docs: reflect Phase 3 agent SDK integration progress

Update phases.md with Phase 3 checklist (in_progress), add session
progress log entry, record claude CLI architecture decision in
task_plan.md, update README/TODO/CHANGELOG with Phase 3 additions,
and sync .claude/CLAUDE.md with current constraints.
This commit is contained in:
Hibryda 2026-03-06 01:02:13 +01:00
parent 314c6d77aa
commit c24e540080
7 changed files with 65 additions and 22 deletions

View file

@ -4,7 +4,7 @@
- v1 is a single-file Python app (`bterminal.py`). Changes are localized.
- v2 docs are in `docs/`. Architecture decisions are in `docs/task_plan.md`.
- Phase 2 (Terminal Pane + Layout) is complete. Phase 3 (Agent SDK) is next.
- Phase 3 (Agent SDK Integration) is in progress. Core implementation done, needs testing and polish.
- Consult Memora (tag: `bterminal`) before making architectural changes.
## Documentation References
@ -25,8 +25,9 @@
## Key Technical Constraints
- WebKit2GTK has no WebGL — xterm.js must use Canvas addon explicitly.
- Claude Agent SDK is 0.2.x (pre-1.0) — all SDK interactions go through the adapter layer (`src/lib/adapters/sdk-messages.ts`).
- Node.js sidecar communicates via stdio NDJSON, not sockets.
- Agent sessions use `claude` CLI with `--output-format stream-json` (not Agent SDK npm package). All output goes through the adapter layer (`src/lib/adapters/sdk-messages.ts`).
- Node.js sidecar (`sidecar/agent-runner.ts`) spawns claude subprocesses, communicates with Rust via stdio NDJSON.
- Agent dispatcher (`src/lib/agent-dispatcher.ts`) is a singleton that routes sidecar events to the agent store.
- Maximum 4 active xterm.js instances to avoid WebKit2GTK memory issues.
## Memora Tags

View file

@ -8,6 +8,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
### Added
- Agent pane with prompt input, structured message rendering, stop button, and cost display (Phase 3)
- Node.js sidecar manager (Rust) for spawning and communicating with agent-runner via stdio NDJSON (Phase 3)
- Agent-runner sidecar: spawns `claude` CLI with `--output-format stream-json` for structured agent output (Phase 3)
- SDK message adapter parsing stream-json into 9 typed message types: init, text, thinking, tool_call, tool_result, status, cost, error, unknown (Phase 3)
- Agent bridge adapter for Tauri IPC (invoke + event listeners) (Phase 3)
- Agent dispatcher routing sidecar events to agent session store (Phase 3)
- Agent session store with message history, cost tracking, and lifecycle management (Phase 3)
- Keyboard shortcut: Ctrl+Shift+N to open new agent pane (Phase 3)
- Sidebar button for creating new agent sessions (Phase 3)
- Rust PTY backend with portable-pty: spawn, write, resize, kill with Tauri event streaming (Phase 2)
- xterm.js terminal pane with Canvas addon, FitAddon, and Catppuccin Mocha theme (Phase 2)
- CSS Grid tiling layout with 5 presets: 1-col, 2-col, 3-col, 2x2, master-stack (Phase 2)

View file

@ -2,7 +2,7 @@
Terminal with session panel (MobaXterm-style), built with GTK 3 + VTE. Catppuccin Mocha theme.
> **v2 in progress (Phase 2 complete):** Redesign as a multi-session Claude agent dashboard using Tauri 2.x + Svelte 5 + Claude Agent SDK. Working multi-pane terminal with PTY backend, CSS Grid tiling, and Catppuccin theme on branch `v2-mission-control`. See [docs/task_plan.md](docs/task_plan.md) for architecture and [docs/phases.md](docs/phases.md) for implementation plan.
> **v2 in progress (Phase 3 in progress):** Redesign as a multi-session Claude agent dashboard using Tauri 2.x + Svelte 5. Working multi-pane terminal with PTY backend, agent panes with structured output from `claude` CLI, CSS Grid tiling, and Catppuccin theme on branch `v2-mission-control`. See [docs/task_plan.md](docs/task_plan.md) for architecture and [docs/phases.md](docs/phases.md) for implementation plan.
![BTerminal](screenshot.png)

