feat(merge): real conflict-hunk parsing pipeline (chunk 2 backend)

Replace the whole-file conflict model with line-level hunks, the
foundation for the full in-app merge editor.

- ConflictMarkerParser: parses git conflict markers (incl. diff3 base)
  into ordered stable/conflict MergeSegments; exact round-trip + Compose
- GitService.MergeNoFfAsync passes -c merge.conflictStyle=diff3 so the
  working tree carries the merge base in conflict markers
- TaskMergeService.GetConflictDocumentsAsync: reads each conflicted file,
  parses into segments, flags binary files
- hub GetMergeConflictDocuments + DTOs (MergeConflictDocumentsDto/
  ConflictDocumentDto/MergeSegmentDto), IWorkerClient + both fakes
- tests: 8 parser unit tests + a real-git integration test asserting
  line-level hunks with a diff3 base
This commit is contained in:
Mika Kuns
2026-06-18 16:22:56 +02:00
parent 4847c5c0a4
commit e779e13654
10 changed files with 378 additions and 1 deletions

View File

@@ -0,0 +1,134 @@
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
namespace ClaudeDo.Data.Git;
/// <summary>
/// One piece of a conflicted file: either common ("stable") text both sides agree on,
/// or a conflict region holding the two — or, with diff3 markers, three — competing versions.
/// </summary>
public sealed record MergeSegment
{
public bool IsConflict { get; init; }
/// <summary>Stable text (verbatim, line endings preserved) when <see cref="IsConflict"/> is false.</summary>
public string Text { get; init; } = "";
/// <summary>"Ours" side (the target branch) when <see cref="IsConflict"/> is true.</summary>
public string Ours { get; init; } = "";
/// <summary>Merge base, present only when the merge used diff3 conflict style; null otherwise.</summary>
public string? Base { get; init; }
/// <summary>"Theirs" side (the incoming branch) when <see cref="IsConflict"/> is true.</summary>
public string Theirs { get; init; } = "";
public static MergeSegment Stable(string text) => new() { Text = text };
public static MergeSegment Conflict(string ours, string? @base, string theirs) =>
new() { IsConflict = true, Ours = ours, Base = @base, Theirs = theirs };
}
/// <summary>
/// Parses a conflicted file's text into ordered stable / conflict segments and reassembles it.
/// Reads git conflict markers verbatim, so a file with no markers yields a single stable
/// segment, and reassembling the stable text plus one chosen resolution per conflict
/// round-trips the file exactly (line endings included).
/// </summary>
public static class ConflictMarkerParser
{
private const string OursMarker = "<<<<<<<";
private const string BaseMarker = "|||||||";
private const string SepMarker = "=======";
private const string TheirsMarker = ">>>>>>>";
public static IReadOnlyList<MergeSegment> Parse(string fileText)
{
var segments = new List<MergeSegment>();
var lines = SplitKeepLineEndings(fileText);
var stable = new StringBuilder();
var i = 0;
while (i < lines.Count)
{
if (!IsMarker(lines[i], OursMarker))
{
stable.Append(lines[i++]);
continue;
}
if (stable.Length > 0)
{
segments.Add(MergeSegment.Stable(stable.ToString()));
stable.Clear();
}
i++; // consume "<<<<<<<"
var ours = new StringBuilder();
while (i < lines.Count && !IsMarker(lines[i], BaseMarker) && !IsMarker(lines[i], SepMarker))
ours.Append(lines[i++]);
string? @base = null;
if (i < lines.Count && IsMarker(lines[i], BaseMarker))
{
i++; // consume "|||||||"
var baseText = new StringBuilder();
while (i < lines.Count && !IsMarker(lines[i], SepMarker))
baseText.Append(lines[i++]);
@base = baseText.ToString();
}
if (i < lines.Count && IsMarker(lines[i], SepMarker)) i++; // consume "======="
var theirs = new StringBuilder();
while (i < lines.Count && !IsMarker(lines[i], TheirsMarker))
theirs.Append(lines[i++]);
if (i < lines.Count && IsMarker(lines[i], TheirsMarker)) i++; // consume ">>>>>>>"
segments.Add(MergeSegment.Conflict(ours.ToString(), @base, theirs.ToString()));
}
if (stable.Length > 0)
segments.Add(MergeSegment.Stable(stable.ToString()));
return segments;
}
/// <summary>True when the file still contains an opening conflict marker.</summary>
public static bool HasConflicts(string fileText) =>
SplitKeepLineEndings(fileText).Any(l => IsMarker(l, OursMarker));
/// <summary>
/// Reassembles a file from its segments. Stable segments emit their text verbatim;
/// each conflict segment emits whatever <paramref name="resolveConflict"/> returns for it.
/// </summary>
public static string Compose(
IEnumerable<MergeSegment> segments, Func<MergeSegment, string> resolveConflict) =>
string.Concat(segments.Select(s => s.IsConflict ? resolveConflict(s) : s.Text));
// A marker line starts with exactly the 7-char marker, then end-of-line or whitespace/label.
private static bool IsMarker(string line, string marker)
{
if (!line.StartsWith(marker, StringComparison.Ordinal)) return false;
if (line.Length == marker.Length) return true;
return line[marker.Length] is ' ' or '\t' or '\r' or '\n';
}
// Splits into physical lines, each retaining its trailing "\n" (and "\r" if present).
private static List<string> SplitKeepLineEndings(string s)
{
var lines = new List<string>();
var i = 0;
while (i < s.Length)
{
var nl = s.IndexOf('\n', i);
if (nl < 0) { lines.Add(s[i..]); break; }
lines.Add(s[i..(nl + 1)]);
i = nl + 1;
}
return lines;
}
}

