# Cate

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. The same evidence rules apply to Podium and its competitors, but they do not remove this conflict of interest.

Page: https://adecomparison.com/ade/cate/
Website: https://cate.cero-ai.com/
Research: covered

Method: https://adecomparison.com/method/

Rank by must-haves met, then preferences, then name. Read each finding's checked date. Findings stay published after their scheduled recheck. Checks over six months old may be outdated.

## cate:ACC-01

Finding: Desktop installers cover macOS (arm64/x64), Windows x64 and Linux x64. No web client or phone-browser client exists; the native iPhone app is the phone route. The product-owned cate CLI is the command interface. No editor extensions for external editors exist. Desktop sessions start/steer/review/resume agent work; OS-native notifications plus iOS push; paired devices continue work across machines.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Browser, phone-browser and editor-extension routes are absent by bounded inspection; remaining findings are as cited.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/electron-builder.yml
Locator: mac/win/linux target blocks
Finding: Desktop targets: macOS DMG+ZIP (x64+arm64), Windows NSIS+ZIP (x64), Linux AppImage+DEB+tar.gz (x64). No other desktop OS targets are configured.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/CHANGELOG.md
Locator: 2.1.0-beta.14 and iOS 0.1.2 (22) entries 2026-11-12; 0.4.0 entry
Finding: Beta.14 and iOS 0.1.2 (22) shipped 2026-11-12; near-daily beta cadence since 2.1.0-beta.1 (2026-10-17). Version 0.4.0 removed the bundled MCP registry and the AI-config/MCP-server subsystem.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/ios/README.md
Locator: Shell description; ios/Cate review-demo/review-pairing plans; SwiftUI views incl. ReviewPanelView, Worktrees
Finding: Native SwiftUI iPhone app running the shared client core headless in a WKWebView. Views cover agent chat, terminals, editors, browser panels, review panels and worktrees. App Store review rehearsal uses scripted demo/pairing plans on a physical iPhone.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/ios-app-store-audit.txt
Locator: Device support; SDK and packaging; Privacy policy access
Finding: Engineering readiness review 2026-11-03 (not a guarantee of Apple approval): iPhone-only device family, iOS 26.0 deployment target, production signing matching App Store Connect, in-app Privacy Policy and Support links. Store description frames iPhone support.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/notifications/contract.ts
Locator: contract/capability/events/settings/gating; client attach
Finding: Workspace notification contracts cover events, gating and per-setting control with one subscription per open workspace. Human permission prompts raise waitingForInput attention notifications; display is OS-native.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/
Locator: Hero; download buttons; footer nav (rendered page)
Finding: Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/kernel/api/contract.ts
Locator: defineCateApi/defineCliArea areas: agent, review, browser, terminal, editor, document
Finding: The product-owned cate CLI exposes agent, review, browser, terminal, editor and document areas to callers in a Cate terminal (including agents), gated by read/control areas. Network pairing and device keys are covered by the architecture transport rules.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:ACC-02

Finding: Seven provider CLIs are supported: Claude Code, Codex, Cursor, Grok, Kiro, OpenCode and Pi, launched as installed CLIs with native logins. No product-level model-provider catalog or custom harness adapters exist; mixed providers share one workspace through the cate CLI.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Product-level model-provider choice is not established; remaining findings are as cited.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

## cate:ACC-03

Finding: Work reuses existing coding-agent subscriptions through native CLI logins; Cate sells nothing and stores no provider credentials. No vendor credits, local-model route, multi-account switching or provider restriction list is established; no Cate account is needed for local or LAN pairing.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Credential handling is each CLI own; credit, switching and restriction facts are as cited.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

## cate:ACC-04

Finding: Install the app and a provider CLI, authenticate it, open a folder and send a message. SSH hosts and WSL distros onboard the same way with automatic runtime install. Git-less folders, prerequisite lists beyond the above, and any managed-cloud setup are not established; no managed cloud exists.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Git-backing variants beyond the cited flows are not established; remaining findings are as cited.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/
Locator: Hero; download buttons; footer nav (rendered page)
Finding: Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/main/updater/runtimeInstall.ts
Locator: Per-arch runtime tarballs for SSH/WSL targets
Finding: The workspace runtime ships as per-architecture tarballs staged with the app and installed onto SSH or WSL machines when a workspace opens there, so local and remote follow the same path.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:ACC-05

