@ainyc/canonry 4.80.0 → 4.82.0

package/assets/agent-workspace/skills/canonry/references/canonry-cli.md

@@ -277,11 +277,15 @@ Mint, list, and revoke the `cnry_…` bearer tokens stored in the `api_keys` tab
 cnry key list                                  # table: NAME / PREFIX / SCOPES / CREATED / LAST USED / STATUS
 cnry key list --format json|jsonl              # jsonl streams one key per line
 cnry key create --name ci-bot                  # mint a full-access key (scopes default to *)
+cnry key create --name reader --read-only      # read-only key: scopes=['read'], denied every write HTTP method
 cnry key create --name reader --scope read     # narrower key; repeat --scope or comma-separate (--scope a,b)
 cnry key create --name ci-bot --format json    # JSON output includes the plaintext key
 cnry key revoke <id>                           # revoke (does not delete); effective on the next request
+cnry key whoami [--format json]                # introspect the CURRENT key (name, scopes, readOnly, status)
 ```
 
+- **`--read-only` keys can read everything but write nothing.** The server denies every mutating method (POST/PUT/PATCH/DELETE) for a read-only key (`403 FORBIDDEN`); GET/HEAD pass. `--read-only` is sugar for `--scope read` and cannot be combined with `--scope`. The key DTO carries a derived `readOnly: boolean`. Point `canonry-mcp` at a read-only key and it auto-restricts to read tools.
+
 - **Create returns the plaintext key exactly once.** It is shown with a "Save this now — it will not be shown again." warning (and is included in the JSON under `key`). It cannot be recovered later, so persist it on receipt.
 - **List never exposes the hash or plaintext** — only safe metadata (id, name, prefix, scopes, created / last-used / revoked timestamps).
 - **Mutations are gated by the `keys.write` scope.** The default key from `cnry init` carries `*`, which satisfies it. A narrower key needs `keys.write` to mint or revoke.
@@ -483,29 +487,37 @@ cnry schedule set <project> --kind ads-sync --preset daily
 `ads sync` runs report `completed` / `partial` (some campaigns failed; per-campaign errors on the run) / `failed`. Doctor checks: `ads.auth.connection`, `ads.data.recent-sync` (both skipped when not connected).
 
 
-## Backlinks (Common Crawl)
+## Backlinks (source-aware: Common Crawl + Bing Webmaster)
+
+Backlinks are **source-aware** — every read takes a `--source commoncrawl|bing-webmaster` filter (default `commoncrawl`) and rows are tagged with their source:
 
-Workspace-level Common Crawl release sync + per-project backlink extraction. Requires DuckDB; install once with `cnry backlinks install`. Releases are downloaded once per workspace and reused across all projects.
+- **Common Crawl** — free public hyperlink graph, ~monthly. Workspace-level release sync + per-project extract. Requires DuckDB (install once with `cnry backlinks install`). Releases download once per workspace and reuse across projects.
+- **Bing Webmaster** — live first-party inbound links from a connected Bing account (`cnry bing connect <project> --api-key <key>`). Per-project; pull with `cnry backlinks bing-sync`.
 
-Common Crawl publishes the hyperlink graph as **rolling, monthly-stepped, overlapping 3-month windows** named by the window's first month's year: `cc-main-YYYY-<mon>-<mon>-<mon>` (e.g. `cc-main-2026-mar-apr-may`). Omit `--release` to auto-discover the newest published window; the legacy fixed-quarter slugs (`jan-feb-mar`, …) still resolve since they're a subset of the cadence.
+Common Crawl publishes the hyperlink graph as **rolling, monthly-stepped, overlapping 3-month windows** named by the window's first month's year: `cc-main-YYYY-<mon>-<mon>-<mon>` (e.g. `cc-main-2026-mar-apr-may`). Omit `--release` to auto-discover the newest published window. Bing windows are synthetic per-UTC-day snapshots (`bing-YYYY-MM-DD`).
