---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/products/openhands/"
data_url: "https://podium.do/compare/agents/products/openhands/data.json"
generated_at: 2026-11-22
oldest_checked_at: 2026-11-07
last_checked_at: 2026-11-22
publisher: "Podium"
---

# OpenHands: ADE findings

> Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. Sourced findings follow the same evidence rules for Podium and its competitors. Facts labeled Podium team research come from Podium's own team and have no linked source. None of this removes the conflict of interest.

> Based on data from adecomparison.com by Podium (https://adecomparison.com; source repository https://github.com/madeinorbit/ade-comparison, snapshot 4322f0c of 2026-11-22), used under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Source links and check dates are kept. Podium arranges the findings into pairs, applies its publication checks, and added its own research where marked "Podium team research". Data license terms: https://github.com/madeinorbit/ade-comparison/blob/4322f0c035f303791413639d1462a138443d8c1e/DATA-LICENSE.md

39 of 51 criteria have a sourced finding; 36 were also cross-checked by a second agent. Source checks: 2026-11-07 to 2026-11-22. A missing sourced finding is not evidence that a capability is absent.

- Website: https://www.openhands.dev/
- Canonical HTML: https://podium.do/compare/agents/products/openhands/
- Machine-readable JSON: https://podium.do/compare/agents/products/openhands/data.json
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Comparisons with OpenHands on podium.do: 1 (listed in the JSON and HTML)
- Compare OpenHands with any other product on adecomparison.com by Podium: https://adecomparison.com/compare/?products=openhands

## Access and agent choice

### ACC-01: Client access

Verification status: Sourced (sourced)
Support: partial

Canvas provides desktop installation paths, browser UI and documented phone/tablet browser access. A separate public source-built native mobile MVP supports iOS/Android direct Agent Server access, including conversation listing and message sending; Cloud login and Canvas pairing remain planned. The product-owned agent-canvas command launches the local stack.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, Public source-built OpenHands native mobile MVP for direct Agent Server access; version=e14b76cca01a71597cee242c202eed730e745ce3 Canvas launcher; source-built native mobile MVP 47f815b1d111b6a71b405dcb77acb3682da59b85; plan=Canvas desktop/browser and launcher; native mobile is limited to direct Agent Server access, without Cloud login or Canvas pairing.; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

- desktop_os — Desktop os [partial]: macOS, Windows and Linux installation is advertised; minimum OS versions unverified. Sources: openhands:nov07-canvas.
- mobile_apps — Mobile apps [partial]: The native Expo source MVP builds for iOS and Android and can list/stream/send to a reachable Agent Server using a session API key. Requires native toolchains; Cloud login, QR pairing and laptop facade are not built. Sources: openhands:gap39-mobile-doc, openhands:gap39-mobile-code.
- browser — Browser [supported]: Browser frontend served by Canvas. Sources: openhands:nov07-readme, openhands:nov07-canvas.
- mobile_browser — Mobile browser [supported]: Open Canvas in a phone/tablet browser through Tailscale or authenticated ngrok/public mode. Sources: openhands:gap-phone.
- cli — Cli [supported]: The agent-canvas command launches the local server/automation/frontend stack and supports help/info/version and deployment flags. This is launcher scope. Sources: openhands:gap39-cli.
- editor_extensions — Editor extensions [unknown]: Editor extensions: The November first-party documentation and repository pass did not establish client access at the rubric's required scope. No installed-product fixture was run.
- task_actions — Task actions [unknown]: Task actions: The November first-party documentation and repository pass did not establish client access at the rubric's required scope. No installed-product fixture was run.
- notifications — Notifications [unknown]: Notifications: The November first-party documentation and repository pass did not establish client access at the rubric's required scope. No installed-product fixture was run.
- cross_device_continuity — Cross device continuity [partial]: Phone/tablet browsers can reach the same host Canvas/backend through Tailscale or authenticated ngrok; continuing a specific task across devices is not described and no desktop-phone handoff fixture was run. Sources: openhands:gap-phone.

Checked 2026-11-07 (15 days old on 2026-11-22); not separately cross-checked.

Sources: openhands:nov07-readme, openhands:nov07-canvas, openhands:gap-phone, openhands:gap39-mobile-doc, openhands:gap39-mobile-code, openhands:gap39-cli

### ACC-02: Agent and model choice

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas integrates OpenHands and ACP agents with custom stdio ACP commands.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- harnesses — Harnesses [supported]: OpenHands agent, Claude Code, Codex, Gemini CLI, Pi, OpenCode or any ACP-compatible agent. Sources: openhands:nov07-canvas, openhands:nov07-readme.
- model_providers — Model providers [supported]: OpenHands agent: any litellm-supported model with your own key, custom model and base URL; saved LLM profiles switch models mid-conversation. ACP agents use their own model settings. Sources: openhands:b09-llm, openhands:b09-readme.
- custom_adapters — Custom adapters [supported]: Custom preset accepts a stdio ACP launch command and optional custom model ID. Sources: openhands:gap-acp.
- session_integration — Session integration [supported]: ACP integration for compatible harnesses. Sources: openhands:nov07-canvas.
- mixed_harness_operation — Mixed harness operation [unknown]: Mixed harness operation: The November first-party documentation and repository pass did not establish agent and model choice at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:nov07-canvas, openhands:nov07-readme, openhands:gap-acp, openhands:b09-llm, openhands:b09-readme

### ACC-03: Subscriptions, API keys and vendor credits

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Local ACP providers can reuse native logins, while clean containers/cloud require credentials and have provider limits.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- agent_subscriptions — Agent subscriptions [supported]: Existing Claude Code, Codex or Gemini subscription access. Sources: openhands:nov07-canvas.
- api_accounts — Api accounts [supported]: OpenHands agent can use an LLM key. Sources: openhands:nov07-canvas.
- vendor_credits — Vendor credits [unknown]: Vendor credits: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
- local_models — Local models [unknown]: Local models: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
- account_switching — Account switching [unknown]: Account switching: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
- vendor_account_requirement — Vendor account requirement [unknown]: Vendor account requirement: The November first-party documentation and repository pass did not establish subscriptions, api keys and vendor credits at the rubric's required scope. No installed-product fixture was run.
- provider_restrictions — Provider restrictions [supported]: Pi and OpenCode offered only for local/self-hosted backends, not OpenHands Cloud; same-container HOME can race on provider config. Sources: openhands:gap-acp.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-canvas, openhands:gap-acp

### ACC-04: Onboarding and project prerequisites

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Local stack requires Node 24 and uv; Docker and hardened VM routes are separate.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- first_task_setup — First task setup [partial]: npm install and agent-canvas launch path; no install timing. Sources: openhands:nov07-readme, openhands:nov07-selfhost.
- no_git — No git [unknown]: No git: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
- local_git_without_remote — Local git without remote [unknown]: Local git without remote: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
- hosted_git — Hosted git [unknown]: Hosted git: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
- prerequisite_guidance — Prerequisite guidance [supported]: Node 24+, uv; Docker is optional. Sources: openhands:nov07-readme, openhands:nov07-selfhost.
- managed_cloud_setup — Managed cloud setup [unknown]: Managed cloud setup: The November first-party documentation and repository pass did not establish onboarding and project prerequisites at the rubric's required scope. No installed-product fixture was run.
- byo_vps_onboarding — Byo vps onboarding [partial]: Documented VM, API key, firewall and TLS setup; user performs provisioning. Sources: openhands:nov07-readme, openhands:nov07-selfhost.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-readme, openhands:nov07-selfhost

### ACC-05: Programmable access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas uses the Agent Server REST API; SDK ownership is separate.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- cli — Cli [partial]: The agent-canvas CLI starts the full stack or a frontend/backend split; it has no commands to start or steer conversations. Sources: openhands:b09-cli.
- api — Api [supported]: Agent Server REST API. Sources: openhands:nov07-readme.
- sdk — Sdk [supported]: Python SDK and TypeScript client live in separate OpenHands repositories. Sources: openhands:nov07-readme.
- mcp_server — Mcp server [unknown]: Mcp server: The November first-party documentation and repository pass did not establish programmable access at the rubric's required scope. No installed-product fixture was run.
- webhooks — Webhooks [supported]: Inbound: automations fire on webhook events, including custom webhook sources with a URL and signing secret. Sources: openhands:b09-automations, openhands:b09-readme.
- operations — Operations [partial]: Canvas translates conversation actions to backend calls; exhaustive operation coverage unverified. Sources: openhands:nov07-readme.
- authentication — Authentication [unknown]: Authentication: The November first-party documentation and repository pass did not establish programmable access at the rubric's required scope. No installed-product fixture was run.
- stability — Stability [unknown]: Stability: The November first-party documentation and repository pass did not establish programmable access at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:nov07-readme, openhands:b09-cli, openhands:b09-automations, openhands:b09-readme