View file

@ -2,7 +2,7 @@
## Active
- [ ] **Phase 3: Agent SDK Integration** — Node.js sidecar, SDK message adapter, structured agent panes with tool call cards.
- [ ] **Phase 3: Agent SDK Integration (polish)** — Markdown rendering in agent text, sidecar crash detection/restart, auto-scroll lock, testing.
- [ ] **Phase 4: Session Management + Markdown** — SQLite persistence, session CRUD, file watcher, markdown rendering. MVP ship after this phase.
- [ ] **Pane drag-resize handles** — Deferred from Phase 2, current presets sufficient for MVP.
- [ ] **Copy/paste (Ctrl+Shift+C/V)** — Deferred from Phase 2.
@ -10,5 +10,6 @@
## Completed
- [x] **Phase 3: Agent SDK Integration (core)** — Sidecar manager, agent-runner (claude CLI subprocess), SDK message adapter (stream-json), agent pane with message rendering/cost/stop. | Done: 2026-03-06
- [x] **Phase 2: Terminal Pane + Layout** — PTY backend (portable-pty), xterm.js + Canvas addon, CSS Grid tiling (5 presets), sidebar, keyboard shortcuts. | Done: 2026-03-05
- [x] **Phase 1: Project Scaffolding** — Tauri 2.x + Svelte 5 scaffolded in `v2/`, Catppuccin theme, Rust stubs, sidecar scaffold. | Done: 2026-03-05

View file

@ -107,22 +107,35 @@ bterminal-v2/
---
## Phase 3: Agent SDK Integration [status: not_started] — MVP
## Phase 3: Agent SDK Integration [status: in_progress] — MVP
- [ ] Node.js sidecar: thin wrapper around Agent SDK `query()`
- [ ] Sidecar communication: Rust spawns Node.js, stdio NDJSON
- [ ] Sidecar lifecycle: spawn on demand, detect crash, restart
- [ ] SDK message adapter (abstraction layer)
- [ ] Agent pane: renders structured messages
- Text -> markdown rendered
- Tool calls -> collapsible cards (tool name + input + output)
- Subagent spawn -> tree node + optional new pane
- Errors -> highlighted error card
- Cost/tokens -> pane header metrics
### Backend
- [x] Node.js sidecar: spawns `claude` CLI with `--output-format stream-json` (not Agent SDK query() — avoids npm dep + version churn)
- [x] Sidecar communication: Rust spawns Node.js, stdio NDJSON
- [x] Sidecar lifecycle: auto-start on app launch, shutdown on exit
- [ ] Sidecar lifecycle: detect crash, offer restart in UI
- [x] Tauri commands: agent_query, agent_stop, agent_ready
### Frontend
- [x] SDK message adapter: parses stream-json into 9 typed AgentMessage types (abstraction layer)
- [x] Agent bridge: Tauri IPC adapter (invoke + event listeners)
- [x] Agent dispatcher: singleton routing sidecar events to store
- [x] Agent store: session state, message history, cost tracking (Svelte 5 $state)
- [x] Agent pane: renders structured messages
- [x] Text -> plain text (markdown rendering deferred)
- [x] Tool calls -> collapsible cards (tool name + input)
- [x] Tool results -> collapsible cards
- [x] Thinking -> collapsible details
- [x] Init -> model badge
- [x] Cost -> USD/tokens/turns/duration summary
- [x] Errors -> highlighted error card
- [ ] Subagent spawn -> tree node + optional new pane (Phase 5)
- [x] Agent status indicator (starting/running/done/error)
- [x] Start/stop agent from UI (prompt form + stop button)
- [ ] Auto-scroll with scroll-lock on user scroll-up
- [ ] Agent status indicator (running/thinking/waiting/done/error)
- [ ] Start/stop/cancel agent from UI
- [ ] Session resume (SDK `resume: sessionId`)
- [x] Keyboard: Ctrl+Shift+N new agent
- [x] Sidebar: agent session button
**Milestone: After Phase 3, we have the core differentiator.** SDK agents run in structured panes alongside raw terminals.

