Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
content(x): move ten X stories to review, record their editor reviews and new proof runs
nirholas59ef51537926
diff --git a/data/x-content/proofs/pocket-console.json b/data/x-content/proofs/pocket-console.jsonnew file mode 100644index 000000000..e03e9052f--- /dev/null+++ b/data/x-content/proofs/pocket-console.json@@ -0,0 +1,73 @@+{+ "id": "pocket-console",+ "scenarioHash": "0f65d3f78035ba624567ee01cfc3a35b706e3731d83034c4ba3649c68e4f011d",+ "ranAt": "2026-09-30T08:36:59.792Z",+ "target": {+ "commit": "fa1136197",+ "revision": "three-ws-api-00469-jz4"+ },+ "passed": false,+ "steps": [+ {+ "index": 1,+ "kind": "goto",+ "target": "https://three.ws/pocket",+ "detail": "loaded https://three.ws/pocket",+ "ok": true,+ "ms": 26815,+ "frames": 0+ },+ {+ "index": 2,+ "kind": "scroll",+ "target": "cartridge 01",+ "detail": "scrolled 249 px",+ "ok": true,+ "ms": 36342,+ "frames": 0+ },+ {+ "index": 3,+ "kind": "read",+ "target": "cartridge",+ "detail": "cartridge = \"01\"",+ "ok": true,+ "ms": 986,+ "frames": 0+ },+ {+ "index": 4,+ "kind": "hold",+ "target": "1400",+ "detail": "1400 ms",+ "ok": true,+ "ms": 52779,+ "frames": 0+ },+ {+ "index": 5,+ "kind": "hold",+ "target": "2400",+ "detail": "2400 ms",+ "ok": true,+ "ms": 66594,+ "frames": 0+ },+ {+ "index": 6,+ "kind": "click",+ "target": "A wave",+ "ok": false,+ "detail": "nothing visible matches \"A wave\"",+ "ms": 50820,+ "frames": 0+ }+ ],+ "facts": {+ "cartridge": "01"+ },+ "saw": [],+ "responses": [],+ "cuts": [],+ "video": null+}diff --git a/data/x-content/proofs/zz-probe-mkt.json b/data/x-content/proofs/zz-probe-mkt.jsonnew file mode 100644index 000000000..8fca80996--- /dev/null+++ b/data/x-content/proofs/zz-probe-mkt.json@@ -0,0 +1,53 @@+{+ "id": "zz-probe-mkt",+ "scenarioHash": "1cf6e9c21e0dba64601d7873a474c538a7966b0032d7642c9150ad24d7063fd1",+ "ranAt": "2026-09-30T08:41:17.590Z",+ "target": {+ "commit": "fa1136197",+ "revision": "three-ws-api-00469-jz4"+ },+ "passed": false,+ "steps": [+ {+ "index": 1,+ "kind": "goto",+ "target": "https://three.ws/marketplace",+ "detail": "loaded https://three.ws/marketplace",+ "ok": true,+ "ms": 11039,+ "frames": 0+ },+ {+ "index": 2,+ "kind": "scroll",+ "target": "Academic",+ "detail": "scrolled 1264 px",+ "ok": true,+ "ms": 17793,+ "frames": 0+ },+ {+ "index": 3,+ "kind": "wait",+ "target": "1500",+ "detail": "1500 ms, not filmed",+ "ok": true,+ "ms": 1525,+ "frames": 0+ },+ {+ "index": 4,+ "kind": "expect",+ "target": "ZZZNOTHERE",+ "ok": false,+ "detail": "locator.waitFor: Timeout 1000ms exceeded.",+ "ms": 1597,+ "frames": 0+ }+ ],+ "facts": {},+ "saw": [],+ "responses": [],+ "cuts": [],+ "video": null+}diff --git a/data/x-content/proofs/zz-probe-walk.json b/data/x-content/proofs/zz-probe-walk.jsonnew file mode 100644index 000000000..378a4fb71--- /dev/null+++ b/data/x-content/proofs/zz-probe-walk.json@@ -0,0 +1,53 @@+{+ "id": "zz-probe-walk",+ "scenarioHash": "bcae70f73429e701ad23fd4ed94b9443da5a0b38622371740d400a6ca30ab6c2",+ "ranAt": "2026-09-30T08:36:50.456Z",+ "target": {+ "commit": "fa1136197",+ "revision": "three-ws-api-00469-jz4"+ },+ "passed": false,+ "steps": [+ {+ "index": 1,+ "kind": "goto",+ "target": "https://three.ws/marketplace-walk",+ "detail": "loaded https://three.ws/marketplace-walk",+ "ok": true,+ "ms": 42356,+ "frames": 0+ },+ {+ "index": 2,+ "kind": "hold",+ "target": "2500",+ "detail": "2500 ms",+ "ok": true,+ "ms": 212336,+ "frames": 0+ },+ {+ "index": 3,+ "kind": "wait",+ "target": "1000",+ "detail": "1000 ms, not filmed",+ "ok": true,+ "ms": 4991,+ "frames": 0+ },+ {+ "index": 4,+ "kind": "expect",+ "target": "ZZZNOTHERE",+ "ok": false,+ "detail": "locator.waitFor: Timeout 1000ms exceeded.",+ "ms": 5141,+ "frames": 0+ }+ ],+ "facts": {},+ "saw": [],+ "responses": [],+ "cuts": [],+ "video": null+}diff --git a/data/x-content/queue.json b/data/x-content/queue.jsonindex 6adb40d03..7470553fd 100644--- a/data/x-content/queue.json+++ b/data/x-content/queue.json@@ -3098,7 +3098,7 @@},{"id": "agent-monitor",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "developer",@@ -3374,7 +3374,7 @@},{"id": "agent-spotlight",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "community",@@ -3673,7 +3673,7 @@},{"id": "avatar-cli",- "status": "draft",+ "status": "review","kind": "post","tier": 3,"lane": "developer",@@ -3971,7 +3971,7 @@},{"id": "choreograph",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "community",@@ -4171,7 +4171,7 @@},{"id": "docs-world",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "community",@@ -4454,7 +4454,7 @@},{"id": "drive-copilot",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "community",@@ -4697,7 +4697,7 @@},{"id": "gestures",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "community",@@ -4914,7 +4914,7 @@},{"id": "glance",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "developer",@@ -5239,7 +5239,7 @@},{"id": "glb-diff",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "developer",@@ -5584,12 +5584,12 @@},{"id": "machine-atlas",- "status": "draft",+ "status": "approved","kind": "post","tier": 2,"lane": "labs","pattern": "mechanism",- "notBefore": "2026-09-30T00:00:00Z",+ "notBefore": "2026-09-30T11:16:58.931Z","covers": ["/assembly"],@@ -5924,11 +5924,12 @@]}],- "mentions": {}+ "mentions": {},+ "approvedBy": "policy"},{"id": "model-inspect",- "status": "draft",+ "status": "review","kind": "post","tier": 2,"lane": "developer",diff --git a/data/x-content/reviews/agent-monitor.json b/data/x-content/reviews/agent-monitor.jsonnew file mode 100644index 000000000..0f21121f5--- /dev/null+++ b/data/x-content/reviews/agent-monitor.json@@ -0,0 +1,201 @@+{+ "id": "agent-monitor",+ "contentHash": "e02df0329e0a2e1466cd00aeeea084afdb7d16d37e3476e35eb0028fdd42be68",+ "reviewedAt": "2026-09-30T08:45:45.698Z",+ "passed": false,+ "blockers": [+ "probe:scenario the filmed scenario: fleet is now \"2,549\", the reel shows \"2,546\"; prove it again",+ "editor (accuracy): The scenario re-probe failed: the fleet now reads \"2,549\" while the filmed reel shows \"2,546\" in the fleet counter of every frame. The copy stays true either way, but the attached proof run is stale and the verification record for the reel fails, so the package must be re-filmed against the live product before it ships.",+ "editor verdict is revise"+ ],+ "texts": [+ "More than 2,500 public agents on one board, ranked by the most recent real thing each one did.\n\nThe Agent Monitor is the ops room for the fleet: live panels on one screen, each one a public endpoint polled on its own cadence, and nothing on the page needs a session. Type a name or a word from a description and the fleet narrows on the server. Pick an agent and its own 3D avatar renders in the page, live.\n\nNothing on it is simulated. When the platform is quiet the board shows zeroes and says so.",+ "A failed panel degrades alone: it badges itself stale and keeps its last good data rather than blanking, so one dead endpoint never takes the board down. Polling pauses while the tab is hidden and every panel refreshes on the way back.\n\nKeys: f focuses the search, r refreshes everything. three.ws/monitor"+ ],+ "lint": [],+ "verification": {+ "ok": false,+ "checks": [+ {+ "claim": "More than 2,500 public agents",+ "kind": "evidence:proof",+ "target": "fleet",+ "ok": true,+ "detail": "the run read fleet = \"2,546\""+ },+ {+ "claim": "ranked by the most recent real thing each one did",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"ranked by its most recent real action\""+ },+ {+ "claim": "the ops room for the fleet",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"is the ops room for the three.ws agent fleet\""+ },+ {+ "claim": "live panels on one screen, each one a public endpoint polled on its own cadence",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"live panels on one screen, each one a real public endpoint polled on its own cadence\""+ },+ {+ "claim": "nothing on the page needs a session",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"Nothing on this page needs a session\""+ },+ {+ "claim": "the fleet narrows on the server",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"Server-side search on name and description\""+ },+ {+ "claim": "the fleet narrows on the server",+ "kind": "evidence:proof",+ "target": "/api/agents/public",+ "ok": true,+ "detail": "GET /api/agents/public answered 200 in 2.6 s"+ },+ {+ "claim": "its own 3D avatar renders in the page, live",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"live 3D avatar, rendered in the page\""+ },+ {+ "claim": "its own 3D avatar renders in the page, live",+ "kind": "evidence:proof",+ "target": "/api/agents/210e9990",+ "ok": true,+ "detail": "GET /api/agents/210e9990-7d7e-47e7-8b80-1e4894ec6b83 answered 200 in 0.3 s"+ },+ {+ "claim": "Nothing on it is simulated",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"Nothing is simulated\""+ },+ {+ "claim": "the board shows zeroes and says so",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"the board shows zeroes and says so\""+ },+ {+ "claim": "A failed panel degrades alone",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"A failed panel degrades alone\""+ },+ {+ "claim": "badges itself stale and keeps its last good data rather than blanking",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"badges itself stale\""+ },+ {+ "claim": "badges itself stale and keeps its last good data rather than blanking",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"keeps showing it rather than blanking\""+ },+ {+ "claim": "one dead endpoint never takes the board down",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"One dead endpoint never takes the board down\""+ },+ {+ "claim": "Polling pauses while the tab is hidden and every panel refreshes on the way back",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"Polling pauses when the tab is hidden\""+ },+ {+ "claim": "Polling pauses while the tab is hidden and every panel refreshes on the way back",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"every panel refreshes on the way back\""+ },+ {+ "claim": "f focuses the search, r refreshes everything",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/monitor",+ "ok": true,+ "detail": "live page shows \"f focuses fleet search, r refreshes everything\""+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": false,+ "detail": "fleet is now \"2,549\", the reel shows \"2,546\"; prove it again"+ },+ {+ "kind": "probe:api",+ "target": "the public fleet feed answers",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/monitor",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 4,+ "clarity": 5,+ "specificity": 5,+ "voice": 5,+ "professionalism": 5,+ "visual": 3+ },+ "issues": [+ {+ "severity": "blocking",+ "area": "accuracy",+ "quote": "More than 2,500 public agents",+ "problem": "The scenario re-probe failed: the fleet now reads \"2,549\" while the filmed reel shows \"2,546\" in the fleet counter of every frame. The copy stays true either way, but the attached proof run is stale and the verification record for the reel fails, so the package must be re-filmed against the live product before it ships.",+ "fix": "Re-run the scenario and recapture the reel so the film and the probe record the current live fleet number (2,549 at last probe). No copy change is needed since 'More than 2,500' holds."