sdl-mcp 0.11.4 → 0.11.5

package/README.md

@@ -772,6 +772,7 @@ flowchart TD
 | [Agent Context](./docs/feature-deep-dives/agent-context.md)                         | Task-shaped context retrieval, feedback loops, portable context summaries             |
 | [Context Modes](./docs/feature-deep-dives/context-modes.md)                         | Precise vs broad retrieval, adaptive symbol ranking, benchmark trade-offs             |
 | [Indexing & Languages](./docs/feature-deep-dives/indexing-languages.md)             | Rust/TS engines, two-pass architecture, 12-language support                           |
+| [Provider-First Indexing](./docs/feature-deep-dives/provider-first-indexing.md)     | SCIP/LSP-first planning, provider facts, shadow DB readiness, fallback boundaries     |
 | [Runtime Execution](./docs/feature-deep-dives/runtime-execution.md)                 | Sandboxed subprocess execution with governance                                        |
 | [CLI Tool Access](./docs/feature-deep-dives/cli-tool-access.md)                     | Direct CLI access to 36 action aliases, output formats, stdin piping, scripting       |
 | [Tool Gateway](./docs/feature-deep-dives/tool-gateway.md)                           | 35 gateway-routable actions, 4 namespace tools, thin schemas, migration guide         |

package/config/sdlmcp.config.example.json

@@ -9,7 +9,12 @@
         "**/dist/**",
         "**/dist-*/**",
         "**/build/**",
+        "**/build-*/**",
+        "**/build_*/**",
+        "**/cmake-build-*/**",
         "**/out/**",
+        "**/out-*/**",
+        "**/out_*/**",
         "**/target/**",
         "**/coverage/**",
         "**/node_modules/**",
@@ -40,6 +45,7 @@
         "sh"
       ],
       "maxFileBytes": 2000000,
+      "sourceFileListPath": null,
       "postIndexSessionTimeoutMs": 900000,
       "includeNodeModulesTypes": true,
       "packageJsonPath": null,
@@ -69,13 +75,38 @@
     "patterns": []
   },
   "indexing": {
+    "pipeline": "auto",
+    "providerFirst": {
+      "activation": "shadowDb",
+      "readyState": "graphPlusAlgorithms",
+      "stagingFormat": "parquet",
+      "maxLegacyFallbackFiles": 1000000,
+      "maxSemanticEligibleFallbackFiles": 0,
+      "lsp": {
+        "mode": "primaryWithCaps",
+        "workspaceSymbolLimit": 5000,
+        "documentSymbolFileLimit": 500,
+        "referenceCandidateLimit": 200,
+        "diagnosticsLimit": 5000
+      }
+    },
     "concurrency": 8,
     "enableFileWatching": true,
     "maxWatchedFiles": 25000,
     "workerPoolSize": null,
     "engine": "rust",
     "watchDebounceMs": 300,
-    "pass2Concurrency": 1
+    "pass2Concurrency": 1,
+    "algorithmRefresh": {
+      "enabled": true,
+      "pageRank": { "enabled": true },
+      "kCore": { "enabled": true },
+      "louvain": {
+        "enabled": true,
+        "maxCallEdges": 10000
+      },
+      "workerTimeoutMs": 120000
+    }
   },
   "liveIndex": {
     "enabled": true,
@@ -111,18 +142,15 @@
   "plugins": {
     "paths": [],
     "enabled": true,
-    "strictVersioning": true
+    "strictVersioning": true,
+    "trustedRoots": []
   },
   "semantic": {
     "enabled": true,
     "provider": "local",
     "embeddingProfile": "specialized",
-    "symbolEmbeddingModels": [
-      "jina-embeddings-v2-base-code"
-    ],
-    "fileSummaryEmbeddingModels": [
-      "nomic-embed-text-v1.5"
-    ],
+    "symbolEmbeddingModels": ["jina-embeddings-v2-base-code"],
+    "fileSummaryEmbeddingModels": ["nomic-embed-text-v1.5"],
     "modelCacheDir": null,
     "generateSummaries": false,
     "summaryProvider": null,
@@ -137,9 +165,7 @@
     "fileSummaryEmbeddingMaxChars": 4096,
     "embeddingsSequential": false,
     "modelVariant": "default",
-    "executionProviders": [
-      "cpu"
-    ],
+    "executionProviders": ["cpu"],
     "retrieval": {
       "mode": "hybrid",
       "extensionsOptional": true,
@@ -240,12 +266,7 @@
   },
   "runtime": {
     "enabled": true,
-    "allowedRuntimes": [
-      "node",
-      "typescript",
-      "python",
-      "shell"
-    ],
+    "allowedRuntimes": ["node", "typescript", "python", "shell"],
