weavatrix-refactor 1.0.13

Native MCP refactoring extension: proven edit plans, transactional application, and rollback
weavatrix-refactor-1.0.13 is not a library.

Weavatrix Refactor

CI npm crates.io docs.rs MIT

The explicit source-write layer of the Weavatrix ecosystem; Core remains read-only.

Refactor across files without letting the agent guess.

Weavatrix Refactor is a native MCP server for coding agents. It finds a symbol through the repository graph, previews byte-exact edits, reports every same-named occurrence it could not prove, and writes only after an explicit, hash-bound confirmation.

The useful difference is not “AI can rename a word.” It is that the agent gets evidence before the write and a recoverable transaction after it.

Install

Run the native binary through npm:

npx -y weavatrix-refactor mcp /absolute/path/to/repository

Or install it with Cargo:

cargo install weavatrix-refactor --locked

weavatrix-refactor mcp /absolute/path/to/repository

An MCP client can start it directly. Prefer an absolute path, or Cursor's ${workspaceFolder} so the write server never follows the host process cwd:

{
  "mcpServers": {
    "weavatrix-refactor": {
      "command": "npx",
      "args": ["-y", "weavatrix-refactor@1.0.13", "mcp", "${workspaceFolder}", "--profile=refactor"],
      "env": {"WEAVATRIX_ALLOW_SOURCE_EDITS": "1"}
    }
  }
}

Leave WEAVATRIX_ALLOW_SOURCE_EDITS unset for preview-only sessions. Preview is a read; only a confirmed apply or rollback requires the gate. One process serves many calls at once. A call passes repository to select a child of the launch root; each child has its own graph, confirm token, and rollback, and a token from one child does not apply to another. Refactor does not expose Core's open_repo. A path outside the launch root needs --allow-retarget.

Install as a plugin

The repository also ships one plugin bundle for Cursor, Codex, Claude Code, and Grok Build. The plugin starts the extension-only profile, so it contributes the 12 Refactor methods without repeating Weavatrix Core's 43 read-only method definitions. Install the separate Weavatrix plugin when both surfaces are needed.

The bundled skill is optional and activates only for explicitly requested refactoring work. Its entry point stays short; each method has an individual reference card that is loaded only when needed.

  • Cursor: search for Weavatrix Refactor after marketplace approval.
  • Codex: add the Weavatrix/weavatrix-refactor marketplace from .agents/plugins, then add weavatrix-refactor@weavatrix-refactor.
  • Claude Code: add the same repository marketplace from .claude-plugin, then install weavatrix-refactor@weavatrix-refactor.
  • Grok Build: run grok plugin marketplace add Weavatrix/weavatrix-refactor, open /marketplace, and install it.

The plugin opens WEAVATRIX_ALLOW_SOURCE_EDITS=1, but every write still needs the exact preview's short-lived, plan-bound single-use token.

For a rename task, expose only the two tools the agent needs:

weavatrix-refactor mcp /absolute/path/to/repository --profile=rename

The rename profile keeps rename_symbol and rollback_last_apply; every unrelated graph and refactor tool is absent and cannot be called. Omit the option (or use --profile=refactor) for all 12 Refactor methods. The narrower catalog reduces repeated agent context; it does not weaken preview hashes, the write gate, the confirmation token, or rollback checks.

When Weavatrix Core is already installed as a separate MCP, expose only the 12 methods that Refactor adds:

weavatrix-refactor mcp /absolute/path/to/repository --profile=refactor

The refactor profile is the default for MCP and list-tools, including the marketplace plugin. The former full compatibility profile has been removed and is rejected by both commands: Refactor no longer republishes Core methods. Install Weavatrix Core as its own MCP when read-only repository intelligence is also needed.

A safe cross-file rename in three calls

Suppose two files declare resolveTarget. A bare name is ambiguous, so the server refuses to pick one and returns exact ids:

// rename_symbol
{"symbol":"resolveTarget","new_name":"locateTarget","output_format":"json"}

{
  "status": "NOT_FOUND",
  "reason": "the name matches more than one symbol; pass one of the candidate ids",
  "candidates": [
    "symbol:src/core.ts#function:resolveTarget@2:1",
    "symbol:src/shadow.ts#function:resolveTarget@3:1"
  ]
}

Retry with the intended id. The result is still read-only: it contains the edit plan, content hashes, the proven edit count, and the references the backend refused to guess at.

// rename_symbol
{
  "symbol": "symbol:src/core.ts#function:resolveTarget@2:1",
  "new_name": "locateTarget",
  "output_format": "json"
}

{
  "status": "PLANNED",
  "completeness": "PARTIAL",
  "renamedEdits": 7,
  "uncertainReferences": ["... three named locations ..."],
  "confirmToken": "single-use-token",
  "plan": {"schemaVersion":"weavatrix.edit-plan.v1","files":["..."]}
}

After reviewing the plan, repeat the same operation with the same inputs and its token:

// rename_symbol
{
  "symbol": "symbol:src/core.ts#function:resolveTarget@2:1",
  "new_name": "locateTarget",
  "mode": "apply",
  "confirm_token": "single-use-token",
  "output_format": "json"
}

{"status":"APPLIED"}

This exact flow is exercised against the real stdio MCP server. The repository fixture requires seven edits across three files, preserves four traps (a longer identifier, string, comment, and unrelated shadow), and must still compile; it scores 12/12.

