{"messages":[{"content":"You are a constitutional council ranking individual git commits for ownership allocation.\n\nCompare these two commits. Decide which contributed more lasting value to the project.\n\nJudge substance, not spectacle:\n- Prefer correct, lasting design and real bugfixes over churn, formatting, renames, or generated noise.\n- Prefer clarity and necessity over sheer line count. A small precise change can beat a large diffuse one.\n- Do not favor a side merely because its patch is longer or noisier.\n- Weight what the change does for the project, not the contributor's name.\n\nReturn ONLY a JSON object: {\"winner\": \"A\" or \"B\", \"ratio\": \"N:M\", \"explanation\": \"...\"}\nThe explanation must cite concrete differences in the patches (1-3 sentences).\n\nSide A — contributor: tommy-mor\nSide A — commit message:\n[0bebe819] Unify kaocha test discovery to one auto-discovered suite.\n\nReplace the two hand-enumerated suites (:http-integration, :browser) with\na single :all suite that picks up every test.* namespace under test/. New\ntest files now run automatically without touching tests.edn — needed for\nthe test.ranking namespace added alongside the #146 fix, and for any\nfuture tests.\n\nBoth ./TEST.sh and CI (.github/workflows/ci.yml) invoke\n`clojure -M:kaocha`, so both pick up the new suite without changes.\n\nCo-Authored-By: Claude Opus 4.7 (1M context) \n\nSide A — unified diff (full patch):\ndiff --git a/tests.edn b/tests.edn\nindex 5e2b0433a66c51806d08ef38d691259cfccd1fe0..e51ffcc81eeae6f41c85d1bfc5ba32f592cc5818 100644\n--- a/tests.edn\n+++ b/tests.edn\n@@ -1,30 +1,14 @@\n #kaocha/v1\n-{:tests\n- [{:id :http-integration\n- :test-paths [\"test\"]\n- :source-paths [\".\"]\n- :ns-patterns [\"^test\\\\.integration$\"\n- \"^test\\\\.auth$\"\n- \"^test\\\\.grants$\"\n- \"^test\\\\.invites$\"\n- \"^test\\\\.room-list$\"]\n- :kaocha.filter/skip-meta [:skip]\n- :parallel? false}\n- {:id :browser\n- :test-paths [\"test\"]\n- :source-paths [\".\"]\n- :ns-patterns [\"^test\\\\.browser-sse$\"\n- \"^test\\\\.browser-ui-morph$\"\n- \"^test\\\\.browser-post-redact$\"\n- \"^test\\\\.browser-room-delete$\"\n- \"^test\\\\.browser-public-garden$\"\n- \"^test\\\\.browser-redact-thread-index$\"\n- \"^test\\\\.browser-garden-pin$\"\n- \"^test\\\\.browser-vote-compare$\"\n- \"^test\\\\.browser-github-resolver$\"]\n- :kaocha.filter/skip-meta [:skip]\n- :parallel? false}]\n- :plugins [:kaocha.plugin/junit-xml]\n- :kaocha.plugin.junit-xml/target-file \"target/kaocha-junit.xml\"\n- :kaocha.plugin.junit-xml/add-location-metadata? true\n- :reporter kaocha.report.progress/report}\n+ {:tests\n+ [{:id :all\n+ :test-paths [\"test\"]\n+ :source-paths [\".\"]\n+ ;; Pick up every test.* namespace under test/. New files don't need to be\n+ ;; enumerated here — drop them in test/ with `(ns test.foo …)` and they run.\n+ :ns-patterns [\"^test\\\\..+\"]\n+ :kaocha.filter/skip-meta [:skip]\n+ :parallel? false}]\n+ :plugins [:kaocha.plugin/junit-xml]\n+ :kaocha.plugin.junit-xml/target-file \"target/kaocha-junit.xml\"\n+ :kaocha.plugin.junit-xml/add-location-metadata? true\n+ :reporter kaocha.report.progress/report}\n\n\nSide B — contributor: tommy-mor\nSide B — commit message:\n[78964dd7] nice\n\nSide B — unified diff (full patch):\ndiff --git a/server/src/fetch/html.rs b/server/src/fetch/html.rs\nindex 9b6c2d0964640a157bca2a6a64cb0820238d8e4f..3e0309ff1c2ac1b17923922d2340ba6710e0f9d1 100644\n--- a/server/src/fetch/html.rs\n+++ b/server/src/fetch/html.rs\n@@ -11,6 +11,9 @@ use