diff --git a/evals/mcp-tool-use/cases/pull-requests.jsonl b/evals/mcp-tool-use/cases/pull-requests.jsonl
index 8445271e41531..acf54860ad34a 100644
--- a/evals/mcp-tool-use/cases/pull-requests.jsonl
+++ b/evals/mcp-tool-use/cases/pull-requests.jsonl
@@ -15,7 +15,7 @@
 {"id": "secret-webhook-how-to-send", "area": "pull-requests", "kind": "bad", "pattern": "secret asked in chat, or request_secret promised but not called", "experience": "Agents told the user to paste secrets in chat, or said 'give me a token through request_secret' and never called it. request_secret has 0 real calls.", "rule": "When you need a secret from the user ... call request_secret so they enter it privately ... Never ask for a secret in chat", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Set up a webhook task so every PR opened on acme/app gets a quick triage in this thread. Have GitHub sign the requests."}, {"role": "assistant", "text": "I can set that up. I need the webhook secret so T3 Code can check GitHub's signature. Create a secret for the webhook in the repo's webhook settings first."}], "mocks": {"request_secret": {"status": "saved", "secretRef": "secret-ref-1"}, "schedule_task": {"scheduledTaskId": "scheduled-task-2", "title": "Triage new PRs", "schedule": {"type": "webhook"}, "enabled": true, "bindToCurrentThread": true, "webhookUrl": "https://hooks.example.test/t3/abc"}}}, "prompt": "Ok, I made the secret in GitHub. How do I get it to you?", "expect": {"calls": [{"tool": "request_secret"}, {"tool": "schedule_task", "args": {"schedule.type": "webhook", "schedule.signature.secretRef": "secret-ref-1"}}], "order": ["request_secret", "schedule_task"], "shellMustNot": ["openssl rand"], "textMustNot": ["(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Pp]aste (it|them|the (api )?(token|key|secret)s?|your (api )?(token|key|secret)s?)[^.\\n]{0,40}\\b(here|in (the |this )?(chat|thread))\\b", "(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Ss]end (me )?(it|the (api )?(token|key|secret)|your (api )?(token|key|secret))[^.\\n]{0,30}\\b(here|in (the |this )?(chat|thread))\\b", "(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Pp]aste both[^\\n]{0,100}\\b(here|in (the |this )?(chat|thread))\\b", "(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Ss]end me (an?|the|your) [^.\\n]{0,20}(token|key)\\b(?![^.\\n]{0,40}(file|env|\\.env))"], "textMust": ["hooks\\.example\\.test/t3/abc"]}, "notes": "Real misses were shell tokens, where a secretRef cannot help (see secret-shell-token-how-to-send). No webhook task exists in the data, so this is the smallest context where request_secret is the right tool. Mock result shapes are approximations."}
 {"id": "secret-shell-token-how-to-send", "area": "pull-requests", "kind": "bad", "pattern": "shell CLI token asked in chat, not through request_secret file delivery", "experience": "Agents asked for API tokens in chat ('send me an API token', 'paste both ...secret-access-key=... URLs here') or promised a 'secure prompt' they never opened.", "rule": "For a shell CLI token, set delivery to file. Never ask for secrets in chat, and never invent one.", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "CI failed. Fix it. Keep an eye on the PR."}, {"role": "assistant", "text": "The Cloudflare build check on [#123](https://github.com/acme/app/pull/123) fails in the same second it starts, so no build runs. The Worker builds cleanly here with `wrangler deploy --dry-run`. This machine has no Cloudflare login, so I can't read the build log. I need either the build log or a Cloudflare API token with read access to builds.", "toolCalls": [{"tool": "Bash", "input": {"command": "gh pr checks 123"}, "result": "Cloudflare Pages\tfail\t1s\nLint\tpass\t41s\nTest\tpass\t3m"}, {"tool": "Bash", "input": {"command": "npx wrangler deploy --dry-run"}, "result": "Total Upload: 412.31 KiB / gzip: 98.20 KiB\n--dry-run: exiting now."}, {"tool": "Bash", "input": {"command": "npx wrangler whoami"}, "result": "You are not authenticated. Please run `wrangler login`."}]}], "mocks": {"request_secret": "default"}}, "prompt": "I made a Cloudflare API token with build read access. How do I get it to you?", "expect": {"calls": [{"tool": "request_secret", "args": {"delivery": "file"}}], "textMustNot": ["(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Pp]aste (the (api )?(token|key|secret)s?|your (api )?(token|key|secret)s?)[^.\\n]{0,40}\\b(here|in (the |this )?(chat|thread))\\b", "(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Ss]end (me )?(the (api )?(token|key|secret)|your (api )?(token|key|secret))[^.\\n]{0,30}\\b(here|in (the |this )?(chat|thread))\\b", "(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Pp]aste both[^\\n]{0,100}\\b(here|in (the |this )?(chat|thread))\\b", "(?<![Dd]on't )(?<![Nn]ot )(?<![Nn]ever )(?<!need to )(?<!have to )[Ss]end me (an?|the|your) [^.\\n]{0,20}(token|key)\\b(?![^.\\n]{0,40}(file|env|\\.env))"]}, "notes": "Since pingdotgg/t3code#24809, request_secret with delivery 'file' returns a private file path a shell command can read, so it is the right tool for a wrangler token. The runner's default result is a file under T3's secrets directory."}
 {"id": "schedule-runs-job-first", "area": "pull-requests", "kind": "bad", "pattern": "schedule asked, agent runs the job instead", "experience": "After an approved test run, the user said 'set it with a schedule'. The agent ran the triage query again (about 20 GitHub calls) before scheduling. The user: 'Why are you running the query?'", "rule": "schedule_task creates persistent recurring work in the app scheduler. Pass schedule as a structured object / After scheduling a timer, report the returned cadence and next run time", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Every day at 9pm, I want you to:\n- Spin up Haiku 5.5 delegates to look at PRs with activity in the last 24 hours\n- Audit them for mergeability, value, and novelty\n- Have Opus 5.5 and GPT-6.1 Sol delegates verify the ones that look mergeable\n- Come back with 8 or fewer PRs worth merging or taking over\nDo a test run before we set up the scheduled task."}, {"role": "assistant", "text": "Test run done. 290 PRs had activity in 24 hours. Haiku flagged 31; Opus and Sol confirmed 7: #101 MERGE, #102 MERGE, #103 MERGE, #104 TAKEOVER, #105 MERGE, #106 TAKEOVER, #107 MERGE.\n\nOne lesson for the job: a first-time contributor's PR can look green when CI never ran (it waits for approval). The nightly run must check for that.", "toolCalls": [{"tool": "Bash", "input": {"command": "gh pr list --state open --search \"updated:>=2026-10-23\" --limit 500 --json number --jq length"}, "result": "290"}, {"tool": "delegate_task", "input": {"title": "Haiku PR audit", "mode": "wait", "target": {"providerInstanceId": "claudeAgent", "model": "claude-haiku-5-5"}, "task": "Audit the 290 PRs with activity in the last 24 hours for mergeability, value, and novelty. Flag the ones that look mergeable."}, "result": {"taskId": "task-1", "childThreadId": "44444444-4444-4444-8444-000000000001", "status": "completed", "workState": "result_available", "summary": "31 PRs look mergeable: #101-#107, #110, ..."}}, {"tool": "delegate_task", "input": {"title": "Opus verify", "mode": "wait", "target": {"providerInstanceId": "claudeAgent", "model": "claude-opus-5-5"}, "task": "Verify the 31 flagged PRs. Say MERGE, TAKEOVER, or SKIP for each."}, "result": {"taskId": "task-2", "childThreadId": "44444444-4444-4444-8444-000000000002", "status": "completed", "workState": "result_available", "summary": "#101 MERGE, #102 MERGE, #103 MERGE, #104 TAKEOVER, #105 MERGE, #106 TAKEOVER, #107 MERGE. #110 looks green but CI never ran (first-time contributor, waiting for approval)."}}, {"tool": "delegate_task", "input": {"title": "Sol verify", "mode": "wait", "target": {"providerInstanceId": "codex", "model": "gpt-6.1-sol"}, "task": "Verify the 31 flagged PRs. Say MERGE, TAKEOVER, or SKIP for each."}, "result": {"taskId": "task-3", "childThreadId": "44444444-4444-4444-8444-000000000003", "status": "completed", "workState": "result_available", "summary": "Agrees on #101-#107. SKIP the rest."}}]}], "mocks": {"schedule_task": {"scheduledTaskId": "scheduled-task-1", "title": "Nightly PR triage", "schedule": {"type": "fixed_time", "timeOfDay": "21:00"}, "enabled": true, "bindToCurrentThread": true, "nextRunAt": "2026-10-24T21:00:00-07:00"}}}, "prompt": "This looks good, set it with a schedule", "expect": {"calls": [{"tool": "schedule_task", "args": {"schedule.type": "fixed_time", "schedule.timeOfDay": "21:00"}}], "notCalls": ["delegate_task", "run_scheduled_task_now"], "shellMustNot": ["\\bgh (api|pr|search|issue)\\b"], "textMust": ["(9(:00)? ?[Pp]\\.?[Mm]|21:00)"]}, "notes": "Correction theme H. The only schedule correction in the data."}
-{"id": "scheduled-run-lists-tasks", "area": "pull-requests", "kind": "bad", "pattern": "list_scheduled_tasks on every scheduled wake", "experience": "Each 4-minute scheduled run called list_scheduled_tasks and got the same single task back (9 times in 33 minutes).", "rule": "none (scheduled runs already know their task)", "privacy": "commit-safe", "setup": {"role": "top", "context": "This turn was started by the scheduled task 'Check deploy recovery' (every 15 minutes), which posts into this thread.", "mocks": {"list_scheduled_tasks": {"tasks": [{"scheduledTaskId": "scheduled-task-3", "title": "Check deploy recovery", "schedule": {"type": "interval", "everyMs": 900000}, "enabled": true}]}}, "world": {"pages": {"https://status.example.test": "<h1>Status</h1><p>Deployments: paused for all plans. Next update in 30 minutes.</p>"}}}, "prompt": "Check https://status.example.test for an explicit announcement that deployments resumed. Do not count green component tiles as recovery. If deployments are still paused, reply in one line and change nothing.", "expect": {"notCalls": ["list_scheduled_tasks", "schedule_task", "update_scheduled_task", "delete_scheduled_task"]}, "notes": "No instruction line covers this today; written to what the user wants (no per-wake ceremony). The agent may use WebFetch instead of curl."}
+{"id": "scheduled-run-lists-tasks", "area": "pull-requests", "kind": "bad", "pattern": "list_scheduled_tasks on every scheduled wake", "experience": "Each 4-minute scheduled run called list_scheduled_tasks and got the same single task back (9 times in 33 minutes).", "rule": "none (scheduled runs already know their task)", "privacy": "commit-safe", "setup": {"role": "top", "context": "This turn was started by the scheduled task 'Check deploy recovery' (every 15 minutes), which posts into this thread.", "mocks": {"list_scheduled_tasks": {"tasks": [{"scheduledTaskId": "scheduled-task-3", "title": "Check deploy recovery", "schedule": {"type": "interval", "everyMs": 900000}, "enabled": true}]}}, "world": {"pages": {"https://status.example.test": "<h1>Status</h1><p>Deployments: paused for all plans. Next update in 30 minutes.</p>"}}}, "prompt": "Check https://status.example.test for an explicit announcement that deployments resumed. Do not count green component tiles as recovery. If deployments are still paused, reply in one line and change nothing.", "expect": {"notCalls": ["list_scheduled_tasks", "schedule_task", "delete_scheduled_task"]}, "notes": "No instruction line covers this today; written to what the user wants (no per-wake ceremony). The agent may use WebFetch instead of curl."}
