Merge remote-tracking branch 'origin/main' into garrytan/openclaw-plan

2026-05-05 13:15:24 +02:00 · 2026-04-04 16:08:14 -07:00
parent 21840c4c67 04b709d91a
commit 04f1fb64c7
98 changed files with 16663 additions and 520 deletions
@@ -0,0 +1,182 @@
+# Adding a New Host to gstack
+
+gstack uses a declarative host config system. Each supported AI coding agent
+(Claude, Codex, Factory, Kiro, OpenCode, Slate, Cursor, OpenClaw) is defined
+as a typed TypeScript config object. Adding a new host means creating one file
+and re-exporting it. Zero code changes to the generator, setup, or tooling.
+
+## How it works
+
+```
+hosts/
+├── claude.ts        # Primary host
+├── codex.ts         # OpenAI Codex CLI
+├── factory.ts       # Factory Droid
+├── kiro.ts          # Amazon Kiro
+├── opencode.ts      # OpenCode
+├── slate.ts         # Slate (Random Labs)
+├── cursor.ts        # Cursor
+├── openclaw.ts      # OpenClaw (hybrid: config + adapter)
+└── index.ts         # Registry: imports all, derives Host type
+```
+
+Each config file exports a `HostConfig` object that tells the generator:
+- Where to put generated skills (paths)
+- How to transform frontmatter (allowlist/denylist fields)
+- What Claude-specific references to rewrite (paths, tool names)
+- What binary to detect for auto-install
+- What resolver sections to suppress
+- What assets to symlink at install time
+
+The generator, setup script, platform-detect, uninstall, health checks, worktree
+copy, and tests all read from these configs. None of them have per-host code.
+
+## Step-by-step: add a new host
+
+### 1. Create the config file
+
+Copy an existing config as a starting point. `hosts/opencode.ts` is a good
+minimal example. `hosts/factory.ts` shows tool rewrites and conditional fields.
+`hosts/openclaw.ts` shows the adapter pattern for hosts with different tool models.
+
+Create `hosts/myhost.ts`:
+
+```typescript
+import type { HostConfig } from '../scripts/host-config';
+
+const myhost: HostConfig = {
+  name: 'myhost',
+  displayName: 'MyHost',
+  cliCommand: 'myhost',        // binary name for `command -v` detection
+  cliAliases: [],              // alternative binary names
+
+  globalRoot: '.myhost/skills/gstack',
+  localSkillRoot: '.myhost/skills/gstack',
+  hostSubdir: '.myhost',
+  usesEnvVars: true,           // false only for Claude (uses literal ~ paths)
+
+  frontmatter: {
+    mode: 'allowlist',         // 'allowlist' keeps only listed fields
+    keepFields: ['name', 'description'],
+    descriptionLimit: null,    // set to 1024 for hosts with limits
+  },
+
+  generation: {
+    generateMetadata: false,   // true only for Codex (openai.yaml)
+    skipSkills: ['codex'],     // codex skill is Claude-only
+  },
+
+  pathRewrites: [
+    { from: '~/.claude/skills/gstack', to: '~/.myhost/skills/gstack' },
+    { from: '.claude/skills/gstack', to: '.myhost/skills/gstack' },
+    { from: '.claude/skills', to: '.myhost/skills' },
+  ],
+
+  runtimeRoot: {
+    globalSymlinks: ['bin', 'browse/dist', 'browse/bin', 'gstack-upgrade', 'ETHOS.md'],
+    globalFiles: { 'review': ['checklist.md', 'TODOS-format.md'] },
+  },
+
+  install: {
+    prefixable: false,
+    linkingStrategy: 'symlink-generated',
+  },
+
+  learningsMode: 'basic',
+};
+
+export default myhost;
+```
+
+### 2. Register in the index
+
+Edit `hosts/index.ts`:
+
+```typescript
+import myhost from './myhost';
+
+// Add to ALL_HOST_CONFIGS array:
+export const ALL_HOST_CONFIGS: HostConfig[] = [
+  claude, codex, factory, kiro, opencode, slate, cursor, openclaw, myhost
+];
+
+// Add to re-exports:
+export { claude, codex, factory, kiro, opencode, slate, cursor, openclaw, myhost };
+```
+
+### 3. Add to .gitignore
+
+Add `.myhost/` to `.gitignore` (generated skill docs are gitignored).
+
+### 4. Generate and verify
+
+```bash
+# Generate skill docs for the new host
+bun run gen:skill-docs --host myhost
+
+# Verify output exists and has no .claude/skills leakage
+ls .myhost/skills/gstack-*/SKILL.md
+grep -r ".claude/skills" .myhost/skills/ | head -5
+# (should be empty)
+
+# Generate for all hosts (includes the new one)
+bun run gen:skill-docs --host all
+
+# Health dashboard shows the new host
+bun run skill:check
+```
+
+### 5. Run tests
+
+```bash
+bun test test/gen-skill-docs.test.ts
+bun test test/host-config.test.ts
+```
+
+The parameterized smoke tests automatically pick up the new host. Zero test
+code to write. They verify: output exists, no path leakage, valid frontmatter,
+freshness check passes, codex skill excluded.
+
+### 6. Update README.md
+
+Add install instructions for the new host in the appropriate section.
+
+## Config field reference
+
+See `scripts/host-config.ts` for the full `HostConfig` interface with JSDoc
+comments on every field.
+
+Key fields:
+
+| Field | Purpose |
+|-------|---------|
+| `frontmatter.mode` | `allowlist` (keep only listed) or `denylist` (strip listed) |
+| `frontmatter.descriptionLimit` | Max chars, `null` for no limit |
+| `frontmatter.descriptionLimitBehavior` | `error` (fail build), `truncate`, `warn` |
+| `frontmatter.conditionalFields` | Add fields based on template values (e.g., sensitive → disable-model-invocation) |
+| `frontmatter.renameFields` | Rename template fields (e.g., voice-triggers → triggers) |
+| `pathRewrites` | Literal replaceAll on content. Order matters. |
+| `toolRewrites` | Rewrite Claude tool names (e.g., "use the Bash tool" → "run this command") |
+| `suppressedResolvers` | Resolver functions that return empty for this host |
+| `coAuthorTrailer` | Git co-author string for commits |
+| `boundaryInstruction` | Anti-prompt-injection warning for cross-model invocations |
+| `adapter` | Path to adapter module for complex transformations |
+
+## Adapter pattern (for hosts with different tool models)
+
+If string-replace tool rewrites aren't enough (the host has fundamentally
+different tool semantics), use the adapter pattern. See `hosts/openclaw.ts`
+and `scripts/host-adapters/openclaw-adapter.ts`.
