---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/products/happy/"
data_url: "https://podium.do/compare/agents/products/happy/data.json"
generated_at: 2026-11-22
oldest_checked_at: 2026-11-08
last_checked_at: 2026-11-13
publisher: "Podium"
---

# Happy: 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; 32 were also cross-checked by a second agent. Source checks: 2026-11-08 to 2026-11-13. A missing sourced finding is not evidence that a capability is absent.

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

## Access and agent choice

### ACC-01: Client access

Verification status: Sourced (sourced)
Support: partial

Happy provides Desktop for macOS, Windows and Linux; mobile iOS, Android and web; and its original happy CLI wrapping Claude Code or Codex. Desktop uses a separate Happy Agent runtime for multi-model sessions and teams. Paired phone apps continue the same encrypted sessions and allow users to read work and respond away from the desktop. The first-party repository describes the mobile app as available on iOS, Android and web. This establishes the phone web client, not desktop parity.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Happy Agent v2026.11.4 (db813011c038b2288fbc1efd0e10ef2149c838d2), Desktop v0.0.103 (a369b7b0a86a344904a2e171a78e2b0daf0b4be8); targeted first-party pass 2026-11-13; no installed-product test; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- The scoped first-party source pass does not establish editor_extensions, notifications. No hands-on scenario was run.

- desktop_os — Desktop os [supported]: Happy provides Desktop for macOS, Windows and Linux; mobile iOS, Android and web; and its original happy CLI wrapping Claude Code or Codex. Desktop uses a separate Happy Agent runtime for multi-model sessions and teams. Sources: happy:nov08-acc-01-1.
- mobile_apps — Mobile apps [supported]: Happy provides Desktop for macOS, Windows and Linux; mobile iOS, Android and web; and its original happy CLI wrapping Claude Code or Codex. Desktop uses a separate Happy Agent runtime for multi-model sessions and teams. Sources: happy:nov08-acc-01-1.
- browser — Browser [supported]: Happy provides Desktop for macOS, Windows and Linux; mobile iOS, Android and web; and its original happy CLI wrapping Claude Code or Codex. Desktop uses a separate Happy Agent runtime for multi-model sessions and teams. Sources: happy:nov08-acc-01-1.
- mobile_browser — Mobile browser [supported]: The first-party repository describes the mobile app as available on iOS, Android and web. This establishes the phone web client, not desktop parity. Sources: happy:nov08-acc-01-1.
- cli — Cli [supported]: Happy provides Desktop for macOS, Windows and Linux; mobile iOS, Android and web; and its original happy CLI wrapping Claude Code or Codex. Desktop uses a separate Happy Agent runtime for multi-model sessions and teams. Sources: happy:nov08-acc-01-1.
- editor_extensions — Editor extensions [unknown]: Editor extensions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_actions — Task actions [supported]: Paired phone apps continue the same encrypted sessions and allow users to read work and respond away from the desktop. Sources: happy:nov08-acc-01-2.
- notifications — Notifications [unknown]: Notifications remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cross_device_continuity — Cross device continuity [supported]: Paired phone apps continue the same encrypted sessions and allow users to read work and respond away from the desktop. Sources: happy:nov08-acc-01-2.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: happy:nov08-acc-01-1, happy:nov08-acc-01-2

### ACC-02: Agent and model choice

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

Happy Agent runs its own loop by default and calls Claude, Codex and Grok models on existing CLI sign-ins. Optional harnesses run Claude Code itself (claude_code) and Codex CLI itself (codex_cli); Gemini runs through Antigravity and OpenCode or other ACP agents through ACP (beta). Grok is a model choice, not a separate harness. Model and effort can change mid-session without discarding the transcript. The original happy CLI wraps Claude Code and Codex directly. Happy Agent v2026.11.4 runs the Antigravity whole-agent harness through antigravity-acp@1.2.0, a community ACP adapter driving the signed-in agy CLI.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08 Antigravity source pass: v2026.11.4 (db813011c038b2288fbc1efd0e10ef2149c838d2). Antigravity integration is beta.; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.
- Antigravity is a beta foreign-harness integration using a community ACP adapter and its own login; new sessions are serialized to avoid conversation binding collisions.

- harnesses — Harnesses [supported]: Happy's own harness by default; claude_code and codex_cli harness options run Claude Code and Codex CLI themselves; Antigravity and OpenCode or other ACP agents (beta). The original CLI wraps Claude Code and Codex. Happy Agent v2026.11.4 runs the Antigravity whole-agent harness through antigravity-acp@1.2.0, a community ACP adapter driving the signed-in agy CLI. Sources: happy:nov08-acc-02-2, happy:nov08-acc-01-1, happy:agy-release-1.
- model_providers — Model providers [supported]: Claude, Codex and Grok models on existing CLI sign-ins, Gemini through Antigravity, and Bedrock. Sources: happy:nov08-acc-02-1.
- custom_adapters — Custom adapters [supported]: Any Agent Client Protocol agent can be added on its own login (beta). Sources: happy:nov08-acc-02-1, happy:nov08-acc-02-2.
- session_integration — Session integration [supported]: The claude_code and codex_cli harnesses run those agents' own loops on their accounts inside Happy sessions. Sources: happy:nov08-acc-02-2.
- mixed_harness_operation — Mixed harness operation [supported]: Subagents pick their own model, and harness options sit alongside Happy's own loop; no mixed-harness run was observed. Sources: happy:nov08-acc-02-1, happy:nov08-acc-02-2.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: happy:nov08-acc-02-1, happy:nov08-acc-02-2, happy:nov08-acc-01-1, happy:agy-release-1

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

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

Happy reuses existing Claude Code, Codex and Grok CLI sign-ins and their subscriptions; Antigravity and ACP agents use their own login. Bedrock API keys or the AWS credential chain are supported.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- agent_subscriptions — Agent subscriptions [supported]: Happy reuses Claude Code, Codex and Grok CLI sign-ins and their subscriptions; Antigravity and ACP use their own login. Bedrock API keys or the AWS credential chain are supported. Happy does not proxy these provider requests. Sources: happy:nov08-acc-03-1.
- api_accounts — Api accounts [supported]: Happy reuses Claude Code, Codex and Grok CLI sign-ins and their subscriptions; Antigravity and ACP use their own login. Bedrock API keys or the AWS credential chain are supported. Happy does not proxy these provider requests. Sources: happy:nov08-acc-03-1.
- vendor_credits — Vendor credits [unknown]: Vendor credits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- local_models — Local models [unknown]: Local models remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- account_switching — Account switching [supported]: Happy reuses Claude Code, Codex and Grok CLI sign-ins and their subscriptions; Antigravity and ACP use their own login. Bedrock API keys or the AWS credential chain are supported. Happy does not proxy these provider requests. Sources: happy:nov08-acc-03-1.
- vendor_account_requirement — Vendor account requirement [unknown]: Vendor account requirement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- provider_restrictions — Provider restrictions [supported]: Happy reuses Claude Code, Codex and Grok CLI sign-ins and their subscriptions; Antigravity and ACP use their own login. Bedrock API keys or the AWS credential chain are supported. Happy does not proxy these provider requests. Sources: happy:nov08-acc-03-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: happy:nov08-acc-03-1

### ACC-04: Onboarding and project prerequisites

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

Importing registers an existing folder without moving, copying or initializing Git. A project without Git uses a plain folder copy when a workspace is needed.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- first_task_setup — First task setup [supported]: Importing registers an existing folder without moving, copying or initializing Git. A project without Git uses a plain folder copy when a workspace is needed. Sources: happy:nov08-acc-04-1.
- no_git — No git [supported]: Importing registers an existing folder without moving, copying or initializing Git. A project without Git uses a plain folder copy when a workspace is needed. Sources: happy:nov08-acc-04-1.
- local_git_without_remote — Local git without remote [supported]: Importing registers an existing folder without moving, copying or initializing Git. A project without Git uses a plain folder copy when a workspace is needed. Sources: happy:nov08-acc-04-1.
- hosted_git — Hosted git [unknown]: Hosted git remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prerequisite_guidance — Prerequisite guidance [unknown]: Prerequisite guidance remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- managed_cloud_setup — Managed cloud setup [unknown]: Managed cloud setup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- byo_vps_onboarding — Byo vps onboarding [unknown]: Byo vps onboarding remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-acc-04-1