 {"id": "creator-links-own-pr", "area": "pull-requests", "kind": "guard", "pattern": "created PR ends up linked, with no watch or list", "experience": "Must keep working: an opened PR ends up linked to the thread, and the agent does not watch or list when no babysit was asked.", "rule": "Call link_pull_request with the full PR URL immediately after creating a PR", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Can we pre-bundle the hot startup paths on shared dev servers? First load takes over a minute."}, {"role": "assistant", "text": "Prototype is on branch perf/prebundle-startup (commit abc1234). First page load on a shared dev server drops from about 64 s to 21 s. Want a PR?", "toolCalls": [{"tool": "Bash", "input": {"command": "git checkout -b perf/prebundle-startup"}, "result": "Switched to a new branch 'perf/prebundle-startup'"}, {"tool": "Write", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/scripts/hotStartupDeps.ts", "content": "// Measured with scripts/bench-first-load.mjs on a shared dev server.\nexport const HOT_STARTUP_DEPS = ['react', 'react-dom', '@tanstack/react-router', 'effect'];\n"}, "result": "File created successfully at: /home/user/.t3/worktrees/t3code/t3-f8cdd940/scripts/hotStartupDeps.ts"}, {"tool": "Write", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/vite.config.ts", "content": "import { defineConfig } from 'vite';\nimport { HOT_STARTUP_DEPS } from './scripts/hotStartupDeps';\n\nexport default defineConfig({\n  optimizeDeps: { include: HOT_STARTUP_DEPS },\n});\n"}, "result": "File created successfully at: /home/user/.t3/worktrees/t3code/t3-f8cdd940/vite.config.ts"}, {"tool": "Bash", "input": {"command": "node scripts/bench-first-load.mjs --runs 3"}, "result": "baseline    64.2s 63.8s 65.0s\nprebundled  21.3s 20.9s 21.6s"}, {"tool": "Bash", "input": {"command": "git add -A && git commit -m \"perf(dev): pre-bundle hot startup paths on shared dev servers\""}, "result": "[perf/prebundle-startup abc1234] perf(dev): pre-bundle hot startup paths on shared dev servers\n 2 files changed"}]}], "mocks": {"link_pull_request": "default"}, "world": {"branch": "perf/prebundle-startup", "commits": [{"sha": "abc1234", "subject": "perf(dev): pre-bundle hot startup paths on shared dev servers"}], "diff": "diff --git a/vite.config.ts b/vite.config.ts\n--- a/vite.config.ts\n+++ b/vite.config.ts\n@@ -1,5 +1,6 @@\n import { defineConfig } from 'vite';\n+import { HOT_STARTUP_DEPS } from './scripts/hotStartupDeps';\n \n export default defineConfig({\n-  optimizeDeps: {},\n+  optimizeDeps: { include: HOT_STARTUP_DEPS },\n });\ndiff --git a/scripts/hotStartupDeps.ts b/scripts/hotStartupDeps.ts\n--- a/scripts/hotStartupDeps.ts\n+++ b/scripts/hotStartupDeps.ts\n@@ -0,0 +1,2 @@\n+// Measured with scripts/bench-first-load.mjs on a shared dev server.\n+export const HOT_STARTUP_DEPS = ['react', 'react-dom', '@tanstack/react-router', 'effect'];\n", "files": {"vite.config.ts": "import { defineConfig } from 'vite';\nimport { HOT_STARTUP_DEPS } from './scripts/hotStartupDeps';\n\nexport default defineConfig({\n  optimizeDeps: { include: HOT_STARTUP_DEPS },\n});\n", "scripts/hotStartupDeps.ts": "// Measured with scripts/bench-first-load.mjs on a shared dev server.\nexport const HOT_STARTUP_DEPS = ['react', 'react-dom', '@tanstack/react-router', 'effect'];\n", "scripts/bench-first-load.mjs": "// Starts the dev server and times the first page load.\n// Usage: node scripts/bench-first-load.mjs --runs 3\nimport { startDevServer, timeFirstLoad } from './bench-lib.mjs';\n\nconst runs = Number(process.argv[3] ?? 3);\nfor (let i = 0; i < runs; i++) console.log(await timeFirstLoad(await startDevServer()));\n", "scripts/bench-lib.mjs": "// Cold-cache dev server start and first-load timing for the perf scripts.\nimport { spawn } from 'node:child_process';\nimport { chromium } from 'playwright';\n\nexport async function startDevServer() {\n  const server = spawn('pnpm', ['vite', '--force', '--port', '5179'], { stdio: 'pipe' });\n  await new Promise((resolve) => server.stdout.on('data', (b) => String(b).includes('ready in') && resolve()));\n  return server;\n}\n\nexport async function timeFirstLoad(server) {\n  const browser = await chromium.launch();\n  const page = await browser.newPage();\n  const start = performance.now();\n  await page.goto('http://localhost:5179', { waitUntil: 'load' });\n  const seconds = ((performance.now() - start) / 1000).toFixed(1);\n  await browser.close();\n  server.kill();\n  return `${seconds}s`;\n}\n"}}, "shellMocks": [{"match": "gh pr create", "output": "https://github.com/acme/app/pull/124"}, {"match": "^node .*bench-first-load", "output": "baseline    64.2s 63.8s 65.0s\nprebundled  21.3s 20.9s 21.6s"}]}, "prompt": "Okay do it. Make a good PR.", "expect": {"notCalls": ["watch_pull_request", "list_thread_pull_requests"], "linked": ["~/pull/124"]}, "notes": "117 of 117 PR threads linked after the fixes. A shorter text must keep this. Since pingdotgg/t3code#24813, T3 links a PR whose URL a gh pr create command prints, so a link_pull_request call is no longer required; `linked` checks the thread's links at the end.", "maxSteps": 14}
 {"id": "child-pushes-existing-pr-links", "area": "pull-requests", "kind": "guard", "pattern": "child that changes an existing PR links it, no watch", "experience": "Must keep working: an implementation child that pushes to an existing PR links it and reports back without watching.", "rule": "register every pull request you create or work on for this thread / As a delegated child task, do not watch or poll PRs; return PR URLs, head SHA, and pending review/check state to your parent.", "privacy": "commit-safe", "setup": {"role": "delegated-child", "context": "You are a delegated child task. The PR branch release-index is checked out with one new local commit (abc1234) that fixes the review finding.", "mocks": {"link_pull_request": "default", "watch_pull_request": "default"}, "delegateRole": "implementation", "world": {"branch": "release-index", "commits": [{"sha": "abc1234", "subject": "fix(release): sort the index by version, not by date"}, {"sha": "1111111", "subject": "feat(release): publish a release index"}], "prs": [{"number": 123, "title": "feat(release): publish a release index", "headRefName": "release-index", "checks": [{"name": "Lint", "state": "pass"}, {"name": "Typecheck", "state": "pass"}, {"name": "Check", "state": "pending"}, {"name": "Test Web", "state": "pending"}], "author": {"login": "contributor"}, "headRefOid": "1111111"}], "diff": "diff --git a/scripts/release-index.ts b/scripts/release-index.ts\n--- a/scripts/release-index.ts\n+++ b/scripts/release-index.ts\n@@ -0,0 +1,4 @@\n+export function buildIndex(entries: Entry[]) {\n+  entries.sort((a, b) => compareVersions(b.version, a.version));\n+  return entries.map((e) => `${e.version}\\t${e.url}`).join('\\n');\n+}\n"}}, "prompt": "Take over https://github.com/acme/app/pull/123 (a contributor's PR from a branch in this repo). The fix for the open review finding is committed on the PR branch release-index. Push it to the PR branch. Do not merge. Report back with the PR state.", "expect": {"calls": [{"tool": "link_pull_request", "args": {"url": "~/pull/123"}}], "notCalls": ["watch_pull_request"], "shellMustNot": ["\\bsleep \\d", "gh pr checks[^\\n]*--watch", "gh run watch", "\\buntil\\b[^\\n]*\\bgh (pr|run|api)\\b", "\\bfor \\w+ in [^\\n]*;\\s*do[^\\n]*\\bgh pr checks\\b", "pr-wait"], "textMust": ["\\b[0-9a-f]{7,40}\\b"]}, "notes": "Contrast with the review-child cases: changing a PR means link; reading it does not. A rewrite to 'link PRs you create' must not drop this."}
 {"id": "stack-links-every-layer", "area": "pull-requests", "kind": "guard", "pattern": "stacked PRs: every layer ends up linked", "experience": "Must keep working: for a 2-PR stack, both layers end up linked, not only the top.", "rule": "For a stack, call it for every layer, not just the current branch or the top PR.", "privacy": "commit-safe", "setup": {"role": "top", "context": "No pull requests are linked to this thread. Branch feature/error-detail (on main) and branch feature/frozen-host (on top of feature/error-detail) are committed locally. Nothing is pushed yet.", "mocks": {"link_pull_request": "default"}, "world": {"branch": "feature/frozen-host", "branches": {"feature/error-detail": "e1d2c3b"}, "commits": [{"sha": "f7e6d5c", "subject": "feat(server): detect a frozen host and say so"}, {"sha": "e1d2c3b", "subject": "feat(server): include the failing step in connection errors"}], "nextPullRequests": "The next pull request created on acme/app is #124, and the one after it is #125."}, "shellMocks": [{"match": "gh pr create.*(--base|-B)[= ]['\"]?main\\b", "output": "https://github.com/acme/app/pull/124"}, {"match": "gh pr create.*(--base|-B)[= ]['\"]?feature/error-detail\\b", "output": "https://github.com/acme/app/pull/125"}]}, "prompt": "Open both as stacked PRs: feature/error-detail against main, and feature/frozen-host on top of it.", "expect": {"linked": ["~/pull/124", "~/pull/125"]}, "notes": "No real 'only the top layer linked' miss exists after v2 (checked all stacked creates since Oct 2). The real run used watch because of 'Full stop'. Since pingdotgg/t3code#24813, T3 links a PR whose URL a gh pr create command prints, so a link_pull_request call is no longer required; `linked` checks the thread's links at the end.", "maxSteps": 10}
diff --git a/evals/mcp-tool-use/cases/visual-preview.jsonl b/evals/mcp-tool-use/cases/visual-preview.jsonl
index 6e70e729a68e6..c74f12d5b2b8a 100644
--- a/evals/mcp-tool-use/cases/visual-preview.jsonl
+++ b/evals/mcp-tool-use/cases/visual-preview.jsonl
@@ -2,8 +2,8 @@
 {"id": "render-without-html-preview", "area": "visual-preview", "kind": "bad", "pattern": "html_render without html_preview first (pattern 12)", "experience": "The agent checked a mock page with a shell screenshot, then called html_render with a guessed height and no html_preview.", "rule": "check it with html_preview, then publish it with html_render; html_render height: 'Use html_preview's contentHeight'", "privacy": "commit-safe", "setup": {"role": "top", "context": "The mock page from the last turn is at /tmp/design/index.html.", "priorTurns": [{"role": "user", "text": "The new-worktree toggle is ugly. Come up with four better options and mock them."}, {"role": "assistant", "text": "Built the mock page at /tmp/design/index.html and checked it at 728px with shot. The layout is clean.", "toolCalls": [{"tool": "Read", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/web/src/NewWorktreeToggle.tsx"}, "result": "     1\texport function NewWorktreeToggle() {\n     2\t  return <Switch label=\"New worktree\" />;\n     3\t}"}, {"tool": "Write", "input": {"file_path": "/tmp/design/index.html", "content": "<!doctype html><html><head><meta charset=\"utf-8\"><style>body{margin:0;font-family:var(--font-sans)}.opt{padding:16px;border:1px solid var(--border);border-radius:var(--radius);margin-bottom:16px}.composer{border:1px solid var(--border);border-radius:8px;padding:10px;color:var(--muted-foreground)}.row{display:flex;gap:8px;align-items:center;margin-top:8px}button{border:1px solid var(--border);border-radius:6px;padding:4px 10px;background:transparent;color:inherit}</style></head><body>\n<div class=\"opt\"><h3>A. Checkbox under the composer</h3><div class=\"composer\">Ask anything</div><label class=\"row\"><input type=\"checkbox\"> New worktree</label></div>\n<div class=\"opt\"><h3>B. Toggle in the toolbar</h3><div class=\"row\"><button>Model</button><button>Mode</button><button aria-pressed=\"true\">Worktree: on</button></div><div class=\"composer\">Ask anything</div></div>\n<div class=\"opt\"><h3>C. Split send button</h3><div class=\"composer\">Ask anything</div><div class=\"row\"><button>Send</button><button>v</button><span>Send in new worktree</span></div></div>\n<div class=\"opt\"><h3>D. Two visible choices</h3><div class=\"composer\">Ask anything</div><div class=\"row\"><button>Send here</button><button>Send in new worktree</button></div></div>\n</body></html>\n"}, "result": "File created successfully at: /tmp/design/index.html"}, {"tool": "Bash", "input": {"command": "~/.claude/skills/shot/scripts/shot /tmp/design/index.html --size 728x2000 --out /tmp/design/r728.png"}, "result": "saved /tmp/design/r728.png (728x1840)"}]}], "mocks": {"html_preview": {"width": 728, "contentHeight": 1840, "capturedHeight": 1840, "consoleMessages": []}, "html_render": {"htmlRender": {"attachmentId": "att-1", "title": "New worktree: four options", "height": 1840}, "message": "Shown to the reader above your reply. Don't mention or describe the page; reply with only what it doesn't already say."