Commit Graph
47 Commits
Author SHA1 Message Date
junesandGitHub 0006d04f9e feat: support multiple workspace roots (#584) 2026-05-07 08:30:52 +08:00
Junmo KimandGitHub 8185f0287e feat(web,hub): cancel queued messages (#568) 2026-05-06 13:32:45 +08:00
Junmo KimandGitHub 9ee014098a feat(opencode): support model selection and mid-session model change (#558)
* refactor(opencode): declare ModelChange capability and add model field to OpencodeMode

Mark opencode flavor as supporting model change by adding Capabilities.ModelChange
to FLAVOR_CAPS.opencode. Add optional `model` field to OpencodeMode so the
set-session-config handler can carry a model alongside the existing permissionMode.

Pure structural change: no behavior change yet. The mid-session model change RPC
and UI wiring follow in subsequent commits, gated by this capability.

* feat(acp): branch setModel by flavor, capture session models metadata, expose getSessionModelsMetadata on AgentBackend interface

Adds an optional `flavor` argument to `AcpSdkBackend.setModel` so it can
dispatch the right `session/*` RPC for each agent flavor without changing
the call site Gemini already uses. Both Gemini and OpenCode wire to
`session/set_model`; the OpenCode response only carries `_meta.opencode`,
so the backend updates the cached `currentModelId` optimistically while
preserving the previously captured `availableModels`.

Captures `availableModels` and `currentModelId` from `session/new` /
`session/load` / `session/set_model` responses into per-session metadata,
exposed as `getSessionModelsMetadata(sessionId)` on the `AgentBackend`
interface so the hub can forward the snapshot to the web client.

* feat(opencode): accept model in set-session-config RPC and forward to launcher

Mirror the Gemini set-session-config handler so the web UI can change the
OpenCode model mid-session. Validates incoming model strings, persists null
("Default") for keepalive metadata, and pushes a keepAlive immediately so
the hub UI reflects the change without waiting for the next 2s tick.

Forward the model through opencodeLoop and into queued OpencodeMode entries
so the launcher can detect a per-batch model change. Add a setModel helper
on OpencodeSession to store the chosen model on the shared session base.

Wire --model up the runner path: parse --model <value> in commands/opencode.ts
and stop excluding opencode in buildCliArgs so the runner spawns OpenCode
with the user-selected initial model.

* feat(opencode): switch model mid-session via ACP RPC

Mirror the Gemini pattern from PR #543: when a user picks a different model
between turns, call backend.setModel with flavor='opencode' so the ACP backend
sends session/set_session_config_option (configId='model') to the running
OpenCode CLI. The next turn then runs against the new model.

The first batch on a fresh session seeds currentBackendModel without firing the
RPC — the OpenCode CLI was launched with that model via --model and there is
nothing to switch yet. If the running build does not implement the RPC we learn
that from the first method-not-found response, latch inline switching off, and
notify the user once. Other errors fall back to the previous model and surface
a one-line failure message.

* feat(hub): expose model selection and discovery for OpenCode sessions

Generalize the /sessions/:id/model guard via supportsModelChange so any flavor
that advertises the ModelChange capability becomes accepted automatically. This
piggybacks on the capability SSOT introduced in PR #400 and turns OpenCode on
without listing flavors inline.

Add a /sessions/:id/opencode-models endpoint that mirrors the existing
codex-models pattern. The endpoint forwards a per-session listOpencodeModels
RPC to the running OpenCode launcher, which returns the availableModels and
currentModelId metadata captured from the ACP session/new and
session/set_session_config_option responses. The web UI consumes this to
render the model dropdown without round-tripping ACP itself.

* feat(web): render OpenCode model dropdown in the chat composer

Mirror the Codex pattern in SessionChat: query /sessions/:id/opencode-models
via a new useOpencodeModels hook and feed the result into the composer's
availableModelOptions. The AssistantChat model dropdown now lists the user's
ollama / mlx / OpenCode Zen models with the same provider/model label that the
ACP server reports, so the picker matches the OpenCode TUI.

Stop falling back to the Claude composer model list when the flavor is
opencode and no custom options are supplied — that fallback briefly surfaced
unrelated Claude models in OpenCode sessions before the RPC response landed.
The NewSession flow keeps an empty MODEL_OPTIONS.opencode for now: model
discovery requires an active OpenCode ACP session, so the dropdown becomes
available once the session boots and stays empty (and hidden) at creation
time.