Finding: The cate CLI covers create/inspect/steer/stop/review across agent, review, browser, terminal, editor and document areas with read/control gating. No public HTTP API, SDK, MCP server or webhooks exist. CLI callers reach only the api capability over an OS-user socket; runtime/client compatibility stays at version 1.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Network caller auth and API stability policy beyond the cited facts are unstated.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/browser/contract/api.ts
Locator: browser command specs: tab list/open/close/switch
Finding: cate browser drives workspace browser panels: list tabs, open/switch/close tabs. localhost in a browser panel means the runtime machine, routed through the workspace connection.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/kernel/api/contract.ts
Locator: defineCateApi/defineCliArea areas: agent, review, browser, terminal, editor, document
Finding: The product-owned cate CLI exposes agent, review, browser, terminal, editor and document areas to callers in a Cate terminal (including agents), gated by read/control areas. Network pairing and device keys are covered by the architecture transport rules.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:ACC-06

Finding: No MCP client exists (subsystem removed in 0.4.0). Official Cate IDE extensions ship through a PR-built catalog; skills install per agent from a curated catalog; the cate CLI plus panel APIs are the agent-usable tools, product-managed with read/control gating and hook modes.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Extension install flow and skill-source review gates are not established; remaining findings are as cited.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/CHANGELOG.md
Locator: 2.1.0-beta.14 and iOS 0.1.2 (22) entries 2026-11-12; 0.4.0 entry
Finding: Beta.14 and iOS 0.1.2 (22) shipped 2026-11-12; near-daily beta cadence since 2.1.0-beta.1 (2026-10-17). Version 0.4.0 removed the bundled MCP registry and the AI-config/MCP-server subsystem.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/skills/runtime/installer.ts
Locator: writeSkill/uninstall; registry/skills-index.json curated catalog; Agent Skills SKILL.md standard
Finding: Skills install from a curated catalog into per-agent target dirs following the open Agent Skills SKILL.md folder standard; installs are recorded per workspace and uninstall cleanly. Relation context reaches turns via the per-agent promptContextHook (additional-context, plain-text or endpoint).
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate-extensions
Locator: Repository description; extensions/ directory
Finding: Official Cate IDE extensions: new extensions land by PR; CI builds artifacts and publishes the catalog to GitHub Pages. Pushed 2026-10-11. No license file is published in that repository.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/kernel/api/contract.ts
Locator: defineCateApi/defineCliArea areas: agent, review, browser, terminal, editor, document
Finding: The product-owned cate CLI exposes agent, review, browser, terminal, editor and document areas to callers in a Cate terminal (including agents), gated by read/control areas. Network pairing and device keys are covered by the architecture transport rules.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:ACC-07

Finding: Desktop is Electron with a React shell; mobile is a native SwiftUI app with a headless shared core. No hybrid framework is used. Evidence is official architecture plus pinned source and build targets.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-05-11
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

No hybrid implementation exists by bounded inspection.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/electron-builder.yml
Locator: mac/win/linux target blocks
Finding: Desktop targets: macOS DMG+ZIP (x64+arm64), Windows NSIS+ZIP (x64), Linux AppImage+DEB+tar.gz (x64). No other desktop OS targets are configured.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/ios/README.md
Locator: Shell description; ios/Cate review-demo/review-pairing plans; SwiftUI views incl. ReviewPanelView, Worktrees
Finding: Native SwiftUI iPhone app running the shared client core headless in a WKWebView. Views cover agent chat, terminals, editors, browser panels, review panels and worktrees. App Store review rehearsal uses scripted demo/pairing plans on a physical iPhone.
Retrieved: 2026-11-12

## cate:PLAN-01

Finding: Work starts from user prompts (with file/photo attachments) or by opening a folder; agents in terminals take the prompts. No external tracker import, chat/Git triggers, sync or round-trips exist; the workspace document is the local authority and panel relations are not issues.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Tracker-shaped questions are answered negatively by bounded inspection; prompts are the only intake.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/git.ts
Locator: gh pr create --fill; gh pr view/list/checkout; worktree-for-PR; merge
Finding: Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:PLAN-02

Finding: Review panels hold a spec with a git/recorded-edits comparison, linked files and notes, and sessions persist across restarts with resume. Acceptance criteria, plan editors, revision history and mid-run amendment are not established.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Only the review-spec findings are established; remaining plan questions are gaps.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

## cate:PLAN-03

Finding: Nested canvases and dock trees give visual grouping without epic semantics. No epics, blockers, readiness, enforcement, state propagation, task-to-epic growth or workflow constraints exist; relations carry context, not dependencies.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Hierarchy is visual only; all coordination semantics are absent by bounded inspection.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:PLAN-04