+ }+ ],+ "rewrite": {+ "posts": [+ "More than 2,500 public agents on one board, ranked by the most recent real thing each one did.\n\nThe Agent Monitor is the ops room for the fleet: live panels on one screen, each one a public endpoint polled on its own cadence, and nothing on the page needs a session. Type a name or a word from a description and the fleet narrows on the server. Pick an agent and its own 3D avatar renders in the page, live.\n\nNothing on it is simulated. When the platform is quiet the board shows zeroes and says so.",+ "A failed panel degrades alone: it badges itself stale and keeps its last good data rather than blanking, so one dead endpoint never takes the board down. Polling pauses while the tab is hidden and every panel refreshes on the way back.\n\nKeys: f focuses the search, r refreshes everything. three.ws/monitor"+ ],+ "altText": []+ },+ "summary": "Every factual claim passed against the live docs page and the API, and the copy obeys the voice contract cleanly. The one blocker is media freshness: the reel shows 2,546 while the live fleet is 2,549 and the re-probe failed, so re-film the scenario before shipping; the text itself ships unchanged.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": []+ },+ "editorError": null+}diff --git a/data/x-content/reviews/agent-spotlight.json b/data/x-content/reviews/agent-spotlight.jsonnew file mode 100644index 000000000..9065d7955--- /dev/null+++ b/data/x-content/reviews/agent-spotlight.json@@ -0,0 +1,166 @@+{+ "id": "agent-spotlight",+ "contentHash": "ee9c078011bc89a7e7b7cd35b8428bec518bdbcdde61c4e68640f3f2306f9974",+ "reviewedAt": "2026-09-30T08:48:02.272Z",+ "passed": false,+ "blockers": [+ "the AI editor did not run: no model was reachable:"+ ],+ "texts": [+ "Open the Agent Spotlight, type the job you need done, and the agent that does it is standing there in 3D with a write-up of what it is for: three.ws/spotlight\n\nThe agents index lists thousands of rows. The Spotlight is the other thing: 15 agents so far, each one a pitch attached to a live agent, never a copy of it. Rename the agent or swap its avatar and the card updates with it.\n\nSearch reads the headline, the one-liner, the write-up and the agent's own description, so a plain word finds the agent built for it.",+ "The write-ups we wrote ourselves carry a Curated badge, so a visitor is never told a builder said something they did not write. The builder's own write-up replaces ours the moment they submit one.\n\nOne upvote per account per entry, and trending decays by the day, so a new entry is seen before it is buried under what was already popular.",+ "Open any one of them, talk to it, fork it, or put your own in front of everybody. Showcase your agent takes a public agent you own, a headline and a one-liner, and the entry is live on its own page with the agent in 3D."+ ],+ "lint": [],+ "verification": {+ "ok": true,+ "checks": [+ {+ "claim": "standing there in 3D",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"the agent standing in 3D, live from its own GLB\""+ },+ {+ "claim": "thousands of rows",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"which is thousands of rows\""+ },+ {+ "claim": "15 agents so far",+ "kind": "evidence:proof",+ "target": "showcased",+ "ok": true,+ "detail": "the run read showcased = \"15\""+ },+ {+ "claim": "a pitch attached to a live agent, never a copy of it",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"pitch attached to a live agent, never a copy of it\""+ },+ {+ "claim": "Rename the agent or swap its avatar and the card updates with it",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"Rename your agent, swap its avatar, register it on-chain: the card updates with it\""+ },+ {+ "claim": "Search reads the headline, the one-liner, the write-up and the agent's own description",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"Full-text over headline, one-liner, write-up, agent name and description\""+ },+ {+ "claim": "Search reads the headline, the one-liner, the write-up and the agent's own description",+ "kind": "evidence:proof",+ "target": "/api/spotlight/list",+ "ok": true,+ "detail": "GET /api/spotlight/list answered 200 in 3.9 s"+ },+ {+ "claim": "carry a Curated badge",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"Some entries carry a Curated badge\""+ },+ {+ "claim": "a visitor is never told a builder said something they did not write",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"so a visitor is never told a builder said something they did not write\""+ },+ {+ "claim": "The builder's own write-up replaces ours the moment they submit one",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"replaces the curated one and the badge goes away\""+ },+ {+ "claim": "The builder's own write-up replaces ours the moment they submit one",+ "kind": "evidence:page",+ "target": "https://three.ws/spotlight/8fecd65a-4ab9-484a-9714-691d4040e9e5",+ "ok": true,+ "detail": "live page shows \"Its builder can replace it with their own write-up at any time\""+ },+ {+ "claim": "One upvote per account per entry",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"One upvote per account per entry\""+ },+ {+ "claim": "trending decays by the day",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"The clock runs in days, not hours\""+ },+ {+ "claim": "a new entry is seen before it is buried",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"the newest submission is seen at all rather than buried\""+ },+ {+ "claim": "Open any one of them, talk to it, fork it, or put your own in front of everybody",+ "kind": "evidence:page",+ "target": "https://three.ws/spotlight",+ "ok": true,+ "detail": "live page shows \"Open any one of them, talk to it, fork it, or put your own in front of everybody\""+ },+ {+ "claim": "a public agent you own",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"Only your own public agents that are not already showcased appear\""+ },+ {+ "claim": "live on its own page with the agent in 3D",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/spotlight",+ "ok": true,+ "detail": "live page shows \"Every entry has its own page at\""+ },+ {+ "claim": "live on its own page with the agent in 3D",+ "kind": "evidence:proof",+ "target": "Machine translation solved meaning years ago",+ "ok": true,+ "detail": "the run waited for and saw \"Machine translation solved meaning years ago\""+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "18 steps passed against the live product, facts unchanged (showcased 15)"+ },+ {+ "kind": "probe:api",+ "target": "the spotlight list answers",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/spotlight",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": null,+ "editorError": "no model was reachable:\n Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog\n openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr\n openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi\n editor returned no JSON object"+}diff --git a/data/x-content/reviews/avatar-cli.json b/data/x-content/reviews/avatar-cli.jsonnew file mode 100644index 000000000..554d2374d--- /dev/null+++ b/data/x-content/reviews/avatar-cli.json@@ -0,0 +1,211 @@+{+ "id": "avatar-cli",+ "contentHash": "c1b7bf2bdc9d324c6d16e5e168eca0067a45ac8cfd39305ace852dec723fd8b5",+ "reviewedAt": "2026-09-30T08:50:44.785Z",+ "passed": false,+ "blockers": [+ "editor verdict is revise"+ ],+ "texts": [+ "An avatar manifest that carries the SHA-256 of the mesh it was built from, so a model re-exported or swapped under the same filename fails your build instead of your page.\n\nthree-ws-avatar reads the GLB once and writes its digest and size into the manifest, then validates the whole document against the published schema. Four commands, one runtime dependency, no network calls, so it runs offline inside a release script.\n\npreview prints the two lines of HTML that embed the avatar. The page pastes them in unmodified, and the viewer on it is that markup rendering.",+ "validate exits non-zero on an invalid manifest and prints each error at the path where it happened, so a bad file fails the build step instead of logging a warning. hash prints the digest alone on stdout, which makes the drift check a one-line comparison.\n\nInstall line, the four commands, and the manifest fields: three.ws/avatar-cli",+ "The owner is a chain-scoped account, so ownership is unambiguous off-platform. A Solana address is accepted as is."