* feat(cli,hub): add cwd-based OpenCode model discovery RPC

Adds a short-lived `opencode acp` probe that runs `initialize` +
`session/new` against a target cwd to read the `availableModels` /
`currentModelId` snapshot, then tears the subprocess down. Results are
cached for 60s per cwd and concurrent probes coalesce into a single
spawn.

Exposes the probe through:
- `listOpencodeModelsForCwd` JSON-RPC handler on the CLI
- `RpcGateway.listOpencodeModelsForCwd` / `SyncEngine.listOpencodeModelsForCwd`
- `GET /api/machines/:id/opencode-models?cwd=...` on the hub

This lets the web NewSession form discover OpenCode models for a chosen
directory before any session is spawned.

* feat(web): add OpenCode model selector to NewSession with loading and default highlight

Adds a `OpencodeModelSelector` panel that the NewSession form swaps in
when the OpenCode flavor is selected. The panel:

- queries the new `GET /api/machines/:id/opencode-models?cwd=...` endpoint
  via `useOpencodeModelsForCwd` (TanStack Query, 60s staleTime, no retry),
- shows a labelled spinner + skeleton rows while discovering,
- renders an inline error with a Retry button when probing fails,
- renders an empty-state message when the directory yields no models,
- highlights the OpenCode-reported `currentModelId` with a "Default" badge
  and auto-selects it (or the first option) so the form has a sensible
  value if the user hits Enter without scrolling.

Selection is reset whenever the agent / machine / directory changes so a
new probe can establish a fresh default. Directory input is wrapped in
`useDeferredValue` so per-keystroke edits do not spawn a fresh
`opencode acp` probe. The chosen model is forwarded on session spawn
via the existing OpenCode `model` parameter.

Adds en + zh-CN locale strings for the loading / failure / empty / retry
/ default-badge labels.

* fix(cli): guard /machines/:id/opencode-models handler with workspace root check

The machine-scoped `listOpencodeModelsForCwd` RPC handler was registered by
`registerCommonHandlers` without any workspace-root check, so a web client
could pass an arbitrary `cwd` and have the runner spawn an `opencode acp`
subprocess plus a `session/new` against that path. That broke runner
isolation, since peer machine-scoped handlers (`list-directory`,
`spawn-happy-session`) already enforce the configured workspace root.

Re-register the handler in `ApiMachineClient` so it reuses the existing
`resolveForWorkspaceCheck` (realpath-based, with missing-tail walking) and
`isWithinWorkspaceRoot` helpers before delegating to the lower-level probe.
The resolved cwd is forwarded down so symlinked-but-contained paths still
work, while traversal attempts are rejected with the same error shape the
peer handlers use. Added unit tests around the new dispatch path. Addresses
HAPI Bot review on PR #558.

* fix(web): gate opencode model discovery on cwd existence

The new-session form previously enabled `useOpencodeModelsForCwd` as
soon as the OpenCode agent, machine, and any non-empty directory string
were present. Because that hook calls `/machines/:id/opencode-models`
and the CLI handler starts an `opencode acp` probe for that cwd, normal
typing through partial paths could launch expensive 30s OpenCode
subprocesses for non-existent directories before the path-existence
result had validated the final cwd.

Reorder NewSession so `useMachinePathsExists` runs before
`useOpencodeModelsForCwd`, then gate the discovery hook on the
directory having been positively confirmed to exist
(`pathExistence[deferredDirectory] === true`). The decision is
factored into a small pure helper `shouldEnableOpencodeModelDiscovery`
so the contract can be unit-tested without provider scaffolding.

* fix(web): keep current opencode model on shortcut without dynamic options

`getNextModelForFlavor` is invoked by the global Ctrl/Cmd+M shortcut in
`HappyComposer`, which is now active for OpenCode sessions because the
agent backend declares the `ModelChange` capability. When the dynamic
OpenCode model list has not yet been loaded — e.g. the user presses the
shortcut before `/opencode-models` returns — the function received an
`undefined`/empty `customOptions` and fell through to the Claude preset
cycler, which would emit `sonnet`/`opus` for an OpenCode session. The
following turn then attempted `session/set_model` with a Claude model id
that no OpenCode provider can serve.

