@quanta-intellect/vessel-browser 0.1.95 → 0.1.99

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -85,9 +85,10 @@ Today, Vessel provides the browser shell, page visibility, and supervisory surfa
85
85
  - **Agent-first browser model** — Vessel is designed around an agent driving the browser while a human watches, intervenes, and redirects
86
86
  - **Human-visible browser UI** — pages render like a normal browser so agent activity stays legible instead of disappearing into a headless run
87
87
  - **Command Bar** (`Ctrl+L`) — a secondary operator surface for harness-driven workflows and future runtime commands
88
- - **Supervisor Sidebar** (`Ctrl+Shift+L`) — live supervision across seven tabs: Supervisor, Bookmarks, Checkpoints, Chat, Automate, History, and Changes
88
+ - **Supervisor Sidebar** (`Ctrl+Shift+L`) — live supervision across eight tabs: Supervisor, Bookmarks, Checkpoints, Chat, Automate, History, Changes, and Research
89
89
  - **Chat Assistant** — built-in conversational AI in the sidebar Chat tab; supports Anthropic, OpenAI, Ollama, llama.cpp, Mistral, xAI, Google Gemini, OpenRouter, and any OpenAI-compatible endpoint; reads the current page automatically; has full access to the same browser tools as external agents; multi-turn session history; configure provider, model, and API key in Settings
90
90
  - **Automation Kits** (Premium) — parameterized workflow templates in the sidebar Automate tab; fill in a short form and the built-in agent executes the workflow autonomously; bundled kits include Research & Collect (multi-source research with bookmark saving) and Price Scout (cross-retailer price comparison); designed for a future kit marketplace
91
+ - **Research Desk** (Beta) — a dedicated sidebar Research tab for structured research reports; start with a topic, complete an in-tab briefing, let Vessel draft research objectives, approve the plan, then dispatch browser sub-agents to collect source-backed claims and synthesize a markdown-exportable report. Starting the brief is free; plan approval, sub-agent execution, and report export require Vessel Premium.
91
92
  - **Dev Tools Panel** (`F12`) — inspect console output, network requests, and MCP/agent activity in a resizable panel at the bottom of the window; export logs by category and date range as JSON
92
93
  - **Browser Basics For Long Runs** — pinned tabs stay compact at the front of the tab strip and are protected from accidental close; tab groups can be color-coded and collapsed; audible tabs show audio indicators with mute controls; open additional browser windows with `Ctrl+N`; print the active page with `Ctrl+P` or save it directly as PDF with `Ctrl+Shift+P`
93
94
  - **Action Undo / Rollback** — restore the browser to the session snapshot captured immediately before the last successful mutating agent action; available from the Supervisor tab and through the `undo_last_action` tool
@@ -144,7 +145,7 @@ That means the product should optimize for:
144
145
  Main Process Renderer (SolidJS)
145
146
  ├── TabManager (WebContentsView[]) ├── TabBar, AddressBar
146
147
  ├── AgentRuntime (session + supervision) ├── CommandBar (secondary surface)
147
- ├── MCP server for external agents ├── AI Sidebar (Supervisor/Bookmarks/Checkpoints/Chat/Automate)
148
+ ├── MCP server for external agents ├── AI Sidebar (Supervisor/Bookmarks/Checkpoints/Chat/Automate/History/Changes/Research)
148
149
  ├── AI providers (Anthropic + OAI-compat) ├── DevTools Panel (Console/Network/Activity)
149
150
  ├── Supervision, bookmarks, checkpoints ├── Agent Transcript Dock
150
151
  └── IPC Handlers ◄──contextBridge──► ──► └── Signal stores (tabs, ai, ui)
@@ -153,7 +154,7 @@ Main Process Renderer (SolidJS)
153
154
 
154
155
  Each browser tab is a separate `WebContentsView` managed by the main process. The browser chrome (SolidJS) runs in its own view layered on top. All communication between renderer and main goes through typed IPC channels via `contextBridge`.
155
156
 
156
- The sidebar Automate tab renders kit forms entirely in the renderer and passes the rendered prompt to the built-in agent via the same `query()` path used by the Chat tab — no additional IPC surface is needed. The Changes tab reads the current page's diff timeline through IPC and unlocks persisted history for Premium users.
157
+ The sidebar Automate tab renders kit forms entirely in the renderer and passes the rendered prompt to the built-in agent via the same `query()` path used by the Chat tab — no additional IPC surface is needed. The Changes tab reads the current page's diff timeline through IPC and unlocks persisted history for Premium users. The Research tab has a dedicated IPC surface for its state machine: briefing is available to everyone, while objective approval, parallel browser sub-agents, report synthesis, and markdown export are Premium-gated during the beta.
157
158
 
158
159
  ## Getting Started
159
160
 
@@ -255,6 +256,7 @@ Notes:
255
256
  - The default MCP port is `3100`
256
257
  - Hermes Agent and OpenClaw should treat Vessel as the persistent, human-visible browser rather than launching their own separate browser session
257
258
  - Vessel supports a built-in Chat tab with configurable AI provider; open Settings (`Ctrl+,`) and enable Chat Assistant to set a provider and model
259
+ - The sidebar Research tab is marked Beta; use it to turn a broad research topic into a brief, approve a multi-thread plan, run browser sub-agents, and export the final report as markdown. Briefing is free, while full execution and export require Premium.
258
260
  - `llama.cpp (Local)` is a first-class chat provider in Settings and targets `http://localhost:8080/v1` by default; Vessel auto-fetches the active model from `llama-server`
259
261
  - For `llama-server`, use `--ctx-size 16384` minimum and `32768` recommended for reliable Vessel agent loops; lower values often fail once prompt, tool schema, and tool history accumulate
260
262
  - Approval policy is controlled live from the sidebar Supervisor panel rather than a separate global settings screen
@@ -545,7 +547,7 @@ src/
545
547
  │ └── src/
546
548
  │ ├── components/
547
549
  │ │ ├── chrome/ # TitleBar, TabBar, AddressBar, AgentTranscriptDock
548
- │ │ ├── ai/ # CommandBar, Sidebar (Supervisor/Bookmarks/Checkpoints/Chat/Automate/History/Changes)
550
+ │ │ ├── ai/ # CommandBar, Sidebar (Supervisor/Bookmarks/Checkpoints/Chat/Automate/History/Changes/Research)
549
551
  │ │ ├── devtools/ # DevTools panel (Console, Network, Activity)
550
552
  │ │ └── shared/ # Settings panel
551
553
  │ ├── stores/ # SolidJS signal stores (tabs, ai, ui, runtime, bookmarks, etc.)