+
+The adapter runs as a post-processing step after all generic rewrites. It
+exports `transform(content: string, config: HostConfig): string`.
+
+## Validation
+
+The `validateHostConfig()` function in `scripts/host-config.ts` checks:
+- Name: lowercase alphanumeric with hyphens
+- CLI command: alphanumeric with hyphens/underscores
+- Paths: safe characters only (alphanumeric, `.`, `/`, `$`, `{}`, `~`, `-`, `_`)
+- No duplicate names, hostSubdirs, or globalRoots across configs
+
+Run `bun run scripts/host-config-export.ts validate` to check all configs.
@@ -0,0 +1,376 @@
+# GStack Browser V0 — The AI-Native Development Browser
+
+**Date:** 2026-03-30
+**Author:** Garry Tan + Claude Code
+**Status:** Phase 1a shipped, Phase 1b in progress
+**Branch:** garrytan/gstack-as-browser
+
+## The Thesis
+
+Every other AI browser (Atlas, Dia, Comet, Chrome Auto Browse) starts with a
+consumer browser and bolts AI onto it. GStack Browser inverts this. It starts
+with Claude Code as the runtime and gives it a browser viewport.
+
+The agent is the primary citizen. The browser is the canvas. Skills are
+first-class capabilities. You don't "use a browser with AI help." You use
+an AI that can see and interact with the web.
+
+This is the IDE for the post-IDE era. Code lives in the terminal. The product
+lives in the browser. The AI works across both simultaneously. What Cursor did
+for text editors, GStack Browser does for the browser.
+
+## What It Is Today (Phase 1a, shipped)
+
+A double-clickable macOS .app that wraps Playwright's Chromium with the gstack
+sidebar extension baked in. You open it and Claude Code can see your screen,
+navigate pages, fill forms, take screenshots, inspect CSS, clean up overlays,
+and run any gstack skill. All without touching a terminal.
+
+```
+GStack Browser.app (389MB, 189MB DMG)
+├── Compiled browse binary (58MB) — CLI + HTTP server
+├── Chrome extension (172KB) — sidebar, activity feed, inspector
+├── Playwright's Chromium (330MB) — the actual browser
+└── Launcher script — binds project dir, sets env vars
+```
+
+Launch → Chromium opens with sidebar → extension auto-connects to browse server
+→ agent ready in ~5 seconds.
+
+## What It Will Be
+
+### Phase 1b: Developer UX (next)
+
+**Command Palette (Cmd+K):** The signature interaction. Opens a fuzzy-filtered
+skill picker. Type "/qa" to start QA testing, "/investigate" to debug, "/ship"
+to create a PR. Skills are fetched from the browse server, not hardcoded. The
+palette is the entry point to everything.
+
+**Quick Screenshot (Cmd+Shift+S):** Capture the current viewport and pipe it into
+the sidebar chat with "What do you see?" context. The AI analyzes the screenshot
+and gives you actionable feedback. Visual bug reports in one keystroke.
+
+**Status Bar:** A persistent 30px bar at the bottom of every page. Shows agent
+status (idle/thinking), workspace name, current branch, and auto-detected dev
+servers. Click a dev server pill to navigate. Always-visible context about what
+the AI is doing.
+
+**Auto-Detect Dev Servers:** On launch, scans common ports (3000, 3001, 4200,
+5173, 5174, 8000, 8080). If exactly one server is found, auto-navigates to it.
+Dev server pills in the status bar for one-click switching.
+
+### Phase 2: BoomLooper Integration
+
+The sidebar connects to BoomLooper's Phoenix/Elixir APIs instead of a local
+`claude -p` subprocess. BoomLooper provides:
+
+- **Multi-agent orchestration.** Spawn 5 agents in parallel, each with its own
+  browser tab. One runs QA, one does design review, one watches for regressions.
+- **Docker infrastructure.** Each agent gets an isolated container. The browser
+  inside the container tests the dev server. No port conflicts, no state leakage.
+- **Session persistence.** Agent conversations survive browser restarts. Pick up
+  where you left off.
+- **Team visibility.** Your teammates can watch what your agents are doing in
+  real-time. Like pair programming, but the pair is 5 AI agents and you're the
+  conductor.
+
+### Phase 3: Browse as BoomLooper Tool
+
+The browse binary becomes an MCP tool in BoomLooper. Agents in Docker containers
+use browse commands to test dev servers, take screenshots, fill forms, and verify
+deployments. Cross-platform compilation (linux-arm64/x64) required.
+
+### Phase 4: Chromium Fork (trigger-gated)
+
+When the extension side panel hits hard API limits, GStack Browser ships to
+external users, build infra exists, and the business justifies maintenance:
+fork Chromium. Brave's `chromium_src` override pattern, CC-powered 6-week
+rebases (2-4 hours with CC vs 1-2 weeks human). ~20-30 files modified.
+
+### Phase 5: Native Shell
+
+SwiftUI/AppKit app shell with native sidebar, isolated Chromium service. Full
+platform integration. May be superseded by Phase 4 if the Chromium fork includes
+a native sidebar.
+
+## Vision: What an AI Browser Can Do
+
+### 1. See What You See
+
+The browser is the AI's eyes. Not through screenshots (though it can do that),
+but through DOM access, CSS inspection, network monitoring, and accessibility
+tree parsing. The AI understands the page structure, not just the pixels.
+
+**Today:** `snapshot` command returns an accessibility-tree representation of any
+page. The AI can "see" every button, link, form field, and text element. Element
+references (`@e1`, `@e2`) let the AI click, fill, and interact.
+
+**Next:** Real-time page observation. The AI notices when a page changes, when an
+error appears in the console, when a network request fails. Proactive debugging
+without being asked.
+
+**Future:** Visual understanding. The AI compares before/after screenshots to catch
+visual regressions. Pixel-level design review. "This button moved 3px left and the
+font changed from 14px to 13px."
+
+### 2. Act on What It Sees
+
+Not just reading pages, but interacting with them like a human user would.
+
+**Today:** Click, fill, select, hover, type, scroll, upload files, handle dialogs,
+navigate, manage tabs. All via simple commands through the browse server.
