{"id":"thinkrail","name":"ThinkRail","website":"https://thinkrail.ai/","researchStatus":"covered","repository":"https://github.com/JetBrains/thinkrail","githubStars":{"value":8189,"observedAt":"2026-11-12","evidenceIds":["thinkrail:repo"]},"lifecycle":{"status":"unknown","note":null},"sourcedClaimCount":50,"crossCheckedClaimCount":49,"oldestCheckedAt":"2026-11-12","lastCheckedAt":"2026-11-12","facets":{"desktop-os":{"macos":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"windows":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"linux":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"}},"web-client":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"phone-client":{"ios":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"android":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"mobile-web":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-01","evidenceIds":["thinkrail:arch"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"}},"cli":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-05","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"agents":{"claude-code":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"codex":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"cursor":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"gemini-cli":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"opencode":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"pi":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal","thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"grok":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"aider":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"antigravity":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:ACC-02","evidenceIds":["thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"}},"byo-subscription":{"value":"yes","verificationStatus":"sourced","claimId":"thinkrail:ACC-03","evidenceIds":["thinkrail:gaps41-subscription"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-03-12"},"execution":{"local":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:RUN-01","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"own-server":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:RUN-01","evidenceIds":["thinkrail:arch","thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"vendor-cloud":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:RUN-01","evidenceIds":["thinkrail:arch","thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"}},"isolation":{"worktree":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:RUN-02","evidenceIds":["thinkrail:readme","thinkrail:site-home"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"container":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:RUN-02","evidenceIds":["thinkrail:code-workspaces"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"vm":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:RUN-02","evidenceIds":["thinkrail:code-workspaces"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"}},"parallel-runs":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:COORD-01","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"coordinator":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:COORD-03","evidenceIds":["thinkrail:arch","thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"issue-tracking":{"value":"yes","verificationStatus":"sourced","claimId":"thinkrail:PLAN-06","evidenceIds":["thinkrail:code-todos","thinkrail:code-workspaces","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-03-12"},"unattended-triggers":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:COORD-04","evidenceIds":["thinkrail:code-nosched"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"multiplayer":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:TEAM-01","evidenceIds":["thinkrail:code-nouser"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"roles":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:TEAM-02","evidenceIds":["thinkrail:code-nouser"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"sso":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:TEAM-02","evidenceIds":["thinkrail:goal","thinkrail:code-nouser"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"pr-workflow":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:SHIP-03","evidenceIds":["thinkrail:blog-030","thinkrail:goal"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"review-ui":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:TEAM-05","evidenceIds":["thinkrail:blog-020","thinkrail:blog-gui"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"license":{"value":"apache-2-0","verificationStatus":"agent-cross-checked","claimId":"thinkrail:OWN-01","evidenceIds":["thinkrail:license","thinkrail:repo"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-05-11"},"self-hosting":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:OWN-02","evidenceIds":["thinkrail:arch","thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-05-11"},"telemetry-opt-out":{"value":"no","verificationStatus":"agent-cross-checked","claimId":"thinkrail:OWN-03","evidenceIds":["thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12"},"free-tier":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:OWN-08","evidenceIds":["thinkrail:license","thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11"},"starting-price":{"value":"free","verificationStatus":"agent-cross-checked","claimId":"thinkrail:OWN-08","evidenceIds":["thinkrail:license","thinkrail:readme"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11"},"pricing-model":{"no-paid-plan":{"value":"yes","verificationStatus":"agent-cross-checked","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:releases"],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11"},"free-plan":{"value":"no","verificationStatus":"sourced","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-01-11"},"subscription":{"value":"no","verificationStatus":"sourced","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-01-11"},"per-seat":{"value":"no","verificationStatus":"sourced","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-01-11"},"usage-based":{"value":"no","verificationStatus":"sourced","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-01-11"},"compute":{"value":"no","verificationStatus":"sourced","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-01-11"},"byok":{"value":"yes","verificationStatus":"sourced","claimId":"thinkrail:ACC-03","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-020"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-03-12"},"one-time":{"value":"no","verificationStatus":"sourced","claimId":"thinkrail:OWN-04","evidenceIds":["thinkrail:readme","thinkrail:goal"],"checkedAt":"2026-11-13","crossCheckedAt":null,"nextCheckAt":"2027-01-11"}},"paid-from":{"value":"unknown","verificationStatus":"unknown","claimId":null,"evidenceIds":[],"checkedAt":null,"crossCheckedAt":null,"nextCheckAt":null},"lifecycle-status":{"value":"unknown","verificationStatus":"unknown","claimId":null,"evidenceIds":[],"checkedAt":null,"crossCheckedAt":null,"nextCheckAt":null},"laptop-independent":{"value":"unknown","verificationStatus":"unknown","claimId":null,"evidenceIds":[],"checkedAt":null,"crossCheckedAt":null,"nextCheckAt":null}},"claims":[{"productId":"thinkrail","claimId":"thinkrail:ACC-01","verificationStatus":"agent-cross-checked","answer":"Desktop apps ship for macOS 14+ (Apple Silicon and Intel), Windows x64 and Linux x64/ARM64; the complete install matrix omits native phone apps and editor extensions. The thinkrail CLI opens the same app in any browser, the web UI adapts to phone viewports over Tailscale, and notifications arrive via desktop alerts plus in-app waiting markers. Same-task state rebuilds on another surface, but running execution does not hand off.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"desktop_os","question":"Desktop os","support":"supported","answer":"Desktop installers cover macOS 14+ Apple Silicon/Intel (DMG), Windows x64 (setup zip) and Linux x64/ARM64 (setup tarball plus installer).","evidenceIds":["thinkrail:readme","thinkrail:blog-intro"]},{"id":"mobile_apps","question":"Mobile apps","support":"unsupported","answer":"Client access, mobile_apps: the install matrix (README Installation plus landing install section) is the complete first-party list of shipped clients — macOS, Windows and Linux desktop plus the CLI browser host — and omits any native iOS or Android app. No mobile packaging exists in apps/ (cli, desktop, web, website only).","evidenceIds":["thinkrail:readme","thinkrail:site-home","thinkrail:repo"]},{"id":"browser","question":"Browser","support":"supported","answer":"The thinkrail CLI opens the same app in a browser; desktop and browser hosts embed the same engine host.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:blog-pi"]},{"id":"mobile_browser","question":"Mobile browser","support":"supported","answer":"The mobile-first React UI adapts below 767px (viewport phone queries) and a phone reaches the selected host over Tailscale; no native app exists.","evidenceIds":["thinkrail:code-viewport","thinkrail:arch"]},{"id":"cli","question":"Cli","support":"supported","answer":"The product-owned thinkrail launcher CLI installs, updates (stable/nightly channels), opens projects and prints help/version; model and agent work stay pi’s.","evidenceIds":["thinkrail:readme","thinkrail:site-home"]},{"id":"editor_extensions","question":"Editor extensions","support":"unsupported","answer":"Client access, editor_extensions: the server ships a fixed external-editor launcher list (VS Code, Emacs, JetBrains IDEs, Vim in packages/server/src/editors/editors.ts) and no editor extension of its own. Opening a worktree in an installed editor is the documented direction.","evidenceIds":["thinkrail:code-editors","thinkrail:goal"]},{"id":"task_actions","question":"Task actions","support":"supported","answer":"Start, steer and queue follow-ups mid-run, review diffs, manage PR state from the topbar, and reopen previous conversations from the chat history popup.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui","thinkrail:blog-030"]},{"id":"notifications","question":"Notifications","support":"supported","answer":"Desktop notifications plus in-app waiting markers: attention engine with per-session unread holds (apps/web/src/notifications) and the palette urgency list; Linux desktop builds require libnotify.","evidenceIds":["thinkrail:code-notify","thinkrail:readme","thinkrail:blog-031"]},{"id":"cross_device_continuity","question":"Cross device continuity","support":"partial","answer":"Client access, cross_device_continuity: hydrate-then-stream rebuilds the same projects, workspaces, sessions and transcripts on a second tab, phone or restart (contracts session.list/session.getMessages), but execution stays on the originating host with no handoff of running work.","evidenceIds":["thinkrail:code-hydrate","thinkrail:arch"]}],"limitations":["The complete install list omits native phone apps and editor extensions. Cross-device state rebuilds; running execution stays on the originating host."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:blog-intro","thinkrail:blog-pi","thinkrail:code-editors","thinkrail:code-hydrate","thinkrail:code-notify","thinkrail:code-viewport","thinkrail:readme","thinkrail:repo","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:ACC-02","verificationStatus":"agent-cross-checked","answer":"The only harness is pi, run in-process with no second runtime. Model choice comes from pi provider auth plus JetBrains AI through the user-owned central CLI and user-added OpenAI-compatible servers (1,639 provider/model pairs in the pi 1.5.1 catalogue). Other coding-agent CLIs are only detected as provider-setup signals, never run as harnesses; mixed-harness operation is excluded by the single-engine design.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"harnesses","question":"Harnesses","support":"supported","answer":"pi is the only engine, run in-process — explicitly no second runtime (no claude-agent-sdk). Claude Code, Codex, Copilot, Kimi CLI and Grok Build appear only as detected provider configs, never as run harnesses.","evidenceIds":["thinkrail:goal","thinkrail:blog-pi","thinkrail:blog-030"]},{"id":"model_providers","question":"Model providers","support":"supported","answer":"Providers connect through pi auth, JetBrains AI via the central CLI, and user-added OpenAI-compatible servers; the 1.5.1 catalogue held 1,639 provider/model pairs.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:central","thinkrail:picompat","thinkrail:blog-031"]},{"id":"custom_adapters","question":"Custom adapters","support":"supported","answer":"Any OpenAI-compatible server fits: company gateways or on-machine models via Settings Providers with Find models, saved into pi models.json for the app and the pi CLI.","evidenceIds":["thinkrail:readme","thinkrail:blog-031"]},{"id":"session_integration","question":"Session integration","support":"supported","answer":"The engine host owns one in-process pi session per chat; the app and the pi CLI share ~/.pi configuration and chat history both ways.","evidenceIds":["thinkrail:arch","thinkrail:blog-pi"]},{"id":"mixed_harness_operation","question":"Mixed harness operation","support":"unsupported","answer":"Agent and model choice, mixed_harness_operation: pi is the only engine with no second runtime and no adapter code; there is nothing to mix.","evidenceIds":["thinkrail:goal","thinkrail:arch"]}],"limitations":["Single-engine product: no second harness exists and mixed-harness operation is excluded."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-pi","thinkrail:central","thinkrail:code-detect","thinkrail:goal","thinkrail:picompat","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:ACC-03","verificationStatus":"sourced","answer":"ThinkRail uses provider API keys and Pi's native OAuth login, including Anthropic subscription credentials recognized by the embedded runtime. External CLI accounts are setup signals rather than borrowed credentials; there is no ThinkRail credit system.","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"Targeted first-party source check 2026-11-13. New implementation findings are pinned to 1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544. Unchanged atomic answers retain the individual source dates and revisions in their cited evidence.","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"agent_subscriptions","question":"Agent subscriptions","support":"supported","answer":"The embedded Pi runtime uses its own OAuth sign-in and explicitly recognizes active Anthropic subscription authentication.","evidenceIds":["thinkrail:gaps41-subscription"]},{"id":"api_accounts","question":"Api accounts","support":"supported","answer":"Provider API keys and in-app sign-in flow through pi’s own auth, including custom OpenAI-compatible servers; secrets are referenced as ${VAR} or !command, never pasted into URLs.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-020"]},{"id":"vendor_credits","question":"Vendor credits","support":"unsupported","answer":"ThinkRail has no accounts of its own and no credit system; the recurring AI-credit quota that exists belongs to JetBrains AI via the user-owned central CLI, not to ThinkRail.","evidenceIds":["thinkrail:goal","thinkrail:readme","thinkrail:central"]},{"id":"local_models","question":"Local models","support":"supported","answer":"On-machine models connect as custom servers with Ollama, LM Studio, vLLM and llama.cpp presets; the key never reaches the browser.","evidenceIds":["thinkrail:readme","thinkrail:blog-031"]},{"id":"account_switching","question":"Account switching","support":"supported","answer":"Settings chooses the pi config folder (for example a personal versus work setup) plus extra environment variables, applied per host on next start; the model picker switches provider and model per chat.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-gui"]},{"id":"vendor_account_requirement","question":"Vendor account requirement","support":"supported","answer":"No ThinkRail account exists or is required; what still requires credentials is the chosen model provider (including JetBrains AI sign-in through central).","evidenceIds":["thinkrail:goal","thinkrail:readme"]},{"id":"provider_restrictions","question":"Provider restrictions","support":"supported","answer":"Custom servers support the OpenAI chat-completions API only with no per-model UI tuning; the model list shows only models the account can use and unavailable models follow existing selection rules.","evidenceIds":["thinkrail:blog-031","thinkrail:blog-030","thinkrail:picompat"]}],"limitations":["This source pass establishes only the named atomic answers. Other parts retain their documented source gaps; no hands-on test was performed."],"checkedAt":"2026-11-12","crossCheckedAt":null,"nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-031","thinkrail:central","thinkrail:code-detect","thinkrail:goal","thinkrail:picompat","thinkrail:readme","thinkrail:gaps41-subscription"]},{"productId":"thinkrail","claimId":"thinkrail:ACC-04","verificationStatus":"agent-cross-checked","answer":"A first-run wizard (intro, privacy question, Connect a model) drops the user on Start/Open project; Start a new project creates an empty git repo, and Clone repository accepts a Git URL. Any local git repo opens as a project, chats without a project work in scratch folders, and GitHub works through the user’s git credentials and gh CLI. No vendor-cloud or user-server hosting path exists.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"first_task_setup","question":"First task setup","support":"supported","answer":"Install, connect a provider in the wizard, open or create a project, pick a model and send a message; Skip setup exists for experts.","evidenceIds":["thinkrail:readme","thinkrail:blog-030","thinkrail:blog-intro"]},{"id":"no_git","question":"No git","support":"supported","answer":"Chats without a project work in their own scratch folder under Chats with files, terminal and plan and no branch, review or pull request; deleting one moves the whole folder to the Trash.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"local_git_without_remote","question":"Local git without remote","support":"supported","answer":"Any local git repo opens as a project and the topbar Remote segment explicitly handles the No remote state with Publish/Push guidance.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-030"]},{"id":"hosted_git","question":"Hosted git","support":"supported","answer":"GitHub works through the machine’s git credentials and SSH keys with gh-driven PR flow; Clone repository opens any Git URL as a project, and GitLab gets a prefilled new-MR page.","evidenceIds":["thinkrail:readme","thinkrail:blog-030"]},{"id":"prerequisite_guidance","question":"Prerequisite guidance","support":"supported","answer":"Prerequisites are stated up front: git on PATH, a model provider, and gh for the PR flow; the wizard explains provider connection before any project opens.","evidenceIds":["thinkrail:readme","thinkrail:blog-030"]},{"id":"managed_cloud_setup","question":"Managed cloud setup","support":"unsupported","answer":"Onboarding and project prerequisites, managed_cloud_setup: there is no vendor-cloud execution to set up; the desktop profile is local only and no cloud onboarding exists in docs, installers or code.","evidenceIds":["thinkrail:arch","thinkrail:goal"]},{"id":"byo_vps_onboarding","question":"Byo vps onboarding","support":"unsupported","answer":"Onboarding and project prerequisites, byo_vps_onboarding: no user-owned-server hosting path exists; the architecture names remote-host dialling as later shared-client work, and installers plus code cover local machines only.","evidenceIds":["thinkrail:arch","thinkrail:readme"]}],"limitations":["Local-only product: no vendor-cloud or BYO-server onboarding exists; remote-host dialling is described as future work."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-intro","thinkrail:blog-030"]},{"productId":"thinkrail","claimId":"thinkrail:ACC-05","verificationStatus":"agent-cross-checked","answer":"The product-owned thinkrail CLI is a launcher with an exhaustive inventory: open, update and uninstall plus connection flags; it exposes no agent operations. The engine-to-UI wire is internal (/ws plus /health and static routes), with no public API, SDK, MCP server or webhooks in the pinned release.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"cli","question":"Cli","support":"supported","answer":"thinkrail opens projects, takes channel/version/uninstall flags and --help/--version; agent operations live in the UI, not the CLI.","evidenceIds":["thinkrail:readme"]},{"id":"api","question":"Api","support":"unsupported","answer":"Programmable access, api: bounded v0.3.2 inspection (packages/server/src/host/server.ts) shows only the internal /ws wire plus /health and static/file routes. No public API exists.","evidenceIds":["thinkrail:code-routes"]},{"id":"sdk","question":"Sdk","support":"unsupported","answer":"Programmable access, sdk: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no SDK surface besides the internal typed wire protocol.","evidenceIds":["thinkrail:code-routes","thinkrail:arch"]},{"id":"mcp_server","question":"Mcp server","support":"unsupported","answer":"Programmable access, mcp_server: ThinkRail is an MCP client only; bounded v0.3.2 inspection found no MCP server transport exposing the product.","evidenceIds":["thinkrail:code-routes","thinkrail:code-mcp"]},{"id":"webhooks","question":"Webhooks","support":"unsupported","answer":"Programmable access, webhooks: bounded v0.3.2 inspection found webhook handling only in the marketing website demo, none in the product.","evidenceIds":["thinkrail:code-routes"]},{"id":"operations","question":"Operations","support":"unsupported","answer":"Programmable access, operations: the complete CLI inventory (args.ts: update/uninstall plus launch flags) exposes no create, inspect, steer, stop or review operations; agent operations live in the UI.","evidenceIds":["thinkrail:code-args"]},{"id":"authentication","question":"Authentication","support":"unsupported","answer":"Programmable access, authentication: no accounts exist and host reach is network-level (Tailscale ACLs); bounded v0.3.2 inspection found no API auth surface.","evidenceIds":["thinkrail:goal","thinkrail:arch"]},{"id":"stability","question":"Stability","support":"unsupported","answer":"Programmable access, stability: no public API exists to carry a stability statement.","evidenceIds":["thinkrail:code-routes"]}],"limitations":["All agent operations are UI-driven. The CLI inventory is complete and omits them; no programmable surface exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:code-args","thinkrail:code-routes","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:ACC-06","verificationStatus":"agent-cross-checked","answer":"MCP servers come from pi mcp.json and Settings with presets, per-chat visibility and in-chat confirm for data-changing calls. pi packages (extensions, skills, prompts) install from npm, git or local folders for the user or a repo with per-item switches. Skills import from Claude, Codex and other agents’ folders; repo-defined resources stay off until a per-project trust grant, and repo MCP entries need per-entry approval.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"mcp_client","question":"Mcp client","support":"supported","answer":"pi’s built-in MCP client reads the user mcp.json and Settings presets (Context7, DeepWiki, Linear read-only, Sentry, Playwright); each chat shows its servers next to background commands and subagents.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-020","thinkrail:blog-gui"]},{"id":"plugins","question":"Plugins","support":"supported","answer":"pi packages install by source (npm, git, local folder) from Settings for the user or a repository, showing every extension, skill and prompt with switches; changes apply when open chats’ turns end.