What is automatic today

The twelve tools do not all claim the same level of automation:

Level Tools What the agent receives
Complete preview/apply workflow rename_symbol, rename_related_symbols A generated plan and token, then a confirmed write by repeating the same operation
Plan-producing change_signature, edit_symbol, bulk_replace, organize_imports, move_file, move_symbol, delete_closure Byte-exact edits or a review plan; use apply_edit_plan where an edit-plan envelope is returned
Advisory delete_readiness A deletion verdict. A private unused symbol can be safe: true. The verdict stays REVIEW_REQUIRED and nothing is written
Safety infrastructure apply_edit_plan, rollback_last_apply Verification/application of an edit-plan envelope and drift-safe restoration

Refactor uses the Rust Weavatrix graph internally for evidence but never exports Core methods. Install the separate Weavatrix plugin for read-only repository intelligence. The Refactor MCP owns exactly its 12 extension methods; --profile=rename is an optional narrower two-method workflow.

Safety model and exact limits

  • Ambiguous names fail with candidate ids instead of selecting the first match.
  • PARTIAL means the graph proved the edits in the plan but did not prove that no other semantic references exist. uncertainReferences names the places requiring review.
  • Every file in a plan carries a content hash. A changed working tree makes the preview stale instead of applying the old coordinates.
  • Apply requires WEAVATRIX_ALLOW_SOURCE_EDITS=1 plus a short-lived, single-use token bound to that repository and exact recomputed plan.
  • rollback_last_apply refuses to overwrite files that drifted after the transaction.
  • Multi-file writes are journaled and crash-recoverable. They are not observationally atomic to unrelated processes: another process may briefly observe an intermediate filesystem state.

Only edits with proven provenance are applied. A lexical or graph backend is deliberately more conservative than a language server and must not be read as a claim of full compiler semantics.

What 1.0.13 actually returns

  • delete_closure plans a symbol, an endpoint, or a file. A repository returns BLOCKED. Exclusive mode returns BLOCKED when another file still imports the selected file. A module, a package, or any other symbol with no source span returns NOT_A_SYMBOL. A handler on the following line of an unclosed call is part of that route, including a uniquely named handler in another file. A closer line may end with a // or /* */ comment. Exclusive mode keeps a shared handler and every other route. Connected mode also takes direct referrers.
  • organize_imports removes a named binding whose identifier occurs once. JavaScript and TypeScript default and namespace imports stay uncertain. A Rust snake_case use, a Python from import or alias, and a Go path segment are removed when unused. A CamelCase Rust import such as use std::io::Write, a pub use, a bare Python import, and a Go blank or dot import stay. A file whose language has no recognised import syntax returns NO_UNUSED_IMPORTS.
  • bulk_replace matches indexed code. Comments and strings are included only when include_trivia is true.
  • change_signature adds or removes a parameter in every indexed language. A typed language copies the previous parameter's type. With a default, existing calls stay. Without one, those calls are listed unless a call-site value is given.
  • move_file renames the file and rewrites relative specifiers in one transaction. A missing parent directory is created at apply and left in place on rollback.
  • edit_symbol ends the declaration at the matching brace, the indent block, or the signature line, and the plan warns that syntax was not checked.
  • move_symbol returns a cycle review and an edit plan that cuts the declaration into the destination file.
  • delete_readiness can report safe: true for a private unused symbol. The verdict stays REVIEW_REQUIRED and nothing is written. A route label is renamed as a path literal. A missing span on a rename is NOT_A_SYMBOL.

Measured benchmark, with unlike layers kept separate

The checked-in August 2026 benchmark uses equivalent adversarial TypeScript, Rust, and Python fixtures. Each has seven required edits, four traps, and a build/test gate. Protocol runs count exact o200k_base initialization, catalog, request, and response tokens. Agent runs use the actual cumulative usage reported by Codex CLI with pinned gpt-5.6-sol / medium reasoning. No byte proxy or estimated tokens-per-second conversion is used.

The new rename-only profile kept all nine protocol runs at 12/12 while reducing fixed MCP context from 9,331 to 485 tokens. Its guided TypeScript agent A/B is:

Arm Correctness Median end-to-end Median input tokens
Naked Codex 12/12 x3 42,602 ms 72,169
Weavatrix 1.0.6 --profile=rename 12/12 x3 48,389 ms 108,155
Weavatrix 1.0.5 full surface 12/12 x3 58,719 ms 275,784
Serena 12/12 x3 68,728 ms 388,271

The full agent matrix is 12/12 in all 27 TypeScript/Rust/Python runs; every run also completed operationally and passed the sanitized edit-channel audit. The deterministic protocol matrix also exposed a language-specific Serena defect: its suggested find_symbol → rename_symbol flow scored 7/12 on TypeScript in all three runs, while Rust and Python passed. It also found and drove fixes for Rust macro calls and Python f-string/module-level call evidence.

On this toy TypeScript repository naked Codex is still faster and cheaper than the narrowed profile. Weavatrix's demonstrated value is preview-before-write, named uncertainty, stale-plan refusal, explicit authorization, and rollback—not a universal small-repository token win.

See the full methodology, all language medians, raw-result links, and limitations.

Contract

The 12 Refactor tool names, schemas, and result states are frozen in contract/refactor-tools.v1.json. All refactor operations are native Rust; the host uses the read-only weavatrix-rust engine internally for graph evidence without exporting its methods on the default surface.

Versions 0.1.x used the JavaScript engine. That line continues as weavatrix-refactor-js and keeps a separate state directory, token store, and rollback journal.

License

MIT.