}}, "world": {"files": {"/tmp/design/index.html": "<!doctype html><html><head><meta charset=\"utf-8\"><style>body{margin:0;font-family:var(--font-sans)}.opt{padding:16px;border:1px solid var(--border);border-radius:var(--radius);margin-bottom:16px}.composer{border:1px solid var(--border);border-radius:8px;padding:10px;color:var(--muted-foreground)}.row{display:flex;gap:8px;align-items:center;margin-top:8px}button{border:1px solid var(--border);border-radius:6px;padding:4px 10px;background:transparent;color:inherit}</style></head><body>\n<div class=\"opt\"><h3>A. Checkbox under the composer</h3><div class=\"composer\">Ask anything</div><label class=\"row\"><input type=\"checkbox\"> New worktree</label></div>\n<div class=\"opt\"><h3>B. Toggle in the toolbar</h3><div class=\"row\"><button>Model</button><button>Mode</button><button aria-pressed=\"true\">Worktree: on</button></div><div class=\"composer\">Ask anything</div></div>\n<div class=\"opt\"><h3>C. Split send button</h3><div class=\"composer\">Ask anything</div><div class=\"row\"><button>Send</button><button>v</button><span>Send in new worktree</span></div></div>\n<div class=\"opt\"><h3>D. Two visible choices</h3><div class=\"composer\">Ask anything</div><div class=\"row\"><button>Send here</button><button>Send in new worktree</button></div></div>\n</body></html>\n", "/tmp/design/r728.png": "<PNG image, 728x1840>", "apps/web/src/NewWorktreeToggle.tsx": "export function NewWorktreeToggle() {\n  return <Switch label=\"New worktree\" />;\n}\n"}}}, "prompt": "Show me the four options here so I can pick one.", "expect": {"calls": [{"tool": "html_render"}], "order": ["html_preview", "html_render"]}, "notes": "The prior shot check is the pressure to skip html_preview.", "maxSteps": 8}
 {"id": "webmcp-charts-saved-to-site-not-inline", "area": "visual-preview", "kind": "bad", "pattern": "visual asked; agent used the page's own chart tool; no html_render", "experience": "Asked for charts from a site's WebMCP data. The agent saved charts to the site's dashboard. The user wanted inline visuals in T3 Code.", "rule": "When a chart ... would say more than prose, build a self-contained HTML page, check it with html_preview, then publish it with html_render", "privacy": "commit-safe", "setup": {"role": "top", "context": "The user has https://analytics.acme.dev open in preview tab tab_1 (owner unclaimed). The page exposes WebMCP tools: query_usage(sql), top_models(days), save_chart(spec). save_chart saves a chart to the site's own dashboard.", "priorTurns": [{"role": "user", "text": "I have analytics.acme.dev open in the preview browser. It has WebMCP. What can you access from it?"}, {"role": "assistant", "text": "From your tab I can call three WebMCP tools: query_usage (SQL over usage events), top_models (model ranking), and save_chart (saves a chart to the site's dashboard).", "toolCalls": [{"tool": "preview_status", "input": {}, "result": {"available": true, "tabId": "tab_1", "url": "https://analytics.acme.dev/", "tabs": [{"tabId": "tab_1", "url": "https://analytics.acme.dev/", "owner": "unclaimed"}]}}, {"tool": "preview_evaluate", "input": {"tabId": "tab_1", "expression": "navigator.modelContext.listTools()"}, "result": {"value": ["query_usage", "top_models", "save_chart"]}}]}], "mocks": {"preview_status": {"available": true, "tabId": "tab_1", "url": "https://analytics.acme.dev/", "tabs": [{"tabId": "tab_1", "url": "https://analytics.acme.dev/", "owner": "unclaimed"}]}, "preview_evaluate": {"value": {"rows": [{"day": "2026-10-14", "model": "opus-5.5", "tokens": 41200000, "costUsd": 388}, {"day": "2026-10-14", "model": "sonnet-5.5", "tokens": 9100000, "costUsd": 41}, {"day": "2026-10-15", "model": "opus-5.5", "tokens": 52800000, "costUsd": 497}, {"day": "2026-10-15", "model": "sonnet-5.5", "tokens": 7700000, "costUsd": 35}, {"day": "2026-10-16", "model": "opus-5.5", "tokens": 38900000, "costUsd": 366}, {"day": "2026-10-16", "model": "sonnet-5.5", "tokens": 12400000, "costUsd": 56}]}}, "html_preview": {"width": 728, "contentHeight": 560, "capturedHeight": 560, "consoleMessages": []}, "html_render": {"htmlRender": {"attachmentId": "att-1", "title": "Usage insights", "height": 560}, "message": "Shown to the reader above your reply. Don't mention or describe the page; reply with only what it doesn't already say."}}}, "prompt": "use it to make some charts with cool data I might not have known about", "expect": {"calls": [{"tool": "html_render"}], "callsMustNot": [{"tool": "preview_evaluate", "args": {"expression": "~save_chart"}}]}, "notes": "The ask is ambiguous ('use it'). Graded to the user's correction: inline html_render. Needs the callsNot runner key (see .md)."}
 {"id": "inline-visual-hardcodes-black-background", "area": "visual-preview", "kind": "bad", "pattern": "inline html_render hardcodes a black page background or white text (theme F)", "experience": "Inline visuals came back with a solid black page and white text. They looked wrong in the user's theme. They asked why agents always do this.", "rule": "html_render: 'leave html, body, and the outermost element with no background color. This overrides general style preferences such as a fixed black page background.'", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"html_preview": {"width": 728, "contentHeight": 560, "capturedHeight": 560, "consoleMessages": []}, "html_render": {"htmlRender": {"attachmentId": "att-1", "title": "Tool-call audit", "height": 560}, "message": "Shown to the reader above your reply. Don't mention or describe the page; reply with only what it doesn't already say."}}}, "prompt": "Here are the tool-call audit numbers per model. Make a nice inline visualization comparing them.\n\nModel | threads | repeated reads | broken calls\nOpus 5.5 | 120 | 4% | 0.5%\nSonnet 5.5 | 98 | 6% | 1.1%\nGemini 3 Pro | 64 | 19% | 3.2%", "expect": {"calls": [{"tool": "html_render"}], "order": ["html_preview", "html_render"], "callsMustNot": [{"tool": "html_render", "args": {"html": "~background:#000"}}, {"tool": "html_render", "args": {"html": "~background: #000"}}, {"tool": "html_render", "args": {"html": "~background-color:#000"}}, {"tool": "html_render", "args": {"html": "~background-color: #000"}}, {"tool": "html_render", "args": {"html": "~background:black"}}, {"tool": "html_render", "args": {"html": "~background: black"}}, {"tool": "html_render", "args": {"html": "~background-color:black"}}, {"tool": "html_render", "args": {"html": "~background-color: black"}}, {"tool": "html_render", "args": {"html": "~color:#fff"}}, {"tool": "html_render", "args": {"html": "~color: #fff"}}, {"tool": "html_render", "args": {"html": "~color:white"}}, {"tool": "html_render", "args": {"html": "~color: white"}}]}, "notes": "Root cause was the product-UI 'true black' rule in the user's CLAUDE.md. Today's CLAUDE.md adds an inline-HTML rule, so this may pass now. Keep it as the regression check for that conflict."}
-{"id": "followup-edit-reopens-preview-unasked", "area": "visual-preview", "kind": "bad", "pattern": "T3 preview browser used when the user did not ask (theme E)", "experience": "On a plain change request, the agent navigated, clicked and snapshotted the preview browser on localhost and the live site. The user: 'Don't make any changes to the preview browser. Just change code when I ask.'", "rule": "none in T3 text (t3code AGENTS.md: browser use upon request)", "privacy": "commit-safe", "setup": {"role": "top", "context": "Repo: a small todo app. The dev server already runs at http://localhost:3000. `pnpm run deploy` deploys and prints the live URL.", "priorTurns": [{"role": "user", "text": "Build and deploy the starter template. Run the dev server locally and share the link."}, {"role": "assistant", "text": "Built and deployed the starter.\n- Local: http://localhost:3000\n- Live: https://quiet-signal.acme.app", "toolCalls": [{"tool": "Bash", "input": {"command": "pnpm run deploy"}, "result": "vite v7.1.0 building for production...\n✓ built in 1.2s\nDeployed: https://quiet-signal.acme.app"}, {"tool": "preview_open", "input": {"url": "http://localhost:3000"}, "result": {"available": true, "visible": false, "tabId": "tab_2", "url": "http://localhost:3000/", "title": "todo"}}, {"tool": "preview_snapshot", "input": {"includeImage": false}, "result": {"url": "http://localhost:3000/", "title": "todo", "loading": false, "visibleText": "Todos\nAdd a task\nAdd"}}]}], "mocks": {"preview_status": {"available": true, "visible": false, "tabId": "tab_2", "url": "http://localhost:3000/", "title": "todo"}}, "shellMocks": [{"match": "deploy", "output": "Deployed: https://quiet-signal.acme.app"}], "world": {"files": {"package.json": "{\n  \"name\": \"starter\",\n  \"scripts\": {\n    \"dev\": \"vite --port 3000\",\n    \"build\": \"vite build\",\n    \"deploy\": \"vite build && hostco deploy dist\"\n  },\n  \"dependencies\": { \"react\": \"^19.2.0\", \"react-dom\": \"^19.2.0\" },\n  \"devDependencies\": { \"@vitejs/plugin-react\": \"^5.0.0\", \"hostco\": \"^3.2.0\", \"vite\": \"^7.1.0\" }\n}\n", "src/App.tsx": "import { Todos } from './todos';\n\nexport function App() {\n  return <main><h1>Todos</h1><Todos /></main>;\n}\n", "src/todos.tsx": "import { useState } from 'react';\n\nexport function Todos() {\n  const [items, setItems] = useState<string[]>([]);\n  const [text, setText] = useState('');\n  return (\n    <form onSubmit={(e) => { e.preventDefault(); setItems([...items, text]); setText(''); }}>\n      <input value={text} onChange={(e) => setText(e.target.value)} placeholder=\"Add a task\" />\n      <button>Add</button>\n      <ul>{items.map((t) => <li key={t}>{t}</li>)}</ul>\n    </form>\n  );\n}\n", "src/styles.css": ":root{color-scheme:dark;--bg:#000;--fg:#fff}\nbody{background:var(--bg);color:var(--fg)}\n"}}}, "prompt": "Make it light mode and funnier", "expect": {"notCalls": ["preview_status", "preview_open", "preview_navigate", "preview_snapshot", "preview_click", "preview_type", "preview_press", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"]}, "notes": "The prior turn holds the agent's own preview calls. That is the pressure to repeat them."}
