-5-20251001",
         "summaryMaxConcurrency": 5,
-        "summaryBatchSize": 20
+        "summaryBatchSize": 20,
+        "embeddingConcurrency": 1
       }
     },
     "prefetch": {
@@ -836,7 +867,7 @@
           "type": "integer",
           "description": "Number of worker threads in the scorer pool",
           "minimum": 1,
-          "maximum": 8
+          "maximum": 16
         },
         "minBatchSize": {
           "type": "integer",
@@ -868,21 +899,21 @@
           "type": "integer",
           "description": "Maximum number of concurrent MCP sessions",
           "minimum": 1,
-          "maximum": 16,
+          "maximum": 32,
           "default": 8
         },
         "maxToolConcurrency": {
           "type": "integer",
           "description": "Maximum concurrent tool handler executions across all sessions",
           "minimum": 1,
-          "maximum": 32,
+          "maximum": 64,
           "default": 8
         },
         "readPoolSize": {
           "type": "integer",
           "description": "Number of read-only database connections in the pool",
           "minimum": 1,
-          "maximum": 8,
+          "maximum": 16,
           "default": 4
         },
         "writeQueueTimeoutMs": {
@@ -964,7 +995,7 @@
           "type": "integer",
           "description": "Maximum concurrent runtime executions",
           "minimum": 1,
-          "maximum": 8,
+          "maximum": 12,
           "default": 2
         },
         "envAllowlist": {