webbrain-one · esokullu · Sep 1, 2026 · Sep 1, 2026 · Sep 1, 2026 · Sep 1, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -249,7 +249,7 @@ This changelog was generated from the repository Git history and release tags. V
 
 ### Changed
 - Changed the Chrome local vision fallback to the fine-tuned `webbrain-one/webbrain-vl-2-450M-onnx` release, with renewed opt-in consent and a versioned ready marker so older caches cannot be mistaken for the new model.
-- Added a consent-gated, durable WebBrain Cloud terminal-runtime outbox so executed terminal tool results survive provider-trace export gaps and can be joined through stable de-identified references.
+- Added a consent-gated, durable WebBrain Compass terminal-runtime outbox so executed terminal tool results survive provider-trace export gaps and can be joined through stable de-identified references.
 - fix: resume vision downloads and organize settings
 - fix: require vision cache marker and isolate queued worker deadlines
 - fix: verify local vision cache and abort timed-out remote vision
@@ -1046,7 +1046,7 @@ This changelog was generated from the repository Git history and release tags. V
 - Added a WebBrain MCP server introduction blog post covering setup for Claude Code, OpenCode, Codex, and Cursor, the loopback security model, and how WebBrain MCP differs from headless browser tools.
 
 ### Changed
-- Excluded WebBrain Cloud from per-run cost limits and metered dedicated vision provider costs separately, so vision-heavy WebBrain Cloud work does not count against the local/router cost allowance (Chrome and Firefox parity).
+- Excluded WebBrain Compass from per-run cost limits and metered dedicated vision provider costs separately, so vision-heavy WebBrain Compass work does not count against the local/router cost allowance (Chrome and Firefox parity).
 - Merged Cloud Bridge (MCP/LM Studio browser delegation) settings into Settings → General → Advanced → Cloud bridge, with synchronized setup guidance and the three bridge ports (MCP `17374`, LM Studio `17375`, WebBrain Cloud `17373`).
 - Hardened screenshot and attachment handling: staged screenshots persist durably until delivery is confirmed at every call site, the per-turn screenshot budget charges only when a model actually receives the capture (vision description or attachment), redaction binds to capture time and scopes to rendered frames, and a child frame URL that cannot identify exactly one descriptor fails closed instead of risking mis-paired redaction regions.
 - Did not stage a full-page screenshot when the capture-time privacy scan cannot prepare redaction geometry; the capture now reports `redactionUnavailable`, explains the blocker, and skips staging while still rendering the preview and save button (Chrome only).
@@ -1067,7 +1067,7 @@ This changelog was generated from the repository Git history and release tags. V
 ### Tests
 - Added mirrored Chrome/Firefox coverage for teacher mode: value-free demonstration capture, session store normalization, automated-run rejection, Enter-as-submit semantics, and cross-browser slash-command wiring.
 - Added mirrored coverage for the saved workflow manager, user-approved locator healing, atomic healing persistence with concurrent-update rejection, and workflow run-claim lifecycle.
-- Added mirrored coverage for screenshot redaction fail-closed behavior, staged attachment recovery, viewport budget charging, full-page capture refusals, Cloud Bridge settings placement, and the WebBrain Cloud cost-limit exclusion.
+- Added mirrored coverage for screenshot redaction fail-closed behavior, staged attachment recovery, viewport budget charging, full-page capture refusals, Cloud Bridge settings placement, and the WebBrain Compass cost-limit exclusion.
 - Updated `test/run.js` with the API badge removal assertions and the sidepanel authorization state checks.
 
