weavatrix 1.1.2 → 1.3.0

package/README.md

@@ -1,4 +1,4 @@
-# Weavatrix — native MCP repository intelligence
+# Weavatrix — native MCP repository intelligence
 
 [![CI](https://github.com/sergii-ziborov/weavatrix/actions/workflows/ci.yml/badge.svg)](https://github.com/sergii-ziborov/weavatrix/actions/workflows/ci.yml)
 [![npm](https://img.shields.io/npm/v/weavatrix.svg)](https://www.npmjs.com/package/weavatrix)
@@ -8,7 +8,7 @@
 **Give your coding agent repository evidence before it starts guessing.**
 
 Weavatrix is the native MCP product for repository intelligence. It gives
-Codex, Claude Code, and other coding agents 39 read-only operations over one
+Codex, Claude Code, and other coding agents 42 read-only operations over one
 revision-bound evidence graph: impact, architecture, APIs, Git history,
 duplicates, dead code, search, semantic links, and temporal memory.
 
@@ -19,6 +19,8 @@ evidence kind, and confidence that produced it.
 This npm package is the convenient prebuilt distribution of the same native
 product published on crates.io as `weavatrix`. It is not a separate
 JavaScript engine; both registry packages run the same Rust adapter and engine.
+The separately versioned `weavatrix-js` package is a legacy compatibility
+implementation and is not bundled here.
 
 ## Install in 30 seconds
 
@@ -72,13 +74,13 @@ contract affected by this branch.
 Build the smallest source bundle needed to edit this symbol safely.
 ```
 
-## The 39 read-only operations
+## The 42 read-only operations
 
 | Workflow | Operations |
 | --- | --- |
-| Graph orientation | `graph_stats`, `get_node`, `get_neighbors`, `query_graph`, `god_nodes`, `shortest_path`, `get_community`, `list_communities`, `module_map` |
-| Change impact | `get_dependents`, `change_impact`, `verified_change`, `prepare_change`, `graph_diff` |
-| Exact source context | `search_code`, `read_source`, `inspect_symbol`, `context_bundle` |
+| Graph orientation | `graph_stats`, `get_node`, `get_neighbors`, `query_graph`, `god_nodes`, `shortest_path`, `get_community`, `list_communities`, `module_map`, `build_graph` |
+| Change impact | `get_dependents`, `change_impact`, `select_tests`, `verified_change`, `prepare_change`, `graph_diff` |
+| Exact source context | `search_code`, `read_source`, `inspect_symbol`, `context_bundle`, `map_stacktrace` |
 | Health and quality | `find_duplicates`, `find_dead_code`, `run_audit`, `coverage_map`, `hot_path_review` |
 | APIs and transports | `list_endpoints`, `trace_endpoint`, `trace_api_contract` |
 | Architecture | `get_architecture_contract`, `verify_architecture`, `explain_architecture_violation`, `propose_architecture_exception` |
@@ -108,12 +110,12 @@ coding agent
     |
     | MCP over stdio
     v
-weavatrix 1.1.2
-    profile catalog · refresh · watcher · MCP framing
+weavatrix 1.3.0
+    profile catalog · refresh · watcher · MCP framing
     |
     v
-weavatrix-rust 2.0.2
-    typed graph · analysis · 39 read-only operations
+weavatrix-rust 2.2.0
+    typed graph · analysis · 42 read-only operations
 ```
 
 This npm product owns MCP transport and native distribution. The
@@ -122,10 +124,13 @@ the reusable protocol-independent engine; it is not an MCP server.
 Its standalone diagnostic therefore reports `weavatrix-rust <engine-version>`,
 while this MCP product reports both its product and embedded-engine identities.
 
-Engine 2.0.2 keeps `find_duplicates` families internally consistent after
-test/classified/low-signal filters and `top_n` truncation. Families are rebuilt
-from the surviving pairs, so excluded members and dangling pair identifiers
-cannot remain in the result.
+Engine 2.2.0 makes three reports carry only what their evidence supports:
+`find_duplicates` reports the lines a clone covers completely and the byte
+range to check them by, `run_audit` runtime findings land on the line they
+matched, and `token_budget` is refused by the operations that cannot apply it
+rather than accepted and ignored. `find_duplicates` also gains
+`include_strings`, which compares the payloads of multi-line literals - inline
+SQL, embedded templates - that the code pass sees as a single token.
 
 ## Release evidence
 
@@ -133,17 +138,13 @@ The installed-package benchmark packs both products, installs them into
 isolated npm roots, starts fresh MCP processes with empty caches, and validates
 identity, advertised operations, results, and cleanup.
 