crate::{\n };\n \n fn entity_panel(node: &NodeState) -> Markup {\n+ if let Some(markup) = crate::render::reddit::entity_markup(node) {\n+ return markup;\n+ }\n html! {\n @if let Some(data) = &node.data {\n div id=\"entity-panel\" class=\"entity-card\" {\ndiff --git a/server/src/html/mod.rs b/server/src/html/mod.rs\nindex e88cc43ddc9d8100f7994be6f5960ec4d8f22c55..3bf9fc7e92e50beed24e2c25106a77421038c90b 100644\n--- a/server/src/html/mod.rs\n+++ b/server/src/html/mod.rs\n@@ -153,16 +153,21 @@ pub fn breadcrumb_path(item: &ItemId) -> Markup {\n }\n }\n \n-fn rank_list(label: &str, items: &[RankedItem], start_rank: usize) -> Markup {\n+fn rank_list(label: &str, items: &[RankedItem], start_rank: usize, tree: &GlobalTree) -> Markup {\n html! {\n @if !items.is_empty() {\n h3 class=\"rank-heading muted small\" { (label) }\n ol class=\"rank-list\" {\n @for (i, r) in items.iter().enumerate() {\n- li {\n+ @let href = item_href(&r.item);\n+ li class=(if crate::render::reddit::is_reddit_post(&r.item) { \"reddit-post-row\" } else { \"\" }) {\n span class=\"rank-num\" { (start_rank + i) \". \" }\n- a href=(item_href(&r.item)) {\n- strong { (display_label(&r.item)) }\n+ @if let Some(row) = crate::render::reddit::child_row_markup(tree, &r.item, &href) {\n+ (row)\n+ } @else {\n+ a href=(href) {\n+ strong { (display_label(&r.item)) }\n+ }\n }\n span class=\"muted\" {\n \" — \"\n@@ -196,9 +201,14 @@ fn unranked_list(label: &str, items: &[ItemId], tree: &GlobalTree) -> Markup {\n h3 class=\"rank-heading muted small\" { (label) }\n ul class=\"rank-list unranked\" {\n @for it in items {\n- li {\n- a href=(item_href(it)) {\n- strong { (child_label(tree, it)) }\n+ @let href = item_href(it);\n+ li class=(if crate::render::reddit::is_reddit_post(it) { \"reddit-post-row\" } else { \"\" }) {\n+ @if let Some(row) = crate::render::reddit::child_row_markup(tree, it, &href) {\n+ (row)\n+ } @else {\n+ a href=(href) {\n+ strong { (child_label(tree, it)) }\n+ }\n }\n }\n }\n@@ -253,7 +263,7 @@ pub fn ranking_panel(item: &ItemId, node: &NodeState, tree: &GlobalTree) -> Mark\n } @else {\n @for (gi, ranked) in ranked_groups.iter().enumerate() {\n @let label = if multi { format!(\"Ranking group {}\", gi + 1) } else { \"Ranking\".to_string() };\n- (rank_list(&label, ranked, 1))\n+ (rank_list(&label, ranked, 1, tree))\n }\n (unranked_list(\"Unranked\", &unranked, tree))\n }\ndiff --git a/server/src/lib.rs b/server/src/lib.rs\nindex 0677363e0ed21d244bfa065f7ec728549ddd9e50..da5f3ebecec1794b05a2a69cc78379551b2ad769 100644\n--- a/server/src/lib.rs\n+++ b/server/src/lib.rs\n@@ -8,6 +8,7 @@ pub mod parser;\n pub mod path_types;\n pub mod ranking;\n pub mod reddit;\n+pub mod render;\n pub mod reducer;\n pub mod journal;\n pub mod state;\ndiff --git a/server/src/reddit.rs b/server/src/reddit.rs\nindex 69d979bc7e4a1cb078f70114dc539bdc1986b574..1168ec2afc77c092514eec91b513bac301cbe225 100644\n--- a/server/src/reddit.rs\n+++ b/server/src/reddit.rs\n@@ -608,6 +608,8 @@ fn parse_subreddit_about(v: &Value) -> Option {\n author: None,\n body_html,\n thumb_url,\n+ image_url: None,\n+ link_url: None,\n })\n }\n \n@@ -635,15 +637,64 @@ fn parse_post_listing(v: &Value) -> Option {\n .and_then(|t| t.as_str())\n .filter(|s| s.starts_with(\"http\"))\n .map(|s| s.to_string());\n+ let image_url = reddit_post_image_url(child);\n+ let link_url = reddit_post_link_url(child);\n \n Some(crate::reducer::EntityData {\n title,\n author,\n body_html,\n thumb_url,\n+ image_url,\n+ link_url,\n })\n }\n \n+fn reddit_post_link_url(data: &Value) -> Option {\n+ for key in [\"url_overridden_by_dest\", \"url\"] {\n+ if let Some(u) = data.get(key).and_then(|v| v.as_str()) {\n+ if u.starts_with(\"http\") {\n+ return Some(u.to_string());\n+ }\n+ }\n+ }\n+ None\n+}\n+\n+/// Full-size still for post detail: direct image `url`, else Reddit preview source.