### ACC-06: External tools and extensions

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas manages backend-scoped MCP, skills and plugins, with health and credential checks.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- mcp_client — Mcp client [supported]: MCP connection library. Sources: openhands:nov07-canvas.
- plugins — Plugins [supported]: Customize includes a Plugins page on local backends; on an OpenHands Cloud backend the local Plugins page is hidden and Skills and Plugins opens Cloud settings. Sources: openhands:gap-customize.
- custom_tools — Custom tools [unknown]: Custom tools: The November first-party documentation and repository pass did not establish external tools and extensions at the rubric's required scope. No installed-product fixture was run.
- instructions_import — Instructions import [supported]: Agent Skills. Sources: openhands:nov07-canvas.
- authentication — Authentication [supported]: MCP health distinguishes credential rejection from connection failure; reachable public MCP does not imply credential verification. Sources: openhands:gap-customize.
- permission_scope — Permission scope [supported]: Skills, MCP servers and secrets are scoped to active backend, not automatically copied across backends. Sources: openhands:gap-customize.
- integration_owner — Integration owner [partial]: Canvas ships the connection library; which component owns external calls was not established. Sources: openhands:nov07-canvas.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:nov07-canvas, openhands:gap-customize

### ACC-07: Client implementation

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas is a React/TypeScript web frontend.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- desktop_implementation — Desktop implementation [unknown]: Desktop implementation: The November first-party documentation and repository pass did not establish client implementation at the rubric's required scope. No installed-product fixture was run.
- mobile_implementation — Mobile implementation [unknown]: Mobile implementation: The November first-party documentation and repository pass did not establish client implementation at the rubric's required scope. No installed-product fixture was run.
- hybrids — Hybrids [supported]: Browser-rendered React/TypeScript frontend. Sources: openhands:nov07-architecture.
- implementation_evidence — Implementation evidence [supported]: Official architecture identifies the UI; native desktop packaging details remain unverified. Sources: openhands:nov07-architecture.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-architecture

## Planning and context

### PLAN-01: Intake and external tracker relationship

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Issue-to-PR automations read tracker issues; Slack, GitHub and webhook events trigger agent runs. Other intake and sync atoms remain unverified.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=Earlier evidence keeps its cited revisions. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=Agent Canvas issue-to-PR, Slack and GitHub/webhook automations with a configured backend and required tracker credentials, tools and secrets. Event/automation availability depends on backend support; these findings do not establish Cloud or source-built mobile parity.; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- local_creation — Local creation [unknown]: Local creation: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
- prompt_intake — Prompt intake [unknown]: Prompt intake: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
- external_import — External import [supported]: Issue-to-PR automations read the title, description, acceptance criteria and linked dependencies of labeled GitHub, GitLab, Jira or Linear issues. Sources: openhands:b09-issue-pr.
- chat_git_triggers — Chat git triggers [supported]: Slack Channel Monitor and GitHub event automations start agents from chat messages and repository events. Sources: openhands:b09-slack, openhands:b09-automations, openhands:b09-readme.
- authoritative_tracker — Authoritative tracker [unknown]: Authoritative tracker: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
- stable_ids — Stable ids [unknown]: Stable ids: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
- sync — Sync [unknown]: Sync: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
- supported_edits — Supported edits [unknown]: Supported edits: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.
- external_roundtrips — External roundtrips [unknown]: External roundtrips: The November first-party documentation and repository pass did not establish intake and external tracker relationship at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:b09-slack, openhands:b09-automations, openhands:b09-readme, openhands:b09-issue-pr

### PLAN-02: Durable task plans

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### PLAN-03: Hierarchy, dependencies and evolving scope

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### PLAN-04: Shared context and memory

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas documents skills and a persistent workspace/user memory setting that can be enabled or disabled.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- instructions — Instructions [supported]: Customize > Skills teaches domain instructions; /add-skill installs for a new conversation. Sources: openhands:gap-customize.
- skills — Skills [supported]: Skills load when a conversation starts. Sources: openhands:gap-customize.
- project_docs — Project docs [unknown]: Project docs: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
- memory — Memory [supported]: Enabled persistent memory loads workspace and user memory into new OpenHands and ACP conversations. Sources: openhands:gap-customize.
- scope — Scope [supported]: Saved configuration follows the selected backend; memory locations are workspace/user scoped. Sources: openhands:gap-customize.
- provenance — Provenance [unknown]: Provenance: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
- correction — Correction [unknown]: Correction: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
- deletion — Deletion [unknown]: Deletion: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
- freshness — Freshness [unknown]: Freshness: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.
- takeover_continuity — Takeover continuity [unknown]: Takeover continuity: The November first-party documentation and repository pass did not establish shared context and memory at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-customize

### PLAN-05: Architecture and API awareness

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### PLAN-06: Native issue management and idea backlog

Verification status: Sourced (sourced)
Support: partial

The Canvas Task List renders the latest TaskTrackerObservation from the current conversation, with position-derived IDs and todo/in-progress/done states. Bounded inspection found no independent native issue/backlog work-item store; saved automations are trigger configurations.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas; version=e14b76cca01a71597cee242c202eed730e745ce3 native Canvas Task List and application stores/routes.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

- create — Create [unsupported]: The inspected native interface renders agent TaskTracker observations rather than providing independent issue/backlog CRUD. Sources: openhands:gap39-task-list.
- edit — Edit [unknown]: Edit: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- discuss — Discuss [unknown]: Discuss: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- prioritize — Prioritize [unknown]: Prioritize: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- label — Label [unknown]: Label: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- assign — Assign [unknown]: Assign: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- search — Search [unknown]: Search: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- filter — Filter [unknown]: Filter: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- archive — Archive [unknown]: Archive: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- reopen — Reopen [unknown]: Reopen: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- project_epic_views — Project epic views [unknown]: Project epic views: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- idea_parking — Idea parking [unknown]: Idea parking: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- explicit_dispatch — Explicit dispatch [unknown]: Explicit dispatch: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- task_session_separation — Task session separation [unsupported]: Task rows derive directly from the current conversation event store and do not have independent stable issue identity. Sources: openhands:gap39-task-list.
- metadata — Metadata [unknown]: Metadata: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.
- durable_states — Durable states [partial]: Task statuses are retained as conversation observations, not as separate persistent backlog work items. Sources: openhands:gap39-task-list.
- external_tracker_requirement — External tracker requirement [unknown]: External tracker requirement: The November first-party documentation and repository pass did not establish native issue management and idea backlog at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-13 (9 days old on 2026-11-22); not separately cross-checked.

Sources: openhands:gap39-task-list

### PLAN-07: Agent-native issue operations

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### PLAN-08: Living product specifications

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Coordination and automation

### COORD-01: Parallel work

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Parallel conversations can use separate Docker runtimes.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- concurrent_sessions — Concurrent sessions [supported]: Multiple simultaneous conversations. Sources: openhands:nov07-readme.
- concurrent_tasks — Concurrent tasks [unknown]: Concurrent tasks: The November first-party documentation and repository pass did not establish parallel work at the rubric's required scope. No installed-product fixture was run.
- quotas — Quotas [unknown]: Quotas: The November first-party documentation and repository pass did not establish parallel work at the rubric's required scope. No installed-product fixture was run.
- observed_concurrency — Observed concurrency [unknown]: Observed concurrency: The November first-party documentation and repository pass did not establish parallel work at the rubric's required scope. No installed-product fixture was run.
- status_visibility — Status visibility [partial]: Canvas conversation UI; status correctness untested. Sources: openhands:nov07-readme.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-readme

### COORD-02: Ownership and dispatch

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### COORD-03: Inspectable delegation and communication

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas launches linked child conversations and returns their results to the parent.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- roles — Roles [supported]: Parent/child conversation relationship remains linked. Sources: openhands:gap-conversations.
- model_harness_effort — Model harness effort [unknown]: Model harness effort: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
- messages — Messages [unknown]: Messages: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
- results_return — Results return [supported]: Child result returns to the parent conversation. Sources: openhands:gap-conversations.
- cross_harness — Cross harness [unknown]: Cross harness: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
- orchestration_owner — Orchestration owner [supported]: Canvas validates launch_child_conversation inputs and creates child conversations. Sources: openhands:gap-conversations.
- activation — Activation [supported]: Agent calls launch_child_conversation on supported local/Cloud targets. Sources: openhands:gap-conversations.
- authentication — Authentication [unknown]: Authentication: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
- live_progress — Live progress [partial]: Each working conversation shows its current stage as a live group in the chat; no parent-level live view of child progress is documented. Sources: openhands:b09-conversations.
- retained_results — Retained results [supported]: The child conversation stays linked to its parent and its result is returned to the parent conversation. Sources: openhands:b09-conversations.
- followup — Followup [unknown]: Followup: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.
- invocation — Invocation [unknown]: Invocation: The November first-party documentation and repository pass did not establish inspectable delegation and communication at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:gap-conversations, openhands:b09-conversations

