LLM/moltbot
1
0
Fork 0
mirror of https://github.com/moltbot/moltbot.git synced 2026-04-26 16:06:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: default and gate apply_patch like write

Browse Source
This commit is contained in:
Peter Steinberger
2026-03-27 01:02:20 +00:00
parent c326083ad8
commit b9c60fd37a
13 changed files with 85 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/tools/apply-patch.md
View File

@@ -36,8 +36,9 @@ The tool accepts a single `input` string that wraps one or more file operations:
- `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.
- Use `*** Move to:` within an `*** Update File:` hunk to rename files.
- `*** End of File` marks an EOF-only insert when needed.
- Experimental and disabled by default. Enable with `tools.exec.applyPatch.enabled`.
- OpenAI-only (including OpenAI Codex). Optionally gate by model via
- Available by default for OpenAI and OpenAI Codex models. Set
`tools.exec.applyPatch.enabled: false` to disable it.
- Optionally gate by model via
`tools.exec.applyPatch.allowModels`.
- Config is only under `tools.exec`.

10
docs/tools/exec.md
View File

@@ -184,16 +184,17 @@ Paste (bracketed by default):
{ "tool": "process", "action": "paste", "sessionId": "<id>", "text": "line1\nline2\n" }
```
## apply_patch (experimental)
## apply_patch
`apply_patch` is a subtool of `exec` for structured multi-file edits.
Enable it explicitly:
It is enabled by default for OpenAI and OpenAI Codex models. Use config only
when you want to disable it or restrict it to specific models:
```json5
{
tools: {
exec: {
applyPatch: { enabled: true, workspaceOnly: true, allowModels: ["gpt-5.2"] },
applyPatch: { workspaceOnly: true, allowModels: ["gpt-5.2"] },
},
},
}
@@ -202,6 +203,7 @@ Enable it explicitly:
Notes:
- Only available for OpenAI/OpenAI Codex models.
- Tool policy still applies; `allow: ["exec"]` implicitly allows `apply_patch`.
- Tool policy still applies; `allow: ["write"]` implicitly allows `apply_patch`.
- Config lives under `tools.exec.applyPatch`.
- `tools.exec.applyPatch.enabled` defaults to `true`; set it to `false` to disable the tool for OpenAI models.
- `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.