 ## [27.0.0] - 2026-08-07
@@ -1202,7 +1202,7 @@ This changelog was generated from the repository Git history and release tags. V
 - Centralized text sanitization and shared UI utilities and standardized provider message logic across Chrome and Firefox, including a Firefox utils dedup follow-up.
 - Hardened interactive Ask streaming: traced the streaming run lifecycle, preserved trace ordering, redacted JSON-shaped streaming secrets, and fixed duplicate normalized streamed answers.
 - Hardened chat/run clearing and cancellation: kept the composer locked while clearing, bounded unavailable stop-state probes, waited for stopped/local/direct run followers before clearing, suppressed updates from cleared runs, guarded the Stop fallback and stopped runs until a terminal state, scoped New Chat aborts to their originating tab, discarded queued prompts before clearing, stopped active runs before starting new chats, and cancelled schedules once active runs settle.
-- Added WebBrain Cloud interface strings and microphone permission messages to all locales, refreshed the evroc provider icon and provider counts, and updated Discord links and added a Chinese community section to the docs sidebars.
+- Added WebBrain Compass interface strings and microphone permission messages to all locales, refreshed the evroc provider icon and provider counts, and updated Discord links and added a Chinese community section to the docs sidebars.
 - Disabled the mode-pill animation for `prefers-reduced-motion`.
 
 ### Fixed
@@ -1241,7 +1241,7 @@ This changelog was generated from the repository Git history and release tags. V
 ### Changed
 - Expanded interactive Ask streaming from GPT-5.6 to documented streaming- and function-calling-capable official OpenAI models, while keeping GPT-5.5 Pro and other unsupported variants non-streaming.
 - Routed Responses-only GPT-5 Pro variants through the Responses API and retained Chat Completions streaming for other supported OpenAI models.
-- Enabled interactive Ask streaming for Anthropic, Azure OpenAI, Gemini, DeepSeek, xAI, Mistral, Nvidia NIM, Groq, Together AI, Fireworks, z.ai, OpenRouter, WebBrain Cloud, llama.cpp, Ollama, LM Studio, Jan, vLLM, SGLang, and LocalAI with provider-specific terminal-event validation.
+- Enabled interactive Ask streaming for Anthropic, Azure OpenAI, Gemini, DeepSeek, xAI, Mistral, Nvidia NIM, Groq, Together AI, Fireworks, z.ai, OpenRouter, WebBrain Compass, llama.cpp, Ollama, LM Studio, Jan, vLLM, SGLang, and LocalAI with provider-specific terminal-event validation.
 - Generalized the Advanced streaming control and made safe transport/protocol fallback silent: the affected generation retries non-streaming once, then streaming stays disabled for the rest of that run.
 
 ### Fixed
@@ -1419,7 +1419,7 @@ This changelog was generated from the repository Git history and release tags. V
 
 ### Changed
 - Updated OpenAI model usage to **gpt-5.4-nano-2026-03-17** and switched to `max_completion_tokens` for completion limits.
-- Switched WebBrain Cloud provider integration from **GitHub Models** to direct **OpenAI API** calls (using `OPENAI_SECRET` via curl), improving consistency across providers.
+- Switched WebBrain Compass provider integration from **GitHub Models** to direct **OpenAI API** calls (using `OPENAI_SECRET` via curl), improving consistency across providers.
 - Updated Chrome and Firefox builds to reflect the provider/model changes and associated configuration/UI updates.
 
 ### Fixed
@@ -1557,11 +1557,11 @@ This changelog was generated from the repository Git history and release tags. V
 ## [23.3.6] - 2026-07-15
 
 ### Added
-- Added a default-on **Help Improve WebBrain** control at the bottom of the visible Settings → General area in Chrome and Firefox. WebBrain Cloud requests now send the current choice as `X-WebBrain-Help-Improve: 1` or `0`; local-model and bring-your-own API requests never receive that header.
+- Added a default-on **Help Improve WebBrain** control at the bottom of the visible Settings → General area in Chrome and Firefox. WebBrain Compass requests now send the current choice as `X-WebBrain-Help-Improve: 1` or `0`; local-model and bring-your-own API requests never receive that header.
 
