feat(agent): add fuzzy whitespace matching to edit_files tool (#22446)

Inspired by openai/codex's `apply_patch` implementation, this changes the `edit_files` search-and-replace to use a cascading match strategy when the exact search string isn't found: 1. **Exact substring match** (byte-for-byte) — existing behavior, unchanged 2. **Line-by-line match ignoring trailing whitespace** — handles trailing spaces/tabs the LLM omits 3. **Line-by-line match ignoring all leading/trailing whitespace** — handles tabs-vs-spaces and wrong indentation depth ## Problem When the chat agent uses `edit_files`, it generates a search string that must match the file content exactly. LLMs frequently get whitespace wrong: - Emitting spaces when the file uses tabs (or vice versa) - Getting the indentation depth wrong by one or more levels - Omitting trailing whitespace that exists in the file When this happens, the edit silently does nothing, and the agent falls into a retry loop using `cat -A` to diagnose the exact whitespace characters. ## Solution Adopted the same cascading fuzzy match strategy that [openai/codex uses in `seek_sequence.rs`](https://github.com/openai/codex/blob/main/codex-rs/apply-patch/src/seek_sequence.rs): - Pass 1: exact match (existing behavior) - Pass 2: `TrimRight` each line before comparing (trailing whitespace tolerance) - Pass 3: `TrimSpace` each line before comparing (full indentation tolerance) When a fuzzy match is found, the matched lines in the original file are replaced with the replacement text. This preserves surrounding content exactly. ## Changes - `agent/agentfiles/files.go`: Replaced `icholy/replace` streaming transformer with in-memory `fuzzyReplace` + helper functions (`seekLines`, `spliceLines`) - `agent/agentfiles/files_test.go`: Added 6 new test cases covering trailing whitespace, tabs-vs-spaces, different indent depths, exact match preference, no-match behavior, and mixed whitespace multiline edits - Removed `icholy/replace` dependency from go.mod/go.sum --------- Co-authored-by: Kyle Carberry <kylecarbs@users.noreply.github.com>
2026-06-02 20:48:20 +00:00 · 2026-02-28 17:02:57 -05:00
parent 22d4539a7a
commit 5945febf06
4 changed files with 206 additions and 15 deletions
@@ -13,9 +13,7 @@ import (
 	"strings"
 	"syscall"

-	"github.com/icholy/replace"
 	"github.com/spf13/afero"
-	"golang.org/x/text/transform"
 	"golang.org/x/xerrors"

 	"cdr.dev/slog/v3"
@@ -422,9 +420,21 @@ func (api *API) editFile(ctx context.Context, path string, edits []workspacesdk.
 		return http.StatusBadRequest, xerrors.Errorf("open %s: not a file", path)
 	}

-	transforms := make([]transform.Transformer, len(edits))
-	for i, edit := range edits {
-		transforms[i] = replace.String(edit.Search, edit.Replace)
+	data, err := io.ReadAll(f)
+	if err != nil {
+		return http.StatusInternalServerError, xerrors.Errorf("read %s: %w", path, err)
+	}
+	content := string(data)
+
+	for _, edit := range edits {
+		var ok bool
+		content, ok = fuzzyReplace(content, edit.Search, edit.Replace)
+		if !ok {
+			api.logger.Warn(ctx, "edit search string not found, skipping",
+				slog.F("path", path),
+				slog.F("search_preview", truncate(edit.Search, 64)),
+			)
+		}
 	}

 	// Create an adjacent file to ensure it will be on the same device and can be
@@ -435,8 +445,7 @@ func (api *API) editFile(ctx context.Context, path string, edits []workspacesdk.
 	}
 	defer tmpfile.Close()

-	_, err = io.Copy(tmpfile, replace.Chain(f, transforms...))
-	if err != nil {
+	if _, err := tmpfile.Write([]byte(content)); err != nil {
 		if rerr := api.filesystem.Remove(tmpfile.Name()); rerr != nil {
 			api.logger.Warn(ctx, "unable to clean up temp file", slog.Error(rerr))
 		}
@@ -450,3 +459,93 @@ func (api *API) editFile(ctx context.Context, path string, edits []workspacesdk.