 
 ```bash
-cnry backlinks install                         # install bundled DuckDB binary
+cnry backlinks install                         # install bundled DuckDB binary (Common Crawl only)
 cnry backlinks doctor                          # show install + plugin status
-cnry backlinks status                          # latest workspace release sync
+cnry backlinks status                          # latest workspace Common Crawl release sync
 cnry backlinks releases                        # list cached releases on disk
 cnry backlinks releases latest                 # probe Common Crawl for the newest published rolling window
-cnry backlinks sync                            # auto-discover + download + query the newest release (workspace-wide)
-cnry backlinks sync --release cc-main-2026-mar-apr-may   # pin a specific rolling window
-cnry backlinks sync --release <id> --wait      # block until ready/failed
-cnry backlinks list <project>                  # top linking domains for the project
+cnry backlinks sync                            # Common Crawl: auto-discover + download + query the newest release (workspace-wide)
+cnry backlinks sync --release cc-main-2026-mar-apr-may --wait   # pin a window, block until ready/failed
+cnry backlinks sources <project>               # per-source availability (connected / has-data / latest window / freshness)
+cnry backlinks sources <project> --exclude-crawlers   # availability counts drop crawler/proxy hosts (matches the dashboard)
+cnry backlinks bing-sync <project>             # Bing: pull live inbound links for the project (needs Bing connected)
+cnry backlinks bing-sync <project> --wait      # block until the sync run completes
+cnry backlinks list <project>                  # top linking domains (Common Crawl, default)
+cnry backlinks list <project> --source bing-webmaster   # top linking domains from Bing inbound links
 cnry backlinks list <project> --limit 100 --release <id>
-cnry backlinks extract <project>               # re-extract this project against the latest ready release
-cnry backlinks extract <project> --release <id> --wait
+cnry backlinks extract <project> --release <id> --wait  # Common Crawl: re-extract against a ready release
 cnry backlinks cache prune --release <id>      # delete cached release files from disk
 ```
 
-All commands support `--format json`. A release sync has statuses `queued` → `downloading` → `querying` → `ready` / `failed`. Per-project extract runs use the standard run statuses (`queued` → `running` → `completed` / `failed`). Projects with the `autoExtractBacklinks` setting enabled get an extract run enqueued automatically when a release sync transitions to `ready`.
+All commands support `--format json`; collection commands (`list`, `sources`, `releases`) also support `--format jsonl`. A Common Crawl release sync has statuses `queued` → `downloading` → `querying` → `ready` / `failed`. Per-project extract / Bing-sync runs use the standard run statuses (`queued` → `running` → `completed` / `failed`). Projects with `autoExtractBacklinks` enabled get a Common Crawl extract enqueued automatically when a release sync transitions to `ready`; Bing-connected projects with a `backlinks-sync` schedule get a Bing pull each tick.
+
+**`jsonl` output schema:** `backlinks list` streams `rows` (each `{ project, release, targetDomain, linkingDomain, numHosts, source }`); `backlinks sources` streams the per-source availability list (`{ project, targetDomain, source, connected, hasData, latestRelease, totalLinkingDomains, lastSyncedAt }`); `backlinks releases` streams cached-release rows bare.
 
 To keep backlinks fresh automatically, schedule a `backlinks-sync` kind (`cnry schedule set <project> --kind backlinks-sync --preset weekly`): each tick re-probes Common Crawl and runs the workspace release sync **only when a newer rolling window is published** (it skips when the newest `ready` sync already covers the latest release, so it never re-downloads a near-identical window).
 

package/assets/assets/{BacklinksPage-dRc62jAY.js → BacklinksPage-CHclt-pq.js}

@@ -1 +1 @@