+
+**Next:** Multi-step user flows. "Log in, go to settings, change the timezone,
+verify the confirmation message." The AI chains commands with verification at each
+step.
+
+**Future:** Autonomous QA agent. "Test every link on this page. Fill every form.
+Try to break it." The AI runs exhaustive interaction testing without a script.
+Finds bugs a human tester would miss because it tries combinations humans don't
+think of.
+
+### 3. Write Code While Browsing
+
+This is the key differentiator. The AI can see the bug in the browser AND fix it
+in the code simultaneously.
+
+**Today:** The sidebar chat connects to Claude Code. You say "this button is
+misaligned" and the AI reads the CSS, identifies the issue, and proposes a fix.
+The `/design-review` skill takes screenshots, identifies visual issues, and
+commits fixes with before/after evidence.
+
+**Next:** Live reload loop. The AI edits CSS/HTML, the browser auto-reloads, the
+AI verifies the fix visually. No human in the loop for simple visual fixes.
+"Fix every spacing issue on this page" becomes a 30-second task.
+
+**Future:** Full-stack debugging. The AI sees a 500 error in the browser, reads
+the server logs, traces to the failing line, writes the fix, and verifies in the
+browser. One command: "This page is broken. Fix it."
+
+### 4. Understand the Whole Stack
+
+The browser isn't just a viewport. It's a window into the application's health.
+
+**Today:**
+- Console log capture — every `console.log`, `console.error`, and warning
+- Network request monitoring — every XHR, fetch, websocket, and static asset
+- Performance metrics — Core Web Vitals, resource timing, paint events
+- Cookie and storage inspection — read and write localStorage, sessionStorage
+- CSS inspection — computed styles, box model, rule cascade
+
+**Next:**
+- Network request replay — "replay this failing request with different params"
+- Performance regression detection — "this page is 200ms slower than yesterday"
+- Dependency auditing — "this page loads 47 third-party scripts"
+- Accessibility auditing — "this form has no labels, these colors fail contrast"
+
+**Future:**
+- Full application telemetry — CPU, memory, GPU usage in real-time
+- Cross-browser testing — same test suite across Chrome, Firefox, Safari
+- Real user monitoring correlation — "this bug affects 12% of production users"
+
+### 5. The Workspace Model
+
+The browser IS the workspace. Not a tab in a workspace. The workspace itself.
+
+**Today:** Each browser session is bound to a project directory. The sidebar shows
+the current branch. The status bar shows detected dev servers.
+
+**Next:** Multi-project support. Switch between projects without closing the
+browser. Each project gets its own set of tabs, its own agent, its own context.
+Like VSCode workspaces, but for the browser.
+
+**Future:** Team workspaces. Multiple developers share a browser workspace. See
+each other's agents working. Collaborative debugging where one person navigates
+and the other watches the AI fix things in real-time.
+
+### 6. Skills as Browser Capabilities
+
+Every gstack skill becomes a browser capability.
+
+| Skill | Browser Capability |
+|-------|-------------------|
+| `/qa` | Test every page, find bugs, fix them, verify fixes |
+| `/design-review` | Screenshot → analyze → fix CSS → screenshot again |
+| `/investigate` | See the error in browser → trace to code → fix → verify |
+| `/benchmark` | Measure page performance → detect regressions → alert |
+| `/canary` | Monitor deployed site → screenshot periodically → alert on changes |
+| `/ship` | Run tests → review diff → create PR → verify deployment in browser |
+| `/cso` | Audit page for XSS, open redirects, clickjacking in real browser |
+| `/office-hours` | Browse competitor sites → synthesize observations → design doc |
+
+The command palette (Cmd+K) is the hub. You don't need to know the skills exist.
+You type what you want, the fuzzy filter finds the right skill, and the AI runs it
+with the browser as context.
+
+### 7. The Design Loop
+
+AI-powered design is a loop, not a handoff.
+
+```
+Generate mockup (GPT Image API)
+  → Review in browser (side-by-side with live site)
+  → Iterate with feedback ("make the header taller")
+  → Approve direction
+  → Generate production HTML/CSS
+  → Preview in browser
+  → Fine-tune with /design-review
+  → Ship
+```
+
+The browser closes the gap between "what it looks like in Figma" and "what it
+looks like in production." Because the AI can see both simultaneously.
+
+### 8. The Security Loop
+
+CSO review in a real browser, not just static analysis.
+
+- Inject XSS payloads into every input field, check if they execute
+- Test CSRF by replaying requests from a different origin
+- Check for open redirects by navigating to crafted URLs
+- Verify CSP headers are actually enforced (not just present)
+- Test auth flows by manipulating cookies and tokens in real-time
+- Check for clickjacking by loading the site in an iframe
+
+Static analysis catches patterns. Browser testing catches reality.
+
+### 9. The Monitoring Loop
+
+Post-deploy canary monitoring, in a real browser.
+
+```
+Deploy → Browser loads production URL
+  → Screenshot baseline
+  → Every 5 minutes: screenshot, compare, check console
+  → Alert on: visual regression, new console errors, performance drop
+  → Auto-rollback if critical error detected
+```
+
+Synthetic monitoring with AI judgment. Not just "did the page return 200" but
+"does the page look right and work correctly."