### ACC-05: Programmable access

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

Happy Agent exposes a token-authenticated REST API for sessions, streaming events and control on user infrastructure. The original happy CLI is a separate product-owned terminal entry point.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- cli — Cli [supported]: Happy Agent exposes a token-authenticated REST API for sessions, streaming events and control on user infrastructure. The original happy CLI is a separate product-owned terminal entry point. Sources: happy:nov08-acc-05-1.
- api — Api [supported]: Happy Agent exposes a token-authenticated REST API for sessions, streaming events and control on user infrastructure. The original happy CLI is a separate product-owned terminal entry point. Sources: happy:nov08-acc-05-1.
- sdk — Sdk [unknown]: Sdk remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- mcp_server — Mcp server [unknown]: Mcp server remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- webhooks — Webhooks [unknown]: Webhooks remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- operations — Operations [supported]: Happy Agent exposes a token-authenticated REST API for sessions, streaming events and control on user infrastructure. The original happy CLI is a separate product-owned terminal entry point. Sources: happy:nov08-acc-05-1.
- authentication — Authentication [supported]: Happy Agent exposes a token-authenticated REST API for sessions, streaming events and control on user infrastructure. The original happy CLI is a separate product-owned terminal entry point. Sources: happy:nov08-acc-05-1.
- stability — Stability [unknown]: Stability remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-acc-05-1

### ACC-06: External tools and extensions

Verification status: Sourced (sourced)
Support: partial

Skills are SKILL.md files and MCP servers are mcp.toml entries; agents can write both. MCP tools need Auto or Full access, every Auto call is reviewed, and MCP servers run outside the OS sandbox.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- mcp_client — Mcp client [supported]: Skills are Markdown files and MCP configuration uses TOML. Agents can write both; MCP tools in Auto mode require review and their servers run outside the OS sandbox. Sources: happy:nov08-acc-06-1.
- plugins — Plugins [unknown]: Plugins remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- custom_tools — Custom tools [supported]: Skills are Markdown files and MCP configuration uses TOML. Agents can write both; MCP tools in Auto mode require review and their servers run outside the OS sandbox. Sources: happy:nov08-acc-06-1.
- instructions_import — Instructions import [supported]: Skills are Markdown files and MCP configuration uses TOML. Agents can write both; MCP tools in Auto mode require review and their servers run outside the OS sandbox. Sources: happy:nov08-acc-06-1.
- authentication — Authentication [unknown]: Authentication remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- permission_scope — Permission scope [supported]: MCP tools need Auto or Full access, every Auto call is reviewed, and MCP servers run outside the OS sandbox. Sources: happy:nov08-acc-06-1, happy:nov08-run-02-2.
- integration_owner — Integration owner [unknown]: Integration owner remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: happy:nov08-acc-06-1, happy:nov08-run-02-2

### ACC-07: Client implementation

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.

## Planning and context

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

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

The built-in Chief of Staff handles setup and task creation through ordinary conversation, including projects, remote hosts and teams. Persistent standalone issue metadata is not established.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- local_creation — Local creation [supported]: The built-in Chief of Staff handles setup and task creation through ordinary conversation, including projects, remote hosts and teams. Persistent standalone issue metadata is not established. Sources: happy:nov08-plan-01-1.
- prompt_intake — Prompt intake [supported]: The built-in Chief of Staff handles setup and task creation through ordinary conversation, including projects, remote hosts and teams. Persistent standalone issue metadata is not established. Sources: happy:nov08-plan-01-1.
- external_import — External import [unknown]: External import remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- chat_git_triggers — Chat git triggers [unknown]: Chat git triggers remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- authoritative_tracker — Authoritative tracker [unknown]: Authoritative tracker remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- stable_ids — Stable ids [unknown]: Stable ids remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- sync — Sync [unknown]: Sync remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- supported_edits — Supported edits [unknown]: Supported edits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- external_roundtrips — External roundtrips [unknown]: External roundtrips remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-plan-01-1

### 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: Agent cross-checked (agent-cross-checked)
Support: partial

Subagent trees are capped at depth three and at most five agents including finished children. Sessions have exact agent IDs for messaging and retained follow-up. This is session hierarchy, not verified issue dependency enforcement.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- epics — Epics [unknown]: Epics remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- hierarchy — Hierarchy [supported]: Subagent trees are capped at depth three and at most five agents including finished children. Sessions have exact agent IDs for messaging and retained follow-up. This is session hierarchy, not verified issue dependency enforcement. Sources: happy:nov08-plan-03-1.
- blockers — Blockers [unknown]: Blockers remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- readiness — Readiness [unknown]: Readiness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- enforcement — Enforcement [unknown]: Enforcement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- state_propagation — State propagation [unknown]: State propagation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_to_epic — Task to epic [unknown]: Task to epic remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- identity_retention — Identity retention [supported]: Subagent trees are capped at depth three and at most five agents including finished children. Sessions have exact agent IDs for messaging and retained follow-up. This is session hierarchy, not verified issue dependency enforcement. Sources: happy:nov08-plan-03-1.
- workflow_constraints — Workflow constraints [supported]: Subagent trees are capped at depth three and at most five agents including finished children. Sessions have exact agent IDs for messaging and retained follow-up. This is session hierarchy, not verified issue dependency enforcement. Sources: happy:nov08-plan-03-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-plan-03-1

### PLAN-04: Shared context and memory

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

AGENTS.md files in the project tree are read by each agent and reread when they change; global AGENTS.md applies across projects.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- instructions — Instructions [supported]: AGENTS.md files in the project tree are read by each agent and reread when they change; global AGENTS.md applies across projects. Sources: happy:nov08-plan-04-1.
- skills — Skills [unknown]: Skills remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- project_docs — Project docs [unknown]: Project docs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- memory — Memory [unknown]: Memory remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- scope — Scope [supported]: AGENTS.md files in the project tree are read by each agent and reread when they change; global AGENTS.md applies across projects. Sources: happy:nov08-plan-04-1.
- provenance — Provenance [unknown]: Provenance remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- correction — Correction [unknown]: Correction remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deletion — Deletion [unknown]: Deletion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- freshness — Freshness [supported]: AGENTS.md files in the project tree are read by each agent and reread when they change; global AGENTS.md applies across projects. Sources: happy:nov08-plan-04-1.
- takeover_continuity — Takeover continuity [unknown]: Takeover continuity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-plan-04-1

### 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

Happy creates persistent task records through its API, agent tool and Desktop UI. Native task operations rename task records. Creating a task without opening text stores an idle draft. The task catalog has a task ID separate from its linked agent and workspace IDs; each task has one root conversation. Task state is persisted as active or archived with restoration and versioned updates. Task archival persists and stops the task agent and descendants. Native unarchive restores an archived task.

Availability: unknown
Delivery: unknown
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Happy Agent v2026.11.4 (db813011c038b2288fbc1efd0e10ef2149c838d2), Desktop v0.0.103 (a369b7b0a86a344904a2e171a78e2b0daf0b4be8); targeted first-party pass 2026-11-13; no installed-product test; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- The scoped first-party source pass does not establish discuss, prioritize, label, assign, search, filter, project_epic_views, explicit_dispatch, metadata, external_tracker_requirement. No hands-on scenario was run.

- create — Create [supported]: Happy creates persistent task records through its API, agent tool and Desktop UI. Sources: happy:facet38-task-schema, happy:facet38-task-operations.
- edit — Edit [supported]: Native task operations rename task records. Sources: happy:facet38-task-operations.
- discuss — Discuss [unknown]: Discuss remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prioritize — Prioritize [unknown]: Prioritize remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- label — Label [unknown]: Label remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- assign — Assign [unknown]: Assign remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- search — Search [unknown]: Search remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- filter — Filter [unknown]: Filter remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- archive — Archive [supported]: Task archival persists and stops the task agent and descendants. Sources: happy:facet38-task-operations.
- reopen — Reopen [supported]: Native unarchive restores an archived task. Sources: happy:facet38-task-operations.
- project_epic_views — Project epic views [unknown]: Project epic views remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- idea_parking — Idea parking [supported]: Creating a task without opening text stores an idle draft. Sources: happy:facet38-task-schema.
- explicit_dispatch — Explicit dispatch [unknown]: Explicit dispatch remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_session_separation — Task session separation [supported]: The task catalog has a task ID separate from its linked agent and workspace IDs; each task has one root conversation. Sources: happy:facet38-task-schema.
- metadata — Metadata [unknown]: Metadata remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- durable_states — Durable states [supported]: Task state is persisted as active or archived with restoration and versioned updates. Sources: happy:facet38-task-schema, happy:facet38-task-operations.
- external_tracker_requirement — External tracker requirement [unknown]: External tracker requirement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

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

Sources: happy:facet38-task-schema, happy:facet38-task-operations

### 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

Subagents run in the background by default and return completion to the parent. Desktop displays subagents and running tools; tree size is bounded.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- concurrent_sessions — Concurrent sessions [supported]: Subagents run in the background by default and return completion to the parent. Desktop displays subagents and running tools; tree size is bounded. Sources: happy:nov08-recheck-01-1.
- concurrent_tasks — Concurrent tasks [supported]: Subagents run in the background by default and return completion to the parent. Desktop displays subagents and running tools; tree size is bounded. Sources: happy:nov08-recheck-01-1.
- quotas — Quotas [supported]: Subagents run in the background by default and return completion to the parent. Desktop displays subagents and running tools; tree size is bounded. Sources: happy:nov08-recheck-01-1.
- observed_concurrency — Observed concurrency [unknown]: Observed concurrency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- status_visibility — Status visibility [supported]: Subagents run in the background by default and return completion to the parent. Desktop displays subagents and running tools; tree size is bounded. Sources: happy:nov08-recheck-01-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-01-1

