Files
zero/internal/tools/write_file.go
Kevin CodexandClaude Fable 5 2749447cdc fix(tools): make apply_patch tolerant and re-expose edit_file (#956)
* fix(tools): make apply_patch tolerant and re-expose edit_file

Head-to-head benchmarking against Grok Build on grok-4.6 (3 tasks × 3 runs)
showed Zero solving every task but spending 2.7× the tokens and 2.3× the
time on the multi-file feature task. Every one of the 20 apply_patch calls
in those runs failed, after which the model degraded to whole-file
write_file rewrites and read→write verification loops.

Root causes and fixes:

- The sandbox and the tool both rejected an absolute path that lies inside
  the workspace ("must stay inside the workspace"). Models routinely echo
  the absolute path read_file showed them. Absolute paths now flow through
  the normal workspace-scope validation (inside → allowed, outside → still
  denied); unified-diff headers are rewritten to a/ b/ relative form before
  git apply, and platform symlink prefixes (/var → /private/var) are
  normalised the same way the other file tools do.
- The structured parser demanded a byte-exact "*** Begin Patch" /
  "*** End Patch"; grok-4.6 writes "*** Begin Patch ***". Decorated marker
  spellings are accepted, and a unified range after "@@" ("-12,4 +12,6",
  optionally with a heading) no longer becomes a literal context search.
- Parse errors now carry a one-line format reminder so a failed call is
  recoverable in one retry instead of a format-guessing loop.
- edit_file (exact search/replace with uniqueness guard, CRLF and fuzzy
  fallbacks) is advertised to the model again alongside apply_patch, and
  the apply_patch description shows the structured format.
- Writers (edit_file, write_file, apply_patch) recorded a file's line total
  with lineCount, which is one higher than read_file's count for a file
  ending in a newline. RecordSeenRange resets every observation when the
  total changes, so a partial read_file after a successful edit silently
  discarded whole-file knowledge and the next edit was refused with
  "content that has not been read exactly in this session". All writers
  now record the same total read_file reports (trackedLineTotal).
- read_file's padded "  N | " line prefix was ~19% of every read (about
  1.5k tokens per 800-line file) and was re-sent on every later call. It is
  now the compact "N→" prefix models already know; nothing parsed the old
  form.
- The editing-discipline prompt steers: edit_file for a targeted change,
  apply_patch for multi-hunk/multi-file changes, write_file only for new
  files or full rewrites; a successful edit result is confirmation, so the
  file is not re-read to verify it.

Tests: regression tests for decorated markers, writer/reader line-total
agreement (edit → partial read → edit far away still succeeds), range hunk headers,
absolute in-workspace paths (structured + unified), outside-workspace
rejection, header-line-only relativisation, and tool visibility; the
prompt and tool-budget tests updated to the new contract.

Benchmark (grok-4.6, 3 tasks x 3 runs, harness in demo/bench-zero-vs-grok):
Zero 0.8.0 617 s / 1,527k tokens -> with this change 346 s / 493k tokens;
Grok Build 407 s / 713k. Every run of every configuration solved its task.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): keep CRLF line endings when relativizing patch headers

relativizeUnifiedPatchPaths split on a normalized "\n" and rejoined with
"\n", so any CRLF patch that needed a header rewrite lost its line endings
everywhere; git apply could then fail to match a CRLF file. Split on "\n"
only and carry each line's trailing "\r" through, including on rewritten
headers.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(sandbox): share the structured-patch classifier with apply_patch

Review follow-ups for #956:

- The tool accepted decorated structured markers ("***Begin Patch") that
  the sandbox's applyPatchPaths did not recognise, so for that spelling the
  boundary scanned the patch as a unified diff, extracted no targets and
  validated nothing. The marker classifier now lives in the sandbox package
  (StructuredPatchMarker / IsStructuredPatch) and the tool delegates to it,
  so both sides accept exactly the same set; tests cover inside, traversal
  and outside targets for the no-space spelling at the boundary.
- Document the containment model at the apply site: structured patches are
  applied through an opened os.Root (descriptor-relative, no-follow);
  unified diffs keep the pre-existing git-apply pathname flow, which the
  absolute-path rewrite does not widen (they become the same root-relative
  form relative paths always used).
- OpenAI addendum: the one-file-per-call rule names read_file, edit_file and
  write_file explicitly and allows a single multi-file apply_patch.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* test(sandbox): compare slash-normalised patch paths so the check passes on Windows

structuredPatchHeaderPaths normalises separators to "/", so the absolute
outside-workspace path in the boundary test must be compared in its slash
form; on Windows the backslash original never matched and the Smoke job
failed.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* test(sandbox): validate the parsed patch path at the scope boundary

For each accepted marker spelling, pass the exact path applyPatchRequestPaths
produced to scope.validate: an outside path must be denied and an inside
path accepted, so a separator-handling regression between the parser and the
scope cannot slip past the test.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): apply unified diffs in-process through the workspace root

Review follow-up for #956. Unified diffs were validated by pathname and then
handed to git apply, which reopened the targets by name — a check-to-use
window a symlink swap could exploit — and the absolute-path rewrite added in
this PR normalised `diff --git` headers with strings.Fields, which splits a
git C-quoted path containing whitespace.