     "allowedExecutables": [],
     "maxDurationMs": 30000,
     "maxStdoutBytes": 1048576,
@@ -307,7 +328,8 @@
       "args": [],
       "autoInstall": true,
       "timeoutMs": 600000,
-      "cleanupAfterIngest": true
+      "cleanupAfterIngest": true,
+      "cacheGeneratedIndexes": true
     }
   },
   "memory": {

package/config/sdlmcp.config.schema.json

@@ -33,7 +33,12 @@
               "**/dist/**",
               "**/dist-*/**",
               "**/build/**",
+              "**/build-*/**",
+              "**/build_*/**",
+              "**/cmake-build-*/**",
               "**/out/**",
+              "**/out-*/**",
+              "**/out_*/**",
               "**/target/**",
               "**/coverage/**",
               "**/node_modules/**",
@@ -91,6 +96,10 @@
             "minimum": 1,
             "default": 2000000
           },
+          "sourceFileListPath": {
+            "type": ["string", "null"],
+            "description": "Optional benchmark/tuning file list. When set, repository scanning uses these repo-relative source paths instead of walking the full tree."
+          },
           "postIndexSessionTimeoutMs": {
             "type": "integer",
             "description": "Hard timeout for post-index finalization writes in milliseconds. Covers embeddings, summaries, deferred index builds, memory sync, and audit flushing after pass-1/pass-2 complete.",
@@ -261,6 +270,104 @@
       "type": "object",
       "description": "Indexing behavior configuration",
       "properties": {
+        "pipeline": {
+          "type": "string",
+          "description": "Indexing pipeline selector. auto uses provider-first when SCIP or LSP coverage is configured, otherwise legacy.",
+          "enum": ["legacy", "providerFirst", "auto"],
+          "default": "auto"
+        },
+        "providerFirst": {
+          "type": "object",
+          "description": "Provider-first indexing options for SCIP/LSP-backed graph facts and shadow database activation.",
+          "properties": {
+            "activation": {
+              "type": "string",
+              "description": "Activation strategy for full provider-first builds.",
+              "enum": ["shadowDb"],
+              "default": "shadowDb"
+            },
+            "readyState": {
+              "type": "string",
+              "description": "Readiness gate for the first usable index state.",
+              "enum": ["graphPlusAlgorithms"],
+              "default": "graphPlusAlgorithms"
+            },
+            "stagingFormat": {
+              "type": "string",
+              "description": "Preferred provider fact staging format for shadow bulk loads. CSV is the fallback when Parquet is unavailable.",
+              "enum": ["parquet", "csv"],
+              "default": "parquet"
+            },
+            "maxLegacyFallbackFiles": {
+              "type": "integer",
+              "description": "Emergency cap for uncovered or provider-unusable files parsed by same-run legacy fallback after provider-first materialization. Defaults high so full provider-first runs build a complete graph; lower it only for partial iteration or resource protection.",
+              "minimum": 0,
+              "maximum": 1000000,
+              "default": 1000000
+            },
+            "maxSemanticEligibleFallbackFiles": {
+              "type": "integer",
+              "description": "Maximum semantic-eligible uncovered or provider-unusable files parsed when the full provider-first fallback gap exceeds maxLegacyFallbackFiles. The default of 0 avoids a misleading partial semantic subset when the main fallback cap was intentionally lowered or exceeded.",
+              "minimum": 0,
+              "maximum": 1000000,
+              "default": 0
+            },
+            "lsp": {
+              "type": "object",
+              "description": "Caps for primary LSP provider collection. LSP servers are consumed from configured commands; SDL-MCP does not install them.",
+              "properties": {
+                "mode": {
+                  "type": "string",