### COORD-04: Unattended triggers

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Automation Server owns schedules/events and Canvas exposes lifecycle/run history.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- schedules — Schedules [supported]: Optional automation backend. Sources: openhands:nov07-readme, openhands:nov07-architecture.
- events — Events [supported]: Events through the automation backend. Sources: openhands:nov07-readme, openhands:nov07-architecture.
- recurring_tasks — Recurring tasks [unknown]: Recurring tasks: The November first-party documentation and repository pass did not establish unattended triggers at the rubric's required scope. No installed-product fixture was run.
- completion_conditions — Completion conditions [unknown]: Completion conditions: The November first-party documentation and repository pass did not establish unattended triggers at the rubric's required scope. No installed-product fixture was run.
- scheduler_location — Scheduler location [supported]: Separate automation service; not the frontend. Sources: openhands:nov07-readme, openhands:nov07-architecture.
- overlaps — Overlaps [supported]: Concurrency-limit exhaustion can produce SKIPPED run status. Sources: openhands:gap-automations.
- retries — Retries [unknown]: Retries: The November first-party documentation and repository pass did not establish unattended triggers at the rubric's required scope. No installed-product fixture was run.
- client_independence — Client independence [partial]: Automations keep running when the laptop is shut only if the backend runs on a server or cloud host; a laptop-local backend stops with the laptop. Sources: openhands:b09-readme.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:nov07-readme, openhands:nov07-architecture, openhands:gap-automations, openhands:b09-readme

### COORD-05: Intervention and attention

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas supports goal interruption and preserves failed-message retry controls.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- pause — Pause [unknown]: Pause: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- stop — Stop [unknown]: Stop: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- resume — Resume [unknown]: Resume: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- steer — Steer [supported]: Normal message interrupts an active /goal and returns control to the user. Sources: openhands:gap-conversations.
- notifications — Notifications [unknown]: Notifications: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- pending_decisions — Pending decisions [unknown]: Pending decisions: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- escalation — Escalation [unknown]: Escalation: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- visible_errors — Visible errors [supported]: Failed message and Retry control persist after history reload. Sources: openhands:gap-conversations.
- chat_terminal_parity — Chat terminal parity [unknown]: Chat terminal parity: The November first-party documentation and repository pass did not establish intervention and attention at the rubric's required scope. No installed-product fixture was run.
- retained_history — Retained history [supported]: Conversation retains message/tool history and supports archival and transcript export. Sources: openhands:gap-conversations.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:gap-conversations

### COORD-06: Fleet and epic management UI

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas shows linked children and grouped conversation metadata. Fleet fixture remains untested.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- fleet_fixture — Fleet fixture [unknown]: Fleet fixture: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
- parent_child — Parent child [supported]: Child conversations remain linked to their parent. Sources: openhands:gap-conversations.
- dependencies — Dependencies [unknown]: Dependencies: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
- attention — Attention [unknown]: Attention: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
- history — History [supported]: Conversation tags store workspace/repo/branch metadata server-side for other browsers. Sources: openhands:gap-conversations.
- workload — Workload [unknown]: Workload: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
- navigation_errors — Navigation errors [unknown]: Navigation errors: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.
- fixture_mode — Fixture mode [unknown]: Fixture mode: The November first-party documentation and repository pass did not establish fleet and epic management ui at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:gap-conversations

### COORD-07: Workflow flexibility and orchestration visibility

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas has reusable profiles, goals and backend-specific configuration.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- quick_task — Quick task [supported]: New conversation starts a single agent session on the active backend. Sources: openhands:gap-conversations.
- growing_epic — Growing epic [unknown]: Growing epic: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- presets — Presets [unknown]: Presets: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- natural_language — Natural language [unknown]: Natural language: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- agent_configuration — Agent configuration [unknown]: Agent configuration: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- in_run_changes — In run changes [supported]: User message interrupts a goal; conversation branching preserves earlier context on supporting local backends. Sources: openhands:gap-conversations.
- live_roles — Live roles [unknown]: Live roles: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- retained_relationships — Retained relationships [unknown]: Retained relationships: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- discoverability — Discoverability [unknown]: Discoverability: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.
- auth_friction — Auth friction [unknown]: Auth friction: The November first-party documentation and repository pass did not establish workflow flexibility and orchestration visibility at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-conversations, openhands:gap-customize

## Execution and reliability

### RUN-01: Laptop-independent execution

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas switches between local, self-hosted remote and optional cloud backends.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=local, self-hosted, managed-cloud; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- local — Local [supported]: Local Agent Server. Sources: openhands:nov07-readme, openhands:nov07-canvas.
- byo_remote — Byo remote [supported]: User-operated dedicated machine or VM. Sources: openhands:nov07-readme, openhands:nov07-canvas.
- self_hosted — Self hosted [unknown]: Self hosted: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
- managed_cloud — Managed cloud [supported]: OpenHands Cloud optional backend. Sources: openhands:nov07-readme, openhands:nov07-canvas.
- hybrid — Hybrid [supported]: One Canvas can switch among backends. Sources: openhands:nov07-readme, openhands:nov07-canvas.
- provisioning — Provisioning [unknown]: Provisioning: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
- payer — Payer [unknown]: Payer: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
- resources — Resources [unknown]: Resources: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
- region — Region [unknown]: Region: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
- expiry — Expiry [unknown]: Expiry: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.
- client_disconnect — Client disconnect [partial]: Vendor states remote server agents continue with laptop off; disconnect was not tested. Sources: openhands:nov07-canvas.
- other_device_continuation — Other device continuation [unknown]: Other device continuation: The November first-party documentation and repository pass did not establish laptop-independent execution at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-readme, openhands:nov07-canvas

### RUN-02: Workspace and process isolation

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Optional containers and worktrees separate execution/files, with documented shared-HOME and shared-workspace limits.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- checkout — Checkout [unknown]: Checkout: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- branch — Branch [supported]: Cloud children use selected repository and branch. Sources: openhands:gap-conversations.
- worktree — Worktree [supported]: Local child conversations may use an isolated worktree or parent shared workspace. Sources: openhands:gap-conversations.
- container — Container [supported]: Optional container per new conversation. Sources: openhands:nov07-readme.
- vm — Vm [unknown]: Vm: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- os_sandbox — Os sandbox [unknown]: Os sandbox: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- filesystem — Filesystem [partial]: Direct mode has host filesystem access; same host workspace mounts still share files. Sources: openhands:nov07-readme.
- process — Process [unknown]: Process: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- network — Network [unknown]: Network: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- secrets — Secrets [unknown]: Secrets: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- code_separation — Code separation [unknown]: Code separation: The November first-party documentation and repository pass did not establish workspace and process isolation at the rubric's required scope. No installed-product fixture was run.
- security_boundary — Security boundary [partial]: Docker execution boundary does not isolate the whole Canvas/automation stack. Sources: openhands:nov07-readme.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:nov07-readme, openhands:gap-conversations, openhands:gap-acp

### RUN-03: Recovery, expiry and continuity

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas reloads backend conversation history and keeps archived conversations without deleting them.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- client_disconnect — Client disconnect [unknown]: Client disconnect: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
- worker_crash — Worker crash [partial]: The Docker container exits with code 1 after the Agent Server fails /alive for about 30 seconds; it recovers only with a configured restart policy. Sources: openhands:b09-readme.
- service_restart — Service restart [unknown]: Service restart: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
- expiry — Expiry [unknown]: Expiry: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
- transcript_reload — Transcript reload [supported]: Full archived conversation history remains on backend; missing runtimes remain readable but cannot be restored from conversation. Sources: openhands:gap-conversations.
- process_reconnect — Process reconnect [unknown]: Process reconnect: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
- task_resume — Task resume [unknown]: Task resume: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
- state_reconstruction — State reconstruction [partial]: Mounted workspace and conversation state survive container replacement. Sources: openhands:nov07-readme.
- context_loss — Context loss [supported]: Runtime-missing conversation is shown archived; readable history does not imply a recoverable execution process. Sources: openhands:gap-conversations.
- duplicate_actions — Duplicate actions [unknown]: Duplicate actions: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.
- manual_repair — Manual repair [partial]: Container health failure exits visibly; restart requires a configured restart policy. Sources: openhands:nov07-readme.
- multi_day_continuity — Multi day continuity [unknown]: Multi day continuity: The November first-party documentation and repository pass did not establish recovery, expiry and continuity at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:nov07-readme, openhands:gap-conversations, openhands:b09-readme

