Files
openclaw/docs/tools/apply-patch.md
Yuval Dinodia edf4aca7bc fix(agents): apply_patch destroys an existing file when a patch creates that path (#114911)
* fix(agents): stop apply_patch from silently overwriting existing files

An "*** Add File:" hunk wrote its target unconditionally. When the path
already existed, apply_patch replaced the entire file, returned Success,
and listed the path under "added", so neither the model nor the UI got
any signal that existing content had been destroyed. The "*** Move to:"
destination of an update hunk had the same gap and reported the clobbered
path as merely modified.

The add and move-to branches now check the destination through the patch
file ops before writing and fail closed when it exists. Routing the check
through fileOps keeps it correct on all three backends (workspace-scoped
fs-safe root, raw fs, sandbox bridge). The check runs per hunk in patch
order, so deleting a path earlier in the same patch and recreating it
still works.

* fix(agents): make apply_patch destination creation atomic

The previous guard checked that an add or move-to destination was absent
and then wrote it. A competing writer could create the path in that gap,
after which the write still replaced it, so the no-clobber guarantee did
not hold under contention.

Destination creation now goes through a single exclusive create-if-absent
operation on every patch backend: Root.create for the workspace-scoped
default, an O_EXCL write for the raw filesystem, and a new pinned create
operation in the sandbox mutation helper that opens the target with
O_CREAT|O_EXCL and reports a reserved exit code when it already exists.
PatchFileOps drops its separate existence check.

Resolving the host ops behind an early return removes the repeated
workspaceOnly branch inside each operation and the optional-call dance
that let a missing root silently skip a write.

* fix(agents): complete atomic apply-patch creation

* fix(agents): preserve raced create replacements

* fix(agents): handle fs-safe patch collisions

* fix(agents): publish sandbox creates atomically

* test(agents): cover exclusive create provenance rollback

* fix(agents): use typed exclusive-create signal

---------

Co-authored-by: Vincent Koc <vincentkoc@ieee.org>
2026-07-29 20:17:54 +08:00

2.2 KiB

summary, read_when, title
summary read_when title
Apply multi-file patches with the apply_patch tool
You need structured file edits across multiple files
You want to document or debug patch-based edits
apply_patch tool

Apply file changes using a structured patch format. This is ideal for multi-file or multi-hunk edits where a single edit call would be brittle.

The tool accepts a single input string that wraps one or more file operations:

*** Begin Patch
*** Add File: path/to/file.txt
+line 1
+line 2
*** Update File: src/app.ts
@@ optional change context
-old line
+new line
*** Delete File: obsolete.txt
*** End Patch

Parameters

  • input (required): Full patch contents including *** Begin Patch and *** End Patch.

Notes

  • Patch paths support relative paths (from the workspace directory) and absolute paths.
  • tools.exec.applyPatch.workspaceOnly defaults to true (workspace-contained). Set it to false only if you intentionally want apply_patch to write/delete outside the workspace directory.
  • *** Add File: and a non-self *** Move to: require the destination path to be absent. To intentionally replace a path, delete it earlier in the same patch before adding or moving the replacement.
  • Use *** Move to: within an *** Update File: hunk to rename files.
  • *** End of File marks an EOF-only insert when needed.
  • Enabled by default for every model. Set tools.exec.applyPatch.enabled: false to disable it, or restrict it to specific models with tools.exec.applyPatch.allowModels (accepts raw ids like gpt-5.4 or full ids like openai/gpt-5.4).
  • Config lives under tools.exec.applyPatch.*.

Example

{
  "tool": "apply_patch",
  "input": "*** Begin Patch\n*** Update File: src/index.ts\n@@\n-const foo = 1\n+const foo = 2\n*** End Patch"
}
Read-only diff viewer for change presentation. Shell command execution from the agent. Sandboxed remote Python analysis with xAI.