+ ],+ "lint": [],+ "verification": {+ "ok": true,+ "checks": [+ {+ "claim": "carries the SHA-256 of the mesh it was built from",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"Reads the mesh once to compute its SHA-256 and size, so the document cannot disagree with the bytes it was built from\""+ },+ {+ "claim": "swapped under the same filename fails your build instead of your page",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"the teammate who swapped the model and kept the filename\""+ },+ {+ "claim": "swapped under the same filename fails your build instead of your page",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"Fail the build, not the page\""+ },+ {+ "claim": "reads the GLB once and writes its digest and size into the manifest",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"Reads the mesh once to compute its SHA-256 and size\""+ },+ {+ "claim": "validates the whole document against the published schema",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"validate it against the published schema\""+ },+ {+ "claim": "Four commands",+ "kind": "evidence:proof",+ "target": "commands",+ "ok": true,+ "detail": "the run read commands = \"4\""+ },+ {+ "claim": "one runtime dependency",+ "kind": "evidence:proof",+ "target": "runtimeDeps",+ "ok": true,+ "detail": "the run read runtimeDeps = \"1\""+ },+ {+ "claim": "no network calls",+ "kind": "evidence:proof",+ "target": "networkCalls",+ "ok": true,+ "detail": "the run read networkCalls = \"0\""+ },+ {+ "claim": "runs offline inside a release script",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"Offline, deterministic, and safe to put in a release script\""+ },+ {+ "claim": "preview prints the two lines of HTML that embed the avatar",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"That is why preview always prints them together\""+ },+ {+ "claim": "The page pastes them in unmodified, and the viewer on it is that markup rendering",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"The markup below is exactly what preview prints, pasted into this page unmodified\""+ },+ {+ "claim": "The page pastes them in unmodified, and the viewer on it is that markup rendering",+ "kind": "evidence:proof",+ "target": "viewer",+ "ok": true,+ "detail": "the run read viewer = \"michelle.glb\""+ },+ {+ "claim": "validate exits non-zero on an invalid manifest and prints each error at the path where it happened",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"prints every error at the instance path where it happened. Non-zero exit makes it a build gate rather than a report\""+ },+ {+ "claim": "hash prints the digest alone on stdout, which makes the drift check a one-line comparison",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"alone on stdout so it composes\""+ },+ {+ "claim": "hash prints the digest alone on stdout, which makes the drift check a one-line comparison",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"makes drift detection a one-line comparison\""+ },+ {+ "claim": "the four commands",+ "kind": "evidence:proof",+ "target": "commands",+ "ok": true,+ "detail": "the run read commands = \"4\""+ },+ {+ "claim": "The owner is a chain-scoped account, so ownership is unambiguous off-platform",+ "kind": "evidence:page",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "live page shows \"Chain-scoped account, so ownership is unambiguous off-platform\""+ },+ {+ "claim": "A Solana address is accepted as is",+ "kind": "evidence:file",+ "target": "packages/avatar-schema/src/index.d.ts",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "16 steps passed against the live product, facts unchanged (commands 4, networkCalls 0, runtimeDeps 1, viewer michelle.glb)"+ },+ {+ "kind": "probe:api",+ "target": "the avatar CLI page is up",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/avatar-cli",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 4,+ "clarity": 4,+ "specificity": 5,+ "voice": 5,+ "professionalism": 5,+ "visual": 5+ },+ "issues": [+ {+ "severity": "major",+ "area": "accuracy",+ "quote": "three-ws-avatar reads the GLB once",+ "problem": "The tool is never named that anywhere in the evidence. The live page, the reel frame, and the install line all name the package @three-ws/avatar-cli. A developer typing 'three-ws-avatar' into npm finds nothing. The post asks readers to install the tool, so the name has to be the one they install.",+ "fix": "Replace with '@three-ws/avatar-cli reads the GLB once and writes its digest and size into the manifest, then validates the whole document against the published schema.'"+ },+ {+ "severity": "minor",+ "area": "clarity",+ "quote": "The owner is a chain-scoped account, so ownership is unambiguous off-platform.",+ "problem": "Post 3 never says whose owner it means. A reader who has not seen the page does not know whether the owner of the CLI, the site, or the manifest is meant. One word pins it.",+ "fix": "Change to 'The manifest's owner is a chain-scoped account, so ownership is unambiguous off-platform. A Solana address is accepted as is.'"+ }+ ],+ "rewrite": {+ "posts": [+ "An avatar manifest that carries the SHA-256 of the mesh it was built from, so a model re-exported or swapped under the same filename fails your build instead of your page.\n\n@three-ws/avatar-cli reads the GLB once and writes its digest and size into the manifest, then validates the whole document against the published schema. Four commands, one runtime dependency, no network calls, so it runs offline inside a release script.\n\npreview prints the two lines of HTML that embed the avatar. The page pastes them in unmodified, and the viewer on it is that markup rendering.",+ "validate exits non-zero on an invalid manifest and prints each error at the path where it happened, so a bad file fails the build step instead of logging a warning. hash prints the digest alone on stdout, which makes the drift check a one-line comparison.\n\nInstall line, the four commands, and the manifest fields: three.ws/avatar-cli",+ "The manifest's owner is a chain-scoped account, so ownership is unambiguous off-platform. A Solana address is accepted as is."+ ],+ "altText": []+ },+ "summary": "Every stated number and mechanism verified against the live page and the filmed run, and the reel frames support each caption. Two fixes: the tool is called by a name nobody can install, and post 3's owner claim never says what it is the owner of.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": [+ "claims: claim \"The owner is a chain-scoped account, so ownership is unambiguous off-platform\" does not appear in the copy; claims must quote the post",+ "claims: @three has no recorded reason; tag only an account the feature genuinely runs on"+ ]+ },+ "editorError": null+}diff --git a/data/x-content/reviews/choreograph.json b/data/x-content/reviews/choreograph.jsonnew file mode 100644index 000000000..3a694d59c--- /dev/null+++ b/data/x-content/reviews/choreograph.json@@ -0,0 +1,166 @@+{+ "id": "choreograph",+ "contentHash": "ec236c6b553481a0e9375a0880f687c23da9369a46eaaba2f23129057774098a",+ "reviewedAt": "2026-09-30T08:54:02.489Z",+ "passed": false,+ "blockers": [+ "editor verdict is revise"+ ],+ "texts": [+ "Load a routine and your agent performs it: sign, celebrate, dance. Add a beat while it plays and the stage follows.\n\nA routine is a performance built from gestures on a timeline. Each row is one beat: drag to reorder, set how long it holds, and point any step at a different clip. Save it to an agent you own and it travels with that agent, so any embed can play it by name.\n\nthree.ws/choreograph",+ "Five performances ship as starting points. A step names a slot rather than a file, so a routine shared with another agent still plays that agent's own take on each gesture. A routine holds up to 24 steps."+ ],+ "lint": [],+ "verification": {+ "ok": true,+ "checks": [+ {+ "claim": "Load a routine and your agent performs it: sign, celebrate, dance",+ "kind": "evidence:proof",+ "target": "sign ·",+ "ok": true,+ "detail": "the run waited for and saw \"sign ·\""+ },+ {+ "claim": "Load a routine and your agent performs it: sign, celebrate, dance",+ "kind": "evidence:file",+ "target": "src/runtime/choreography.js",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "Add a beat while it plays and the stage follows",+ "kind": "evidence:proof",+ "target": "wave ·",+ "ok": true,+ "detail": "the run waited for and saw \"wave ·\""+ },+ {+ "claim": "Add a beat while it plays and the stage follows",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"The stage follows every edit\""+ },+ {+ "claim": "A routine is a performance",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"A routine is a performance\""+ },+ {+ "claim": "Each row is one beat: drag to reorder, set how long it holds, and point any step at a different clip",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"Each row is one beat\""+ },+ {+ "claim": "Each row is one beat: drag to reorder, set how long it holds, and point any step at a different clip",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"Drag to reorder, set how long it holds, and point any step at a different clip\""+ },+ {+ "claim": "Save it to an agent you own and it travels with that agent, so any embed can play it by name",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"Save the routine to an agent you own and it travels with that agent\""+ },+ {+ "claim": "Save it to an agent you own and it travels with that agent, so any embed can play it by name",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"any embed can play it by name\""+ },+ {+ "claim": "Five performances ship as starting points",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"Five performances built from the shipped slot vocabulary\""+ },+ {+ "claim": "Five performances ship as starting points",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"they are starting points\""+ },+ {+ "claim": "A step names a slot rather than a file, so a routine shared with another agent still plays that agent's own take on each gesture",+ "kind": "evidence:page",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "live page shows \"A step names a slot, so a routine shared with another agent still plays that agent's own take on each gesture\""+ },+ {+ "claim": "A routine holds up to 24 steps",+ "kind": "evidence:file",+ "target": "src/runtime/choreography.js",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "10 steps passed against the live product"+ },+ {+ "kind": "probe:api",+ "target": "the choreographer page is up",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/choreograph",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 4,+ "clarity": 5,+ "specificity": 5,+ "voice": 5,+ "professionalism": 5,+ "visual": 5+ },+ "issues": [+ {+ "severity": "major",+ "area": "accuracy",+ "quote": "A step names a slot rather than a file",+ "problem": "The passing verification supports \"A step names a slot\" from the live page, but the words \"rather than a file\" appear in no passing check. The claim smuggles in an unverified contrast about file handling.",+ "fix": "Cut the unverified clause: \"A step names a slot, so a routine shared with another agent still plays that agent's own take on each gesture.\""+ }+ ],+ "rewrite": {+ "posts": [+ "Load a routine and your agent performs it: sign, celebrate, dance. Add a beat while it plays and the stage follows.