Both go away by not shelling out at all: parseUnifiedPatch translates a
unified diff into the same operations a structured patch produces, and both
formats are applied by applyPatchOperations through os.OpenRoot — every
stat, read, create and write is descriptor-relative and refuses to follow a
link out of the root. git is no longer required by apply_patch.

Unified-diff support: modifications, creations (--- /dev/null), deletions
(+++ /dev/null), multiple hunks per file, git "rename from/to" (a move,
hunks optional) and "copy from/to" (a new copy operation whose destination
inherits only the tracker credit the source had), "\ No newline at end of
file" on either side, a/ b/ prefixes, C-quoted paths, CRLF patches, and
git's diff/index/mode lines. Hunks are placed at their "@@ -a,b" range when
the expected lines match there and located by context otherwise (so a
stale range still applies and duplicate blocks are disambiguated by the
range). Binary patches are rejected.

Removed: the git apply flow, relativizeUnifiedPatchPaths,
recheckPatchWriteTargets, missingPatchTargets, completeCreatedPatchTargets
and recordCreatedPatchTargets. validatePatchPaths/changedFilesFromPatch stay
for mutation-target listing.

Tests: the existing unified-diff suite now runs through the in-process
applier unchanged; new coverage for quoted whitespace paths (inside applies,
outside is refused untouched), a workspace path swapped for a symlink that
escapes the root (both formats refused, outside file unmodified), create +
delete + no-newline markers, range hint vs context fallback, rename with a
hunk, and binary/empty rejection.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): harden unified-diff parsing and cover the copy operation

Review follow-ups for #956 (in-process unified applier):

- A hunk that ends before its declared line counts is reported as
  malformed instead of silently absorbing the next file's ---/+++ header
  pair (which then failed later against the wrong file). Both shapes are
  caught: leftover counts at a header or at end of input, and a --- line
  directly followed by +++ inside a hunk. The element after a patch's final
  newline is no longer counted as an empty context line, so a truncated
  hunk cannot look complete.
- "\ No newline at end of file" may only follow a file's final hunk; a
  marker before another hunk is rejected rather than leaking into that
  hunk's result.
- Zero-context insertions (git diff -U0) are documented as
  position-trusting by design, matching git apply without fuzz; hunks with
  context are verified at the range before it is used.

Tests: copy from/to (source kept, destination created with the hunk
applied and tracked with the source's whole-file state; existing
destination refused untouched; copy onto itself refused), over-declared and
truncated hunk counts, and the no-newline marker before vs after the final
hunk.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): require an @@ line before treating ---/+++ inside a hunk as a file boundary

A removed "-- x" line directly followed by an added "++ y" line is valid
hunk content that also matches the ---/+++ header shape; the boundary check
now additionally requires the following line to be a hunk header, and a
regression test keeps such a pair intact. End-of-input strictness for a hunk
cut short is documented as deliberate: applying a truncated hunk would make
a partial change (removals without their replacements).

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* refactor(tools): share one line-count implementation between reader and writer

sourceLineCount and trackedLineTotal computed the same count; keeping two
copies invites exactly the reader/writer drift this PR fixed. The reader now
delegates to trackedLineTotal, which carries the tracker contract.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): verify a unified deletion's expected content before removing the file

A unified diff's "+++ /dev/null" hunks state the content being removed, but
the in-process applier dropped them and deleted unconditionally, so a stale
deletion removed a file whose current content the patch never described.
Unified deletions now keep their hunks, require at least one, and run them
through the same verifier as updates: the hunks must match the current file
and leave nothing behind, otherwise the deletion is refused and the file is
untouched. A structured "*** Delete File" keeps its unconditional meaning.

Hardening from the same review: every non-create change re-reads its source
through the opened root immediately before commit and refuses to proceed if
the bytes differ from what was planned.