### RUN-04: Development environment reliability

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

The user chooses workspace mounts and runtime configuration.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- dependencies — Dependencies [supported]: Local Node/uv or Docker prerequisites. Sources: openhands:nov07-readme.
- caches — Caches [unknown]: Caches: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- snapshots — Snapshots [unknown]: Snapshots: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- services — Services [unknown]: Services: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- ports — Ports [unknown]: Ports: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- secrets — Secrets [unknown]: Secrets: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- duplicate_installs — Duplicate installs [unknown]: Duplicate installs: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- collisions — Collisions [unknown]: Collisions: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.
- remote_setup — Remote setup [supported]: Operator provisions and hardens the server. Sources: openhands:nov07-readme.
- automatic_repair — Automatic repair [unknown]: Automatic repair: The November first-party documentation and repository pass did not establish development environment reliability at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-readme

### RUN-05: Limits and failure handling

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Goals and experimental critic refinement have explicit iteration limits.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- time_limits — Time limits [unknown]: Time limits: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
- turn_limits — Turn limits [supported]: Experimental OpenHands critic refinement defaults to at most three attempts; not generalized to ACP agents. Sources: openhands:gap-critic.
- token_limits — Token limits [unknown]: Token limits: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
- spend_limits — Spend limits [supported]: Enterprise managed gateway supports monthly organization/user budgets. Direct provider calls are outside enforcement. Sources: openhands:gap-budgets.
- timeouts — Timeouts [unknown]: Timeouts: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
- retries — Retries [unknown]: Retries: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
- provider_failures — Provider failures [unknown]: Provider failures: The November first-party documentation and repository pass did not establish limits and failure handling at the rubric's required scope. No installed-product fixture was run.
- enforcement — Enforcement [supported]: Refinement stops at score threshold or max iterations; documentation only. Sources: openhands:gap-critic.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-critic, openhands:gap-budgets, openhands:gap-conversations

### RUN-06: Truthful status and operational statistics

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas displays automation phase/status and exports reported costs with null for unavailable cost.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- logs — Logs [supported]: Script-run View logs shows the script's output; on cloud backends logs are read from the run sandbox and become unavailable after that sandbox is deleted. Sources: openhands:gap-automations.
- traces — Traces [unknown]: Traces: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- failure_reasons — Failure reasons [partial]: Health check can exit the container after roughly thirty seconds of Agent Server failure. Sources: openhands:nov07-readme.
- usage_export — Usage export [supported]: Activity Log exports CSV/JSON with numeric reported cost or null. Sources: openhands:gap-automations.
- task_stats — Task stats [unknown]: Task stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- agent_stats — Agent stats [unknown]: Agent stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- project_stats — Project stats [unknown]: Project stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- time_stats — Time stats [unknown]: Time stats: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- failure_status — Failure status [supported]: Statuses include failed/cancelled/skipped and structured disablement reason with time. Sources: openhands:gap-automations.
- approval_status — Approval status [unknown]: Approval status: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- reconnect_consistency — Reconnect consistency [unknown]: Reconnect consistency: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- performance_method — Performance method [unknown]: Performance method: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.
- responsiveness — Responsiveness [unknown]: Responsiveness: The November first-party documentation and repository pass did not establish truthful status and operational statistics at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:nov07-readme, openhands:gap-automations

### RUN-07: Per-task API and compute cost

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas automation history exposes reported per-run LLM cost with explicit missing values.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- task_cost — Task cost [supported]: Completed automation run reported LLM cost displayed in USD to four decimal places. Sources: openhands:gap-automations.
- session_cost — Session cost [unknown]: Session cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- child_cost — Child cost [unknown]: Child cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- epic_cost — Epic cost [unknown]: Epic cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- harness_aggregation — Harness aggregation [unknown]: Harness aggregation: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- billed_vs_estimated — Billed vs estimated [partial]: Value is described as backend-reported LLM cost; the Activity Log does not say whether it is billed or estimated, and no provider invoice reconciliation is established. Sources: openhands:gap-automations.
- tokens — Tokens [unknown]: Tokens: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- subscription_allowance — Subscription allowance [unknown]: Subscription allowance: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- provider_reconciliation — Provider reconciliation [partial]: Enterprise gateway budget counters and conversation-ledger estimates have different scope/period; docs explain reconciling those two views, not reconciliation with provider invoices. Sources: openhands:gap-budgets.
- compute_cost — Compute cost [unknown]: Compute cost: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.
- refresh_delay — Refresh delay [supported]: Enterprise budget spend is marked live, stale or unavailable, with observation time; unavailable never means zero. Sources: openhands:gap-budgets.
- alerts — Alerts [supported]: Enterprise organization thresholds such as 80/90/100 percent notify Admins/Owners by email and configured Slack. Sources: openhands:gap-budgets.
- export — Export [supported]: CSV/JSON activity export includes numeric cost or null. Sources: openhands:gap-automations.
- drilldown — Drilldown [unknown]: Drilldown: The November first-party documentation and repository pass did not establish per-task api and compute cost at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-automations, openhands:gap-budgets

### RUN-08: Compute-aware scheduling and verification

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Backend concurrency caps can skip automation dispatch; resource-aware fairness remains unknown.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- concurrency — Concurrency [supported]: Automation run can be SKIPPED when backend concurrency limit is reached. Sources: openhands:gap-automations.
- queues — Queues [unknown]: Queues: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- cpu_ram — Cpu ram [unknown]: Cpu ram: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- backpressure — Backpressure [supported]: Capacity limitation is surfaced as skipped status rather than assumed successful execution. Sources: openhands:gap-automations.
- host_awareness — Host awareness [unknown]: Host awareness: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- check_reuse — Check reuse [unknown]: Check reuse: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- check_deduplication — Check deduplication [unknown]: Check deduplication: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- bounded_tests — Bounded tests [unknown]: Bounded tests: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- cancellation — Cancellation [unknown]: Cancellation: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- fairness — Fairness [unknown]: Fairness: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- recovery — Recovery [unknown]: Recovery: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.
- shared_limits — Shared limits [unknown]: Shared limits: The November first-party documentation and repository pass did not establish compute-aware scheduling and verification at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:gap-automations

## Human collaboration and control

### TEAM-01: Live human collaboration

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Cloud organization automation conversations support read-only team visibility. Same-agent co-prompting remains unestablished.

Availability: unknown
Delivery: unknown
Scope: surfaces=OpenHands Cloud; version=not specified; plan=Cloud organization automation conversations; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- visibility — Visibility [supported]: Other organization users may follow automation conversation history read-only. Sources: openhands:gap-automations.
- discussion — Discussion [unknown]: Discussion: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- comments — Comments [unknown]: Comments: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- presence — Presence [unknown]: Presence: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- coprompting — Coprompting [unsupported]: Non-owner viewers of shared automation conversations explicitly cannot send messages. Scope is shared automation runs, not every collaboration mode. Sources: openhands:gap-automations.
- ordering — Ordering [unknown]: Ordering: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- conflicts — Conflicts [unknown]: Conflicts: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- attribution — Attribution [unknown]: Attribution: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- permissions — Permissions [unknown]: Permissions: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- plan_restrictions — Plan restrictions [unknown]: Plan restrictions: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.
- owner_online — Owner online [unknown]: Owner online: The November first-party documentation and repository pass did not establish live human collaboration at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:gap-automations

### TEAM-02: Roles and access boundaries

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Organizations document Member/Admin/Owner permissions; paid Teams/Enterprise separately advertise SSO/SAML.

Availability: unknown
Delivery: unknown
Scope: surfaces=OpenHands Cloud, OpenHands Agent Server backends; version=not specified; plan=Cloud organization roles; Teams/Enterprise self-hosted SSO/SAML; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- organization_roles — Organization roles [supported]: Member creates conversations/private settings; Admin invites/promotes and manages org settings; Owner deletes org/claims Git organizations. Sources: openhands:gap-roles.
- project_roles — Project roles [unknown]: Project roles: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
- task_roles — Task roles [unknown]: Task roles: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
- membership — Membership [supported]: Members join as Member; Admins invite and change Member/Admin roles. Sources: openhands:gap-roles.
- sso — Sso [supported]: OpenHands Enterprise installations document SAML single sign-on with a corporate identity provider; the pricing page lists SSO/SAML on Teams and Enterprise, not free Agent Canvas. Sources: openhands:src1-sso, openhands:src1-pricing.
- provisioning — Provisioning [unknown]: Provisioning: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
- unauthorized_access — Unauthorized access [unknown]: Unauthorized access: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
- revocation — Revocation [unknown]: Revocation: The November first-party documentation and repository pass did not establish roles and access boundaries at the rubric's required scope. No installed-product fixture was run.
- plan_scope — Plan scope [supported]: Cloud/Enterprise organization roles; free Canvas uses a shared identity. Sources: openhands:gap-roles.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-roles, openhands:gap-pricing, openhands:src1-sso, openhands:src1-pricing