\n\nA routine is a performance built from gestures on a timeline. Each row is one beat: drag to reorder, set how long it holds, and point any step at a different clip. Save it to an agent you own and it travels with that agent, so any embed can play it by name.\n\nthree.ws/choreograph",+ "Five performances ship as starting points. A step names a slot, so a routine shared with another agent still plays that agent's own take on each gesture. A routine holds up to 24 steps."+ ],+ "altText": []+ },+ "summary": "Every claim was verified against the live page and code, the reel frames match the captions and the copy, and the voice is clean. The only fix is dropping \"rather than a file\", an unverified addition to an otherwise supported slot claim in post 2.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": [+ "claims: claim \"A step names a slot rather than a file, so a routine shared with another agent still plays that agent's own take on each gesture\" does not appear in the copy; claims must quote the post"+ ]+ },+ "editorError": null+}diff --git a/data/x-content/reviews/docs-world.json b/data/x-content/reviews/docs-world.jsonnew file mode 100644index 000000000..751bbad54--- /dev/null+++ b/data/x-content/reviews/docs-world.json@@ -0,0 +1,201 @@+{+ "id": "docs-world",+ "contentHash": "c6329dfe58f5c87cc0403919adac6ec4c3793263ddf4eb9c937a9a5badd2aded",+ "reviewedAt": "2026-09-30T08:56:12.523Z",+ "passed": false,+ "blockers": [+ "probe:scenario the filmed scenario: pages is now \"307\", the reel shows \"306\"; prove it again",+ "editor (accuracy): The probe scenario failed: the live product now reads pages = 307, while the reel and the copy both say 306. The live product is the source of truth, so the filmed run is stale and the number in the copy is no longer supported by a passing check.",+ "editor verdict is revise"+ ],+ "texts": [+ "This is the documentation, rebuilt as a place. 306 pages, and you read them by walking up to them.\n\nEvery docs section is a pavilion on a ring, 15 in all. Search a page from wherever you stand and a trail of arrows leads to the pavilion that holds it. Enter reads it there and then: the real page opens inside the scene, as text you can select and zoom.\n\nthree.ws/docs/world",+ "Same files as the classic docs, so the two can never drift apart. Walk with the arrow keys or the touch joystick, and pass any rigged GLB with ?avatar= to make it your body in the world."+ ],+ "lint": [],+ "verification": {+ "ok": false,+ "checks": [+ {+ "claim": "306 pages",+ "kind": "evidence:proof",+ "target": "pages",+ "ok": true,+ "detail": "the run read pages = \"306\""+ },+ {+ "claim": "you read them by walking up to them",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"you walk an avatar between them and read the real pages inside the scene\""+ },+ {+ "claim": "Every docs section is a pavilion on a ring",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"Every section of the sidebar is a glowing pavilion on a ring\""+ },+ {+ "claim": "15 in all",+ "kind": "evidence:proof",+ "target": "pavilions",+ "ok": true,+ "detail": "the run read pavilions = \"15\""+ },+ {+ "claim": "Search a page from wherever you stand",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"opens a palette over every page\""+ },+ {+ "claim": "a trail of arrows leads to the pavilion that holds it",+ "kind": "evidence:file",+ "target": "src/docs-world/wayfinder.js",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "a trail of arrows leads to the pavilion that holds it",+ "kind": "evidence:proof",+ "target": "Read now",+ "ok": true,+ "detail": "the run waited for and saw \"Read now\""+ },+ {+ "claim": "Enter reads it there and then",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"Enter on a result opens the page at once\""+ },+ {+ "claim": "the real page opens inside the scene",+ "kind": "evidence:proof",+ "target": "/docs/forge",+ "ok": true,+ "detail": "GET /docs/forge.md answered 200 in 0.1 s"+ },+ {+ "claim": "the real page opens inside the scene",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"read the real pages inside the scene\""+ },+ {+ "claim": "as text you can select and zoom",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"text is selectable, zoomable\""+ },+ {+ "claim": "Same files as the classic docs, so the two can never drift apart",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"Both render the same files\""+ },+ {+ "claim": "Same files as the classic docs, so the two can never drift apart",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"the two surfaces can never drift apart\""+ },+ {+ "claim": "Walk with the arrow keys or the touch joystick",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"WASD or arrow keys\""+ },+ {+ "claim": "Walk with the arrow keys or the touch joystick",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"Virtual joystick\""+ },+ {+ "claim": "pass any rigged GLB with ?avatar= to make it your body in the world",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/docs-world",+ "ok": true,+ "detail": "live page shows \"Pass any rigged GLB with ?avatar=\""+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": false,+ "detail": "pages is now \"307\", the reel shows \"306\"; prove it again"+ },+ {+ "kind": "probe:api",+ "target": "the docs index still holds the 15 sections the post counts",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/docs/world",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 3,+ "clarity": 5,+ "specificity": 4,+ "voice": 5,+ "professionalism": 5,+ "visual": 4+ },+ "issues": [+ {+ "severity": "blocking",+ "area": "accuracy",+ "quote": "306 pages, and you read them by walking up to them",+ "problem": "The probe scenario failed: the live product now reads pages = 307, while the reel and the copy both say 306. The live product is the source of truth, so the filmed run is stale and the number in the copy is no longer supported by a passing check.",+ "fix": "Rerun npm run x:content prove for this scenario to recapture the reel against current production so pages reads the live count, and update the copy to the number the new run reads off the screen. Until then, drop the page count from the copy."+ },+ {+ "severity": "minor",+ "area": "specificity",+ "quote": "Search a page from wherever you stand",+ "problem": "The reel caption and the on-screen UI both show Shift+Enter lays the trail, which is a concrete detail the copy omits in favor of a vaguer phrasing. This is polish, not a discrepancy.",+ "fix": "Optionally tighten to: press Shift+Enter on a result and a trail of chevrons leads to the pavilion that holds it."+ }+ ],+ "rewrite": {+ "posts": [+ "This is the documentation, rebuilt as a place: every docs section is a pavilion on a ring, 15 in all, and you read the pages by walking an avatar up to them.\n\nSearch a page from wherever you stand and a trail of arrows leads to the pavilion that holds it. Enter opens the real page at once inside the scene, as text you can select and zoom.\n\nthree.ws/docs/world",+ "Same files as the classic docs, so the two can never drift apart. Walk with the arrow keys or the touch joystick, and pass any rigged GLB with ?avatar= to make it your body in the world."+ ],+ "altText": [+ "A 3D scene of the three.ws Docs World: glowing pavilions arranged on a ring, an avatar walking between them, a search palette listing every docs page, a chevron trail on the ground leading to a pavilion, and the real Forge docs page opening as selectable, zoomable text inside the scene."+ ]+ },+ "summary": "The post is well written and in voice, but the scenario probe failed: production now shows 307 pages while the copy and reel say 306, so the number and the footage must not ship as is. Recapture the reel against current production and update the copy to the live count; the rewrite drops the count as a fallback so the post is accurate either way.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": [+ "claims: claim \"306 pages\" does not appear in the copy; claims must quote the post",+ "claims: claim \"you read them by walking up to them\" does not appear in the copy; claims must quote the post",+ "claims: claim \"Enter reads it there and then\" does not appear in the copy; claims must quote the post",+ "claims: claim \"the real page opens inside the scene\" does not appear in the copy; claims must quote the post"+ ]+ },+ "editorError": null+}diff --git a/data/x-content/reviews/drive-copilot.json b/data/x-content/reviews/drive-copilot.jsonnew file mode 100644index 000000000..47eed4a99--- /dev/null+++ b/data/x-content/reviews/drive-copilot.json@@ -0,0 +1,201 @@+{+ "id": "drive-copilot",+ "contentHash": "fd85956638bce5179cab098917a7e799ca4e3eec39b8ea479529dd5e4d8002eb",+ "reviewedAt": "2026-09-30T08:59:43.116Z",+ "passed": false,+ "blockers": [+ "probe:scenario the filmed scenario: step 11 (expect Speaking): locator.waitFor: Timeout 60000ms exceeded."+ ],+ "texts": [+ "Put your phone in the cradle, open Drive, and your agent rides along.\n\nThe page starts in Driving: a face, a voice, four controls, and no keyboard. Hold Talk and speak. The reply comes back in one or two short sentences, spoken in full and clamped to two lines on screen. Park, and Type unlocks. Night is the default, because a bright panel at speed is glare.",+ "It is the same talk loop the site already runs (mic, transcript, reply, voice, lip sync on a rigged avatar), sized for a car panel. Runs on a head unit browser or a phone in a cradle: three.ws/drive",+ "\"Repeat that\", \"stop talking\", \"louder\" and \"night mode\" are answered by the page itself, with no round trip to a server."+ ],+ "lint": [],+ "verification": {+ "ok": false,+ "checks": [+ {+ "claim": "Put your phone in the cradle",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"on a phone in a cradle\""+ },+ {+ "claim": "The page starts in Driving",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"The page starts in Driving and hides text entry\""+ },+ {+ "claim": "The page starts in Driving",+ "kind": "evidence:proof",+ "target": "Ready",+ "ok": true,+ "detail": "the run waited for and saw \"Ready\""+ },+ {+ "claim": "four controls, and no keyboard",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"Four controls, no more. Hands free, Repeat, Stop, Type.