+
+## Architecture
+
+```
+-------------------------------------------------------+
+|                  GStack Browser                        |
+|                                                        |
+|  +------------------+  +---------------------------+  |
+|  |   Chromium        |  |   Extension Side Panel    |  |
+|  |   (Playwright)    |  |   ├── Chat (Claude Code)  |  |
+|  |                   |  |   ├── Activity Feed        |  |
+|  |   ┌────────────┐  |  |   ├── Element Refs         |  |
+|  |   │ Status Bar  │  |  |   ├── CSS Inspector        |  |
+|  |   └────────────┘  |  |   ├── Command Palette      |  |
+|  +--------┬──────────+  |   └── Settings             |  |
+|           │              +-------------┬--------------+  |
+-----------┼────────────────────────────┼─────────────────+
+            │                            │
+            v                            v
+  +---------┴-----------+    +-----------┴-----------+
+  |  Browse Server      |    |  Sidebar Agent        |
+  |  (HTTP + SSE)       |    |  (claude -p wrapper)  |
+  |  :34567             |    |  Runs gstack skills   |
+  |                     |    |  Per-tab isolation     |
+  |  Commands:          |    |                       |
+  |  goto, click, fill  |    |  Future: BoomLooper   |
+  |  snapshot, screenshot|   |  GenServer agents     |
+  |  css, inspect, eval |    |                       |
+  +---------┬-----------+    +-----------┬-----------+
+            │                            │
+            v                            v
+  +---------┴-----------+    +-----------┴-----------+
+  |  User's App         |    |  Claude Code          |
+  |  localhost:3000     |    |  (reads/writes code)  |
+  |  (or any URL)       |    |                       |
+  +---------------------+    +-----------------------+
+```
+
+## Competitive Landscape
+
+| Browser | Approach | Differentiator | Weakness |
+|---------|----------|---------------|----------|
+| **Atlas** | Chromium fork + AI layer | Agentic browser, "OWL" isolated Chromium | Consumer-focused, no code integration |
+| **Dia** | AI-native browser | Clean UI, built for AI interaction | No dev tools, no code editing |
+| **Comet** | AI browser | Multi-agent browsing | Early, unclear dev workflow |
+| **Chrome Auto Browse** | Extension | Google's own, deep Chrome integration | Extension-only, no code editing |
+| **Cursor** | VSCode fork + AI | Best-in-class code editing | No browser viewport |
+| **GStack Browser** | CC runtime + browser viewport | See bug in browser, fix in code, verify | Currently macOS-only, no consumer features |
+
+GStack Browser doesn't compete with consumer browsers. It competes with the
+workflow of switching between browser and editor. The goal is to make that switch
+invisible.
+
+## Design System
+
+From DESIGN.md:
+- **Primary accent:** Amber-500 (#F59E0B) — agent active, focus states, pulse
+- **Background:** Zinc-950 (#09090B) through Zinc-800 (#27272A) — dark, dense
+- **Typography:** JetBrains Mono (code/status), DM Sans (UI/labels)
+- **Border radius:** 8px (md), 12px (lg), full (pills)
+- **Motion:** Pulse animation on agent active, 200ms transitions
+- **Layout:** Sidebar (right), status bar (bottom), palette (centered overlay)
+
+## Implementation Status
+
+| Component | Status | Notes |
+|-----------|--------|-------|
+| .app bundle | **SHIPPED** | 389MB, launches in ~5s |
+| DMG packaging | **SHIPPED** | 189MB compressed |
+| `GSTACK_CHROMIUM_PATH` | **SHIPPED** | Custom Chromium binary support |
+| `BROWSE_EXTENSIONS_DIR` | **SHIPPED** | Extension path override |
+| Auth via `/health` | **SHIPPED** | Replaces .auth.json file approach, auto-refreshes on server restart |
+| Build script | **SHIPPED** | `scripts/build-app.sh` |
+| Model routing | **SHIPPED** | Sonnet for actions, Opus for analysis (`pickSidebarModel`) |
+| Debug logging | **SHIPPED** | 40+ silent catches → prefixed console logging across 4 files |
+| No idle timeout (headed) | **SHIPPED** | Browser stays alive as long as window is open |
+| Cookie import button | **SHIPPED** | One-click in sidebar footer, opens `/cookie-picker` |
+| Sidebar arrow hint | **SHIPPED** | Points to sidebar, hides only when sidebar actually opens |
+| Architecture doc | **SHIPPED** | `docs/designs/SIDEBAR_MESSAGE_FLOW.md` |
+| Command palette | Planned | Phase 1b |
+| Quick screenshot | Planned | Phase 1b |
+| Status bar | Planned | Phase 1b |
+| Dev server detection | Planned | Phase 1b |
+| BoomLooper integration | Future | Phase 2 |
+| Cross-platform | Future | Phase 3 |
+| Chromium fork | Trigger-gated | Phase 4 |
+| Native shell | Deferred | Phase 5 |
+
+## The 12-Month Vision
+
+```
+TODAY (Phase 1)               6 MONTHS (Phase 2-3)          12 MONTHS (Phase 4-5)
+─────────────                 ──────────────────            ────────────────────
+macOS .app wrapper            BoomLooper multi-agent         Chromium fork OR
+Extension sidebar             Docker containers              Native SwiftUI shell
+Local claude -p agent         Team workspaces                Cross-platform
+Single project                Linux/x64 browse               Auto-update
+Manual skill invocation       Autonomous QA loops            Skill marketplace
+                              Performance monitoring          Plugin API
+                              Real-time collaboration         Enterprise features
+```
+
+The 12-month ideal: you open GStack Browser, it detects your project, starts
+your dev server, runs your test suite, and reports what's broken. You say "fix
+it" and the AI fixes every bug, verifies each fix visually, and creates a PR.
+You review the PR in the same browser, approve it, and the AI deploys it and
+monitors the canary. All in one window.
+
+That's the browser as AI workspace. Not a browser with AI bolted on. An AI
+with a browser bolted on.
+
+## Review History
+
+This plan went through 4 reviews:
+
+1. **CEO Review** (`/plan-ceo-review`, SELECTIVE EXPANSION) — 9 scope proposals,
+   3 accepted (Cmd+K, Cmd+Shift+S, status bar), 5 deferred, 1 skipped
+2. **Design Review** (`/plan-design-review`) — scored 5/10 → 8/10, 9 design
+   decisions added, 2 approved mockups generated
+3. **Eng Review** (`/plan-eng-review`) — 4 issues found, 0 critical gaps,
+   test plan produced
+4. **Codex Review** (outside voice) — 9 findings, 3 critical gaps caught
+   (server bundling, auth file location, project binding). All resolved.
+
+The Codex review caught 3 real architecture gaps that survived 3 prior reviews.
+Cross-model review works.
@@ -0,0 +1,190 @@
+# Sidebar Message Flow
+
+How the GStack Browser sidebar actually works. Read this before touching
+sidepanel.js, background.js, content.js, server.ts sidebar endpoints,
+or sidebar-agent.ts.