### COORD-02: Ownership and dispatch

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

Bots and their subtasks may create a full conversation in a new workspace, with the creator as coordinator. Only the creating session may archive that workspace.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- human_assignment — Human assignment [unknown]: Human assignment remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- agent_assignment — Agent assignment [supported]: Bots and their subtasks may create a full conversation in a new workspace, with the creator as coordinator. Only the creating session may archive that workspace. Sources: happy:nov08-recheck-02-1.
- claims — Claims [unknown]: Claims remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- queues — Queues [unknown]: Queues remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- routing — Routing [unknown]: Routing remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- duplicate_prevention — Duplicate prevention [unknown]: Duplicate prevention remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ownership_enforcement — Ownership enforcement [supported]: Bots and their subtasks may create a full conversation in a new workspace, with the creator as coordinator. Only the creating session may archive that workspace. Sources: happy:nov08-recheck-02-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-02-1

### COORD-03: Inspectable delegation and communication

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

Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- roles — Roles [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- model_harness_effort — Model harness effort [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- messages — Messages [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- results_return — Results return [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- cross_harness — Cross harness [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- orchestration_owner — Orchestration owner [unknown]: Orchestration owner remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- activation — Activation [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- authentication — Authentication [unknown]: Authentication remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- live_progress — Live progress [unknown]: Live progress remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_results — Retained results [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- followup — Followup [supported]: Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines. Sources: happy:nov08-recheck-03-1.
- invocation — Invocation [unknown]: Invocation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-03-1

### COORD-04: Unattended triggers

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

Primary sessions can schedule messages to known agent IDs, list or cancel them and survive intervening runtime restarts. Durable waits end early on new input. This establishes scheduled work, not an unrestricted external-event scheduler.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- schedules — Schedules [supported]: Primary sessions can schedule messages to known agent IDs, list or cancel them and survive intervening runtime restarts. Durable waits end early on new input. This establishes scheduled work, not an unrestricted external-event scheduler. Sources: happy:nov08-recheck-04-1.
- events — Events [unknown]: Events remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- recurring_tasks — Recurring tasks [unknown]: Recurring tasks remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- completion_conditions — Completion conditions [unknown]: Completion conditions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- scheduler_location — Scheduler location [supported]: Primary sessions can schedule messages to known agent IDs, list or cancel them and survive intervening runtime restarts. Durable waits end early on new input. This establishes scheduled work, not an unrestricted external-event scheduler. Sources: happy:nov08-recheck-04-1.
- overlaps — Overlaps [unknown]: Overlaps remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retries — Retries [unknown]: Retries remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- client_independence — Client independence [supported]: Primary sessions can schedule messages to known agent IDs, list or cancel them and survive intervening runtime restarts. Durable waits end early on new input. This establishes scheduled work, not an unrestricted external-event scheduler. Sources: happy:nov08-recheck-04-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-04-1

### COORD-05: Intervention and attention

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

Agent questions remain in the conversation and experimental Inbox; answering on one device closes the shared state. Away presence instructs agents to continue with notes instead of waiting indefinitely.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- pause — Pause [unknown]: Pause remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- stop — Stop [unknown]: Stop remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- resume — Resume [unknown]: Resume remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- steer — Steer [supported]: Agent questions remain in the conversation and experimental Inbox; answering on one device closes the shared state. Away presence instructs agents to continue with notes instead of waiting indefinitely. Sources: happy:nov08-recheck-05-1.
- notifications — Notifications [supported]: Agent questions remain in the conversation and experimental Inbox; answering on one device closes the shared state. Away presence instructs agents to continue with notes instead of waiting indefinitely. Sources: happy:nov08-recheck-05-1.
- pending_decisions — Pending decisions [supported]: Agent questions remain in the conversation and experimental Inbox; answering on one device closes the shared state. Away presence instructs agents to continue with notes instead of waiting indefinitely. Sources: happy:nov08-recheck-05-1.
- escalation — Escalation [unknown]: Escalation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- visible_errors — Visible errors [unknown]: Visible errors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- chat_terminal_parity — Chat terminal parity [unknown]: Chat terminal parity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_history — Retained history [supported]: Agent questions remain in the conversation and experimental Inbox; answering on one device closes the shared state. Away presence instructs agents to continue with notes instead of waiting indefinitely. Sources: happy:nov08-recheck-05-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-05-1

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

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

Per-session UI shows phase, tools, background processes, subagents, waiting state, whole-tree token usage and changed files. Fleet navigation has not been measured.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- fleet_fixture — Fleet fixture [unknown]: Fleet fixture remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- parent_child — Parent child [supported]: Per-session UI shows phase, tools, background processes, subagents, waiting state, whole-tree token usage and changed files. Fleet navigation has not been measured. Sources: happy:nov08-recheck-06-1.
- dependencies — Dependencies [unknown]: Dependencies remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- attention — Attention [supported]: Per-session UI shows phase, tools, background processes, subagents, waiting state, whole-tree token usage and changed files. Fleet navigation has not been measured. Sources: happy:nov08-recheck-06-1.
- history — History [supported]: Per-session UI shows phase, tools, background processes, subagents, waiting state, whole-tree token usage and changed files. Fleet navigation has not been measured. Sources: happy:nov08-recheck-06-1.
- workload — Workload [supported]: Per-session UI shows phase, tools, background processes, subagents, waiting state, whole-tree token usage and changed files. Fleet navigation has not been measured. Sources: happy:nov08-recheck-06-1.
- navigation_errors — Navigation errors [unknown]: Navigation errors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- fixture_mode — Fixture mode [unknown]: Fixture mode remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-06-1

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

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

The built-in Chief of Staff configures accounts, imports projects, pairs phones, deploys remote agents and creates teams through conversation.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- quick_task — Quick task [supported]: The built-in Chief of Staff configures accounts, imports projects, pairs phones, deploys remote agents and creates teams through conversation. Sources: happy:nov08-recheck-07-1.
- growing_epic — Growing epic [unknown]: Growing epic remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- presets — Presets [unknown]: Presets remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- natural_language — Natural language [supported]: The built-in Chief of Staff configures accounts, imports projects, pairs phones, deploys remote agents and creates teams through conversation. Sources: happy:nov08-recheck-07-1.
- agent_configuration — Agent configuration [supported]: The built-in Chief of Staff configures accounts, imports projects, pairs phones, deploys remote agents and creates teams through conversation. Sources: happy:nov08-recheck-07-1.
- in_run_changes — In run changes [unknown]: In run changes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- live_roles — Live roles [unknown]: Live roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_relationships — Retained relationships [unknown]: Retained relationships remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- discoverability — Discoverability [unknown]: Discoverability remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- auth_friction — Auth friction [unknown]: Auth friction remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-recheck-07-1

## Execution and reliability

### RUN-01: Laptop-independent execution

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

Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- local — Local [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.
- byo_remote — Byo remote [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.
- self_hosted — Self hosted [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.
- managed_cloud — Managed cloud [unknown]: Managed cloud remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- hybrid — Hybrid [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.
- provisioning — Provisioning [unknown]: Provisioning remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- payer — Payer [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.
- resources — Resources [unknown]: Resources remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- region — Region [unknown]: Region remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- expiry — Expiry [unknown]: Expiry remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- client_disconnect — Client disconnect [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.
- other_device_continuation — Other device continuation [supported]: Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute. Sources: happy:nov08-run-01-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-run-01-1

### RUN-02: Workspace and process isolation

Verification status: Sourced (sourced)
Support: partial

Parallel workspaces use Git worktrees on branches cut from the remote trunk. File sync and setup commands run per workspace; nongit projects use a plain copy. The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. No VM or microVM isolation backend exists in the inspected runtime; local OS sandboxing and Docker are separate options.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Happy Agent v2026.11.4 (db813011c038b2288fbc1efd0e10ef2149c838d2), Desktop v0.0.103 (a369b7b0a86a344904a2e171a78e2b0daf0b4be8); targeted first-party pass 2026-11-13; no installed-product test; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- The scoped first-party source pass does not establish checkout, process. No hands-on scenario was run.

