oh-my-opencode 5.0.0-beta.86 → 5.0.0-beta.87

package/dist/skills/visual-qa/SKILL.md

@@ -49,7 +49,7 @@ Before any reviewer sees an image, verify each capture yourself: the file signat
 ### Web
 
 1. Capture a REFERENCE image: the user's mock/target, generated page snapshot, Figma export, source-site capture, or known-good baseline. Save as PNG. If the user provided overview text or annotations, save them next to the image and treat them as part of the reference packet.
-2. Capture the ACTUAL rendered screenshot at the reference viewport. Use two browser tiers from js eval: (1) `new Bun.WebView()` on Bun >= 1.4 (macOS default; Linux/Windows need installed Chrome/Chromium/Edge); (2) otherwise, or for Chrome semantics, stealth, trace, or authenticated profiles, WRITE a `playwright-core` script and run it from the kernel against local Chrome (`chromium.launch({ channel: "chrome" })` / `launchPersistentContext` on a CLONED profile, never the live one). In Codex, prefer `browser:control-in-app-browser` for ordinary captures. Save PNG and return its path; close the browser context. See `$SKILL_DIR/references/browser-setup.md` for fixed-viewport examples and prerequisites.
+2. Capture the ACTUAL rendered screenshot at the reference viewport with omowright from js eval (the library is staged in the `browser` skill): the owned engine (`connectPipe` on a task-owned profile, viewport pinned with `emulate`, then `page.screenshot()`) for anything unauthenticated, or the attached engine (`connectBrowserSkill()` → `session.screenshot()`) when the page needs the user's login — never a clone of, or a launch against, the user's live profile. Save PNG and return its path; close the browser or stop the session. See `$SKILL_DIR/references/browser-setup.md` for fixed-viewport examples and prerequisites.
 3. Run the diff and keep the JSON:
 
 ```

package/dist/skills/visual-qa/references/browser-setup.md

@@ -1,75 +1,75 @@
 # Browser setup (Web capture)
 
-Use the js-eval kernel for both tiers. In Codex, prefer
-`browser:control-in-app-browser` for ordinary captures.
+Capture with omowright from the js-eval kernel. The library is staged inside the `browser` skill;
+load it once per session:
 
-## Tier 1: Bun.WebView
+```js
+const { loadOmowright } = await import("<browser-skill-root>/scripts/omowright.mjs")
+const { omowright } = await loadOmowright()
+```
+
+## Owned engine (default for QA)
 
-On a Bun >= 1.4 kernel, `new Bun.WebView()` is the macOS default (system
-WebKit, no browser download). Linux/Windows require `backend: "chrome"`
-and installed Chrome/Chromium/Edge. WebView is headless; WebKit has no CDP,
-and `type()` emits no keyboard events. Use tier 2 when these differences matter.
+A browser your code launches, with a task-owned profile, pinned viewport and no user state.
+`connectPipe` opens no listening port and reaps the process on `close()`.
 
 ```js
 // js-eval cell; url and pngPath belong to this QA run.
-const view = new Bun.WebView({ width: 1280, height: 720 })
+const { mkdtempSync, rmSync } = await import("node:fs")
+const profile = mkdtempSync(`${(await import("node:os")).tmpdir()}/visual-qa-`)
+const browser = await omowright.connectPipe({
+  browserPath: chromeBinary,                      // installed Chrome, Chromium, CloakBrowser or chrome-headless-shell
+  browserArgs: ["--headless", "--no-first-run", `--user-data-dir=${profile}`],
+  storageRoot: profile,
+})
 try {
-  await view.navigate(url)
-  await Bun.write(pngPath, await view.screenshot())
+  const page = await browser.newTab("about:blank")
+  await omowright.emulate(page, { width: 1280, height: 720, deviceScaleFactor: 1, mobile: false, hasTouch: false })
+  await page.goto(url, { waitUntil: "load" })
+  await Bun.write(pngPath, await page.screenshot())
   console.log(pngPath)
 } finally {
-  view[Symbol.dispose]()
+  await browser.close()
+  rmSync(profile, { recursive: true, force: true })
 }
 ```
 
-## Tier 2: playwright-core with local Chrome
+Chrome must already be installed; report an absent executable rather than downloading a managed
+browser. For bot-scored or WAF targets use `connectCloakProfile({ profileDir })` (CloakBrowser
+with a pinned fingerprint seed) — the `browser` skill's `references/owned-engine/README.md`
+covers it.