+
+## Components
+
+```
+┌─────────────────┐     ┌──────────────┐     ┌─────────────┐     ┌────────────────┐
+│  sidepanel.js   │────▶│ background.js│────▶│  server.ts   │────▶│sidebar-agent.ts│
+│  (Chrome panel) │     │ (svc worker) │     │  (Bun HTTP)  │     │  (Bun process) │
+└─────────────────┘     └──────────────┘     └─────────────┘     └────────────────┘
+        ▲                                           │                      │
+        │           polls /sidebar-chat             │    polls queue file   │
+        └───────────────────────────────────────────┘                      │
+                                                    ◀──────────────────────┘
+                                                    POST /sidebar-agent/event
+```
+
+## Startup Timeline
+
+```
+T+0ms     CLI runs `$B connect`
+            ├── Server starts on port 34567
+            ├── Writes state to .gstack/browse.json (pid, port, token)
+            ├── Launches headed Chromium with extension
+            └── Clears sidebar-agent-queue.jsonl
+
+T+500ms   sidebar-agent.ts spawned by CLI
+            ├── Reads auth token from .gstack/browse.json
+            ├── Creates queue file if missing
+            ├── Sets lastLine = current line count
+            └── Starts polling every 200ms
+
+T+1-3s    Extension loads in Chromium
+            ├── background.js: health poll every 1s (fast startup)
+            │     └── GET /health → gets auth token
+            ├── content.js: injects on welcome page
+            │     └── Does NOT fire gstack-extension-ready (waits for sidebar)
+            └── Side panel: may auto-open via chrome.sidePanel.open()
+
+T+2-10s   Side panel connects
+            ├── tryConnect() → asks background for port/token
+            ├── Fallback: direct GET /health for token
+            ├── updateConnection(url, token)
+            │     ├── Starts chat polling (1s interval)
+            │     ├── Starts tab polling (2s interval)
+            │     ├── Connects SSE activity stream
+            │     └── Sends { type: 'sidebarOpened' } to background
+            └── background relays to content script → hides welcome arrow
+
+T+10s+    Ready for messages
+```
+
+## Message Flow: User Types → Claude Responds
+
+```
+1. User types "go to hn" in sidebar, hits Enter
+
+2. sidepanel.js sendMessage()
+   ├── Renders user bubble immediately (optimistic)
+   ├── Renders thinking dots immediately
+   ├── Switches to fast poll (300ms)
+   └── chrome.runtime.sendMessage({ type: 'sidebar-command', message, tabId })
+
+3. background.js
+   ├── Gets active Chrome tab URL
+   └── POST /sidebar-command { message, activeTabUrl }
+       with Authorization: Bearer ${authToken}
+
+4. server.ts /sidebar-command handler
+   ├── validateAuth(req)
+   ├── syncActiveTabByUrl(extensionUrl) — syncs Playwright tab to Chrome tab
+   ├── pickSidebarModel(message) — 'sonnet' for actions, 'opus' for analysis
+   ├── Adds user message to chat buffer
+   ├── Builds system prompt + args
+   └── Appends JSON to ~/.gstack/sidebar-agent-queue.jsonl
+
+5. sidebar-agent.ts poll() (within 200ms)
+   ├── Reads new line from queue file
+   ├── Parses JSON entry
+   ├── Checks processingTabs — skips if tab already has agent running
+   └── askClaude(entry) — fire and forget
+
+6. sidebar-agent.ts askClaude()
+   ├── spawn('claude', ['-p', prompt, '--model', model, ...])
+   ├── Streams stdout line-by-line (stream-json format)
+   ├── For each event: POST /sidebar-agent/event { type, tool, text, tabId }
+   └── On close: POST /sidebar-agent/event { type: 'agent_done' }
+
+7. server.ts processAgentEvent()
+   ├── Adds entry to chat buffer (in-memory + disk)
+   ├── On agent_done: sets tab status to 'idle'
+   └── On agent_done: processes next queued message for that tab
+
+8. sidepanel.js pollChat() (every 300ms during fast poll)
+   ├── GET /sidebar-chat?after=${chatLineCount}&tabId=${tabId}
+   ├── Renders new entries (text, tool_use, agent_done)
+   └── On agent idle: removes thinking dots, stops fast poll
+```
+
+## Arrow Hint Hide Flow (4-step signal chain)
+
+The welcome page shows a right-pointing arrow until the sidebar opens.
+
+```
+1. sidepanel.js updateConnection()
+   └── chrome.runtime.sendMessage({ type: 'sidebarOpened' })
+
+2. background.js
+   └── chrome.tabs.sendMessage(activeTabId, { type: 'sidebarOpened' })
+
+3. content.js onMessage handler
+   └── document.dispatchEvent(new CustomEvent('gstack-extension-ready'))
+
+4. welcome.html script
+   └── addEventListener('gstack-extension-ready', () => arrow.classList.add('hidden'))
+```
+
+The arrow does NOT hide when the extension loads. Only when the sidebar connects.
+
+## Auth Token Flow
+
+```
+Server starts → AUTH_TOKEN = crypto.randomUUID()
+    │
+    ├── GET /health (no auth) → returns { token: AUTH_TOKEN }
+    │
+    ├── background.js checkHealth() → authToken = data.token
+    │     └── Refreshes on EVERY health poll (fixes stale token on restart)
+    │
+    ├── sidepanel.js tryConnect() → serverToken from background or /health
+    │     └── Used for chat polling: Authorization: Bearer ${serverToken}
+    │
+    └── sidebar-agent.ts refreshToken() → reads from .gstack/browse.json
+          └── Used for event relay: Authorization: Bearer ${authToken}
+```
+
+If the server restarts, all three components get fresh tokens within 10s
+(background health poll interval).
+
+## Model Routing
+
+`pickSidebarModel(message)` in server.ts classifies messages:
+
+| Pattern | Model | Why |
+|---------|-------|-----|
+| "click @e24", "go to hn", "screenshot" | sonnet | Deterministic tool calls, no thinking needed |
+| "what does this page say?", "summarize" | opus | Needs comprehension |
+| "find bugs", "check for broken links" | opus | Analysis task |
+| "navigate to X and fill the form" | sonnet | Action-oriented, no analysis words |
+
+Analysis words (`what`, `why`, `how`, `summarize`, `describe`, `analyze`, `read X and Y`)
+always override action verbs and force opus.