- checkout — Checkout [unknown]: Checkout remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- branch — Branch [supported]: Parallel workspaces use Git worktrees on branches cut from the remote trunk. File sync and setup commands run per workspace; nongit projects use a plain copy. Sources: happy:nov08-run-02-1.
- worktree — Worktree [supported]: Parallel workspaces use Git worktrees on branches cut from the remote trunk. File sync and setup commands run per workspace; nongit projects use a plain copy. Sources: happy:nov08-run-02-1.
- container — Container [supported]: The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. Sources: happy:nov08-run-02-2.
- vm — Vm [unsupported]: No VM or microVM isolation backend exists in the inspected runtime; local OS sandboxing and Docker are separate options. Sources: happy:facet38-isolation-options.
- os_sandbox — Os sandbox [supported]: The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. Sources: happy:nov08-run-02-2.
- filesystem — Filesystem [supported]: The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. Sources: happy:nov08-run-02-2.
- process — Process [unknown]: Process remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- network — Network [supported]: The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. Sources: happy:nov08-run-02-2.
- secrets — Secrets [supported]: The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. Sources: happy:nov08-run-02-2.
- code_separation — Code separation [supported]: Parallel workspaces use Git worktrees on branches cut from the remote trunk. File sync and setup commands run per workspace; nongit projects use a plain copy. Sources: happy:nov08-run-02-1.
- security_boundary — Security boundary [supported]: The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container. Sources: happy:nov08-run-02-2.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: happy:nov08-run-02-1, happy:nov08-run-02-2, happy:facet38-isolation-options

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

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

Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- client_disconnect — Client disconnect [supported]: Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test. Sources: happy:nov08-run-03-1.
- worker_crash — Worker crash [unknown]: Worker crash remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- service_restart — Service restart [supported]: Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test. Sources: happy:nov08-run-03-1.
- expiry — Expiry [unknown]: Expiry remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- transcript_reload — Transcript reload [supported]: Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test. Sources: happy:nov08-run-03-1.
- process_reconnect — Process reconnect [unknown]: Process reconnect remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_resume — Task resume [supported]: Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test. Sources: happy:nov08-run-03-1.
- state_reconstruction — State reconstruction [unknown]: State reconstruction remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- context_loss — Context loss [supported]: Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test. Sources: happy:nov08-run-03-1.
- duplicate_actions — Duplicate actions [unknown]: Duplicate actions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- manual_repair — Manual repair [unknown]: Manual repair remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- multi_day_continuity — Multi day continuity [unknown]: Multi day continuity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-run-03-1

### RUN-04: Development environment reliability

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

New workspaces copy configured sync files and run setup_commands. They start with a cold build cache. A failed setup command logs a warning while checkout and file sync determine readiness.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- dependencies — Dependencies [supported]: New workspaces copy configured sync files and run setup_commands. They start with a cold build cache. A failed setup command logs a warning while checkout and file sync determine readiness. Sources: happy:nov08-run-04-1.
- caches — Caches [supported]: New workspaces copy configured sync files and run setup_commands. They start with a cold build cache. A failed setup command logs a warning while checkout and file sync determine readiness. Sources: happy:nov08-run-04-1.
- snapshots — Snapshots [unknown]: Snapshots remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- services — Services [unknown]: Services remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ports — Ports [unknown]: Ports remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- secrets — Secrets [supported]: New workspaces copy configured sync files and run setup_commands. They start with a cold build cache. A failed setup command logs a warning while checkout and file sync determine readiness. Sources: happy:nov08-run-04-1.
- duplicate_installs — Duplicate installs [supported]: New workspaces copy configured sync files and run setup_commands. They start with a cold build cache. A failed setup command logs a warning while checkout and file sync determine readiness. Sources: happy:nov08-run-04-1.
- collisions — Collisions [unknown]: Collisions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- remote_setup — Remote setup [unknown]: Remote setup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- automatic_repair — Automatic repair [unknown]: Automatic repair remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-run-04-1

### RUN-05: Limits and failure handling

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

Smart provider pools can rotate same-provider accounts after authentication or quota-exhaustion errors. Provider quotas are polled about every fifteen minutes and are observations rather than billing records.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- time_limits — Time limits [unknown]: Time limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- turn_limits — Turn limits [unknown]: Turn limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- token_limits — Token limits [unknown]: Token limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- spend_limits — Spend limits [unknown]: Spend limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- timeouts — Timeouts [unknown]: Timeouts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retries — Retries [supported]: Smart provider pools can rotate same-provider accounts after authentication or quota-exhaustion errors. Provider quotas are polled about every fifteen minutes and are observations rather than billing records. Sources: happy:nov08-run-05-1.
- provider_failures — Provider failures [supported]: Smart provider pools can rotate same-provider accounts after authentication or quota-exhaustion errors. Provider quotas are polled about every fifteen minutes and are observations rather than billing records. Sources: happy:nov08-run-05-1.
- enforcement — Enforcement [unknown]: Enforcement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-run-05-1

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

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

Session status includes active tools, background work, subagents, waiting state, tokens and changed files. Deliberate failure and approval consistency after reconnect remain untested.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- logs — Logs [supported]: Session status includes active tools, background work, subagents, waiting state, tokens and changed files. Deliberate failure and approval consistency after reconnect remain untested. Sources: happy:nov08-run-06-1.
- traces — Traces [unknown]: Traces remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- failure_reasons — Failure reasons [unknown]: Failure reasons remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- usage_export — Usage export [unknown]: Usage export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_stats — Task stats [unknown]: Task stats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- agent_stats — Agent stats [supported]: Session status includes active tools, background work, subagents, waiting state, tokens and changed files. Deliberate failure and approval consistency after reconnect remain untested. Sources: happy:nov08-run-06-1.
- project_stats — Project stats [unknown]: Project stats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- time_stats — Time stats [unknown]: Time stats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- failure_status — Failure status [unknown]: Failure status remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- approval_status — Approval status [unknown]: Approval status remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- reconnect_consistency — Reconnect consistency [unknown]: Reconnect consistency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- performance_method — Performance method [unknown]: Performance method remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- responsiveness — Responsiveness [unknown]: Responsiveness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-run-06-1

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

Verification status: Sourced (sourced)
Support: partial

Provider quotas are polled about every fifteen minutes and shown in the app; they are observations, not billing records.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- task_cost — Task cost [unknown]: Task cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- session_cost — Session cost [unknown]: Session cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- child_cost — Child cost [unknown]: Child cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- epic_cost — Epic cost [unknown]: Epic cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- harness_aggregation — Harness aggregation [unknown]: Harness aggregation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- billed_vs_estimated — Billed vs estimated [supported]: Provider quotas are polled about every fifteen minutes. These are not invoices; Happy does not present unknown subscription marginal cost as free model use. Sources: happy:nov08-run-07-1.
- tokens — Tokens [unknown]: Tokens remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- subscription_allowance — Subscription allowance [supported]: Provider quotas are polled about every fifteen minutes. These are not invoices; Happy does not present unknown subscription marginal cost as free model use. Sources: happy:nov08-run-07-1.
- provider_reconciliation — Provider reconciliation [unknown]: Provider reconciliation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- compute_cost — Compute cost [unknown]: Compute cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- refresh_delay — Refresh delay [supported]: Provider quotas are polled about every fifteen minutes. These are not invoices; Happy does not present unknown subscription marginal cost as free model use. Sources: happy:nov08-run-07-1.
- alerts — Alerts [unknown]: Alerts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- export — Export [unknown]: Export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- drilldown — Drilldown [unknown]: Drilldown remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: happy:nov08-run-07-1

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

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.

## Human collaboration and control

### TEAM-01: Live human collaboration

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

Team members see the same projects and sessions and can speak to the agent. Changes in speaker include the member name/email; per-member drafts and task ordering stay personal.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- visibility — Visibility [supported]: Team members see the same projects and sessions and can speak to the agent. Changes in speaker include the member name/email; per-member drafts and task ordering stay personal. Sources: happy:nov08-team-01-1.
- discussion — Discussion [unknown]: Discussion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- comments — Comments [unknown]: Comments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- presence — Presence [unknown]: Presence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- coprompting — Coprompting [supported]: Team members see the same projects and sessions and can speak to the agent. Changes in speaker include the member name/email; per-member drafts and task ordering stay personal. Sources: happy:nov08-team-01-1.
- ordering — Ordering [unknown]: Ordering remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- conflicts — Conflicts [unknown]: Conflicts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- attribution — Attribution [supported]: Team members see the same projects and sessions and can speak to the agent. Changes in speaker include the member name/email; per-member drafts and task ordering stay personal. Sources: happy:nov08-team-01-1.
- permissions — Permissions [supported]: Team members see the same projects and sessions and can speak to the agent. Changes in speaker include the member name/email; per-member drafts and task ordering stay personal. Sources: happy:nov08-team-01-1.
- plan_restrictions — Plan restrictions [unknown]: Plan restrictions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- owner_online — Owner online [unknown]: Owner online remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-team-01-1