 	return 0, nil
 }
+
+// fuzzyReplace attempts to find `search` inside `content` and replace its first
+// occurrence with `replace`. It uses a cascading match strategy inspired by
+// openai/codex's apply_patch:
+//
+//  1. Exact substring match (byte-for-byte).
+//  2. Line-by-line match ignoring trailing whitespace on each line.
+//  3. Line-by-line match ignoring all leading/trailing whitespace (indentation-tolerant).
+//
+// When a fuzzy match is found (passes 2 or 3), the replacement is still applied
+// at the byte offsets of the original content so that surrounding text (including
+// indentation of untouched lines) is preserved.
+//
+// Returns the (possibly modified) content and a bool indicating whether a match
+// was found.
+func fuzzyReplace(content, search, replace string) (string, bool) {
+	// Pass 1 – exact substring (replace all occurrences).
+	if strings.Contains(content, search) {
+		return strings.ReplaceAll(content, search, replace), true
+	}
+
+	// For line-level fuzzy matching we split both content and search into lines.
+	contentLines := strings.SplitAfter(content, "\n")
+	searchLines := strings.SplitAfter(search, "\n")
+
+	// A trailing newline in the search produces an empty final element from
+	// SplitAfter.  Drop it so it doesn't interfere with line matching.
+	if len(searchLines) > 0 && searchLines[len(searchLines)-1] == "" {
+		searchLines = searchLines[:len(searchLines)-1]
+	}
+
+	// Pass 2 – trim trailing whitespace on each line.
+	if start, end, ok := seekLines(contentLines, searchLines, func(a, b string) bool {
+		return strings.TrimRight(a, " \t\r\n") == strings.TrimRight(b, " \t\r\n")
+	}); ok {
+		return spliceLines(contentLines, start, end, replace), true
+	}
+
+	// Pass 3 – trim all leading and trailing whitespace (indentation-tolerant).
+	if start, end, ok := seekLines(contentLines, searchLines, func(a, b string) bool {
+		return strings.TrimSpace(a) == strings.TrimSpace(b)
+	}); ok {
+		return spliceLines(contentLines, start, end, replace), true
+	}
+
+	return content, false
+}
+
+// seekLines scans contentLines looking for a contiguous subsequence that matches
+// searchLines according to the provided `eq` function. It returns the start and
+// end (exclusive) indices into contentLines of the match.
+func seekLines(contentLines, searchLines []string, eq func(a, b string) bool) (start, end int, ok bool) {
+	if len(searchLines) == 0 {
+		return 0, 0, true
+	}
+	if len(searchLines) > len(contentLines) {
+		return 0, 0, false
+	}
+outer:
+	for i := 0; i <= len(contentLines)-len(searchLines); i++ {
+		for j, sLine := range searchLines {
+			if !eq(contentLines[i+j], sLine) {
+				continue outer
+			}
+		}
+		return i, i + len(searchLines), true
+	}
+	return 0, 0, false
+}
+
+// spliceLines replaces contentLines[start:end] with replacement text, returning
+// the full content as a single string.
+func spliceLines(contentLines []string, start, end int, replacement string) string {
+	var b strings.Builder
+	for _, l := range contentLines[:start] {
+		_, _ = b.WriteString(l)
+	}
+	_, _ = b.WriteString(replacement)
+	for _, l := range contentLines[end:] {
+		_, _ = b.WriteString(l)
+	}
+	return b.String()
+}
+
+func truncate(s string, n int) string {
+	if len(s) <= n {
+		return s
+	}
+	return s[:n] + "..."
+}
@@ -649,6 +649,106 @@ func TestEditFiles(t *testing.T) {