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-031"]},{"id":"custom_tools","question":"Custom tools","support":"supported","answer":"Custom tools arrive via MCP servers, pi packages and bundled agent tools (structured questions, Mermaid diagrams, comparisons, file previews, UI mockups).","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-020"]},{"id":"instructions_import","question":"Instructions import","support":"supported","answer":"Skills load from ~/.pi, ~/.claude, ~/.codex, ~/.copilot and ~/.gemini plus project counterparts, and ThinkRail imports skills from Claude, Codex and other coding agents via Settings Extensions or the per-project Skills dialog.","evidenceIds":["thinkrail:readme","thinkrail:blog-pi"]},{"id":"authentication","question":"Authentication","support":"supported","answer":"ThinkRail signs into OAuth MCP servers from Settings; server secrets must be ${VAR} or !command and pasted URL credentials are refused.","evidenceIds":["thinkrail:readme","thinkrail:blog-020"]},{"id":"permission_scope","question":"Permission scope","support":"supported","answer":"Data-changing MCP calls confirm on the call with Deny, Allow once, Allow in this chat or Always allow (per project, lapsing when the server command or URL changes); a repo cannot ship itself pre-approved.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"integration_owner","question":"Integration owner","support":"supported","answer":"Connections are product-managed in Settings and per-chat popups, while also inheriting the underlying pi configuration (~/.pi, mcp.json); bundled ThinkRail extensions ship with the host.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-pi"]}],"limitations":[],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:blog-pi","thinkrail:code-mcp","thinkrail:code-trust","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:ACC-07","verificationStatus":"agent-cross-checked","answer":"The desktop app is an Electrobun package: a native system-webview shell around the same engine host the CLI uses. No native mobile client exists (apps/ holds cli, desktop, web and website only; the install matrix omits mobile) and no hybrid construction exists beyond the system-webview shell.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"desktop_implementation","question":"Desktop implementation","support":"supported","answer":"Desktop apps are packaged with Electrobun as a native system-webview shell — not Electron — running identically to the CLI browser host.","evidenceIds":["thinkrail:blog-pi","thinkrail:arch"]},{"id":"mobile_implementation","question":"Mobile implementation","support":"unsupported","answer":"Client implementation, mobile_implementation: apps/ holds cli, desktop, web and website only, and the complete install matrix omits mobile builds; phone access is the mobile-first web UI.","evidenceIds":["thinkrail:repo","thinkrail:readme","thinkrail:arch"]},{"id":"hybrids","question":"Hybrids","support":"unsupported","answer":"Client implementation, hybrids: bounded v0.3.2 inspection found no hybrid client construction beyond the Electrobun system-webview shell.","evidenceIds":["thinkrail:arch","thinkrail:blog-pi"]},{"id":"implementation_evidence","question":"Implementation evidence","support":"supported","answer":"Official architecture documentation names the Electrobun shell and the React 19 UI; the apps/desktop launcher source lives in the public repo.","evidenceIds":["thinkrail:arch","thinkrail:blog-pi","thinkrail:repo"]}],"limitations":["No native mobile client or hybrid construction exists to classify."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-05-11","evidenceIds":["thinkrail:arch","thinkrail:blog-pi","thinkrail:repo"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-01","verificationStatus":"agent-cross-checked","answer":"Projects, workspaces and scratch chats are created locally from prompts, and asking for work in a side workspace makes the agent start the workspace and its chat itself. External intake is repository-shaped (clone URL, attached worktrees) with GitHub PR metadata read back into the topbar and PR round-trips through gh. No issue tracker, sync, or chat/git triggers exist in docs or the pinned release.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"local_creation","question":"Local creation","support":"supported","answer":"Projects, workspaces and scratch chats are created in the app from the Welcome screen, Create dialog, palette or Chats section.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-gui"]},{"id":"prompt_intake","question":"Prompt intake","support":"supported","answer":"The Create workspace description becomes the workspace name and the agent’s initial prompt; asking for work in a side workspace has the agent start that workspace and chat itself.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-workspaces"]},{"id":"external_import","question":"External import","support":"supported","answer":"Clone repository opens a Git URL as a project and existing git worktrees attach in place; GitHub PR checks and review decisions are read into the topbar. No Linear, Jira or other tracker import exists.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-030"]},{"id":"chat_git_triggers","question":"Chat git triggers","support":"unsupported","answer":"Intake and external tracker relationship, chat_git_triggers: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, web, CLI) found no chat or git-event triggers that start work.","evidenceIds":["thinkrail:code-nosched"]},{"id":"authoritative_tracker","question":"Authoritative tracker","support":"unsupported","answer":"Intake and external tracker relationship, authoritative_tracker: no issue tracker exists in docs or code; work state lives in workspaces/chats and PR truth stays on the forge.","evidenceIds":["thinkrail:code-workspaces","thinkrail:goal"]},{"id":"stable_ids","question":"Stable ids","support":"unsupported","answer":"Intake and external tracker relationship, stable_ids: bounded v0.3.2 inspection found no stable cross-surface issue IDs; workspace entities are not issues.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"sync","question":"Sync","support":"unsupported","answer":"Intake and external tracker relationship, sync: bounded v0.3.2 inspection found no tracker sync code.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"supported_edits","question":"Supported edits","support":"unsupported","answer":"Intake and external tracker relationship, supported_edits: bounded v0.3.2 inspection found no external-tracker edit operations.","evidenceIds":["thinkrail:code-pr"]},{"id":"external_roundtrips","question":"External roundtrips","support":"supported","answer":"The app pushes the branch and opens or updates the GitHub PR through gh and reads back checks and review decisions; GitLab gets a prefilled MR page without local merge or review actions.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]}],"limitations":["No external issue-tracker relationship exists; PR round-trips are GitHub-only and partial on GitLab."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-030","thinkrail:blog-gui","thinkrail:code-nosched","thinkrail:code-pr","thinkrail:code-workspaces","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-02","verificationStatus":"agent-cross-checked","answer":"Shared TODO plans carry the work with per-step review and independent reviewers, editable by user and agent, with implementation links through per-step commits and turn receipts. Plans survive restarts and mid-run steering. Completed steps form immutable history; explicit acceptance-criteria fields and a separate plan-edit history are undescribed.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"plans","question":"Plans","support":"supported","answer":"A shared TODO plan tracks next steps one click from the full plan, worked by the agent and edited by the user.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-gui"]},{"id":"acceptance_criteria","question":"Acceptance criteria","support":"supported","answer":"Plan steps act as acceptance units: a completed step is committed on its own when its changes are provably its own and can go to an independent reviewer; no separate acceptance-criteria field was established.","evidenceIds":["thinkrail:goal"]},{"id":"editors","question":"Editors","support":"supported","answer":"Both the agent (which updates the plan) and the user (who reviews and edits) write the shared plan.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"revisions","question":"Revisions","support":"partial","answer":"Durable task plans, revisions: completed steps are immutable plan history with per-step commits and revision shas (todos.ts); a dedicated plan-edit history beyond step commits is undescribed.","evidenceIds":["thinkrail:code-todos"]},{"id":"implementation_links","question":"Implementation links","support":"supported","answer":"Turn receipts tie runs to changed files, per-step commits tie steps to code, and Review turn opens the whole run as one Changes tab.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"amendment","question":"Amendment","support":"supported","answer":"Running turns accept steering and queued follow-ups without waiting for the agent to finish.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"restart_persistence","question":"Restart persistence","support":"supported","answer":"Previous conversations reopen, rename and delete from the chat history popup, and resource history persists across host restarts.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal"]}],"limitations":["Acceptance criteria live in plan steps, not a dedicated object; plan-edit history beyond step commits is undescribed."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-gui","thinkrail:code-todos","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-03","verificationStatus":"agent-cross-checked","answer":"The pinned release implements a flat workspace model (own branch/cwd, settled/active states) with side workspaces and handoff growth, but no epics, parent/child depth, blockers, readiness gates, dependency enforcement or state propagation. A bundled workflow skill set routes by default without a mandatory gate.","availability":"unknown","delivery":"unknown","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"epics","question":"Epics","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, epics: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"hierarchy","question":"Hierarchy","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, hierarchy: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"blockers","question":"Blockers","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, blockers: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"readiness","question":"Readiness","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, readiness: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"enforcement","question":"Enforcement","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, enforcement: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"state_propagation","question":"State propagation","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, state_propagation: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"task_to_epic","question":"Task to epic","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, task_to_epic: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"identity_retention","question":"Identity retention","support":"unsupported","answer":"Hierarchy, dependencies and evolving scope, identity_retention: bounded v0.3.2 inspection (packages/server/src/workspaces/workspaces.ts) shows a flat workspace model with branch, cwd and settled/active states and no such construct.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"workflow_constraints","question":"Workflow constraints","support":"partial","answer":"Hierarchy, dependencies and evolving scope, workflow_constraints: the pi-thinkrail-workflow skill set ships with an always-on routing rule, but no mandatory workflow or preset gate was found; scope changes do not require recreating work (Continue-in-workspace handoff grows chats into workspaces).","evidenceIds":["thinkrail:goal","thinkrail:readme"]}],"limitations":["No hierarchy, dependency or enforcement constructs exist; only the workflow routing default was found."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:code-workspaces"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-04","verificationStatus":"agent-cross-checked","answer":"Project knowledge persists in the mtime-guarded SPEC.md graph the agent searches and maintains, plus pi skills, project skills and session state shared between CLI and app. Per-project trust grants scope what loads. Provenance, correction and freshness beyond index revalidation are only partly established.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"instructions","question":"Instructions","support":"partial","answer":"Shared context and memory, instructions: repository instruction and skill files load in place subject to per-project trust grants (skillAdmission); instruction precedence rules are undescribed.","evidenceIds":["thinkrail:code-trust","thinkrail:readme"]},{"id":"skills","question":"Skills","support":"supported","answer":"ThinkRail loads pi skills plus project skills from pi, Claude, Codex, Copilot and Gemini folders, with a per-chat Skills popup, per-project dialog and disk-change reload.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-pi","thinkrail:blog-gui"]},{"id":"project_docs","question":"Project docs","support":"supported","answer":"The connected SPEC.md graph beside the code is the durable project intent store, rendered as a tree in the read-only Specs tool.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal"]},{"id":"memory","question":"Memory","support":"supported","answer":"Specs persist intent across sessions and pi session state (config, history) is shared between the app and the pi CLI both ways.","evidenceIds":["thinkrail:site-home","thinkrail:goal","thinkrail:blog-pi"]},{"id":"scope","question":"Scope","support":"supported","answer":"Skill lists differ per project and workspace; one pi config folder applies per host, not per project.","evidenceIds":["thinkrail:readme","thinkrail:blog-pi"]},{"id":"provenance","question":"Provenance","support":"partial","answer":"Shared context and memory, provenance: per-project trust records (trusted, piResourceTrust) scope what the agent may load; per-memory citation is undescribed.","evidenceIds":["thinkrail:code-trust"]},{"id":"correction","question":"Correction","support":"partial","answer":"Shared context and memory, correction: specs and plans edit as files, skills reload on disk change with per-chat switches; dedicated correction flows are undescribed.","evidenceIds":["thinkrail:readme","thinkrail:blog-pi"]},{"id":"deletion","question":"Deletion","support":"supported","answer":"Chats (with their scratch folders) delete to the Trash and skills/packages switch off per chat or project; memory-specific deletion controls are undescribed.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"freshness","question":"Freshness","support":"supported","answer":"Shared context and memory, freshness: the spec index revalidates every file by mtime and size and never serves a stale graph; spec statuses include stale.","evidenceIds":["thinkrail:code-spec"]},{"id":"takeover_continuity","question":"Takeover continuity","support":"supported","answer":"Sessions move between the pi CLI and ThinkRail without losing configuration, history or work.","evidenceIds":["thinkrail:blog-pi"]}],"limitations":["Provenance is trust scoping, correction is file edits plus reload; deeper memory controls are undescribed."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-gui","thinkrail:blog-pi","thinkrail:code-spec","thinkrail:code-trust","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-05","verificationStatus":"agent-cross-checked","answer":"The agent retrieves code and specs through pi tools, spec_search and a ranked spec index that also powers palette # search; file text search, web research and MCP knowledge presets extend it. Voice dictation and @ files add input modalities. Retrieval freshness and scope are partly established; citations, conflict detection and review-time rule enforcement are not.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"code_search","question":"Code search","support":"supported","answer":"Palette file search (Cmd/Ctrl-Shift-F, grouped by file with a code preview) plus the agent’s own code search via pi tools.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"indexing","question":"Indexing","support":"supported","answer":"The spec graph core backs the agent’s spec_search and the palette’s ranked # section search over the same engine.","evidenceIds":["thinkrail:site-home","thinkrail:goal","thinkrail:arch"]},{"id":"external_knowledge","question":"External knowledge","support":"supported","answer":"Web research tools ship with the GUI and MCP presets add Context7, DeepWiki, Sentry and Playwright knowledge.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"multimodal_inputs","question":"Multimodal inputs","support":"supported","answer":"Local dictation (NVIDIA Nemotron streaming model, one-time user-started download) types into every text field, and @ files attaches file context in the composer.","evidenceIds":["thinkrail:goal","thinkrail:blog-chat","thinkrail:site-home"]},{"id":"freshness","question":"Freshness","support":"partial","answer":"Architecture and API awareness, freshness: the spec index revalidates by mtime/size; code search runs live; external-source freshness is undescribed.","evidenceIds":["thinkrail:code-spec"]},{"id":"access_scope","question":"Access scope","support":"partial","answer":"Architecture and API awareness, access_scope: search is workspace-scoped with per-chat MCP server visibility; formal scope boundaries are undescribed.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"api_retrieval","question":"Api retrieval","support":"supported","answer":"The agent searches, navigates and maintains the spec graph through dedicated spec_* tools; the palette can hand a question the specs phrase differently to the agent.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal"]},{"id":"citations","question":"Citations","support":"unsupported","answer":"Architecture and API awareness, citations: bounded v0.3.2 inspection (packages/spec-graph) found no citation mechanism in search tools.","evidenceIds":["thinkrail:code-spec"]},{"id":"conflict_detection","question":"Conflict detection","support":"unsupported","answer":"Architecture and API awareness, conflict_detection: bounded v0.3.2 inspection (spec-graph, todos, reviews) found no architecture-conflict detection.","evidenceIds":["thinkrail:code-spec"]},{"id":"review_enforcement","question":"Review enforcement","support":"supported","answer":"Completed plan steps can go to an independent reviewer and turn diffs carry Keep/Revert/Ask-agent review; architecture-rule enforcement at review is undescribed.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]}],"limitations":["Freshness and scope are partly established; no citation, conflict-detection or rule-enforcement mechanism exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:blog-020","thinkrail:blog-chat","thinkrail:code-spec","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-06","verificationStatus":"agent-cross-checked","answer":"ThinkRail manages work as projects, workspaces (active to Settled shelf) and shared TODO plans rather than a labelled tracker: creation, edit, discussion, search, archive/Trash, reopen, dispatch-by-handoff and durable states exist and were confirmed in code, but prioritisation, labels, assignment and filters do not. No external tracker is required for core work.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"create","question":"Create","support":"supported","answer":"Projects, workspaces, scratch chats and TODO plans are created in-app from prompts.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"edit","question":"Edit","support":"supported","answer":"Chats rename, plans edit, specs edit as Markdown, and review comments collect on lines and diffs.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui","thinkrail:blog-020"]},{"id":"discuss","question":"Discuss","support":"supported","answer":"Anchored review comments collect without starting the agent and go to chats as structured context; plan discussion happens in the shared TODO plan. Dedicated issue threads were not established.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"prioritize","question":"Prioritize","support":"unsupported","answer":"Native issue management and idea backlog, prioritize: bounded v0.3.2 inspection (workspaces, todos, reviews code) found no such work-item model.","evidenceIds":["thinkrail:code-workspaces","thinkrail:code-todos"]},{"id":"label","question":"Label","support":"unsupported","answer":"Native issue management and idea backlog, label: bounded v0.3.2 inspection (workspaces, todos, reviews code) found no such work-item model.","evidenceIds":["thinkrail:code-workspaces","thinkrail:code-todos"]},{"id":"assign","question":"Assign","support":"unsupported","answer":"Native issue management and idea backlog, assign: bounded v0.3.2 inspection (workspaces, todos, reviews code) found no such work-item model.","evidenceIds":["thinkrail:code-workspaces","thinkrail:code-todos"]},{"id":"search","question":"Search","support":"supported","answer":"The palette finds chats, workspaces, projects, specs and settings with urgency-ranked waiting items.","evidenceIds":["thinkrail:blog-031","thinkrail:readme"]},{"id":"filter","question":"Filter","support":"unsupported","answer":"Native issue management and idea backlog, filter: bounded v0.3.2 inspection (workspaces, todos, reviews code) found no such work-item model.","evidenceIds":["thinkrail:code-workspaces","thinkrail:code-todos"]},{"id":"archive","question":"Archive","support":"supported","answer":"Finished and dormant workspaces settle to the Settled shelf (PR merge/close or a quiet week) and return when worked in again; deleted chats move to the Trash.","evidenceIds":["thinkrail:readme"]},{"id":"reopen","question":"Reopen","support":"supported","answer":"Settled workspaces return on touch, closed PRs can be reopened from the topbar, and previous conversations reopen from history.","evidenceIds":["thinkrail:readme","thinkrail:blog-030","thinkrail:blog-gui"]},{"id":"project_epic_views","question":"Project epic views","support":"supported","answer":"The Projects panel lists open projects, their workspaces and the Settled shelf; no epic or board views exist.","evidenceIds":["thinkrail:blog-gui","thinkrail:readme"]},{"id":"idea_parking","question":"Idea parking","support":"supported","answer":"Chats without a project park an idea as a scratch-folder draft with no execution, later continued into a real workspace via agent-written handoff.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"explicit_dispatch","question":"Explicit dispatch","support":"supported","answer":"Parked chats dispatch later through Continue in workspace, and side-workspace requests start workspace chats on demand.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"task_session_separation","question":"Task session separation","support":"supported","answer":"Workspaces (durable work entities with branch and state) are separate from chats (sessions), with several sessions per workspace.","evidenceIds":["thinkrail:goal","thinkrail:site-home","thinkrail:blog-gui"]},{"id":"metadata","question":"Metadata","support":"supported","answer":"Workspaces carry branch, remote/PR state and description; labels, priorities and estimates were not established.","evidenceIds":["thinkrail:blog-030","thinkrail:readme"]},{"id":"durable_states","question":"Durable states","support":"supported","answer":"Workspaces move through active and Settled states with PR merge/close transitions; TODO steps review independently.