\""+ },+ {+ "claim": "four controls, and no keyboard",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"hides text entry\""+ },+ {+ "claim": "Hold Talk and speak",+ "kind": "evidence:file",+ "target": "pages/drive.html",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "The reply comes back in one or two short sentences",+ "kind": "evidence:file",+ "target": "src/drive/index.js",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "The reply comes back in one or two short sentences",+ "kind": "evidence:proof",+ "target": "/api/chat",+ "ok": true,+ "detail": "POST /api/chat answered 200 in 6.8 s"+ },+ {+ "claim": "spoken in full and clamped to two lines on screen",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"The reply is clamped to two lines and spoken in full\""+ },+ {+ "claim": "spoken in full and clamped to two lines on screen",+ "kind": "evidence:proof",+ "target": "Speaking",+ "ok": true,+ "detail": "the run waited for and saw \"Speaking\""+ },+ {+ "claim": "Park, and Type unlocks",+ "kind": "evidence:file",+ "target": "src/drive/index.js",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "Park, and Type unlocks",+ "kind": "evidence:proof",+ "target": "Parked",+ "ok": true,+ "detail": "the run waited for and saw \"Parked\""+ },+ {+ "claim": "Night is the default, because a bright panel at speed is glare",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"Night is the default because a bright panel at speed is glare\""+ },+ {+ "claim": "It is the same talk loop the site already runs (mic, transcript, reply, voice, lip sync on a rigged avatar)",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"The loop is the platform's existing one, unchanged\""+ },+ {+ "claim": "It is the same talk loop the site already runs (mic, transcript, reply, voice, lip sync on a rigged avatar)",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"audio into the lipsync driver and onto a real rigged avatar\""+ },+ {+ "claim": "Runs on a head unit browser or a phone in a cradle",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"on a head unit browser, on a phone in a cradle\""+ },+ {+ "claim": "are answered by the page itself, with no round trip to a server",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"Local commands with no round trip\""+ },+ {+ "claim": "are answered by the page itself, with no round trip to a server",+ "kind": "evidence:page",+ "target": "https://three.ws/docs/carplay",+ "ok": true,+ "detail": "live page shows \"are answered by the page itself\""+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": false,+ "detail": "step 11 (expect Speaking): locator.waitFor: Timeout 60000ms exceeded."+ },+ {+ "kind": "probe:api",+ "target": "the Drive page is up",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/drive",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "publish",+ "scores": {+ "accuracy": 5,+ "clarity": 5,+ "specificity": 5,+ "voice": 5,+ "professionalism": 5,+ "visual": 4+ },+ "issues": [+ {+ "severity": "minor",+ "area": "visual",+ "quote": "expect Speaking: locator.waitFor: Timeout 60000ms exceeded",+ "problem": "One scenario probe timed out waiting for the Speaking state, although a separate proof in the same verification saw 'Speaking', the API answered 200, and the reel frame at 8.7 s visibly shows 'Michelle Speaking' with the reply on screen. The filmed evidence supports the claim, but the failing probe should not recur silently.",+ "fix": "No copy change. Re-run npm run x:content -- prove for this scenario and confirm the Speaking step passes before the next Drive post; the current reel already shows the state it claims."+ }+ ],+ "rewrite": {+ "posts": [+ "Put your phone in the cradle, open Drive, and your agent rides along.\n\nThe page starts in Driving: a face, a voice, four controls, and no keyboard. Hold Talk and speak. The reply comes back in one or two short sentences, spoken in full and clamped to two lines on screen. Park, and Type unlocks. Night is the default, because a bright panel at speed is glare.",+ "It is the same talk loop the site already runs (mic, transcript, reply, voice, lip sync on a rigged avatar), sized for a car panel. Runs on a head unit browser or a phone in a cradle: three.ws/drive",+ "\"Repeat that\", \"stop talking\", \"louder\" and \"night mode\" are answered by the page itself, with no round trip to a server."+ ],+ "altText": []+ },+ "summary": "Every claim in the copy is verified word for word against the live docs page or the code, and the reel frames corroborate each step (Driving lock, Parked typing, Speaking with a two-line reply). The only blemish is one timed-out probe for the Speaking state, contradicted by a passing proof, a 200 API answer, and the film itself, so it is noted as minor rather than blocking.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": []+ },+ "editorError": null+}diff --git a/data/x-content/reviews/gestures.json b/data/x-content/reviews/gestures.jsonnew file mode 100644index 000000000..610c5d07d--- /dev/null+++ b/data/x-content/reviews/gestures.json@@ -0,0 +1,159 @@+{+ "id": "gestures",+ "contentHash": "7dfd76e0a23d4e49a38a730523b5ecb0fc749a20ec4577448b76afeeb993ffd1",+ "reviewedAt": "2026-09-30T09:02:27.520Z",+ "passed": false,+ "blockers": [+ "editor verdict is revise"+ ],+ "texts": [+ "An agent waves, celebrates, then dances, and it did not pick an animation file for any of them.\n\nAn agent does not pick animation files. It names a slot, and the platform resolves that slot to a real clip. There are 19 slots, fixed names an agent can override: point a slot at any other clip in the library and the agent changes its move.\n\nA skill declares a hint when it starts. The hint resolves to a slot, the slot resolves to a clip, and the avatar plays it.",+ "Choose any slot to play it on a live avatar. Every row of what triggers a gesture is generated from the shipped skill definitions, and each clip is measured from its own keyframes: how energetic it is and how much of that energy is above the waist.\n\nthree.ws/gestures"+ ],+ "lint": [],+ "verification": {+ "ok": true,+ "checks": [+ {+ "claim": "An agent waves, celebrates, then dances",+ "kind": "evidence:proof",+ "target": "Wave · wave",+ "ok": true,+ "detail": "the run waited for and saw \"Wave · wave\""+ },+ {+ "claim": "An agent waves, celebrates, then dances",+ "kind": "evidence:proof",+ "target": "Celebrate · celebrate",+ "ok": true,+ "detail": "the run waited for and saw \"Celebrate · celebrate\""+ },+ {+ "claim": "An agent waves, celebrates, then dances",+ "kind": "evidence:proof",+ "target": "Rumba · rumba",+ "ok": true,+ "detail": "the run waited for and saw \"Rumba · rumba\""+ },+ {+ "claim": "An agent does not pick animation files. It names a slot, and the platform resolves that slot to a real clip.",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"An agent does not pick animation files. It names a slot, and the platform resolves that slot to a real clip.\""+ },+ {+ "claim": "There are 19 slots",+ "kind": "evidence:proof",+ "target": "slots",+ "ok": true,+ "detail": "the run read slots = \"19\""+ },+ {+ "claim": "fixed names an agent can override",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"Fixed names an agent can override\""+ },+ {+ "claim": "point a slot at any other clip in the library",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"how to point a slot at any other clip in the library\""+ },+ {+ "claim": "A skill declares a hint when it starts. The hint resolves to a slot, the slot resolves to a clip, and the avatar plays it.",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"A skill declares a hint when it starts. The hint resolves to a slot, the slot resolves to a clip, and the avatar plays it.\""+ },+ {+ "claim": "Choose any slot to play it on a live avatar",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"Choose any slot to play it on a live avatar\""+ },+ {+ "claim": "Every row of what triggers a gesture is generated from the shipped skill definitions",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"Every row below is generated from the shipped skill definitions\""+ },+ {+ "claim": "Every row of what triggers a gesture is generated from the shipped skill definitions",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"What triggers a gesture\""+ },+ {+ "claim": "each clip is measured from its own keyframes: how energetic it is and how much of that energy is above the waist",+ "kind": "evidence:page",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "live page shows \"measured from its own keyframes and plotted by how energetic it is and how much of that energy is above the waist\""+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "14 steps passed against the live product, facts unchanged (slots 19)"+ },+ {+ "kind": "probe:api",+ "target": "the gestures page is up",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/gestures",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 5,+ "clarity": 4,+ "specificity": 4,+ "voice": 4,+ "professionalism": 5,+ "visual": 5+ },+ "issues": [+ {+ "severity": "minor",+ "area": "clarity",+ "quote": "and it did not pick an animation file for any of them.\n\nAn agent does not pick animation files.",+ "problem": "The same point is stated twice in back-to-back paragraphs, and the head repeats 'An agent' to open both sentences. The reel shows the wave, celebrate, and dance clips being resolved, so the copy only needs to say it once, then spend the saved characters on the mechanism.",+ "fix": "Drop the second occurrence of 'An agent does not pick animation files.' and continue directly with 'It names a slot, and the platform resolves that slot to a real clip.'"+ }+ ],+ "rewrite": {+ "posts": [+ "An agent waves, celebrates, then dances, and it did not pick an animation file for any of them.\n\nIt names a slot, and the platform resolves that slot to a real clip. There are 19 slots, fixed names an agent can override: point a slot at any other clip in the library and the agent changes its move.\n\nA skill declares a hint when it starts. The hint resolves to a slot, the slot resolves to a clip, and the avatar plays it.",+ "Choose any slot to play it on a live avatar. Every row of what triggers a gesture is generated from the shipped skill definitions, and each clip is measured from its own keyframes: how energetic it is and how much of that energy is above the waist.\n\nthree.ws/gestures"+ ],+ "altText": []+ },+ "summary": "Every claim is verified against the live gestures page and the filmed run, including the 19-slot count, and the reel frames and captions genuinely show slot selection and clip resolution on a live avatar. The only fix needed is removing the duplicated 'does not pick animation files' sentence in the head post, then it ships.