\n+fn reddit_post_image_url(data: &Value) -> Option {\n+ for key in [\"url\", \"url_overridden_by_dest\"] {\n+ if let Some(u) = data.get(key).and_then(|v| v.as_str()) {\n+ if reddit_direct_image_url(u) {\n+ return Some(u.to_string());\n+ }\n+ }\n+ }\n+ reddit_preview_source_url(data)\n+}\n+\n+fn reddit_preview_source_url(data: &Value) -> Option {\n+ data.pointer(\"/preview/images/0/source/url\")\n+ .and_then(|v| v.as_str())\n+ .filter(|s| s.starts_with(\"http\"))\n+ .map(str::to_string)\n+}\n+\n+fn reddit_direct_image_url(url: &str) -> bool {\n+ let u = url.to_ascii_lowercase();\n+ if u.contains(\"redgifs.com\") {\n+ return false;\n+ }\n+ u.contains(\"i.redd.it\")\n+ || u.contains(\"preview.redd.it\")\n+ || u.contains(\"external-preview.redd.it\")\n+ || u.ends_with(\".jpg\")\n+ || u.ends_with(\".jpeg\")\n+ || u.ends_with(\".png\")\n+ || u.ends_with(\".gif\")\n+ || u.ends_with(\".webp\")\n+}\n+\n #[cfg(test)]\n mod tests {\n use super::*;\n@@ -672,4 +723,20 @@ mod tests {\n .unwrap();\n assert_eq!(entity.title, \"The Rust Programming Language\");\n }\n+\n+ #[test]\n+ fn parse_post_listing_extracts_thumb_and_full_preview() {\n+ let json = include_str!(\"../../test/fixtures/reddit/post_preview.json\");\n+ let v: Value = serde_json::from_str(json).unwrap();\n+ let id = ItemId::parse(\"reddit.com/r/nsfw/comments/1tpy6a1/angel_eyes\").unwrap();\n+ let entity = entity_view_from_payload(&id, &v).unwrap();\n+ assert_eq!(entity.title, \"Angel Eyes\");\n+ assert!(entity.thumb_url.as_ref().unwrap().contains(\"width=140\"));\n+ assert!(entity.image_url.as_ref().unwrap().contains(\"auto=webp\"));\n+ assert!(!entity.image_url.as_ref().unwrap().contains(\"redgifs\"));\n+ assert_eq!(\n+ entity.link_url.as_deref(),\n+ Some(\"http://v3.redgifs.com/watch/impossibleprestigioushedgehog\")\n+ );\n+ }\n }\ndiff --git a/server/src/reducer.rs b/server/src/reducer.rs\nindex 4e42d0369dab50bb2f8ca664aa69b628292f6c07..336e78b77d3ab59361b89af5c9868e13da4ac962 100644\n--- a/server/src/reducer.rs\n+++ b/server/src/reducer.rs\n@@ -122,7 +122,12 @@ pub struct EntityData {\n pub title: String,\n pub author: Option,\n pub body_html: Option,\n+ /// Small preview (subreddit listing / child rows).\n pub thumb_url: Option,\n+ /// Full-size still image for the post detail view.\n+ pub image_url: Option,\n+ /// Outbound link for link/video posts (`url` / `url_overridden_by_dest`).\n+ pub link_url: Option,\n }\n \n /// One node in the fractal tree: entity + ranked children.\ndiff --git a/server/src/render/mod.rs b/server/src/render/mod.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..c2c41404abe01c671139658fcccdeced5be388e4\n--- /dev/null\n+++ b/server/src/render/mod.rs\n@@ -0,0 +1,3 @@\n+//! Domain-specific HTML fragments for imported entities.\n+\n+pub mod reddit;\ndiff --git a/server/src/render/reddit.rs b/server/src/render/reddit.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..4a18de93cf57d8395ded3caa373a708f39b3f43f\n--- /dev/null\n+++ b/server/src/render/reddit.rs\n@@ -0,0 +1,64 @@\n+//! Reddit post cards: thumbnail in child lists, full image on the post page.