### TEAM-03: Approvals and temporary access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Self-hosted public mode requires the backend API key.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- command — Command [unknown]: Command: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- tool — Tool [unknown]: Tool: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- network — Network [unknown]: Network: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- secret — Secret [partial]: X-Session-API-Key authenticates API calls; this is server access, not per-tool approval. Sources: openhands:nov07-selfhost.
- delivery — Delivery [unknown]: Delivery: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- approver_identity — Approver identity [unknown]: Approver identity: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- lifetime — Lifetime [unknown]: Lifetime: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- allow — Allow [unknown]: Allow: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- deny — Deny [unknown]: Deny: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- revoke — Revoke [unknown]: Revoke: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- tunnels — Tunnels [unknown]: Tunnels: The November first-party documentation and repository pass did not establish approvals and temporary access at the rubric's required scope. No installed-product fixture was run.
- defaults — Defaults [supported]: Public mode does not inject the key into frontend HTML. Sources: openhands:nov07-selfhost.
- safer_modes — Safer modes [supported]: Firewall and TLS setup guidance. Sources: openhands:nov07-selfhost.
- enforcement — Enforcement [partial]: Backend key and network boundary documented; unauthorized-access tests not run. Sources: openhands:nov07-selfhost.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-selfhost

### TEAM-04: Decision and activity history

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas exports timestamped conversation/tool history and retains archived messages.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- actions — Actions [unknown]: Actions: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- approvals — Approvals [unknown]: Approvals: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- edits — Edits [unknown]: Edits: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- discussion — Discussion [unknown]: Discussion: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- decisions — Decisions [unknown]: Decisions: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- cross_user_persistence — Cross user persistence [unknown]: Cross user persistence: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- cross_session_persistence — Cross session persistence [supported]: Archiving preserves full backend history and is reversible. Sources: openhands:gap-conversations.
- export — Export [supported]: Self-contained Markdown/HTML export optionally includes full tool input/output and timestamps; generated in browser. Sources: openhands:gap-conversations.
- mutability — Mutability [unknown]: Mutability: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.
- retention — Retention [supported]: Archive preserves history until deletion; Delete all includes hidden archived conversations. Sources: openhands:gap-conversations.
- integrity — Integrity [unknown]: Integrity: The November first-party documentation and repository pass did not establish decision and activity history at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:gap-conversations

### TEAM-05: Review experience and guidance

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas exposes combined commit/uncommitted diffs and experimental critic feedback.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- pending_reviews — Pending reviews [unknown]: Pending reviews: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- change_understanding — Change understanding [supported]: Unified Commits drawer combines commit history and uncommitted changes. Sources: openhands:gap-conversations.
- evidence_navigation — Evidence navigation [supported]: Conversation overview links workspace Git context, Files and Commits drawers. Sources: openhands:gap-conversations.
- comments — Comments [unknown]: Comments: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- request_changes — Request changes [unknown]: Request changes: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- shipping_guidance — Shipping guidance [unknown]: Shipping guidance: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- effort — Effort [unknown]: Effort: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- missed_evidence — Missed evidence [unknown]: Missed evidence: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- keyboard — Keyboard [unknown]: Keyboard: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- narrow_screen — Narrow screen [unknown]: Narrow screen: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- context_switching — Context switching [unknown]: Context switching: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- roles — Roles [unknown]: Roles: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.
- retained_context — Retained context [unknown]: Retained context: The November first-party documentation and repository pass did not establish review experience and guidance at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-conversations, openhands:gap-critic

### TEAM-06: Colleague takeover and continuity

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas renders file artifacts, images and unified code-change views.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends, OpenHands Cloud; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- diffs — Diffs [supported]: Commits drawer combines commit history and uncommitted changes. Sources: openhands:gap-conversations.
- documents — Documents [supported]: Created Markdown files render inline with full-file Files drawer access. Sources: openhands:gap-conversations.
- screenshots — Screenshots [unknown]: Screenshots: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- recordings — Recordings [unknown]: Recordings: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- previews — Previews [partial]: Browser view is rendered; previewing a running app in it was not established. Sources: openhands:nov07-architecture.
- test_outputs — Test outputs [unknown]: Test outputs: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- reviewer_outputs — Reviewer outputs [unknown]: Reviewer outputs: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- gallery — Gallery [unknown]: Gallery: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- task_links — Task links [unknown]: Task links: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- revision_links — Revision links [unknown]: Revision links: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- persistence — Persistence [unknown]: Persistence: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.
- child_findings — Child findings [supported]: Child conversation results return to the parent conversation. Sources: openhands:gap-conversations.
- prompt_leakage — Prompt leakage [unknown]: Prompt leakage: The November first-party documentation and repository pass did not establish retained artifacts and outputs at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-architecture, openhands:gap-conversations

### SHIP-02: Verification and spec gates

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Experimental critic evaluates OpenHands-agent results and can request bounded refinement.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- tests — Tests [partial]: The Issue-to-PR automation prompt has the agent run tests before opening the PR; no enforced test gate is documented. Sources: openhands:b09-issue-pr.
- lint — Lint [unknown]: Lint: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- types — Types [unknown]: Types: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- ci — Ci [unknown]: Ci: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- independent_review — Independent review [supported]: Additional critic evaluation supplies likelihood score and issue categories; no human review or acceptance-test equivalence. Sources: openhands:gap-critic.
- spec_checks — Spec checks [unknown]: Spec checks: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- required_checks — Required checks [unknown]: Required checks: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- failure_blocking — Failure blocking [unknown]: Failure blocking: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- requirement_conflicts — Requirement conflicts [unknown]: Requirement conflicts: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.
- configured_policy — Configured policy [supported]: User can enable refinement and configure threshold/max attempts in Verification settings. Sources: openhands:gap-critic.
- enforced_policy — Enforced policy [unknown]: Enforced policy: The November first-party documentation and repository pass did not establish verification and spec gates at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:gap-critic, openhands:b09-issue-pr

### SHIP-03: Git and pull request workflow

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas Git controls prompt the agent to commit, pull, push and work with PRs.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- branches — Branches [supported]: Issue-to-PR creates a feature branch per issue with a configurable prefix; Cloud child conversations use the selected branch. Sources: openhands:b09-issue-pr, openhands:b09-conversations.
- worktrees — Worktrees [supported]: Local child conversations can use an isolated worktree or the parent's shared workspace. Sources: openhands:b09-conversations.
- commits — Commits [supported]: Commits drawer offers commit/pull/push prompts and recent commits. Sources: openhands:gap-conversations.
- pull_requests — Pull requests [supported]: Git-actions control sends pull-request prompts to the agent; no completed PR fixture. Sources: openhands:gap-conversations.
- comments — Comments [unknown]: Comments: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
- ci_response — Ci response [unknown]: Ci response: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
- rebase — Rebase [unknown]: Rebase: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
- conflicts — Conflicts [unknown]: Conflicts: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.
- product_state — Product state [unknown]: Product state: The November first-party documentation and repository pass did not establish git and pull request workflow at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:gap-conversations, openhands:b09-issue-pr, openhands:b09-conversations

### SHIP-04: Merge and deployment authority

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### SHIP-05: Completion evidence and rollback

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### SHIP-06: Batch review and high-volume shipping

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Ownership, privacy and economics

### OWN-01: Source and license

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

The Canvas source distribution is MIT.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- client_license — Client license [supported]: MIT, subject to component notices. Sources: openhands:nov07-license.
- server_license — Server license [unknown]: Server license: The November first-party documentation and repository pass did not establish source and license at the rubric's required scope. No installed-product fixture was run.
- hosted_extensions — Hosted extensions [unknown]: Hosted extensions: The November first-party documentation and repository pass did not establish source and license at the rubric's required scope. No installed-product fixture was run.
- source_visibility — Source visibility [supported]: Public Canvas source. Sources: openhands:nov07-license.
- source_revision — Source revision [supported]: b811a4c33979ca4b5d241730b995b56362f4ab34 Sources: openhands:nov07-license.
- hosted_parity — Hosted parity [unknown]: Hosted parity: The November first-party documentation and repository pass did not establish source and license at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-license

### OWN-02: Hosting and exit

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Canvas self-hosts and provides portable conversation and automation exports.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- self_hosting — Self hosting [supported]: Frontend, Agent Server and automation stack on the operator machine. Sources: openhands:nov07-selfhost, openhands:nov07-readme.
- vendor_dependencies — Vendor dependencies [partial]: Selected model/harness services and optional cloud backend remain separate. Sources: openhands:nov07-selfhost, openhands:nov07-readme.
- export — Export [supported]: Conversation transcript downloads as Markdown/HTML. Sources: openhands:gap-conversations.
- import — Import [unknown]: Import: The November first-party documentation and repository pass did not establish hosting and exit at the rubric's required scope. No installed-product fixture was run.
- formats — Formats [supported]: Self-contained Markdown/HTML transcript; automation specs separately export JSON. Sources: openhands:gap-conversations, openhands:gap-automations.
- cancellation — Cancellation [unknown]: Cancellation: The November first-party documentation and repository pass did not establish hosting and exit at the rubric's required scope. No installed-product fixture was run.
- account_independence — Account independence [unknown]: Account independence: The November first-party documentation and repository pass did not establish hosting and exit at the rubric's required scope. No installed-product fixture was run.
- history_portability — History portability [supported]: Local export loads full event history; Cloud export uses currently loaded events. Sources: openhands:gap-conversations.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:nov07-selfhost, openhands:nov07-readme, openhands:gap-conversations, openhands:gap-automations