+
+## Known Failure Modes
+
+| Failure | Symptom | Root Cause | Fix |
+|---------|---------|------------|-----|
+| Stale auth token | "Unauthorized" in input | Server restarted, background had old token | background.js refreshes token on every health poll |
+| Tab ID mismatch | Message sent, no response visible | Server assigned tabId 1, sidebar polling tabId 0 | switchChatTab preserves optimistic UI during switch |
+| Sidebar agent not running | Messages queue forever | Agent process failed to spawn or crashed | Check `ps aux | grep sidebar-agent` |
+| Agent stale token | Agent runs but no events appear in sidebar | sidebar-agent has old token from .gstack/browse.json | Agent re-reads token before each event POST |
+| Queue file missing | spawnClaude fails | Race between server start and agent start | Both sides create file if missing |
+| Optimistic UI blown away | User bubble + dots vanish | switchChatTab replaced DOM with welcome screen | Preserved DOM when lastOptimisticMsg is set |
+
+## Per-Tab Concurrency
+
+Each browser tab can run its own agent simultaneously:
+
+- Server: `tabAgents: Map<number, TabAgentState>` with per-tab queue (max 5)
+- sidebar-agent: `processingTabs: Set<number>` prevents duplicate spawns
+- Two messages on same tab: queued sequentially, processed in order
+- Two messages on different tabs: run concurrently
+
+## File Locations
+
+| Component | File | Runs in |
+|-----------|------|---------|
+| Sidebar UI | `extension/sidepanel.js` | Chrome side panel |
+| Service worker | `extension/background.js` | Chrome background |
+| Content script | `extension/content.js` | Page context |
+| Welcome page | `browse/src/welcome.html` | Page context |
+| HTTP server | `browse/src/server.ts` | Bun (compiled binary) |
+| Agent process | `browse/src/sidebar-agent.ts` | Bun (non-compiled, can spawn) |
+| CLI entry | `browse/src/cli.ts` | Bun (compiled binary) |
+| Queue file | `~/.gstack/sidebar-agent-queue.jsonl` | Filesystem |
+| State file | `.gstack/browse.json` | Filesystem |
+| Chat log | `~/.gstack/sessions/<id>/chat.jsonl` | Filesystem |
@@ -0,0 +1,290 @@
+# Slate Host Integration — Research & Design Doc
+
+**Date:** 2026-04-02
+**Branch:** garrytan/slate-agent-support
+**Status:** Research complete, blocked on host config refactor
+**Supersedes:** None
+
+## What is Slate
+
+Slate is a proprietary coding agent CLI from Random Labs.
+Install: `npm i -g @randomlabs/slate` or `brew install anthropic/tap/slate`.
+License: Proprietary. 85MB compiled Bun binary (arm64/x64, darwin/linux/windows).
+npm package: `@randomlabs/slate@1.0.25` (thin 8.8KB launcher + platform-specific optional deps).
+
+Multi-model: dynamically selects Claude Sonnet/Opus/Haiku, plus other models.
+Built for "swarm orchestration" with extended multi-hour sessions.
+
+## Slate is an OpenCode fork
+
+**Confirmed via binary strings analysis** of the 85MB Mach-O arm64 binary:
+
+- Internal name: `name: "opencode"` (literal string in binary)
+- All `OPENCODE_*` env vars present alongside `SLATE_*` equivalents
+- Shares OpenCode's tool/skill architecture, LSP integration, terminal management
+- Own branding, API endpoints (`api.randomlabs.ai`, `agent-worker-prod.randomlabs.workers.dev`), and config paths
+
+This matters for integration: OpenCode conventions mostly apply, but Slate adds
+its own paths and env vars on top.
+
+## Skill Discovery (confirmed from binary)
+
+Slate scans ALL four directory families for skills. Error messages in binary confirm:
+
+```
+"failed .slate directory scan for skills"
+"failed .claude directory scan for skills"
+"failed .agents directory scan for skills"
+"failed .opencode directory scan for skills"
+```
+
+**Discovery paths (priority order from Slate docs):**
+
+1. `.slate/skills/<name>/SKILL.md` — project-level, highest priority
+2. `~/.slate/skills/<name>/SKILL.md` — global
+3. `.opencode/skills/`, `.agents/skills/` — compatibility fallback
+4. `.claude/skills/` — Claude Code compatibility fallback (lowest)
+5. Custom paths via `slate.json`
+
+**Glob patterns:** `**/SKILL.md` and `{skill,skills}/**/SKILL.md`
+
+**Commands:** Same directory structure but under `commands/` subdirs:
+`/.slate/commands/`, `/.claude/commands/`, `/.agents/commands/`, `/.opencode/commands/`
+
+**Skill frontmatter:** YAML with `name` and `description` fields (per Slate docs).
+No documented length limits on either field.
+
+## Project Instructions
+
+Slate reads both `CLAUDE.md` and `AGENTS.md` for project instructions.
+Both literal strings confirmed in binary. No changes needed to existing
+gstack projects... CLAUDE.md works as-is.
+
+## Configuration
+
+**Config file:** `slate.json` / `slate.jsonc` (NOT opencode.json)
+
+**Config options (from Slate docs):**
+- `privacy` (boolean) — disables telemetry/logging
+- Permissions: `allow`, `ask`, `deny` per tool (`read`, `edit`, `bash`, `grep`, `webfetch`, `websearch`, `*`)
+- Model slots: `models.main`, `models.subagent`, `models.search`, `models.reasoning`
+- MCP servers: local or remote with custom commands and headers
+- Custom commands: `/commands` with templates
+
+The setup script should NOT create `slate.json`. Users configure their own permissions.
+
+## CLI Flags (Headless Mode)
+
+```
+--stream-json / --output-format stream-json  — JSONL output, "compatible with Anthropic Claude Code SDK"
+--dangerously-skip-permissions               — bypass all permission checks (CI/automation)
+--input-format stream-json                   — programmatic input
+-q                                           — non-interactive mode
+-w <dir>                                     — workspace directory
+--output-format text                         — plain text output (default)
+```
+
+**Stream-JSON format:** Slate docs claim "compatible with Anthropic Claude Code SDK."
+Not yet empirically verified. Given OpenCode heritage, likely matches Claude Code's
+NDJSON event schema (type: "assistant", type: "tool_result", type: "result").
+
+**Need to verify:** Run `slate -q "hello" --stream-json` with valid credits and
+capture actual JSONL events before building the session runner parser.
