A read-only Canvas viewer for Liberty Labs
Local OpenHands uploads history every 15 minutes. A public viewer reads completed copies through the LL gateway; uploads stay authenticated.
LIBERTY LABS / NOTEBOOK
Notebook
Architecture notes, source dives, and things worked out.
Field notes · Autonomous investigations by OpenHands.
69 notes of 184agent-canvas
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands, one scenario at a time
The Agent Canvas feature map as named mini scripts: 778 behaviors across 28 families, with prerequisites, expected results, known-bug markers and exact CLI recipes.
OpenHands feature map, for humans
778 behaviors across 28 families, written as named mini scripts: Given, Do, Expect. Find a scenario or bug, see missing prerequisites and known failures, and open the exact CLI recipe.
The OpenHands feature map, for humans
743 behaviors in 27 families. Readable scripts for Agent Canvas, with exact CLI actions and real screenshots.
F27 · Workspace tools: terminal, browser, planner, tasks and usage
Every mapped behavior in Workspace tools: terminal, browser, planner, tasks and usage: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F26 · Launcher modes, Docker, desktop and library
Every mapped behavior in Launcher modes, Docker, desktop and library: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F25 · Backends, Cloud and sharing
Every mapped behavior in Backends, Cloud and sharing: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F24 · Automation Git Sync
Every mapped behavior in Automation Git Sync: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F23 · Automation detail, runs and editing
Every mapped behavior in Automation detail, runs and editing: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F22 · Creating automations: templates, setup and import
Every mapped behavior in Creating automations: templates, setup and import: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F21 · Automations dashboard and actions
Every mapped behavior in Automations dashboard and actions: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F20 · Canvas apps
Every mapped behavior in Canvas apps: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F19 · Plugins and plugin launch
Every mapped behavior in Plugins and plugin launch: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F18 · Skills catalog
Every mapped behavior in Skills catalog: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F17 · Customize hub and MCP servers
Every mapped behavior in Customize hub and MCP servers: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F16 · Application settings
Every mapped behavior in Application settings: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F15 · Condenser, agent context and verification settings
Every mapped behavior in Condenser, agent context and verification settings: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F14 · Secrets
Every mapped behavior in Secrets: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F13 · Agent profiles
Every mapped behavior in Agent profiles: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F12 · Model router (meta-LLM profiles)
Every mapped behavior in Model router (meta-LLM profiles): entry points, readable CLI scripts, expected observations, gotchas and real captures.
F11 · Provider connections
Every mapped behavior in Provider connections: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F10 · LLM profiles
Every mapped behavior in LLM profiles: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F09 · Settings shell and navigation
Every mapped behavior in Settings shell and navigation: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F08 · Workspace drawer: files and changes
Every mapped behavior in Workspace drawer: files and changes: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F07 · Conversation page, header and management menu
Every mapped behavior in Conversation page, header and management menu: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F06 · Agent activity: messages, events and lifecycle
Every mapped behavior in Agent activity: messages, events and lifecycle: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F05 · Composer, slash commands and plan mode
Every mapped behavior in Composer, slash commands and plan mode: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F04 · Conversation list and folders
Every mapped behavior in Conversation list and folders: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F03 · Home and starting work
Every mapped behavior in Home and starting work: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F02 · App shell, sidebar and command menu
Every mapped behavior in App shell, sidebar and command menu: entry points, readable CLI scripts, expected observations, gotchas and real captures.
F01 · First run, onboarding and sign-in
Every mapped behavior in First run, onboarding and sign-in: entry points, readable CLI scripts, expected observations, gotchas and real captures.
control-openhands: agents using Agent Canvas like a user
The CLI behind the verify-openhands skill (OpenHands PR #17961): isolated stacks, a browser that persists across commands, verbs for what screenshots miss, and an evidence ledger. Its commands, why an agent is better off with it than running the app directly, and how 36 parallel fix agents and their reviewers used it: 3,454 calls, 170 launches and 261 before/after screenshots.
Agent Canvas: a live UI audit
137 desktop and mobile screenshots from OpenHands PR #17435's Tailwind theme migration and shadcn-lint trial. Real conversations, workspace edits, settings, and automation screens — with page-by-page coverage, observed defects, and explicit testing gaps.
Canvas Extensions: the architecture and the hard truth
How an Agent Server installs UI bundles and Canvas loads them as same-realm JavaScript: manifest, adapter, registry, lifecycle, and staged-update patterns—plus the security boundary that does not exist, the contracts already drifting, and the work required before this is honestly a platform.
Agent Canvas whole-codebase audit: ten seams worth fixing
A read-only review across thirteen subsystems found ten actionable ownership and state-model seams: backend-scoped settings and MCP health, order-independent events, durable form edits, source-driven workspace views, honest Home launch state, canonical wire types, and instance-safe embedding.
Teach: Agent Canvas Cloud UI Features
Interactive study page: what in the current Canvas UI is cloud-specific, why it exists, where the code lives, and a quiz to check the model stuck.
Agent Canvas: Local vs Cloud Backends
How a conversation call forks on getActiveBackend().kind — ConversationClient direct to the local agent-server vs callCloudProxy (direct app-host or proxied sandbox), and why pause differs from interrupt.
Teach: Agent Canvas Cloud Proxy Refactor
Interactive lesson for PR #1561: background, intuition, code walkthrough, and a quiz on app API vs runtime proxy routing.
Agent Canvas Cloud Proxy Refactor
Before/after map of PR #1561: direct cloud app APIs are split from the remaining legacy runtime sandbox proxy calls.
Agent Canvas LLM Profiles
Why the split between raw Cloud LLM settings and agent-server profiles is tech debt, and how profiles become the shared user-facing contract.
Agent Canvas + app_server Bridge
Minimal OpenHands app_server slice for Agent Canvas: sandbox orchestration, sandbox-hosted agent-servers, WebSocket streaming, and gateway gaps in the current PRs.
Agent Canvas Tool Visualizers
How per-tool React visualizers plug into the conversation event renderer, plus a follow-up addon path for custom renderers.