### OWN-03: Data handling and telemetry

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Backend settings/secrets and browser-generated exports have explicit boundaries. At v1.38.0 an anonymous usage-data switch defaults on with a consent prompt and can be turned off on local and self-hosted backends; it is forced on for OpenHands Cloud.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=Telemetry from OpenHands v1.38.0 source (e14b76c); other parts from first-party documentation checked 2026-11-07. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- code_data — Code data [unknown]: Code data: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- prompts — Prompts [unknown]: Prompts: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- credentials — Credentials [supported]: Agent Server owns ACP credentials/subprocesses; onboarding secrets go to backend secret store. Sources: openhands:gap-acp.
- logs — Logs [unknown]: Logs: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- artifacts — Artifacts [unknown]: Artifacts: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- retention — Retention [unknown]: Retention: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- deletion — Deletion [unknown]: Deletion: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- training — Training [unknown]: Training: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- residency — Residency [unknown]: Residency: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- subprocessors — Subprocessors [unknown]: Subprocessors: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- telemetry_disclosure — Telemetry disclosure [unknown]: Telemetry disclosure: The November first-party documentation and repository pass did not establish data handling and telemetry at the rubric's required scope. No installed-product fixture was run.
- telemetry_defaults — Telemetry defaults [supported]: The anonymous usage-data switch defaults on when the user has not chosen; on a Cloud backend it is forced on. Source inspection at v1.38.0, not tested. Sources: openhands:src1-telemetry-settings.
- telemetry_controls — Telemetry controls [supported]: App settings offer a switch to stop sending anonymous usage data on local and self-hosted backends; it is disabled on Cloud backends. Source inspection at v1.38.0, not tested. Sources: openhands:src1-telemetry-settings.
- consent_prompt — Consent prompt [supported]: A consent modal asks whether to send anonymous usage data and records the choice. Source inspection at v1.38.0; when it appears was not tested. Sources: openhands:src1-telemetry-consent.
- provider_separation — Provider separation [supported]: ACP provider owns its LLM/tools/execution; Canvas sends turns and renders results. Sources: openhands:gap-acp.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-acp, openhands:gap-conversations, openhands:src1-telemetry-settings, openhands:src1-telemetry-consent

### OWN-04: Price and included usage

Verification status: Sourced (sourced)
Support: partial

The current public self-hosted offer is free Canvas, Teams at $500/month for ten users plus $50/month additional seats with a 5000-session monthly cap, and custom Enterprise. No one-time licence is listed. The optional Cloud backend is not priced in this table; its documented OpenHands LLM credits buy model access, so product-wide metered ADE and compute pricing remain unestablished.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic answers are established by this source pass. Remaining atomic answers retain their documented gaps.

- currency — Currency [supported]: Paid Teams list price in USD. Sources: openhands:gap-pricing.
- interval — Interval [supported]: Teams billed monthly at $500 for up to ten users; $50 monthly additional seats. Sources: openhands:gap-pricing.
- seats — Seats [supported]: Teams includes up to ten users; Enterprise unlimited seats. Sources: openhands:gap-pricing.
- seat_minimum — Seat minimum [unknown]: Seat minimum: The November first-party documentation and repository pass did not establish price and included usage at the rubric's required scope. No installed-product fixture was run.
- workspace_fees — Workspace fees [unknown]: Workspace fees: The November first-party documentation and repository pass did not establish price and included usage at the rubric's required scope. No installed-product fixture was run.
- included_usage — Included usage [supported]: The current Teams table caps usage at 5000 sessions per month; Enterprise is uncapped. Sources: openhands:gap39-plan-table.
- credits — Credits [unknown]: Credits: The November first-party documentation and repository pass did not establish price and included usage at the rubric's required scope. No installed-product fixture was run.
- trial — Trial [supported]: Teams advertises a 30-day trial. Sources: openhands:gap-pricing.
- overages — Overages [unknown]: Overages: The November first-party documentation and repository pass did not establish price and included usage at the rubric's required scope. No installed-product fixture was run.
- taxes — Taxes [unknown]: Taxes: The November first-party documentation and repository pass did not establish price and included usage at the rubric's required scope. No installed-product fixture was run.
- model_cost — Model cost [supported]: Self-hosted plans use user-provided LLM keys. Optional OpenHands Cloud LLM keys consume separately purchased model credits and can also be used in other agents. Sources: openhands:gap39-plan-table, openhands:gap39-cloud-model-credits.
- compute_cost — Compute cost [unknown]: The self-hosted table does not price the optional Cloud backend; a vendor sandbox/compute charge is not established by model credits. Sources: openhands:gap39-plan-table, openhands:gap39-cloud-model-credits.

Checked 2026-11-07 (15 days old on 2026-11-22); not separately cross-checked.

Sources: openhands:gap-pricing, openhands:gap39-plan-table, openhands:gap39-cloud-model-credits

### OWN-05: Scenario cost and controls

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-06: Availability and support

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Teams and Enterprise plans carry paid identity governance; support ranges from community support for Agent Canvas to best-effort email on Teams and SLA-based response on Enterprise.

Availability: unknown
Delivery: unknown
Scope: surfaces=Agent Canvas, OpenHands Cloud, OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture. Batch 09 recheck 2026-11-22: docs.openhands.dev Agent Canvas pages and repository at v1.43.0 (d5d7908, released 2026-11-20); release list v1.37.0-v1.43.0. Newer code is not attributed to earlier releases.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.
- Documentation and public-code recheck only (2026-11-22); no product fixture was run.

- release_stage — Release stage [partial]: Agent Canvas ships as 1.x releases; Apps are beta and the critic is experimental. Sources: openhands:b09-apps, openhands:b09-critic, openhands:b09-releases.
- access_restrictions — Access restrictions [supported]: Teams/Enterprise governance/identity paid; Canvas uses shared identity. Sources: openhands:gap-pricing.
- support — Support [supported]: Canvas community support; Teams best-effort email; Enterprise SLA-based response times. Sources: openhands:gap-pricing.
- response_commitments — Response commitments [unknown]: Response commitments: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.
- release_activity — Release activity [supported]: Seven releases from v1.37.0 (2026-11-06) to v1.43.0 (2026-11-20). Sources: openhands:b09-releases.
- status_history — Status history [unknown]: Status history: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.
- deprecation — Deprecation [unknown]: Deprecation: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.
- export_options — Export options [unknown]: Export options: The November first-party documentation and repository pass did not establish availability and support at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-22 (checked today on 2026-11-22); agent cross-checked 2026-11-22.

Sources: openhands:gap-pricing, openhands:b09-releases, openhands:b09-apps, openhands:b09-critic

### OWN-07: Enterprise assurance

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-08: Useful free tier and evaluation access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

The vendor advertises free local and self-managed Canvas use.

Availability: generally-available
Delivery: native
Scope: surfaces=Agent Canvas, OpenHands Agent Server backends; version=First-party sources checked 2026-11-07; pinned implementations retain their cited revision.; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- The remaining atomic questions and the rubric scenario are unverified. Documentation is not a successful product test.

- ongoing_free — Ongoing free [supported]: Free local Canvas. Sources: openhands:nov07-canvas.
- trial — Trial [unknown]: Trial: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- credits_trial — Credits trial [unknown]: Credits trial: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- self_host_cost — Self host cost [partial]: Self-hosted VM is labeled free, OSS and self-managed. The page gives no infrastructure or provider cost detail. Sources: openhands:nov07-canvas.
- paid_only — Paid only [unknown]: Paid only: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- early_access — Early access [unknown]: Early access: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- free_scenarios — Free scenarios [unknown]: Free scenarios: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- card_required — Card required [unknown]: Card required: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- usage_caps — Usage caps [unknown]: Usage caps: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.
- paid_evaluation — Paid evaluation [unknown]: Paid evaluation: The November first-party documentation and repository pass did not establish useful free tier and evaluation access at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-07.

Sources: openhands:nov07-canvas

### OWN-09: Pricing transparency

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Pricing page publishes monthly Teams rate and session caps, with Enterprise by quote.

Availability: unknown
Delivery: unknown
Scope: surfaces=OpenHands Agent Server backends; version=First-party documentation/source checked 2026-11-07; exact pinned source revision is recorded in each citation. No installed-product fixture.; plan=Agent Canvas unless answer explicitly scopes paid Teams/Enterprise; os=not specified; execution_modes=not specified; region=not specified; harness=not specified.

Limitations:
- Only the named atomic facts are established by documentation. Remaining rubric scenarios and unknown answers were not demonstrated.