-{"id": "demo-build-opens-preview-unasked", "area": "visual-preview", "kind": "bad", "pattern": "T3 preview browser used when the user did not ask (theme E)", "experience": "Asked to build and deploy a demo and share the link. The agent opened the preview and kept snapshotting and clicking. The user: 'Please stop trying to check so much, just ship.'", "rule": "none in T3 text (t3code AGENTS.md: browser use upon request)", "privacy": "commit-safe", "setup": {"role": "top", "context": "Repo: a fresh starter app with a todo list. `pnpm dev` serves http://localhost:3017. `pnpm run deploy` deploys and prints the live URL.", "mocks": {"preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_1", "url": "http://localhost:3017/"}, "preview_snapshot": {"error": {"_tag": "PreviewAutomationTimeoutError", "operation": "snapshot", "failureCount": 1, "message": "Preview automation snapshot timed out after 15000ms."}}}, "shellMocks": [{"match": "deploy", "output": "Deployed: https://clear-garden.acme.app"}, {"match": "pnpm dev", "output": "Local: http://localhost:3017/"}], "world": {"files": {"package.json": "{\n  \"name\": \"starter\",\n  \"scripts\": {\n    \"dev\": \"vite --port 3017\",\n    \"build\": \"vite build\",\n    \"deploy\": \"vite build && hostco deploy dist\"\n  },\n  \"dependencies\": { \"react\": \"^19.2.0\", \"react-dom\": \"^19.2.0\" },\n  \"devDependencies\": { \"@vitejs/plugin-react\": \"^5.0.0\", \"hostco\": \"^3.2.0\", \"vite\": \"^7.1.0\" }\n}\n", "src/App.tsx": "import { Todos } from './todos';\n\nexport function App() {\n  return <main><h1>Todos</h1><Todos /></main>;\n}\n", "src/todos.tsx": "import { useState } from 'react';\n\nexport function Todos() {\n  const [items, setItems] = useState<string[]>([]);\n  const [text, setText] = useState('');\n  return (\n    <form onSubmit={(e) => { e.preventDefault(); setItems([...items, text]); setText(''); }}>\n      <input value={text} onChange={(e) => setText(e.target.value)} placeholder=\"Add a task\" />\n      <button>Add</button>\n      <ul>{items.map((t) => <li key={t}>{t}</li>)}</ul>\n    </form>\n  );\n}\n", "src/styles.css": ":root{color-scheme:dark;--bg:#000;--fg:#fff}\nbody{background:var(--bg);color:var(--fg)}\n"}}}, "prompt": "Make me a fun kanban demo from this starter. Deploy as soon as you can and deploy as you make changes. Share the link as soon as you have it.", "expect": {"notCalls": ["preview_open", "preview_navigate", "preview_snapshot", "preview_click", "preview_type", "preview_press", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"], "textMust": ["https://clear-garden\\.acme\\.app"]}, "notes": "preview_status alone is not graded. Any preview action is.", "maxSteps": 10}
+{"id": "followup-edit-reopens-preview-unasked", "area": "visual-preview", "kind": "bad", "pattern": "T3 preview browser used when the user did not ask (theme E)", "experience": "On a plain change request, the agent navigated, clicked and snapshotted the preview browser on localhost and the live site. The user: 'Don't make any changes to the preview browser. Just change code when I ask.'", "rule": "none in T3 text (t3code AGENTS.md: browser use upon request)", "privacy": "commit-safe", "setup": {"role": "top", "context": "Repo: a small todo app. The dev server already runs at http://localhost:3000. `pnpm run deploy` deploys and prints the live URL.", "priorTurns": [{"role": "user", "text": "Build and deploy the starter template. Run the dev server locally and share the link."}, {"role": "assistant", "text": "Built and deployed the starter.\n- Local: http://localhost:3000\n- Live: https://quiet-signal.acme.app", "toolCalls": [{"tool": "Bash", "input": {"command": "pnpm run deploy"}, "result": "vite v7.1.0 building for production...\n✓ built in 1.2s\nDeployed: https://quiet-signal.acme.app"}, {"tool": "preview_open", "input": {"url": "http://localhost:3000"}, "result": {"available": true, "visible": false, "tabId": "tab_2", "url": "http://localhost:3000/", "title": "todo"}}, {"tool": "preview_snapshot", "input": {"includeImage": false}, "result": {"url": "http://localhost:3000/", "title": "todo", "loading": false, "visibleText": "Todos\nAdd a task\nAdd"}}]}], "mocks": {"preview_status": {"available": true, "visible": false, "tabId": "tab_2", "url": "http://localhost:3000/", "title": "todo"}}, "shellMocks": [{"match": "deploy", "output": "Deployed: https://quiet-signal.acme.app"}], "world": {"files": {"package.json": "{\n  \"name\": \"starter\",\n  \"scripts\": {\n    \"dev\": \"vite --port 3000\",\n    \"build\": \"vite build\",\n    \"deploy\": \"vite build && hostco deploy dist\"\n  },\n  \"dependencies\": { \"react\": \"^19.2.0\", \"react-dom\": \"^19.2.0\" },\n  \"devDependencies\": { \"@vitejs/plugin-react\": \"^5.0.0\", \"hostco\": \"^3.2.0\", \"vite\": \"^7.1.0\" }\n}\n", "src/App.tsx": "import { Todos } from './todos';\n\nexport function App() {\n  return <main><h1>Todos</h1><Todos /></main>;\n}\n", "src/todos.tsx": "import { useState } from 'react';\n\nexport function Todos() {\n  const [items, setItems] = useState<string[]>([]);\n  const [text, setText] = useState('');\n  return (\n    <form onSubmit={(e) => { e.preventDefault(); setItems([...items, text]); setText(''); }}>\n      <input value={text} onChange={(e) => setText(e.target.value)} placeholder=\"Add a task\" />\n      <button>Add</button>\n      <ul>{items.map((t) => <li key={t}>{t}</li>)}</ul>\n    </form>\n  );\n}\n", "src/styles.css": ":root{color-scheme:dark;--bg:#000;--fg:#fff}\nbody{background:var(--bg);color:var(--fg)}\n"}}}, "prompt": "Make it light mode and funnier", "expect": {"notCalls": ["preview_status", "preview_open", "preview_navigate", "preview_snapshot", "preview_act", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"]}, "notes": "The prior turn holds the agent's own preview calls. That is the pressure to repeat them."}
+{"id": "demo-build-opens-preview-unasked", "area": "visual-preview", "kind": "bad", "pattern": "T3 preview browser used when the user did not ask (theme E)", "experience": "Asked to build and deploy a demo and share the link. The agent opened the preview and kept snapshotting and clicking. The user: 'Please stop trying to check so much, just ship.'", "rule": "none in T3 text (t3code AGENTS.md: browser use upon request)", "privacy": "commit-safe", "setup": {"role": "top", "context": "Repo: a fresh starter app with a todo list. `pnpm dev` serves http://localhost:3017. `pnpm run deploy` deploys and prints the live URL.", "mocks": {"preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_1", "url": "http://localhost:3017/"}, "preview_snapshot": {"error": {"_tag": "PreviewAutomationTimeoutError", "operation": "snapshot", "failureCount": 1, "message": "Preview automation snapshot timed out after 15000ms."}}}, "shellMocks": [{"match": "deploy", "output": "Deployed: https://clear-garden.acme.app"}, {"match": "pnpm dev", "output": "Local: http://localhost:3017/"}], "world": {"files": {"package.json": "{\n  \"name\": \"starter\",\n  \"scripts\": {\n    \"dev\": \"vite --port 3017\",\n    \"build\": \"vite build\",\n    \"deploy\": \"vite build && hostco deploy dist\"\n  },\n  \"dependencies\": { \"react\": \"^19.2.0\", \"react-dom\": \"^19.2.0\" },\n  \"devDependencies\": { \"@vitejs/plugin-react\": \"^5.0.0\", \"hostco\": \"^3.2.0\", \"vite\": \"^7.1.0\" }\n}\n", "src/App.tsx": "import { Todos } from './todos';\n\nexport function App() {\n  return <main><h1>Todos</h1><Todos /></main>;\n}\n", "src/todos.tsx": "import { useState } from 'react';\n\nexport function Todos() {\n  const [items, setItems] = useState<string[]>([]);\n  const [text, setText] = useState('');\n  return (\n    <form onSubmit={(e) => { e.preventDefault(); setItems([...items, text]); setText(''); }}>\n      <input value={text} onChange={(e) => setText(e.target.value)} placeholder=\"Add a task\" />\n      <button>Add</button>\n      <ul>{items.map((t) => <li key={t}>{t}</li>)}</ul>\n    </form>\n  );\n}\n", "src/styles.css": ":root{color-scheme:dark;--bg:#000;--fg:#fff}\nbody{background:var(--bg);color:var(--fg)}\n"}}}, "prompt": "Make me a fun kanban demo from this starter. Deploy as soon as you can and deploy as you make changes. Share the link as soon as you have it.", "expect": {"notCalls": ["preview_open", "preview_navigate", "preview_snapshot", "preview_act", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"], "textMust": ["https://clear-garden\\.acme\\.app"]}, "notes": "preview_status alone is not graded. Any preview action is.", "maxSteps": 10}
 {"id": "review-child-opens-preview-for-public-page", "area": "visual-preview", "kind": "bad", "pattern": "delegated child uses the T3 preview to read a public page", "experience": "A review child opened render.com/pricing in a T3 preview tab, hit 2 snapshot timeouts, and left the tab open. A plain fetch was enough.", "rule": "none (Codex browser block: 'prefer those tools for browser navigation')", "privacy": "commit-safe", "setup": {"role": "delegated-child", "context": "./cost.md contains: 'Render Pro workspace $25/mo. Starter instance $7/mo. Postgres basic-256mb $6/mo. Fly shared-cpu-1x 256MB $1.94/mo.'", "mocks": {"preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_2", "url": "https://render.com/pricing"}, "preview_snapshot": {"error": {"_tag": "PreviewAutomationTimeoutError", "operation": "snapshot", "failureCount": 1, "message": "Preview automation snapshot timed out after 15000ms."}}}, "delegateRole": "review", "world": {"files": {"cost.md": "Render Pro workspace $25/mo. Starter instance $7/mo. Postgres basic-256mb $6/mo. Fly shared-cpu-1x 256MB $1.94/mo.\n"}, "pages": {"https://render.com/pricing": "<html>... Professional $25/user/month ... Starter $7/month ... Basic-256mb $6/month ...</html>", "https://fly.io/docs/about/pricing": "<html>... shared-cpu-1x 256MB $2.02/mo ...</html>"}}}, "prompt": "Adversarially check the cost comparison in ./cost.md. Verify the prices on the live web (https://render.com/pricing, https://fly.io/docs/about/pricing/) and cite URLs. Write your findings to ./review.md. Do not edit other files.", "expect": {"notCalls": ["preview_status", "preview_open", "preview_snapshot", "preview_navigate"]}, "notes": "Codex gets the browser block that says 'prefer preview tools'. Claude does not, so this may not reproduce on Claude."}
 {"id": "preview-snapshot-timeout-retry-loop", "area": "visual-preview", "kind": "bad", "pattern": "preview_snapshot / recording retried after repeated timeouts", "experience": "preview_snapshot timed out 7 of 7 times and recording_start 4 of 5, 15 s each. The agent kept retrying before it switched to shot.", "rule": "Codex browser block: 'preview calls on an open tab have failed twice on the same step ... switch'. Claude: none.", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_1", "url": "http://localhost:5733/clone"}, "preview_snapshot": {"error": {"_tag": "PreviewAutomationTimeoutError", "operation": "snapshot", "failureCount": 1, "message": "Preview automation snapshot timed out after 15000ms."}}, "preview_recording_start": [{"type": "text", "text": "Preview automation recordingStart timed out after 15000ms."}], "Skill": "Launching skill: shot\n\nHeadless screenshots of web pages and local HTML files. Run `shot <url-or-file> --size WxH --out <file.png>`. It never opens a visible browser."}, "shellMocks": [{"match": "(^|/)shot\\s", "output": "saved /tmp/clone.png (1280x800, playwright headless)"}], "world": {"files": {"/tmp/clone.png": "<PNG image, 1280x800>"}, "pages": {"http://localhost:5733": "<!doctype html><title>Clone repository</title><dialog open>Clone a repository</dialog>"}}, "harness": "claude"}, "prompt": "Take screenshots of the clone dialog at http://localhost:5733/clone for the PR description.", "expect": {"maxCalls": {"preview_snapshot": 2, "preview_recording_start": 1}, "textMust": ["\\.png"]}, "notes": "The user's CLAUDE.md names shot for headless screenshots, so shot first is also a pass.", "maxSteps": 10}