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": [+ "claims: claim \"An agent does not pick animation files. It names a slot, and the platform resolves that slot to a real clip.\" does not appear in the copy; claims must quote the post"+ ]+ },+ "editorError": null+}diff --git a/data/x-content/reviews/glance.json b/data/x-content/reviews/glance.jsonnew file mode 100644index 000000000..315105a4d--- /dev/null+++ b/data/x-content/reviews/glance.json@@ -0,0 +1,280 @@+{+ "id": "glance",+ "contentHash": "5edcc20180079aa136fda85f5d3e4fb37ab6edf1d18bef77c826fa305fee0e5b",+ "reviewedAt": "2026-09-30T09:09:00.461Z",+ "passed": false,+ "blockers": [+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "evidence:page https://three.ws/glance: page answered HTTP 0",+ "editor (accuracy): The only evidence for this is a page check that failed (page answered HTTP 0), and no frame of the reel shows this behavior. A claim whose verification failed cannot ship.",+ "editor (accuracy): All three supporting page checks failed (HTTP 0), and no frame of the reel shows an Edge install flow, a widgets board, or a refresh interval. The 15-minute figure is unverified.",+ "editor verdict is revise"+ ],+ "texts": [+ "Paste an agent id on three.ws/glance and the page hands back that agent's status card four ways: a live element for any page, an image URL for a README or a Slack message, a command for your terminal, and the raw API call.\n\nAll four read one endpoint, so the number on the card is what the agent did today. Pick light, dark, or the reader's system setting, and the Windows 11 widgets board runs the same card.",+ "The live element is one module script and one tag, and it polls only while it is on screen and the tab is visible.\n\nThe image is one URL, with the size and theme in the query string.\n\nOn Windows 11, install the site from Edge, open the widgets board, and pick Agent glance; it refreshes itself every 15 minutes."+ ],+ "lint": [],+ "verification": {+ "ok": false,+ "checks": [+ {+ "claim": "four ways",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "four ways",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "four ways",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "four ways",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "a live element for any page",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "a live element for any page",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "an image URL for a README or a Slack message",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "a command for your terminal, and the raw API call",+ "kind": "evidence:proof",+ "target": "cli",+ "ok": true,+ "detail": "the run read cli = \"npx @three-ws/agent-glance\""+ },+ {+ "claim": "a command for your terminal, and the raw API call",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "All four read one endpoint",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "the number on the card is what the agent did today",+ "kind": "evidence:proof",+ "target": "metric",+ "ok": true,+ "detail": "the run read metric = \"moves today\""+ },+ {+ "claim": "Pick light, dark, or the reader's system setting",+ "kind": "evidence:proof",+ "target": "theme",+ "ok": true,+ "detail": "the run read theme = \"dark\""+ },+ {+ "claim": "Pick light, dark, or the reader's system setting",+ "kind": "evidence:file",+ "target": "public/glance/index.html",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "Pick light, dark, or the reader's system setting",+ "kind": "evidence:file",+ "target": "docs/glance.md",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "the Windows 11 widgets board runs the same card",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "one module script and one tag",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "polls only while it is on screen and the tab is visible",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "The image is one URL",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "with the size and theme in the query string",+ "kind": "evidence:proof",+ "target": "/api/glance/card",+ "ok": true,+ "detail": "GET /api/glance/card answered 200 in 36.7 s"+ },+ {+ "claim": "with the size and theme in the query string",+ "kind": "evidence:file",+ "target": "public/glance/glance-page.js",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "install the site from Edge, open the widgets board, and pick Agent glance",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "install the site from Edge, open the widgets board, and pick Agent glance",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "install the site from Edge, open the widgets board, and pick Agent glance",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "claim": "it refreshes itself every 15 minutes",+ "kind": "evidence:page",+ "target": "https://three.ws/glance",+ "ok": false,+ "detail": "page answered HTTP 0"+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "19 steps passed against the live product, facts unchanged (name Whatchget, metric moves today, theme dark, cli npx @three-ws/agent-glance)"+ },+ {+ "kind": "probe:api",+ "target": "the glance card endpoint answers for the agent in the reel",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/glance",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 2,+ "clarity": 4,+ "specificity": 4,+ "voice": 5,+ "professionalism": 5,+ "visual": 5+ },+ "issues": [+ {+ "severity": "blocking",+ "area": "accuracy",+ "quote": "it polls only while it is on screen and the tab is visible",+ "problem": "The only evidence for this is a page check that failed (page answered HTTP 0), and no frame of the reel shows this behavior. A claim whose verification failed cannot ship.",+ "fix": "Cut the sentence, or re-run a check that passes on the live page before including it."+ },+ {+ "severity": "blocking",+ "area": "accuracy",+ "quote": "On Windows 11, install the site from Edge, open the widgets board, and pick Agent glance; it refreshes itself every 15 minutes.",+ "problem": "All three supporting page checks failed (HTTP 0), and no frame of the reel shows an Edge install flow, a widgets board, or a refresh interval. The 15-minute figure is unverified.",+ "fix": "Cut it from post 2. Post 1's 'the Windows 11 widgets board runs the same card' can stay because the filmed live page states 'The same card renders on the Windows 11 widgets board' in the passing run."+ },+ {+ "severity": "minor",+ "area": "specificity",+ "quote": "a command for your terminal, and the raw API call",+ "problem": "The run verified the exact command (npx @three-ws/agent-glance) and the live endpoint (GET /api/glance/card answered 200), and frame 4 shows both, so the post can name them instead of gesturing at them.",+ "fix": "Name the command and the endpoint in post 2."+ }+ ],+ "rewrite": {+ "posts": [+ "Paste an agent id on three.ws/glance and the page hands back that agent's status card four ways: a live element for any page, an image URL for a README or a Slack message, a command for your terminal, and the raw API call.\n\nAll four read one endpoint, so the number on the card is what the agent did today. Pick light, dark, or the reader's system setting, and the Windows 11 widgets board runs the same card.",+ "The live element is one module script and one tag. The image is one URL, with the size and theme in the query string. The terminal command is npx @three-ws/agent-glance, and the API call is a GET to three.ws/api/glance/card, which answered 200 during the filming of this reel."+ ],+ "altText": []+ },+ "summary": "The reels and the passing run back the core of the post: four surfaces, one endpoint, themes, and the Windows 11 card all appear on the filmed live page. Post 2's polling behavior, Edge install steps, and 15-minute refresh rest entirely on page checks that failed, so they are cut and the verified command and endpoint are named instead.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": [+ "claims: claim \"polls only while it is on screen and the tab is visible\" does not appear in the copy; claims must quote the post",+ "claims: claim \"install the site from Edge, open the widgets board, and pick Agent glance\" does not appear in the copy; claims must quote the post",+ "claims: claim \"it refreshes itself every 15 minutes\" does not appear in the copy; claims must quote the post",+ "claims: \"200\" is an unverified number; declare it in claims with evidence",+ "claims: @three has no recorded reason; tag only an account the feature genuinely runs on"+ ]+ },+ "editorError": null+}diff --git a/data/x-content/reviews/glb-diff.json b/data/x-content/reviews/glb-diff.jsonnew file mode 100644index 000000000..f34aa9d84--- /dev/null+++ b/data/x-content/reviews/glb-diff.json@@ -0,0 +1,239 @@+{+ "id": "glb-diff",+ "contentHash": "89077a17ec4e9d34016fb54aa7ed5a86e9d8b1e8c0394ea8a7c0fcd8146c348a",+ "reviewedAt": "2026-09-30T09:12:38.068Z",+ "passed": false,+ "blockers": [+ "editor verdict is revise"+ ],+ "texts": [+ "A checksum tells you two GLB files differ. It cannot tell a lossless re-export from a rig that quietly lost joints, and only one of those takes your avatar off the screen.\n\nModel Diff reads both files and reports the change set: geometry, materials, textures, skeletons and animation clips, with renames and moves detected the way git detects them. Both files are parsed and compared in your browser. Nothing is uploaded.\n\nIn the reel, two different characters: the verdict is breaking, with 2 joints lost, 5 animations removed and 4 objects renamed rather than rewritten. three.ws/diff",+ "Severity is one of none, cosmetic, minor, major, breaking, so a build can gate on it. Breaking means something a consumer references by name is gone: a clip, a joint, a mesh. That is the failure that renders fine and never moves.\n\nVertex data is compared at a quantum of 1e-4 units, so the float drift of a re-export does not register while a genuine edit does.",+ "The same engine runs this page, the CLI and the free API, so a verdict in CI cannot disagree with what you see here. The package is three-ws/glb-diff on npm: hand the CLI two files and a --fail-on level, and the build fails on the severity you choose."