Finding: Relation context and per-agent skill dirs feed turns; project docs are plain files; agent CLIs persist their own sessions with resume. Provenance, citation, correction/deletion and staleness controls are not established; a joining device inherits the full live context.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Memory is CLI-owned; context governance questions are gaps.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/skills/runtime/installer.ts
Locator: writeSkill/uninstall; registry/skills-index.json curated catalog; Agent Skills SKILL.md standard
Finding: Skills install from a curated catalog into per-agent target dirs following the open Agent Skills SKILL.md folder standard; installs are recorded per workspace and uninstall cleanly. Relation context reaches turns via the per-agent promptContextHook (additional-context, plain-text or endpoint).
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

## cate:PLAN-05

Finding: Ripgrep search, file/photo attachments, in-app browser panels and editor conflict detection exist. Indexing, external knowledge, citations, API retrieval and review-time enforcement are not established; review checks stay optional.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Retrieval depth questions are gaps; enforcement is absent.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

## cate:PLAN-06

Finding: No native issue management exists: no create/edit/discuss/prioritize/label/assign/search/filter/archive/reopen, no idea parking, no dispatch, no task/session separation, no durable issue states. Panels and relations are not issues and no external tracker is required for any issue workflow.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.



Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:PLAN-07

Finding: Agents operate on panels, files, reviews and conversations through the cate CLI, but no shared issue records exist, so no agent-native issue operations (read/create/update, claim, assign, state changes, dependencies, children, results, attribution, permissions, conflicts) apply.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.



Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:PLAN-08

Finding: No living product specifications exist: requirements do not persist across tasks, no human/agent editing with revisions or approvals, no requirement links, retrieval, drift detection or review integration. Review specs are single-review artifacts.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.



Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:COORD-01

Finding: Independent agent sessions run concurrently in separate terminals, one per worktree branch, with running/waiting/finished states visible on the canvas. No concurrency quotas are documented and concurrent execution was not witnessed in a fixture.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Quotas and witnessed concurrency are not established.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/usage/types.ts
Locator: Usage record pricing; subscription-limit types; README Usage button
Finding: Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

## cate:COORD-02

Finding: Work is not assigned: every paired client has full access and there are no claims, routing or ownership enforcement. Per-panel prompt queues hold pending and failed prompts visibly for all clients.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Assignment semantics are limited to panel placement and shared queues.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:COORD-03

Finding: Any agent in a terminal can start, message, read and wait on other agent sessions through the shipped cate CLI, with live progress and retained results. Effort control stays CLI-side and cross-harness use is possible but only through that CLI.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Roles are informal and effort control is CLI-side; remaining findings are as cited.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/kernel/api/contract.ts
Locator: defineCateApi/defineCliArea areas: agent, review, browser, terminal, editor, document
Finding: The product-owned cate CLI exposes agent, review, browser, terminal, editor and document areas to callers in a Cate terminal (including agents), gated by read/control areas. Network pairing and device keys are covered by the architecture transport rules.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

## cate:COORD-04

Finding: No unattended triggers exist: no schedules, event triggers, recurring tasks, completion conditions, scheduler location, overlap handling or retries. Polling-style automation would be a manual integration, of which none is documented.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.



Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:COORD-05

Finding: Turns stop via per-CLI interrupt keys, sessions resume by id, prompts steer running work, permission waits raise attention notifications, and history is retained. Pause, escalation and a separate chat surface do not exist.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Pause and escalation are absent by bounded inspection.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/notifications/contract.ts
Locator: contract/capability/events/settings/gating; client attach
Finding: Workspace notification contracts cover events, gating and per-setting control with one subscription per open workspace. Human permission prompts raise waitingForInput attention notifications; display is OS-native.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:COORD-06

Finding: The canvas shows parallel streams on colored worktree territories with running/waiting attention states, but there is no epic model, dependency view, history, workload view or fixture-witnessed navigation.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Fleet visibility is canvas-only; navigation is unwitnessed.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/usage/types.ts
Locator: Usage record pricing; subscription-limit types; README Usage button
Finding: Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/notifications/contract.ts
Locator: contract/capability/events/settings/gating; client attach
Finding: Workspace notification contracts cover events, gating and per-setting control with one subscription per open workspace. Human permission prompts raise waitingForInput attention notifications; display is OS-native.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:COORD-07

Finding: Any prompt can start work with no mandatory workflow; canvases grow with worktrees while keeping panel relationships. Agent choice and hook modes are configurable per run, discovery runs through Cmd+K and pairing is a QR scan, but presets, natural-language configuration and model/effort control do not exist.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Configuration depth is CLI-side; presets and NL configuration are absent.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:RUN-01