 ### Changed
-- Updated the public privacy policy and developer data-flow documentation to disclose selected WebBrain Cloud interaction retention and model-improvement use, the future-interaction opt-out, a 12-month raw-data limit, and a five-year limit for de-identified datasets.
-- Added opaque per-conversation WebBrain Cloud session grouping across main, planner, compaction, intent, memory, and vision generations, with permanent opt-out tainting and no collection metadata on local or bring-your-own providers.
+- Updated the public privacy policy and developer data-flow documentation to disclose selected WebBrain Compass interaction retention and model-improvement use, the future-interaction opt-out, a 12-month raw-data limit, and a five-year limit for de-identified datasets.
+- Added opaque per-conversation WebBrain Compass session grouping across main, planner, compaction, intent, memory, and vision generations, with permanent opt-out tainting and no collection metadata on local or bring-your-own providers.
 - Added encrypted, compressed, text-and-tool-only Cloud improvement storage with image omission, authenticated session browsing, de-identified JSONL export, 12-month pruning, and isolated OpenRouter logging/no-logging key routing.
 
 ### Tests
@@ -1868,12 +1868,12 @@ This changelog was generated from the repository Git history and release tags. V
 ## [20.1.0] - 2026-07-03
 
 ### Changed
-- Raised the built-in WebBrain Cloud provider context window to 1,000,000 tokens in Chrome and Firefox, while migrating stored legacy 256k configs forward without dropping saved API keys.
+- Raised the built-in WebBrain Compass provider context window to 1,000,000 tokens in Chrome and Firefox, while migrating stored legacy 256k configs forward without dropping saved API keys.
 - Scaled the agent's soft context character and message budgets from the active provider token budget, so 1M-context providers no longer compact at the legacy 80k-character or 50-message limits.
 - Updated release metadata, Settings subtitle versions, Chrome / Firefox manifests, package versions, and browser architecture docs for 20.1.0.
 
 ### Tests
-- Added Chrome and Firefox regression coverage for the WebBrain Cloud 1M default, legacy context-window migration, adaptive character/message context budgets, and large-window conversations avoiding premature compaction.
+- Added Chrome and Firefox regression coverage for the WebBrain Compass 1M default, legacy context-window migration, adaptive character/message context budgets, and large-window conversations avoiding premature compaction.
 
 ## [20.0.0] - 2026-07-03
 
@@ -2105,17 +2105,17 @@ This changelog was generated from the repository Git history and release tags. V
 
 ### Added
 - Added XML-style raw tool-call parsing for Chrome and Firefox so local/chat-template models that emit `<tool_call><function=...><parameter=...>` output can execute tools instead of returning raw markup.
-- Added a WebBrain Cloud billing panel in Chrome and Firefox settings with device-bound Stripe account links, localized account copy, and expanded WebBrain Cloud provider notes for subscription, billing, and privacy links.
+- Added a WebBrain Compass billing panel in Chrome and Firefox settings with device-bound Stripe account links, localized account copy, and expanded WebBrain Compass provider notes for subscription, billing, and privacy links.
 - Added Polish UI locale support for the Chrome and Firefox settings/payment flows.
 
 ### Changed
-- Updated WebBrain Cloud `/subscribe` URLs and 402 allowance messages to include the device GUID as Stripe `client_reference_id`, and made the subscribe page require a device-bound link before redirecting to checkout.
+- Updated WebBrain Compass `/subscribe` URLs and 402 allowance messages to include the device GUID as Stripe `client_reference_id`, and made the subscribe page require a device-bound link before redirecting to checkout.
 - Reworded the subscribe fallback page to tell users with outdated extension links to update the browser plugin.
 - Documented the newer slash commands in the English, French, and Chinese README files.
 - Updated release metadata, Settings subtitle versions, architecture docs, Chrome / Firefox manifests, and package versions for 17.2.0.
 
 ### Fixed
-- Purged legacy `auth.webbrain.one` token, email, and default-model storage during settings startup now that WebBrain Cloud billing is device-GUID based.
+- Purged legacy `auth.webbrain.one` token, email, and default-model storage during settings startup now that WebBrain Compass billing is device-GUID based.
 - Firefox side-panel message bubbles now expose copy buttons on user messages, with styling that remains legible on accent-colored bubbles.
 - Suppressed streamed raw tool-call text before rendered tool steps, so fallback tool calls do not linger as assistant text.
 