### TEAM-02: Roles and access boundaries

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

Team mode verifies per-user WorkOS tokens. The owner alone renames the installation, toggles global skills or archives others tasks; members otherwise have equal access and can select Full access. A remove-member action is explicitly not built yet.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- organization_roles — Organization roles [supported]: Team mode verifies per-user WorkOS tokens. The owner alone renames the installation, toggles global skills or archives others tasks; members otherwise have equal access and can select Full access. A remove-member action is explicitly not built yet. Sources: happy:nov08-team-02-1.
- project_roles — Project roles [unknown]: Project roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_roles — Task roles [unknown]: Task roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- membership — Membership [supported]: Team mode verifies per-user WorkOS tokens. The owner alone renames the installation, toggles global skills or archives others tasks; members otherwise have equal access and can select Full access. A remove-member action is explicitly not built yet. Sources: happy:nov08-team-02-1.
- sso — Sso [supported]: Team mode can replace Happy's WorkOS accounts with the organization's own identity provider through an organization-run OAuth authorization server whose JWTs the daemon verifies (Agent v2026.11.4; desktop v0.0.103 discovers sign-in methods). Documented and source-inspected, not tested; the deployer must operate the authorization server. Sources: happy:src4-enterprise-signin, happy:src4-agent-teamjwt, happy:src4-desktop-auth.
- provisioning — Provisioning [unknown]: Provisioning remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- unauthorized_access — Unauthorized access [unknown]: Unauthorized access remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- revocation — Revocation [unknown]: Revocation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- plan_scope — Plan scope [supported]: Team mode verifies per-user WorkOS tokens. The owner alone renames the installation, toggles global skills or archives others tasks; members otherwise have equal access and can select Full access. A remove-member action is explicitly not built yet. Sources: happy:nov08-team-02-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: happy:nov08-team-02-1, happy:src4-enterprise-signin, happy:src4-agent-teamjwt, happy:src4-desktop-auth

### TEAM-03: Approvals and temporary access

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

Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- command — Command [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- tool — Tool [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- network — Network [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- secret — Secret [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- delivery — Delivery [unknown]: Delivery remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- approver_identity — Approver identity [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- lifetime — Lifetime [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- allow — Allow [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- deny — Deny [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- revoke — Revoke [unknown]: Revoke remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- tunnels — Tunnels [unknown]: Tunnels remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- defaults — Defaults [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- safer_modes — Safer modes [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.
- enforcement — Enforcement [supported]: Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed. Sources: happy:nov08-team-03-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-team-03-1

### TEAM-04: Decision and activity history

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

Session transcripts retain provider-specific opaque data; compaction creates a visible message describing replaced content. No immutable audit retention guarantee was verified.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- actions — Actions [supported]: Session transcripts retain provider-specific opaque data; compaction creates a visible message describing replaced content. No immutable audit retention guarantee was verified. Sources: happy:nov08-team-04-1.
- approvals — Approvals [unknown]: Approvals remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- edits — Edits [unknown]: Edits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- discussion — Discussion [unknown]: Discussion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- decisions — Decisions [unknown]: Decisions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cross_user_persistence — Cross user persistence [unknown]: Cross user persistence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cross_session_persistence — Cross session persistence [supported]: Session transcripts retain provider-specific opaque data; compaction creates a visible message describing replaced content. No immutable audit retention guarantee was verified. Sources: happy:nov08-team-04-1.
- export — Export [unknown]: Export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- mutability — Mutability [unknown]: Mutability remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retention — Retention [unknown]: Retention remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- integrity — Integrity [unknown]: Integrity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-team-04-1

### TEAM-05: Review experience and guidance

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

The desktop interface has conversations, files, diffs and an attachable terminal; current docs describe changed files beside each conversation. Guided batch review was not established.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- pending_reviews — Pending reviews [unknown]: Pending reviews remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- change_understanding — Change understanding [supported]: The desktop interface has conversations, files, diffs and an attachable terminal; current docs describe changed files beside each conversation. Guided batch review was not established. Sources: happy:nov08-team-05-1.
- evidence_navigation — Evidence navigation [supported]: The desktop interface has conversations, files, diffs and an attachable terminal; current docs describe changed files beside each conversation. Guided batch review was not established. Sources: happy:nov08-team-05-1.
- comments — Comments [unknown]: Comments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- request_changes — Request changes [unknown]: Request changes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- shipping_guidance — Shipping guidance [unknown]: Shipping guidance remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- effort — Effort [unknown]: Effort remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- missed_evidence — Missed evidence [unknown]: Missed evidence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- keyboard — Keyboard [unknown]: Keyboard remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- narrow_screen — Narrow screen [unknown]: Narrow screen remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- context_switching — Context switching [unknown]: Context switching remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- roles — Roles [unknown]: Roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_context — Retained context [unknown]: Retained context remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-team-05-1

### TEAM-06: Colleague takeover and continuity

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

Named teammates operate on shared sessions and projects on the same team server. This is not a verified transfer preserving every permission and runtime detail after owner disconnect.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- ongoing_takeover — Ongoing takeover [unknown]: Ongoing takeover remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- same_task — Same task [supported]: Named teammates operate on shared sessions and projects on the same team server. This is not a verified transfer preserving every permission and runtime detail after owner disconnect. Sources: happy:nov08-team-06-1.
- session_history — Session history [supported]: Named teammates operate on shared sessions and projects on the same team server. This is not a verified transfer preserving every permission and runtime detail after owner disconnect. Sources: happy:nov08-team-06-1.
- decisions — Decisions [unknown]: Decisions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- artifacts — Artifacts [unknown]: Artifacts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- permissions — Permissions [unknown]: Permissions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- runtime_context — Runtime context [unknown]: Runtime context remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- owner_disconnect — Owner disconnect [unknown]: Owner disconnect remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ownership — Ownership [unknown]: Ownership remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- attribution — Attribution [supported]: Named teammates operate on shared sessions and projects on the same team server. This is not a verified transfer preserving every permission and runtime detail after owner disconnect. Sources: happy:nov08-team-06-1.
- context_loss — Context loss [unknown]: Context loss remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- harness_transfer — Harness transfer [unknown]: Harness transfer remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-team-06-1

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

Verification status: Sourced (sourced)
Support: partial

Happy Desktop shows files and diffs with conversations, and its documentation includes a recipe for a live, shared HTML artifact. No exact-revision cross-task gallery test was run.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- diffs — Diffs [supported]: The initial Desktop release shows files and diffs alongside agent conversations. Sources: happy:nov08-team-05-1.
- documents — Documents [supported]: The documentation includes a recipe for building a live, shared HTML artifact. Sources: happy:nov08-ship-01-1.
- screenshots — Screenshots [unknown]: Screenshots remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- recordings — Recordings [unknown]: Recordings remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- previews — Previews [unknown]: Previews remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- test_outputs — Test outputs [unknown]: Test outputs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- reviewer_outputs — Reviewer outputs [unknown]: Reviewer outputs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- gallery — Gallery [unknown]: Gallery remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_links — Task links [unknown]: Task links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- revision_links — Revision links [unknown]: Revision links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- persistence — Persistence [unknown]: Persistence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- child_findings — Child findings [unknown]: Child findings remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prompt_leakage — Prompt leakage [unknown]: Prompt leakage remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: happy:nov08-ship-01-1, happy:nov08-team-05-1

### SHIP-02: Verification and spec gates

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-03: Git and pull request workflow

Verification status: Sourced (sourced)
Support: partial

The pinned runtime and clients manage Git workspaces and file changes. They have no built-in PR creation or management path; users can ask a coding agent to use external shell or MCP tools.

Availability: unknown
Delivery: unknown
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Happy Agent v2026.11.4 (db813011c038b2288fbc1efd0e10ef2149c838d2), Desktop v0.0.103 (a369b7b0a86a344904a2e171a78e2b0daf0b4be8); targeted first-party pass 2026-11-13; no installed-product test; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- The scoped first-party source pass does not establish branches, worktrees, commits, comments, ci_response, rebase, conflicts, product_state. No hands-on scenario was run.

- branches — Branches [unknown]: Branches remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- worktrees — Worktrees [unknown]: Worktrees remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- commits — Commits [unknown]: Commits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- pull_requests — Pull requests [unsupported]: The inspected release has no built-in PR create/manage interface. External shell or MCP tools remain possible. Sources: happy:facet38-pr-boundary.
- comments — Comments [unknown]: Comments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ci_response — Ci response [unknown]: Ci response remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- rebase — Rebase [unknown]: Rebase remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- conflicts — Conflicts [unknown]: Conflicts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- product_state — Product state [unknown]: Product state remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

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

Sources: happy:facet38-pr-boundary

### 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 mobile app, original CLI and relay repository has the MIT license. Happy Desktop documentation also explicitly describes its app/runtime as MIT. Hosted and provider services remain separate.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- client_license — Client license [supported]: The mobile app, original CLI and relay repository has the MIT license. Happy Desktop documentation also explicitly describes its app/runtime as MIT. Hosted and provider services remain separate. Sources: happy:nov08-own-01-1.
- server_license — Server license [supported]: The mobile app, original CLI and relay repository has the MIT license. Happy Desktop documentation also explicitly describes its app/runtime as MIT. Hosted and provider services remain separate. Sources: happy:nov08-own-01-1.
- hosted_extensions — Hosted extensions [unknown]: Hosted extensions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- source_visibility — Source visibility [supported]: The mobile app, original CLI and relay repository has the MIT license. Happy Desktop documentation also explicitly describes its app/runtime as MIT. Hosted and provider services remain separate. Sources: happy:nov08-own-01-1.
- source_revision — Source revision [supported]: The mobile app, original CLI and relay repository has the MIT license. Happy Desktop documentation also explicitly describes its app/runtime as MIT. Hosted and provider services remain separate. Sources: happy:nov08-own-01-1.
- hosted_parity — Hosted parity [unknown]: Hosted parity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-own-01-1