+
+## Attached engine (authenticated pages)
 
-For other kernels, real-Chrome semantics, stealth, traces, or authenticated
-profiles, WRITE a script beside the project's installed `playwright-core`
-dependency and execute it from js eval. The user installs `playwright-core`
-once with `bun add playwright-core` if needed; Chrome must already exist.
-No managed browser download is needed.
+When the capture needs the user's login, drive the browser they are signed into instead of
+cloning its profile:
 
 ```js
-// capture.mjs
-import { chromium } from "playwright-core"
-const [url, pngPath] = process.argv.slice(2)
-const browser = await chromium.launch({ channel: "chrome", headless: true })
+const session = await omowright.connectBrowserSkill({ name: "visual-qa capture", focused: false })
 try {
-  const page = await browser.newPage({ viewport: { width: 1280, height: 720 }, deviceScaleFactor: 1 })
-  await page.goto(url, { waitUntil: "load", timeout: 30000 })
-  await page.screenshot({ path: pngPath })
-  console.log(pngPath)
+  await session.navigate(url, { waitUntil: "load" })
+  await session.resize(1280, 720)
+  const shot = await session.screenshot()            // { buffer, width, height }
+  await Bun.write(pngPath, shot.buffer)
 } finally {
-  await browser.close()
+  await session.stop()
 }
 ```
 
-Run from the js-eval kernel (also works on a Node kernel):
-
-```js
-const { promisify } = await import("node:util")
-const { execFile } = await import("node:child_process")
-const result = await promisify(execFile)("node", [scriptPath, url, pngPath], { timeout: 45000 })
-console.log(result.stdout)
-```
-
-For auth, CLONE the user-data directory to a private task-owned directory
-and use `chromium.launchPersistentContext(clonePath, { channel: "chrome" })`.
-NEVER launch against or clear cookies/cache/site data from the live profile.
-Close the context and remove only the clone after QA. For script-based stealth,
-read the ultimate-browsing skill's `references/chrome-stealth.md`.
+NEVER launch anything against, or clear cookies/cache/site data from, the user's live profile;
+the attached engine is the only sanctioned way to a signed-in page. If no extension is connected,
+run the `browser` skill's `scripts/browser-install.mjs`, relay its one human step, and wait — do
+not fall back to the owned engine for an authenticated criterion.
 
 ## Capture a screenshot at a fixed viewport
 
-Match CSS viewport AND PNG dimensions: WebKit follows native display scale
-(a 1280x720 viewport can yield 2560x1440 pixels). Use matching reference
-captures or Chrome's `deviceScaleFactor`, not resizing to force a pass.
-Wait for the specific page state, not a sleep, then compare:
+Match CSS viewport AND PNG dimensions: pin `deviceScaleFactor` through `emulate` (owned) or
+`resize` (attached) instead of resizing the PNG to force a pass. Wait for the specific page state
+(a locator, a `waitForURL`, a `createNetworkSnoop(page).waitFor(...)`), not a sleep, then compare:
 
 ```sh
 node "$SKILL_DIR/scripts/visual-qa.mjs" image-diff reference.png actual.png
 ```
 
-Inspect `dimensionsMatch` and `diffRatio`, then inspect the image. Close every
-WebView/browser context and the fixture server, even on a failed capture.
+Inspect `dimensionsMatch` and `diffRatio`, then inspect the image. Close every browser and session
+and the fixture server, even on a failed capture; remove the owned profile in the same `finally`.