+ ],+ "lint": [],+ "verification": {+ "ok": true,+ "checks": [+ {+ "claim": "A checksum tells you two GLB files differ",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"A checksum says two files differ\""+ },+ {+ "claim": "It cannot tell a lossless re-export from a rig that quietly lost joints",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"It cannot tell a lossless recompression from a rig that quietly lost three finger joints\""+ },+ {+ "claim": "only one of those takes your avatar off the screen",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"only one of those takes your avatar off the screen\""+ },+ {+ "claim": "reports the change set: geometry, materials, textures, skeletons and animation clips",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"get the change set: geometry, materials, textures, skeletons, and clips\""+ },+ {+ "claim": "with renames and moves detected the way git detects them",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"with renames and moves detected the way git detects them\""+ },+ {+ "claim": "Both files are parsed and compared in your browser",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"The comparison runs on your machine\""+ },+ {+ "claim": "Both files are parsed and compared in your browser",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"RUNS IN YOUR BROWSER\""+ },+ {+ "claim": "Nothing is uploaded",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"Nothing is uploaded\""+ },+ {+ "claim": "two different characters",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"Two different characters\""+ },+ {+ "claim": "the verdict is breaking",+ "kind": "evidence:proof",+ "target": "severity",+ "ok": true,+ "detail": "the run read severity = \"BREAKING\""+ },+ {+ "claim": "2 joints lost",+ "kind": "evidence:proof",+ "target": "jointsLost",+ "ok": true,+ "detail": "the run read jointsLost = \"2\""+ },+ {+ "claim": "5 animations removed",+ "kind": "evidence:proof",+ "target": "clipsRemoved",+ "ok": true,+ "detail": "the run read clipsRemoved = \"5\""+ },+ {+ "claim": "4 objects renamed rather than rewritten",+ "kind": "evidence:proof",+ "target": "renamed",+ "ok": true,+ "detail": "the run read renamed = \"4\""+ },+ {+ "claim": "4 objects renamed rather than rewritten",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"reads as a rename, not as a rewrite\""+ },+ {+ "claim": "Severity is one of none, cosmetic, minor, major, breaking, so a build can gate on it",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"Severity you can gate on\""+ },+ {+ "claim": "Severity is one of none, cosmetic, minor, major, breaking, so a build can gate on it",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"none, cosmetic, minor, major, breaking\""+ },+ {+ "claim": "Breaking means something a consumer references by name is gone: a clip, a joint, a mesh",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"Breaking means something a consumer references by name is gone: a clip, a joint, a mesh\""+ },+ {+ "claim": "That is the failure that renders fine and never moves",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"That is the failure that renders fine and never moves\""+ },+ {+ "claim": "Vertex data is compared at a quantum of 1e-4 units, so the float drift of a re-export does not register while a genuine edit does",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"Vertex data is compared at a quantum of 1e-4 units, so the float drift a re-export or a Draco round trip introduces does not register while a genuine edit does\""+ },+ {+ "claim": "The same engine runs this page, the CLI and the free API, so a verdict in CI cannot disagree with what you see here",+ "kind": "evidence:page",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "live page shows \"This page, the glb-diff CLI, and the free API all run @three-ws/glb-diff, so a verdict in CI can never disagree with what you see here\""+ },+ {+ "claim": "hand the CLI two files and a --fail-on level, and the build fails on the severity you choose",+ "kind": "evidence:file",+ "target": "packages/glb-diff/README.md",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "hand the CLI two files and a --fail-on level, and the build fails on the severity you choose",+ "kind": "evidence:file",+ "target": "packages/glb-diff/README.md",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "17 steps passed against the live product, facts unchanged (severity BREAKING, jointsLost 2, clipsRemoved 5, renamed 4)"+ },+ {+ "kind": "probe:api",+ "target": "the diff page is up",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/diff",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "revise",+ "scores": {+ "accuracy": 4,+ "clarity": 4,+ "specificity": 5,+ "voice": 5,+ "professionalism": 5,+ "visual": 5+ },+ "issues": [+ {+ "severity": "major",+ "area": "accuracy",+ "quote": "The package is three-ws/glb-diff on npm",+ "problem": "No verification result confirms the package is published on npm, and the only verified name is the scoped @three-ws/glb-diff from the live page. The unscoped 'three-ws/glb-diff on npm' would misdirect a developer searching npm.",+ "fix": "Replace with: \"The engine is @three-ws/glb-diff: hand the CLI two files and a --fail-on level, and the build fails on the severity you choose.\""+ },+ {+ "severity": "minor",+ "area": "clarity",+ "quote": "Model Diff reads both files",+ "problem": "The verified product name and page text never say 'Model Diff'; the page calls the surface three.ws/diff and the engine @three-ws/glb-diff. An invented display name risks contradiction with the live page.",+ "fix": "Change to \"The diff reads both files and reports the change set: geometry, materials, textures, skeletons, and clips,\" matching the live page wording."+ }+ ],+ "rewrite": {+ "posts": [+ "A checksum tells you two GLB files differ. It cannot tell a lossless re-export from a rig that quietly lost joints, and only one of those takes your avatar off the screen.\n\nThe diff reads both files and reports the change set: geometry, materials, textures, skeletons, and clips, with renames and moves detected the way git detects them. Both files are parsed and compared in your browser. Nothing is uploaded.\n\nIn the reel, two different characters: the verdict is breaking, with 2 joints lost, 5 animations removed and 4 objects renamed rather than rewritten. three.ws/diff",+ "Severity is one of none, cosmetic, minor, major, breaking, so a build can gate on it. Breaking means something a consumer references by name is gone: a clip, a joint, a mesh. That is the failure that renders fine and never moves.\n\nVertex data is compared at a quantum of 1e-4 units, so the float drift of a re-export does not register while a genuine edit does.",+ "The same engine runs this page, the CLI and the free API, so a verdict in CI cannot disagree with what you see here. The engine is @three-ws/glb-diff: hand the CLI two files and a --fail-on level, and the build fails on the severity you choose."+ ],+ "altText": []+ },+ "summary": "Strong, fully verified correction-lead post; the reel frames and captions match the numbers the run read. Two naming fixes needed: the npm publication and the unscoped package name are unverified, and 'Model Diff' is not the name the live page uses.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": [+ "claims: claim \"reports the change set: geometry, materials, textures, skeletons and animation clips\" does not appear in the copy; claims must quote the post",+ "claims: @three has no recorded reason; tag only an account the feature genuinely runs on"+ ]+ },+ "editorError": null+}diff --git a/data/x-content/reviews/machine-atlas.json b/data/x-content/reviews/machine-atlas.jsonnew file mode 100644index 000000000..4cd5ad514--- /dev/null+++ b/data/x-content/reviews/machine-atlas.json@@ -0,0 +1,245 @@+{+ "id": "machine-atlas",+ "contentHash": "15c9a3ec33835ad11b3d544b5b2cac961c73ee94fbb3032dc149084411f06f32",+ "reviewedAt": "2026-09-30T09:16:58.920Z",+ "passed": true,+ "blockers": [],+ "texts": [+ "A nine-cylinder radial engine and a steam locomotive, with no model file behind either one. It is a Labs experiment in building 3D geometry from code instead of files.\n\nBoth machines are built when the page loads: dimensions become profiles, profiles get revolved or extruded, and the results are merged into the parts you can see. Move a slider and the geometry is rebuilt. Nine cylinders to five, and the displacement readout, the parts list and the source panel follow, because all of them are derived from the same numbers.",+ "The motion is solved, not baked animation. Pistons come from the exact planar slider-crank, and the locomotive valve gear closes a four-bar chain by intersecting circles every frame, which is why a rod length that cannot physically reach refuses to move rather than stretching.\n\nEach machine is a small JSON object of numbers. Copy the spec, hand it to an agent, get a different machine back, then export the result as GLB. three.ws/assembly"+ ],+ "lint": [],+ "verification": {+ "ok": true,+ "checks": [+ {+ "claim": "A nine-cylinder radial engine",+ "kind": "evidence:proof",+ "target": "cylinders",+ "ok": true,+ "detail": "the run read cylinders = \"9\""+ },+ {+ "claim": "A nine-cylinder radial engine",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Air-cooled radial aero engine\""+ },+ {+ "claim": "a steam locomotive",+ "kind": "evidence:proof",+ "target": "Outside-cylinder steam locomotive",+ "ok": true,+ "detail": "the run waited for and saw \"Outside-cylinder steam locomotive\""+ },+ {+ "claim": "a steam locomotive",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Coupled Six\""+ },+ {+ "claim": "no model file behind either one",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"no model files\""+ },+ {+ "claim": "no model file behind either one",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Two machines. Nothing downloaded.