### OWN-02: Hosting and exit

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

The core Happy Agent runs self-hosted on user machines or servers, with Desktop connecting remotely. Happy Social/WorkOS team sign-in and the mobile relay are distinct service dependencies.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- self_hosting — Self hosting [supported]: The core Happy Agent runs self-hosted on user machines or servers, with Desktop connecting remotely. Happy Social/WorkOS team sign-in and the mobile relay are distinct service dependencies. Sources: happy:nov08-own-02-1.
- vendor_dependencies — Vendor dependencies [supported]: The core Happy Agent runs self-hosted on user machines or servers, with Desktop connecting remotely. Happy Social/WorkOS team sign-in and the mobile relay are distinct service dependencies. Sources: happy:nov08-own-02-1.
- export — Export [unknown]: Export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- import — Import [unknown]: Import remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- formats — Formats [unknown]: Formats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cancellation — Cancellation [unknown]: Cancellation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- account_independence — Account independence [unknown]: Account independence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- history_portability — History portability [unknown]: History portability remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-own-02-1

### OWN-03: Data handling and telemetry

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

Happy apps send pseudonymous usage events to PostHog, excluding message content, prompts, code and file names, and offer a Settings opt-out that stops them; the desktop app has its own switch. Happy Agent itself sends no analytics.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- code_data — Code data [unknown]: Code data remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prompts — Prompts [unknown]: Prompts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- credentials — Credentials [unknown]: Credentials remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- logs — Logs [unknown]: Logs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- artifacts — Artifacts [unknown]: Artifacts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retention — Retention [unknown]: Retention remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deletion — Deletion [unknown]: Deletion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- training — Training [unknown]: Training remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- residency — Residency [unknown]: Residency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- subprocessors — Subprocessors [unknown]: Subprocessors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- telemetry_disclosure — Telemetry disclosure [supported]: Happy apps send product usage events to PostHog and offer a Settings opt-out that stops analytics events. Happy Agent itself sends no analytics. Provider/model work still follows provider policies. Sources: happy:nov08-own-03-1.
- telemetry_defaults — Telemetry defaults [supported]: Happy apps send product usage events to PostHog and offer a Settings opt-out that stops analytics events. Happy Agent itself sends no analytics. Provider/model work still follows provider policies. Sources: happy:nov08-own-03-1.
- telemetry_controls — Telemetry controls [supported]: Happy apps send product usage events to PostHog and offer a Settings opt-out that stops analytics events. Happy Agent itself sends no analytics. Provider/model work still follows provider policies. Sources: happy:nov08-own-03-1.
- consent_prompt — Consent prompt [unknown]: Consent prompt remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- provider_separation — Provider separation [unknown]: Provider separation: the privacy file describes Happy's own analytics and ElevenLabs voice handling but does not separate model-provider policies. Independent cross-check on 2026-11-08: the cited source does not establish this part. Missing results are not negative evidence.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-10.

Sources: happy:nov08-own-03-1

### OWN-04: Price and included usage

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

Happy is free and MIT licensed. Model use is paid through existing subscriptions and user compute. Phone voice has twenty free minutes per thirty days and an optional paid allowance; custom ElevenLabs use is separate.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- currency — Currency [unknown]: Currency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- interval — Interval [unknown]: Interval remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- seats — Seats [unknown]: Seats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- seat_minimum — Seat minimum [unknown]: Seat minimum remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- workspace_fees — Workspace fees [unknown]: Workspace fees remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- included_usage — Included usage [supported]: Happy is free and MIT licensed. Model use is paid through existing subscriptions and user compute. Phone voice has twenty free minutes per thirty days and an optional paid allowance; custom ElevenLabs use is separate. Sources: happy:nov08-own-04-1.
- credits — Credits [unknown]: Credits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- trial — Trial [unknown]: Trial remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- overages — Overages [unknown]: Overages remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- taxes — Taxes [unknown]: Taxes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- model_cost — Model cost [supported]: Happy is free and MIT licensed. Model use is paid through existing subscriptions and user compute. Phone voice has twenty free minutes per thirty days and an optional paid allowance; custom ElevenLabs use is separate. Sources: happy:nov08-own-04-1.
- compute_cost — Compute cost [supported]: Happy is free and MIT licensed. Model use is paid through existing subscriptions and user compute. Phone voice has twenty free minutes per thirty days and an optional paid allowance; custom ElevenLabs use is separate. Sources: happy:nov08-own-04-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-own-04-1

### 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

Happy Agent v0.4.108 adds GPT-6.1 Terra and stop-state persistence; Desktop v0.0.102 has opt-in beta Stem cells. Current release activity does not imply all experimental UI is enabled by default.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- release_stage — Release stage [supported]: Happy Agent v0.4.108 adds GPT-6.1 Terra and stop-state persistence; Desktop v0.0.102 has opt-in beta Stem cells. Current release activity does not imply all experimental UI is enabled by default. Sources: happy:nov08-own-06-1.
- access_restrictions — Access restrictions [unknown]: Access restrictions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- support — Support [unknown]: Support remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- response_commitments — Response commitments [unknown]: Response commitments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- release_activity — Release activity [supported]: Happy Agent v0.4.108 adds GPT-6.1 Terra and stop-state persistence; Desktop v0.0.102 has opt-in beta Stem cells. Current release activity does not imply all experimental UI is enabled by default. Sources: happy:nov08-own-06-1.
- status_history — Status history [unknown]: Status history remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deprecation — Deprecation [unknown]: Deprecation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- export_options — Export options [unknown]: Export options remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-own-06-1

### 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 desktop application and self-hosted runtime are free. Model subscriptions and host compute are separate costs; optional phone voice has its own allowance.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- ongoing_free — Ongoing free [supported]: The desktop application and self-hosted runtime are free. Model subscriptions and host compute are separate costs; optional phone voice has its own allowance. Sources: happy:nov08-own-08-1.
- trial — Trial [unknown]: Trial remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- credits_trial — Credits trial [unknown]: Credits trial remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- self_host_cost — Self host cost [supported]: The desktop application and self-hosted runtime are free. Model subscriptions and host compute are separate costs; optional phone voice has its own allowance. Sources: happy:nov08-own-08-1.
- paid_only — Paid only [unknown]: Paid only remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- early_access — Early access [unknown]: Early access remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- free_scenarios — Free scenarios [supported]: The desktop application and self-hosted runtime are free. Model subscriptions and host compute are separate costs; optional phone voice has its own allowance. Sources: happy:nov08-own-08-1.
- card_required — Card required [unknown]: Card required remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- usage_caps — Usage caps [unknown]: Usage caps remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- paid_evaluation — Paid evaluation [unknown]: Paid evaluation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-own-08-1

### OWN-09: Pricing transparency

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

The core ADE has no software subscription charge; coding-model subscriptions, host resources and optional voice are separately scoped. No standardized task-scenario total was invented.

Availability: generally-available
Delivery: native
Scope: surfaces=Happy Desktop with Happy Agent runtime; native mobile apps, original CLI and self-hosted team mode where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=local or user remote host; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- units — Units [supported]: The core ADE has no software subscription charge; coding-model subscriptions, host resources and optional voice are separately scoped. No standardized task-scenario total was invented. Sources: happy:nov08-own-09-1.
- included_limits — Included limits [supported]: The core ADE has no software subscription charge; coding-model subscriptions, host resources and optional voice are separately scoped. No standardized task-scenario total was invented. Sources: happy:nov08-own-09-1.
- overages — Overages [unknown]: Overages remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- compute_markup — Compute markup [unknown]: Compute markup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- model_markup — Model markup [unknown]: Model markup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- minimum_commitment — Minimum commitment [unknown]: Minimum commitment remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cancellation — Cancellation [unknown]: Cancellation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- sales_only_unknowns — Sales only unknowns [unknown]: Sales only unknowns remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- transparency_classification — Transparency classification [supported]: The core ADE has no software subscription charge; coding-model subscriptions, host resources and optional voice are separately scoped. No standardized task-scenario total was invented. Sources: happy:nov08-own-09-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: happy:nov08-own-09-1

## Sources

### happy:nov08-acc-01-1

Happy: How Happy fits together; Original Happy CLI. Happy provides Desktop for macOS, Windows and Linux; mobile iOS, Android and web; and its original happy CLI wrapping Claude Code or Codex. Desktop uses a separate Happy Agent runtime for multi-model sessions and teams.