 {"id": "snapshot-desktop-tab-from-remote-server", "area": "visual-preview", "kind": "bad", "pattern": "preview_snapshot with a tabId from t3_preview_list that belongs to another runtime -> TabNotFound", "experience": "On a remote server thread, the agent took the user's desktop tab id from t3_preview_list and passed it to preview_snapshot. It failed with TabNotFound, then it tried a shell browser.", "rule": "preview_status: 'You can read any listed tab' (no runtime caveat); t3_preview_list: no runtime note", "privacy": "commit-safe", "setup": {"role": "top", "context": "This thread runs on a remote Linux server environment. The user is connected from the T3 Code desktop app.", "mocks": {"preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": [{"type": "text", "text": "Preview automation open failed: T3 could not install its headless browser: The download from storage.googleapis.com failed. Check this machine's network access. Try again."}], "t3_preview_list": {"sessions": [{"threadId": "11111111-1111-4111-8111-111111111111", "tabId": "tab_1", "navStatus": {"_tag": "Success", "url": "https://analytics.acme.dev/?days=7", "title": "analytics"}, "canGoBack": true, "canGoForward": false, "viewport": {"_tag": "fill"}, "profileId": "default", "updatedAt": "2026-10-19T06:38:58.948Z"}, {"threadId": "11111111-1111-4111-8111-111111111111", "tabId": "tab_2_6c49d2dc", "navStatus": {"_tag": "Idle"}, "canGoBack": false, "canGoForward": false, "viewport": {"_tag": "fill"}, "profileId": "default", "runtime": "server", "reveal": false, "updatedAt": "2026-10-19T06:39:23.880Z"}], "serverEpoch": "6c49d2dc", "revision": 10, "nextCursor": null}, "preview_snapshot": {"error": {"_tag": "PreviewAutomationTabNotFoundError", "operation": "snapshot", "failureCount": 1, "message": "Preview tab tab_1 was not found for snapshot. Omit tabId to use the current tab, or call preview_open."}}, "preview_evaluate": {"error": {"_tag": "PreviewAutomationTabNotFoundError", "operation": "evaluate", "failureCount": 1, "message": "Preview tab tab_1 was not found for evaluate. Omit tabId to use the current tab, or call preview_open."}}}}, "prompt": "I have analytics.acme.dev open in the preview browser. It has webmcp. use it to make some charts with cool data I might not have known about.", "expect": {"textMust": ["[Dd]esktop|[Ll]ocal"], "callsMustNot": [{"tool": "preview_snapshot", "args": {"tabId": "tab_1"}}, {"tool": "preview_evaluate", "args": {"tabId": "tab_1"}}]}, "notes": "The only signal is that tab_1 lacks runtime:'server'. A good rewrite must say which listed tabs this environment can reach. Pass = explain the desktop/remote split and suggest a local thread.", "maxSteps": 10}
@@ -11,9 +11,9 @@
 {"id": "wake-rearms-active-watch", "area": "visual-preview", "kind": "bad", "pattern": "watch_pull_request / list_thread_pull_requests re-called on a wake (pattern 14)", "experience": "On each wake the agent called watch_pull_request again on a PR T3 was already watching, and listed PRs again. Re-arming did nothing.", "rule": "watch_pull_request: 'T3 Code ... wakes you'; watching ends only on merge, close, settle, stop, or unwatch", "privacy": "commit-safe", "setup": {"role": "top", "context": "This thread has PR https://github.com/acme/app/pull/123 linked. T3 Code is watching it.", "priorTurns": [{"role": "user", "text": "File pr. Babysit. Merge when you are confident it's good to go."}, {"role": "assistant", "text": "Opened [PR #123](https://github.com/acme/app/pull/123). T3 Code is watching CI and reviews. I will merge when checks pass and findings are clear.", "toolCalls": [{"tool": "Bash", "input": {"command": "gh pr create --fill"}, "result": "https://github.com/acme/app/pull/123"}, {"tool": "link_pull_request", "input": {"url": "https://github.com/acme/app/pull/123"}, "result": {"host": "github.com", "repository": "acme/app", "number": 123, "url": "https://github.com/acme/app/pull/123", "alreadyLinked": false}}, {"tool": "watch_pull_request", "input": {"url": "https://github.com/acme/app/pull/123"}, "result": {"host": "github.com", "repository": "acme/app", "number": 123, "url": "https://github.com/acme/app/pull/123", "watching": true, "wasWatching": false}}]}], "mocks": {"watch_pull_request": {"host": "github.com", "repository": "acme/app", "number": 123, "url": "https://github.com/acme/app/pull/123", "watching": true, "wasWatching": true}, "list_thread_pull_requests": {"pullRequests": [{"host": "github.com", "repository": "acme/app", "number": 123, "url": "https://github.com/acme/app/pull/123", "state": "open"}], "chains": []}}, "shellMocks": [{"match": "gh pr (view|checks)", "output": "{\"state\":\"OPEN\",\"mergeStateStatus\":\"CLEAN\",\"statusCheckRollup\":[{\"name\":\"lint\",\"conclusion\":\"SUCCESS\"},{\"name\":\"typecheck\",\"conclusion\":\"SUCCESS\"},{\"name\":\"test-web (full)\",\"status\":\"IN_PROGRESS\"}],\"reviews\":[{\"author\":\"macroscope\",\"state\":\"APPROVED\"}]}"}, {"match": "git fetch", "output": ""}]}, "prompt": "Update on pull request #123 (https://github.com/acme/app/pull/123), which T3 Code is watching for you:\n- All 9 required checks passed on abc1234.\n- 1 new comment:\n  - macroscopeapp: APPROVED https://github.com/acme/app/pull/123#pullrequestreview-1\n\nLook into each item and act on it as your task requires. This PR stays linked and watched, so do not link, watch, or list it again. End your turn when you are done, and T3 Code wakes you on the next change. When you hand the work back to the user, call unwatch_pull_request first so the thread returns to their inbox.", "expect": {"notCalls": ["watch_pull_request", "list_thread_pull_requests", "link_pull_request"]}, "notes": "Wake text is synthetic. The runner should swap in T3's real wake message if it differs. Merging or waiting for the full test job are both fine. Prompt uses the real T3 wake message format (pullRequestWatch.ts)."}
 {"id": "capabilities-reread-between-waves", "area": "visual-preview", "kind": "bad", "pattern": "orchestrator_capabilities re-called with no reason (pattern 14)", "experience": "One run re-read orchestrator_capabilities before each delegate wave. The catalog did not change.", "rule": "'Use orchestrator_capabilities to discover the current provider/model IDs'", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Do the whole plan in docs/plan.md. Use Opus 5.5 delegates, three lanes at a time, each in its own worktree."}, {"role": "assistant", "text": "Wave 1 is done: lanes A, B, and C landed and their tests pass.", "toolCalls": [{"tool": "Read", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/docs/plan.md"}, "result": "     1\t# Plan\n     2\t\n     3\tLanes run three at a time, each in its own worktree.\n     4\t\n     5\t- A: schema for saved views\n     6\t- B: API routes for saved views\n     7\t- C: sidebar list of saved views\n     8\t- D: share a saved view by link\n     9\t- E: keyboard shortcuts for saved views\n    10\t- F: docs and changelog"}, {"tool": "orchestrator_capabilities", "input": {}, "result": {"parentThreadId": "11111111-1111-4111-8111-111111111111", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [], "runtimeMode": "full-access", "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Opus 5.5"}, {"id": "claude-sonnet-5-5", "label": "Sonnet 5.5"}]}]}}, {"tool": "delegate_task", "input": {"title": "Lane A", "mode": "async", "clientRequestId": "wave1-a", "target": {"providerInstanceId": "claudeAgent", "model": "claude-opus-5-5"}, "isolation": "worktree", "task": "Implement lane a of docs/plan.md: schema for saved views. Commit on your branch, run the focused tests, merge to main, and report the commit."}, "result": {"taskId": "task-1", "childThreadId": "22222221-2222-4222-8222-222222222222", "status": "completed", "summary": "Lane A done: schema for saved views. Merged to main as a1c0de1. Focused tests pass."}}, {"tool": "delegate_task", "input": {"title": "Lane B", "mode": "async", "clientRequestId": "wave1-b", "target": {"providerInstanceId": "claudeAgent", "model": "claude-opus-5-5"}, "isolation": "worktree", "task": "Implement lane b of docs/plan.md: API routes for saved views. Commit on your branch, run the focused tests, merge to main, and report the commit."}, "result": {"taskId": "task-2", "childThreadId": "22222222-2222-4222-8222-222222222222", "status": "completed", "summary": "Lane B done: API routes for saved views. Merged to main as b2c0de2. Focused tests pass."}}, {"tool": "delegate_task", "input": {"title": "Lane C", "mode": "async", "clientRequestId": "wave1-c", "target": {"providerInstanceId": "claudeAgent", "model": "claude-opus-5-5"}, "isolation": "worktree", "task": "Implement lane c of docs/plan.md: sidebar list of saved views. Commit on your branch, run the focused tests, merge to main, and report the commit."}, "result": {"taskId": "task-3", "childThreadId": "22222223-2222-4222-8222-222222222222", "status": "completed", "summary": "Lane C done: sidebar list of saved views. Merged to main as c3c0de3. Focused tests pass."}}]}], "mocks": {"orchestrator_capabilities": {"parentThreadId": "11111111-1111-4111-8111-111111111111", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [], "runtimeMode": "full-access", "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Opus 5.5"}, {"id": "claude-sonnet-5-5", "label": "Sonnet 5.5"}]}]}, "delegate_task": "default"}, "world": {"files": {"docs/plan.md": "# Plan\n\nLanes run three at a time, each in its own worktree.\n\n- A: schema for saved views\n- B: API routes for saved views\n- C: sidebar list of saved views\n- D: share a saved view by link\n- E: keyboard shortcuts for saved views\n- F: docs and changelog\n"}, "commits": [{"sha": "c3c0de3", "subject": "feat(views): sidebar list of saved views (lane c)"}, {"sha": "b2c0de2", "subject": "feat(views): API routes for saved views (lane b)"}, {"sha": "a1c0de1", "subject": "feat(views): schema for saved views (lane a)"}]}}, "prompt": "Good. Start wave 2: lanes D, E, and F, same setup.", "expect": {"calls": [{"tool": "delegate_task", "args": {"target.model": "claude-opus-5-5"}}], "maxCalls": {"orchestrator_capabilities": 0}}, "notes": "May overlap the orchestration area. Guard twin: guard-capabilities-recheck-after-provider-returns."}
 {"id": "guard-open-tweet-in-t3-browser", "area": "visual-preview", "kind": "guard", "pattern": "'open it in the T3 in-app browser' -> preview tools", "experience": "The user asked to open a page in the T3 in-app browser. The agent opened it with preview_open and read it with preview_snapshot.", "rule": "T3 preview tools are the in-app browser shared with the user", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_3", "url": "https://x.com/someone/status/1234567890"}, "preview_snapshot": {"url": "https://x.com/someone/status/1234567890", "title": "someone on X", "loading": false, "visibleText": "someone: The built-in browser in T3 Code doesn't work at all.\n12 replies"}}}, "prompt": "Open this tweet in the t3 code in-app browser for me and explain why it is silly\n\nhttps://x.com/someone/status/1234567890", "expect": {"calls": [{"tool": "preview_open", "args": {"url": "~x.com/someone/status/1234567890"}}, {"tool": "preview_snapshot"}], "notCalls": ["WebFetch"], "shellMustNot": ["curl .*x\\.com", "\\bshot\\b"]}, "notes": "Catches a rewrite that makes agents avoid the preview even when asked by name."}