Finding: Work executes locally or on user-owned SSH/WSL machines whose runtimes Cate installs; self-hosted always-available workspaces are supported. No vendor cloud execution exists. The runtime survives client disconnects per workspace Availability and any paired device continues the same live workspace.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Resource, region facts are gaps; managed cloud and hybrid are absent.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/LICENSE
Locator: License grant
Finding: Root MIT license grant covering the application, including desktop, runtime and iOS sources in the same repository.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/
Locator: Hero; download buttons; footer nav (rendered page)
Finding: Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/main/updater/runtimeInstall.ts
Locator: Per-arch runtime tarballs for SSH/WSL targets
Finding: The workspace runtime ships as per-architecture tarballs staged with the app and installed onto SSH or WSL machines when a workspace opens there, so local and remote follow the same path.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:RUN-02

Finding: Workspaces are plain folder checkouts with git worktree isolation per branch; device links are Noise-encrypted with pinned keys. No container, VM or OS-sandbox workload isolation exists, and process boundaries, secret management and hostile-code containment are not established as product guarantees.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Isolation is worktree-level; stronger boundaries are absent by bounded inspection.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:RUN-03

Finding: Disconnects, restarts and expiry follow the Availability choice with transcript reload and session resume. Crash specifics, context loss, duplicate actions and manual repair are not established; multi-day work relies on Stay-available runtimes.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Failure edge-cases beyond the cited restore paths are gaps.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

## cate:RUN-04

Finding: Only the remote runtime install is product-automated; CLIs install through vendor flows and project dependencies are agent work in terminals. Caches, snapshots, services, ports, collision handling and automatic repair are not established as product behavior.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Environment reliability beyond remote runtime install is agent-side or unstated.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/main/updater/runtimeInstall.ts
Locator: Per-arch runtime tarballs for SSH/WSL targets
Finding: The workspace runtime ships as per-architecture tarballs staged with the app and installed onto SSH or WSL machines when a workspace opens there, so local and remote follow the same path.
Retrieved: 2026-11-12

## cate:RUN-05

Finding: Wait timeouts (5-60s) and CLI timeouts bound product calls; token/subscription limits are displayed, not enforced; spend limits do not exist. Retry and provider-failure specifics beyond stale-guard rails are not established.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Limit coverage is display plus timeouts; the rest are gaps.

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/git.ts
Locator: gh pr create --fill; gh pr view/list/checkout; worktree-for-PR; merge
Finding: Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/usage/types.ts
Locator: Usage record pricing; subscription-limit types; README Usage button
Finding: Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

## cate:RUN-06

Finding: Terminals, conversations, failure text, per-agent usage stats and reconnect-consistent shared state exist. Usage export, project stats, performance figures and responsiveness claims are not established.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Statistics are usage-centric; export and performance facts are gaps.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/usage/types.ts
Locator: Usage record pricing; subscription-limit types; README Usage button
Finding: Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

## cate:RUN-07

Finding: Workspace token usage and API-equivalent cost by time, agent and model are visible, with subscription-limit display; billed-charge reconciliation, per-task/per-child accounting, compute costs, alerts, export and drill-down are not established.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Cost visibility is aggregate estimates; accounting depth is absent or unstated.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/usage/types.ts
Locator: Usage record pricing; subscription-limit types; README Usage button
Finding: Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/
Locator: Hero; download buttons; footer nav (rendered page)
Finding: Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:RUN-08

Finding: No compute-aware scheduling exists: no concurrency limits, queues, CPU/RAM controls, backpressure, host awareness or check dedup. Turn cancellation via interrupt keys is the only bounded control.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Only cancellation is established; the rest are absent or unstated.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:TEAM-01

Finding: Collaborators share one live workspace with presence and simultaneous prompting through shared queues; no in-product discussion or comments exist. No roles, ordering, conflict or plan rules govern co-steering; the original owner need not stay online.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Simultaneous prompting is shared-queue only; governance questions are gaps or absent.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:TEAM-02

Finding: No organization, project or task roles and no SSO or provisioning exist. Membership is device pairing with immediate revocation; unauthorized devices cannot connect thanks to pinned keys.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Membership is pairing-only; roles and SSO are absent.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:TEAM-03

Finding: Cate enforces no command, tool, network or secret approvals itself: agent CLIs own their permission policies. Delivery is gated by review completion (assigned agent only) and device access ends on removal; defaults are full access with hook-mode and CLI-area controls.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Approvals are CLI-owned; product enforcement covers CLI areas, reviews and pairing.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:TEAM-04

Finding: Conversations, permission states, connected edits and review findings persist across users, sessions and restarts, but unattributed: no identities exist. No discussion threads, export or integrity model exist; retention beyond in-memory registrations is workspace files.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

History is retained but unattributed; export and integrity are gaps or absent.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:TEAM-05