package/dist/tui.js

@@ -3537,7 +3537,7 @@ var init_category_model_requirements = __esm(() => {
     },
     quick: {
       fallbackChain: [
-        { providers: ["chatgpt-subscription"], model: "gpt-6-luna-fast", variant: "low" },
+        { providers: ["openai", "chatgpt-subscription"], model: "gpt-6-luna-fast", variant: "low" },
         { providers: ["deepseek"], model: "deepseek-flash", variant: "off" },
         {
           providers: ["qwen-token-plan", "alibaba-token-plan", "bailian-coding-plan"],
@@ -3582,7 +3582,7 @@ var init_category_model_requirements = __esm(() => {
         {
           providers: ["anthropic", "anthropic-api", "github-copilot", "opencode"],
           model: "claude-opus-5-5",
-          variant: "max"
+          variant: "medium"
         },
         { providers: ["zai-coding-plan", "opencode-go"], model: "glm-5.3", variant: "max" },
         {
@@ -3593,6 +3593,7 @@ var init_category_model_requirements = __esm(() => {
       ]
     },
     writing: {
+      requiresAnyModel: true,
       fallbackChain: [
         {
           providers: ["anthropic", "anthropic-api", "github-copilot", "opencode"],
@@ -5271,7 +5272,7 @@ var init_openai_categories = __esm(() => {
     },
     {
       name: "unspecified-high",
-      config: { model: "anthropic/claude-opus-5-5", variant: "max" },
+      config: { model: "anthropic/claude-opus-5-5", variant: "medium" },
       description: "Tasks that don't fit other categories, high effort required",
       callerGuidance: UNSPECIFIED_HIGH_CATEGORY_CALLER_GUIDANCE,
       promptAppend: UNSPECIFIED_HIGH_CATEGORY_PROMPT_APPEND,
@@ -69924,6 +69925,8 @@ var init_model_profile = __esm(() => {
   init_fallback_models();
   OmoModelProfileInputSchema = object({
     display_name: string2().optional(),
+    family: _enum(["daily", "geeky"]).optional(),
+    tier: _enum(["normal", "heavy"]).optional(),
     models: array(union([string2(), OmoFallbackModelObjectSchema])).optional()
   }).strict();
   OmoModelProfileSchema = preprocess((value) => isRecord8(value) ? normalizeLegacyModelFields(value) : value, OmoModelProfileInputSchema);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "oh-my-opencode",
-  "version": "5.0.0-beta.86",
+  "version": "5.0.0-beta.87",
   "description": "The Best AI Agent Harness - Batteries-Included OpenCode Plugin with Multi-Model Orchestration, Parallel Background Agents, and Crafted LSP/AST Tools",
   "main": "./dist/index.js",
   "types": "dist/index.d.ts",
@@ -183,7 +183,7 @@
     "zod": "^4.6.5"
   },
   "devDependencies": {
-    "@code-yeongyu/senpi": "2026.9.23-2",
+    "@code-yeongyu/senpi": "2026.9.23-4",
     "@oh-my-opencode/agents-md-core": "workspace:*",
     "@oh-my-opencode/ast-grep-mcp": "workspace:*",
     "@oh-my-opencode/boulder-state": "workspace:*",
@@ -219,22 +219,23 @@
     "@xterm/xterm": "^6.0.0",
     "bun-types": "1.4.2",
     "node-pty": "^1.1.0",
+    "omowright": "github:code-yeongyu/omowright#25781c8ac04f9aae358b06551520b792ac45c6ed",
     "puppeteer-core": "^25.11.0",
     "typescript": "^7.0.2"
   },
   "optionalDependencies": {
-    "oh-my-opencode-darwin-arm64": "5.0.0-beta.86",
-    "oh-my-opencode-darwin-x64": "5.0.0-beta.86",
-    "oh-my-opencode-darwin-x64-baseline": "5.0.0-beta.86",
-    "oh-my-opencode-linux-arm64": "5.0.0-beta.86",
-    "oh-my-opencode-linux-arm64-musl": "5.0.0-beta.86",
-    "oh-my-opencode-linux-x64": "5.0.0-beta.86",
-    "oh-my-opencode-linux-x64-baseline": "5.0.0-beta.86",
-    "oh-my-opencode-linux-x64-musl": "5.0.0-beta.86",
-    "oh-my-opencode-linux-x64-musl-baseline": "5.0.0-beta.86",
-    "oh-my-opencode-windows-arm64": "5.0.0-beta.86",
-    "oh-my-opencode-windows-x64": "5.0.0-beta.86",
-    "oh-my-opencode-windows-x64-baseline": "5.0.0-beta.86"
+    "oh-my-opencode-darwin-arm64": "5.0.0-beta.87",
+    "oh-my-opencode-darwin-x64": "5.0.0-beta.87",
+    "oh-my-opencode-darwin-x64-baseline": "5.0.0-beta.87",
+    "oh-my-opencode-linux-arm64": "5.0.0-beta.87",
+    "oh-my-opencode-linux-arm64-musl": "5.0.0-beta.87",
+    "oh-my-opencode-linux-x64": "5.0.0-beta.87",
+    "oh-my-opencode-linux-x64-baseline": "5.0.0-beta.87",
+    "oh-my-opencode-linux-x64-musl": "5.0.0-beta.87",
+    "oh-my-opencode-linux-x64-musl-baseline": "5.0.0-beta.87",
+    "oh-my-opencode-windows-arm64": "5.0.0-beta.87",
+    "oh-my-opencode-windows-x64": "5.0.0-beta.87",
+    "oh-my-opencode-windows-x64-baseline": "5.0.0-beta.87"
   },
   "overrides": {
     "@earendil-works/pi-agent-core": "0.84.2",

package/packages/omo-codex/plugin/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "omo",
-  "version": "5.0.0-beta.86",
+  "version": "5.0.0-beta.87",
   "description": "One Codex plugin namespace for Yeongyu's local Codex components.",
   "author": {
     "name": "Yeongyu Kim",

package/packages/omo-codex/plugin/components/bootstrap/dist/cli.js

@@ -7292,6 +7292,8 @@ function isRecord6(value) {
 }
 var OmoModelProfileInputSchema = object({
   display_name: string2().optional(),
+  family: _enum(["daily", "geeky"]).optional(),
+  tier: _enum(["normal", "heavy"]).optional(),
   models: array(union([string2(), OmoFallbackModelObjectSchema])).optional()