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"external_tracker_requirement","question":"External tracker requirement","support":"supported","answer":"Core planning, specs, review and merge-prep work without any external tracker; GitHub is needed only for the PR leg.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]}],"limitations":["No labelled, prioritised or assigned issue model exists in docs or code; work tracking is workspaces plus TODO plans."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:code-todos","thinkrail:code-workspaces","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-07","verificationStatus":"agent-cross-checked","answer":"The agent works the same workspaces, chats and PRs the human sees: it starts side workspaces with chats, checks their chats, PRs and diffs, delegates to subagents and reports results, all visible in the Resources view. Reads, creates and result reporting are established in docs and tool code. Claims, assignment, state changes, dependencies, issue children, attribution and conflict handling do not exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"shared_ids","question":"Shared ids","support":"supported","answer":"Agent-started workspaces and chats are the same entities humans open, list and continue; no separate agent-private work graph was described.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"read","question":"Read","support":"supported","answer":"The agent checks its chats’, PRs’ and diffs’ status across open projects.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"create","question":"Create","support":"supported","answer":"Asked for work in a side workspace, the agent starts the workspace and its chat itself rather than the host deciding.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"update","question":"Update","support":"partial","answer":"Agent-native issue operations, update: the agent writes plans, specs and sessions through host tools (Agent, background_command, request review, resolve comment, set title); field-level updates to durable issue records beyond those writes are undescribed.","evidenceIds":["thinkrail:code-delegation","thinkrail:code-bgcmd"]},{"id":"claim","question":"Claim","support":"unsupported","answer":"Agent-native issue operations, claim: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]},{"id":"assign","question":"Assign","support":"unsupported","answer":"Agent-native issue operations, assign: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]},{"id":"state_changes","question":"State changes","support":"unsupported","answer":"Agent-native issue operations, state_changes: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]},{"id":"dependencies","question":"Dependencies","support":"unsupported","answer":"Agent-native issue operations, dependencies: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]},{"id":"children","question":"Children","support":"unsupported","answer":"Agent-native issue operations, children: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]},{"id":"results","question":"Results","support":"supported","answer":"Subagents return results through get_subagent_result and turns end with file-change receipts the human reviews.","evidenceIds":["thinkrail:arch","thinkrail:blog-020"]},{"id":"human_visibility","question":"Human visibility","support":"supported","answer":"Delegated work, background commands and their outcomes stay visible per chat in the Resources view with finished history.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"attribution","question":"Attribution","support":"unsupported","answer":"Agent-native issue operations, attribution: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]},{"id":"permissions","question":"Permissions","support":"supported","answer":"Trust grants gate what the agent may load and MCP confirms gate data-changing calls, with Always-allow scoped per project.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"conflicts","question":"Conflicts","support":"unsupported","answer":"Agent-native issue operations, conflicts: bounded v0.3.2 inspection (host tool registry: Agent, get_subagent_result, background_command, request review, resolve comment, set title; subagent delegation for children of runs, not issues) found no such issue operation.","evidenceIds":["thinkrail:code-delegation"]}],"limitations":["Agent issue operations are limited to the documented tool set; tracker-style claim/assign/state/dependency operations do not exist."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:blog-020","thinkrail:blog-gui","thinkrail:code-bgcmd","thinkrail:code-delegation","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:PLAN-08","verificationStatus":"agent-cross-checked","answer":"SPEC.md files form a versioned, human- and agent-editable requirement graph beside the code with frontmatter parent links, maintained by spec_* tools and retrieved in later work through agent search and palette # search. Approval rules, automated drift checks and review-time spec gates do not exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"persistent_requirements","question":"Persistent requirements","support":"supported","answer":"A connected graph of spec files (goal, architecture, modules, tasks) lives beside the code as the product ground truth.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"human_edits","question":"Human edits","support":"supported","answer":"Specs are plain Markdown with frontmatter edited in editor tabs; the Specs tree renders them live.","evidenceIds":["thinkrail:site-home","thinkrail:readme"]},{"id":"agent_edits","question":"Agent edits","support":"supported","answer":"The agent reads, searches and maintains specs with dedicated spec_* tools and keeps them honest as it builds.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal"]},{"id":"revisions","question":"Revisions","support":"supported","answer":"Specs version with the code in git and spec-affecting changes update the spec in the same change.","evidenceIds":["thinkrail:goal","thinkrail:arch"]},{"id":"approvals","question":"Approvals","support":"unsupported","answer":"Living product specifications, approvals: bounded v0.3.2 inspection (spec-graph tools: create/delete/get/update/validate/grep) found no approval rules.","evidenceIds":["thinkrail:code-spec"]},{"id":"implementation_links","question":"Implementation links","support":"supported","answer":"Specs link into the module graph via frontmatter parents and reading them is documented as sufficient to formulate the next task.","evidenceIds":["thinkrail:site-home","thinkrail:arch"]},{"id":"later_retrieval","question":"Later retrieval","support":"supported","answer":"Later work retrieves specs through the agent’s spec_search and the palette’s # section search on the same engine.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal"]},{"id":"drift_detection","question":"Drift detection","support":"partial","answer":"Living product specifications, drift_detection: the spec-first convention updates specs in the same change and a validate tool exists; automated drift checks are undescribed.","evidenceIds":["thinkrail:code-spec","thinkrail:goal"]},{"id":"review_integration","question":"Review integration","support":"unsupported","answer":"Living product specifications, review_integration: bounded v0.3.2 inspection (server reviews code) found no spec-conformance checks at review.","evidenceIds":["thinkrail:code-reviewflow"]}],"limitations":["Approval rules and review-time spec gates do not exist; drift control is convention plus a validate tool."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:code-reviewflow","thinkrail:code-spec","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-01","verificationStatus":"agent-cross-checked","answer":"Several sessions run concurrently per workspace and several workspaces run in parallel, each isolated on its own branch and cwd — implemented in the session manager with parallel Agent calls and background commands. The Projects rail and Resources views show running work. No quotas exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"concurrent_sessions","question":"Concurrent sessions","support":"supported","answer":"Several concurrent work sessions run per workspace, each with its own model, streaming concurrently.","evidenceIds":["thinkrail:site-home","thinkrail:goal","thinkrail:readme"]},{"id":"concurrent_tasks","question":"Concurrent tasks","support":"supported","answer":"Parallel workspaces each run an agent on its own branch; side workspaces run without waiting for each other.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal"]},{"id":"quotas","question":"Quotas","support":"unsupported","answer":"Parallel work, quotas: bounded v0.3.2 inspection found no documented or coded concurrency quotas (background commands cap at 8 active with 20 retained, which is a buffer bound, not a quota).","evidenceIds":["thinkrail:code-bgcmd"]},{"id":"observed_concurrency","question":"Observed concurrency","support":"supported","answer":"Parallel work, observed_concurrency: concurrency is implemented, not merely displayed — one in-process pi session per chat in the session manager, parallel Agent calls, and session-owned background commands.","evidenceIds":["thinkrail:arch","thinkrail:code-delegation","thinkrail:code-bgcmd"]},{"id":"status_visibility","question":"Status visibility","support":"supported","answer":"The Projects panel shows workspaces per project with the Settled shelf, and Resources tracks background commands and subagents per chat.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal","thinkrail:readme"]}],"limitations":["No concurrency quotas exist in docs or code."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-gui","thinkrail:code-bgcmd","thinkrail:code-delegation","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-02","verificationStatus":"agent-cross-checked","answer":"Dispatch is user-initiated: people create workspace chats and agents delegate to subagents; worktree isolation prevents file collision. No queues, claims, routing, duplicate prevention or enforced ownership exist in docs or code.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"human_assignment","question":"Human assignment","support":"unsupported","answer":"Ownership and dispatch, human_assignment: bounded v0.3.2 inspection (server, workspaces, delegation code) found no such dispatch construct; single-owner product.","evidenceIds":["thinkrail:code-nouser","thinkrail:code-workspaces"]},{"id":"agent_assignment","question":"Agent assignment","support":"supported","answer":"Users dispatch work by creating workspace chats or asking for side workspaces; agents further delegate to subagents. No queue or routing layer exists.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:arch"]},{"id":"claims","question":"Claims","support":"unsupported","answer":"Ownership and dispatch, claims: bounded v0.3.2 inspection (server, workspaces, delegation code) found no such dispatch construct; single-owner product.","evidenceIds":["thinkrail:code-nouser","thinkrail:code-workspaces"]},{"id":"queues","question":"Queues","support":"unsupported","answer":"Ownership and dispatch, queues: bounded v0.3.2 inspection (server, workspaces, delegation code) found no such dispatch construct; single-owner product.","evidenceIds":["thinkrail:code-nouser","thinkrail:code-workspaces"]},{"id":"routing","question":"Routing","support":"unsupported","answer":"Ownership and dispatch, routing: bounded v0.3.2 inspection (server, workspaces, delegation code) found no such dispatch construct; single-owner product.","evidenceIds":["thinkrail:code-nouser","thinkrail:code-workspaces"]},{"id":"duplicate_prevention","question":"Duplicate prevention","support":"unsupported","answer":"Ownership and dispatch, duplicate_prevention: bounded v0.3.2 inspection (server, workspaces, delegation code) found no such dispatch construct; single-owner product.","evidenceIds":["thinkrail:code-nouser","thinkrail:code-workspaces"]},{"id":"ownership_enforcement","question":"Ownership enforcement","support":"unsupported","answer":"Ownership and dispatch, ownership_enforcement: bounded v0.3.2 inspection (server, workspaces, delegation code) found no such dispatch construct; single-owner product.","evidenceIds":["thinkrail:code-nouser","thinkrail:code-workspaces"]}],"limitations":["No queue, claim, routing, duplicate-prevention or ownership-enforcement construct exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:code-nouser","thinkrail:code-workspaces","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-03","verificationStatus":"agent-cross-checked","answer":"ThinkRail-bundled pi-subagents and pi-delegation give every parent session Agent and get_subagent_result tools over isolated child sessions, with per-session model and effort choice, live progress and retained outcomes in Resources. Delegation is pi-only with no cross-harness teams; child messaging detail and auth are undescribed, and follow-up is re-reading, not reopening.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"roles","question":"Roles","support":"supported","answer":"Parent sessions delegate to isolated child sessions in the foreground, in parallel or in the background.","evidenceIds":["thinkrail:goal","thinkrail:arch"]},{"id":"model_harness_effort","question":"Model harness effort","support":"supported","answer":"Each session picks its own model and reasoning effort (for example Claude Sonnet with High effort in the documented UI).","evidenceIds":["thinkrail:blog-gui","thinkrail:site-home"]},{"id":"messages","question":"Messages","support":"supported","answer":"Parents and children exchange work and results through the delegation tools; message-level inspection detail is undescribed.","evidenceIds":["thinkrail:arch","thinkrail:goal"]},{"id":"results_return","question":"Results return","support":"supported","answer":"Children return results via get_subagent_result and finished outcomes persist in resource history.","evidenceIds":["thinkrail:arch","thinkrail:goal"]},{"id":"cross_harness","question":"Cross harness","support":"unsupported","answer":"Delegation runs on pi only: pi is the only engine with no second runtime, so cross-harness teams are excluded.","evidenceIds":["thinkrail:goal"]},{"id":"orchestration_owner","question":"Orchestration owner","support":"supported","answer":"Orchestration is product-owned: ThinkRail bundles the portable pi-subagents and pi-delegation packages into every parent session from its server registry.","evidenceIds":["thinkrail:arch"]},{"id":"activation","question":"Activation","support":"supported","answer":"Delegation tools are bundled into every parent session with no activation flag or experimental gate described.","evidenceIds":["thinkrail:arch"]},{"id":"authentication","question":"Authentication","support":"unsupported","answer":"Inspectable delegation and communication, authentication: in-process sessions with no accounts; bounded v0.3.2 inspection found no delegation auth surface.","evidenceIds":["thinkrail:goal","thinkrail:code-nouser"]},{"id":"live_progress","question":"Live progress","support":"supported","answer":"The Resources popup follows background commands and subagents while they run, per chat.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal"]},{"id":"retained_results","question":"Retained results","support":"supported","answer":"Finished background work keeps outcomes and command log tails for the workspace lifetime, across host restarts.","evidenceIds":["thinkrail:goal"]},{"id":"followup","question":"Followup","support":"partial","answer":"Inspectable delegation and communication, followup: finished subagent reports can be re-read via get_subagent_result with outcomes retained in resource history; reopening a completed child as a new run is undescribed.","evidenceIds":["thinkrail:code-delegation","thinkrail:goal"]},{"id":"invocation","question":"Invocation","support":"supported","answer":"Documented invocation is delegating to subagents plus natural-language side-workspace requests; bundled workflow skills add project setup, brainstorming and ship-PR flows.","evidenceIds":["thinkrail:readme","thinkrail:goal"]}],"limitations":["Delegation is pi-only with no cross-harness teams; messaging detail, auth and reopening are undescribed or absent."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:goal","thinkrail:arch","thinkrail:readme","thinkrail:blog-gui","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-04","verificationStatus":"agent-cross-checked","answer":"Unattended triggers do not exist: bounded v0.3.2 inspection of packages/server, apps/* and packages/* for schedul|cron|trigger|recur|setInterval-based scheduling found only UI polling, update checks and request replay. No schedules, event triggers, recurring tasks or completion-driven runs exist.","availability":"unknown","delivery":"unknown","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"schedules","question":"Schedules","support":"unsupported","answer":"Unattended triggers, schedules: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"events","question":"Events","support":"unsupported","answer":"Unattended triggers, events: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"recurring_tasks","question":"Recurring tasks","support":"unsupported","answer":"Unattended triggers, recurring_tasks: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"completion_conditions","question":"Completion conditions","support":"unsupported","answer":"Unattended triggers, completion_conditions: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"scheduler_location","question":"Scheduler location","support":"unsupported","answer":"Unattended triggers, scheduler_location: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"overlaps","question":"Overlaps","support":"unsupported","answer":"Unattended triggers, overlaps: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"retries","question":"Retries","support":"unsupported","answer":"Unattended triggers, retries: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]},{"id":"client_independence","question":"Client independence","support":"unsupported","answer":"Unattended triggers, client_independence: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2) found no scheduler or trigger mechanism; the only timer-driven code is polling, update checks and request replay.","evidenceIds":["thinkrail:code-nosched"]}],"limitations":["No scheduler, trigger, recurrence or completion-condition mechanism exists in the pinned release."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:code-nosched"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-05","verificationStatus":"agent-cross-checked","answer":"Running turns accept steering and queued follow-ups; background commands and subagents can be watched, inspected and stopped from Resources. MCP data-changing calls and structured agent questions surface as pending decisions with allow/deny control, and history persists. Pause, resume, escalation and terminal-side intervention do not exist; errors surface as toasts.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"pause","question":"Pause","support":"unsupported","answer":"Intervention and attention, pause: bounded v0.3.2 inspection found no run-pause mechanism (terminal resume and request replay only).","evidenceIds":["thinkrail:code-terminal"]},{"id":"stop","question":"Stop","support":"supported","answer":"Resources watches, inspects and stops background commands and subagents; stopping the main turn itself is undescribed.","evidenceIds":["thinkrail:goal"]},{"id":"resume","question":"Resume","support":"unsupported","answer":"Intervention and attention, resume: bounded v0.3.2 inspection found no run-resume mechanism.","evidenceIds":["thinkrail:code-terminal"]},{"id":"steer","question":"Steer","support":"supported","answer":"Steer a running turn or queue a follow-up with no waiting for the agent to finish.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"notifications","question":"Notifications","support":"supported","answer":"Desktop notifications plus in-app waiting markers (palette urgency list) flag chats needing the user; escalation paths are undescribed.","evidenceIds":["thinkrail:readme","thinkrail:blog-031"]},{"id":"pending_decisions","question":"Pending decisions","support":"supported","answer":"MCP data-changing calls confirm on the tool card and the agent asks structured multiple-choice questions in the chat instead of guessing.","evidenceIds":["thinkrail:blog-020","thinkrail:readme"]},{"id":"escalation","question":"Escalation","support":"unsupported","answer":"Intervention and attention, escalation: bounded v0.3.2 inspection found no escalation behaviour.","evidenceIds":["thinkrail:code-errors"]},{"id":"visible_errors","question":"Visible errors","support":"partial","answer":"Intervention and attention, visible_errors: user-facing error toasts exist in the transcript UI; silent waits and systematic error surfacing are undescribed.","evidenceIds":["thinkrail:code-errors"]},{"id":"chat_terminal_parity","question":"Chat terminal parity","support":"unsupported","answer":"Intervention and attention, chat_terminal_parity: the MCP confirm path fails closed with no UI attached, so terminal-side intervention parity does not exist.","evidenceIds":["thinkrail:code-mcp"]},{"id":"retained_history","question":"Retained history","support":"supported","answer":"Conversations reopen from history and resource outcomes persist across host restarts.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal"]}],"limitations":["No pause, resume, escalation or terminal-side intervention exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:code-errors","thinkrail:code-mcp","thinkrail:code-terminal","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-06","verificationStatus":"agent-cross-checked","answer":"The Projects panel lists workspaces across projects with settled states, attention markers and per-branch PR status; no parent/child, dependency or workload views exist and no fleet fixture was exercised. Navigation errors cannot be determined without running the product.","availability":"unknown","delivery":"unknown","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"fleet_fixture","question":"Fleet fixture","support":"unsupported","answer":"Fleet and epic management UI, fleet_fixture: no multi-epic fixture was exercised in this docs-and-code pass.","evidenceIds":["thinkrail:blog-gui","thinkrail:code-workspaces"]},{"id":"parent_child","question":"Parent child","support":"unsupported","answer":"Fleet and epic management UI, parent_child: bounded v0.3.2 inspection (ProjectTree, workspaces) found no parent/child work relationships to display.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"dependencies","question":"Dependencies","support":"unsupported","answer":"Fleet and epic management UI, dependencies: bounded v0.3.2 inspection found no dependency model to display.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"attention","question":"Attention","support":"partial","answer":"Fleet and epic management UI, attention: per-session unread holds, palette urgency ordering and PR check/decision display mark attention needs; a unified attention view is undescribed.","evidenceIds":["thinkrail:code-notify","thinkrail:blog-031","thinkrail:blog-030"]},{"id":"history","question":"History","support":"partial","answer":"Fleet and epic management UI, history: reopenable conversations and workspace-lifetime resource history exist; fleet-level history views are undescribed.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"workload","question":"Workload","support":"unsupported","answer":"Fleet and epic management UI, workload: bounded v0.3.2 inspection found no workload view.