 				filepath.Join(tmpdir, "file3"): "edited3 3",
 			},
 		},
+		{
+			name:     "TrailingWhitespace",
+			contents: map[string]string{filepath.Join(tmpdir, "trailing-ws"): "foo   \nbar\t\t\nbaz"},
+			edits: []workspacesdk.FileEdits{
+				{
+					Path: filepath.Join(tmpdir, "trailing-ws"),
+					Edits: []workspacesdk.FileEdit{
+						{
+							Search:  "foo\nbar\nbaz",
+							Replace: "replaced",
+						},
+					},
+				},
+			},
+			expected: map[string]string{filepath.Join(tmpdir, "trailing-ws"): "replaced"},
+		},
+		{
+			name:     "TabsVsSpaces",
+			contents: map[string]string{filepath.Join(tmpdir, "tabs-vs-spaces"): "\tif true {\n\t\tfoo()\n\t}"},
+			edits: []workspacesdk.FileEdits{
+				{
+					Path: filepath.Join(tmpdir, "tabs-vs-spaces"),
+					Edits: []workspacesdk.FileEdit{
+						{
+							// Search uses spaces but file uses tabs.
+							Search:  "    if true {\n        foo()\n    }",
+							Replace: "\tif true {\n\t\tbar()\n\t}",
+						},
+					},
+				},
+			},
+			expected: map[string]string{filepath.Join(tmpdir, "tabs-vs-spaces"): "\tif true {\n\t\tbar()\n\t}"},
+		},
+		{
+			name:     "DifferentIndentDepth",
+			contents: map[string]string{filepath.Join(tmpdir, "indent-depth"): "\t\t\tdeep()\n\t\t\tnested()"},
+			edits: []workspacesdk.FileEdits{
+				{
+					Path: filepath.Join(tmpdir, "indent-depth"),
+					Edits: []workspacesdk.FileEdit{
+						{
+							// Search has wrong indent depth (1 tab instead of 3).
+							Search:  "\tdeep()\n\tnested()",
+							Replace: "\t\t\tdeep()\n\t\t\tchanged()",
+						},
+					},
+				},
+			},
+			expected: map[string]string{filepath.Join(tmpdir, "indent-depth"): "\t\t\tdeep()\n\t\t\tchanged()"},
+		},
+		{
+			name:     "ExactMatchPreferred",
+			contents: map[string]string{filepath.Join(tmpdir, "exact-preferred"): "hello world"},
+			edits: []workspacesdk.FileEdits{
+				{
+					Path: filepath.Join(tmpdir, "exact-preferred"),
+					Edits: []workspacesdk.FileEdit{
+						{
+							Search:  "hello world",
+							Replace: "goodbye world",
+						},
+					},
+				},
+			},
+			expected: map[string]string{filepath.Join(tmpdir, "exact-preferred"): "goodbye world"},
+		},
+		{
+			name:     "NoMatchStillSucceeds",
+			contents: map[string]string{filepath.Join(tmpdir, "no-match"): "original content"},
+			edits: []workspacesdk.FileEdits{
+				{
+					Path: filepath.Join(tmpdir, "no-match"),
+					Edits: []workspacesdk.FileEdit{
+						{
+							Search:  "this does not exist in the file",
+							Replace: "whatever",
+						},
+					},
+				},
+			},
+			// File should remain unchanged.
+			expected: map[string]string{filepath.Join(tmpdir, "no-match"): "original content"},
+		},
+		{
+			name:     "MixedWhitespaceMultiline",
+			contents: map[string]string{filepath.Join(tmpdir, "mixed-ws"): "func main() {\n\tresult := compute()\n\tfmt.Println(result)\n}"},
+			edits: []workspacesdk.FileEdits{
+				{
+					Path: filepath.Join(tmpdir, "mixed-ws"),
+					Edits: []workspacesdk.FileEdit{
+						{
+							// Search uses spaces, file uses tabs.
+							Search:  "  result := compute()\n  fmt.Println(result)\n",
+							Replace: "\tresult := compute()\n\tlog.Println(result)\n",
+						},
+					},
+				},
+			},
+			expected: map[string]string{filepath.Join(tmpdir, "mixed-ws"): "func main() {\n\tresult := compute()\n\tlog.Println(result)\n}"},
+		},
 		{
 			name: "MultiError",