-The packaged 1.1.2 product (`weavatrix-rust` 2.0.2) passed the bounded native
-gate on 2026-07-30: 39 tools; cold initialize **405.770 ms**; `tools/list`
-**0.790 ms**; first `graph_stats` **54.880 ms**; and 1,000 hot `graph_stats`
-calls at **136.83 calls/s** with **0 failures**, p50 **7.610 ms**, p95
-**10.180 ms**, and p99 **12.230 ms**.
-
-The last published baseline (`weavatrix` 1.0.0 versus `weavatrix-js` 0.3.15)
-measured a **30.34x** median cold-boundary ratio and **156.10x** warm-call
-ratio. Those comparison numbers remain historical and are not presented as a
-fresh competitor benchmark; the current 1.1.2 gate is bounded and does not
-relabel them.
+The packaged 1.2.0 product (`weavatrix-rust` 2.1.1) was measured on 2026-08-03
+against installed `weavatrix-js` 0.3.15 on a real JavaScript service
+repository: paired cold-boundary median **32.06x** (spawn to first tool
+result: **157.34 ms** vs 5,068.22 ms) and warm tools/call median **36.85x**
+(**7.94 ms** vs 292.55 ms), passing the 24x cold and 30x warm release
+thresholds and sitting slightly above the 30.34x recorded for the 1.0.0
+baseline.
 
 Full evidence and methodology:
 [benchmarks](https://github.com/sergii-ziborov/weavatrix/blob/main/docs/benchmarks.md).

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "weavatrix",
-  "version": "1.1.2",
-  "weavatrixEngineVersion": "2.0.2",
-  "description": "Native repository intelligence for coding agents: 39 read-only MCP operations backed by typed evidence graphs, impact, architecture, APIs, Git, search, semantics, and memory.",
+  "version": "1.3.0",
+  "weavatrixEngineVersion": "2.2.0",
+  "description": "Native repository intelligence for coding agents: 42 read-only MCP operations backed by typed evidence graphs, impact, architecture, APIs, Git, search, semantics, and memory.",
   "author": "Sergii Ziborov <sergii.ziborov@gmail.com>",
   "license": "MIT",
   "homepage": "https://weavatrix.com",

package/server.json

@@ -1,20 +1,20 @@
-{
+{
   "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
   "name": "io.github.sergii-ziborov/weavatrix",
   "title": "Weavatrix",
-  "description": "Native Weavatrix MCP: 39 read-only repository tools across 24 code and configuration surfaces.",
+  "description": "Native Weavatrix MCP: 42 read-only repository tools across 24 code and configuration surfaces.",
   "repository": {
     "url": "https://github.com/sergii-ziborov/weavatrix",
     "source": "github"
   },
-  "version": "1.1.2",
+  "version": "1.3.0",
   "websiteUrl": "https://weavatrix.com",
   "packages": [
     {
       "registryType": "npm",
       "registryBaseUrl": "https://registry.npmjs.org",
       "identifier": "weavatrix",
-      "version": "1.1.2",
+      "version": "1.3.0",
       "runtimeHint": "npx",
       "transport": {
         "type": "stdio"

package/skill/references/tool-routing.md

@@ -4,14 +4,24 @@
 
 - `graph_stats`: repository identity, freshness, counts, and evidence.
 - `module_map`, `list_communities`, `get_community`, `god_nodes`: topology.
+- `build_graph`: workspace aggregators, members, targets, and runner
+  configurations from manifest evidence; no build tool runs.
 - `get_node`, `get_neighbors`, `inspect_symbol`, `context_bundle`: exact
   entities and local evidence.
 - `query_graph`, `shortest_path`, `get_dependents`: bounded traversal.
 - `search_code`, `read_source`: lexical and source confirmation.
+- `map_stacktrace`: paste a Node, JVM, Python, or Rust stack trace; frames map
+  to repository files and the nearest symbol, so debugging starts at the graph
+  instead of at a directory listing.
+- Pass `token_budget` on `search_code`, `read_source`, `context_bundle`, or
+  `query_graph` to fit the answer into the context window you have left; the
+  report states exactly what was dropped.
 
 ## Change and history
 
 - `change_impact`: current diff, explicit files, or supplied patch.
+- `select_tests`: the suites a change most plausibly needs to run, ranked by
+  graph distance; static selection, no coverage run consumed.
 - `graph_diff`: structural comparison with an immutable Git revision.
 - `git_history`: churn and co-change in one repository.
 - `cross_repo_git`: histories, shared commits, or diffs across repositories.