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"navigation_errors","question":"Navigation errors","support":"unknown","answer":"Fleet and epic management UI, navigation_errors: navigation steps and errors require interacting with the product and cannot be determined from sources or code; the catalog runs no hands-on tests.","evidenceIds":[]},{"id":"fixture_mode","question":"Fixture mode","support":"unsupported","answer":"Fleet and epic management UI, fixture_mode: no fixture was exercised in this docs-and-code pass.","evidenceIds":["thinkrail:blog-gui","thinkrail:code-workspaces"]}],"limitations":["No parent/child, dependency or workload views exist; no fleet fixture was exercised. Navigation errors need interaction and stay unknown."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:code-notify","thinkrail:code-workspaces"]},{"productId":"thinkrail","claimId":"thinkrail:COORD-07","verificationStatus":"agent-cross-checked","answer":"Quick scratch chats grow into workspace work via Continue-in-workspace handoff, and plain-language side-workspace requests configure delegation; per-session model and effort plus mid-run steering adapt execution live. Bundled workflow skills exist without a mandatory preset gate. Roles during work and retained relationships are only partly described.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"quick_task","question":"Quick task","support":"supported","answer":"Chats without a project and the Default workspace take quick interactive work with no ceremony.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"growing_epic","question":"Growing epic","support":"supported","answer":"A scratch chat grows into workspace work when it turns real: the agent writes a handoff summary that starts the new workspace chat; side workspaces extend open projects.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"presets","question":"Presets","support":"supported","answer":"Bundled workflow skills cover project setup, design brainstorming and shipping a PR with an always-on routing rule; no mandatory workflow or preset selection was described.","evidenceIds":["thinkrail:goal","thinkrail:arch"]},{"id":"natural_language","question":"Natural language","support":"supported","answer":"Asking for work in a side workspace configures and starts it in plain language.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"agent_configuration","question":"Agent configuration","support":"supported","answer":"Per-session model and reasoning-effort choice plus per-host pi config and environment variables adapt execution.","evidenceIds":["thinkrail:blog-gui","thinkrail:readme","thinkrail:goal"]},{"id":"in_run_changes","question":"In run changes","support":"supported","answer":"Steering and queued follow-ups change execution while it runs.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"live_roles","question":"Live roles","support":"supported","answer":"Resources shows running subagents and background commands with their chats; role labelling during work is undescribed.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal"]},{"id":"retained_relationships","question":"Retained relationships","support":"supported","answer":"Finished delegation outcomes persist in resource history; retained role/relationship graphs are undescribed.","evidenceIds":["thinkrail:goal"]},{"id":"discoverability","question":"Discoverability","support":"supported","answer":"The first-run wizard, palette and bundled skills make the paths discoverable; coordinator invocation docs beyond delegation are undescribed.","evidenceIds":["thinkrail:blog-030","thinkrail:readme"]},{"id":"auth_friction","question":"Auth friction","support":"supported","answer":"There is no ThinkRail auth to create friction; provider credentials come from the user’s own tools.","evidenceIds":["thinkrail:goal","thinkrail:readme"]}],"limitations":["Only the cited atomic findings are established. Live role labelling, retained relationship views and coordinator docs are only partly described."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal","thinkrail:arch","thinkrail:blog-030","thinkrail:blog-gui"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-01","verificationStatus":"agent-cross-checked","answer":"Execution is local: the desktop app and the CLI host run the in-process pi engine on the user’s own machine, provisioned by the installer, with no vendor cloud, no user-server path and no resource, region or expiry concepts. State rebuilds on other surfaces over the wire, but execution does not survive the originating host.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"local","question":"Local","support":"supported","answer":"Desktop and CLI hosts run the in-process pi engine on the user’s computer; both embed the same engine host.","evidenceIds":["thinkrail:arch","thinkrail:readme","thinkrail:blog-pi"]},{"id":"byo_remote","question":"Byo remote","support":"unsupported","answer":"Laptop-independent execution, byo_remote: running the host on a user-owned server is not a product path; the architecture names remote-host dialling as later shared-client work, and installers plus code cover local machines only.","evidenceIds":["thinkrail:arch","thinkrail:readme"]},{"id":"self_hosted","question":"Self hosted","support":"supported","answer":"The whole product runs on user-controlled machines with no vendor compute; state lives under ~/.thinkrail.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:arch"]},{"id":"managed_cloud","question":"Managed cloud","support":"unsupported","answer":"No vendor cloud exists: the desktop profile is local only and ThinkRail keeps no accounts or hosted compute.","evidenceIds":["thinkrail:arch","thinkrail:goal"]},{"id":"hybrid","question":"Hybrid","support":"unknown","answer":"Laptop-independent execution, hybrid: hybrid execution modes were not established.","evidenceIds":[]},{"id":"provisioning","question":"Provisioning","support":"supported","answer":"Laptop-independent execution, provisioning: the user-run installer (install.sh/install.ps1 with stable/nightly channels) provisions the app on the local machine; no vendor provisioning applies.","evidenceIds":["thinkrail:readme"]},{"id":"payer","question":"Payer","support":"supported","answer":"The user pays with their own hardware; ThinkRail bills nothing and model spend goes to the user’s own providers.","evidenceIds":["thinkrail:goal","thinkrail:readme"]},{"id":"resources","question":"Resources","support":"unsupported","answer":"Laptop-independent execution, resources: bounded v0.3.2 inspection found no provisioned-compute resource concepts; execution is the local machine.","evidenceIds":["thinkrail:arch"]},{"id":"region","question":"Region","support":"unsupported","answer":"Laptop-independent execution, region: regions do not apply to local execution; bounded v0.3.2 inspection found no region concept.","evidenceIds":["thinkrail:arch"]},{"id":"expiry","question":"Expiry","support":"unsupported","answer":"Laptop-independent execution, expiry: bounded v0.3.2 inspection found no sandbox or session expiry; workspaces persist locally.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"client_disconnect","question":"Client disconnect","support":"partial","answer":"Laptop-independent execution, client_disconnect: client reconnect rebuilds state and repairs missed deltas, but continued execution after the originating client disconnects is undescribed.","evidenceIds":["thinkrail:code-hydrate"]},{"id":"other_device_continuation","question":"Other device continuation","support":"partial","answer":"Laptop-independent execution, other_device_continuation: a second tab or phone rebuilds the same state over the wire, but execution does not survive the host laptop sleeping and is not handed off.","evidenceIds":["thinkrail:code-hydrate","thinkrail:arch"]}],"limitations":["Local-only execution with no remote, hosted or laptop-independent operation; state follows surfaces, execution does not."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:blog-pi","thinkrail:code-hydrate","thinkrail:code-workspaces","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-02","verificationStatus":"agent-cross-checked","answer":"Isolation is git worktrees: separate directories, branches and cwds per workspace on the same machine and OS user, with env-based secret handling. No container, VM, OS-sandbox, process or network boundary exists; pi runs in-process. A worktree is file separation, not a security boundary.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"checkout","question":"Checkout","support":"supported","answer":"Each workspace is its own worktree directory (for example ~/.thinkrail/worktrees/<project>/workspace-1) with its own cwd for files, terminals and chats.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:goal"]},{"id":"branch","question":"Branch","support":"supported","answer":"Each workspace has its own branch; main stays clean until merge.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:blog-intro"]},{"id":"worktree","question":"Worktree","support":"supported","answer":"Isolation uses real git worktree functionality to create and manage the environments.","evidenceIds":["thinkrail:readme","thinkrail:site-home"]},{"id":"container","question":"Container","support":"unsupported","answer":"Workspace and process isolation, container: bounded v0.3.2 inspection found no such isolation primitive; the product isolates with git worktrees on the local machine.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"vm","question":"Vm","support":"unsupported","answer":"Workspace and process isolation, vm: bounded v0.3.2 inspection found no such isolation primitive; the product isolates with git worktrees on the local machine.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"os_sandbox","question":"Os sandbox","support":"unsupported","answer":"Workspace and process isolation, os_sandbox: bounded v0.3.2 inspection found no such isolation primitive; the product isolates with git worktrees on the local machine.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"filesystem","question":"Filesystem","support":"supported","answer":"Workspace directories separate files, diffs, terminals and chats per workspace; same-machine, same-OS-user boundaries only.","evidenceIds":["thinkrail:site-home","thinkrail:readme"]},{"id":"process","question":"Process","support":"unsupported","answer":"Workspace and process isolation, process: pi runs in-process with the host; bounded v0.3.2 inspection found no process boundary.","evidenceIds":["thinkrail:arch"]},{"id":"network","question":"Network","support":"unsupported","answer":"Workspace and process isolation, network: bounded v0.3.2 inspection found no network boundary besides the loopback-default host bind.","evidenceIds":["thinkrail:arch","thinkrail:code-routes"]},{"id":"secrets","question":"Secrets","support":"supported","answer":"Extra environment variables apply per host for agents, terminals and MCP; MCP secrets must be ${VAR} or !command with URL credentials refused.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-020"]},{"id":"code_separation","question":"Code separation","support":"partial","answer":"Workspace and process isolation, code_separation: separate worktree directories, branches and cwds separate concurrent changes; same OS user and process, so not a security boundary.","evidenceIds":["thinkrail:site-home","thinkrail:readme"]},{"id":"security_boundary","question":"Security boundary","support":"unsupported","answer":"Workspace and process isolation, security_boundary: a worktree separates files and is not a security sandbox; no hostile-containment evidence exists.","evidenceIds":["thinkrail:site-home"]}],"limitations":["File separation only: same machine, user and process; no security boundary is claimed."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-intro","thinkrail:code-routes","thinkrail:code-workspaces","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-03","verificationStatus":"agent-cross-checked","answer":"State reconstructs from host reads on reload, second tab, phone or host restart, with request replay and delta repair on reconnect; transcripts persist on disk. Disconnect, crash and multi-day behaviour on one machine are partly established. Expiry, duplicates handling and repair flows do not exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"client_disconnect","question":"Client disconnect","support":"partial","answer":"Recovery, expiry and continuity, client_disconnect: reconnect rebuilds state and repairs missed request deltas; in-flight run continuity across disconnect is undescribed.","evidenceIds":["thinkrail:code-hydrate"]},{"id":"worker_crash","question":"Worker crash","support":"partial","answer":"Recovery, expiry and continuity, worker_crash: transcripts persist (chat history plus pi on-disk sessions unioned into session.list); automatic worker recovery is undescribed.","evidenceIds":["thinkrail:code-hydrate","thinkrail:blog-gui"]},{"id":"service_restart","question":"Service restart","support":"supported","answer":"Resource history (outcomes and command log tails) survives host restarts for the workspace lifetime.","evidenceIds":["thinkrail:goal"]},{"id":"expiry","question":"Expiry","support":"unsupported","answer":"Recovery, expiry and continuity, expiry: bounded v0.3.2 inspection found no sandbox or session expiry; local workspaces persist.","evidenceIds":["thinkrail:code-workspaces"]},{"id":"transcript_reload","question":"Transcript reload","support":"supported","answer":"Previous conversations reopen, rename and delete from the chat history popup.","evidenceIds":["thinkrail:blog-gui"]},{"id":"process_reconnect","question":"Process reconnect","support":"partial","answer":"Recovery, expiry and continuity, process_reconnect: the request replay cache retains in-flight requests per client and reconnect repairs missed deltas; worker-process reconnection is undescribed.","evidenceIds":["thinkrail:code-hydrate"]},{"id":"task_resume","question":"Task resume","support":"supported","answer":"Settled workspaces return the moment work resumes in them; full task resumption after compute replacement is undescribed.","evidenceIds":["thinkrail:readme"]},{"id":"state_reconstruction","question":"State reconstruction","support":"supported","answer":"Recovery, expiry and continuity, state_reconstruction: hydrate-then-stream reconstructs domain state from host reads (project/workspace/session lists plus messages) on reload, second tab, phone or host restart.","evidenceIds":["thinkrail:code-hydrate","thinkrail:arch"]},{"id":"context_loss","question":"Context loss","support":"partial","answer":"Recovery, expiry and continuity, context_loss: state rebuilds from the host on reconnect; bounded loss analysis is undescribed.","evidenceIds":["thinkrail:code-hydrate"]},{"id":"duplicate_actions","question":"Duplicate actions","support":"unsupported","answer":"Recovery, expiry and continuity, duplicate_actions: bounded v0.3.2 inspection found no duplicate-action handling; abandoned requests are reported, not deduplicated.","evidenceIds":["thinkrail:code-hydrate"]},{"id":"manual_repair","question":"Manual repair","support":"unsupported","answer":"Recovery, expiry and continuity, manual_repair: bounded v0.3.2 inspection found no repair flows.","evidenceIds":["thinkrail:code-nosched"]},{"id":"multi_day_continuity","question":"Multi day continuity","support":"partial","answer":"Recovery, expiry and continuity, multi_day_continuity: local disk persistence plus restart rebuilds carry multi-day epics on the same machine; compute-replacement migration is undescribed.","evidenceIds":["thinkrail:code-hydrate","thinkrail:readme"]}],"limitations":["Continuity is same-machine persistence plus state rebuild; crash recovery, duplicates and repair are undescribed or absent."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-gui","thinkrail:code-hydrate","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-04","verificationStatus":"agent-cross-checked","answer":"The only environment mechanism is per-host environment-variable injection for agents, terminals and MCP servers. Dependency setup, caches, snapshots, services, ports, duplication, collisions, remote setup and automatic repair do not exist in the product.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"dependencies","question":"Dependencies","support":"unsupported","answer":"Development environment reliability, dependencies: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"caches","question":"Caches","support":"unsupported","answer":"Development environment reliability, caches: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"snapshots","question":"Snapshots","support":"unsupported","answer":"Development environment reliability, snapshots: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"services","question":"Services","support":"unsupported","answer":"Development environment reliability, services: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"ports","question":"Ports","support":"unsupported","answer":"Development environment reliability, ports: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"secrets","question":"Secrets","support":"supported","answer":"Settings Environment sets extra environment variables for the agent, terminals and MCP servers, applied per host on next start.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"duplicate_installs","question":"Duplicate installs","support":"unsupported","answer":"Development environment reliability, duplicate_installs: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"collisions","question":"Collisions","support":"unsupported","answer":"Development environment reliability, collisions: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"remote_setup","question":"Remote setup","support":"unsupported","answer":"Development environment reliability, remote_setup: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]},{"id":"automatic_repair","question":"Automatic repair","support":"unsupported","answer":"Development environment reliability, automatic_repair: bounded v0.3.2 inspection (server, terminal, installers) found no such environment management; the host only runs user terminals plus a free-port pick for its own listen port.","evidenceIds":["thinkrail:readme"]}],"limitations":["Environment support is env injection only; all other reliability mechanisms are absent."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-05","verificationStatus":"agent-cross-checked","answer":"Limits and failure handling do not exist: bounded v0.3.2 inspection of the server found only model maxTokens passthrough and an internal session-shutdown budget. No time, turn, token or spend limits, timeouts, retries or provider-failure budgets exist. Token and cost displays are visibility, not enforcement.","availability":"unknown","delivery":"unknown","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"time_limits","question":"Time limits","support":"unsupported","answer":"Limits and failure handling, time_limits: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"turn_limits","question":"Turn limits","support":"unsupported","answer":"Limits and failure handling, turn_limits: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"token_limits","question":"Token limits","support":"unsupported","answer":"Limits and failure handling, token_limits: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"spend_limits","question":"Spend limits","support":"unsupported","answer":"Limits and failure handling, spend_limits: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"timeouts","question":"Timeouts","support":"unsupported","answer":"Limits and failure handling, timeouts: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"retries","question":"Retries","support":"unsupported","answer":"Limits and failure handling, retries: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"provider_failures","question":"Provider failures","support":"unsupported","answer":"Limits and failure handling, provider_failures: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]},{"id":"enforcement","question":"Enforcement","support":"unsupported","answer":"Limits and failure handling, enforcement: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server code) found no such limit or handling; only model maxTokens passthrough and an internal shutdown budget exist.","evidenceIds":["thinkrail:code-nolimits"]}],"limitations":["No limits, timeouts, retries or failure budgets exist in the pinned release."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:code-nolimits"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-06","verificationStatus":"agent-cross-checked","answer":"Turn receipts, folded tool steps, command log tails, per-chat token and cost ticks, MCP pending-confirm cards and topbar PR checks and review decisions give live status; per-chat token stats are the only statistics, and reconnects repair state. Usage export and measured responsiveness do not exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"logs","question":"Logs","support":"supported","answer":"Agent thinking and tool use display as folded batches; background commands keep command log tails in resource history.","evidenceIds":["thinkrail:blog-chat","thinkrail:goal"]},{"id":"traces","question":"Traces","support":"supported","answer":"Turns expose step lists (for example 6 steps: read, thinking, edit, bash) with tool counts and durations; full execution traces are undescribed.","evidenceIds":["thinkrail:site-home"]},{"id":"failure_reasons","question":"Failure reasons","support":"supported","answer":"Open PRs show CI checks and review decisions with Fix-with-agent next steps; worker failure reasons beyond that are undescribed.","evidenceIds":["thinkrail:blog-030"]},{"id":"usage_export","question":"Usage export","support":"unsupported","answer":"Truthful status and operational statistics, usage_export: bounded v0.3.2 inspection found no usage export; the only CSV code renders data files, not usage.","evidenceIds":["thinkrail:code-noexport"]},{"id":"task_stats","question":"Task stats","support":"supported","answer":"Each chat shows input, output, cache reads and writes, cost and context-window fullness; no cross-task aggregates exist.","evidenceIds":["thinkrail:blog-gui","thinkrail:site-home"]},{"id":"agent_stats","question":"Agent stats","support":"unknown","answer":"Truthful status and operational statistics, agent_stats: per-agent statistics were not established.","evidenceIds":[]},{"id":"project_stats","question":"Project stats","support":"unknown","answer":"Truthful status and operational statistics, project_stats: per-project statistics were not established.","evidenceIds":[]},{"id":"time_stats","question":"Time stats","support":"unknown","answer":"Truthful status and operational statistics, time_stats: time-based statistics were not established.","evidenceIds":[]},{"id":"failure_status","question":"Failure status","support":"supported","answer":"Resources distinguishes running and finished background work (a 0.3.1 fix stopped showing finished subagents as Working); systematic failure states are undescribed.","evidenceIds":["thinkrail:blog-031","thinkrail:goal"]},{"id":"approval_status","question":"Approval status","support":"supported","answer":"MCP data-changing calls wait visibly on their tool cards and the PR segment shows review decisions; blocked versus working states beyond that are undescribed.","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030"]},{"id":"reconnect_consistency","question":"Reconnect consistency","support":"partial","answer":"Truthful status and operational statistics, reconnect_consistency: reconnect repairs missed deltas and rebuilds state from host reads; board-level agreement checks after reconnect are undescribed.","evidenceIds":["thinkrail:code-hydrate"]},{"id":"performance_method","question":"Performance method","support":"unsupported","answer":"Truthful status and operational statistics, performance_method: the catalog measures none; the shown turn figures are single documented cases and analytics, and bounded inspection found no measurement instrumentation.","evidenceIds":["thinkrail:code-noperf","thinkrail:site-home"]},{"id":"responsiveness","question":"Responsiveness","support":"unsupported","answer":"Truthful status and operational statistics, responsiveness: bounded v0.3.2 inspection found no interaction-timing instrumentation; no timings are claimed.","evidenceIds":["thinkrail:code-noperf"]}],"limitations":["Statistics stop at per-chat tokens and cost; no export, aggregates or measured timings exist."