- URL: https://github.com/slopus/happy/blob/df13fc0678ec4093b85fe97c0c48ec9422f5a7c2/README.md
- Locator: How Happy fits together; Original Happy CLI
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-acc-01-2

Happy: Mobile access. Paired phone apps continue the same encrypted sessions and allow users to read work and respond away from the desktop.

- URL: https://happy.engineering/mobile/
- Locator: Mobile access
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-acc-02-1

Happy: Supported providers; Switch models. Happy runs Claude, Codex and Grok on the user's existing Claude Code, Codex or Grok CLI sign-ins, Gemini through Antigravity, and OpenCode or other ACP agents on their own login (beta). Model or effort can change mid-session without discarding the transcript.

- URL: https://happy.engineering/models/
- Locator: Supported providers; Switch models
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-acc-02-2

Happy: Harnesses: Claude Code, Codex CLI, Antigravity, OpenCode, and ACP agents. Happy's own harness runs the loop by default; the claude_code harness runs Claude Code itself on a claude account and codex_cli does the same for Codex, while Antigravity, OpenCode and other ACP agents sign in themselves. Grok is not listed as a harness.

- URL: https://happy.engineering/recepies/harnesses/
- Locator: Harnesses
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:agy-release-1

Happy Antigravity support at v2026.11.4. Happy Agent v2026.11.4 runs the Antigravity whole-agent harness through antigravity-acp@1.2.0, a community ACP adapter driving the signed-in agy CLI.

- URL: https://github.com/slopus/happy-agent/blob/db813011c038b2288fbc1efd0e10ef2149c838d2/packages/happy-providers/sources/vendors/foreignAgents/antigravityAgent.ts#L30-L63
- Locator: packages/happy-providers/sources/vendors/foreignAgents/antigravityAgent.ts lines 30-63, v2026.11.4, commit db813011c038b2288fbc1efd0e10ef2149c838d2
- Evidence kind: source-inspected
- Source date: 2026-11-10
- Retrieved: 2026-11-10
- Commit: db813011c038b2288fbc1efd0e10ef2149c838d2
- Path: packages/happy-providers/sources/vendors/foreignAgents/antigravityAgent.ts

### happy:nov08-acc-03-1

Happy: Models and Subscriptions. Happy uses existing Claude Code, Codex and Grok CLI sign-ins, so no Happy plan or pasted key is needed for model access; Antigravity and ACP agents use their own login. Bedrock works with an API key or the AWS credential chain.

- URL: https://happy.engineering/models/
- Locator: Models and Subscriptions
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-acc-04-1

Happy: Add a project. Importing registers an existing folder without moving, copying or initializing Git. A project without Git uses a plain folder copy when a workspace is needed.

- URL: https://happy.engineering/workspaces/
- Locator: Add a project
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-acc-05-1

Happy: REST API. Happy Agent exposes a token-authenticated REST API for sessions, streaming events and control on user infrastructure. The original happy CLI is a separate product-owned terminal entry point.

- URL: https://happy.engineering/recepies/rest-api/
- Locator: REST API
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-acc-06-1

Happy: Skills and MCP. Skills are SKILL.md files and MCP servers are mcp.toml entries, shared by every model; an agent can write both. MCP tools need Auto or Full access and every Auto call is reviewed. MCP servers from Codex or Claude Code configuration are not imported.

- URL: https://happy.engineering/extending/
- Locator: Skills and MCP
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-02-2

Happy: What the OS sandbox enforces. The documented OS sandbox uses macOS Seatbelt or Linux namespaces and seccomp. Shell writes, network and host sockets are restricted; file tools can still read credential folders, and MCP servers run outside the sandbox. Docker-backed sessions nest that sandbox inside the container.

- URL: https://happy.engineering/permissions/
- Locator: What the OS sandbox enforces
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-plan-01-1

Happy: Chief of Staff. The built-in Chief of Staff handles setup and task creation through ordinary conversation, including projects, remote hosts and teams. Persistent standalone issue metadata is not established.

- URL: https://happy.engineering/chief-of-staff/
- Locator: Chief of Staff
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-plan-03-1

Happy: Subagents. Subagent trees are capped at depth three and at most five agents including finished children. Sessions have exact agent IDs for messaging and retained follow-up. This is session hierarchy, not verified issue dependency enforcement.

- URL: https://happy.engineering/agents/
- Locator: Subagents
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-plan-04-1

Happy: Add a project. AGENTS.md files in the project tree are read by each agent and reread when they change; global AGENTS.md applies across projects.

- URL: https://happy.engineering/workspaces/
- Locator: Add a project
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:facet38-task-schema

Happy task catalog schema at v2026.11.4. Task records have independent task, agent and workspace IDs, owner and creator fields, versioned active/archived state and timestamps. Creation accepts no opening text, allowing an idle draft before work starts.

- URL: https://github.com/slopus/happy-agent/blob/db813011c038b2288fbc1efd0e10ef2149c838d2/packages/happy-agent-modules/sources/tasks/Task.ts#L28-L151
- Locator: Task record schema and createTaskInputSchema, lines 28-151
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: db813011c038b2288fbc1efd0e10ef2149c838d2
- Path: packages/happy-agent-modules/sources/tasks/Task.ts

### happy:facet38-task-operations

Happy native task operations at v2026.11.4. The TasksModule creates distinct task and agent records, supports rename, join, reorder, archive and unarchive, and persists catalog state. The API and Desktop task creation surface expose the task catalog.

- URL: https://github.com/slopus/happy-agent/blob/db813011c038b2288fbc1efd0e10ef2149c838d2/packages/happy-agent-modules/sources/tasks/TasksModule.ts#L664-L725
- Locator: createWithResult and task archive/unarchive operations; corresponding TaskMigrations.ts table
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: db813011c038b2288fbc1efd0e10ef2149c838d2
- Path: packages/happy-agent-modules/sources/tasks/TasksModule.ts

### happy:nov08-recheck-01-1

Happy: Subagents; What Happy Desktop shows. Subagents run in the background by default and return completion to the parent. Desktop displays subagents and running tools; tree size is bounded.

- URL: https://happy.engineering/agents/
- Locator: Subagents; What Happy Desktop shows
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-recheck-02-1

Happy: How agents work in another workspace. Bots and their subtasks may create a full conversation in a new workspace, with the creator as coordinator. Only the creating session may archive that workspace.

- URL: https://happy.engineering/workspaces/
- Locator: How agents work in another workspace
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-recheck-03-1

Happy: Subagents; How agents message each other. Agents delegate bounded work, choose each child model and effort, receive background completion notices and send follow-ups to finished children with retained context. Exact IDs route messages across projects or machines.

- URL: https://happy.engineering/agents/
- Locator: Subagents; How agents message each other
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-recheck-04-1

Happy: Durable waits and scheduled messages. Primary sessions can schedule messages to known agent IDs, list or cancel them and survive intervening runtime restarts. Durable waits end early on new input. This establishes scheduled work, not an unrestricted external-event scheduler.

- URL: https://happy.engineering/agents/
- Locator: Durable waits and scheduled messages
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-recheck-05-1

Happy: Inbox and presence. Agent questions remain in the conversation and experimental Inbox; answering on one device closes the shared state. Away presence instructs agents to continue with notes instead of waiting indefinitely.

- URL: https://happy.engineering/agents/
- Locator: Inbox and presence
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-recheck-06-1

Happy: What Happy Desktop shows. Per-session UI shows phase, tools, background processes, subagents, waiting state, whole-tree token usage and changed files. Fleet navigation has not been measured.

- URL: https://happy.engineering/agents/
- Locator: What Happy Desktop shows
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-recheck-07-1

Happy: What you get. The built-in Chief of Staff configures accounts, imports projects, pairs phones, deploys remote agents and creates teams through conversation.

- URL: https://happy.engineering/welcome/
- Locator: What you get
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-01-1

Happy: Remote server. Happy Agent can run on an always-on user server while Desktop connects over Tailcat and phones connect through an encrypted relay. Closing the controlling laptop does not stop work on that reachable host. Users supply host compute.

- URL: https://happy.engineering/guides/remote-server/
- Locator: Remote server
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-02-1

Happy: How Happy creates a workspace. Parallel workspaces use Git worktrees on branches cut from the remote trunk. File sync and setup commands run per workspace; nongit projects use a plain copy.

- URL: https://happy.engineering/workspaces/
- Locator: How Happy creates a workspace
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:facet38-isolation-options

Happy execution configuration at v2026.11.4. The scoped runtime config and runner implementation provide host process execution and optional Docker image/container execution, with OS sandbox restrictions. No VM or microVM isolation backend is implemented in the inspected release. A user provisioning a host VM is separate.

- URL: https://github.com/slopus/happy-agent/blob/db813011c038b2288fbc1efd0e10ef2149c838d2/packages/happy-agent-modules/sources/config/impl/userConfigurationTemplate.ts#L261-L272
- Locator: Docker configuration lines 261-272; sources/runners and runtime inspection; search terms docker, virtual machine, microvm
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: db813011c038b2288fbc1efd0e10ef2149c838d2
- Path: packages/happy-agent-modules/sources/config/impl/userConfigurationTemplate.ts

### happy:nov08-run-03-1

Happy: Agents That Never Die. Conversations and child sessions persist across window closure and runtime restart; finished children accept follow-ups with their full context. This is a documentation claim, not a crash test.