 }).strict();
 var OmoModelProfileSchema = preprocess((value) => isRecord6(value) ? normalizeLegacyModelFields(value) : value, OmoModelProfileInputSchema);

package/packages/omo-codex/plugin/components/bootstrap/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"command": "node \"${PLUGIN_ROOT}/components/bootstrap/dist/cli.js\" hook session-start",
 						"commandWindows": "powershell -NoProfile -ExecutionPolicy Bypass -File \"${PLUGIN_ROOT}\\components\\bootstrap\\scripts\\bootstrap.ps1\"",
 						"timeout": 30,
-						"statusMessage": "(OmO 5.0.0-beta.86) Checking Bootstrap Provisioning"
+						"statusMessage": "(OmO 5.0.0-beta.87) Checking Bootstrap Provisioning"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/bootstrap/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@sisyphuslabs/codex-bootstrap",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex SessionStart bootstrap component that provisions LazyCodex runtime dependencies from a detached worker.",
 	"type": "module",
 	"private": true,

package/packages/omo-codex/plugin/components/comment-checker/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-tool-use",
 						"timeout": 30,
-						"statusMessage": "(OmO 5.0.0-beta.86) Checking Comments"
+						"statusMessage": "(OmO 5.0.0-beta.87) Checking Comments"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/comment-checker/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-comment-checker",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex plugin that runs comment-checker after edit-like PostToolUse hooks.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/git-bash/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook pre-tool-use",
 						"timeout": 5,
-						"statusMessage": "(OmO 5.0.0-beta.86) Recommending Git Bash MCP"
+						"statusMessage": "(OmO 5.0.0-beta.87) Recommending Git Bash MCP"
 					}
 				]
 			}
@@ -20,7 +20,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-compact",
 						"timeout": 5,
-						"statusMessage": "(OmO 5.0.0-beta.86) Resetting Git Bash MCP Reminder"
+						"statusMessage": "(OmO 5.0.0-beta.87) Resetting Git Bash MCP Reminder"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/git-bash/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@sisyphuslabs/codex-git-bash-hook",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex hook component that reminds Windows sessions to prefer the OMO git_bash MCP.",
 	"type": "module",
 	"private": true,

package/packages/omo-codex/plugin/components/lazycodex-executor-verify/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/components/lazycodex-executor-verify/dist/cli.js\" hook subagent-stop",
 						"timeout": 10,
-						"statusMessage": "(OmO 5.0.0-beta.86) Verifying LazyCodex Executor Evidence"
+						"statusMessage": "(OmO 5.0.0-beta.87) Verifying LazyCodex Executor Evidence"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/lazycodex-executor-verify/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-lazycodex-executor-verify",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex SubagentStop evidence verifier for LazyCodex executor completions.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/lsp/dist/.omo-runtime-manifest.json

@@ -1,7 +1,7 @@
 {
   "schemaVersion": 1,
-  "version": "5.0.0-beta.86",
-  "inputDigest": "sha256:5529e0ca0e2604cde58c8d77af425b3d0a06feed87148856d577aa0bbc0c9a18",
+  "version": "5.0.0-beta.87",
+  "inputDigest": "sha256:72acd620e3bb18d2b7ff2299536bc0c48b009811a865fa1504e934010d24ea98",
   "outputs": [
     {
       "path": "cli.d.ts",

package/packages/omo-codex/plugin/components/lsp/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-tool-use",
 						"timeout": 60,
-						"statusMessage": "(OmO 5.0.0-beta.86) Checking LSP Diagnostics"
+						"statusMessage": "(OmO 5.0.0-beta.87) Checking LSP Diagnostics"
 					}
 				]
 			}
@@ -21,7 +21,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-compact",
 						"timeout": 5,
-						"statusMessage": "(OmO 5.0.0-beta.86) Resetting LSP Diagnostics Cache"
+						"statusMessage": "(OmO 5.0.0-beta.87) Resetting LSP Diagnostics Cache"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/lsp/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-lsp",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex plugin that exposes Language Server Protocol tools and post-edit diagnostics.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/rules/bundled-rules/hephaestus/gpt-6.md

@@ -53,7 +53,7 @@ Arm an available completion or state-change subscription when starting a build,
 
 Scale the scope of checks to the change and keep the rigor. A non-behavioral single-file edit needs diagnostics on that file. A single-domain behavior change adds related tests and one run of the affected entry point. Multi-file or cross-cutting work adds the build and user-visible behavior exercised through its real surface. omo-codex injects LSP diagnostics after edits; reported errors are blocking until resolved. Broaden or repeat checks only when a new change, failure, or open concern justifies it; otherwise keep moving toward completion.