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-chat","thinkrail:blog-gui","thinkrail:code-hydrate","thinkrail:code-noexport","thinkrail:code-noperf","thinkrail:goal","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-07","verificationStatus":"agent-cross-checked","answer":"Every chat ticks pi-reported tokens (input, output, cache reads and writes) and cost live; JetBrains AI quota snapshots on a 30-second default cadence with a 20-second PR-check refresh. Child, epic and aggregate costs, reconciliation, alerts, export and drill-down do not exist, and unknown subscription marginal cost is never rendered as zero.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"task_cost","question":"Task cost","support":"supported","answer":"Turns and chats show pi-reported token and cost figures live in the header (for example Done 5s, 25.9k tok, $0.17).","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"session_cost","question":"Session cost","support":"supported","answer":"Per-chat token usage (input, output, cache reads and writes) and cost display per session.","evidenceIds":["thinkrail:blog-gui"]},{"id":"child_cost","question":"Child cost","support":"unsupported","answer":"Per-task API and compute cost, child_cost: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"epic_cost","question":"Epic cost","support":"unsupported","answer":"Per-task API and compute cost, epic_cost: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"harness_aggregation","question":"Harness aggregation","support":"unsupported","answer":"Per-task API and compute cost, harness_aggregation: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"billed_vs_estimated","question":"Billed vs estimated","support":"unsupported","answer":"Per-task API and compute cost, billed_vs_estimated: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"tokens","question":"Tokens","support":"supported","answer":"Input, output, cache reads and writes plus context-window fullness display per chat.","evidenceIds":["thinkrail:blog-gui"]},{"id":"subscription_allowance","question":"Subscription allowance","support":"supported","answer":"The central integration reports the JetBrains AI recurring AI-credit quota (remaining plus total) on a configured cadence.","evidenceIds":["thinkrail:central"]},{"id":"provider_reconciliation","question":"Provider reconciliation","support":"unsupported","answer":"Per-task API and compute cost, provider_reconciliation: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"compute_cost","question":"Compute cost","support":"unsupported","answer":"Per-task API and compute cost, compute_cost: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"refresh_delay","question":"Refresh delay","support":"supported","answer":"Quota snapshots refresh on a 1–3600 second cadence (30 seconds default); PR checks re-read every 20 seconds.","evidenceIds":["thinkrail:central","thinkrail:blog-030"]},{"id":"alerts","question":"Alerts","support":"unsupported","answer":"Per-task API and compute cost, alerts: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"export","question":"Export","support":"unsupported","answer":"Per-task API and compute cost, export: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]},{"id":"drilldown","question":"Drilldown","support":"unsupported","answer":"Per-task API and compute cost, drilldown: bounded v0.3.2 inspection found no such aggregation, reconciliation, alert, export or compute-billing code; cost display is per-chat pi-reported tokens and JetBrains AI quota.","evidenceIds":["thinkrail:goal","thinkrail:central"]}],"limitations":["Cost visibility is per-chat tokens plus quota snapshots only; no aggregation, reconciliation, alerts or export exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:site-home","thinkrail:goal","thinkrail:blog-gui","thinkrail:central","thinkrail:blog-030"]},{"productId":"thinkrail","claimId":"thinkrail:RUN-08","verificationStatus":"agent-cross-checked","answer":"Parallel sessions and workspaces run with no declared concurrency limits, queues or resource awareness; the only controls are session ownership and stopping background commands or subagents. No bounded load behaviour was established in code.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"concurrency","question":"Concurrency","support":"supported","answer":"Concurrent sessions per workspace and parallel workspaces are documented with no stated limits; safe-capacity behaviour is undescribed.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"queues","question":"Queues","support":"unsupported","answer":"Compute-aware scheduling and verification, queues: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"cpu_ram","question":"Cpu ram","support":"unsupported","answer":"Compute-aware scheduling and verification, cpu_ram: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"backpressure","question":"Backpressure","support":"unsupported","answer":"Compute-aware scheduling and verification, backpressure: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"host_awareness","question":"Host awareness","support":"unsupported","answer":"Compute-aware scheduling and verification, host_awareness: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"check_reuse","question":"Check reuse","support":"unsupported","answer":"Compute-aware scheduling and verification, check_reuse: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"check_deduplication","question":"Check deduplication","support":"unsupported","answer":"Compute-aware scheduling and verification, check_deduplication: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"bounded_tests","question":"Bounded tests","support":"unsupported","answer":"Compute-aware scheduling and verification, bounded_tests: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"cancellation","question":"Cancellation","support":"supported","answer":"Background commands and subagents can be stopped from the Resources view; queue or run cancellation beyond that is undescribed.","evidenceIds":["thinkrail:goal"]},{"id":"fairness","question":"Fairness","support":"unsupported","answer":"Compute-aware scheduling and verification, fairness: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"recovery","question":"Recovery","support":"unsupported","answer":"Compute-aware scheduling and verification, recovery: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]},{"id":"shared_limits","question":"Shared limits","support":"unsupported","answer":"Compute-aware scheduling and verification, shared_limits: bounded v0.3.2 inspection (JetBrains/thinkrail@v0.3.2: server, delegation, background commands) found no such scheduling construct.","evidenceIds":["thinkrail:code-bgcmd","thinkrail:code-delegation"]}],"limitations":["No limits, queues, resource awareness or bounded testing exist."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"productId":"thinkrail","claimId":"thinkrail:TEAM-01","verificationStatus":"agent-cross-checked","answer":"Live human collaboration does not exist: ThinkRail is a single-owner local product whose auth model (Tailscale ACLs plus an owner field, no login UI) has no second user, shared prompting, presence, ordering, attribution or permission constructs. The launch post’s Git-and-GitHub line does not establish co-steering.","availability":"unknown","delivery":"unknown","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"visibility","question":"Visibility","support":"unsupported","answer":"Live human collaboration, visibility: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"discussion","question":"Discussion","support":"unsupported","answer":"Live human collaboration, discussion: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"comments","question":"Comments","support":"unsupported","answer":"Live human collaboration, comments: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"presence","question":"Presence","support":"unsupported","answer":"Live human collaboration, presence: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"coprompting","question":"Coprompting","support":"unsupported","answer":"Live human collaboration, coprompting: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"ordering","question":"Ordering","support":"unsupported","answer":"Live human collaboration, ordering: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"conflicts","question":"Conflicts","support":"unsupported","answer":"Live human collaboration, conflicts: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"attribution","question":"Attribution","support":"unsupported","answer":"Live human collaboration, attribution: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"permissions","question":"Permissions","support":"unsupported","answer":"Live human collaboration, permissions: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"plan_restrictions","question":"Plan restrictions","support":"unsupported","answer":"Live human collaboration, plan_restrictions: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]},{"id":"owner_online","question":"Owner online","support":"unsupported","answer":"Live human collaboration, owner_online: bounded v0.3.2 inspection found no second-user concept; auth is Tailscale ACLs plus a single owner field, so co-steering cannot exist.","evidenceIds":["thinkrail:code-nouser","thinkrail:arch"]}],"limitations":["Single-owner product: no multi-user construct exists in docs or code."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:code-nouser","thinkrail:goal"]},{"productId":"thinkrail","claimId":"thinkrail:TEAM-02","verificationStatus":"agent-cross-checked","answer":"Roles and access boundaries do not exist: no organisations, project or task roles, membership, SSO, provisioning, revocation or plan scoping, because there are no accounts. Host reach is a network (Tailscale) matter, and SSO is excluded by the no-login-UI non-goal.","availability":"unknown","delivery":"unknown","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"organization_roles","question":"Organization roles","support":"unsupported","answer":"Roles and access boundaries, organization_roles: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"project_roles","question":"Project roles","support":"unsupported","answer":"Roles and access boundaries, project_roles: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"task_roles","question":"Task roles","support":"unsupported","answer":"Roles and access boundaries, task_roles: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"membership","question":"Membership","support":"unsupported","answer":"Roles and access boundaries, membership: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"sso","question":"Sso","support":"unsupported","answer":"Enterprise SSO is excluded by decision: ThinkRail accounts and any login UI are non-goals.","evidenceIds":["thinkrail:goal"]},{"id":"provisioning","question":"Provisioning","support":"unsupported","answer":"Roles and access boundaries, provisioning: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"unauthorized_access","question":"Unauthorized access","support":"unsupported","answer":"Roles and access boundaries, unauthorized_access: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"revocation","question":"Revocation","support":"unsupported","answer":"Roles and access boundaries, revocation: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]},{"id":"plan_scope","question":"Plan scope","support":"unsupported","answer":"Roles and access boundaries, plan_scope: bounded v0.3.2 inspection found no such model; there are no accounts, so no roles, membership or provisioning exist.","evidenceIds":["thinkrail:code-nouser"]}],"limitations":["No role, membership, SSO or provisioning construct exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:code-nouser","thinkrail:goal"]},{"productId":"thinkrail","claimId":"thinkrail:TEAM-03","verificationStatus":"agent-cross-checked","answer":"MCP data-changing calls confirm in the chat with Deny, Allow once, Allow in this chat or Always allow (per project, lapsing on entry change); repo resources and repo MCP entries stay off until explicit grants; shell-credential hygiene is host-enforced. The human user approves merges. Shell-command and network approvals are not a product surface, and no tunnels exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"command","question":"Command","support":"unsupported","answer":"Approvals and temporary access, command: the product adds no shell-command approval of its own; shell behaviour is the underlying pi engine’s and no approval hook exists in ThinkRail server or terminal code.","evidenceIds":["thinkrail:code-terminal"]},{"id":"tool","question":"Tool","support":"supported","answer":"Data-changing MCP tool calls confirm on the call with the arguments listed.","evidenceIds":["thinkrail:blog-020","thinkrail:goal"]},{"id":"network","question":"Network","support":"unsupported","answer":"Approvals and temporary access, network: bounded v0.3.2 inspection (web-access extension, server) found no network approval gate.","evidenceIds":["thinkrail:code-terminal"]},{"id":"secret","question":"Secret","support":"supported","answer":"MCP secrets must be ${VAR} or !command, pasted URL credentials are refused, and the model key never reaches the browser.","evidenceIds":["thinkrail:blog-020","thinkrail:blog-031"]},{"id":"delivery","question":"Delivery","support":"supported","answer":"Publish, merge, reopen and branch-delete actions are user-operated from the topbar; the agent drafts but does not merge.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]},{"id":"approver_identity","question":"Approver identity","support":"supported","answer":"The human user in the chat approves; no second approver or role exists in this single-user product.","evidenceIds":["thinkrail:blog-020","thinkrail:goal"]},{"id":"lifetime","question":"Lifetime","support":"supported","answer":"Grants scope to once, this chat, or every chat of the project, and lapse when the server command or URL changes.","evidenceIds":["thinkrail:blog-020"]},{"id":"allow","question":"Allow","support":"supported","answer":"Allow once, Allow in this chat and Always allow are offered on the call.","evidenceIds":["thinkrail:blog-020"]},{"id":"deny","question":"Deny","support":"supported","answer":"Deny is offered on every data-changing call.","evidenceIds":["thinkrail:blog-020"]},{"id":"revoke","question":"Revoke","support":"supported","answer":"Grants lapse on entry change; packages, skills and servers switch off per chat or project from Settings and popups.","evidenceIds":["thinkrail:blog-020","thinkrail:readme","thinkrail:blog-pi"]},{"id":"tunnels","question":"Tunnels","support":"unsupported","answer":"Approvals and temporary access, tunnels: bounded v0.3.2 inspection found no temporary tunnels or shared access.","evidenceIds":["thinkrail:code-routes"]},{"id":"defaults","question":"Defaults","support":"supported","answer":"Repo-defined MCP servers and project resources default to off until a per-project, per-entry grant.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"safer_modes","question":"Safer modes","support":"supported","answer":"Trust grants plus read-only presets (for example Linear read-only) are the safer paths; a general safer-mode policy is undescribed.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"enforcement","question":"Enforcement","support":"supported","answer":"Enforcement is product-side: credential-in-URL refusal, grants stored on the project record (never in the repo), and user-operated delivery actions.","evidenceIds":["thinkrail:blog-020","thinkrail:goal"]}],"limitations":["No product-owned shell or network approval and no tunnels exist; MCP, trust-grant and delivery approvals do."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-031","thinkrail:code-routes","thinkrail:code-terminal","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:TEAM-04","verificationStatus":"agent-cross-checked","answer":"Turn receipts, resource history, anchored review comments and PR states persist across sessions and host restarts; Settled workspaces and Trash give retention shape. History alteration is delete-only, export and integrity models do not exist, and no audit claim is made.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"actions","question":"Actions","support":"supported","answer":"Turns end with file-change receipts and step lists; background outcomes and log tails persist per workspace.","evidenceIds":["thinkrail:blog-020","thinkrail:goal","thinkrail:site-home"]},{"id":"approvals","question":"Approvals","support":"supported","answer":"MCP grants live on the project record and PR review decisions display in the topbar; a unified approval log is undescribed.","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030"]},{"id":"edits","question":"Edits","support":"supported","answer":"Plan edits, renames and Keep/Revert hunk actions persist; a full edit history is undescribed.","evidenceIds":["thinkrail:goal","thinkrail:blog-020"]},{"id":"discussion","question":"Discussion","support":"supported","answer":"Anchored comments and chat transcripts persist with the work.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"decisions","question":"Decisions","support":"supported","answer":"Review decisions and merge states display on the PR segment; decision links beyond that are undescribed.","evidenceIds":["thinkrail:blog-030"]},{"id":"cross_user_persistence","question":"Cross user persistence","support":"unsupported","answer":"Decision and activity history, cross_user_persistence: single-owner product; bounded v0.3.2 inspection found no cross-user history.","evidenceIds":["thinkrail:code-nouser"]},{"id":"cross_session_persistence","question":"Cross session persistence","support":"supported","answer":"History and resource outcomes persist across host restarts and reopen in later sessions.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"export","question":"Export","support":"unsupported","answer":"Decision and activity history, export: bounded v0.3.2 inspection found no history export.","evidenceIds":["thinkrail:code-noexport"]},{"id":"mutability","question":"Mutability","support":"partial","answer":"Decision and activity history, mutability: the only alteration path found is delete-to-Trash (chats) plus Keep/Revert on diffs; no history-edit API exists.","evidenceIds":["thinkrail:readme"]},{"id":"retention","question":"Retention","support":"supported","answer":"Workspace-lifetime resource history, Settled shelf after a quiet week, and Trash for deleted chats give retention shape; a retention policy is undescribed.","evidenceIds":["thinkrail:goal","thinkrail:readme"]},{"id":"integrity","question":"Integrity","support":"unsupported","answer":"Decision and activity history, integrity: bounded v0.3.2 inspection found no retention or integrity model; the word audit is not used.","evidenceIds":["thinkrail:code-noaudit"]}],"limitations":["Retention shape only; no export or integrity model exists and no audit claim is made."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-gui","thinkrail:code-noaudit","thinkrail:code-noexport","thinkrail:code-nouser","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:TEAM-05","verificationStatus":"agent-cross-checked","answer":"Review is a guided loop: the palette and Review-turn button surface pending work, stacked Changes tabs with Keep/Revert/Ask-agent plus Next-unreviewed (J key in code) navigate evidence, anchored comments and Fix-with-agent request changes, and the topbar names the next shipping step. Phone viewports adapt; effort timing, missed-evidence analysis and switching costs are not measured.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"pending_reviews","question":"Pending reviews","support":"supported","answer":"Waiting chats surface in the empty palette ordered by urgency; turn receipts carry Review turn buttons and the topbar shows open PR state.","evidenceIds":["thinkrail:blog-031","thinkrail:blog-020","thinkrail:blog-030"]},{"id":"change_understanding","question":"Change understanding","support":"supported","answer":"Read-only diff tabs, rendered Markdown with source toggle, and turn summaries show what changed without reading the transcript.","evidenceIds":["thinkrail:blog-gui","thinkrail:blog-020"]},{"id":"evidence_navigation","question":"Evidence navigation","support":"supported","answer":"One stacked Changes tab per run, One-file view mode, hunk Keep/Revert/Ask agent, progress bar and Next unreviewed (J); big diffs collapse with a switch hint past 50 files.","evidenceIds":["thinkrail:blog-020"]},{"id":"comments","question":"Comments","support":"supported","answer":"The Review panel collects anchored comments on lines of files and diffs and sends them to the agent as structured context.","evidenceIds":["thinkrail:goal","thinkrail:blog-gui"]},{"id":"request_changes","question":"Request changes","support":"supported","answer":"Comments resolve through chats and failing checks get a Fix with agent next step.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]},{"id":"shipping_guidance","question":"Shipping guidance","support":"supported","answer":"The topbar always shows the branch’s next step: Publish, Push, Sync, open PR, Ready for review, Merge, Reopen or Delete remote branch.","evidenceIds":["thinkrail:blog-030"]},{"id":"effort","question":"Effort","support":"unsupported","answer":"Review experience and guidance, effort: bounded v0.3.2 inspection found no review-effort measurement.","evidenceIds":["thinkrail:code-noperf"]},{"id":"missed_evidence","question":"Missed evidence","support":"unsupported","answer":"Review experience and guidance, missed_evidence: bounded v0.3.2 inspection found no missed-evidence analysis.","evidenceIds":["thinkrail:code-noperf"]},{"id":"keyboard","question":"Keyboard","support":"supported","answer":"J steps through unreviewed hunks; palette and file search have full keyboard access; complete keyboard-only review is undescribed.","evidenceIds":["thinkrail:blog-020","thinkrail:readme"]},{"id":"narrow_screen","question":"Narrow screen","support":"supported","answer":"Review experience and guidance, narrow_screen: the phone-viewport hook adapts the UI below 767px width.","evidenceIds":["thinkrail:code-viewport"]},{"id":"context_switching","question":"Context switching","support":"unsupported","answer":"Review experience and guidance, context_switching: bounded v0.3.2 inspection found no context-switching measurement.","evidenceIds":["thinkrail:code-noperf"]},{"id":"roles","question":"Roles","support":"supported","answer":"Plan steps can route to an independent reviewer; agent-role labelling in review beyond that is undescribed.","evidenceIds":["thinkrail:goal"]},{"id":"retained_context","question":"Retained context","support":"supported","answer":"Keep marks survive line shifts and lapse only when the agent re-edits the hunk; One-file and stacked views share progress.","evidenceIds":["thinkrail:blog-020"]}],"limitations":["Review effort, missed evidence and switching costs are not measured. Bulk and cross-branch review queues are judged in SHIP-06."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:code-keyboard","thinkrail:code-noperf","thinkrail:code-viewport","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:TEAM-06","verificationStatus":"agent-cross-checked","answer":"Same-user continuity is implemented: previous conversations reopen with history and sessions move between the pi CLI and the app. Second-person takeover, ownership transfer, permissions, runtime handoff and context-loss handling do not exist in this single-owner product.