-import{r as n,j as e}from"./vendor-tanstack-Dq7p98wZ.js";import{c as E,bM as O,ad as V,bN as U,bO as Y,bP as K,g as l,aF as L,T as f,B as z,i as A,am as J,bQ as X,bR as Z,ag as ee,bS as se}from"./index-EnY_OBRd.js";import{C as ae,D as te,T as ne,a as ce}from"./trash-2-JpcztiS5.js";import"./vendor-radix-B57xfQbP.js";import"./vendor-recharts-ClRVR6aX.js";import"./vendor-markdown-DK7fbRNb.js";const ie=[["circle",{cx:"12",cy:"12",r:"10",key:"1mglay"}],["line",{x1:"12",x2:"12",y1:"8",y2:"12",key:"1pkeuh"}],["line",{x1:"12",x2:"12.01",y1:"16",y2:"16",key:"4dfq90"}]],re=E("circle-alert",ie);const le=[["path",{d:"M15 3h6v6",key:"1q9fwt"}],["path",{d:"M10 14 21 3",key:"gplh6r"}],["path",{d:"M18 13v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6",key:"a6xqqp"}]],de=E("external-link",le);function h({children:a,label:m="More info",placement:t="top",className:d}){const o=n.useId(),[y,r]=n.useState(!1);return e.jsxs("span",{className:`relative inline-flex ${d??""}`,children:[e.jsx("button",{type:"button","aria-label":m,"aria-describedby":y?o:void 0,className:"inline-flex h-4 w-4 items-center justify-center rounded-full text-zinc-500 hover:text-zinc-200 focus:text-zinc-200 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500",onMouseEnter:()=>r(!0),onMouseLeave:()=>r(!1),onFocus:()=>r(!0),onBlur:()=>r(!1),children:e.jsx(ce,{className:"h-3.5 w-3.5","aria-hidden":!0})}),y&&e.jsx("span",{id:o,role:"tooltip",className:`absolute z-50 w-64 rounded border border-zinc-700 bg-zinc-900 px-3 py-2 text-xs font-normal leading-relaxed text-zinc-200 shadow-lg ${t==="top"?"bottom-full mb-2":"top-full mt-2"} left-1/2 -translate-x-1/2 whitespace-normal`,children:a})]})}const oe="https://commoncrawl.org/web-graphs";function w(a){return a==null?"—":a>=1e12?`${(a/1e12).toFixed(1)} TB`:a>=1e9?`${(a/1e9).toFixed(1)} GB`:a>=1e6?`${(a/1e6).toFixed(1)} MB`:a>=1e3?`${(a/1e3).toFixed(1)} KB`:`${a} B`}function b(a){if(!a)return"—";const m=Date.now()-new Date(a).getTime(),t=Math.floor(m/6e4);if(t<1)return"just now";if(t<60)return`${t}m ago`;const d=Math.floor(t/60);return d<24?`${d}h ago`:`${Math.floor(d/24)}d ago`}function v(a){switch(a){case"ready":return"positive";case"failed":return"negative";case"downloading":case"querying":case"queued":return"caution"}}function fe(){const[a,m]=n.useState(null),[t,d]=n.useState(null),[o,y]=n.useState([]),[r,M]=n.useState([]),[u,P]=n.useState(null),[D,S]=n.useState(!0),[C,B]=n.useState(!1),[p,R]=n.useState(!1),[N,g]=n.useState(""),[F,k]=n.useState(!1),[q,i]=n.useState(null),[I,x]=n.useState(null),j=n.useCallback(async()=>{S(!0),i(null);try{const[s,c,_,W,H]=await Promise.all([O(),V().catch(()=>null),U().catch(()=>[]),Y().catch(()=>[]),K().catch(()=>null)]);m(s),d(c),y(_),M(W),P(H)}catch(s){i(s instanceof Error?s.message:"Failed to load backlinks status")}finally{S(!1)}},[]);n.useEffect(()=>{j()},[j]);async function $(){B(!0),i(null),x(null);try{const s=await X();x(s.alreadyPresent?`DuckDB already installed (${s.version}).`:`Installed DuckDB ${s.version}.`),await j()}catch(s){i(s instanceof Error?s.message:"Failed to install DuckDB")}finally{B(!1)}}async function T(){const s=N.trim()||void 0;R(!0),i(null),x(null);try{const c=await Z(s);x(s?`Queued sync for ${c.release}. Download + query runs in the background.`:`Queued sync for auto-discovered release ${c.release}. Download + query runs in the background.`),g(""),k(!1),await j()}catch(c){c instanceof ee&&c.code==="MISSING_DEPENDENCY"?i("DuckDB is not installed. Install it first."):i(c instanceof Error?c.message:"Failed to trigger sync")}finally{R(!1)}}async function Q(s){i(null),x(null);try{await se(s),x(`Pruned cached release ${s}.`),await j()}catch(c){i(c instanceof Error?c.message:"Failed to prune release")}}const G=t?.status==="ready"&&r.every(s=>s.release!==t.release);return e.jsxs("div",{className:"page-container",children:[e.jsx("div",{className:"page-header",children:e.jsxs("div",{className:"page-header-left",children:[e.jsx("h1",{className:"page-title",children:"Backlinks"}),e.jsx("p",{className:"page-subtitle",children:"Find domains that link to your projects, computed from the open Common Crawl web graph. Runs entirely on your machine — nothing is sent to third parties."})]})}),e.jsx(l,{className:"surface-card p-4 mb-6 border-amber-800/60",children:e.jsxs("div",{className:"flex items-start gap-3",children:[e.jsx(L,{className:"h-5 w-5 text-amber-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{className:"text-sm text-zinc-300 leading-relaxed",children:[e.jsx("p",{className:"font-medium text-amber-200",children:"Heads up — a release sync is a large download."}),e.jsxs("ul",{className:"mt-1.5 space-y-1 text-zinc-400",children:[e.jsxs("li",{children:[e.jsx("span",{className:"text-zinc-200",children:"~16 GB"})," of gzipped vertex + edge files per release, stored at"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/"}),"."]}),e.jsxs("li",{children:[e.jsx("span",{className:"text-zinc-200",children:"10–20 min on a fast connection"})," for the download, then ~5 min for the DuckDB query."]}),e.jsx("li",{children:"One sync covers every project in this workspace. Releases are immutable, so the download only happens once per release."