 
-A behavior change starts with one failing test at its seam, observed failing for the right reason, then the smallest change that passes it. Formatting, comments, renames, dependency bumps, and visual-only work get review and a real-surface check instead. Leave out tests that mirror the implementation or cannot fail for the regression they name.
+Read existing tests first - the behavior of record: update those your change makes stale; one wrong before your change is a finding, not a test to edit green. Reproduce a bug before fixing it. The run proves the change: add a test only where the repository keeps tests for this behavior and a regression would otherwise pass unnoticed - sized like its neighbors, never restating the change.
 
 ### Test Discipline
 

package/packages/omo-codex/plugin/components/rules/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook session-start",
 						"timeout": 10,
-						"statusMessage": "(OmO 5.0.0-beta.86) Loading Project Rules"
+						"statusMessage": "(OmO 5.0.0-beta.87) Loading Project Rules"
 					}
 				]
 			}
@@ -19,7 +19,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook user-prompt-submit",
 						"timeout": 10,
-						"statusMessage": "(OmO 5.0.0-beta.86) Loading Project Rules"
+						"statusMessage": "(OmO 5.0.0-beta.87) Loading Project Rules"
 					}
 				]
 			}
@@ -32,7 +32,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-tool-use",
 						"timeout": 10,
-						"statusMessage": "(OmO 5.0.0-beta.86) Matching Project Rules"
+						"statusMessage": "(OmO 5.0.0-beta.87) Matching Project Rules"
 					}
 				]
 			}
@@ -45,7 +45,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-compact",
 						"timeout": 10,
-						"statusMessage": "(OmO 5.0.0-beta.86) Resetting Project Rule Cache"
+						"statusMessage": "(OmO 5.0.0-beta.87) Resetting Project Rule Cache"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/rules/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-rules",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex plugin that injects project rule files into model context through lifecycle hooks.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/teammode/hooks/hooks.json

@@ -8,7 +8,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook post-tool-use",
 						"timeout": 10,
-						"statusMessage": "(OmO 5.0.0-beta.86) Checking Thread Title Hygiene"
+						"statusMessage": "(OmO 5.0.0-beta.87) Checking Thread Title Hygiene"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/teammode/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@sisyphuslabs/codex-teammode",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex team-mode hook component that keeps background thread titles descriptive after create_thread.",
 	"type": "module",
 	"private": true,

package/packages/omo-codex/plugin/components/telemetry/hooks/hooks.json

@@ -7,7 +7,7 @@
 						"type": "command",
 						"command": "node \"${PLUGIN_ROOT}/dist/cli.js\" hook session-start",
 						"timeout": 5,
-						"statusMessage": "(OmO 5.0.0-beta.86) Recording Session Telemetry"
+						"statusMessage": "(OmO 5.0.0-beta.87) Recording Session Telemetry"
 					}
 				]
 			}

package/packages/omo-codex/plugin/components/telemetry/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@code-yeongyu/codex-telemetry",
-	"version": "5.0.0-beta.86",
+	"version": "5.0.0-beta.87",
 	"description": "Codex plugin component that emits omo-codex anonymous daily-active telemetry on SessionStart.",
 	"type": "module",
 	"packageManager": "npm@11.12.1",

package/packages/omo-codex/plugin/components/ultrawork/README.md

@@ -11,7 +11,7 @@ All 12 bundled agent TOMLs set `model = "gpt-6-astra"`; each role keeps its own
 | Mandate | Behavior |
 |---|---|
 | Goal + binding success criteria | Call `create_goal` (or open with a `# Goal` block) listing the deliverable + **3+ realistic QA scenarios** (happy path, edge cases, adjacent-surface regression). Each scenario MUST name which **Manual-QA channel** it will use. "Tests pass" is supporting signal, NEVER completion proof. |