+                  "enum": ["primaryWithCaps"],
+                  "default": "primaryWithCaps"
+                },
+                "workspaceSymbolLimit": {
+                  "type": "integer",
+                  "minimum": 0,
+                  "maximum": 100000,
+                  "default": 5000
+                },
+                "documentSymbolFileLimit": {
+                  "type": "integer",
+                  "minimum": 0,
+                  "maximum": 50000,
+                  "default": 500
+                },
+                "referenceCandidateLimit": {
+                  "type": "integer",
+                  "minimum": 0,
+                  "maximum": 10000,
+                  "default": 200
+                },
+                "diagnosticsLimit": {
+                  "type": "integer",
+                  "minimum": 0,
+                  "maximum": 100000,
+                  "default": 5000
+                }
+              },
+              "default": {
+                "mode": "primaryWithCaps",
+                "workspaceSymbolLimit": 5000,
+                "documentSymbolFileLimit": 500,
+                "referenceCandidateLimit": 200,
+                "diagnosticsLimit": 5000
+              }
+            }
+          },
+          "default": {
+            "activation": "shadowDb",
+            "readyState": "graphPlusAlgorithms",
+            "stagingFormat": "parquet",
+            "lsp": {
+              "mode": "primaryWithCaps",
+              "workspaceSymbolLimit": 5000,
+              "documentSymbolFileLimit": 500,
+              "referenceCandidateLimit": 200,
+              "diagnosticsLimit": 5000
+            }
+          }
+        },
         "concurrency": {
           "type": "integer",
           "description": "Number of concurrent indexing workers",
@@ -304,15 +411,86 @@
           "minimum": 1,
           "maximum": 16,
           "default": 1
+        },
+        "algorithmRefresh": {
+          "type": "object",
+          "description": "Optional post-index graph algorithm refresh. Canonical clusters/processes always run; PageRank/K-core use a bounded worker and Louvain is skipped above maxCallEdges.",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "default": true
+            },
+            "pageRank": {
+              "type": "object",
+              "properties": {
+                "enabled": { "type": "boolean", "default": true }
+              },
+              "default": { "enabled": true }
+            },
+            "kCore": {
+              "type": "object",
+              "properties": {
+                "enabled": { "type": "boolean", "default": true }
+              },
+              "default": { "enabled": true }
+            },
+            "louvain": {
+              "type": "object",
+              "properties": {
+                "enabled": { "type": "boolean", "default": true },
+                "maxCallEdges": {
+                  "type": "integer",
+                  "minimum": 0,
+                  "default": 10000
+                }
+              },
+              "default": { "enabled": true, "maxCallEdges": 10000 }
+            },
+            "workerTimeoutMs": {
+              "type": "integer",
+              "minimum": 1000,
+              "maximum": 1800000,
+              "default": 120000
+            }
+          },
+          "default": {
+            "enabled": true,
+            "pageRank": { "enabled": true },
+            "kCore": { "enabled": true },
+            "louvain": { "enabled": true, "maxCallEdges": 10000 },
+            "workerTimeoutMs": 120000
+          }
         }
       },
       "default": {
+        "pipeline": "auto",
+        "providerFirst": {
+          "activation": "shadowDb",
+          "readyState": "graphPlusAlgorithms",
+          "stagingFormat": "parquet",
+          "maxLegacyFallbackFiles": 1000000,
+          "maxSemanticEligibleFallbackFiles": 0,
+          "lsp": {
+            "mode": "primaryWithCaps",
+            "workspaceSymbolLimit": 5000,
+            "documentSymbolFileLimit": 500,
