* feat(web): add workspace browser for multi-directory navigation
Add /browse route with a folder browser that lets users navigate
filesystem directories on connected machines and launch sessions
from any folder. Supports saved workspace paths and direct path
input. The "Start Session" action pre-fills the NewSession form.
- CLI: register machine-level `list-directory` RPC handler
- Hub: add POST /machines/:id/list-directory route
- Web: add WorkspaceBrowser component with git repo detection
- Web: add /browse route with navigation from sessions sidebar
- Web: support initialDirectory/initialMachineId in NewSession
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add --workspace-root opt-in scoping for /browse and session spawn
Adds a single new flag, \`--workspace-root <path>\` (with \`~\` / \`~/foo\`
expansion), on \`hapi runner start\` and \`hapi runner start-sync\`.
When set:
- The runner reports the path in machine metadata.
- The list-directory and spawn-session RPC handlers reject paths outside
the root, so the web UI can't escape the configured tree even if
someone crafts a request manually.
- The /browse page in the web UI auto-opens that root, restricts the
breadcrumb / go-up to its subtree, and shows directory entries with
git-repo annotations.
- The /sessions/new form keeps its existing free-text directory input
plus autocomplete + recent-paths chips, and gains a small "Browse"
button (next to the input) that opens /browse for picking a folder.
- Reconnect-time metadata sync ensures stale records get the field
filled in (or cleared when the flag is dropped on a later restart),
so the hub state matches the CLI's intent.
When unset:
- Runner behaves like the legacy hapi (no scoping, no browse feature).
- /browse renders an informative state pointing at the flag instead of
blocking the user.
- The /sessions/new form looks identical to the pre-change behavior;
the "Browse" button is hidden.
Includes a startup banner so \`runner start-sync\` no longer looks like
it hung, and surfaces the workspace-root sync result on stdout.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(hub): preserve workspaceRoot when rehydrating machines from store
MachineCache.refreshMachine() rebuilt the metadata object from an
explicit field allowlist, so any field not in the list (including the
new workspaceRoot) was silently dropped on every read — even though it
was correctly written to the store.
Add workspaceRoot to the zod schema, the Machine interface, and the
hand-rolled projection.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(web): friendlier empty state on /sessions
When there are zero sessions the page used to be a vast blank
rectangle with just the "0 sessions in 0 projects" caption. Render a
centered empty state instead: a calendar/agenda icon, a short heading
and hint, and two buttons — "Start a session" (→ /sessions/new) and
"Browse workspace" (→ /browse).
SessionList gains an optional onBrowse prop. Router wires it on the
sessions page so the secondary button resolves; other callers can leave
it unset to hide that button.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs: document --workspace-root flag in cli/README and root README
Add a short paragraph under "Runner management" in cli/README.md
explaining what \`--workspace-root\` enables (scoped /browse tree,
list/spawn enforcement, tilde expansion) and that omitting it keeps
the legacy behavior. Mention the workspace browser in the top-level
README's Features list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: address PR #526 review feedback
Three findings from the review bot:
1. [Major] Workspace-scope check was lexical only. With workspaceRoot
= /safe, a symlink such as /safe/out -> /etc would pass the relative-
path test and let list-directory / spawn-happy-session reach paths
outside the configured root. realpath the workspaceRoot at construction
time, and resolve every incoming path through realpath (walking up to
the nearest existing parent for spawn targets that haven't been
created yet) before the containment check.
2. [Minor] \`hapi runner start --workspace-root\` with no value used to
drop the flag silently and start the runner unscoped. Now treats a
missing or flag-shaped next argument as an error.
3. [Minor] /sessions/new's "Browse" button always opened /browse using
localStorage's last-used machine, ignoring the user's current
selection. NewSession already passes machineId in its callback;
forward it through the /browse search params and seed
WorkspaceBrowser with it.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(cli): gate list-directory RPC behind --workspace-root opt-in
Without a configured workspaceRoot, isWithinWorkspaceRoot() returns
true unconditionally, leaving the new list-directory RPC able to
enumerate any path on the runner. The Web UI already hides Browse
for these machines, but the backend should enforce the opt-in too.
Refuse the RPC up front when no workspace root is configured.
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Define PROTOCOL_VERSION constant in shared/src/version.ts
- Server sets X-Hapi-Protocol-Version header on /cli/* responses
- Server includes protocolVersion in /health endpoint
- CLI extracts serverProtocolVersion from API responses
- CLI shows version mismatch hints in both directions
- Add tests for error utilities and version extraction
close#104
Kill entire process tree instead of just the direct child to prevent
orphans when Gemini CLI ignores SIGTERM. Implements killProcessTree that
collects all PIDs synchronously, signals children first, then waits for
termination with auto-escalation to SIGKILL after 2 seconds. Also removes
Node.js signal option from spawn since built-in abort handling doesn't
handle grandchildren.