View File

@@ -252,8 +252,11 @@ public sealed class GitService
public async Task<(int ExitCode, string Stderr)> MergeNoFfAsync(
string repoDir, string sourceBranch, string message, CancellationToken ct = default)
{
// diff3 conflict style writes the merge base (|||||||) into conflict markers so the
// in-app resolver can show a true three-way view. It only enriches conflicted hunks;
// clean merges are unaffected.
var (exitCode, _, stderr) = await RunGitAsync(repoDir,
["merge", "--no-ff", "-m", message, sourceBranch], ct);
["-c", "merge.conflictStyle=diff3", "merge", "--no-ff", "-m", message, sourceBranch], ct);
return (exitCode, stderr);
}

View File

@@ -55,6 +55,7 @@ public interface IWorkerClient : INotifyPropertyChanged
// ── Conflict resolution (worker hub side implemented by Layer C) ──
Task<MergeResultDto> StartConflictMergeAsync(string taskId, string targetBranch);
Task<MergeConflictsDto> GetMergeConflictsAsync(string taskId);
Task<MergeConflictDocumentsDto> GetMergeConflictDocumentsAsync(string taskId);
Task WriteConflictResolutionAsync(string taskId, string path, string resolvedContent);
Task<MergeResultDto> ContinueConflictMergeAsync(string taskId);
Task AbortConflictMergeAsync(string taskId);

View File

@@ -275,6 +275,9 @@ public partial class WorkerClient : ObservableObject, IAsyncDisposable, IWorkerC
public Task<MergeConflictsDto> GetMergeConflictsAsync(string taskId)
=> _hub.InvokeAsync<MergeConflictsDto>("GetMergeConflicts", taskId);
public Task<MergeConflictDocumentsDto> GetMergeConflictDocumentsAsync(string taskId)
=> _hub.InvokeAsync<MergeConflictDocumentsDto>("GetMergeConflictDocuments", taskId);
public Task WriteConflictResolutionAsync(string taskId, string path, string resolvedContent)
=> _hub.InvokeAsync("WriteConflictResolution", taskId, path, resolvedContent);
@@ -559,6 +562,9 @@ public record MergeTargetsDto(string DefaultBranch, IReadOnlyList<string> LocalB
public record MergeConflictsDto(string TaskId, IReadOnlyList<ConflictFileDto> Files);
public record ConflictFileDto(string Path, IReadOnlyList<ConflictHunkDto> Hunks);
public record ConflictHunkDto(string Ours, string Theirs, string? Base);
public record MergeConflictDocumentsDto(string TaskId, IReadOnlyList<ConflictDocumentDto> Files);
public record ConflictDocumentDto(string Path, bool IsBinary, IReadOnlyList<MergeSegmentDto> Segments);
public record MergeSegmentDto(bool IsConflict, string Text, string Ours, string? Base, string Theirs);
public sealed record UpdateListDto(string Id, string Name, string? WorkingDir, string DefaultCommitType);
public sealed record UpdateListConfigDto(string ListId, string? Model, string? SystemPrompt, string? AgentPath, int? MaxTurns = null);
public sealed record UpdateTaskAgentSettingsDto(string TaskId, string? Model, string? SystemPrompt, string? AgentPath, int? MaxTurns = null);