Finding: Review panels show diffs, files, notes and evidence with comments, request-changes and shipping via merge/PR flows; keyboard shortcuts are rebindable and the iPhone app (with a review view) serves narrow screens. Pending-review discovery, effort and missed-evidence facts are not established.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Discovery and effort facts are gaps; guidance is flow-level.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/ios/README.md
Locator: Shell description; ios/Cate review-demo/review-pairing plans; SwiftUI views incl. ReviewPanelView, Worktrees
Finding: Native SwiftUI iPhone app running the shared client core headless in a WKWebView. Views cover agent chat, terminals, editors, browser panels, review panels and worktrees. App Store review rehearsal uses scripted demo/pairing plans on a physical iPhone.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/git.ts
Locator: gh pr create --fill; gh pr view/list/checkout; worktree-for-PR; merge
Finding: Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

## cate:TEAM-06

Finding: A second paired person takes over the same live task with full session history, decisions, artifacts and runtime context, including after the first person disconnects; ownership and attribution do not exist as concepts. Harness transfer means prompting a different CLI in the same workspace.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Takeover is total but identity-free; migration is manual.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/runtime/daemon/AvailabilitySettings.tsx
Locator: finish/stay-available/stop choices; 5-minute stop; SSH restart note
Finding: Per-workspace Availability: Finish running work (agents keep going until done), Stay available, or Stop with Cate (everything stops 5 minutes after the last window closes). A paired device can reconnect while running but cannot start a stopped workspace; reopening over SSH starts it again.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:SHIP-01

Finding: Diffs, file previews, browser panels, test output in terminals and reviewer findings persist per workspace and across restarts, with revision-linked review comparisons. No artifact gallery, recordings, task links or build links exist; prompt-leakage handling is unstated.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Artifacts are panel-local; gallery and link depth are absent or unstated.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/browser/contract/api.ts
Locator: browser command specs: tab list/open/close/switch
Finding: cate browser drives workspace browser panels: list tabs, open/switch/close tabs. localhost in a browser panel means the runtime machine, routed through the workspace connection.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/git.ts
Locator: gh pr create --fill; gh pr view/list/checkout; worktree-for-PR; merge
Finding: Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:SHIP-02

Finding: No tests, lint, type, CI, spec or required checks gate delivery; the optional agent review with request-changes is the only verification flow, and nothing blocks merges on failure. Enforcement policy beyond CLI areas does not exist.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Verification is an optional flow; gates do not exist.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/agent-activity.md
Locator: Per-CLI approval evidence table; Codex approval-mode label
Finding: Per-CLI table maps hook/notification evidence to running vs waitingForInput for all seven CLIs. Settings shows a read-only Codex approvals label; there are no approval overrides and Cate never modifies a CLI permission policy.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:SHIP-03

Finding: Branches, worktrees, PR creation/listing/context and merge-back flows are product-owned via the host gh login; commits, comments and rebases stay agent/terminal-side. CI response surfacing and product-held PR state do not exist.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Git depth is worktree/PR-shaped; commit and CI depth are terminal-side or absent.

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/api.ts
Locator: agentApi: start/types/list/read/wait/send; agentCliArea read/control; AGENT_WAIT_MIN/MAX_SECONDS
Finding: Product-owned cate CLI for agents: agent start (prompt max 50000 chars, agent/worktree/new-worktree/canvas placement), types, list, read, wait (5-60s), send (queued prompts with ids). Read vs control permission areas gate observation vs steering. Callable in a Cate terminal, i.e. by the agents running there.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/connected-editors.md
Locator: Sharing rules; flush-before-submit; conflict handling
Finding: Editors reachable through a terminal panel outgoing relation share a normal working file with the agent; autosave after 300ms; submitting a prompt flushes connected editors and a conflict or failed save blocks submission. Explicitly does not execute relations, send tasks automatically or coordinate agent workflows.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/git.ts
Locator: gh pr create --fill; gh pr view/list/checkout; worktree-for-PR; merge
Finding: Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:SHIP-04

Finding: Merges run through product worktree flows and PR creation, but approval, release and deployment do not exist as product capabilities; exact-revision discipline and authority enforcement are absent.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Shipping authority is the user; product gates do not exist.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:SHIP-05

Finding: Worktree-PR links, delivery states and retained conversations/notes exist; commit, build and deployment links, rollback, revert and stale-approval invalidation do not.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Delivery traceability is naming- and state-level only.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/contract/worktrees.ts
Locator: Branch-name sanitizer; pr-<n>-<head> folder names; checkout inheritance
Finding: Free-text work descriptions become branch names; PR checkouts use pr-<n>-<head> folders. A new terminal or agent run inherits its caller checkout or a named worktree. Typing what you work on creates the worktree and branch.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/presence.ts
Locator: Hook-anchored pid registry; falling-edge finished detection
Finding: Presence derives from authenticated agent-hook posts anchored to process-table pids; the falling edge resolves finished and clears the resume stamp. Combined with shared live workspaces, every connected client sees whose agents and devices are present with full shared control.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/relations/contract/graph.ts
Locator: RelationRole: execution/produces/targetOptions; Next/Always/Off setting; panelRelationsEnabled kill-switch
Finding: Relations link panels with context/use/verify intents and produce changes, findings or notes; the relation setting is Next/Always/Off with a workspace kill-switch. Relations carry no states, assignees, priorities or due dates and are not an issue tracker.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:SHIP-06