- URL: https://happy.engineering/agents/
- Locator: Agents That Never Die
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-04-1

Happy: How Happy creates a workspace. New workspaces copy configured sync files and run setup_commands. They start with a cold build cache. A failed setup command logs a warning while checkout and file sync determine readiness.

- URL: https://happy.engineering/workspaces/
- Locator: How Happy creates a workspace
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-05-1

Happy: Use several accounts; Provider usage and quotas. Smart provider pools can rotate same-provider accounts after authentication or quota-exhaustion errors. Provider quotas are polled about every fifteen minutes and are observations rather than billing records.

- URL: https://happy.engineering/models/
- Locator: Use several accounts; Provider usage and quotas
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-06-1

Happy: What Happy Desktop shows. Session status includes active tools, background work, subagents, waiting state, tokens and changed files. Deliberate failure and approval consistency after reconnect remain untested.

- URL: https://happy.engineering/agents/
- Locator: What Happy Desktop shows
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-run-07-1

Happy: Provider usage and quotas. Provider quotas are polled about every fifteen minutes and shown in the app; they are observations, not billing records.

- URL: https://happy.engineering/models/
- Locator: Provider usage and quotas
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-team-01-1

Happy: Shared work. Team members see the same projects and sessions and can speak to the agent. Changes in speaker include the member name/email; per-member drafts and task ordering stay personal.

- URL: https://happy.engineering/multiplayer/
- Locator: Shared work
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-team-02-1

Happy: Owner; Sign-in; Leaving. Team mode verifies per-user WorkOS tokens. The owner alone renames the installation, toggles global skills or archives others tasks; members otherwise have equal access and can select Full access. A remove-member action is explicitly not built yet.

- URL: https://happy.engineering/multiplayer/
- Locator: Owner; Sign-in; Leaving
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:src4-enterprise-signin

Happy website source: Set up enterprise JWT sign-in. Recipe for a team-mode Happy Agent whose members sign in through the organization's own identity provider (Okta, Entra ID, Google Workspace, Keycloak or internal SSO) instead of Happy's WorkOS accounts; the daemon verifies JWTs from an organization-owned OAuth authorization server and needs an Agent release with enterprise JWT authentication.

- URL: https://github.com/slopus/slopus.github.io/blob/275790de18910e7a3ff82dab749eb0f4c7cdb427/content/desktop/recepies/enterprise-sign-in.mdx#L1-L15
- Locator: content/desktop/recepies/enterprise-sign-in.mdx lines 1-15, commit 275790d
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-10

### happy:src4-agent-teamjwt

Happy Agent TeamJwtConfig at release v2026.11.4. The released Happy Agent v2026.11.4 parses a [feature.team.jwt] machine configuration with an authorization URL and exactly one of a JWKS URL, public key or secret, used to verify organization-issued team tokens.

- URL: https://github.com/slopus/happy-agent/blob/db813011c038b2288fbc1efd0e10ef2149c838d2/packages/happy-agent-modules/sources/config/TeamJwtConfig.ts#L47-L140
- Locator: packages/happy-agent-modules/sources/config/TeamJwtConfig.ts lines 47-140, tag v2026.11.4 (commit db81301)
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-10
- Commit: db813011c038b2288fbc1efd0e10ef2149c838d2
- Path: packages/happy-agent-modules/sources/config/TeamJwtConfig.ts

### happy:src4-desktop-auth

Happy Desktop server sign-in discovery at release v0.0.103. The released desktop app v0.0.103 queries a Happy Agent server's v0/authentication endpoint to discover its sign-in methods.

- URL: https://github.com/slopus/happy-desktop/blob/a369b7b0a86a344904a2e171a78e2b0daf0b4be8/packages/happy-desktop-electron/sources/main/serverSessions.ts#L318
- Locator: packages/happy-desktop-electron/sources/main/serverSessions.ts line 318, tag v0.0.103 (commit a369b7b)
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-10
- Commit: a369b7b0a86a344904a2e171a78e2b0daf0b4be8
- Path: packages/happy-desktop-electron/sources/main/serverSessions.ts

### happy:nov08-team-03-1

Happy: Four permission modes; Auto review. Read only, Workspace write, Auto and Full access share a permission model. Auto sends boundary-crossing actions to a separate read-only reviewer and grants only that execution if allowed. Reads and workspace edits are not reviewed.

- URL: https://happy.engineering/permissions/
- Locator: Four permission modes; Auto review
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-team-04-1

Happy: Switch models; How compaction works. Session transcripts retain provider-specific opaque data; compaction creates a visible message describing replaced content. No immutable audit retention guarantee was verified.

- URL: https://happy.engineering/models/
- Locator: Switch models; How compaction works
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-team-05-1

Happy: Initial core release; Current interface. The desktop interface has conversations, files, diffs and an attachable terminal; current docs describe changed files beside each conversation. Guided batch review was not established.

- URL: https://happy.engineering/changelog/
- Locator: Initial core release; Current interface
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-team-06-1

Happy: Shared work. Named teammates operate on shared sessions and projects on the same team server. This is not a verified transfer preserving every permission and runtime detail after owner disconnect.

- URL: https://happy.engineering/multiplayer/
- Locator: Shared work
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-ship-01-1

Happy: Artifacts. The Chief of Staff documentation links a recipe for building a live, shared HTML artifact. No exact-revision cross-task gallery test was run.

- URL: https://happy.engineering/chief-of-staff/
- Locator: Artifacts
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:facet38-pr-boundary

Happy Git module and bounded PR integration inspection. The pinned runtime Git module and clients provide file changes, branches and workspaces, but no product-owned pull-request creation or management path was found. PRs can still be operated through an external shell command or MCP service; that is not a built-in Happy PR workflow.

- URL: https://github.com/slopus/happy-agent/blob/db813011c038b2288fbc1efd0e10ef2149c838d2/packages/happy-agent-modules/sources/git/GitModule.ts
- Locator: GitModule.ts and sibling sources/git, sources/api, sources/tasks; happy-desktop AppHappyAgentView.tsx at a369b7b; happy CLI/iOS/Android sources at df13fc0. Searches: pull request, pull_request, gh pr, pr create.
- Evidence kind: source-inspected
- Source date: Not stated
- Retrieved: 2026-11-13
- Commit: db813011c038b2288fbc1efd0e10ef2149c838d2
- Path: packages/happy-agent-modules/sources/git/GitModule.ts

### happy:nov08-own-01-1

Happy: MIT License. The mobile app, original CLI and relay repository has the MIT license. Happy Desktop documentation also explicitly describes its app/runtime as MIT. Hosted and provider services remain separate.

- URL: https://github.com/slopus/happy/blob/df13fc0678ec4093b85fe97c0c48ec9422f5a7c2/LICENSE
- Locator: MIT License
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-own-02-1

Happy: How a Happy team server works. The core Happy Agent runs self-hosted on user machines or servers, with Desktop connecting remotely. Happy Social/WorkOS team sign-in and the mobile relay are distinct service dependencies.

- URL: https://happy.engineering/multiplayer/
- Locator: How a Happy team server works
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-own-03-1

Happy: Analytics: PostHog. Happy apps send pseudonymous product usage events to PostHog, excluding message content, prompts, code and file names, and offer a Settings opt-out that stops them; the desktop app has its own switch. Happy Agent itself sends no analytics.

- URL: https://github.com/slopus/happy/blob/df13fc0678ec4093b85fe97c0c48ec9422f5a7c2/PRIVACY.md
- Locator: Analytics: PostHog
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-own-04-1

Happy: What does Happy cost?. Happy is free and MIT licensed. Model use is paid through existing subscriptions and user compute. Phone voice has twenty free minutes per thirty days and an optional paid allowance; custom ElevenLabs use is separate.

- URL: https://happy.engineering/welcome/
- Locator: What does Happy cost?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-own-06-1

Happy: October 26, 2026. Happy Agent v0.4.108 adds GPT-6.1 Terra and stop-state persistence; Desktop v0.0.102 has opt-in beta Stem cells. Current release activity does not imply all experimental UI is enabled by default.

- URL: https://happy.engineering/changelog/
- Locator: October 26, 2026
- Evidence kind: documented
- Source date: 2026-10-26
- Retrieved: 2026-11-08

### happy:nov08-own-08-1

Happy: What does Happy cost?. The desktop application and self-hosted runtime are free. Model subscriptions and host compute are separate costs; optional phone voice has its own allowance.

- URL: https://happy.engineering/welcome/
- Locator: What does Happy cost?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### happy:nov08-own-09-1

Happy: What does Happy cost?. The core ADE has no software subscription charge; coding-model subscriptions, host resources and optional voice are separately scoped. No standardized task-scenario total was invented.

- URL: https://happy.engineering/welcome/
- Locator: What does Happy cost?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08