\""+ },+ {+ "claim": "a Labs experiment in building 3D geometry from code instead of files",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"The rest of the experiments running live on three.ws\""+ },+ {+ "claim": "a Labs experiment in building 3D geometry from code instead of files",+ "kind": "evidence:file",+ "target": "data/pages.json",+ "ok": true,+ "detail": "file supports the claim"+ },+ {+ "claim": "Both machines are built when the page loads",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Both machines are built when the page loads\""+ },+ {+ "claim": "dimensions become profiles, profiles get revolved or extruded, and the results are merged into the parts you can see",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Dimensions become profiles, profiles get revolved or extruded, and the results are merged into the parts you can see\""+ },+ {+ "claim": "Move a slider and the geometry is rebuilt",+ "kind": "evidence:proof",+ "target": "cylindersAfter",+ "ok": true,+ "detail": "the run read cylindersAfter = \"5\""+ },+ {+ "claim": "Move a slider and the geometry is rebuilt",+ "kind": "evidence:proof",+ "target": "16.5 L",+ "ok": true,+ "detail": "the run waited for and saw \"16.5 L\""+ },+ {+ "claim": "Nine cylinders to five",+ "kind": "evidence:proof",+ "target": "cylinders",+ "ok": true,+ "detail": "the run read cylinders = \"9\""+ },+ {+ "claim": "Nine cylinders to five",+ "kind": "evidence:proof",+ "target": "cylindersAfter",+ "ok": true,+ "detail": "the run read cylindersAfter = \"5\""+ },+ {+ "claim": "the displacement readout, the parts list and the source panel follow, because all of them are derived from the same numbers",+ "kind": "evidence:proof",+ "target": "displacement",+ "ok": true,+ "detail": "the run read displacement = \"29.7 L\""+ },+ {+ "claim": "the displacement readout, the parts list and the source panel follow, because all of them are derived from the same numbers",+ "kind": "evidence:proof",+ "target": "16.5 L",+ "ok": true,+ "detail": "the run waited for and saw \"16.5 L\""+ },+ {+ "claim": "the displacement readout, the parts list and the source panel follow, because all of them are derived from the same numbers",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Generated from the values on the right, so it always matches what is on screen\""+ },+ {+ "claim": "The motion is solved, not baked animation",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"The motion is solved, not keyframed\""+ },+ {+ "claim": "The motion is solved, not baked animation",+ "kind": "evidence:proof",+ "target": "Solved four-bar chain, not baked animation",+ "ok": true,+ "detail": "the run waited for and saw \"Solved four-bar chain, not baked animation\""+ },+ {+ "claim": "Pistons come from the exact planar slider-crank",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Pistons come from the exact planar slider-crank\""+ },+ {+ "claim": "the locomotive valve gear closes a four-bar chain by intersecting circles every frame",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"The valve gear closes a four-bar chain by intersecting circles every frame\""+ },+ {+ "claim": "the locomotive valve gear closes a four-bar chain by intersecting circles every frame",+ "kind": "evidence:proof",+ "target": "Solved four-bar chain, not baked animation",+ "ok": true,+ "detail": "the run waited for and saw \"Solved four-bar chain, not baked animation\""+ },+ {+ "claim": "a rod length that cannot physically reach refuses to move rather than stretching",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"a rod length that cannot physically reach refuses to move rather than stretching\""+ },+ {+ "claim": "Each machine is a small JSON object of numbers",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Every machine is a small JSON object of numbers\""+ },+ {+ "claim": "Copy the spec, hand it to an agent, get a different machine back",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Copy the spec, hand it to an agent, get a different machine back\""+ },+ {+ "claim": "export the result as GLB",+ "kind": "evidence:page",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "live page shows \"Export the result as GLB\""+ },+ {+ "kind": "probe:scenario",+ "target": "the filmed scenario",+ "ok": true,+ "detail": "17 steps passed against the live product, facts unchanged (machines TWO, cylinders 9, displacement 29.7 L, cylindersAfter 5)"+ },+ {+ "kind": "probe:api",+ "target": "the machine atlas page is up",+ "ok": true,+ "detail": "HTTP 200, expectations met"+ },+ {+ "kind": "link",+ "target": "https://three.ws/assembly",+ "ok": true,+ "detail": "HTTP 200"+ }+ ]+ },+ "editor": {+ "verdict": "publish",+ "scores": {+ "accuracy": 5,+ "clarity": 5,+ "specificity": 5,+ "voice": 5,+ "professionalism": 5,+ "visual": 5+ },+ "issues": [],+ "rewrite": {+ "posts": [+ "A nine-cylinder radial engine and a steam locomotive, with no model file behind either one. It is a Labs experiment in building 3D geometry from code instead of files.\n\nBoth machines are built when the page loads: dimensions become profiles, profiles get revolved or extruded, and the results are merged into the parts you can see. Move a slider and the geometry is rebuilt. Nine cylinders to five, and the displacement readout, the parts list and the source panel follow, because all of them are derived from the same numbers.",+ "The motion is solved, not baked animation. Pistons come from the exact planar slider-crank, and the locomotive valve gear closes a four-bar chain by intersecting circles every frame, which is why a rod length that cannot physically reach refuses to move rather than stretching.\n\nEach machine is a small JSON object of numbers. Copy the spec, hand it to an agent, get a different machine back, then export the result as GLB. three.ws/assembly"+ ],+ "altText": []+ },+ "summary": "Every claim passed verification against the live page and the filmed run: nine cylinders to five, solved four-bar motion, JSON spec, GLB export, and the link resolves. The reel frames and captions match the copy, the voice contract is fully obeyed, and the first line leads with the strongest checkable fact.\nShip it unchanged.",+ "model": "nvidia:moonshotai/kimi-k3",+ "fallbacks": [+ "Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",+ "openrouter 402: {\"error\":{\"message\":\"Insufficient credits. Add more using https://openrouter.ai/settings/credits\",\"code\":402,\"metadata\":{\"limit_source\":\"openrouter_credits\",\"remedy_hint\":\"Add credits at https://openr",+ "openai 429: {\n \"error\": {\n \"message\": \"Your account is not active, please check your billing details on our website.\",\n \"type\": \"billing_not_active\",\n \"param\": null,\n \"code\": \"billi"+ ],+ "rewriteFindings": []+ },+ "editorError": null+}diff --git a/data/x-content/reviews/splat-viewer.json b/data/x-content/reviews/splat-viewer.jsonindex a5cfde7c4..c4efe1c2f 100644--- a/data/x-content/reviews/splat-viewer.json+++ b/data/x-content/reviews/splat-viewer.json@@ -1,9 +1,11 @@{"id": "splat-viewer",- "contentHash": "82702888307a86f711f878c81d282e069da647bf6d9341d0ec74c65b6f1d3f5d",- "reviewedAt": "2026-09-30T08:19:30.664Z",- "passed": true,- "blockers": [],+ "contentHash": "14b82c8faa27a36f7b18ebd422432277140b289d7b746c66f3ef861a3264c669",+ "reviewedAt": "2026-09-30T08:42:30.481Z",+ "passed": false,+ "blockers": [+ "editor verdict is revise"+ ],"texts": ["A Gaussian splat rebuilds a person or a room as millions of tiny blobs instead of polygons. The splat viewer decodes one on your own device and draws it in a browser tab with WebGL, so the file stays with you.\n\nPaste a link to a capture or drop the file in. It reads five formats and tells them apart by their bytes, not their filenames.\n\nThe reel is the built-in sample: 14,000 splats, synthetic, generated on the page.","Both built-in samples are synthetic. They exist to exercise the renderer and are not real captures. A real one comes out of a capture engine trained on footage of a person, exported as a file, then opened here.\n\nthree.ws/splat",@@ -139,25 +141,33 @@]},"editor": {- "verdict": "publish",+ "verdict": "revise","scores": {- "accuracy": 5,+ "accuracy": 4,"clarity": 5,"specificity": 5,"voice": 5,"professionalism": 5,"visual": 5},- "issues": [],+ "issues": [+ {+ "severity": "major",+ "area": "accuracy",+ "quote": "which is the difference between a capture you can send as a link and one you cannot",+ "problem": "The verified evidence covers only the size comparison (a 1 GB PLY is roughly 100 MB as SPZ). The conclusion that file size determines whether a capture can be sent as a link is unverified and misleading: the previous sentence just explained that ?src= passing works for any address, so a 1 GB file is equally linkable. It overreads the docs quote and invites a pedantic correction from the developer audience.",+ "fix": "End the sentence at the verified fact: \"The same scene that is a 1 GB PLY is roughly 100 MB as SPZ.\""+ }+ ],"rewrite": {"posts": ["A Gaussian splat rebuilds a person or a room as millions of tiny blobs instead of polygons. The splat viewer decodes one on your own device and draws it in a browser tab with WebGL, so the file stays with you.\n\nPaste a link to a capture or drop the file in. It reads five formats and tells them apart by their bytes, not their filenames.\n\nThe reel is the built-in sample: 14,000 splats, synthetic, generated on the page.","Both built-in samples are synthetic. They exist to exercise the renderer and are not real captures. A real one comes out of a capture engine trained on footage of a person, exported as a file, then opened here.\n\nthree.ws/splat",- "To share a capture, add ?src= and the address of the file to the address of the viewer. The scene loads as the page opens, so the link is the whole handoff.\n\nThe same scene that is a 1 GB PLY is roughly 100 MB as SPZ, which is the difference between a capture you can send as a link and one you cannot."+ "To share a capture, add ?src= and the address of the file to the address of the viewer. The scene loads as the page opens, so the link is the whole handoff.\n\nThe same scene that is a 1 GB PLY is roughly 100 MB as SPZ."],"altText": []},- "summary": "Every claim, number, and caption verifies against the live pages and the filmed run, and the reel frames show exactly what the copy describes, including the 14,000-splat sample. The voice is clean: mechanism lead, no hashtags, no dashes, one link in a reply. Ship it unchanged.",+ "summary": "Every claim verifies against the live pages and the run, and the reel frames and captions match the copy including the 14,000 splats figure. The only fix is trimming the unverified and misleading tail of post 3, which implied file size determines whether a capture can be shared as a link.","model": "nvidia:moonshotai/kimi-k3","fallbacks": ["Vertex 403: {\n \"error\": {\n \"code\": 403,\n \"message\": \"Request had insufficient authentication scopes.\",\n \"status\": \"PERMISSION_DENIED\",\n \"details\": [\n {\n \"@type\": \"type.googleapis.com/goog",