Add an `opencode` branch that returns the (normalized) current model
unchanged when no dynamic options are available, mirroring the existing
empty-list policy of `getModelOptionsForFlavor`. Unit tests cover the
undefined / empty / null-current-model variants and lock the
no-Claude-fallback contract. Addresses HAPI Bot review on PR #558.
2026-05-03 12:50:22 +08:00
010dc41369 feat: workspace browser with --workspace-root opt-in scoping (#526)
* 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>
2026-04-26 09:59:18 +08:00
xiaobaifly7andGitHub 4ec9537e4a feat(hub): add ServerChan task notifications (#515)
* fix(hub): 修复发送后状态显示延迟

* feat(hub): 接入Server酱任务通知

* fix(hub): 仅在会话结束时发送完成通知

* fix(hub): avoid reviving inactive queued sessions

* fix(hub): address notification review feedback

* fix(hub): expire queued thinking on hub clock

* fix(hub): 修复任务通知 review 反馈
2026-04-25 22:01:02 +08:00
Junmo KimandGitHub 32755f9056 feat(web): show queued status for messages pending inference (#492) 2026-04-20 19:49:26 +08:00
Junmo KimandGitHub e6eaff83c5 fix(hub,cli): forward permissionMode on session resume (#460)
* feat(hub,cli): forward permissionMode on session resume

When a session is resumed, the cached permissionMode is now forwarded
through the Hub → Runner → CLI pipeline via a new --permission-mode
flag. Previously the mode was lost on resume, resetting to 'default'.

Each CLI flavor validates the flag value against its own allowed
permission modes (e.g. CLAUDE_PERMISSION_MODES) and rejects unknown
values. The existing --yolo flag is preserved as a shorthand.

* refactor(cli): extract buildCliArgs from startRunner

Extract the CLI argument construction logic into a standalone
exported function so it can be unit-tested independently.
No behavior change.

* test(cli): add buildCliArgs unit tests for --permission-mode

Verify that the runner correctly forwards valid permission modes
via --permission-mode, rejects invalid values, and falls back to
--yolo when no permission mode is set.

* fix(cli): let --permission-mode take precedence over --yolo

When both flags are present, --permission-mode was silently
overwritten by a later --yolo. Guard legacy flag branches with
a hasExplicitPermissionMode check so the explicit flag wins.
2026-04-15 11:13:21 +08:00
ShujakuinandGitHub 0bffb03b05 feat(cli): support optional extra headers for hub requests (#445)
* feat(cli): support extra headers for hub requests

* fix(types): normalize missing session fields to null

* refactor(cli): simplify socket extra headers config
2026-04-14 13:54:51 +08:00
weishu 79a13d26c6 Fix Codex reasoning effort resume and updates 2026-04-10 11:50:03 +08:00
Haoqing WangandGitHub 279f75815e fix(cli): prevent system-injected messages from appearing as user role (#361) 2026-03-26 08:06:30 +08:00
a200fe9628 feat(claude): add effort setting parity with model across stack (#353)
Co-authored-by: Xiaoyi <xiaoyizhang@microsoft.com>
2026-03-24 21:15:48 +08:00
Junmo KimandGitHub d76b1a6ac0 refactor: introduce model-agnostic agent interfaces (#323) 2026-03-20 08:45:32 +08:00
ROOOOandGitHub cb09f0b898 feat: add codex reasoning effort option (#297) 2026-03-17 22:55:55 +08:00
ROOOOandGitHub caa76826f4 fix(cli): preserve invoked cwd for local launcher (#299) 2026-03-17 22:55:23 +08:00
weishu 16829b7c78 Add support for codex plan mode 2026-03-16 20:48:39 +08:00
weishu 329d28a93c remove , using instead 2026-03-16 18:29:09 +08:00
weishu 02c8e12e80 unify model selection 2026-03-16 18:29:09 +08:00
4716d315b7 feat: improve spawn error handling and reporting across full stack (#249)
* feat: improve spawn error handling and reporting across full stack

- Return error result instead of throwing in apiMachine spawn handler
- Add lastSpawnError field to RunnerState for persistent error tracking
- Add error awaiter system for early process exit/error detection before webhook
- Build detailed webhook failure messages with exit code, signal, and stderr tail
- Report spawn outcomes to hub via runner state updates
- Handle more spawn result types in rpcGateway with better error messages
- Display runner last spawn error in web UI (NewSession & SpawnSession)
- Extract shared formatRunnerSpawnError utility to avoid duplication

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(cli): narrow spawnResult type check to fix TS2339 error