View file

@ -60,5 +60,23 @@
- [x] npm dependencies: @xterm/xterm, @xterm/addon-canvas, @xterm/addon-fit
- [x] Cargo dependencies: portable-pty, uuid
### Phase 3: Agent SDK Integration (in progress)
- [x] Rust SidecarManager: spawn Node.js, stdio NDJSON, query/stop/shutdown (sidecar.rs, 218 lines)
- [x] Node.js agent-runner: spawns `claude -p --output-format stream-json`, manages sessions (agent-runner.ts, 176 lines)
- [x] Tauri commands: agent_query, agent_stop, agent_ready in lib.rs
- [x] Sidecar auto-start on app launch
- [x] SDK message adapter: full stream-json parser with 9 typed message types (sdk-messages.ts, 234 lines)
- [x] Agent bridge: Tauri IPC adapter for sidecar communication (agent-bridge.ts, 53 lines)
- [x] Agent dispatcher: routes sidecar events to agent store (agent-dispatcher.ts, 87 lines)
- [x] Agent store: session state with messages, cost tracking (agents.ts, 91 lines)
- [x] AgentPane component: prompt input, message rendering, stop button, cost display (AgentPane.svelte, 420 lines)
- [x] UI integration: Ctrl+Shift+N for new agent, sidebar agent button, TilingGrid routing
Architecture decision: Uses `claude` CLI with `--output-format stream-json` instead of Agent SDK `query()` API. Avoids SDK npm dependency and version churn while getting identical structured output.
### Next Steps
- [ ] Begin Phase 3: Agent SDK Integration (Node.js sidecar, SDK message adapter)
- [ ] Markdown rendering in agent text messages
- [ ] Sidecar crash detection and restart UI
- [ ] Auto-scroll lock on user scroll-up
- [ ] Testing: vitest for sdk-messages adapter, cargo test for sidecar
- [ ] Begin Phase 4: Session Management + Markdown Viewer

View file

@ -3,7 +3,7 @@
## Goal
Redesign BTerminal from a GTK3 terminal emulator into a **multi-session Claude agent dashboard** optimized for 32:9 ultrawide (5120x1440). Simultaneous visibility of all active sessions, agent tree visualization, inline markdown rendering, maximum information density.
## Status: BUILDING (Phase 2 complete — Rev 2)
## Status: BUILDING (Phase 3 in progress — Rev 2)
---
@ -74,9 +74,9 @@ The Agent SDK cannot run in Rust or the webview. Solution:
└─────────────────────────────────────────────────────┘
```
- Rust spawns Node.js child process on demand (when user starts an SDK agent session)
- Rust spawns Node.js child process on app launch (auto-start in setup)
- Communication: stdio with newline-delimited JSON (simple, no socket server)
- Node.js process runs a thin wrapper that calls `query()` and forwards messages
- Node.js process runs a thin wrapper that spawns `claude -p --output-format stream-json` and forwards NDJSON events
- If sidecar crashes: detect via process exit, show error in UI, offer restart
- **Packaging:** Bundle the sidecar JS as a single file (esbuild bundle). Require Node.js 20+ as system dependency. Document in install.sh.
- **Future:** Could replace Node.js with Deno (single binary, no npm) for better packaging.
@ -123,6 +123,7 @@ See [phases.md](phases.md) for the full phased implementation plan (Phases 1-6).
| SDK abstraction layer | SDK is 0.2.x, 127 versions in 5 months. Must insulate UI from wire format changes | 2026-03-05 |
| MVP = Phases 1-4 | Ship usable tool before tackling tree viz, packaging, polish | 2026-03-05 |
| Canvas addon (not WebGL) | WebKit2GTK has no WebGL. Explicit Canvas addon avoids silent fallback | 2026-03-05 |
| claude CLI over Agent SDK query() | Use `claude -p --output-format stream-json` instead of SDK npm package. Avoids dependency + version churn, identical structured output | 2026-03-06 |
## Open Questions