Finding: No batch review queue, summaries, grouping, filters, dependency queues or check dedup exist; request-changes and per-review findings with linked artifacts carry high-volume work instead, without stale-approval rules.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Batch review is per-panel, not queue-driven.

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/contract/api.ts
Locator: reviewApi: inspect/complete/note.add/note.resolve; sticky target
Finding: cate review inspect prints comparison/files/notes; complete marks review done; note.add/note.resolve record findings on diff lines with severity. Reviews target an explicit or sticky panel.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/git.ts
Locator: gh pr create --fill; gh pr view/list/checkout; worktree-for-PR; merge
Finding: Runs host gh: pr create --fill --head for the worktree branch, pr view/list for status, pr checkout into a new worktree, plus worktree create/merge/prune. Operations time out (60-120s) and surface errors in product UI.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/client/flows.ts
Locator: mergeWorktree; prune merged branches; switch panel checkout
Finding: Product flows merge a worktree branch into its base with result/error reporting, delete only already-merged branches, warn about unpublished commits, and switch a panel to another checkout.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/panels/review/session.ts
Locator: reviewWithAgent; requestChanges; reviewerExited; completeAgentReview
Finding: Review panels compare git state or recorded edits: a read-only agent reviewer can be started over the comparison; open findings can be sent back to the source agent or a new one; a reviewer whose terminal exits without cate review complete counts as failed; only the assigned review agent may complete. Findings carry file/line/side/severity and resolve by id.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:OWN-01

Finding: The whole application repository is MIT-licensed public source at the pinned tag; the hosted Cate Connect service is a separate closed component whose parity is not established, and the extensions repository publishes no license.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-05-11
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Extensions licensing and hosted parity are not established.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate
Locator: Header: owner, description, stars, license, branch, activity
Finding: Owner 0-AI-UG; description An infinite zoomable canvas for coding; homepage cate.cero-ai.com; 2235 stars observed 2026-11-12; MIT license; default branch main; pushed 2026-11-12; not archived or disabled. Task URL github.com/eneskirca/cate returns HTTP 404; the live repository is 0-AI-UG/cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/LICENSE
Locator: License grant
Finding: Root MIT license grant covering the application, including desktop, runtime and iOS sources in the same repository.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate-extensions
Locator: Repository description; extensions/ directory
Finding: Official Cate IDE extensions: new extensions land by PR; CI builds artifacts and publishes the catalog to GitHub Pages. Pushed 2026-10-11. No license file is published in that repository.
Retrieved: 2026-11-12

## cate:OWN-02

Finding: Self-hosting is the default: MIT software runs on user machines with no vendor account, LAN pairing and on-disk workspace state. GitHub (updates), provider CLIs and the optional Connect relay are the vendor dependencies; no product export/import format exists beyond plain files.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-05-11
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Portability is file-level, not format-level.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/registry.ts
Locator: AgentId union; AGENT_DEFS table: command, resume argv, sessionStore, promptArgs, interruptKeys
Finding: Exactly seven supported agent CLIs, total-record compile-checked: claude-code (claude), codex, cursor (cursor-agent), grok, kiro (kiro-cli), opencode, pi. Each declares launch command, resume argv, CLI session-store path, prompt args and interrupt keys. No gemini-cli, aider, antigravity or custom-adapter entry exists in this closed table.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/LICENSE
Locator: License grant
Finding: Root MIT license grant covering the application, including desktop, runtime and iOS sources in the same repository.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/main/updater/runtimeInstall.ts
Locator: Per-arch runtime tarballs for SSH/WSL targets
Finding: The workspace runtime ships as per-architecture tarballs staged with the app and installed onto SSH or WSL machines when a workspace opens there, so local and remote follow the same path.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:OWN-03