Use `type === 'error'` instead of `type !== 'success'` to properly
narrow the discriminated union, allowing TypeScript to infer errorMessage.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-09 20:55:50 +08:00
weishu 37e10a831b feat: rename server package to hub
Rename the `server/` directory to `hub/` and update all references
across CLI, docs, web, and workspace configuration.
2026-01-27 19:51:21 +08:00
weishu 1b22fe0f82 feat: add CLI-server protocol version mismatch detection
- 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
2026-01-27 16:28:52 +08:00
weishu 87c79c3b94 feat: add session resume capability with automatic continuation
Add ability to resume inactive sessions and automatically continue with new
session ID. Includes message merging for preserving conversation history,
UI improvements to allow sending during inactive state, and database schema
migration. close #87
2026-01-27 14:44:53 +08:00
weishu 6567f22978 refactor: remove passthrough() from zod schemas and make validation explicit
- Replace .passthrough() with explicit field definitions across all schemas
- Add missing optional fields (homeDir, happyHomeDir, happyLibDir, displayName)
- Refactor RawJSONLinesSchema to use structured base schema for clarity
- Improve schema validation strictness and type safety
- Update Machine interface to reflect explicit fields instead of index signature
2026-01-23 16:04:37 +08:00
weishu 6f8f44a314 refactor: move attachment metadata schema to shared protocol package 2026-01-23 16:04:37 +08:00
weishu 78f56ad0f7 refactor: migrate socket types and payloads to shared protocol package
Move socket-related type definitions and schemas from cli and server packages
into a shared @hapi/protocol package for centralized type management. This
includes migrating Update types, socket event interfaces (ClientToServerEvents,
ServerToClientEvents), and terminal payload schemas. Add strongly-typed socket
handlers that reference the protocol package instead of duplicating definitions.
2026-01-23 16:04:37 +08:00
weishu e130dfd24b feat: add model selection for AI agents (claude, codex, gemini)
Add a new ModelSelector component that allows users to choose specific model variants for different AI agents. This includes:
- ModelSelector UI component with agent-specific model options
- Model parameter propagation through API, RPC, and spawning layers
- Support for auto model selection (default behavior)
- Localization strings for English and Chinese
- Type definitions for model options per agent
2026-01-23 11:55:29 +08:00
weishu 53fff54c84 Release version 0.10.0 2026-01-19 13:07:25 +08:00
weishu 9e335fa305 refactor: rename configuration variables for clarity
Standardize naming across CLI and server components:
- CLI: serverUrl → apiUrl, HAPI_SERVER_URL → HAPI_API_URL
- Server: webapp* → listen*, miniAppUrl → publicUrl, WEBAPP_* → HAPI_LISTEN_*, WEBAPP_URL → HAPI_PUBLIC_URL
- Rename serverUrlInit.ts → apiUrlInit.ts with updated logic for backward compatibility
- Update all imports, function calls, and documentation accordingly
2026-01-19 12:57:37 +08:00
weishu 0228146b99 refactor: rename daemon to runner throughout codebase 2026-01-19 11:12:48 +08:00
weishu 53e4de6684 feat: add file upload support 2026-01-17 19:38:12 +08:00
weishu f33d142446 fix: send session-alive signal immediately on socket connect to prevent initial offline flicker 2026-01-15 22:21:03 +08:00
weishu d388c92114 refactor: remove CLI dead code
Remove unused daemon installation/uninstallation logic and unnecessary re-exports:
- Delete cli/src/daemon/mac/ directory (macOS LaunchDaemon install/uninstall not used)
- Delete cli/src/daemon/install.ts and uninstall.ts wrappers
- Remove daemon install/uninstall subcommands from cli/src/commands/daemon.ts
- Delete cli/src/api/encryption.ts (misleading name, just base64 encoding)
- Inline base64 encoding directly in cli/src/persistence.ts
- Delete cli/src/modules/common/gitHandlers.ts (unnecessary re-export)
- Update cli/src/modules/common/registerCommonHandlers.ts to import directly from handlers/git

Part of refactoring plan item #1 "删除 CLI 死代码".
2026-01-05 13:00:48 +08:00
weishu 7a487269ea refactor: replace hardcoded permission/model modes with centralized schema validation
Extract permission and model mode validation into reusable functions utilizing
@hapi/protocol schemas. Use isPermissionModeAllowedForFlavor and
isModelModeAllowedForFlavor to validate modes based on session flavor (claude/codex).
Replace inline type definitions with shared types from @hapi/protocol.
2026-01-04 22:07:03 +08:00
weishu f2f46e9383 refactor(api): extract versioned update handling to shared utility
Extract duplicate version acknowledgment logic from apiMachine and
apiSession into a reusable applyVersionedAck utility. This handles
success, version-mismatch, and error responses consistently with
customizable parsing and error handling via options object.
2026-01-03 22:23:29 +08:00
weishu aa0c3f2f0d refactor(cli): split command routing and modularize RPC handlers
Restructure CLI entry point and RPC handler registration to improve maintainability:

