2 Commits

Author	SHA1	Message	Date
Haileyesus	dc5d73936a	refactor(projects): identify projects by DB projectId instead of folder-derived name ... GET /api/projects used to scan ~/.claude/projects/ on every request, derive each project's identity from the encoded folder name, and re-parse JSONL files to build session lists. Using the folder-derived name as the project identifier leaked the Claude CLI's on-disk encoding into every API route, forced every downstream endpoint to re-resolve a real path via JSONL 'cwd' inspection, and made the project list endpoint O(projects x sessions) on disk I/O. This change switches the entire API surface to identify projects by the stable primary key from the 'projects' table and drives the listing straight from the DB: - Add projectsDb.getProjectPathById as the canonical projectId -> path resolver so routes no longer need to touch the filesystem to figure out where a project lives. - Rewrite getProjects so it reads the project list from the 'projects' table and the per-project session list from the 'sessions' table (one SELECT per project). No filesystem scanning happens for this endpoint anymore, which removes the dependency on ~/.claude/projects existing, on Cursor's MD5-hashed chat folders being discoverable, and on Codex's JSONL history being on disk. Per the migration spec each session now exposes 'summary' sourced from sessions.custom_name, 'messageCount' = 0 (message counting is not implemented), and sessionMeta.hasMore is pinned to false since this endpoint doesn't drive session pagination. - Introduce id-based wrappers (getSessionsById, renameProjectById, deleteSessionById, deleteProjectById, getProjectTaskMasterById) so every caller can pass projectId and resolve the real path through the DB. renameProjectById also writes to projects.custom_project_name so the DB-driven getProjects response reflects renames immediately; it keeps project-config.json in sync for any legacy reader that still consults the JSON file. - Migrate every /api/projects/:projectName route in server/index.js, server/routes/taskmaster.js, and server/routes/messages.js to :projectId, and change server/routes/git.js so the 'project' query/body parameter carries a projectId that is resolved through the DB before any git command runs. TaskMaster WebSocket broadcasts emit 'projectId' for the same reason so the frontend can match notifications against its current selection without another lookup. - Delete helpers that existed only to feed the old getProjects path (getCursorSessions, getGeminiCliSessions, getProjectTaskMaster) along with their unused imports (better-sqlite3's Database, applyCustomSessionNames). The legacy folder-name helpers (getSessions, renameProject, deleteSession, deleteProject, extractProjectDirectory) are kept as internal implementation details of the id-based wrappers and of destructive cleanup / conversation search, but they are no longer re-exported. - searchConversations still walks JSONL to produce match snippets (that data doesn't live in the DB), but it now includes the resolved projectId in each result so the sidebar can cross-reference hits with its already loaded project list without a second round-trip. Frontend migration: - Project.name is replaced by Project.projectId in src/types/app.ts, and ProjectSession.__projectName becomes __projectId so session tagging and sidebar state keys stay aligned with the backend identifier. Settings continues to use SettingsProject.name for legacy consumers, but it is populated from projectId by normalizeProjectForSettings. - All places that previously indexed per-project state by project.name (sidebar expanded/starred/loading/deletingProjects sets, additionalSessions map, projectHasMoreOverrides, starredProjects localStorage, command history and draft-input localStorage, TaskMaster caches) now key on projectId so state survives display-name edits and is consistent across the app. - src/utils/api.js renames every endpoint parameter to projectId, the unified messages endpoint takes projectId in its query string, and useSessionStore forwards projectId on fetchFromServer / fetchMore / refreshFromServer. Git panel, file tree, code editor, PRD editor, plugins context, MCP server flows and TaskMaster hooks are all updated to pass projectId. - DEFAULT_PROJECT_FOR_EMPTY_SHELL is updated to carry a 'default' projectId sentinel so the empty-shell placeholder still satisfies the Project contract. Bug fix bundled in: - sessionsDb.setName no longer bumps updated_at when a row already exists. Renaming is a label change, not activity, so there is no reason for it to reset 'last activity' in the sidebar. It also no longer relies on SQLite's CURRENT_TIMESTAMP, which stores a naive 'YYYY-MM-DD HH:MM:SS' value that JavaScript parses as local time and caused renamed sessions to appear shifted backwards by the client's UTC offset. When an INSERT actually happens it now writes ISO-8601 UTC with a 'Z' suffix. - buildSessionsByProviderFromDb normalizes any legacy naive timestamps in the sessions table to ISO-8601 UTC on the way out so rows written before this change also render correctly on the client. Other cleanup: - Removed the filesystem-first project-discovery comment block at the top of server/projects.js and replaced it with a short note that describes the new DB-driven flow and lists the few remaining filesystem-dependent helpers (message reads, search, destructive delete, manual project registration). - server/modules/providers/index.ts is added as a small barrel so the providers module exposes a stable public surface. Made-with: Cursor	2026-04-24 18:12:10 +03:00
