sdl-mcp 0.11.7 → 0.11.9

package/README.md

@@ -67,14 +67,25 @@ SDL-MCP fixes this. It indexes your codebase into a searchable **symbol graph**
 ```bash
 # Install (requires Node.js 24+)
 npm install -g sdl-mcp
+# Plain npm installs run lifecycle scripts in the background, so run
+# `sdl-mcp init` after install. Use `--foreground-scripts` only when you
+# specifically want npm to show the install-time wizard and lifecycle output.
 
-# Initialize, auto-detect languages, index your repo, and run health checks
+# Non-interactive setup: initialize, auto-detect languages, index, and run health checks
 sdl-mcp init -y --auto-index
 
 # Start the MCP server for your coding agent
 sdl-mcp serve --stdio
 ```
 
+For a clean foreground installer flow, use the tiny wrapper package:
+
+```bash
+npx create-sdl-mcp
+```
+
+Run `npx create-sdl-mcp --update` for the fast update path: it installs the server binaries, skips repo setup, and prints the repo-init commands to run later.
+
 Point your MCP client at the server and the agent gains access to SDL-MCP's current configured surface. By default that is exclusive Code Mode; set `codeMode.exclusive: false` when you want Code Mode plus the regular flat or gateway tools in one session.
 
 > **npx users:** Replace `sdl-mcp` with `npx --yes sdl-mcp@latest` in all commands above.
@@ -273,7 +284,7 @@ When enabled, memories are **automatically surfaced** inside graph slices — wh
 
 ### SCIP Integration — Compiler-Grade Cross-References
 
-Tree-sitter gives SDL-MCP fast, syntax-level symbol extraction across the built-in TypeScript/JavaScript, Python, Go, Java, C#, C/C++, Rust, and Kotlin surface. PHP and Shell/Bash are explicit opt-in language packs for LSP provider-first work and are not enabled by default. SCIP (Source Code Intelligence Protocol) supplements this with **compiler-grade cross-references** from tools like scip-typescript, scip-go, and rust-analyzer. Generate a `.scip` index file, point SDL-MCP at it, and heuristic edges are upgraded to exact compiler-verified edges, external dependency symbols become first-class graph nodes, and new `implements` edges reveal interface/trait relationships that syntax analysis cannot discover.
+Tree-sitter gives SDL-MCP fast, syntax-level symbol extraction across the built-in TypeScript/JavaScript, Python, Go, Java, C#, C/C++, Rust, and Kotlin surface. PHP and Shell/Bash are explicit opt-in language packs for LSP provider-first work and are not enabled by default. SCIP (Source Code Intelligence Protocol) supplies **compiler-grade cross-references** from tools like scip-typescript, scip-go, and rust-analyzer. When `scip.enabled` is true, SDL-MCP uses provider-first indexing to materialize those facts directly, with legacy parsing retained only for uncovered or provider-unusable files.
 
 ![SCIP integration compiler cross-reference ingestion flow](./docs/readme-assets/readme-scip-integration.webp)
 
@@ -282,7 +293,7 @@ Tree-sitter gives SDL-MCP fast, syntax-level symbol extraction across the built-
 - Upgrades heuristic call resolution to **compiler-verified exact edges** (confidence 0.95)
 - External dependencies (npm packages, Go modules, crate deps) become searchable graph nodes
 - Interface/trait implementations tracked via `implements` edges
-- Auto-ingest on `sdl.index.refresh` keeps SCIP data current with zero manual steps
+- Provider-first indexing keeps SCIP/LSP facts owned by the provider path; legacy indexing does not ingest `.scip` overlays
 - Complementary: tree-sitter provides structure, SCIP provides semantic precision
 
 [SCIP Integration Deep Dive →](./docs/feature-deep-dives/scip-integration.md)
@@ -422,9 +433,6 @@ The generated source of truth is [`docs/generated/tool-inventory.md`](./docs/gen
 <tr><td><code>sdl.workflow</code></td><td>Multi-step operations with budget tracking, ETag caching, and transforms</td></tr>
 <tr><td><code>sdl.manual</code></td><td>Self-documentation — query usage guide, action schemas, output format reference</td></tr>
 
-<tr><td><strong>SCIP</strong></td>
-    <td><code>sdl.scip.ingest</code></td><td>Ingest a pre-built SCIP index for compiler-grade cross-references (with dry-run support)</td></tr>
-
 <tr><td rowspan="2"><strong>File</strong></td>
     <td><code>sdl.file.read</code></td><td>Read non-indexed files (configs, docs, templates) with line-range, search, or JSON-path modes</td></tr>
 <tr><td><code>sdl.file.write</code></td><td>Policy-aware write helper for non-indexed files and templates</td></tr>
@@ -556,7 +564,7 @@ A **VSCode extension** (`sdl-mcp-vscode/`) provides live buffer integration for
 | [Semantic Embeddings Setup](./docs/feature-deep-dives/semantic-embeddings-setup.md) | Dependencies, model installation, provider configuration, tier-by-tier setup          |
 | [Code Mode](./docs/feature-deep-dives/code-mode.md)                                 | `sdl.context`, `sdl.workflow`, action discovery, manual reference, one-call workflows |
 | [Development Memories](./docs/feature-deep-dives/development-memories.md)           | Graph-backed cross-session memory, file sync, staleness detection, auto-surfacing     |
-| [SCIP Integration](./docs/feature-deep-dives/scip-integration.md)                   | Compiler-grade cross-references, external deps, implements edges, auto-ingest         |
+| [SCIP Integration](./docs/feature-deep-dives/scip-integration.md)                   | Provider-first compiler-grade cross-references, external deps, implements edges       |
 | [Token Savings Meter](./docs/feature-deep-dives/token-savings-meter.md)             | Per-call meter, session summaries, lifetime tracking, `sdl.usage.stats`               |
 
 <br/>

package/config/sdlmcp.config.example.json

@@ -94,6 +94,7 @@
         "diagnosticsTimeoutMs": 5000
       }
     },
+    "watchProvider": "auto",
     "concurrency": 8,
     "enableFileWatching": true,
     "maxWatchedFiles": 25000,

package/config/sdlmcp.config.json

@@ -121,6 +121,7 @@
   "indexing": {
     "concurrency": 4,
     "enableFileWatching": true,
+    "watchProvider": "auto",
     "maxWatchedFiles": 25000
   },
   "slice": {

package/config/sdlmcp.config.schema.json

@@ -405,6 +405,12 @@
             }
           }
         },
+        "watchProvider": {
+          "type": "string",
+          "description": "File watcher event source. auto tries Watchman, then Chokidar, then fs.watch. Explicit providers fail visibly when unavailable.",
+          "enum": ["auto", "watchman", "chokidar", "fsWatch"],
+          "default": "auto"
+        },
         "concurrency": {
           "type": "integer",
           "description": "Number of concurrent indexing workers",
@@ -519,6 +525,7 @@
             "diagnosticsTimeoutMs": 5000
           }
         },
+        "watchProvider": "auto",
         "concurrency": 8,
         "enableFileWatching": true,
         "maxWatchedFiles": 25000,
@@ -1837,7 +1844,7 @@
             },
             "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.",
+              "description": "Deprecated compatibility field for legacy post-refresh SCIP ingest cleanup. Provider-first does not delete generated indexes after collection.",
               "default": true
             },
             "cacheGeneratedIndexes": {