Tests: matching deletion, stale deletion (file byte-for-byte unchanged),
partial deletion, header-only deletion, multi-hunk deletion with one stale
hunk (nothing removed) and all-good hunks, structured delete unchanged, and
a source changed between planning and commit for update and delete.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* test(tools): a move with a missing source is refused before publishing

The pre-commit recheck now refuses a move whose source vanished after
planning instead of publishing the destination and then failing; update the
test to the safer contract (error names the recheck, nothing is created).

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): byte-exact unified deletions and git's header-only empty-file forms

Review follow-ups for #956:

- A unified deletion is verified byte for byte: the removed lines (with the
  removed side's "\ No newline at end of file" honoured) must equal the
  current file exactly, with only the file's own line-ending style
  normalised. None of the whitespace tolerance used to locate update hunks
  applies, and a whitespace-only remainder no longer passes; a deletion is
  not recoverable, so it fails closed.
- git describes an empty file's deletion or creation with header lines only
  ("diff --git", "deleted file mode"/"new file mode", "index") and no
  hunks. Both forms are recognised: the deletion is applied only when the
  current file is empty, the creation writes an empty file, and they compose
  with hunk-carrying files in the same patch.
- The pre-commit recheck test also covers the copy operation and asserts no
  destination is created on refusal.

Tests: whitespace/indentation/blank-line/space-only/missing-newline
mismatches all refused with the file unchanged, matching no-newline marker
and CRLF file accepted, header-only deletion of a non-empty file refused,
multi-file patch with header-only delete + create + a normal hunk.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* test(tools): remove the move source after planning via a deterministic hook

The refused-move test now creates source.txt, plans the move, and removes
the file through a test-only pre-commit hook (structuredPatchBeforeCommit)
so it exercises the post-planning disappearance path rather than a source
that was never there. Assertions unchanged: refused before publishing, no
destination created.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* test(tui): read_file fixtures use the compact N→ prefix

Three TUI fixtures still built fake read_file output in the legacy
"  N | text" shape; they pass either way but pinned an outdated contract.
They now mirror what appendReadFileRange emits, and the shape comment and
the expanded-card assertion are updated.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

* fix(tools): name the committed files when a patch is partially applied

Review follow-up for #956. When a later change in a multi-file patch fails
(for example the pre-commit recheck refuses a file that changed after
planning), the error now lists exactly which files were already committed
and states that the rest are unchanged, instead of a generic "partially
applied" warning. The model can then re-read only what actually changed.

Test: a three-file structured patch whose second file is altered after
planning fails with "already committed: first.txt", first.txt holds the
patched content, and the other two files are untouched.

Co-Authored-By: Claude Fable 5 <[email protected]>
Claude-Session: https://claude.ai/code/session_012JqvAf7zsP1qYFVZayKXHq