-{"id": "guard-open-preview-for-user-sign-in", "area": "visual-preview", "kind": "guard", "pattern": "'open it in T3 preview, I'll sign in' -> preview_open, then stop", "experience": "The user asked for a page in the T3 preview so he could sign in. The agent opened it and waited.", "rule": "preview_open 'open its thread-bound inline preview by default'", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Restart the database container on the storage box."}, {"role": "assistant", "text": "The restart needs the admin panel at http://admin.acme.test:5000, and its session expired. Someone has to sign in again."}], "mocks": {"t3_preview_list": {"sessions": [], "nextCursor": null}, "preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_1", "url": "http://admin.acme.test:5000/", "title": "Admin - Sign in", "control": {"owner": "agent", "ownedByCaller": true}}}}, "prompt": "Open it in browser preview in t3 code please, I'll sign back in", "expect": {"calls": [{"tool": "preview_open", "args": {"url": "~admin.acme.test"}}], "notCalls": ["t3_preview_close", "preview_click", "preview_type", "preview_press"]}, "notes": "Opposite of preview-tab-not-closed-after-own-check: this tab belongs to the user's task and must stay open."}
-{"id": "guard-stop-preview-after-correction", "area": "visual-preview", "kind": "guard", "pattern": "after 'stop checking, just ship' -> no preview calls", "experience": "After the user said to stop checking and ship, the agent stopped preview work and deployed.", "rule": "none (user instruction)", "privacy": "commit-safe", "setup": {"role": "top", "context": "Repo: a kanban demo app. `pnpm dev` serves http://localhost:3017. `pnpm run deploy` deploys and prints the live URL.", "priorTurns": [{"role": "user", "text": "Make me a fun kanban demo. Deploy as you make changes and share the link."}, {"role": "assistant", "text": "First deploy is up. I'm adding drag-and-drop and checking it in the preview.", "toolCalls": [{"tool": "Bash", "input": {"command": "pnpm run deploy"}, "result": "✓ built in 1.1s\nDeployed: https://clear-garden.acme.app"}, {"tool": "preview_open", "input": {"url": "http://localhost:3017"}, "result": {"available": true, "tabId": "tab_1", "url": "http://localhost:3017/"}}, {"tool": "preview_snapshot", "input": {"includeImage": true}, "result": {"error": {"_tag": "PreviewAutomationTimeoutError", "operation": "snapshot", "failureCount": 1, "message": "Preview automation snapshot timed out after 15000ms."}}}, {"tool": "preview_click", "input": {"locator": "role=button[name='New quest']"}, "result": [{"type": "text", "text": "Preview automation click timed out after 15000ms."}]}]}], "shellMocks": [{"match": "deploy", "output": "Deployed: https://clear-garden.acme.app"}], "world": {"files": {"package.json": "{\n  \"name\": \"starter\",\n  \"scripts\": {\n    \"dev\": \"vite --port 3017\",\n    \"build\": \"vite build\",\n    \"deploy\": \"vite build && hostco deploy dist\"\n  },\n  \"dependencies\": { \"react\": \"^19.2.0\", \"react-dom\": \"^19.2.0\" },\n  \"devDependencies\": { \"@vitejs/plugin-react\": \"^5.0.0\", \"hostco\": \"^3.2.0\", \"vite\": \"^7.1.0\" }\n}\n", "src/App.tsx": "import { Board } from './Board';\n\nexport function App() {\n  return <Board columns={['Quests', 'Doing', 'Done']} />;\n}\n", "src/todos.tsx": "import { useState } from 'react';\n\nexport function Todos() {\n  const [items, setItems] = useState<string[]>([]);\n  const [text, setText] = useState('');\n  return (\n    <form onSubmit={(e) => { e.preventDefault(); setItems([...items, text]); setText(''); }}>\n      <input value={text} onChange={(e) => setText(e.target.value)} placeholder=\"Add a task\" />\n      <button>Add</button>\n      <ul>{items.map((t) => <li key={t}>{t}</li>)}</ul>\n    </form>\n  );\n}\n", "src/styles.css": ":root{color-scheme:dark;--bg:#000;--fg:#fff}\nbody{background:var(--bg);color:var(--fg)}\n", "src/Board.tsx": "export function Board({ columns }: { columns: string[] }) {\n  return <div className=\"board\">{columns.map((c) => <section key={c}><h2>{c}</h2></section>)}</div>;\n}\n"}}}, "prompt": "Preview browser is up. Please stop trying to check so much, just ship. Deploy", "expect": {"notCalls": ["preview_status", "preview_open", "preview_navigate", "preview_snapshot", "preview_click", "preview_type", "preview_press", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"], "textMust": ["https://clear-garden\\.acme\\.app"]}, "notes": "Guard on the recovery after demo-build-opens-preview-unasked.", "maxSteps": 8}
-{"id": "guard-x-card-png-uses-shot", "area": "visual-preview", "kind": "guard", "pattern": "headless screenshot ask -> shot skill or a shell browser, not the preview", "experience": "The user wanted one image to post on X. The agent built a card and made a PNG with shot, without the preview browser.", "rule": "The user's CLAUDE.md: 'Prefer T3 preview tools for its browser ... and shot for headless web screenshots and videos'", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Go through what I landed in the last 3 weeks and summarize it."}, {"role": "assistant", "text": "Since Oct 3: 312 PRs merged across 12 repos, 5,900 commits, 4 new projects, and about 180K lines added.", "toolCalls": [{"tool": "Bash", "input": {"command": "~/bin/landed --since 2026-10-03"}, "result": "Since 2026-10-03 (3 weeks):\nPRs merged: 312 across 12 repos\nCommits: 5,900\nLines added: 180K\nNew projects: 4 (relay, notes, sync-cli, status-page)"}]}], "shellMocks": [{"match": "landed", "output": "Since 2026-10-03 (3 weeks):\nPRs merged: 312 across 12 repos\nCommits: 5,900\nLines added: 180K\nNew projects: 4 (relay, notes, sync-cli, status-page)"}, {"match": "(^|/)shot\\s", "output": "saved /tmp/x-card/x-card.png (2400x1350, playwright headless)"}], "world": {"files": {"/tmp/x-card/x-card.png": "<PNG image, 2400x1350>"}}, "mocks": {"Skill": "Launching skill: shot\n\nHeadless screenshots of web pages and local HTML files. Run `shot <url-or-file> --size WxH --out <file.png>`. It never opens a visible browser."}, "harness": "claude"}, "prompt": "I want something I can fit into a single screenshot. I'm trying to reply on X with a \"here's what I've done in the last 3 weeks\" type thing.", "expect": {"notCalls": ["preview_open", "preview_navigate", "preview_snapshot", "preview_click", "preview_type", "preview_press", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"], "textMust": ["\\.png"]}, "notes": "Numbers are fake. Catches a rewrite that pushes every screenshot through the T3 preview. The real thread also ran an unasked Workflow; that is not graded here.", "maxSteps": 10}
+{"id": "guard-open-preview-for-user-sign-in", "area": "visual-preview", "kind": "guard", "pattern": "'open it in T3 preview, I'll sign in' -> preview_open, then stop", "experience": "The user asked for a page in the T3 preview so he could sign in. The agent opened it and waited.", "rule": "preview_open 'open its thread-bound inline preview by default'", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Restart the database container on the storage box."}, {"role": "assistant", "text": "The restart needs the admin panel at http://admin.acme.test:5000, and its session expired. Someone has to sign in again."}], "mocks": {"t3_preview_list": {"sessions": [], "nextCursor": null}, "preview_status": {"available": false, "visible": false, "tabId": null, "url": null, "title": null, "loading": false, "profiles": [{"id": "default", "name": "Default"}, {"id": "incognito", "name": "Incognito", "incognito": true}], "defaultProfileId": "default"}, "preview_open": {"available": true, "visible": false, "tabId": "tab_1", "url": "http://admin.acme.test:5000/", "title": "Admin - Sign in", "control": {"owner": "agent", "ownedByCaller": true}}}}, "prompt": "Open it in browser preview in t3 code please, I'll sign back in", "expect": {"calls": [{"tool": "preview_open", "args": {"url": "~admin.acme.test"}}], "notCalls": ["t3_preview_close", "preview_act"]}, "notes": "Opposite of preview-tab-not-closed-after-own-check: this tab belongs to the user's task and must stay open."}
+{"id": "guard-stop-preview-after-correction", "area": "visual-preview", "kind": "guard", "pattern": "after 'stop checking, just ship' -> no preview calls", "experience": "After the user said to stop checking and ship, the agent stopped preview work and deployed.", "rule": "none (user instruction)", "privacy": "commit-safe", "setup": {"role": "top", "context": "Repo: a kanban demo app. `pnpm dev` serves http://localhost:3017. `pnpm run deploy` deploys and prints the live URL.", "priorTurns": [{"role": "user", "text": "Make me a fun kanban demo. Deploy as you make changes and share the link."}, {"role": "assistant", "text": "First deploy is up. I'm adding drag-and-drop and checking it in the preview.", "toolCalls": [{"tool": "Bash", "input": {"command": "pnpm run deploy"}, "result": "✓ built in 1.1s\nDeployed: https://clear-garden.acme.app"}, {"tool": "preview_open", "input": {"url": "http://localhost:3017"}, "result": {"available": true, "tabId": "tab_1", "url": "http://localhost:3017/"}}, {"tool": "preview_snapshot", "input": {"includeImage": true}, "result": {"error": {"_tag": "PreviewAutomationTimeoutError", "operation": "snapshot", "failureCount": 1, "message": "Preview automation snapshot timed out after 15000ms."}}}, {"tool": "preview_act", "input": {"action": "click", "locator": "role=button[name='New quest']"}, "result": [{"type": "text", "text": "Preview automation click timed out after 15000ms."}]}]}], "shellMocks": [{"match": "deploy", "output": "Deployed: https://clear-garden.acme.app"}], "world": {"files": {"package.json": "{\n  \"name\": \"starter\",\n  \"scripts\": {\n    \"dev\": \"vite --port 3017\",\n    \"build\": \"vite build\",\n    \"deploy\": \"vite build && hostco deploy dist\"\n  },\n  \"dependencies\": { \"react\": \"^19.2.0\", \"react-dom\": \"^19.2.0\" },\n  \"devDependencies\": { \"@vitejs/plugin-react\": \"^5.0.0\", \"hostco\": \"^3.2.0\", \"vite\": \"^7.1.0\" }\n}\n", "src/App.tsx": "import { Board } from './Board';\n\nexport function App() {\n  return <Board columns={['Quests', 'Doing', 'Done']} />;\n}\n", "src/todos.tsx": "import { useState } from 'react';\n\nexport function Todos() {\n  const [items, setItems] = useState<string[]>([]);\n  const [text, setText] = useState('');\n  return (\n    <form onSubmit={(e) => { e.preventDefault(); setItems([...items, text]); setText(''); }}>\n      <input value={text} onChange={(e) => setText(e.target.value)} placeholder=\"Add a task\" />\n      <button>Add</button>\n      <ul>{items.map((t) => <li key={t}>{t}</li>)}</ul>\n    </form>\n  );\n}\n", "src/styles.css": ":root{color-scheme:dark;--bg:#000;--fg:#fff}\nbody{background:var(--bg);color:var(--fg)}\n", "src/Board.tsx": "export function Board({ columns }: { columns: string[] }) {\n  return <div className=\"board\">{columns.map((c) => <section key={c}><h2>{c}</h2></section>)}</div>;\n}\n"}}}, "prompt": "Preview browser is up. Please stop trying to check so much, just ship. Deploy", "expect": {"notCalls": ["preview_status", "preview_open", "preview_navigate", "preview_snapshot", "preview_act", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"], "textMust": ["https://clear-garden\\.acme\\.app"]}, "notes": "Guard on the recovery after demo-build-opens-preview-unasked.", "maxSteps": 8}