+            "referenceCandidateLimit": 200,
+            "diagnosticsLimit": 5000
+          }
+        },
         "concurrency": 8,
         "enableFileWatching": true,
         "maxWatchedFiles": 25000,
         "engine": "rust",
         "watchDebounceMs": 300,
-        "pass2Concurrency": 1
+        "pass2Concurrency": 1,
+        "algorithmRefresh": {
+          "enabled": true,
+          "pageRank": { "enabled": true },
+          "kCore": { "enabled": true },
+          "louvain": { "enabled": true, "maxCallEdges": 10000 },
+          "workerTimeoutMs": 120000
+        }
       }
     },
     "liveIndex": {
@@ -530,12 +708,21 @@
           "type": "boolean",
           "description": "Require plugin API version compatibility",
           "default": true
+        },
+        "trustedRoots": {
+          "type": "array",
+          "description": "Trusted plugin directories. Relative roots resolve from the config file directory; plugin entrypoints must resolve inside one root after symlinks are resolved.",
+          "items": {
+            "type": "string"
+          },
+          "default": []
         }
       },
       "default": {
         "paths": [],
         "enabled": true,
-        "strictVersioning": true
+        "strictVersioning": true,
+        "trustedRoots": []
       }
     },
     "semantic": {
@@ -1023,11 +1210,31 @@
             "enabled": { "type": "boolean", "default": true },
             "mode": { "enum": ["observe", "safe"], "default": "safe" },
             "minSamples": { "type": "integer", "minimum": 1, "default": 20 },
-            "suppressionWasteRate": { "type": "number", "minimum": 0, "maximum": 1, "default": 0.8 },
-            "boostHitRate": { "type": "number", "minimum": 0, "maximum": 1, "default": 0.35 },
+            "suppressionWasteRate": {
+              "type": "number",
+              "minimum": 0,
+              "maximum": 1,
+              "default": 0.8
+            },
+            "boostHitRate": {
+              "type": "number",
+              "minimum": 0,
+              "maximum": 1,
+              "default": 0.35
+            },
             "retentionDays": { "type": "integer", "minimum": 1, "default": 14 },
-            "maxPriorityBoost": { "type": "integer", "minimum": 0, "maximum": 100, "default": 25 },
-            "maxBudgetTrimPercent": { "type": "integer", "minimum": 0, "maximum": 100, "default": 50 }
+            "maxPriorityBoost": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100,
+              "default": 25
+            },
+            "maxBudgetTrimPercent": {
+              "type": "integer",
+              "minimum": 0,
+              "maximum": 100,
+              "default": 50
+            }
           },
           "default": {
             "enabled": true,
@@ -1566,13 +1773,18 @@
             "timeoutMs": {
               "type": "integer",
               "minimum": 1000,
-              "maximum": 1800000,
+              "maximum": 18000000,
               "default": 600000
             },
             "cleanupAfterIngest": {
               "type": "boolean",
               "description": "Delete <repoRoot>/index.scip after the post-refresh ingest consumes it. The file is regenerated every refresh, so keeping it just clutters the working tree. Only the default output location is cleaned up — passing --output via args opts you out of cleanup automatically.",
               "default": true
+            },
+            "cacheGeneratedIndexes": {
+              "type": "boolean",
+              "description": "Cache generated SCIP artifacts by source/config fingerprint and reuse them on later unchanged refreshes. The cache invalidates when tracked source files, common build manifests, generator args, or the scip-io binary change.",
+              "default": true
             }
           },
           "default": {
@@ -1581,7 +1793,8 @@
             "args": [],
             "autoInstall": true,
             "timeoutMs": 600000,
-            "cleanupAfterIngest": true
+            "cleanupAfterIngest": true,
+            "cacheGeneratedIndexes": true
           }
         }
       }