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"ongoing_takeover","question":"Ongoing takeover","support":"unsupported","answer":"Colleague takeover and continuity, ongoing_takeover: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"same_task","question":"Same task","support":"unsupported","answer":"Colleague takeover and continuity, same_task: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"session_history","question":"Session history","support":"supported","answer":"The chat history popup reopens, renames and deletes previous conversations with their transcripts.","evidenceIds":["thinkrail:blog-gui"]},{"id":"decisions","question":"Decisions","support":"unsupported","answer":"Colleague takeover and continuity, decisions: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"artifacts","question":"Artifacts","support":"unsupported","answer":"Colleague takeover and continuity, artifacts: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"permissions","question":"Permissions","support":"unsupported","answer":"Colleague takeover and continuity, permissions: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"runtime_context","question":"Runtime context","support":"unsupported","answer":"Colleague takeover and continuity, runtime_context: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"owner_disconnect","question":"Owner disconnect","support":"unsupported","answer":"Colleague takeover and continuity, owner_disconnect: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"ownership","question":"Ownership","support":"unsupported","answer":"Colleague takeover and continuity, ownership: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"attribution","question":"Attribution","support":"unsupported","answer":"Colleague takeover and continuity, attribution: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"context_loss","question":"Context loss","support":"unsupported","answer":"Colleague takeover and continuity, context_loss: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]},{"id":"harness_transfer","question":"Harness transfer","support":"unsupported","answer":"Colleague takeover and continuity, harness_transfer: bounded v0.3.2 inspection found no second-person, ownership-transfer or runtime-handoff constructs; single-owner product.","evidenceIds":["thinkrail:code-nouser"]}],"limitations":["Same-user session continuity only; no second-person handoff exists to evaluate."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-gui","thinkrail:blog-pi","thinkrail:code-nouser"]},{"productId":"thinkrail","claimId":"thinkrail:SHIP-01","verificationStatus":"agent-cross-checked","answer":"Diffs, documents, file previews, UI mockups, test outputs and reviewer outputs persist with the transcript and branch; per-run Changes tabs and per-hunk review carry the evidence. Screenshot capture, recordings, a cross-task gallery and prompt leakage into outputs do not exist in the pinned release.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"diffs","question":"Diffs","support":"supported","answer":"Live git diffs per branch plus per-run stacked Changes tabs with rendered Markdown and code diffs.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:blog-020"]},{"id":"documents","question":"Documents","support":"supported","answer":"Rendered Markdown documents with heading outlines and the Specs tree persist beside the code.","evidenceIds":["thinkrail:readme","thinkrail:site-home"]},{"id":"screenshots","question":"Screenshots","support":"unsupported","answer":"Retained artifacts and outputs, screenshots: bounded v0.3.2 inspection (app, server, CLI) found no such capture or gallery; the only gallery link points at the pi package registry, and renderers show message parts only.","evidenceIds":["thinkrail:code-nogallery"]},{"id":"recordings","question":"Recordings","support":"unsupported","answer":"Retained artifacts and outputs, recordings: bounded v0.3.2 inspection (app, server, CLI) found no such capture or gallery; the only gallery link points at the pi package registry, and renderers show message parts only.","evidenceIds":["thinkrail:code-nogallery"]},{"id":"previews","question":"Previews","support":"supported","answer":"File previews, comparison views and rendered before/after UI mockups display inline in chat.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"test_outputs","question":"Test outputs","support":"supported","answer":"Test results show in the transcript (for example All 17 tests pass) and persist with it; no dedicated test-output gallery exists.","evidenceIds":["thinkrail:site-home"]},{"id":"reviewer_outputs","question":"Reviewer outputs","support":"supported","answer":"Turn summaries, receipts and independent-reviewer step results persist with chats and resource history.","evidenceIds":["thinkrail:blog-020","thinkrail:goal"]},{"id":"gallery","question":"Gallery","support":"unsupported","answer":"Retained artifacts and outputs, gallery: bounded v0.3.2 inspection (app, server, CLI) found no such capture or gallery; the only gallery link points at the pi package registry, and renderers show message parts only.","evidenceIds":["thinkrail:code-nogallery"]},{"id":"task_links","question":"Task links","support":"supported","answer":"Turn receipts link runs to changed files and per-step commits link plan steps to code; a unified task graph is undescribed.","evidenceIds":["thinkrail:blog-020","thinkrail:goal"]},{"id":"revision_links","question":"Revision links","support":"supported","answer":"Changes track against origin/main with hunk-level Keep keyed to content; exact-revision approval links are judged in SHIP-04/SHIP-06.","evidenceIds":["thinkrail:blog-020","thinkrail:readme"]},{"id":"persistence","question":"Persistence","support":"supported","answer":"Reopened conversations and workspace-lifetime resource history keep artifacts usable after sessions end; no gallery exists.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal"]},{"id":"child_findings","question":"Child findings","support":"supported","answer":"Subagent outcomes and command log tails stay in resource history for the workspace lifetime.","evidenceIds":["thinkrail:goal"]},{"id":"prompt_leakage","question":"Prompt leakage","support":"unsupported","answer":"Retained artifacts and outputs, prompt_leakage: bounded v0.3.2 inspection (app, server, CLI) found no such capture or gallery; the only gallery link points at the pi package registry, and renderers show message parts only.","evidenceIds":["thinkrail:code-nogallery"]}],"limitations":["No screenshot/record capture, cross-task gallery or prompt leakage path exists."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-gui","thinkrail:code-nogallery","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:SHIP-02","verificationStatus":"agent-cross-checked","answer":"Verification is agent-driven and displayed, not product-enforced: the agent runs tests in terminals, CI checks display on the PR, and plan steps can route to an independent reviewer. Required gates, lint/type gates, failure blocking, requirement-conflict handling and configured or enforced policy do not exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"tests","question":"Tests","support":"supported","answer":"The agent runs the tests itself (for example Run the args unit test when done) in worktree-scoped terminals; no required-test gate exists.","evidenceIds":["thinkrail:site-home","thinkrail:readme"]},{"id":"lint","question":"Lint","support":"unsupported","answer":"Verification and spec gates, lint: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]},{"id":"types","question":"Types","support":"unsupported","answer":"Verification and spec gates, types: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]},{"id":"ci","question":"Ci","support":"supported","answer":"GitHub CI checks and review decisions display on the open PR with re-reads every 20 seconds; enforcement is GitHub’s, not ThinkRail’s.","evidenceIds":["thinkrail:blog-030"]},{"id":"independent_review","question":"Independent review","support":"supported","answer":"Completed plan steps can be reviewed by an independent reviewer before their changes commit.","evidenceIds":["thinkrail:goal"]},{"id":"spec_checks","question":"Spec checks","support":"unsupported","answer":"Verification and spec gates, spec_checks: bounded v0.3.2 inspection (reviews code, spec-graph) found no persistent-spec conformance checks.","evidenceIds":["thinkrail:code-nogates","thinkrail:code-spec"]},{"id":"required_checks","question":"Required checks","support":"unsupported","answer":"Verification and spec gates, required_checks: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]},{"id":"failure_blocking","question":"Failure blocking","support":"unsupported","answer":"Verification and spec gates, failure_blocking: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]},{"id":"requirement_conflicts","question":"Requirement conflicts","support":"unsupported","answer":"Verification and spec gates, requirement_conflicts: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]},{"id":"configured_policy","question":"Configured policy","support":"unsupported","answer":"Verification and spec gates, configured_policy: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]},{"id":"enforced_policy","question":"Enforced policy","support":"unsupported","answer":"Verification and spec gates, enforced_policy: bounded v0.3.2 inspection (todos, reviews, pr code) found no such gate or policy; verification is agent-driven and displayed, never product-enforced.","evidenceIds":["thinkrail:code-nogates"]}],"limitations":["ThinkRail configures and enforces no verification gates of its own."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:code-nogates","thinkrail:code-spec","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:SHIP-03","verificationStatus":"agent-cross-checked","answer":"The full GitHub loop is integrated in the topbar: own branches and worktrees, per-step commits, PR open/update through gh with templates or agent drafts, CI response with Fix-with-agent, rebase preview, and merge/reopen/branch-delete actions — all present in the pinned pr/github modules. PR-comment round-trips and GitLab review actions are the limits.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"branches","question":"Branches","support":"supported","answer":"Every workspace owns its branch; the topbar tracks it against origin with ahead/behind state.","evidenceIds":["thinkrail:site-home","thinkrail:readme","thinkrail:blog-030"]},{"id":"worktrees","question":"Worktrees","support":"supported","answer":"Work happens in git worktrees with publish, push and sync from the topbar.","evidenceIds":["thinkrail:readme","thinkrail:blog-030"]},{"id":"commits","question":"Commits","support":"supported","answer":"Completed plan steps commit on their own when provably theirs; PR descriptions can come from the plan, commits, template or agent draft.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]},{"id":"pull_requests","question":"Pull requests","support":"supported","answer":"Open or update the GitHub PR through gh from the plan or topbar (GitLab: prefilled MR page); drafts supported with Ready-for-review promotion.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]},{"id":"comments","question":"Comments","support":"supported","answer":"Anchored local comments send structured context to chats; responding to forge PR review comments is undescribed.","evidenceIds":["thinkrail:goal"]},{"id":"ci_response","question":"Ci response","support":"supported","answer":"Open PRs show checks and review decisions with Fix with agent on failure and diverged-branch integration with the agent.","evidenceIds":["thinkrail:blog-030","thinkrail:goal"]},{"id":"rebase","question":"Rebase","support":"supported","answer":"Sync previews the git pull --rebase it would run and never force-pushes.","evidenceIds":["thinkrail:blog-030"]},{"id":"conflicts","question":"Conflicts","support":"supported","answer":"Diverged branches integrate with the agent; conflict detection detail is undescribed.","evidenceIds":["thinkrail:blog-030"]},{"id":"product_state","question":"Product state","support":"supported","answer":"The topbar owns Remote/PR segments, dialogs and merge actions through gh — an integrated workflow, not bare git commands.","evidenceIds":["thinkrail:goal","thinkrail:blog-030"]}],"limitations":["GitLab is limited to a prefilled MR page; forge PR-comment round-trips are undescribed in code."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-030","thinkrail:code-pr","thinkrail:goal","thinkrail:readme","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:SHIP-04","verificationStatus":"agent-cross-checked","answer":"The human user approves (Ready for review), merges (repo-allowed methods, remembered per project), reopens and deletes remote branches from the topbar, governed by GitHub merge state. Release and deploy authority do not exist in the product.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"approve","question":"Approve","support":"supported","answer":"Draft PRs promote through user-operated Ready for review; merge follows GitHub merge state, not vote counting.","evidenceIds":["thinkrail:blog-030"]},{"id":"merge","question":"Merge","support":"supported","answer":"Merge runs from the dialog with only the repo’s allowed methods; merged or closed PRs offer Reopen and Delete remote branch.","evidenceIds":["thinkrail:blog-030"]},{"id":"release","question":"Release","support":"unsupported","answer":"Merge and deployment authority, release: bounded v0.3.2 inspection found no release or deployment authority; the only release machinery is the app’s self-update.","evidenceIds":["thinkrail:code-args"]},{"id":"deploy","question":"Deploy","support":"unsupported","answer":"Merge and deployment authority, deploy: bounded v0.3.2 inspection found no release or deployment authority; the only release machinery is the app’s self-update.","evidenceIds":["thinkrail:code-args"]},{"id":"exact_revision","question":"Exact revision","support":"supported","answer":"Merge goes by the revision GitHub deems mergeable; explicit exact-revision approval records are undescribed.","evidenceIds":["thinkrail:blog-030"]},{"id":"authority_enforcement","question":"Authority enforcement","support":"supported","answer":"The boundary is user-operated dialogs plus GitHub merge state; the agent drafts and fixes but does not merge, while running with the user’s git/gh credentials.","evidenceIds":["thinkrail:blog-030","thinkrail:goal"]}],"limitations":["Release and deployment authority do not exist in the product."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-030","thinkrail:code-args","thinkrail:goal"]},{"productId":"thinkrail","claimId":"thinkrail:SHIP-05","verificationStatus":"agent-cross-checked","answer":"Turn receipts and per-step commits link work to code, the topbar links branches to PRs with delivery state and retained transcripts, and local revert (hunk/file Keep/Revert) plus stale-approval invalidation (Keep lapses on re-edit) are built in. Build/deployment links and post-merge rollback do not exist.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"commit_links","question":"Commit links","support":"supported","answer":"Turn receipts tie runs to changed files and completed steps commit on their own.","evidenceIds":["thinkrail:blog-020","thinkrail:goal"]},{"id":"pr_links","question":"Pr links","support":"supported","answer":"The Remote/PR segments tie the workspace branch to its PR with publish/push/sync/open/merge states.","evidenceIds":["thinkrail:blog-030"]},{"id":"build_links","question":"Build links","support":"unsupported","answer":"Completion evidence and rollback, build_links: bounded v0.3.2 inspection found no such links or rollback; only local hunk/file revert exists.","evidenceIds":["thinkrail:code-pr"]},{"id":"deployment_links","question":"Deployment links","support":"unsupported","answer":"Completion evidence and rollback, deployment_links: bounded v0.3.2 inspection found no such links or rollback; only local hunk/file revert exists.","evidenceIds":["thinkrail:code-pr"]},{"id":"delivery_status","question":"Delivery status","support":"supported","answer":"The topbar always shows the branch’s next delivery step plus checks and review decisions for open PRs.","evidenceIds":["thinkrail:blog-030"]},{"id":"retained_evidence","question":"Retained evidence","support":"supported","answer":"Transcripts, Changes tabs and resource history retain the evidence after sessions end.","evidenceIds":["thinkrail:blog-gui","thinkrail:goal"]},{"id":"rollback","question":"Rollback","support":"unsupported","answer":"Completion evidence and rollback, rollback: bounded v0.3.2 inspection found no such links or rollback; only local hunk/file revert exists.","evidenceIds":["thinkrail:code-pr"]},{"id":"revert","question":"Revert","support":"supported","answer":"Host-owned revert of a hunk or file plus per-hunk Keep/Revert operates on the branch diff.","evidenceIds":["thinkrail:blog-020","thinkrail:arch"]},{"id":"stale_approval_invalidation","question":"Stale approval invalidation","support":"supported","answer":"Keep marks are keyed to hunk content: editing a hunk lapses its Keep and it needs re-review.","evidenceIds":["thinkrail:blog-020"]}],"limitations":["Build and deployment links plus post-merge rollback do not exist."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:arch","thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-gui","thinkrail:code-pr","thinkrail:goal"]},{"productId":"thinkrail","claimId":"thinkrail:SHIP-06","verificationStatus":"agent-cross-checked","answer":"Per-branch review is implemented (receipts, retained findings, anchored change requests, next-step topbar, stale-Keep invalidation), and the Projects/Settled views list reviewable work — but grouping, risk filters, exact-revision batch approval, dependency queues and check dedup do not exist. No batch queue exists.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"review_queue","question":"Review queue","support":"supported","answer":"The Projects panel plus Settled shelf plus urgency-ranked palette list reviewable work; a coordinated batch queue is undescribed.","evidenceIds":["thinkrail:blog-gui","thinkrail:readme","thinkrail:blog-031"]},{"id":"summaries","question":"Summaries","support":"supported","answer":"Every changing turn ends with a file-change summary line and receipt.","evidenceIds":["thinkrail:blog-020"]},{"id":"grouping","question":"Grouping","support":"unsupported","answer":"Batch review and high-volume shipping, grouping: bounded v0.3.2 inspection found no such queue, filter or approval construct.","evidenceIds":["thinkrail:code-noqueue"]},{"id":"risk_size_filters","question":"Risk size filters","support":"unsupported","answer":"Batch review and high-volume shipping, risk_size_filters: bounded v0.3.2 inspection found no such queue, filter or approval construct.","evidenceIds":["thinkrail:code-noqueue"]},{"id":"findings","question":"Findings","support":"supported","answer":"Subagent outcomes and reviewer step results persist in resource history; cross-task finding views are undescribed.","evidenceIds":["thinkrail:goal"]},{"id":"artifacts","question":"Artifacts","support":"supported","answer":"Per-branch Changes tabs carry the artifacts; cross-task artifact navigation is undescribed.","evidenceIds":["thinkrail:blog-020"]},{"id":"request_changes","question":"Request changes","support":"supported","answer":"Anchored comments plus Ask-agent-on-hunk request changes with Fix-with-agent follow-through.","evidenceIds":["thinkrail:goal","thinkrail:blog-020","thinkrail:blog-030"]},{"id":"exact_revision_approval","question":"Exact revision approval","support":"unsupported","answer":"Batch review and high-volume shipping, exact_revision_approval: bounded v0.3.2 inspection found no such queue, filter or approval construct.","evidenceIds":["thinkrail:code-noqueue"]},{"id":"dependency_queues","question":"Dependency queues","support":"unsupported","answer":"Batch review and high-volume shipping, dependency_queues: bounded v0.3.2 inspection found no such queue, filter or approval construct.","evidenceIds":["thinkrail:code-noqueue"]},{"id":"next_actions","question":"Next actions","support":"supported","answer":"The topbar and palette always name the next action per branch and per waiting chat.","evidenceIds":["thinkrail:blog-030","thinkrail:blog-031"]},{"id":"stale_approval_invalidation","question":"Stale approval invalidation","support":"supported","answer":"Re-edited hunks lapse their Keep and return for review.","evidenceIds":["thinkrail:blog-020"]},{"id":"check_deduplication","question":"Check deduplication","support":"unsupported","answer":"Batch review and high-volume shipping, check_deduplication: bounded v0.3.2 inspection found no such queue, filter or approval construct.","evidenceIds":["thinkrail:code-noqueue"]}],"limitations":["Per-branch review only, not a coordinated batch review-and-delivery queue."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-020","thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:code-noqueue","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-01","verificationStatus":"agent-cross-checked","answer":"ThinkRail is Apache-2.0 across the public repo: desktop app, CLI host, engine library, contracts, web UI and all bundled extensions ship from one codebase with no proprietary twin or licence exception. The revision is pinned to release v0.3.2 (commit 1bc1a9b).","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"client_license","question":"Client license","support":"supported","answer":"Desktop and browser clients ship from the Apache-2.0 repository from the same codebase.","evidenceIds":["thinkrail:license","thinkrail:repo","thinkrail:readme"]},{"id":"server_license","question":"Server license","support":"supported","answer":"The engine host library ships from the same Apache-2.0 repository; no separate server licence exists.","evidenceIds":["thinkrail:license","thinkrail:repo","thinkrail:arch"]},{"id":"hosted_extensions","question":"Hosted extensions","support":"supported","answer":"Source and license, hosted_extensions: all extensions ship from the same Apache-2.0 repository (pi-extensions, thinkrail-extensions, server registry); no differently-licensed or hosted-only extension was found.","evidenceIds":["thinkrail:license","thinkrail:repo"]},{"id":"source_visibility","question":"Source visibility","support":"supported","answer":"The full source is public at github.com/JetBrains/thinkrail under the JetBrains organisation.","evidenceIds":["thinkrail:repo"]},{"id":"source_revision","question":"Source revision","support":"supported","answer":"This pass covers stable v0.3.2 (2026-11-06) with default-branch commit e473363 observed 2026-11-12.","evidenceIds":["thinkrail:releases","thinkrail:repo"]},{"id":"hosted_parity","question":"Hosted parity","support":"supported","answer":"Desktop and browser hosts embed the same engine host; there is no hosted service to diverge from the source.","evidenceIds":["thinkrail:readme","thinkrail:arch"]}],"limitations":["Single-repo finding: no component carries a different licence."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-05-11","evidenceIds":["thinkrail:license","thinkrail:repo","thinkrail:releases","thinkrail:readme","thinkrail:arch"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-02","verificationStatus":"agent-cross-checked","answer":"The core ADE runs entirely on user-controlled machines with no vendor services to keep: optional companions are the user’s git, gh, central CLI and Tailscale. Uninstall removes the binary and optionally ~/.thinkrail state. Task, context and history export formats do not exist.","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"self_hosting","question":"Self hosting","support":"supported","answer":"Desktop and CLI hosts run on the user’s own machines; no vendor-hosted control plane or compute exists.","evidenceIds":["thinkrail:arch","thinkrail:goal","thinkrail:readme"]},{"id":"vendor_dependencies","question":"Vendor dependencies","support":"supported","answer":"Only optional user-owned services: git, gh for PRs, central CLI for JetBrains AI, Tailscale for phone reach, and PostHog for analytics.