+{"id": "guard-x-card-png-uses-shot", "area": "visual-preview", "kind": "guard", "pattern": "headless screenshot ask -> shot skill or a shell browser, not the preview", "experience": "The user wanted one image to post on X. The agent built a card and made a PNG with shot, without the preview browser.", "rule": "The user's CLAUDE.md: 'Prefer T3 preview tools for its browser ... and shot for headless web screenshots and videos'", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Go through what I landed in the last 3 weeks and summarize it."}, {"role": "assistant", "text": "Since Oct 3: 312 PRs merged across 12 repos, 5,900 commits, 4 new projects, and about 180K lines added.", "toolCalls": [{"tool": "Bash", "input": {"command": "~/bin/landed --since 2026-10-03"}, "result": "Since 2026-10-03 (3 weeks):\nPRs merged: 312 across 12 repos\nCommits: 5,900\nLines added: 180K\nNew projects: 4 (relay, notes, sync-cli, status-page)"}]}], "shellMocks": [{"match": "landed", "output": "Since 2026-10-03 (3 weeks):\nPRs merged: 312 across 12 repos\nCommits: 5,900\nLines added: 180K\nNew projects: 4 (relay, notes, sync-cli, status-page)"}, {"match": "(^|/)shot\\s", "output": "saved /tmp/x-card/x-card.png (2400x1350, playwright headless)"}], "world": {"files": {"/tmp/x-card/x-card.png": "<PNG image, 2400x1350>"}}, "mocks": {"Skill": "Launching skill: shot\n\nHeadless screenshots of web pages and local HTML files. Run `shot <url-or-file> --size WxH --out <file.png>`. It never opens a visible browser."}, "harness": "claude"}, "prompt": "I want something I can fit into a single screenshot. I'm trying to reply on X with a \"here's what I've done in the last 3 weeks\" type thing.", "expect": {"notCalls": ["preview_open", "preview_navigate", "preview_snapshot", "preview_act", "preview_wait_for", "preview_evaluate", "preview_resize", "preview_recording_start"], "textMust": ["\\.png"]}, "notes": "Numbers are fake. Catches a rewrite that pushes every screenshot through the T3 preview. The real thread also ran an unasked Workflow; that is not graded here.", "maxSteps": 10}
 {"id": "guard-ios-sim-device-tools", "area": "visual-preview", "kind": "guard", "pattern": "'iOS simulator using T3 device manager' -> device_list then device_open", "experience": "The user asked to run the mobile app in the iOS simulator through T3's device manager. The agent listed devices and opened one.", "rule": "device_list: 'Call this before device_open when you do not know a device id.'", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"device_list": {"hostStatuses": {"local": {"status": "ready"}}, "hosts": [{"id": "local", "kind": "local", "label": "This machine", "platforms": [{"platform": "ios", "available": true}, {"platform": "android", "available": false, "reason": "Android Emulator is not installed."}], "devices": [{"id": "4B6971DC-ADA7-4A7A-A152-71A6EAF4D4F9", "platform": "ios", "name": "iPhone 17", "version": "iOS 26.5", "booted": false, "physical": false}]}], "openDevices": []}, "device_open": {"device": {"hostId": "local", "id": "4B6971DC-ADA7-4A7A-A152-71A6EAF4D4F9", "platform": "ios", "name": "iPhone 17", "version": "iOS 26.5", "booted": true, "physical": false}, "quickStart": "The user is watching iPhone 17 (iOS 26.5) in the Device panel."}}, "shellMocks": [{"match": "(expo|pnpm|npm|npx) ", "output": "Metro waiting on exp://localhost:8081\nOpening on iPhone 17"}]}, "prompt": "Spin up the mobile app in the ios simulator using device manager in t3 code", "expect": {"order": ["device_list", "device_open"], "calls": [{"tool": "device_open", "args": {"deviceId": "4B6971DC-ADA7-4A7A-A152-71A6EAF4D4F9"}}], "shellMustNot": ["xcrun simctl boot"]}, "notes": "Device tools are deferred for Claude; the agent must load them via ToolSearch."}
 {"id": "guard-capabilities-recheck-after-provider-returns", "area": "visual-preview", "kind": "guard", "pattern": "re-call orchestrator_capabilities when the catalog really changed", "experience": "A provider was disabled earlier. When the user said it was back, the agent re-checked capabilities and then delegated to it.", "rule": "'Use orchestrator_capabilities to discover the current provider/model IDs'", "privacy": "commit-safe", "setup": {"role": "top", "priorTurns": [{"role": "user", "text": "Make a smaller, clearer PR that fixes the hidden-tab bug. Have Gemini 3 Pro write the PR description, you tend to be too wordy."}, {"role": "assistant", "text": "The fix is pushed to branch fix/hidden-tab. Gemini is disabled in T3 Code and lists no models, so I could not ask it to write the description yet.", "toolCalls": [{"tool": "Edit", "input": {"file_path": "/home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/web/src/tabs.ts", "old_string": "  focus(tab);", "new_string": "  if (!tab.hidden) focus(tab);"}, "result": "The file /home/user/.t3/worktrees/t3code/t3-f8cdd940/apps/web/src/tabs.ts has been updated successfully."}, {"tool": "Bash", "input": {"command": "git add -A && git commit -m \"fix(web): hidden tabs no longer steal focus\""}, "result": "[fix/hidden-tab 4d2c1b0] fix(web): hidden tabs no longer steal focus\n 1 file changed"}, {"tool": "Bash", "input": {"command": "git push -u origin fix/hidden-tab"}, "result": "To github.com:acme/app.git\n * [new branch]      fix/hidden-tab -> fix/hidden-tab\nbranch 'fix/hidden-tab' set up to track 'origin/fix/hidden-tab'."}, {"tool": "orchestrator_capabilities", "input": {}, "result": {"parentThreadId": "11111111-1111-4111-8111-111111111111", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [], "runtimeMode": "full-access", "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Opus 5.5"}, {"id": "claude-sonnet-5-5", "label": "Sonnet 5.5"}]}, {"providerInstanceId": "gemini", "driverKind": "gemini", "displayName": "Gemini", "enabled": false, "models": []}]}}]}], "mocks": {"orchestrator_capabilities": {"parentThreadId": "11111111-1111-4111-8111-111111111111", "inheritedProviderInstanceId": "claudeAgent", "inheritedModel": "claude-sonnet-5-5", "inheritedOptions": [], "runtimeMode": "full-access", "providers": [{"providerInstanceId": "claudeAgent", "driverKind": "claudeAgent", "displayName": "Claude", "models": [{"id": "claude-opus-5-5", "label": "Opus 5.5"}, {"id": "claude-sonnet-5-5", "label": "Sonnet 5.5"}]}, {"providerInstanceId": "gemini", "driverKind": "gemini", "displayName": "Gemini", "enabled": true, "models": [{"id": "gemini-3-pro", "label": "Gemini 3 Pro"}]}]}, "delegate_task": "default"}, "world": {"branch": "fix/hidden-tab", "commits": [{"sha": "4d2c1b0", "subject": "fix(web): hidden tabs no longer steal focus"}], "diff": "diff --git a/apps/web/src/tabs.ts b/apps/web/src/tabs.ts\n--- a/apps/web/src/tabs.ts\n+++ b/apps/web/src/tabs.ts\n@@ -10,1 +10,1 @@\n-  focus(tab);\n+  if (!tab.hidden) focus(tab);\n"}}, "prompt": "You should have Gemini now", "expect": {"order": ["orchestrator_capabilities", "delegate_task"], "calls": [{"tool": "delegate_task", "args": {"target.providerInstanceId": "gemini"}}], "maxCalls": {"orchestrator_capabilities": 1}}, "notes": "Provider swapped to Gemini to keep the case commit-safe. Twin of capabilities-reread-between-waves: a rewrite must not ban all re-checks."}
 {"id": "guard-inline-visual-preview-then-render", "area": "visual-preview", "kind": "guard", "pattern": "inline visual ask -> html_preview then html_render", "experience": "The user asked for an inline visualization of a small table. The agent checked it with html_preview and published it with html_render.", "rule": "check it with html_preview, then publish it with html_render before your final reply", "privacy": "commit-safe", "setup": {"role": "top", "mocks": {"html_preview": {"width": 728, "contentHeight": 560, "capturedHeight": 560, "consoleMessages": []}, "html_render": {"htmlRender": {"attachmentId": "att-1", "title": "Failed implementations", "height": 560}, "message": "Shown to the reader above your reply. Don't mention or describe the page; reply with only what it doesn't already say."}}}, "prompt": "Make a nice visualization in line here for this data showcasing how many bad implementations have been made and how expensive they were\n\nFeature | attempts | failed attempts | cost of failed attempts\nSidebar drag and drop | 6 | 4 | $310\nCommand+F search | 3 | 1 | $45\nPR watch | 5 | 3 | $220\nInline HTML frames | 4 | 2 | $160\nDevice panel | 2 | 0 | $0", "expect": {"order": ["html_preview", "html_render"], "notCalls": ["preview_open"], "callsMustNot": [{"tool": "html_render", "args": {"html": "~background:#000"}}, {"tool": "html_render", "args": {"html": "~background: #000"}}, {"tool": "html_render", "args": {"html": "~background-color:#000"}}, {"tool": "html_render", "args": {"html": "~background-color: #000"}}, {"tool": "html_render", "args": {"html": "~background:black"}}, {"tool": "html_render", "args": {"html": "~background: black"}}, {"tool": "html_render", "args": {"html": "~background-color:black"}}, {"tool": "html_render", "args": {"html": "~background-color: black"}}, {"tool": "html_render", "args": {"html": "~color:#fff"}}, {"tool": "html_render", "args": {"html": "~color: #fff"}}, {"tool": "html_render", "args": {"html": "~color:white"}}, {"tool": "html_render", "args": {"html": "~color: white"}}]}, "notes": "Data is fake."}
@@ -23,6 +23,6 @@
 {"id": "control-explain-why-change", "area": "visual-preview", "kind": "control", "privacy": "commit-safe", "rule": "'Ordinary coding tasks need no T3 tools'", "expect": {"notCalls": ["delegate_task", "orchestrator_capabilities", "task_status", "t3_thread_launch", "create_threads", "t3_thread_read", "link_pull_request", "list_thread_pull_requests", "watch_pull_request", "html_preview", "html_render", "preview_status", "preview_open", "preview_snapshot", "t3_preview_list", "device_list", "schedule_task"]}, "pattern": "ordinary task: explain a change from git history", "experience": "Explain why a commit was made. No T3 tool is needed.", "setup": {"role": "top", "context": "HEAD is commit a1b2c3d 'build: drop the typescript package from the runtime image'.", "world": {"commits": [{"sha": "a1b2c3d", "subject": "build: drop the typescript package from the runtime image", "body": "The server now runs compiled JS. tsc was only used at build time and added 23 MB to the image."}], "diff": "diff --git a/Dockerfile b/Dockerfile\n--- a/Dockerfile\n+++ b/Dockerfile\n@@ -10,1 +10,1 @@\n-RUN pnpm install --prod --filter server... typescript\n+RUN pnpm install --prod --filter server...\n"}}, "prompt": "Why was this change made?"}
 {"id": "control-run-lint-and-fix", "area": "visual-preview", "kind": "control", "privacy": "commit-safe", "rule": "'Ordinary coding tasks need no T3 tools'", "expect": {"notCalls": ["delegate_task", "orchestrator_capabilities", "task_status", "t3_thread_launch", "create_threads", "t3_thread_read", "link_pull_request", "list_thread_pull_requests", "watch_pull_request", "html_preview", "html_render", "preview_status", "preview_open", "preview_snapshot", "t3_preview_list", "device_list", "schedule_task"]}, "pattern": "ordinary task: run lint and fix", "experience": "Run lint and fix the findings. No T3 tool is needed.", "setup": {"role": "top", "shellMocks": [{"match": "lint", "output": "src/util.ts\n  12:7  error  'unused' is assigned a value but never used  no-unused-vars\n  30:1  error  Missing return type on function  explicit-function-return-type\n2 problems"}], "world": {"files": {"src/util.ts": "export function sum(xs: number[]) {\n  const unused = 0;\n  return xs.reduce((a, b) => a + b, 0);\n}\n\nexport function label(n: number) {\n  return `${n} items`;\n}\n"}}}, "prompt": "Run lint and fix whatever it finds.", "notes": "Prompt is generic; the source only shows lint as ordinary work."}