View File

@@ -61,6 +61,9 @@ public record MergeTargetsDto(string DefaultBranch, IReadOnlyList<string> LocalB
public record MergeConflictsDto(string TaskId, IReadOnlyList<ConflictFileDto> Files);
public record ConflictFileDto(string Path, IReadOnlyList<ConflictHunkDto> Hunks);
public record ConflictHunkDto(string Ours, string Theirs, string? Base);
public record MergeConflictDocumentsDto(string TaskId, IReadOnlyList<ConflictDocumentDto> Files);
public record ConflictDocumentDto(string Path, bool IsBinary, IReadOnlyList<MergeSegmentDto> Segments);
public record MergeSegmentDto(bool IsConflict, string Text, string Ours, string? Base, string Theirs);
public record UpdateListDto(string Id, string Name, string? WorkingDir, string DefaultCommitType);
public record UpdateListConfigDto(string ListId, string? Model, string? SystemPrompt, string? AgentPath, int? MaxTurns = null);
public record UpdateTaskAgentSettingsDto(string TaskId, string? Model, string? SystemPrompt, string? AgentPath, int? MaxTurns = null);
@@ -383,6 +386,18 @@ public sealed class WorkerHub : Microsoft.AspNetCore.SignalR.Hub
new[] { new ConflictHunkDto(f.Ours, f.Theirs, f.Base) })).ToList());
});
public Task<MergeConflictDocumentsDto> GetMergeConflictDocuments(string taskId)
=> HubGuard(async () =>
{
var c = await _mergeService.GetConflictDocumentsAsync(taskId, CancellationToken.None);
return new MergeConflictDocumentsDto(
c.TaskId,
c.Files.Select(f => new ConflictDocumentDto(
f.Path, f.IsBinary,
f.Segments.Select(s => new MergeSegmentDto(
s.IsConflict, s.Text, s.Ours, s.Base, s.Theirs)).ToList())).ToList());
});
public Task WriteConflictResolution(string taskId, string path, string resolvedContent)
=> HubGuard(() => _mergeService.WriteResolutionAsync(
taskId, path, resolvedContent ?? "", CancellationToken.None));

View File

@@ -33,6 +33,15 @@ public sealed record ConflictFileContent(
string Theirs,
string? Base);
public sealed record ConflictDocuments(
string TaskId,
IReadOnlyList<ConflictDocumentContent> Files);
public sealed record ConflictDocumentContent(
string Path,
bool IsBinary,
IReadOnlyList<MergeSegment> Segments);
public sealed class TaskMergeService
{
public const string StatusMerged = "merged";
@@ -256,6 +265,45 @@ public sealed class TaskMergeService
return new MergeConflicts(taskId, result);
}
/// <summary>
/// Reads each conflicted working-tree file and parses its conflict markers into line-level
/// segments (with the diff3 merge base when present). Binary files are flagged and skipped.
/// </summary>
public async Task<ConflictDocuments> GetConflictDocumentsAsync(string taskId, CancellationToken ct)
{
var (_, list, _) = await LoadMergeContextAsync(taskId, ct);
if (string.IsNullOrWhiteSpace(list.WorkingDir))
throw new InvalidOperationException("list has no working directory");
var files = await _git.ListConflictedFilesAsync(list.WorkingDir, ct);
var result = new List<ConflictDocumentContent>(files.Count);
foreach (var path in files)
{
var full = Path.Combine(list.WorkingDir, path.Replace('/', Path.DirectorySeparatorChar));
string text;
try { text = await File.ReadAllTextAsync(full, ct); }
catch { text = ""; }
if (LooksBinary(text))
{
result.Add(new ConflictDocumentContent(path, true, Array.Empty<MergeSegment>()));
continue;
}
result.Add(new ConflictDocumentContent(path, false, ConflictMarkerParser.Parse(text)));
}
return new ConflictDocuments(taskId, result);
}
// A NUL byte in the head of the file is the conventional binary sniff.
private static bool LooksBinary(string text)
{
var n = Math.Min(text.Length, 8000);
for (var i = 0; i < n; i++)
if (text[i] == '\0') return true;
return false;
}
public async Task WriteResolutionAsync(string taskId, string path, string content, CancellationToken ct)
{
var (_, list, _) = await LoadMergeContextAsync(taskId, ct);