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-030"]},{"id":"export","question":"Export","support":"unsupported","answer":"Hosting and exit, export: bounded v0.3.2 inspection found no export formats or history portability; app state lives in the internal ~/.thinkrail tree.","evidenceIds":["thinkrail:code-noexport"]},{"id":"import","question":"Import","support":"supported","answer":"Git URLs clone into projects, existing worktrees attach in place, and skills/packages import from user, repo and third-party agent folders.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:blog-pi"]},{"id":"formats","question":"Formats","support":"unsupported","answer":"Hosting and exit, formats: bounded v0.3.2 inspection found no export formats or history portability; app state lives in the internal ~/.thinkrail tree.","evidenceIds":["thinkrail:code-noexport"]},{"id":"cancellation","question":"Cancellation","support":"supported","answer":"There is no account to cancel: thinkrail uninstall removes the binary and PATH entry and optionally deletes ~/.thinkrail with confirmation.","evidenceIds":["thinkrail:readme"]},{"id":"account_independence","question":"Account independence","support":"supported","answer":"Everything except provider-authenticated model calls works with no vendor account; analytics extras switch off.","evidenceIds":["thinkrail:goal","thinkrail:readme"]},{"id":"history_portability","question":"History portability","support":"unsupported","answer":"Hosting and exit, history_portability: bounded v0.3.2 inspection found no export formats or history portability; app state lives in the internal ~/.thinkrail tree.","evidenceIds":["thinkrail:code-noexport"]}],"limitations":["Export formats and history portability do not exist."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-05-11","evidenceIds":["thinkrail:arch","thinkrail:blog-030","thinkrail:blog-pi","thinkrail:code-noexport","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-03","verificationStatus":"agent-cross-checked","answer":"Code, prompts and credentials stay with the user: in-process pi sends them to the user’s own providers, never to ThinkRail servers. Telemetry is basic install-ID events plus always-on error reports via PostHog; extra sharing is opt-in at first run and in Settings Privacy (or --no-analytics). Retention beyond a 30-day link expiry, training use and residency are unstated business facts.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"code_data","question":"Code data","support":"supported","answer":"Code is processed in-process and by the user’s providers; usage analytics explicitly never include code, prompts or files.","evidenceIds":["thinkrail:goal","thinkrail:readme"]},{"id":"prompts","question":"Prompts","support":"supported","answer":"Prompts go to the user’s providers; analytics never include prompts and feedback answers send only on explicit Send.","evidenceIds":["thinkrail:readme"]},{"id":"credentials","question":"Credentials","support":"supported","answer":"Provider credentials stay in pi auth and the OS; analytics never include credentials and the model key never reaches the browser.","evidenceIds":["thinkrail:readme","thinkrail:blog-031"]},{"id":"logs","question":"Logs","support":"supported","answer":"Error reports carry the error type, code and ThinkRail code location only — never messages, paths, names, URLs or project content.","evidenceIds":["thinkrail:readme"]},{"id":"artifacts","question":"Artifacts","support":"partial","answer":"Data handling and telemetry, artifacts: artifacts live in local workspaces; analytics and error reports exclude code, prompts, files, paths and project content, but no artifact-specific routing policy is stated.","evidenceIds":["thinkrail:readme"]},{"id":"retention","question":"Retention","support":"supported","answer":"The website-visit link for installed builds expires after 30 days; general retention and deletion timelines are unstated.","evidenceIds":["thinkrail:readme"]},{"id":"deletion","question":"Deletion","support":"supported","answer":"Chats delete to Trash, uninstall optionally removes ~/.thinkrail data, and survey answers delete on emailed request; a general deletion policy is unstated.","evidenceIds":["thinkrail:readme"]},{"id":"training","question":"Training","support":"unknown","answer":"Data handling and telemetry, training: model-training use of user data is a vendor business fact unstated in ThinkRail sources; no statement was found either way.","evidenceIds":[]},{"id":"residency","question":"Residency","support":"unknown","answer":"Data handling and telemetry, residency: data residency is a vendor business fact unstated in ThinkRail sources.","evidenceIds":[]},{"id":"subprocessors","question":"Subprocessors","support":"supported","answer":"Analytics run on PostHog services for apps and website (surveys collect email only when volunteered); PostHog policy linked.","evidenceIds":["thinkrail:readme"]},{"id":"telemetry_disclosure","question":"Telemetry disclosure","support":"supported","answer":"Launches, chat creation, message sends, provider connections and error reports are disclosed as collected, tied to a random install ID.","evidenceIds":["thinkrail:readme"]},{"id":"telemetry_defaults","question":"Telemetry defaults","support":"supported","answer":"Additional sharing defaults to the first-run choice (off unless enabled); error reports are always sent.","evidenceIds":["thinkrail:readme"]},{"id":"telemetry_controls","question":"Telemetry controls","support":"supported","answer":"Settings Privacy toggles additional sharing and thinkrail --no-analytics (or THINKRAIL_NO_ANALYTICS=1) disables it per launch.","evidenceIds":["thinkrail:readme"]},{"id":"consent_prompt","question":"Consent prompt","support":"supported","answer":"The privacy switch is offered during first-run setup (or right after skipping it).","evidenceIds":["thinkrail:readme"]},{"id":"provider_separation","question":"Provider separation","support":"supported","answer":"Orchestration-vendor data (basic ThinkRail events) is separate from model-provider data (user code and prompts to their providers).","evidenceIds":["thinkrail:goal","thinkrail:readme"]}],"limitations":["Retention timelines, training use and residency are unstated."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-03-12","evidenceIds":["thinkrail:blog-031","thinkrail:code-nouser","thinkrail:goal","thinkrail:readme"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-04","verificationStatus":"agent-cross-checked","answer":"ThinkRail itself is free: Apache-2.0 source, free downloads, no accounts, no paid plan and no metered units. Model and compute spend belongs to the user’s own providers and hardware and is never billed or marked up by ThinkRail. Billing dimensions do not apply to a product with no paid offering.","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"currency","question":"Currency","support":"unknown","answer":"Price and included usage, currency: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"interval","question":"Interval","support":"unknown","answer":"Price and included usage, interval: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"seats","question":"Seats","support":"unknown","answer":"Price and included usage, seats: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"seat_minimum","question":"Seat minimum","support":"unknown","answer":"Price and included usage, seat_minimum: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"workspace_fees","question":"Workspace fees","support":"unknown","answer":"Price and included usage, workspace_fees: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"included_usage","question":"Included usage","support":"unknown","answer":"Price and included usage, included_usage: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"credits","question":"Credits","support":"unknown","answer":"Price and included usage, credits: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"trial","question":"Trial","support":"unknown","answer":"Price and included usage, trial: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"overages","question":"Overages","support":"unknown","answer":"Price and included usage, overages: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"taxes","question":"Taxes","support":"unknown","answer":"Price and included usage, taxes: no paid offering exists, so this billing dimension is a moot business fact with nothing to disclose.","evidenceIds":[]},{"id":"model_cost","question":"Model cost","support":"supported","answer":"Model spend is the user’s own provider billing (including JetBrains AI quota via central); ThinkRail charges nothing and marks nothing up.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:central"]},{"id":"compute_cost","question":"Compute cost","support":"supported","answer":"Compute is the user’s own machine with no vendor compute fees; user hardware cost is unstated.","evidenceIds":["thinkrail:arch","thinkrail:goal"]}],"limitations":["No paid plans exist, so billing atoms are moot business facts; model and compute spend is the user’s own provider and hardware cost."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11","evidenceIds":["thinkrail:arch","thinkrail:central","thinkrail:goal","thinkrail:license","thinkrail:readme","thinkrail:releases"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-05","verificationStatus":"agent-cross-checked","answer":"Fixed ThinkRail cost is $0 for one, two or five developers (free installs, parallel workspaces included, no seats). Variable cost is the team’s own provider spend on tokens; no invented per-task averages are used. Two-person collaboration is limited by the single-user design and shared via git.","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"one_person","question":"One person","support":"supported","answer":"One developer: $0 app cost plus own provider spend; full local workflow included.","evidenceIds":["thinkrail:readme","thinkrail:license"]},{"id":"two_people","question":"Two people","support":"supported","answer":"Two developers: $0 plus $0 installs with own provider spend each; no shared-prompting or team features — collaboration goes through git and the forge.","evidenceIds":["thinkrail:readme","thinkrail:license","thinkrail:goal"]},{"id":"five_people","question":"Five people","support":"supported","answer":"Five developers: $0 times five installs with own provider spend each; same single-user limits as the two-person case.","evidenceIds":["thinkrail:readme","thinkrail:license"]},{"id":"task_assumptions","question":"Task assumptions","support":"supported","answer":"No fixed task, token or compute-hour assumptions are stated; per-task cost is not averaged.","evidenceIds":["thinkrail:readme"]},{"id":"concurrency","question":"Concurrency","support":"supported","answer":"Parallel sessions and workspaces carry no ThinkRail surcharge.","evidenceIds":["thinkrail:site-home","thinkrail:goal"]},{"id":"tokens","question":"Tokens","support":"unknown","answer":"Scenario cost and controls, tokens: token volumes per scenario depend on usage and cannot be established by source or code inspection; no invented averages are used.","evidenceIds":[]},{"id":"compute_hours","question":"Compute hours","support":"unknown","answer":"Scenario cost and controls, compute_hours: compute hours on user-owned machines cannot be established by inspection; no invented figures are used.","evidenceIds":[]},{"id":"fixed_cost","question":"Fixed cost","support":"supported","answer":"Fixed cost is $0 in every scenario: no subscription, seats, workspace fees or compute billing.","evidenceIds":["thinkrail:readme","thinkrail:license","thinkrail:releases"]},{"id":"variable_cost","question":"Variable cost","support":"supported","answer":"Variable cost is provider token/metered spend (including JetBrains AI quota), varying by provider and use.","evidenceIds":["thinkrail:central","thinkrail:readme"]},{"id":"included_cost","question":"Included cost","support":"supported","answer":"All app capabilities are included at $0 with no paid tier gating them.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"unknown_cost","question":"Unknown cost","support":"supported","answer":"Unknown: token volumes, provider rates and hardware/electricity costs are unstated and scenario-dependent.","evidenceIds":["thinkrail:readme"]}],"limitations":["Fixed $0 cost is established; variable provider spend cannot be fixed without usage assumptions, which are not invented."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:license","thinkrail:releases","thinkrail:central","thinkrail:site-home"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-06","verificationStatus":"agent-cross-checked","answer":"Pre-1.0 beta under active development: stable v0.3.2 plus public nightlies with daily commits, free of access restrictions beyond provider credentials. Support is Discord plus GitHub issues with no committed response times and no published status history; uninstall documents exit without export.","availability":"beta","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"release_stage","question":"Release stage","support":"supported","answer":"Pre-1.0 beta: stable and nightly channels with the GUI overview noting the product is still in development.","evidenceIds":["thinkrail:releases","thinkrail:blog-gui"]},{"id":"access_restrictions","question":"Access restrictions","support":"supported","answer":"Open source with free downloads and no invite wall; provider credentials (and gh for PRs) are the only gates.","evidenceIds":["thinkrail:readme","thinkrail:license","thinkrail:blog-030"]},{"id":"support","question":"Support","support":"supported","answer":"Discord for questions and discussion; GitHub issues for bugs and feature requests.","evidenceIds":["thinkrail:readme","thinkrail:blog-031","thinkrail:issues"]},{"id":"response_commitments","question":"Response commitments","support":"unknown","answer":"Availability and support, response_commitments: support response times are a vendor business fact with no public commitment.","evidenceIds":[]},{"id":"release_activity","question":"Release activity","support":"supported","answer":"Nightly releases (0.4.0-nightly.12 on 2026-11-12), stable v0.3.2 on 2026-11-06, and default-branch commits on 2026-11-12 show active development.","evidenceIds":["thinkrail:releases","thinkrail:repo"]},{"id":"status_history","question":"Status history","support":"unknown","answer":"Availability and support, status_history: no public status page or status history is published; an archived repo would not prove hosted-service status either.","evidenceIds":[]},{"id":"deprecation","question":"Deprecation","support":"supported","answer":"No deprecation policy exists; the documented exit path is thinkrail uninstall with optional state deletion.","evidenceIds":["thinkrail:readme"]},{"id":"export_options","question":"Export options","support":"unsupported","answer":"Availability and support, export_options: bounded v0.3.2 inspection found no deprecation-time export; exit is uninstall only.","evidenceIds":["thinkrail:code-noexport"]}],"limitations":["Response commitments, status history and export options are unpublished or absent."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11","evidenceIds":["thinkrail:blog-030","thinkrail:blog-031","thinkrail:blog-gui","thinkrail:code-noexport","thinkrail:issues","thinkrail:license","thinkrail:readme","thinkrail:releases","thinkrail:repo"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-08","verificationStatus":"agent-cross-checked","answer":"Free outright: Apache-2.0 source with free desktop and CLI downloads and no paid plan, card, trial, credit programme, gated early access or usage caps. Meaningful evaluation needs only provider credentials (JetBrains AI or own keys/local models); two-person same-work collaboration is limited by the single-user design.","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"ongoing_free","question":"Ongoing free","support":"supported","answer":"Apache-2.0 repository with free downloads and no paid plan: free with no time limit.","evidenceIds":["thinkrail:license","thinkrail:readme","thinkrail:releases"]},{"id":"trial","question":"Trial","support":"unsupported","answer":"Useful free tier and evaluation access, trial: bounded v0.3.2 inspection (docs, releases, code) found no such programme or cap; nightly builds are public and no ThinkRail-side caps exist.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"credits_trial","question":"Credits trial","support":"unsupported","answer":"Useful free tier and evaluation access, credits_trial: bounded v0.3.2 inspection (docs, releases, code) found no such programme or cap; nightly builds are public and no ThinkRail-side caps exist.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"self_host_cost","question":"Self host cost","support":"supported","answer":"Self-hosting cost is the user’s own machine plus provider spend; no ThinkRail charge.","evidenceIds":["thinkrail:readme","thinkrail:goal"]},{"id":"paid_only","question":"Paid only","support":"unsupported","answer":"No paid-only gate exists: the whole ADE is free with no paid tier.","evidenceIds":["thinkrail:readme","thinkrail:license","thinkrail:releases"]},{"id":"early_access","question":"Early access","support":"unsupported","answer":"Useful free tier and evaluation access, early_access: bounded v0.3.2 inspection (docs, releases, code) found no such programme or cap; nightly builds are public and no ThinkRail-side caps exist.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"free_scenarios","question":"Free scenarios","support":"supported","answer":"Local workspaces, BYO keys and local models, phone-browser reach, local issue-style plans and review all work free; same-work two-person collaboration is limited by the single-user design.","evidenceIds":["thinkrail:readme","thinkrail:goal","thinkrail:arch"]},{"id":"card_required","question":"Card required","support":"supported","answer":"No payment exists anywhere in the product, so no card is required.","evidenceIds":["thinkrail:readme"]},{"id":"usage_caps","question":"Usage caps","support":"unsupported","answer":"Useful free tier and evaluation access, usage_caps: bounded v0.3.2 inspection (docs, releases, code) found no such programme or cap; nightly builds are public and no ThinkRail-side caps exist.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"paid_evaluation","question":"Paid evaluation","support":"supported","answer":"Evaluation needs provider credentials but no payment to ThinkRail and no sales approval.","evidenceIds":["thinkrail:readme","thinkrail:goal"]}],"limitations":["Evaluation needs provider credentials; same-work two-person scenarios are limited by the single-user design."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11","evidenceIds":["thinkrail:license","thinkrail:readme","thinkrail:releases","thinkrail:goal","thinkrail:arch"]},{"productId":"thinkrail","claimId":"thinkrail:OWN-09","verificationStatus":"agent-cross-checked","answer":"Pricing is transparent because there is nothing to hide: free with no paid plan, no metered units, no overages, no markups, no minimums and nothing sales-gated. Model and compute economics are the user’s own provider and hardware spend, never marked up.","availability":"generally-available","delivery":"native","scope":{"surfaceIds":["desktop","browser"],"version":"v0.3.2 stable (2026-11-06); default-branch commit e473363 (2026-11-12)","plan":null,"os":[],"executionModes":["local"],"region":null,"harness":"pi","surfaces":[{"id":"desktop","name":"ThinkRail desktop app (Electrobun system-webview)","type":"desktop"},{"id":"browser","name":"thinkrail CLI browser host (same app in a browser)","type":"browser"}]},"questions":[{"id":"units","question":"Units","support":"supported","answer":"No priced units exist; the app is free with no metering by ThinkRail.","evidenceIds":["thinkrail:readme","thinkrail:license"]},{"id":"included_limits","question":"Included limits","support":"supported","answer":"No paid plan means no included-limit schedule; provider-side quotas (JetBrains AI) are separate.","evidenceIds":["thinkrail:readme","thinkrail:central"]},{"id":"overages","question":"Overages","support":"unsupported","answer":"Pricing transparency, overages: no billing exists in docs, releases or code, so no such rate, commitment or sales gate exists.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"compute_markup","question":"Compute markup","support":"unsupported","answer":"Pricing transparency, compute_markup: no billing exists in docs, releases or code, so no such rate, commitment or sales gate exists.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"model_markup","question":"Model markup","support":"unsupported","answer":"Pricing transparency, model_markup: no billing exists in docs, releases or code, so no such rate, commitment or sales gate exists.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"minimum_commitment","question":"Minimum commitment","support":"unsupported","answer":"Pricing transparency, minimum_commitment: no billing exists in docs, releases or code, so no such rate, commitment or sales gate exists.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"cancellation","question":"Cancellation","support":"unsupported","answer":"Pricing transparency, cancellation: no billing exists in docs, releases or code, so no such rate, commitment or sales gate exists.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"sales_only_unknowns","question":"Sales only unknowns","support":"unsupported","answer":"Pricing transparency, sales_only_unknowns: no billing exists in docs, releases or code, so no such rate, commitment or sales gate exists.","evidenceIds":["thinkrail:readme","thinkrail:releases"]},{"id":"transparency_classification","question":"Transparency classification","support":"supported","answer":"Transparent: the free, no-paid-plan model with user-side provider spend is fully stated in public sources.","evidenceIds":["thinkrail:readme","thinkrail:license","thinkrail:goal"]}],"limitations":["Billing atoms do not apply to a free product with no paid tier."],"checkedAt":"2026-11-12","crossCheckedAt":"2026-11-12","nextCheckAt":"2027-01-11","evidenceIds":["thinkrail:readme","thinkrail:license","thinkrail:goal","thinkrail:central"]}],"sources":[{"id":"thinkrail:site-home","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/","title":"ThinkRail — the agentic IDE that gets better every time you use it","locator":"Hero and install matrix; Why ThinkRail; Features (workspaces, editor, agent-chat, specs); Open source section","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Agentic IDE around the pi agent: git-worktree workspaces with own branch and cwd, Monaco editor tabs, terminals, diffs, concurrent chats with per-session model and live token/cost ticks, and a spec graph the agent reads. Desktop apps for macOS, Windows and Linux plus a thinkrail CLI that opens the same app in a browser. Open source Apache-2.0; a JetBrains InnovationHub project."},{"id":"thinkrail:blog-intro","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/introducing-thinkrail/","title":"Introducing ThinkRail","locator":"Install; What is next","sourceDate":"2026-08-19","retrievedAt":"2026-11-12","finding":"ThinkRail is an agentic IDE for the Pi coding agent that complements its CLI. Desktop installers for macOS, Windows x64 and Linux x64/ARM64, or a CLI host that opens a browser tab. Every working session operates on a separate git branch merged only after review; LLM providers are configured in Settings."},{"id":"thinkrail:blog-030","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/thinkrail-0-3-0-whole-loop-one-window/","title":"ThinkRail 0.3.0: the whole loop in one window","locator":"Ship the branch from the topbar; A first run that ends with a working model","sourceDate":"2026-10-29","retrievedAt":"2026-11-12","finding":"Topbar Remote and Pull request segments drive publish, push, sync, open-PR and merge through the user-owned gh CLI, showing CI checks and review decision re-read every 20 seconds; merging locally and GitLab review actions are not yet available. First-run wizard detects signed-in Claude Code, Codex, Copilot, Kimi CLI or Grok Build configs and connects through pi auth without borrowing their credentials."