+
+## Environment Variables (from binary strings)
+
+### Slate-specific
+```
+SLATE_API_KEY                              — API key
+SLATE_AGENT                                — agent selection
+SLATE_AUTO_SHARE                           — auto-share setting
+SLATE_CLIENT                               — client identifier
+SLATE_CONFIG                               — config override
+SLATE_CONFIG_CONTENT                       — inline config
+SLATE_CONFIG_DIR                           — config directory
+SLATE_DANGEROUSLY_SKIP_PERMISSIONS         — bypass permissions
+SLATE_DIR                                  — data directory override
+SLATE_DISABLE_AUTOUPDATE                   — disable auto-update
+SLATE_DISABLE_CLAUDE_CODE                  — disable Claude Code integration entirely
+SLATE_DISABLE_CLAUDE_CODE_PROMPT           — disable Claude Code prompt loading
+SLATE_DISABLE_CLAUDE_CODE_SKILLS           — disable .claude/skills/ loading
+SLATE_DISABLE_DEFAULT_PLUGINS              — disable default plugins
+SLATE_DISABLE_FILETIME_CHECK               — disable file time checks
+SLATE_DISABLE_LSP_DOWNLOAD                 — disable LSP auto-download
+SLATE_DISABLE_MODELS_FETCH                 — disable models config fetch
+SLATE_DISABLE_PROJECT_CONFIG               — disable project-level config
+SLATE_DISABLE_PRUNE                        — disable session pruning
+SLATE_DISABLE_TERMINAL_TITLE               — disable terminal title updates
+SLATE_ENABLE_EXA                           — enable Exa search
+SLATE_ENABLE_EXPERIMENTAL_MODELS           — enable experimental models
+SLATE_EXPERIMENTAL                         — enable experimental features
+SLATE_EXPERIMENTAL_BASH_DEFAULT_TIMEOUT_MS — bash timeout override
+SLATE_EXPERIMENTAL_DISABLE_COPY_ON_SELECT  — disable copy on select
+SLATE_EXPERIMENTAL_DISABLE_FILEWATCHER     — disable file watcher
+SLATE_EXPERIMENTAL_EXA                     — Exa search (alt flag)
+SLATE_EXPERIMENTAL_FILEWATCHER             — enable file watcher
+SLATE_EXPERIMENTAL_ICON_DISCOVERY          — icon discovery
+SLATE_EXPERIMENTAL_LSP_TOOL               — LSP tool
+SLATE_EXPERIMENTAL_LSP_TY                 — LSP type checking
+SLATE_EXPERIMENTAL_MARKDOWN               — markdown mode
+SLATE_EXPERIMENTAL_OUTPUT_TOKEN_MAX       — output token limit
+SLATE_EXPERIMENTAL_OXFMT                  — oxfmt integration
+SLATE_EXPERIMENTAL_PLAN_MODE              — plan mode
+SLATE_FAKE_VCS                            — fake VCS for testing
+SLATE_GIT_BASH_PATH                       — git bash path (Windows)
+SLATE_MODELS_URL                          — models config URL
+SLATE_PERMISSION                          — permission override
+SLATE_SERVER_PASSWORD                     — server auth
+SLATE_SERVER_USERNAME                     — server auth
+SLATE_TELEMETRY_DISABLED                  — disable telemetry
+SLATE_TEST_HOME                           — test home directory
+SLATE_TOKEN_DIR                           — token storage directory
+```
+
+### OpenCode legacy (still functional)
+```
+OPENCODE_DISABLE_LSP_DOWNLOAD
+OPENCODE_EXPERIMENTAL_DISABLE_FILEWATCHER
+OPENCODE_EXPERIMENTAL_FILEWATCHER
+OPENCODE_EXPERIMENTAL_ICON_DISCOVERY
+OPENCODE_EXPERIMENTAL_LSP_TY
+OPENCODE_EXPERIMENTAL_OXFMT
+OPENCODE_FAKE_VCS
+OPENCODE_GIT_BASH_PATH
+OPENCODE_LIBC
+OPENCODE_TERMINAL
+```
+
+### Critical env vars for gstack integration
+
+**`SLATE_DISABLE_CLAUDE_CODE_SKILLS`** — When set, `.claude/skills/` loading is disabled.
+This makes publishing to `.slate/skills/` load-bearing, not just an optimization.
+Without native `.slate/` publishing, gstack skills vanish when this flag is set.
+
+**`SLATE_TEST_HOME`** — Useful for E2E tests. Can redirect Slate's home directory
+to an isolated temp directory, similar to how Codex tests use a temp HOME.
+
+**`SLATE_DANGEROUSLY_SKIP_PERMISSIONS`** — Required for headless E2E tests.
+
+## Model References (from binary)
+
+```
+anthropic/claude-sonnet-4.6
+anthropic/claude-opus-4
+anthropic/claude-haiku-4
+anthropic/slate              — Slate's own model routing
+openai/gpt-5.3-codex
+google/nano-banana
+randomlabs/fast-default-alpha
+```
+
+## API Endpoints (from binary)
+
+```
+https://api.randomlabs.ai                          — main API
+https://api.randomlabs.ai/exaproxy                 — Exa search proxy
+https://agent-worker-prod.randomlabs.workers.dev   — production worker
+https://agent-worker-dev.randomlabs.workers.dev    — dev worker
+https://dashboard.randomlabs.ai                    — dashboard
+https://docs.randomlabs.ai                         — documentation
+https://randomlabs.ai/config.json                  — remote config
+```
+
+Brew tap: `anthropic/tap/slate` (notable: under Anthropic's tap, not Random Labs)
+
+## npm Package Structure
+
+```
+@randomlabs/slate (8.8 kB, thin launcher)
+├── bin/slate           — Node.js launcher (finds platform binary in node_modules)
+├── bin/slate1          — Bun launcher (same logic, import.meta.filename)
+├── postinstall.mjs     — Verifies platform binary exists, symlinks if needed
+└── package.json        — Declares optionalDependencies for all platforms
+
+Platform packages (85MB each):
+├── @randomlabs/slate-darwin-arm64
+├── @randomlabs/slate-darwin-x64
+├── @randomlabs/slate-linux-arm64
+├── @randomlabs/slate-linux-x64
+├── @randomlabs/slate-linux-x64-musl
+├── @randomlabs/slate-linux-arm64-musl
+├── @randomlabs/slate-linux-x64-baseline
+├── @randomlabs/slate-linux-x64-baseline-musl
+├── @randomlabs/slate-darwin-x64-baseline
+├── @randomlabs/slate-windows-x64
+└── @randomlabs/slate-windows-x64-baseline
+```
+
+Binary override: `SLATE_BIN_PATH` env var skips all discovery, runs the specified binary directly.
+
+## What Already Works Today
+
+gstack skills already work in Slate via the `.claude/skills/` fallback path.
+No changes needed for basic functionality. Users who install gstack for Claude Code
+and also use Slate will find their skills available in both agents.