Haile	a77f213dd5	fix: numerous bugs (#528) ... * fix(shell): copy terminal selections from xterm buffer The shell was delegating Cmd/Ctrl+C to document.execCommand('copy'), which copied the rendered DOM selection instead of xterm's logical buffer text. Wrapped values like login URLs could pick up row whitespace or line breaks and break when pasted. Route keyboard copy through terminal.getSelection() and the shared clipboard helper. Also intercept native copy events on the terminal container so mouse selection and browser copy actions use the same normalized terminal text. Remove the copy listener during teardown to avoid leaking handlers across terminal reinitialization. * fix(shell): restore terminal focus when switching to the shell tab Pass shell activity state from MainContent through StandaloneShell and use it inside Shell to explicitly focus the xterm instance once the terminal is both initialized and connected. Previously, switching to the Shell tab left focus on the tab button because isActive was being ignored and the terminal never called focus() after the tab activation lifecycle completed. As a result, users had to click inside the terminal before keyboard input would be accepted. This change wires isActive through the shell stack, removes the unused prop handling in Shell, and adds a focus effect that runs when the shell becomes active and ready. The effect uses both requestAnimationFrame and a zero-delay timeout so focus is applied reliably after rendering and connection state updates settle. This restores immediate typing when opening the shell tab and also improves the reconnect path by re-focusing the terminal after the shell connection is ready. * fix(shell): remove fallback command for codex and claude session resumes The `|| claude` and `|| codex` fallback commands were causing errors as they are not valid commands. * fix: use fallback while resuming codex and claude sessions for linux and windows * feat(git): add revert latest local commit action in git panel Add a complete revert-local-commit flow so users can undo the most recent local commit directly from the Git header, placed before the refresh icon. Backend - add POST /api/git/revert-local-commit endpoint in server/routes/git.js - validate project input and repository state before executing git operations - revert latest commit with `git reset --soft HEAD~1` to keep changes staged - handle initial-commit edge case by deleting HEAD ref when no parent exists - return clear success and error responses for UI consumption Frontend - add useRevertLocalCommit hook to encapsulate API call and loading state - wire hook into GitPanel and refresh git data after successful revert - add new toolbar action in GitPanelHeader before refresh icon - route action through existing confirmation modal flow - disable action while request is in flight and show activity indicator Shared UI and typing updates - extend ConfirmActionType with `revertLocalCommit` - add confirmation title, label, and style mappings for new action - render RotateCcw icon for revert action in ConfirmActionModal Result - users can safely undo the latest local commit from the UI - reverted commit changes remain staged for immediate recommit/edit workflows * fix: run cursor with --trust if workspace trust prompt is detected, and retry once * fix(git): handle repositories without commits across status and remote flows Improve git route behavior for repositories initialized with `git init` but with no commits yet. Previously, several routes called `git rev-parse --abbrev-ref HEAD`, which fails before the first commit and caused noisy console errors plus a broken Git panel state. What changed - add `getGitErrorDetails` helper to normalize git process failure text - add `isMissingHeadRevisionError` helper to detect no-HEAD/no-revision cases - add `getCurrentBranchName` helper: - uses `git symbolic-ref --short HEAD` first (works before first commit) - falls back to `git rev-parse --abbrev-ref HEAD` for detached HEAD and edge cases - add `repositoryHasCommits` helper using `git rev-parse --verify HEAD` Status route improvements - replace inline branch/HEAD error handling with shared helpers - keep returning valid branch + `hasCommits: false` for fresh repositories Remote status improvements - avoid hard failure when repository has no commits - return a safe, non-error payload with: - `hasUpstream: false` - `ahead: 0`, `behind: 0` - detected remote name when remotes exist - message: "Repository has no commits yet" - preserve existing upstream detection behavior for repositories with commits Consistency updates - switch fetch/pull/push/publish branch lookup to shared `getCurrentBranchName` to ensure the same branch-resolution behavior everywhere Result - `git init` repositories no longer trigger `rev-parse HEAD` ambiguity failures - Git panel remains usable before the first commit - backend branch detection is centralized and consistent across git operations * fix(git): resolve file paths against repo root for paths with spaces Fix path resolution for git