},{"id":"thinkrail:blog-031","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/thinkrail-0-3-1-release/","title":"ThinkRail 0.3.1 release","locator":"One box; Your own model server; pi packages; closing channels","sourceDate":"2026-11-01","retrievedAt":"2026-11-12","finding":"Command palette finds chats, workspaces, commands and settings. Custom OpenAI chat-completions servers (Ollama, LM Studio, vLLM, llama.cpp presets) are saved into pi models.json. pi packages install from Settings for the user or a repository. Post notes ThinkRail is backed by JetBrains and links X (@ThinkRailAI), YouTube, TikTok, Discord and the GitHub repository."},{"id":"thinkrail:blog-gui","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/gui-overview/","title":"GUI overview","locator":"The main GUI; The chat; The workspace; Settings","sourceDate":"2026-10-28","retrievedAt":"2026-11-12","finding":"Fifteen numbered components: chat tabs with turn summaries and Review turn, read-only file and diff tabs, chat history popup, terminals, per-chat token usage, Resources popup (background commands, subagents, MCP servers), Skills popup, model picker, Projects/workspaces/Settled panel, Specs/Files/Changes/Review/TODO panels, command palette, and provider, MCP, prompt, Pi-config and chat-tuning settings."},{"id":"thinkrail:blog-pi","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/thinkrail-pi-skills-and-desktop-apps/","title":"An agentic IDE that follows Pi's philosophy","locator":"Pi compatibility; The Skills window; Desktop apps","sourceDate":"2026-10-01","retrievedAt":"2026-11-12","finding":"ThinkRail embeds its own pi coding agent as a library running inside ThinkRail’s own process and shares pi’s ~/.pi folder, so CLI and app sessions keep history both ways. Skills and extensions from pi, Claude, Codex, Copilot and Gemini project folders are reused with per-chat switches. Desktop apps packaged with Electrobun run identically to the CLI browser host."},{"id":"thinkrail:blog-020","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/thinkrail-0-2-0-review-the-turn/","title":"ThinkRail 0.2.0: review the turn, not the chat log","locator":"Every turn gets a receipt; MCP servers, finally","sourceDate":"2026-10-18","retrievedAt":"2026-11-12","finding":"Turn receipts (files changed plus Review turn button) and a stacked Changes tab with per-hunk Keep, Revert and Ask agent plus Next-unreviewed (J). MCP runs on pi’s built-in engine with presets (Context7, DeepWiki, Linear read-only, Sentry, Playwright); secrets must be ${VAR} or !command and repo .pi/mcp.json entries need per-entry approval; data-changing calls confirm in the chat with Deny, Allow once, Allow in this chat or Always allow."},{"id":"thinkrail:blog-chat","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/the-chat/","title":"The Chat","locator":"Message batching; Code highlighting","sourceDate":"2026-11-06","retrievedAt":"2026-11-12","finding":"Chat groups pi messages into styled batches with folded thinking and tool use, renders Markdown with Mermaid diagrams, highlights 36 languages with Shiki, and opens read-only code and diff tabs from Files. The composer references @ files."},{"id":"thinkrail:readme","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/blob/main/README.md","title":"ThinkRail README","locator":"Installation; What you get; Installation details; Analytics & privacy; Under the hood","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Native desktop installer plus self-contained thinkrail CLI with stable and nightly channels and checksum verification. Workspaces are git worktrees with own branch and cwd; finished ones settle after PR merge/close or a quiet week. Concurrent sessions per workspace each with its own model; shared TODO plans with per-step review; subagents and background commands watched from a per-chat Resources view; spec tools; skills import from Claude/Codex agents; MCP from pi mcp.json; JetBrains AI or any pi provider auth with no ThinkRail accounts. App state lives under ~/.thinkrail. Basic usage events tie to a random install ID; extra sharing is opt-in via Settings Privacy or --no-analytics."},{"id":"thinkrail:goal","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/blob/main/goal-and-requirements.md","title":"ThinkRail — product goal and scope","locator":"Value; Principles; Capabilities; Non-goals","sourceDate":null,"retrievedAt":"2026-11-12","finding":"pi is the only engine, run in-process, with no second runtime. Git, GitHub and model access go through the user-owned git, gh and central CLI plus pi provider auth; ThinkRail keeps no accounts or tokens. Cloned-repository resources and repo MCP servers load only after a per-project trust grant. Capabilities include projects-to-workspaces, scratch chats, concurrent steerable chats, plans with per-step independent review, subagents and background commands, agent-started workspaces, anchored review comments, PR open/update via gh, specs, workflows, providers, pi config, agent tools, pi packages and MCP. Non-goals: a second agent runtime, and ThinkRail accounts or a login UI — who may reach a host is decided by Tailscale ACLs."},{"id":"thinkrail:arch","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/blob/main/architecture.md","title":"ThinkRail — top-level architecture","locator":"Drivers; Topology — three rings","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Engine host (Bun HTTP+WS with one in-process pi session per chat) launched by the CLI or the Electrobun desktop shell; typed versioned wire protocol; mobile-first React UI that dials any host over the network, with a phone reaching the selected host over Tailscale. Desktop profile is local only; a later shared-client profile can dial an existing host. Bundled extensions pi-spec-graph, pi-thinkrail-workflow and pi-todos; portable packages pi-delegation, pi-background-commands and pi-subagents (Agent plus get_subagent_result tools) bundled into every parent session."},{"id":"thinkrail:central","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/blob/main/central-integration.md","title":"JetBrains AI via the Central CLI","locator":"The chain; Quota chain","sourceDate":null,"retrievedAt":"2026-11-12","finding":"JetBrains AI models reach ThinkRail through the user-owned central CLI with a recurring AI-credit quota; sign-in, status and quota orchestration span the provider card and shell, with quota snapshots on a 1–3600 second cadence (30 seconds by default)."},{"id":"thinkrail:picompat","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/blob/main/pi-compatibility.md","title":"Pi compatibility","locator":"Last re-check","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Host tracks pi releases with per-upgrade re-checks (pi 1.5.2 verified against the installed dist). Bundled chat catalogue holds 1,639 provider/model pairs in pi 1.5.1 (66 added, 19 removed); unavailable models follow the existing selection rules."},{"id":"thinkrail:releases","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/releases","title":"ThinkRail releases","locator":"Releases list; per-release version and date","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Stable v0.3.2 published 2026-11-06; v0.4.0 stable published 2026-11-12 (latest at check time). Free desktop and CLI assets per platform with SHA256SUMS."},{"id":"thinkrail:repo","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail","title":"JetBrains/thinkrail","locator":"Repository header and metadata","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Public repository in the JetBrains organisation, default branch main, pushed 2026-11-12. 8,189 stars, 518 forks and 257 open issues observed 2026-11-12. Licensed Apache-2.0; homepage thinkrail.ai."},{"id":"thinkrail:license","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/blob/main/LICENSE","title":"Apache License 2.0","locator":"License grant","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Repository licensed under the Apache License, Version 2.0."},{"id":"thinkrail:issues","productId":"thinkrail","kind":"documented","url":"https://github.com/JetBrains/thinkrail/issues","title":"ThinkRail issues","locator":"Issues list (bugs and feature requests venue)","sourceDate":null,"retrievedAt":"2026-11-12","finding":"GitHub issues is the venue for bugs and feature requests, with Discord linked for discussion. No roadmap document, changelog file or milestones were found; release history is spread across the blog and releases."},{"id":"thinkrail:blog-workspaces","productId":"thinkrail","kind":"vendor-claimed","url":"https://thinkrail.ai/blog/thinkrail-workspaces/","title":"ThinkRail Workspaces","locator":"Create an isolated workspace; Work safely on many tasks at the same time","sourceDate":"2026-09-03","retrievedAt":"2026-11-12","finding":"Workspaces are git worktrees under ~/.thinkrail/worktrees with their own branch and cwd; parallel agents stay on their branches and merge back (or open a PR) only on request."},{"id":"thinkrail:code-args","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/cli/src/args.ts","title":"ThinkRail v0.3.2 — args.ts","locator":"USAGE string; exhaustive parseArgs (unknown options throw); SUBCOMMANDS update/uninstall","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Complete CLI inventory: launch flags plus update and uninstall subcommands only. No session, task, steering or review operations exist in the launcher.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/cli/src/args.ts"},{"id":"thinkrail:code-routes","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/host/server.ts","title":"ThinkRail v0.3.2 — server.ts","locator":"fetch handler: /ws, /health, static and file/font routes only; no REST router","sourceDate":null,"retrievedAt":"2026-11-12","finding":"The host exposes only the internal /ws wire, /health and static/file routes. No public REST API, SDK surface, MCP server transport or webhooks exist in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/host/server.ts"},{"id":"thinkrail:code-workspaces","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/workspaces/workspaces.ts","title":"ThinkRail v0.3.2 — workspaces.ts","locator":"status available/detached; settledOverride settled/active; Default kind non-settleable; external attach","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Flat workspace model with available/detached status and settled/active lifecycle. No epics, labels, priorities, queues, blockers, readiness gates or dependencies in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/workspaces/workspaces.ts"},{"id":"thinkrail:code-delegation","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/pi-subagents/src/extension.ts","title":"ThinkRail v0.3.2 — extension.ts","locator":"Agent tool (model/thinking choice, run_in_background, subagents cannot call MCP tools); get_subagent_result status/report reads","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Delegation tools are product-bundled: Agent with per-call model and thinking choice plus background runs, and get_subagent_result for status and finished reports. Subagents cannot call MCP tools.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/pi-subagents/src/extension.ts"},{"id":"thinkrail:code-bgcmd","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/pi-background-commands/src/extension.ts","title":"ThinkRail v0.3.2 — extension.ts","locator":"background_command start/list/output/stop; at most 8 active; latest 20 finished retained; stop cancels without waking parent","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Background commands are session-owned with start, list, output and stop; at most 8 active with the latest 20 finished records retained.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/pi-background-commands/src/extension.ts"},{"id":"thinkrail:code-mcp","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/agent/mcp/sessionHost.ts","title":"ThinkRail v0.3.2 — sessionHost.ts","locator":"MCP_CONFIRM_ALWAYS; confirm() on data-changing calls with no-UI-attached fallback; allow once/chat/always","sourceDate":null,"retrievedAt":"2026-11-12","finding":"MCP confirmation is product code: data-changing calls confirm with Deny, Allow once, Allow in this chat or Always allow, and fail closed with no UI attached.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/agent/mcp/sessionHost.ts"},{"id":"thinkrail:code-trust","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/agent/skillAdmission.ts","title":"ThinkRail v0.3.2 — skillAdmission.ts","locator":"trusted / piResourceTrust per project; untrusted default","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Project resources load only after per-project trust grants (trusted, piResourceTrust); untrusted is the default.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/agent/skillAdmission.ts"},{"id":"thinkrail:code-todos","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/todos/todos.ts","title":"ThinkRail v0.3.2 — todos.ts","locator":"done steps immutable history; per-step commits; revision shas; TodoReviewInfo states","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Completed plan steps are immutable history with per-step commits and revision shas; steps carry review states.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/todos/todos.ts"},{"id":"thinkrail:code-reviewflow","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/todos/reviews.ts","title":"ThinkRail v0.3.2 — reviews.ts","locator":"independent reviewer flow; reviewLock; reviewerRole (see also host/planReviewQueue.ts)","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Per-step independent review with locks and reviewer roles. No spec-conformance checks at review.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/todos/reviews.ts"},{"id":"thinkrail:code-hydrate","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/contracts/src/wsProtocol.ts","title":"ThinkRail v0.3.2 — wsProtocol.ts","locator":"session.list / session.getMessages / session.created; host requestReplayCache repairs missed deltas","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Hydrate-then-stream: clients rebuild projects, workspaces, sessions and transcripts on reload, second tab, phone or host restart; reconnect repairs missed deltas.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/contracts/src/wsProtocol.ts"},{"id":"thinkrail:code-notify","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/web/src/notifications/attentionNotificationEngine.ts","title":"ThinkRail v0.3.2 — attentionNotificationEngine.ts","locator":"rising-edge attention gate per session; desktopNotifications; unread holds","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Attention engine with per-session unread holds plus desktop notifications.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/web/src/notifications/attentionNotificationEngine.ts"},{"id":"thinkrail:code-editors","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/editors/editors.ts","title":"ThinkRail v0.3.2 — editors.ts","locator":"GUI_CANDIDATES vscode/emacs; JETBRAINS_CANDIDATES bins; TERMINAL vim; no extension packaging","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Fixed external-editor launcher list (VS Code, Emacs, JetBrains IDEs, Vim). No ThinkRail editor extension ships.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/editors/editors.ts"},{"id":"thinkrail:code-spec","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/spec-graph/tools/index.ts","title":"ThinkRail v0.3.2 — index.ts","locator":"create/delete/get/update/validate/grep tools; statuses draft/active/stale/done/deprecated; core/store.ts mtime revalidation","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Spec CRUD plus validate and grep tools; the index revalidates by mtime/size and never serves stale. No approval, citation or conflict-detection tools.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/spec-graph/tools/index.ts"},{"id":"thinkrail:code-nosched","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src","title":"ThinkRail v0.3.2 — src","locator":"Searched packages/server, apps/* and packages/* at v0.3.2 for schedul|cron|trigger|recur|setInterval-based scheduling; hits are UI polling, update checks and request replay only","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Bounded inspection found no user-facing schedules, event triggers, recurring tasks or completion-driven runs.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src"},{"id":"thinkrail:code-nouser","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/auth","title":"ThinkRail v0.3.2 — auth","locator":"Searched auth, contracts and web store for sso|organization|invite|member-role models; auth is Tailscale ACLs plus an owner field","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No user, organisation, role, SSO, membership or provisioning model in code. Single-owner external auth.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/auth"},{"id":"thinkrail:code-nolimits","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/agent","title":"ThinkRail v0.3.2 — agent","locator":"Searched server code for spend/budget/token-limit/rate-limit/throttle enforcement; only model maxTokens passthrough and a shutdown budget","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No user-facing time, turn, token or spend limits, retries or failure budgets in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/agent"},{"id":"thinkrail:code-noexport","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src","title":"ThinkRail v0.3.2 — src","locator":"Searched server and web code for exportHistory/exportChat/backup/usage-export; only CSV file renderers and package-registry links","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No history, usage or task export in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src"},{"id":"thinkrail:code-nogallery","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/web/src","title":"ThinkRail v0.3.2 — src","locator":"Searched app, server and CLI for screenshot/captureScreen/gallery capture; GalleryLink points at the pi package registry","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No artifact gallery, screenshot or recording capture in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/web/src"},{"id":"thinkrail:code-nogates","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src","title":"ThinkRail v0.3.2 — src","locator":"Searched todos/reviews/pr for required/enforced verification gates; CI is displayed, review is optional, nothing blocks","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No required or enforced verification gates in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src"},{"id":"thinkrail:code-noqueue","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src","title":"ThinkRail v0.3.2 — src","locator":"Searched host/todos for batch/dependency queues; planReviewQueue is per-step review, settledLifecycle is workspace states","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No batch review or dependency-aware merge queues in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src"},{"id":"thinkrail:code-viewport","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/web/src/lib/viewport.ts","title":"ThinkRail v0.3.2 — viewport.ts","locator":"PHONE_QUERIES pointer:coarse and max-width:767px; usePhoneViewport hook","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Phone-viewport detection adapts the UI below 767px width.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/web/src/lib/viewport.ts"},{"id":"thinkrail:code-keyboard","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/web/src/panels/ChangesReviewPane.tsx","title":"ThinkRail v0.3.2 — ChangesReviewPane.tsx","locator":"NEXT_UNREVIEWED_KEY j; hotkey handling in Composer, HistoryOverlay and review panes","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Keyboard operation including J for next-unreviewed plus palette and file-search shortcuts.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/web/src/panels/ChangesReviewPane.tsx"},{"id":"thinkrail:code-errors","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/web/src/chat/ChatTranscript.tsx","title":"ThinkRail v0.3.2 — ChatTranscript.tsx","locator":"toast.error on locate and resolve failures","sourceDate":null,"retrievedAt":"2026-11-12","finding":"User-facing error toasts exist; silent waits and escalation paths do not.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/web/src/chat/ChatTranscript.tsx"},{"id":"thinkrail:code-terminal","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/terminal","title":"ThinkRail v0.3.2 — terminal","locator":"Searched terminal code for approv|confirm|permission: none; completionQueue resume is output resumption","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No approval or intervention model in terminal code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/terminal"},{"id":"thinkrail:code-detect","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/auth/detectAccounts.ts","title":"ThinkRail v0.3.2 — detectAccounts.ts","locator":"detectClaudeCode/Codex/Copilot read own config files as setup signals; pi performs the login","sourceDate":null,"retrievedAt":"2026-11-12","finding":"Third-party CLIs are read as provider-setup signals only; sign-in stays pi’s own flow.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/auth/detectAccounts.ts"},{"id":"thinkrail:code-pr","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src/pr/pr.ts","title":"ThinkRail v0.3.2 — pr.ts","locator":"pushAndPreview plus reviewActions (ready/merge/reopen/delete-branch) via gh; no forge comment ingestion in pr/github modules","sourceDate":null,"retrievedAt":"2026-11-12","finding":"PR open/update/ready/merge/reopen/delete-branch through gh with checks display. Forge review-comment ingestion not found.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/pr/pr.ts"},{"id":"thinkrail:code-noperf","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/apps/web/src","title":"ThinkRail v0.3.2 — web app source","locator":"Searched app and server code for timing, metrics, perf-hook or review-measurement instrumentation: only product analytics events","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No interaction-timing, review-effort or measurement instrumentation in code; shown figures are single documented cases and analytics.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"apps/web/src"},{"id":"thinkrail:code-noaudit","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/v0.3.2/packages/server/src","title":"ThinkRail v0.3.2 — server source","locator":"Searched server for audit, integrity or retention-model code: history is append/delete only","sourceDate":null,"retrievedAt":"2026-11-12","finding":"No audit, retention or integrity model in code.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src"},{"id":"thinkrail:gaps41-subscription","productId":"thinkrail","kind":"source-inspected","url":"https://github.com/JetBrains/thinkrail/blob/1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544/packages/server/src/agent/anthropicExtraUsage.ts#L1-L40","title":"ThinkRail native Pi subscription authentication","locator":"anthropicExtraUsage.ts anthropicSubscriptionAuthActive; auth/providerLogin.ts startLogin; auth/detectAccounts.ts known subscription plans","sourceDate":null,"retrievedAt":"2026-11-13","finding":"ThinkRail starts Pi's own OAuth login flow, and its runtime explicitly recognizes active Anthropic subscription OAuth credentials for extra-usage warnings. Detected Claude/Codex CLI account plans are setup signals, not borrowed credentials. This establishes subscription use through the embedded Pi provider login rather than a separate CLI runtime.","commit":"1bc1a9bc5b0bb9d2c029da32125fadf0bd29d544","path":"packages/server/src/agent/anthropicExtraUsage.ts"}],"lifecycleNotice":null}