@@ -2125,7 +2125,7 @@ This changelog was generated from the repository Git history and release tags. V
 ## [17.1.0] - 2026-06-24
 
 ### Added
-- Introduced a better payment UI for WebBrain Cloud: the quota-exceeded error now surfaces a Subscribe button that links users directly to upgrade their plan, with the button persisting and rebinding across chat restores.
+- Introduced a better payment UI for WebBrain Compass: the quota-exceeded error now surfaces a Subscribe button that links users directly to upgrade their plan, with the button persisting and rebinding across chat restores.
 
 ### Changed
 - Translated the Subscribe button strings into all supported locales.
@@ -2248,7 +2248,7 @@ This changelog was generated from the repository Git history and release tags. V
 
 ### Changed
 - Updated release metadata, Settings subtitle versions, architecture docs, Chrome / Firefox manifests, and package versions for 15.1.0.
-- Updated README and architecture docs to describe WebBrain Cloud 1.0 as the default managed cloud option and document the scheduled-task system.
+- Updated README and architecture docs to describe WebBrain Compass 1.0 as the default managed cloud option and document the scheduled-task system.
 - Refreshed release artwork and regenerated packaged Chrome / Firefox submission archives.
 
 ### Fixed
@@ -2335,7 +2335,7 @@ This changelog was generated from the repository Git history and release tags. V
 ## [14.0.0] - 2026-06-18
 
 ### Changed
-- WebBrain Cloud is now the default provider for new WebBrain configurations.
+- WebBrain Compass is now the default provider for new WebBrain configurations.
 - Updated release metadata, Settings subtitle versions, architecture docs, and Chrome / Firefox manifests for 14.0.0.
 
 ### Fixed

diff --git a/README.fr.md b/README.fr.md
@@ -77,7 +77,7 @@ Trois modes contrôlent ce que l'agent a le droit de faire :
 
 ## Choisir un modèle
 
-**WebBrain Cloud 1.0** est l'option par défaut : ni clé API, ni configuration
+**WebBrain Compass 1.0** est l'option par défaut : ni clé API, ni configuration
 locale.
 
 **Les modèles locaux** ne demandent pas non plus de clé API. Pointez WebBrain

diff --git a/README.md b/README.md
@@ -74,7 +74,7 @@ Three modes control what the agent is allowed to do:
 
 ## Pick a model
 
-**WebBrain Cloud 1.0** is the default and needs no API key or local setup.
+**WebBrain Compass 1.0** is the default and needs no API key or local setup.
 
 **Local models** need no API key either. Point WebBrain at any OpenAI-compatible
 server:

diff --git a/README.zh-CN.md b/README.zh-CN.md
@@ -71,7 +71,7 @@ git clone https://github.com/webbrain-one/webbrain.git
 
 ## 选择模型
 
-**WebBrain Cloud 1.0** 是默认选项，无需 API 密钥或本地配置。
+**WebBrain Compass 1.0** 是默认选项，无需 API 密钥或本地配置。
 
 **本地模型** 同样无需 API 密钥。将 WebBrain 指向任意 OpenAI 兼容服务即可：
 

diff --git a/TODOs.md b/TODOs.md
@@ -156,7 +156,7 @@ work is staging/optionality and in-product explanations.
 
 ---
 
-## 7. Lock down the WebBrain Cloud auth handoff
+## 7. Lock down the WebBrain Compass auth handoff
 
 `src/chrome/src/ui/settings.js` accepts `WB_AUTH_TOKEN` from `window.message`
 and writes the token into extension storage, then auto-configures the WebBrain

diff --git a/assets/webstore-explainer-2026/06-launch-offer.png b/assets/webstore-explainer-2026/06-launch-offer.png
diff --git a/assets/webstore-explainer-2026/README.md b/assets/webstore-explainer-2026/README.md
@@ -39,7 +39,7 @@ Files (1280×800):
 - 03-ask-any-page.png: Ask mode, cropped to the answer panel
 - 04-any-llm.png: Model picker, cropped to the provider dropdown
 - 05-plan-before-act.png: Plan review with Approve/Adjust before actions run
-- 06-launch-offer.png: WebBrain Cloud $5/mo (reg. $8), Save 35%
+- 06-launch-offer.png: WebBrain Compass $5/mo (reg. $8), Save 35%
 - 07-social-proof.png: ~1000 GitHub stars, ~50 contributors, GPL — repo bar with contributor avatars
 