Add exponential backoff retry mechanism to handle ECONNREFUSED errors when the
server isn't ready yet during daemon startup. This includes:
- New errorUtils module with error classification helpers
- withRetry function in time.ts supporting configurable exponential backoff
- Machine registration retry with sensible defaults (60 attempts, 1-30s delays)
- Error refactoring to consolidate extractErrorInfo utility
close#35
- Added /health endpoint to server for readiness checks (no auth required)
- Created autoStartServer module that auto-starts server when:
- HAPI_SERVER_URL not set (using default localhost:3006)
- cliApiToken exists in settings (server previously used)
- Port 3006 is not currently listening
- Server runs as child process (not daemon) and exits when CLI exits
- Integrated maybeAutoStartServer() into hapi, codex, and gemini commands
When HAPI_WORKTREE_* environment variables are not set, fall back to
probing git to detect if running inside a worktree. This enables
worktree features to work automatically without explicit env vars.
Implement comprehensive worktree session support allowing users to spawn sessions in temporary git worktrees. Includes backend worktree management, full-stack integration, and refined UI for session type selection.
Backend:
- Add worktree creation/removal utilities with branch management
- Track worktree metadata (basePath, branch, name, path) in session metadata
- Automatic cleanup of worktrees when sessions fail or exit
- Enhanced error handling with stderr tail logging
UI improvements:
- Redesign session type toggle with improved alignment and spacing
- Move worktree description inline with label for cleaner layout
- Add branch name input field that appears when worktree mode selected
- Auto-focus on worktree input when switching modes
- Reduce gap between radio options from gap-3 to gap-1.5
- Update descriptive text and placeholders for clarity
Integration:
- Thread worktree parameters through API client, RPC handlers, and daemon
- Add worktreeEnv utility to read worktree info from environment
- Update session spawning to support both simple and worktree modes
Consolidate process lifecycle management (kill, check alive) into a new
utility module with proper Windows/Unix handling, replacing scattered
process.kill() calls with consistent async APIs.
- Add shared isBunCompiled() function for consistent runtime detection
- Support Windows virtual filesystem paths (/~BUN/) alongside Linux/macOS (/$bunfs/)
- Use Bun.main for reliable detection instead of process.argv[1]
- Remove redundant $bunfs checks from cli/src/index.ts
- Update cli/src/utils/bunRuntime.ts to use shared detection function
- Create server/src/utils/bunCompiled.ts for server-side compilation check
Remove tsx dependency and update all dev scripts and documentation to use bun
as the primary TypeScript runtime for development. Consolidate process detection
logic in daemon.ts to check for dev mode via src/index.ts regardless of runtime.
Remove support for custom executable paths and bundled Claude versions, including
deprecated environment variables HAPI_USE_BUNDLED_CLAUDE and HAPI_USE_GLOBAL_CLAUDE.
This simplifies the codebase to rely only on the global Claude CLI installation.
Updates Claude Code spawning logic to remove special handling for .js/.cjs files,
adds configurable BUN_BE_BUN environment variable handling, and streamlines path
resolution to throw an error when Claude Code CLI is not found on PATH.
Migrate HAPI CLI from npm-based distribution to Bun single-executable format:
- Remove npm bin wrappers (bin/happy.mjs, bin/happy-mcp.mjs)
- Simplify package.json: remove npm publish config (exports, main, module, types, files, publishConfig)
- Update bin entry to point to TypeScript source (src/index.ts)
- Migrate shebang from Node to Bun (#!/usr/bin/env bun)
- Simplify build scripts: remove npm-specific steps (pkgroll, prepublishOnly, release-it)
- Update spawnHappyCLI to support compiled binaries and development TypeScript mode
- Update daemon/doctor diagnostics for new process detection logic
- Production: use `bun build --compile` for single-executable releases
- Development: run TypeScript directly via `bun src/index.ts` or `tsx src/index.ts`
- Add support for running CLI from TypeScript source when using tsx or similar tools
- Fix outdated happy__change_title reference to hapi__change_title in codex prompt
This commit rebrands the project from "Happy" to "HAPI" throughout the codebase, including documentation, comments, logs, and tool references. It also adds comprehensive README files for the server and web components, clarifies the monorepo structure in AGENTS.md and root README.md, and removes the outdated roadmap.md file.
Changes include:
- Rebrand references from Happy to HAPI in CLI, server, and web components
- MCP tool names updated from mcp__happy__ to mcp__hapi__
- Process/service names updated consistently
- New server/README.md with deployment and configuration guide
- New web/README.md with stack and development instructions
- Updated root README.md with quickstart guide
- Updated AGENTS.md with cleaner structure documentation
- Removed cli/roadmap.md (now superseded by documentation)
Enables building hapi as standalone Bun-compiled executables for macOS,
Linux, and Windows (x64/arm64). Adds build script, bootstrap entry point,
runtime asset management, and automatic deployment of bundled tools
(ripgrep, difftastic). Includes MCP stdio bridge support and proper
environment handling for compiled binaries. Updates documentation with
build and installation instructions for single executable distribution.
Replace hardcoded 'node' commands with process.execPath to support
Bun runtime alongside Node.js. Add runtime detection and entrypoint
resolution for Bun. Update documentation to reflect multi-runtime support.