\n+\n+use maud::{html, Markup};\n+\n+use crate::{\n+ path_types::ItemId,\n+ reducer::{EntityData, GlobalTree, NodeState},\n+};\n+\n+pub fn is_reddit_post(id: &ItemId) -> bool {\n+ id.as_str().starts_with(\"reddit.com/\") && id.as_str().contains(\"/comments/\")\n+}\n+\n+/// Post detail card (`#entity-panel`).\n+pub fn entity_markup(node: &NodeState) -> Option {\n+ if !is_reddit_post(&node.id) {\n+ return None;\n+ }\n+ let data = node.data.as_ref()?;\n+ Some(post_entity_card(data))\n+}\n+\n+/// One row in a parent ranking list (thumbnail + title).\n+pub fn child_row_markup(tree: &GlobalTree, id: &ItemId, href: &str) -> Option {\n+ if !is_reddit_post(id) {\n+ return None;\n+ }\n+ let data = tree.get(id)?.data.as_ref()?;\n+ Some(html! {\n+ @if let Some(thumb) = &data.thumb_url {\n+ a class=\"reddit-post-thumb-link\" href=(href) {\n+ img class=\"reddit-post-thumb\" src=(thumb) alt=\"\" loading=\"lazy\";\n+ }\n+ }\n+ a href=(href) {\n+ strong { (data.title) }\n+ }\n+ })\n+}\n+\n+fn post_entity_card(data: &EntityData) -> Markup {\n+ let image = data.image_url.as_ref().or(data.thumb_url.as_ref());\n+ html! {\n+ div id=\"entity-panel\" class=\"entity-card reddit-post\" {\n+ h2 { (data.title) }\n+ @if let Some(author) = &data.author {\n+ p class=\"muted small\" { \"by \" (author) }\n+ }\n+ @if let Some(url) = &data.link_url {\n+ p class=\"reddit-post-url muted small\" {\n+ a href=(url) rel=\"noopener noreferrer\" { (url) }\n+ }\n+ }\n+ @if let Some(src) = image {\n+ figure class=\"reddit-post-figure\" {\n+ img class=\"reddit-post-image\" src=(src) alt=\"\" loading=\"lazy\";\n+ }\n+ }\n+ @if let Some(body) = &data.body_html {\n+ div class=\"entity-body\" { (maud::PreEscaped(body)) }\n+ }\n+ }\n+ }\n+}\ndiff --git a/server/static/sorter.css b/server/static/sorter.css\nindex 1f9f5158414902d43a380dd899232c70d8cf5d63..021918f8e778b84e4b3eac8559fab7d223a3d490 100644\n--- a/server/static/sorter.css\n+++ b/server/static/sorter.css\n@@ -171,6 +171,41 @@ code {\n margin-top: 0;\n }\n \n+.reddit-post-row {\n+ display: flex;\n+ align-items: center;\n+ gap: 0.6rem;\n+}\n+\n+.reddit-post-thumb-link {\n+ flex-shrink: 0;\n+ line-height: 0;\n+}\n+\n+.reddit-post-thumb {\n+ width: 64px;\n+ height: 64px;\n+ object-fit: cover;\n+ border-radius: 4px;\n+ border: 1px solid var(--border);\n+}\n+\n+.reddit-post-url a {\n+ word-break: break-all;\n+}\n+\n+.reddit-post-figure {\n+ margin: 0.75rem 0;\n+}\n+\n+.reddit-post-image {\n+ display: block;\n+ max-width: 100%;\n+ height: auto;\n+ border-radius: 6px;\n+ border: 1px solid var(--border);\n+}\n+\n .scope-name {\n color: var(--accent);\n font-weight: 600;\ndiff --git a/test/fixtures/reddit/post_preview.json b/test/fixtures/reddit/post_preview.json\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..c6ed31ae397dc0f7b6e07e5e010e617df78d9c18\n--- /dev/null\n+++ b/test/fixtures/reddit/post_preview.json\n@@ -0,0 +1,22 @@\n+{\n+ \"kind\": \"t3\",\n+ \"data\": {\n+ \"title\": \"Angel Eyes\",\n+ \"permalink\": \"/r/nsfw/comments/1tpy6a1/angel_eyes/\",\n+ \"author\": \"alice\",\n+ \"thumbnail\": \"https://external-preview.redd.it/Kb6Nf5Q4RAucat-2RFcYMeQb2d6vgYNo5EPlf6kGLbs.jpeg?width=140&height=140&auto=webp&s=d7238240ebf191b954ef5f42b0cf61b67aecec88\",\n+ \"url\": \"http://v3.redgifs.com/watch/impossibleprestigioushedgehog\",\n+ \"post_hint\": \"rich:video\",\n+ \"preview\": {\n+ \"images\": [\n+ {\n+ \"source\": {\n+ \"url\": \"https://external-preview.redd.it/Kb6Nf5Q4RAucat-2RFcYMeQb2d6vgYNo5EPlf6kGLbs.jpeg?auto=webp&s=ccdabee3b81e46ef2d7cec072f6604a09f61dc9a\",\n+ \"width\": 480,\n+ \"height\": 480\n+ }\n+ }\n+ ]\n+ }\n+ }\n+}\n","role":"user"}],"model":"openai/gpt-chat-latest"}