 			contents: map[string]string{
@@ -490,7 +490,6 @@ require (
 	github.com/elazarl/goproxy v1.8.0
 	github.com/fsnotify/fsnotify v1.9.0
 	github.com/go-git/go-git/v5 v5.16.5
-	github.com/icholy/replace v0.6.0
 	github.com/mark3labs/mcp-go v0.38.0
 	gonum.org/v1/gonum v0.17.0
 )
@@ -620,7 +620,6 @@ github.com/google/btree v1.1.3 h1:CVpQJjYgC4VbzxeGVHfvZrv1ctoYCAI8vbl07Fcxlyg=
 github.com/google/btree v1.1.3/go.mod h1:qOPhT0dTNdNzV6Z/lhRX0YXUafgPLFUh+gZMl761Gm4=
 github.com/google/flatbuffers v25.2.10+incompatible h1:F3vclr7C3HpB1k9mxCGRMXq6FdUalZ6H/pNX4FP1v0Q=
 github.com/google/flatbuffers v25.2.10+incompatible/go.mod h1:1AeVuKshWv4vARoZatz6mlQ0JxURH0Kv5+zNeJKJCa8=
-github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
@@ -730,8 +729,6 @@ github.com/hugelgupf/vmtest v0.0.0-20240216064925-0561770280a1 h1:jWoR2Yqg8tzM0v
 github.com/hugelgupf/vmtest v0.0.0-20240216064925-0561770280a1/go.mod h1:B63hDJMhTupLWCHwopAyEo7wRFowx9kOc8m8j1sfOqE=
 github.com/iancoleman/orderedmap v0.3.0 h1:5cbR2grmZR/DiVt+VJopEhtVs9YGInGIxAoMJn+Ichc=
 github.com/iancoleman/orderedmap v0.3.0/go.mod h1:XuLcCUkdL5owUCQeF2Ue9uuw1EptkJDkXXS7VoV7XGE=
-github.com/icholy/replace v0.6.0 h1:EBiD2pGqZIOJAbEaf/5GVRaD/Pmbb4n+K3LrBdXd4dw=
-github.com/icholy/replace v0.6.0/go.mod h1:zzi8pxElj2t/5wHHHYmH45D+KxytX/t4w3ClY5nlK+g=
 github.com/illarion/gonotify v1.0.1 h1:F1d+0Fgbq/sDWjj/r66ekjDG+IDeecQKUFH4wNwsoio=
 github.com/illarion/gonotify v1.0.1/go.mod h1:zt5pmDofZpU1f8aqlK0+95eQhoEAn/d4G4B/FjVW4jE=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
@@ -1053,7 +1050,6 @@ github.com/spf13/cast v1.10.0 h1:h2x0u2shc1QuLHfxi+cTJvs30+ZAHOGRic8uyGTDWxY=
 github.com/spf13/cast v1.10.0/go.mod h1:jNfB8QC9IA6ZuY2ZjDp0KtFO2LZZlg4S/7bzP6qqeHo=
 github.com/spf13/cobra v1.10.2 h1:DMTTonx5m65Ic0GOoRY2c16WCbHxOOw6xxezuLaBpcU=
 github.com/spf13/cobra v1.10.2/go.mod h1:7C1pvHqHw5A4vrJfjNwvOdzYu0Gml16OCs2GRiTUUS4=
-github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
 github.com/spf13/pflag v1.0.9/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 github.com/spf13/pflag v1.0.10 h1:4EBh2KAYBwaONj6b2Ye1GiHfwjqyROoF4RwYO+vPwFk=
 github.com/spf13/pflag v1.0.10/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
@@ -1344,7 +1340,6 @@ golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/mod v0.33.0 h1:tHFzIWbBifEmbwtGz65eaWyGiGZatSrT9prnU8DbVL8=
 golang.org/x/mod v0.33.0/go.mod h1:swjeQEj+6r7fODbD2cqrnje9PnziFuw4bmLbBZFrQ5w=
-golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
@@ -1448,7 +1443,6 @@ golang.org/x/text v0.34.0/go.mod h1:homfLqTYRFyVYemLBFl5GgL/DWEiH5wcsQ5gSh1yziA=
 golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
 golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-golang.org/x/tools v0.0.0-20190624222133-a101b041ded4/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
@@ -1514,7 +1508,6 @@ gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gotest.tools v2.2.0+incompatible h1:VsBPFP1AI068pPrMxtb/S8Zkgf9xEmTLJjfM+P5UIEo=
 gotest.tools v2.2.0+incompatible/go.mod h1:DsYFclhRJ6vuDpmuTbkuFWG+y2sxOXAzmJt81HFBacw=
-gotest.tools/v3 v3.0.2/go.mod h1:3SzNCllyD9/Y+b5r9JIKQ474KzkZyqLqEfYqMsX94Bk=
 gotest.tools/v3 v3.5.2 h1:7koQfIKdy+I8UTetycgUqXWSDwpgv193Ka+qRsmBY8Q=
 gotest.tools/v3 v3.5.2/go.mod h1:LtdLGcnqToBH83WByAAi/wiwSFCArdFIUV/xxN4pcjA=
 gvisor.dev/gvisor v0.0.0-20240509041132-65b30f7869dc h1:DXLLFYv/k/xr0rWcwVEvWme1GR36Oc4kNMspg38JeiE=