Finding: Local-first: files and sessions stay on the runtime machine, telemetry and crash reports are always-on and undisablable, and agent traffic goes to user-configured providers under their terms. Retention, residency and training facts are partly unstated.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-03-12
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Telemetry is undisablable; retention detail, residency and training are gaps.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/ios-app-store-audit.txt
Locator: Device support; SDK and packaging; Privacy policy access
Finding: Engineering readiness review 2026-11-03 (not a guarantee of Apple approval): iPhone-only device family, iOS 26.0 deployment target, production signing matching App Store Connect, in-app Privacy Policy and Support links. Store description frames iPhone support.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/main/analytics/analytics.ts
Locator: ANALYTICS_ENDPOINT; packaged-builds gating; CommonContext
Finding: Anonymous telemetry posts to analytics.cero-ai.com; only packaged builds send; no file paths, project names, workspace contents, hostnames or account data. Payload carries a random install id plus app version/platform/arch/locale.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/main/sentry.ts
Locator: initSentry: packaged gating; sendDefaultPii false; scrubbing
Finding: Sentry crash reporting is always on in packaged builds (dev only with SENTRY_DSN). sendDefaultPii is false; home paths are scrubbed and navigation breadcrumbs keep only the origin.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/shells/desktop/ui/app/dialogs/WelcomeDialog.tsx
Locator: File header; telemetry notice block; PRIVACY_URL
Finding: First-run welcome shows a privacy notice stating Cate collects usage data and crash reports, informational only: there is no choice, just the privacy-policy link. Shown once per TELEMETRY_NOTICE_VERSION.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/workspace/repository/runtime/github.ts
Locator: gh auth status; pull-request listing and PR context
Finding: GitHub works through the host gh login: connection state, the account pull-request and review-request listing, and per-PR context (head/base). Signed-out state directs the user to sign in to GitHub.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/runtime/setup/adapters.ts
Locator: AGENT_SETUP_ADAPTERS for all seven CLIs; allowlisted identity fields
Finding: Per-agent adapters install each CLI (vendor install scripts/npm) and drive its native login (device auth, CLI auth login, Pi /login extension). Only allowlisted public identity fields leave the CLI; Cate stores no provider credentials of its own.
Retrieved: 2026-11-12

## cate:OWN-04

Finding: Cate is MIT open source and free to download, with no paid plan found; it runs agents on the user own existing agent subscriptions and sells no tokens. No priced dimensions (currency, seats, overages, taxes) are stated.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-01-11
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Priced dimensions are absent because no paid plan exists in the checked sources; no purchase or billing test was run.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/LICENSE
Locator: License grant
Finding: Root MIT license grant covering the application, including desktop, runtime and iOS sources in the same repository.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/privacy
Locator: Desktop crash reporting and usage analytics; Cate Connect; Controller; Automatic updates
Finding: Controller: 0-AI UG (haftungsbeschraenkt), Stuttgart. Desktop telemetry and crash reporting are always on from 1.3.1 and cannot be disabled; usage events cover launches/installs/updates/feature use with a random install id and exclude workspace contents, paths and AI messages. Cate Connect relays E2E-encrypted traffic it cannot read; registrations live in memory and vanish on disconnect; removing a device revokes access. Agent requests use the user own account or API key under provider terms. Packaged builds check GitHub for updates.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/
Locator: Hero; download buttons; footer nav (rendered page)
Finding: Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12

## cate:OWN-06

Finding: Desktop releases ship as versioned betas (2.1.0-beta.14 on 2026-11-12) with near-daily cadence; iOS builds are versioned while App Store review is pending. Support channels, response commitments, status history and deprecation/export options are not established.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-01-11
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Support and status facts are gaps; deprecation absence is not a finding.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/CHANGELOG.md
Locator: 2.1.0-beta.14 and iOS 0.1.2 (22) entries 2026-11-12; 0.4.0 entry
Finding: Beta.14 and iOS 0.1.2 (22) shipped 2026-11-12; near-daily beta cadence since 2.1.0-beta.1 (2026-10-17). Version 0.4.0 removed the bundled MCP registry and the AI-config/MCP-server subsystem.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/ios-app-store-audit.txt
Locator: Device support; SDK and packaging; Privacy policy access
Finding: Engineering readiness review 2026-11-03 (not a guarantee of Apple approval): iPhone-only device family, iOS 26.0 deployment target, production signing matching App Store Connect, in-app Privacy Policy and Support links. Store description frames iPhone support.
Retrieved: 2026-11-12

## cate:OWN-08

Finding: The MIT desktop download is a free, ongoing tier for macOS, Windows and Linux with no paid plan, card or evaluation purchase; agent spend stays provider-side. Trial, caps and paid-evaluation questions do not apply to a free product and are answered negatively; iOS ships beta builds pending store review.