- units — Units [supported]: Teams $500 monthly up to ten users plus $50 monthly extra seats. Sources: openhands:gap-pricing.
- included_limits — Included limits [supported]: Teams 5000 sessions per month; Enterprise uncapped. Sources: openhands:gap-pricing.
- overages — Overages [unknown]: Overages: The November first-party documentation and repository pass did not establish pricing transparency at the rubric's required scope. No installed-product fixture was run.
- compute_markup — Compute markup [unknown]: Compute markup: The November first-party documentation and repository pass did not establish pricing transparency at the rubric's required scope. No installed-product fixture was run.
- model_markup — Model markup [unknown]: Model markup: The November first-party documentation and repository pass did not establish pricing transparency at the rubric's required scope. No installed-product fixture was run.
- minimum_commitment — Minimum commitment [unknown]: Minimum commitment: The November first-party documentation and repository pass did not establish pricing transparency at the rubric's required scope. No installed-product fixture was run.
- cancellation — Cancellation [unknown]: Cancellation: The November first-party documentation and repository pass did not establish pricing transparency at the rubric's required scope. No installed-product fixture was run.
- sales_only_unknowns — Sales only unknowns [supported]: Enterprise exact price requires a quote. Sources: openhands:gap-pricing.
- transparency_classification — Transparency classification [unknown]: Transparency classification: The November first-party documentation and repository pass did not establish pricing transparency at the rubric's required scope. No installed-product fixture was run.

Checked 2026-11-07 (15 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: openhands:gap-pricing

## Sources

### openhands:nov07-readme

OpenHands README. Canvas launches local Agent Server/automation services with Node 24 and uv, or optional Docker runtimes. Backends can live on laptop, remote VM or managed cloud. Same host workspace mounts still share files.

- URL: https://github.com/OpenHands/OpenHands/blob/b811a4c33979ca4b5d241730b995b56362f4ab34/README.md
- Locator: Overview, setup, features and component boundaries
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:nov07-canvas

OpenHands Agent Canvas. Vendor describes desktop installs, ACP agents with existing subscriptions, extensions and local, self-hosted or managed backends.

- URL: https://www.openhands.dev/product/canvas
- Locator: ACP; Where your agents run; Get started
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:gap-phone

OpenHands Tailscale; ngrok. Canvas documents phone/tablet browser access through Tailscale or authenticated public-mode ngrok; it does not establish native mobile apps.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/mobile-access
- Locator: Tailscale; ngrok
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:gap39-mobile-doc

OpenHands native mobile MVP. The public native Expo MVP can list conversations, stream history/events and send messages to a reachable Agent Server using a session API key. Source-build instructions cover Android and iOS with native toolchains. Cloud login, QR pairing and a laptop remote-session facade are still planned; no store/release binary is asserted.

- URL: https://github.com/OpenHands/openhands-mobile/blob/47f815b1d111b6a71b405dcb77acb3682da59b85/README.md
- Locator: What works today; Prerequisites; Install
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### openhands:gap39-mobile-code

OpenHands native mobile Agent Server client. The native mobile client implements REST conversation listing/history and sends message events to /api/conversations/{id}/events; ChatScreen calls that sendMessage path, and useConversationSocket streams events through WebSocket. app.json declares iOS and Android native platforms.

- URL: https://github.com/OpenHands/openhands-mobile/blob/47f815b1d111b6a71b405dcb77acb3682da59b85/src/api/agent-server.ts
- Locator: conversation search/create; sendMessage, lines 220-238; src/screens/ChatScreen.tsx
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: 47f815b1d111b6a71b405dcb77acb3682da59b85
- Path: src/api/agent-server.ts

### openhands:gap39-cli

Agent Canvas command-line launcher. The product-owned agent-canvas CLI starts the local Agent Server, automation backend and pre-built frontend. It exposes version, stack-info, public/frontend-only/backend-only and help flags. This establishes a user-runnable launcher CLI, without asserting a separate task-operation CLI.

- URL: https://github.com/OpenHands/OpenHands/blob/e14b76cca01a71597cee242c202eed730e745ce3/bin/agent-canvas.mjs
- Locator: CLI entry point; help/info; local stack startup
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: e14b76cca01a71597cee242c202eed730e745ce3
- Path: bin/agent-canvas.mjs

### openhands:gap-acp

OpenHands docs/ACP_AGENTS.md. Local ACP agents reuse provider-native logins; clean containers/cloud need credentials. Pi/OpenCode are offered only on local/self-hosted backends. Same-provider conversations sharing container HOME can race on auth/config/lock files; Canvas cannot yet send SDK per-conversation data-dir isolation. Agent choice is per backend and running conversations retain their original agent.

- URL: https://github.com/OpenHands/OpenHands/blob/b811a4c33979ca4b5d241730b995b56362f4ab34/docs/ACP_AGENTS.md
- Locator: Authentication; Per-conversation isolation; Model switching
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:b09-readme

OpenHands Agent Canvas README (v1.43.0). Agent Canvas runs the OpenHands agent and third-party agents such as Claude Code, Codex, Gemini CLI, Pi and OpenCode, or any ACP agent. Agent Canvas lists 'Bring your own model: use with any LLM' and automations that integrate with Slack, GitHub and Linear and run on a schedule or in response to webhook events. Running on a cloud server lets agents continue when the laptop is shut. The Docker entrypoint stops the container with exit code 1 when the Agent Server fails its /alive check for about 30 seconds; automatic recovery needs a restart policy such as --restart unless-stopped.

- URL: https://github.com/OpenHands/OpenHands/blob/d5d790823e468587e9e4d8517860ca8ef75aad6a/README.md
- Locator: Line 36 (agents); feature table lines 40-45; Quickstart lines 51-56; Docker note lines 143-148
- Evidence kind: documented
- Source date: 2026-11-20
- Retrieved: 2026-11-22

### openhands:b09-llm

OpenHands docs: LLM settings. Bring your own LLM and API key: any model supported by litellm; basic settings list popular providers (OpenHands provider, Anthropic, OpenAI and others); advanced settings take a provider-prefixed custom model and base URL. LLM profiles save multiple configurations and switch between them during an active conversation.

- URL: https://docs.openhands.dev/openhands/usage/settings/llm-settings
- Locator: Basic settings; Advanced settings (Custom Model, Base URL); LLM Profiles
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:nov07-selfhost

Agent Canvas self-hosting. User provisions and hardens a VM; public mode requires an API key, with TLS/firewall setup and shared-origin editor caveats.

- URL: https://github.com/OpenHands/OpenHands/blob/b811a4c33979ca4b5d241730b995b56362f4ab34/docs/SELF_HOSTING.md
- Locator: Quickstart; public mode; security posture
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:b09-cli

agent-canvas launcher CLI (v1.43.0). The npm package's only bin, agent-canvas, starts the full local stack or a frontend-only or backend-only split, with port, bind host, public API-key mode and version/info flags. Its help says LLM settings are configured in the web UI. It has no commands to start, list or steer conversations.

- URL: https://github.com/OpenHands/OpenHands/blob/d5d790823e468587e9e4d8517860ca8ef75aad6a/bin/agent-canvas.mjs
- Locator: bin/agent-canvas.mjs lines 55-100 (--help text); package.json bin entry agent-canvas
- Evidence kind: source-inspected
- Source date: 2026-11-20
- Retrieved: 2026-11-22
- Commit: d5d790823e468587e9e4d8517860ca8ef75aad6a
- Path: bin/agent-canvas.mjs

### openhands:b09-automations

OpenHands docs: Managing automations. Automations trigger on a schedule, webhook or event. Event triggers accept GitHub, Jira Data Center, Bitbucket Data Center and Azure DevOps events; custom webhook sources registered under Automate > Events get a webhook URL and signing secret, when the backend's automation service supports it.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/managing-automations
- Locator: Trigger configuration; Event triggers and event types; Event Sources
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:gap-customize

OpenHands Persistent memory; MCP health; Per-backend settings. Canvas loads workspace/user persistent memory when enabled. Skills/MCP/secrets are backend-scoped. MCP health distinguishes reachable, rejected credentials and connection failure; public-server reachability does not verify credentials. Skills load on new conversation start.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/customize-and-settings
- Locator: Persistent memory; MCP health; Per-backend settings
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:nov07-architecture

Agent Canvas architecture. Canvas renders conversations and controls backend APIs; execution, isolation and automation belong to separate runtime services.