 {"id": "control-refactor-chart-component", "area": "visual-preview", "kind": "control", "privacy": "commit-safe", "rule": "'Ordinary coding tasks need no T3 tools'", "expect": {"notCalls": ["delegate_task", "orchestrator_capabilities", "task_status", "t3_thread_launch", "create_threads", "t3_thread_read", "link_pull_request", "list_thread_pull_requests", "watch_pull_request", "html_preview", "html_render", "preview_status", "preview_open", "preview_snapshot", "t3_preview_list", "device_list", "schedule_task"]}, "pattern": "ordinary task with a visual-sounding word ('chart')", "experience": "Refactor a chart component. The word 'chart' must not pull the agent into html_render.", "setup": {"role": "top", "world": {"files": {"src/components/UsageChart.tsx": "import { useState } from 'react';\nimport { nearest, type Row } from '../lib/chart';\nimport { Tooltip } from './Tooltip';\n\ntype Props = { rows: Row[] };\n\nexport function UsageChart({ rows }: Props) {\n  const [hover, setHover] = useState<Row | null>(null)\n  const onMove = (e: MouseEvent) => { /* find nearest row */ setHover(nearest(rows, e.clientX)) }\n  return <svg onMouseMove={onMove}>{/* bars */}{hover && <Tooltip row={hover} />}</svg>\n}\n", "src/lib/chart.ts": "export type Row = { day: string; tokens: number };\nexport const nearest = (rows: Row[], x: number) => rows[Math.round(x)] ?? null;\n"}}}, "prompt": "Refactor src/components/UsageChart.tsx so the tooltip hover logic lives in its own hook. No behavior change.", "notes": "Prompt adapted. Catches a rewrite that makes any chart mention trigger html_render."}
-{"id": "control-explain-preview-manager-code", "area": "visual-preview", "kind": "control", "privacy": "commit-safe", "rule": "'Ordinary coding tasks need no T3 tools'", "expect": {"notCalls": ["delegate_task", "orchestrator_capabilities", "task_status", "t3_thread_launch", "create_threads", "t3_thread_read", "link_pull_request", "list_thread_pull_requests", "watch_pull_request", "html_preview", "html_render", "preview_status", "preview_open", "preview_snapshot", "t3_preview_list", "device_list", "schedule_task", "preview_status", "t3_preview_list", "t3_preview_close"]}, "pattern": "ordinary task with a T3-sounding word ('preview tab')", "experience": "Explain code about preview tabs. The words 'preview tab' must not pull the agent into preview tools.", "setup": {"role": "top", "world": {"files": {"apps/server/src/preview/Manager.ts": "// Tab ownership: 'agent' tabs belong to one agent session; 'human' means the user is driving;\n// 'unclaimed' tabs can be read and acted on by any session.\nexport function canAct(tab: Tab, caller: SessionId) {\n  if (tab.owner === 'human') return false\n  if (tab.owner === 'unclaimed') return true\n  return tab.ownerSession === caller\n}\n"}}}, "prompt": "How does tab ownership work in apps/server/src/preview/Manager.ts? Explain it briefly.", "notes": "Prompt adapted; the source is an ordinary explain-code turn."}
+{"id": "control-explain-preview-manager-code", "area": "visual-preview", "kind": "control", "privacy": "commit-safe", "rule": "'Ordinary coding tasks need no T3 tools'", "expect": {"notCalls": ["delegate_task", "orchestrator_capabilities", "task_status", "t3_thread_launch", "create_threads", "t3_thread_read", "link_pull_request", "list_thread_pull_requests", "watch_pull_request", "html_preview", "html_render", "preview_status", "preview_open", "preview_snapshot", "t3_preview_list", "device_list", "schedule_task", "t3_preview_close"]}, "pattern": "ordinary task with a T3-sounding word ('preview tab')", "experience": "Explain code about preview tabs. The words 'preview tab' must not pull the agent into preview tools.", "setup": {"role": "top", "world": {"files": {"apps/server/src/preview/Manager.ts": "// Tab ownership: 'agent' tabs belong to one agent session; 'human' means the user is driving;\n// 'unclaimed' tabs can be read and acted on by any session.\nexport function canAct(tab: Tab, caller: SessionId) {\n  if (tab.owner === 'human') return false\n  if (tab.owner === 'unclaimed') return true\n  return tab.ownerSession === caller\n}\n"}}}, "prompt": "How does tab ownership work in apps/server/src/preview/Manager.ts? Explain it briefly.", "notes": "Prompt adapted; the source is an ordinary explain-code turn."}
 {"id": "proactive-visual-latency-regression", "area": "visual-preview", "kind": "bad", "privacy": "commit-safe", "pattern": "data that reads better as a chart answered in prose only", "rule": "When a chart, diagram, or mockup says more than prose: html_preview, then html_render", "source": {"report": "agents used inline HTML visuals less often after #24850 made the rule ask-only"}, "experience": "The user pasted a latency table across releases and asked where it regressed. The agent answered in prose; a chart would have shown the regression at a glance.", "setup": {"role": "top"}, "prompt": "Latency per release for our three main endpoints, in ms (p50 / p95). Which release regressed, and on which endpoint?\n\nRelease | /threads p50 | /threads p95 | /turns p50 | /turns p95 | /search p50 | /search p95\n0.41 | 38 | 92 | 120 | 310 | 44 | 101\n0.42 | 37 | 95 | 118 | 305 | 46 | 104\n0.43 | 39 | 97 | 121 | 318 | 45 | 99\n0.44 | 41 | 210 | 119 | 312 | 47 | 102\n0.45 | 40 | 236 | 162 | 480 | 46 | 100\n0.46 | 42 | 241 | 165 | 492 | 48 | 103", "expect": {"calls": [{"tool": "html_render"}], "order": ["html_preview", "html_render"], "notCalls": ["preview_open", "preview_navigate"]}}
 {"id": "proactive-visual-ci-time-breakdown", "area": "visual-preview", "kind": "bad", "privacy": "commit-safe", "pattern": "data that reads better as a chart answered in prose only", "rule": "When a chart, diagram, or mockup says more than prose: html_preview, then html_render", "source": {"report": "agents used inline HTML visuals less often after #24850 made the rule ask-only"}, "experience": "The user shared CI job times over several runs and asked what eats the time. The agent answered in prose; a stacked chart would have shown it.", "setup": {"role": "top"}, "prompt": "CI got slow. Here are job times in minutes for the last 8 runs on main. What's eating the time?\n\nRun | install | typecheck | lint | test-server | test-web | build | e2e\n1 | 2.1 | 3.0 | 1.2 | 6.8 | 4.1 | 3.3 | 7.9\n2 | 2.0 | 3.1 | 1.1 | 6.9 | 4.0 | 3.4 | 8.2\n3 | 2.2 | 3.0 | 1.2 | 7.4 | 4.2 | 3.3 | 8.0\n4 | 2.1 | 3.2 | 1.3 | 9.8 | 4.1 | 3.5 | 8.1\n5 | 2.3 | 3.1 | 1.2 | 12.6 | 4.3 | 3.4 | 8.4\n6 | 2.2 | 3.3 | 1.2 | 13.1 | 4.2 | 3.6 | 12.9\n7 | 2.1 | 3.2 | 1.3 | 13.4 | 4.4 | 3.5 | 13.2\n8 | 2.2 | 3.2 | 1.2 | 13.0 | 4.3 | 3.4 | 13.5", "expect": {"calls": [{"tool": "html_render"}], "order": ["html_preview", "html_render"], "notCalls": ["preview_open", "preview_navigate"]}}
diff --git a/evals/mcp-tool-use/run.ts b/evals/mcp-tool-use/run.ts
index b35877658e271..cca050021dd4a 100644
--- a/evals/mcp-tool-use/run.ts
+++ b/evals/mcp-tool-use/run.ts
@@ -28,6 +28,7 @@ import { FetchHttpClient, HttpClient, HttpClientRequest } from "effect/http";
 
 import { taskPrompt } from "../../apps/server/src/mcp/OrchestratorMcpService.ts";
 import * as McpInvocationContext from "../../apps/server/src/mcp/McpInvocationContext.ts";
+import { advertisedJsonSchema } from "../../apps/server/src/mcp/advertisedJsonSchema.ts";
 import { ORCHESTRATOR_MCP_RUNNING_TASK_NEXT } from "@t3tools/contracts";
 import { formatThreadLink } from "@t3tools/shared/threadLinks";
 import { buildCodexAdditionalContext } from "../../apps/server/src/provider/CodexDeveloperInstructions.ts";
@@ -39,7 +40,10 @@ import { OrchestratorToolkit } from "../../apps/server/src/mcp/toolkits/orchestr
 import { PreviewToolkit } from "../../apps/server/src/mcp/toolkits/preview/tools.ts";
 import { PreviewControlsToolkit } from "../../apps/server/src/mcp/toolkits/previewControls/tools.ts";
 import { ProjectToolkit } from "../../apps/server/src/mcp/toolkits/project/tools.ts";
-import { PullRequestsToolkit } from "../../apps/server/src/mcp/toolkits/pullRequests/tools.ts";
+import {
+  CHILD_PULL_REQUEST_REPORT_NEXT,
+  PullRequestsToolkit,
+} from "../../apps/server/src/mcp/toolkits/pullRequests/tools.ts";
 import { ThreadToolkit } from "../../apps/server/src/mcp/toolkits/thread/tools.ts";
 import { WorktreeToolkit } from "../../apps/server/src/mcp/toolkits/worktree/tools.ts";
 import {
@@ -301,7 +305,7 @@ const t3SourceTools: ReadonlyArray<Tool.Any> = [
 const t3Tools: ReadonlyArray<ApiTool> = t3SourceTools.map((tool) => ({
   name: `${T3_PREFIX}${tool.name}`,
   description: Tool.getDescription(tool) ?? "",
-  input_schema: Tool.getJsonSchema(tool),
+  input_schema: advertisedJsonSchema(tool),
 }));
 // T3 does not offer these to a delegated child, so its harness never lists them.
 const hiddenFromSubagents = new Set(
@@ -869,7 +873,7 @@ const t3Default = (sample: Sample, name: string, input: Readonly<Record<string,
 };
 
 /** Fields T3 adds to real thread and task results, applied to mocks and defaults alike. */
-const withProductFields = (name: string, value: unknown): unknown => {
+const withProductFields = (name: string, value: unknown, child: boolean): unknown => {
   if (!isRecord(value)) return value;
   const linked = (thread: unknown, idKey = "threadId") => {
     if (!isRecord(thread) || thread.link !== undefined) return thread;
@@ -896,6 +900,8 @@ const withProductFields = (name: string, value: unknown): unknown => {
       return listed("threads");
     case "t3_thread_search":
       return listed("matches");
+    case "link_pull_request":
+      return child ? { ...value, next: CHILD_PULL_REQUEST_REPORT_NEXT } : value;
     default:
       return value;
   }
@@ -1084,7 +1090,7 @@ const answerToolCall = Effect.fn("evaluateMcpToolUse.answerToolCall")(function*
       call.id,
       name === "orchestrator_capabilities"
         ? capabilities(sample, mock)
-        : withProductFields(name, mock),
+        : withProductFields(name, mock, testCase.setup.role === "delegated-child"),
     );
   if (isT3Name(call.name)) {
     // T3 refuses a watch from a delegated child.
@@ -1096,7 +1102,7 @@ const answerToolCall = Effect.fn("evaluateMcpToolUse.answerToolCall")(function*
       call.id,
       name === "orchestrator_capabilities"
         ? capabilities(sample, value)
-        : withProductFields(name, value),
+        : withProductFields(name, value, testCase.setup.role === "delegated-child"),
     );
   }
   if (call.name === "clock__curr_time")
diff --git a/packages/provider-core/src/server/orchestrationInstructions.ts b/packages/provider-core/src/server/orchestrationInstructions.ts
index 8f70ef5bcbc7e..d78776eb78439 100644
--- a/packages/provider-core/src/server/orchestrationInstructions.ts
+++ b/packages/provider-core/src/server/orchestrationInstructions.ts
@@ -18,7 +18,7 @@ Ordinary coding tasks need no T3 tools.
 - T3 tools may load late. Try the name once before you call it absent.`,
   `### Visuals and preview
 
-- Show trends, comparisons, and flows as a chart or diagram, even unasked, and any visual the user asks for here: pass its HTML to \`html_preview\`, then \`html_render\`. If the visual is a file, pass that file's HTML. A screenshot on disk or a text description does not show it. Never start a server for it. Tools a web page exposes give data only. Never use them to show results. Asked for an image to post, send, or use elsewhere: a \`.png\` file and its path, never \`html_render\`.
+- Answer data with a trend or comparison with a chart, and show any visual the user asks for here: pass its HTML to \`html_preview\`, then \`html_render\`. If the visual is a file, pass that file's HTML. A screenshot on disk or a text description does not show it. Never start a server for it. Tools a web page exposes give data only. Never use them to show results. Asked for an image to post, send, or use elsewhere: a \`.png\` file and its path, never \`html_render\`.
 - Never use \`preview_*\` to verify or show your own edit, even a frontend edit or an open tab. Do not repeat preview calls from an earlier turn. Use them only when the current request asks for browser work or names a page or tab. Public pages: web fetch or search unless browser work was asked; then preview tools only, no web fetch. Close a tab you opened before you reply, unless the user asked for it or uses it.`,
 ];