Verification: agent-cross-checked
Checked: 2026-11-12
Scheduled recheck: 2027-01-11
Plan: Not specified
Surface: Cate desktop app (macOS, Windows, Linux); Cate Mobile for iPhone; Cate workspace runtime daemon (local, SSH, WSL)
Version: Tag v2.1.0-beta.14 (commit 985917b3fc7d2fbba80035452eae041ce1a7d469); first-party source pass 2026-11-12. Desktop is production Electron; iOS app 0.1.2 (build 22); local and remote runtimes share one daemon build.

Provider-side subscription limits still apply to agent work. No purchase test was run.

Source: https://github.com/0-AI-UG/cate/blob/HEAD/README.md
Locator: Install table; What is inside; Shared workspaces and remote access
Finding: Infinite-canvas IDE for parallel coding agents. Install: macOS DMG/ZIP arm64+x64, Windows NSIS/ZIP x64, Linux AppImage/DEB/tar.gz x64, plus Homebrew cask. Features: shared live workspaces, agent-aware terminals with running/waiting/finished states, sessions survive restarts with resume, shared prompt queues, usage overview by time/agent/model plus Claude/Codex subscription limits, git worktrees with colored canvas territories, panels on canvas or dock, multi-repo git with side-by-side diffs, ripgrep search, Cmd+K. Share pairs devices by QR/code over LAN or Cate Connect with end-to-end encryption; Availability choices: finish running work, stay available, stop with Cate.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/architecture.md
Locator: Sections 1-3, 7.6-7.7, 9.7, 10.3, 12, 15; decisions D1-D10
Finding: The runtime is the application: one daemon per workspace; clients (desktop Electron+React shell, iPhone SwiftUI shell) render runtime state. Transports: local socket, machine (SSH/WSL command), network (LAN or Cate Connect). Cate Connect passes connection setup and runs a TURN relay; it never sees workspace plaintext. Agent means one provider CLI identity. D3: every client is the same to the runtime; no roles, no per-client permissions. D4: Noise handshake with pinned keys, only known devices; local transport is OS-user protected with a caller token reaching only the api capability. iOS push goes through an APNs target with a notification service extension.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/releases/tag/v2.1.0-beta.14
Locator: Release body: Fixed/Changed sections
Finding: Pinned release 2026-11-12: native agent conversation tracking fixes across restarts/switches; iPhone workspace controls; mobile chat state sync; all seven CLIs exercise the same native reset and saved-conversation switch contract. Compatibility version remains 1.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/LICENSE
Locator: License grant
Finding: Root MIT license grant covering the application, including desktop, runtime and iOS sources in the same repository.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/HEAD/docs/ios-app-store-audit.txt
Locator: Device support; SDK and packaging; Privacy policy access
Finding: Engineering readiness review 2026-11-03 (not a guarantee of Apple approval): iPhone-only device family, iOS 26.0 deployment target, production signing matching App Store Connect, in-app Privacy Policy and Support links. Store description frames iPhone support.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/blob/v2.1.0-beta.14/src/services/agents/contract/usage/types.ts
Locator: Usage record pricing; subscription-limit types; README Usage button
Finding: Usage is recorded per agent/model and priced per day/hour from a custom override, a CLI-recorded cost or LiteLLM rates; the model also reads CLI-known subscription limits. The sidebar Usage button shows workspace token usage and API-equivalent cost by time, agent and model, plus Claude Code and Codex subscription limits. Display only; no spend enforcement.
Retrieved: 2026-11-12

Source: https://cate.cero-ai.com/
Locator: Hero; download buttons; footer nav (rendered page)
Finding: Hero: terminals, editors and browsers on one infinite canvas; downloads for macOS, Windows and Linux (v2.0.5 at fetch time); GitHub star count shown. Footer nav is Blog/Privacy/Impressum/GitHub; no pricing, plans, billing or Cloud-hosted-execution offer appears anywhere on the rendered page.
Retrieved: 2026-11-12

Source: https://github.com/0-AI-UG/cate/tree/v2.1.0-beta.14/src
Locator: Grep across src/**, docs/**, ios/** at the pinned commit
Finding: Bounded search at the pinned commit found no implementation for: scheduled/recurring runs (cron, node-schedule, recurrence terms; only timer/debounce/polling hits); webhooks (only a GraphQL language-mode label and the GitHub API client); SSO/SAML/OIDC/SCIM; container/VM isolation for workloads (docker/podman/firecracker/microVM; only Electron/webview sandboxing); a product MCP client or MCP server (only a Claude --strict-mcp-config passthrough); audit-log export; kanban/backlog/sprint/issue entities; workspace export/import; Cate Connect pricing or paid tiers. Search terms: cron, schedule, webhook, sso, saml, oidc, scim, docker, container, sandbox, microvm, firecracker, mcp, audit, kanban, backlog, sprint, export.
Retrieved: 2026-11-12