- URL: https://github.com/OpenHands/OpenHands/blob/b811a4c33979ca4b5d241730b995b56362f4ab34/docs/architecture.md
- Locator: System boundaries; Runtime modes; Packaging
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:b09-slack

OpenHands docs: Slack Channel Monitor. Prebuilt automation that watches a Slack channel and triggers an OpenHands agent when a message matches the instructions; requires creating a Slack app and installing MCP servers and secrets in Agent Canvas.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/prebuilt/slack-channel-monitor
- Locator: Intro; Prerequisites
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:b09-issue-pr

OpenHands docs: Issue to Pull Request automation. Issue-to-PR automations watch GitHub Issues, GitLab Issues, Jira or Linear for issues labeled or moved to an implementation-ready state (polled, default every 15 minutes), read the issue title, description, acceptance criteria and linked dependencies, create a feature branch (configurable prefix), run tests, open a PR linking the issue and post progress and the PR link back to the tracker. The steps are carried out by the agent following the automation prompt.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/prebuilt/issue-to-pr
- Locator: How it works steps 1-6; supported combinations; setup (trigger label or state, branch prefix, schedule)
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:gap39-task-list

Canvas conversation task list. The Canvas Task List derives its entries from the latest TaskTrackerObservation in the current conversation event store. IDs are generated from list position and statuses are todo/in_progress/done. Inspection of the native task-list route and API/store surfaces found no independent issue/backlog work-item entity; automations are separate trigger definitions.

- URL: https://github.com/OpenHands/OpenHands/blob/e14b76cca01a71597cee242c202eed730e745ce3/src/hooks/use-task-list.ts
- Locator: getTaskListFromEvent; useTaskList; routes/task-list-tab.tsx
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: e14b76cca01a71597cee242c202eed730e745ce3
- Path: src/hooks/use-task-list.ts

### openhands:gap-conversations

OpenHands Child conversations; Commits drawer; Goals; Export; Archive. Canvas child conversations stay linked and return results; local children may use isolated worktrees or shared workspace. Commit drawer shows diffs and agent Git/PR actions. Goals use a judge with round caps and user-message interruption. Transcripts export locally as Markdown/HTML with tool details; archive keeps backend history.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/conversations
- Locator: Child conversations; Commits drawer; Goals; Export; Archive
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:b09-conversations

OpenHands docs: Agent Canvas conversations. launch_child_conversation starts a child on a local or Cloud target; local children use an isolated worktree or the parent's shared workspace; Cloud children use the selected repository and branch. The child stays linked to its parent and its result returns to the parent conversation. While an agent works, its current stage appears as a live group at the end of the chat; this is the only live agent status shown.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/conversations
- Locator: Child Conversations; stage groups; Live Agent Status
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:gap-automations

OpenHands Run statuses; Activity costs; Shared automation conversations; Export/import. Automations have pending/running/completed/failed/cancelled/skipped status; concurrency limits may skip runs. Activity exports CSV/JSON with numeric USD cost or null. Automations export/import versioned JSON; disabling preserves configuration. Other Cloud organization users can view run conversations read-only but cannot send messages.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/managing-automations
- Locator: Run statuses; Activity costs; Shared automation conversations; Export/import
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:gap-critic

OpenHands Experimental critic; Iterative refinement. Experimental critic applies to OpenHands-agent conversations; ACP agents may not expose the path. Default threshold 0.6 and maximum three refinement attempts. Results expose score and detected issue categories; this is additional evaluation, not a successful acceptance-test result.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/critic
- Locator: Experimental critic; Iterative refinement
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:gap-budgets

OpenHands Enterprise managed gateway budgets; Usage; Why totals differ. Enterprise managed-gateway budgets cap organization/user monthly spend. Gateway admits requests and can block at limits; direct provider calls are outside enforcement. Dashboard conversation estimates and gateway budget counters differ in scope/freshness. Spend may be live/stale/unavailable, not zero when unavailable; threshold alerts go to admins/owners.

- URL: https://docs.openhands.dev/openhands/usage/cloud/organizations/budgets
- Locator: Enterprise managed gateway budgets; Usage; Why totals differ
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:gap-roles

OpenHands Roles table; Private settings. Cloud/Enterprise organization roles are Member, Admin and Owner. Members create conversations and own private MCP/secrets/settings; Admins invite/promote users and manage LLM settings/credits; Owners delete organizations and claim Git organizations. Private settings remain private from other members including admins.

- URL: https://docs.openhands.dev/openhands/usage/cloud/organizations/roles-permissions
- Locator: Roles table; Private settings
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:gap-pricing

OpenHands Plan cards; Comparison table. Canvas is free, MIT, single-user/shared-identity and self-hosted. Teams is $500 monthly for up to ten users with $50 monthly per additional seat, 5000 sessions per month, 30-day trial, RBAC and SSO/SAML. Enterprise has custom pricing. LLM keys are user-provided.

- URL: https://www.openhands.dev/pricing
- Locator: Plan cards; Comparison table
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-07

### openhands:src1-sso

OpenHands Enterprise SAML SSO guide. The guide explains how to let users of an OpenHands Enterprise installation sign in through a corporate SAML identity provider such as Okta, Entra ID, Google Workspace or ADFS.

- URL: https://docs.openhands.dev/enterprise/integrations/saml-sso
- Locator: Prerequisites, Step 1 and Step 2 sections
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-10

### openhands:src1-pricing

OpenHands pricing. Agent Canvas is free and MIT licensed. Teams costs 500 USD per month for up to ten users plus 50 USD per extra seat and lists SSO/SAML and RBAC; Enterprise has custom pricing. The page returns HTTP 403 to some automated fetchers but loads with a browser user agent.

- URL: https://www.openhands.dev/pricing
- Locator: Plan cards and comparison table (Agent Canvas, Teams, Enterprise)
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-10

### openhands:nov07-license

OpenHands license. The cited root license governs this repository distribution, subject to component notices.

- URL: https://github.com/OpenHands/OpenHands/blob/b811a4c33979ca4b5d241730b995b56362f4ab34/LICENSE
- Locator: Root license grant
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-07
- Commit: b811a4c33979ca4b5d241730b995b56362f4ab34
- Path: LICENSE

### openhands:src1-telemetry-settings

Agent Canvas app settings analytics switch. App settings render a 'send anonymous usage data' switch that defaults on and saves user_consents_to_analytics and the telemetry consent as granted or denied. On a Cloud backend the switch is disabled and stays on.

- URL: https://github.com/OpenHands/OpenHands/blob/e14b76cca01a71597cee242c202eed730e745ce3/src/routes/app-settings.tsx#L217-L231
- Locator: src/routes/app-settings.tsx lines 112-136 and 217-231 (enable-analytics-switch), release v1.38.0 commit e14b76c
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-10
- Commit: e14b76cca01a71597cee242c202eed730e745ce3
- Path: src/routes/app-settings.tsx

### openhands:src1-telemetry-consent

Agent Canvas telemetry consent modal. A telemetry consent modal asks the user whether to send anonymous usage data and saves the choice as granted or denied.

- URL: https://github.com/OpenHands/OpenHands/blob/e14b76cca01a71597cee242c202eed730e745ce3/src/components/features/analytics/telemetry-consent-banner.tsx#L60-L112
- Locator: src/components/features/analytics/telemetry-consent-banner.tsx lines 60-112, release v1.38.0 commit e14b76c
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-10
- Commit: e14b76cca01a71597cee242c202eed730e745ce3
- Path: src/components/features/analytics/telemetry-consent-banner.tsx

### openhands:gap39-plan-table

OpenHands current self-hosted plan table. The current public price table lists free self-hosted Canvas, self-hosted Teams at $500/month for ten users plus $50/month additional seats, capped at 5000 sessions monthly, and custom Enterprise. It lists no one-time licence. The separately linked Cloud backend is not priced in this table.

- URL: https://www.openhands.dev/pricing
- Locator: Agent Canvas, Teams and Enterprise; Comparison table
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### openhands:gap39-cloud-model-credits

OpenHands Cloud model credits. Cloud users must buy at least $10 in credits before generating an OpenHands LLM Key. That key can be used in the CLI, self-hosted OpenHands or other coding agents. These are model-provider credits, not proof of a metered ADE or sandbox price.

- URL: https://docs.openhands.dev/openhands/usage/settings/api-keys-settings
- Locator: OpenHands LLM Key
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### openhands:b09-apps

OpenHands docs: Apps (Beta). Apps are a beta feature whose name and API may change; the beta supports custom pages only and does not isolate app code.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/canvas-extensions
- Locator: Apps (Beta) warning; Design for the Beta Lifecycle
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:b09-critic

OpenHands docs: Critic. The critic feature is experimental; configuration options and scoring behavior may change.

- URL: https://docs.openhands.dev/openhands/usage/agent-canvas/critic
- Locator: Experimental warning
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-22

### openhands:b09-releases

OpenHands GitHub releases. Releases v1.37.0 (2026-11-06), v1.38.0 (2026-11-10), v1.39.0 (2026-11-11), v1.40.0 (2026-11-12), v1.41.0 (2026-11-16), v1.42.0 (2026-11-18) and v1.43.0 (2026-11-20, latest).

- URL: https://github.com/OpenHands/OpenHands/releases
- Locator: Release list v1.37.0-v1.43.0
- Evidence kind: documented
- Source date: 2026-11-20
- Retrieved: 2026-11-22