file operations when project directories include spaces or when API calls are issued from subdirectories inside a repository. Problem - operations like commit/discard/diff could receive file paths that were valid from repo root but were executed from a nested cwd - this produced pathspec errors like: - warning: could not open directory '4/4/' - fatal: pathspec '4/hello_world.ts' did not match any files Root cause - file arguments were passed directly to git commands using the project cwd - inconsistent path forms (repo-root-relative vs cwd-relative) were not normalized Changes - remove unsafe fallback decode in `getActualProjectPath`; fail explicitly when the real project path cannot be resolved - add repository/file-path helpers: - `getRepositoryRootPath` - `normalizeRepositoryRelativeFilePath` - `parseStatusFilePaths` - `buildFilePathCandidates` - `resolveRepositoryFilePath` - update file-based git endpoints to resolve paths before executing commands: - GET `/diff` - GET `/file-with-diff` - POST `/commit` - POST `/generate-commit-message` - POST `/discard` - POST `/delete-untracked` - stage/restore/reset operations now use `--` before pathspecs for safer argument separation Behavioral impact - git operations now work reliably for repositories under directories containing spaces - file operations are consistent even when project cwd is a subdirectory of repo root - endpoint responses continue to preserve existing payload shapes Verification - syntax check: `node --check server/routes/git.js` - typecheck: `npm run typecheck` - reproduced failing scenario in a temp path with spaces; confirmed root-resolved path staging succeeds where subdir-cwd pathspec previously failed * fix(git-ui): prevent large commit diffs from freezing the history tab Harden commit diff loading/rendering so opening a very large commit no longer hangs the browser tab. Problem - commit history diff viewer rendered every diff line as a React node - very large commits could create thousands of nodes and lock the UI thread - backend always returned full commit patch payloads, amplifying frontend pressure Backend safeguards - add `COMMIT_DIFF_CHARACTER_LIMIT` (500,000 chars) in git routes - update GET `/api/git/commit-diff` to truncate oversized diff payloads - include `isTruncated` flag in response for observability/future UI handling - append truncation marker text when server-side limit is applied Frontend safeguards - update `GitDiffViewer` to use bounded preview rendering: - character cap: 200,000 - line cap: 1,500 - move diff preprocessing into `useMemo` for stable, one-pass preview computation - show a clear "Large diff preview" notice when truncation is active Impact - commit diff expansion remains responsive even for high-change commits - UI still shows useful diff content while avoiding tab lockups - changes apply to shared diff viewer usage and improve resilience broadly Validation - `node --check server/routes/git.js` - `npm run typecheck` - `npx eslint src/components/git-panel/view/shared/GitDiffViewer.tsx` * fix(cursor-chat): stabilize first-run UX and clean cursor message rendering Fix three Cursor chat regressions observed on first message runs: 1. Full-screen UI refresh/flicker after first response. 2. Internal wrapper tags rendered in user messages. 3. Duplicate assistant message on response finalization. Root causes - Project refresh from chat completion used the global loading path, toggling app-level loading UI. - Cursor history conversion rendered raw internal wrapper payloads as user-visible message text. - Cursor response handling could finalize through overlapping stream/ result paths, and stdout chunk parsing could split JSON lines. Changes - Added non-blocking project refresh plumbing for chat/session flows. - Introduced fetch options in useProjectsState (showLoadingState flag). - Added refreshProjectsSilently() to update metadata without global loading UI. - Wired window.refreshProjects to refreshProjectsSilently in AppContent. - Added Cursor user-message sanitization during history conversion. - Added extractCursorUserQuery() to keep only <user_query> payload. - Added sanitizeCursorUserMessageText() to strip internal wrappers: <user_info>, <agent_skills>, <available_skills>, <environment_context>, <environment_info>. - Applied sanitization only for role === 'user' in convertCursorSessionMessages(). - Hardened Cursor backend stream parsing and finalization. - Added line-buffered stdout parser for chunk-split JSON payloads. - Flushed trailing unterminated stdout line on process close. - Removed redundant content_block_stop emission on Cursor result. - Added frontend duplicate guard in cursor-result handling. - Skips a second assistant bubble when final result text equals already-rendered streamed content. Code comments - Added focused comments describing silent refresh behavior, tag stripping rationale, duplicate guard behavior, and line buffering. Validation - ESLint passes for touched files. - Production build succeeds. Files - server/cursor-cli.js - src/components/app/AppContent.tsx - src/components/chat/hooks/useChatRealtimeHandlers.ts - src/components/chat/utils/messageTransforms.ts - src/hooks/useProjectsState.ts --------- Co-authored-by: Haileyesus <something@gmail.com> Co-authored-by: Simos Mikelatos <simosmik@gmail.com>	2026-03-11 00:16:11 +01:00