-| Manual-QA channels (TESTS ALONE NEVER PROVE DONE) | A dedicated top-level section enumerates the **four** channels you can use to verify a criterion in reality: **(1) HTTP call** (`curl -i` / Playwright APIRequestContext), **(2) tmux** (`tmux new-session` + `send-keys` + `capture-pane`), **(3) Browser use** (in Codex, `browser:control-in-app-browser` first when no authenticated/persistent browser profile is needed; otherwise Playwright / puppeteer / Chromium driving the real page), **(4) Computer use** (OS-level GUI automation against the running app). Every criterion picks one channel, builds a real-usage scenario, runs it, and captures the artifact — every time. Aux surfaces (CLI stdout / DB diff / parsed config) only count for genuinely CLI- or data-shaped criteria. |
+| Manual-QA channels (TESTS ALONE NEVER PROVE DONE) | A dedicated top-level section enumerates the **four** channels you can use to verify a criterion in reality: **(1) HTTP call** (`curl -i` / an HTTP client from js eval), **(2) tmux** (`tmux new-session` + `send-keys` + `capture-pane`), **(3) Browser use** (in Codex, `browser:control-in-app-browser` first when no authenticated/persistent browser profile is needed; otherwise omowright driving the real page — the owned engine for a browser you launch, the attached engine for the user's signed-in browser), **(4) Computer use** (OS-level GUI automation against the running app). Every criterion picks one channel, builds a real-usage scenario, runs it, and captures the artifact — every time. Aux surfaces (CLI stdout / DB diff / parsed config) only count for genuinely CLI- or data-shaped criteria. |
 | Surface + paired cleanup | Execution loop step 4 (**SURFACE-AS-SCENARIO**) runs the chosen channel scenario end-to-end. Step 5 (**CLEANUP, PAIRED**) tears down every QA-spawned process / tmux session / browser context / container / port / temp dir, with a one-line receipt appended to the notepad. Leftover state → NOT done. |
 | Durable /tmp notepad | `mktemp -t ulw-$(date +%Y%m%d-%H%M%S).XXXXXX.md` with sections `Plan`, `Success criteria + QA scenarios`, `Now`, `Todo`, `Findings`, `Learnings`. **Append**, never rewrite. |
 | Obsessive atomic todos | Every action — even one-line edits, `ls`, single test runs — becomes a todo. Format: `path: <action> for <criterion> — verify by <check>`. One in_progress at a time, mark completed immediately. |

package/packages/omo-codex/plugin/components/ultrawork/agents/plan.toml

@@ -94,10 +94,10 @@ Critical path: Task 1 -> Task 2 -> Task 6
   - [ ] <verifiable condition with the exact command or assertion>
 
   QA scenarios (MANDATORY - task incomplete without these):
-  > Name the exact tool AND its exact invocation - not "verify it works". Browser use: in Codex, prefer `browser:control-in-app-browser`; otherwise, or for Chrome semantics, stealth, trace, or auth, write and run a `playwright-core` script from js eval against local Chrome (`channel: "chrome"`; persistent context on a CLONED profile, never the live one). Computer use: OS-level GUI automation for a non-browser desktop app.
+  > Name the exact tool AND its exact invocation - not "verify it works". Browser use: in Codex, prefer `browser:control-in-app-browser`; otherwise omowright from js eval (staged in the `browser` skill) — `connectPipe`/`connectCloakProfile` for a browser you own, `connectBrowserSkill()` for the user's signed-in browser; never a clone of the live profile. Computer use: OS-level GUI automation for a non-browser desktop app.
   ```
   Scenario: <happy path>
-    Tool:     <bash | curl | tmux | browser:control-in-app-browser | playwright-core(js eval, local Chrome) | computer-use>
+    Tool:     <bash | curl | tmux | browser:control-in-app-browser | omowright(js eval; owned or attached engine) | computer-use>
     Steps:    <exact command / API call / page action with concrete inputs - URL, payload, keystrokes, selectors>
     Expected: <concrete, binary pass/fail observable>
     Evidence: <attemptDir>/task-<N>-<slug>.<ext>   (attemptDir = currentAttemptDir from `omo-agent-toolkit ulw-loop status --json`, .omo/evidence/ulw/<session>/<goalId>/a<attempt>)