+
+## What First-Class Support Adds
+
+1. **Reliability** — `.slate/skills/` is Slate's highest-priority path. Immune to
+   `SLATE_DISABLE_CLAUDE_CODE_SKILLS`.
+2. **Optimized frontmatter** — Strip Claude-specific fields (allowed-tools, hooks, version)
+   that Slate doesn't use. Keep only `name` and `description`.
+3. **Setup script** — Auto-detect `slate` binary, install skills to `~/.slate/skills/`.
+4. **E2E tests** — Verify skills work when invoked by Slate directly.
+
+## Blocked On: Host Config Refactor
+
+Codex's outside voice review identified that adding Slate as a 4th host (after Claude,
+Codex, Factory) is "host explosion for a path alias." The current architecture has:
+
+- Hard-coded host names in `type Host = 'claude' | 'codex' | 'factory'`
+- Per-host branches in `transformFrontmatter()` with near-duplicate logic
+- Per-host config in `EXTERNAL_HOST_CONFIG` with similar patterns
+- Per-host functions in the setup script (`create_codex_runtime_root`, `link_codex_skill_dirs`)
+- Host names duplicated in `bin/gstack-platform-detect`, `bin/gstack-uninstall`, `bin/dev-setup`
+
+Adding Slate means copying all of these patterns again. A refactor to make hosts
+data-driven (config objects instead of if/else branches) would make Slate integration
+trivial AND make future hosts (any new OpenCode fork, any new agent) zero-effort.
+
+### Missing from the plan (identified by Codex)
+
+- `lib/worktree.ts` only copies `.agents/`, not `.slate/` — E2E tests in worktrees won't
+  have Slate skills
+- `bin/gstack-uninstall` doesn't know about `.slate/`
+- `bin/dev-setup` doesn't wire `.slate/` for contributor dev mode
+- `bin/gstack-platform-detect` doesn't detect Slate
+- E2E tests should set `SLATE_DISABLE_CLAUDE_CODE_SKILLS=1` to prove `.slate/` path
+  actually works (not just falling back to `.claude/`)
+
+## Session Runner Design (for later)
+
+When the JSONL format is verified, the session runner should:
+
+- Spawn: `slate -q "<prompt>" --stream-json --dangerously-skip-permissions -w <dir>`
+- Parse: Claude Code SDK-compatible NDJSON (assumed, needs verification)
+- Skills: Install to `.slate/skills/` in test fixture (not `.claude/skills/`)
+- Auth: Use `SLATE_API_KEY` or existing `~/.slate/` credentials
+- Isolation: Use `SLATE_TEST_HOME` for home directory isolation
+- Timeout: 300s default (same as Codex)
+
+```typescript
+export interface SlateResult {
+  output: string;
+  toolCalls: string[];
+  tokens: number;
+  exitCode: number;
+  durationMs: number;
+  sessionId: string | null;
+  rawLines: string[];
+  stderr: string;
+}
+```
+
+## Docs References
+
+- Slate docs: https://docs.randomlabs.ai
+- Quickstart: https://docs.randomlabs.ai/en/getting-started/quickstart
+- Skills: https://docs.randomlabs.ai/en/using-slate/skills
+- Configuration: https://docs.randomlabs.ai/en/using-slate/configuration
+- Hotkeys: https://docs.randomlabs.ai/en/using-slate/hotkey_reference
@@ -36,7 +36,7 @@ Detailed guides for every gstack skill — philosophy, workflow, and examples.
 | [`/freeze`](#safety--guardrails) | **Edit Lock** | Restrict all file edits to a single directory. Blocks Edit and Write outside the boundary. Accident prevention for debugging. |
 | [`/guard`](#safety--guardrails) | **Full Safety** | Combines /careful + /freeze in one command. Maximum safety for prod work. |
 | [`/unfreeze`](#safety--guardrails) | **Unlock** | Remove the /freeze boundary, allowing edits everywhere again. |
-| [`/connect-chrome`](#connect-chrome) | **Chrome Controller** | Launch your real Chrome controlled by gstack with the Side Panel extension. Watch every action live. |
+| [`/open-gstack-browser`](#open-gstack-browser) | **GStack Browser** | Launch GStack Browser with sidebar, anti-bot stealth, auto model routing, cookie import, and Claude Code integration. Watch every action live. |
 | [`/setup-deploy`](#setup-deploy) | **Deploy Configurator** | One-time setup for `/land-and-deploy`. Detects your platform, production URL, and deploy commands. |
 | [`/gstack-upgrade`](#gstack-upgrade) | **Self-Updater** | Upgrade gstack to the latest version. Detects global vs vendored install, syncs both, shows what changed. |

@@ -955,21 +955,21 @@ Claude: 23 learnings for this project (14 high confidence, 6 medium, 3 low)

 ---

-## `/connect-chrome`
+## `/open-gstack-browser`

 This is my **co-presence mode**.

-`/browse` runs headless by default. You don't see what the agent sees. `/connect-chrome` changes that. It launches your actual Chrome browser controlled by Playwright, with the gstack Side Panel extension auto-loaded. You watch every action in real time... same screen, same window.
+`/browse` runs headless by default. You don't see what the agent sees. `/open-gstack-browser` changes that. It launches GStack Browser (rebranded Chromium with anti-bot stealth) controlled by Playwright, with the sidebar extension auto-loaded. You watch every action in real time.

-A subtle green shimmer at the top edge tells you which Chrome window gstack controls. All existing browse commands work unchanged. The Side Panel shows a live activity feed of every command and a chat sidebar where you can direct Claude with natural language instructions.
+The sidebar chat is a Claude instance that controls the browser. It auto-routes to the right model: Sonnet for navigation and actions (click, goto, fill, screenshot), Opus for reading and analysis (summarize, find bugs, describe). One-click cookie import from the sidebar footer. The browser stays alive as long as the window is open... no idle timeout in headed mode. The menu bar says "GStack Browser" instead of "Chrome for Testing."

 ```
-You:   /connect-chrome
+You:   /open-gstack-browser

-Claude: Launched Chrome with Side Panel extension.
-        Green shimmer indicates the controlled window.
-        All $B commands now run in headed mode.
-        Type in the Side Panel to direct the browser agent.
+Claude: Launched GStack Browser with sidebar extension.
+        Anti-bot stealth active. All $B commands run in headed mode.
+        Type in the sidebar to direct the browser agent.
+        Sidebar model routing: sonnet for actions, opus for analysis.
 ```

 ---