 Light-background alternates of the two dark slides (originals kept, use whichever fits the gallery):

diff --git a/assets/webstore-explainer-2026/render.mjs b/assets/webstore-explainer-2026/render.mjs
@@ -381,7 +381,7 @@ function offerScene() {
     theme: 'dark',
     body: `
       <div style="height:100%; display:flex; flex-direction:column; align-items:center; justify-content:center; text-align:center;">
-        <h1 style="font-size:60px;">WebBrain Cloud launch pricing</h1>
+        <h1 style="font-size:60px;">WebBrain Compass launch pricing</h1>
         <div style="display:flex; align-items:baseline; gap:28px; margin-top:30px;">
           <!-- Bricolage sets line-through low on heavy figures, so the strike is drawn manually. -->
           <span class="num" style="position:relative; font-size:60px; line-height:1; color:var(--muted);">$8

diff --git a/docs/THREAT-MODEL.md b/docs/THREAT-MODEL.md
@@ -63,7 +63,7 @@ The defensible claim is *not* "we're more secure than everyone." It's that the s
 
 1. Is page-derived content structurally isolated from the instruction path? (We do this and test it.)
 2. Is the action/automation surface bounded, or does the agent inherit full ambient authority? (Our gap G1/G2/G4 — being closed.)
-3. Where does inference run, and what leaves the device? (The selected provider determines this: WebBrain Cloud and bring-your-own cloud providers receive the request context; local model runtimes keep inference on the machine, while a local gateway may forward it upstream.)
+3. Where does inference run, and what leaves the device? (The selected provider determines this: WebBrain Compass and bring-your-own cloud providers receive the request context; local model runtimes keep inference on the machine, while a local gateway may forward it upstream.)
 4. Is there evidence, or just assertions? (Adversarial corpus + ablation, in-repo.)
 
 Before making any *comparative* claim about a specific competitor (Edge's AI, OpenAI's browser, the Claude browser, etc.), verify their actual behaviour — don't assert it. The strong, honest line is "here are the dimensions; here's exactly where we stand on each, with tests" and let the comparison speak for itself.

diff --git a/docs/architecture.md b/docs/architecture.md
@@ -245,7 +245,7 @@ Official OpenAI GPT-5.6 and streaming-capable Responses-only GPT-5 Pro variants
 use Responses streaming. Other supported official OpenAI models use Chat
 Completions streaming. Anthropic uses its native Messages event parser, Azure
 OpenAI uses its deployment-based parser, and Gemini, DeepSeek, xAI, Mistral,
-Nvidia NIM, Groq, Together AI, Fireworks, z.ai, OpenRouter, WebBrain Cloud,
+Nvidia NIM, Groq, Together AI, Fireworks, z.ai, OpenRouter, WebBrain Compass,
 Ollama, LM Studio, Jan, vLLM, SGLang, LocalAI, and Unsloth Studio use the OpenAI-compatible
 Chat Completions parser. z.ai streaming tool calls add its documented
 `tool_stream` request flag. llama.cpp uses its dedicated OpenAI-compatible
@@ -586,10 +586,10 @@ copied nor fingerprinted in request events. Policy revisions are bumped when
 controlled prompt templates or tool-exposure rules change; private request
 content does not affect them.
 
-WebBrain Cloud runs also have a separate consent-gated terminal-runtime path.
+WebBrain Compass runs also have a separate consent-gated terminal-runtime path.
 After an executed tool result is made durable in `chrome.storage.local`, a
-bounded `terminal_runtime` envelope is sent to the Cloud improvement endpoint.
-Transient failures remain in the outbox for the next Cloud run; acknowledged or
+bounded `terminal_runtime` envelope is sent to the Compass improvement endpoint.
+Transient failures remain in the outbox for the next Compass run; acknowledged or
 non-retryable records are removed. This path does not depend on optional local
 IndexedDB tracing, is disabled for local/bring-your-own providers, and never
 blocks the visible answer on the network request. Chrome and Firefox use the