- Introduce command registry pattern with CommandDefinition interface for consistent command structure
- Extract individual command modules (claude, codex, daemon, doctor, gemini, auth, connect, etc.)
- Move RPC handlers into separate feature modules (bash, files, git, directories, ripgrep, difftastic, slashCommands)
- Create shared RPC types and response helpers (rpcTypes.ts, rpcResponses.ts)
- Move SpawnSessionOptions and SpawnSessionResult to rpcTypes for proper type organization
- Simplify index.ts to minimal entrypoint using command registry
- Update imports in apiMachine.ts and daemon/run.ts to use rpcTypes module

This enables:
- Better code organization by feature/command
- Easier testing of individual commands
- Safer RPC handler registration without side effects
- Clearer separation of concerns between routing and business logic
2026-01-03 17:29:05 +08:00
weishu e2028b6914 Unify protocol types and modes 2026-01-03 14:43:59 +08:00
weishu e821458af8 feat: add namespace-based multi-user isolation
Implement namespace support across sessions, machines, and users for multi-user server deployments. Add access control with specific error reasons (namespace-missing, access-denied, not-found) and database schema updates with namespace columns and indexes.
2025-12-31 21:56:01 +08:00
weishu b160888101 feat: implement message backfill to prevent message loss on reconnection 2025-12-30 13:22:27 +08:00
weishu 334cebc2da feat: add real-time permission and model mode synchronization close #21
Implements bidirectional sync of permission/model modes between CLI sessions and web app. Adds Codex-specific permission modes (read-only, safe-yolo, yolo) alongside Claude's modes. Web can now control CLI session state via RPC set-session-config handler, while CLI broadcasts state changes through keep-alive payloads. UI controls are flavor-aware, showing appropriate modes for Claude vs Codex vs Gemini. Type centralization in api/types eliminates circular dependencies.
2025-12-28 20:51:18 +08:00
weishu 05deb6fff8 feat: add directory autocomplete with validation for new session form 2025-12-28 16:31:53 +08:00
weishu c35a5ce827 feat: add git worktree session support with improved UI
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
2025-12-28 13:17:58 +08:00
58e61b3db9 feat: create new session with yolo mode (#13)
* feat: create new session with yolo mode

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>

* fix: harden sequence typecheck

* feat: add unified --yolo flag across all agents

---------

Signed-off-by: Ruihang Xia <waynestxia@gmail.com>
Co-authored-by: weishu <twsxtd@gmail.com>
2025-12-27 21:03:34 +08:00
weishu 18e6310451 feat: implement web terminal feature with xterm.js and Socket.IO proxy
- Add CLI-side terminal management via Bun.Terminal with TerminalManager
- Implement server-side Socket.IO proxy for terminal I/O between web and CLI
- Create web terminal UI component with xterm.js and support for resize/reconnect
- Add terminal route and navigation button in session chat
- Include comprehensive terminal implementation plan and architecture docs
2025-12-25 21:57:18 +08:00
weishu 2a10ce9675 feat: add support for user message events from Codex
Add sendUserMessage() method to ApiSessionClient and CodexSession to handle
user_message events from Codex. Updates CodexConversionResult type and
convertCodexEvent() to process user_message payloads, with test coverage.
2025-12-24 17:24:16 +08:00
weishu 4290f539bd refactor(codex): extract session management and launcher logic into separate modules
Reorganized runCodex.ts to improve maintainability by extracting:
- CodexSession class for session lifecycle management
- CodexLocalLauncher and CodexRemoteLauncher for mode-specific initialization
- CodexEventConverter for MCP message handling and UI buffer updates
- CodexSessionScanner for resume file discovery
- emitReadyIfIdle utility for ready event emission

Added codexSessionId field to metadata schema for session tracking.
Updated UI components to work with refactored architecture.
2025-12-22 19:14:47 +08:00
weishu 4f03f29ac3 docs: rebrand Happy to HAPI and add component documentation
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)
2025-12-21 18:49:04 +08:00
weishu ac67718ec0 feat: implement AskUserQuestion tool with interactive UI and question flow
Add comprehensive support for the AskUserQuestion tool including:
- New footer component for handling user responses with multi-step question flow
- Type definitions and parsing utilities for question and answer formats
- View component for displaying questions and options
- Integration with permission system to capture user answers
- Support for single and multi-select questions with optional text input
- Haptic feedback and error handling for better UX
2025-12-18 23:24:41 +08:00
weishu b4654acb92 init 2025-12-16 15:03:50 +08:00