---------

Co-authored-by: Claude Fable 5 <[email protected]>
2026-08-25 20:23:48 +08:00

159 lines
6.4 KiB
Go

package tools
import (
"context"
"fmt"
"os"
"path/filepath"
"strings"
)
type writeFileTool struct {
baseTool
workspaceRoot string
scope PathScope
}
func NewScopedWriteFileTool(workspaceRoot string, scope PathScope) Tool {
return writeFileTool{
baseTool: baseTool{
name: "write_file",
description: "Create a new file, refusing to overwrite existing files unless overwrite is true.",
parameters: Schema{
Type: "object",
Properties: map[string]PropertySchema{
"path": {Type: "string", Description: "Absolute or relative path of the file to write."},
"content": {Type: "string", Description: "Full file contents to write."},
"overwrite": {Type: "boolean", Description: "Whether to allow overwriting an existing file.", Default: false},
},
Required: []string{"path", "content"},
AdditionalProperties: false,
},
safety: promptSafety(SideEffectWrite, "Creates or overwrites files."),
capabilities: ToolCapabilities{Effect: EffectWorkspaceWrite, ThreadSafe: false, ResourceKeys: fileResourceKeys},
},
workspaceRoot: normalizeWorkspaceRoot(workspaceRoot),
scope: scope,
}
}
func (tool writeFileTool) Run(ctx context.Context, args map[string]any) Result {
return tool.RunWithOptions(ctx, args, RunOptions{})
}
func (tool writeFileTool) RunWithOptions(ctx context.Context, args map[string]any, options RunOptions) Result {
requestedPath, err := aliasedStringArg(args, []string{"path", "file", "file_path", "filename"}, "", true, false)
if err != nil {
return errorResult("Error: Invalid arguments for write_file: " + err.Error())
}
content, err := fileContentArg(args)
if err != nil {
return errorResult("Error: Invalid arguments for write_file: " + err.Error())
}
overwrite, err := boolArg(args, "overwrite", false)
if err != nil {
return errorResult("Error: Invalid arguments for write_file: " + err.Error())
}
absolutePath, relativePath, err := resolveScopedTargetPath(tool.workspaceRoot, tool.scope, requestedPath)
if err != nil {
return errorResult("Error writing file " + requestedPath + ": " + err.Error())
}
existed := false
if _, err := os.Stat(absolutePath); err == nil {
existed = true
if !overwrite {
return errorResult("Error: " + relativePath + " already exists. Pass overwrite: true to replace it.")
}
} else if !os.IsNotExist(err) {
return errorResult("Error writing file " + relativePath + ": " + err.Error())
}
// On overwrite, refuse to clobber a tracked file that changed on disk outside
// Zero since it was last read — the new content was likely composed against a
// stale view. Only read current bytes when there is a baseline to compare,
// so a first-touch create/overwrite stays a single write with no extra read.
if existed {
if options.FileTracker != nil && !options.FileTracker.SeenWhole(absolutePath) {
return errorResult(fileUnseenMessage(relativePath))
}
if _, tracked := options.FileTracker.Version(absolutePath); tracked {
// Fail CLOSED: if the tracked file can't be re-read to verify it, refuse
// the overwrite rather than clobbering a file whose current state is
// unknown (it may have been replaced or removed out from under us).
current, rerr := os.ReadFile(absolutePath)
if rerr != nil {
return errorResult(fileConflictMessage(relativePath))
}
if cerr := options.FileTracker.CheckConflict(absolutePath, current); cerr != nil {
return errorResult(fileConflictMessage(relativePath))
}
}
}
// Capture the prior content (before we replace it) so an overwrite can show a
// real diff; a fresh create stays "" and previews as all-additions.
priorContent := ""
if existed {
if prev, rerr := os.ReadFile(absolutePath); rerr == nil {
priorContent = string(prev)
}
}
if err := os.MkdirAll(filepath.Dir(absolutePath), 0o755); err != nil {
return errorResult("Error writing file " + relativePath + ": " + err.Error())
}
if err := recheckScopedWriteTarget(tool.workspaceRoot, tool.scope, requestedPath); err != nil {
return errorResult("Error writing file " + relativePath + ": " + err.Error())
}
if err := os.WriteFile(absolutePath, []byte(content), 0o644); err != nil {
return errorResult("Error writing file " + relativePath + ": " + err.Error())
}
modelKnownContent := content
// Optional format-on-write (ZERO_FORMAT_ON_WRITE). Must run BEFORE the
// FileTracker baseline: recording pre-format content would make the very
// next edit look like an external modification and trip the conflict guard.
content = maybeFormatWrittenFile(ctx, absolutePath, content)
// Baseline the freshly written content so a later edit/overwrite in this
// session compares against what is now on disk.
newInfo, _ := os.Stat(absolutePath)
options.FileTracker.Record(absolutePath, []byte(content), newInfo)
if content == modelKnownContent {
options.FileTracker.RecordSeenRange(absolutePath, 1, trackedLineTotal(content), trackedLineTotal(content))
}
if !existed {
options.FileTracker.RecordCreated(absolutePath)
}
verb := "Created"
if existed {
verb = "Overwrote"
}
// Report line count (not bytes): "Wrote 282 lines" reads as real work at a
// glance, where a byte total is opaque noise.
lines := strings.Count(content, "\n")
if content != "" && !strings.HasSuffix(content, "\n") {
lines++
}
summary := fmt.Sprintf("%s %s (%d lines).", verb, relativePath, lines)
summary += inlineDiagnostics(ctx, options, absolutePath, relativePath)
result := okResult(summary)
result.ChangedFiles = []string{relativePath}
// Card-only preview: a real unified diff (all-green for a create, red/green for
// an overwrite) on Display.Preview. Output stays the summary, so the model never
// re-reads the file — the rich preview costs zero model tokens.
result.Display = Display{Summary: summary, Kind: "file", Preview: boundedUnifiedDiff(relativePath, priorContent, content)}
return result
}
// fileContentArg reads the file body from "content" or a common alias that weaker
// models sometimes use instead (contents/text/body/data/file_content). It
// delegates to the shared aliasedStringArg so the present-but-non-string type
// error ("content must be a string") and the required-but-missing error
// ("content is required") stay consistent with every other tool. An empty string
// is allowed (writing an empty file), so allowEmpty is true.
func fileContentArg(args map[string]any) (string, error) {
return aliasedStringArg(args, []string{"content", "contents", "text", "body", "data", "file_content"}, "", true, true)
}