})]})]})]})}),e.jsxs("section",{className:"page-section-divider",children:[e.jsx("div",{className:"section-head section-head-inline",children:e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"About"}),e.jsx("h2",{children:"How it works"})]})}),e.jsxs(l,{className:"surface-card p-5",children:[e.jsxs("p",{className:"text-sm text-zinc-400 leading-relaxed max-w-3xl mb-4",children:["Common Crawl publishes a quarterly snapshot of the public web’s hyperlink graph. Canonry downloads one"," ",e.jsx("span",{className:"text-zinc-200",children:"release"})," at a time and extracts backlinks for every project in this workspace in a single pass."]}),e.jsxs("ol",{className:"space-y-3 text-sm text-zinc-400 max-w-3xl",children:[e.jsxs("li",{className:"flex gap-3",children:[e.jsx("span",{className:"shrink-0 inline-flex h-6 w-6 items-center justify-center rounded-full border border-zinc-700 bg-zinc-900 text-xs font-semibold text-zinc-300 tabular-nums",children:"1"}),e.jsxs("span",{children:[e.jsx("span",{className:"text-zinc-200 font-medium",children:"Download (one-time, ~16 GB)"})," — vertex + edge files cached to"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/"}),". Runs once per release; subsequent operations reuse the cache."]})]}),e.jsxs("li",{className:"flex gap-3",children:[e.jsx("span",{className:"shrink-0 inline-flex h-6 w-6 items-center justify-center rounded-full border border-zinc-700 bg-zinc-900 text-xs font-semibold text-zinc-300 tabular-nums",children:"2"}),e.jsxs("span",{children:[e.jsx("span",{className:"text-zinc-200 font-medium",children:"Query (~5 min)"})," — one DuckDB pass scans the cached files and extracts referring domains for every project’s canonical domain. DuckDB is only used to ",e.jsx("span",{className:"text-zinc-200",children:"read"})," these dumps; it doesn’t store any canonry state."]})]}),e.jsxs("li",{className:"flex gap-3",children:[e.jsx("span",{className:"shrink-0 inline-flex h-6 w-6 items-center justify-center rounded-full border border-zinc-700 bg-zinc-900 text-xs font-semibold text-zinc-300 tabular-nums",children:"3"}),e.jsxs("span",{children:[e.jsx("span",{className:"text-zinc-200 font-medium",children:"Persist"})," — results land in the same SQLite database the rest of canonry uses. After the first sync, per-project reads (and re-run extracts against the cached release) are instant."]})]})]})]})]}),q&&e.jsx(l,{className:"surface-card p-4 mb-4 border-rose-800/60",children:e.jsx("p",{className:"text-sm text-rose-300",children:q})}),I&&e.jsx(l,{className:"surface-card p-4 mb-4 border-emerald-800/60",children:e.jsx("p",{className:"text-sm text-emerald-300",children:I})}),e.jsxs("section",{className:"page-section-divider",children:[e.jsxs("div",{className:"section-head section-head-inline",children:[e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"Dependency"}),e.jsxs("h2",{className:"flex items-center gap-2",children:["DuckDB install status",e.jsxs(h,{label:"Why DuckDB?",children:[e.jsx("span",{className:"block",children:"DuckDB is a query engine canonry uses to scan the ~16 GB Common Crawl dumps and pull out your referring domains."}),e.jsxs("span",{className:"mt-2 block text-zinc-400",children:["It does ",e.jsx("span",{className:"text-zinc-200",children:"not"})," store any canonry data — your backlink results live in SQLite alongside the rest of your projects. DuckDB is purely a tool for processing the raw CSV files."]}),e.jsxs("span",{className:"mt-2 block text-zinc-500",children:["Installed on demand (not bundled) into ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/plugins/"})," so users who never run backlinks don’t pay the ~40 MB install cost."]})]})]})]}),a?.duckdbInstalled?e.jsx(f,{tone:"positive",children:"Installed"}):e.jsx(f,{tone:"caution",children:"Not installed"})]}),e.jsx(l,{className:"surface-card p-5",children:D?e.jsx("p",{className:"text-sm text-zinc-500",children:"Checking…"}):a?.duckdbInstalled?e.jsxs("div",{className:"flex items-start gap-3",children:[e.jsx(ae,{className:"h-5 w-5 text-emerald-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{children:[e.jsxs("p",{className:"text-sm text-zinc-200",children:["Version ",a.duckdbVersion??"unknown"," installed at"," ",e.jsx("code",{className:"text-zinc-300",children:a.pluginDir})]}),e.jsxs("p",{className:"text-xs text-zinc-500 mt-1",children:["Required spec: ",a.duckdbSpec]})]})]}):e.jsxs("div",{className:"flex items-start gap-3",children:[e.jsx(re,{className:"h-5 w-5 text-amber-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{className:"flex-1",children:[e.jsx("p",{className:"text-sm text-zinc-200",children:"DuckDB is not installed. It’s the query engine canonry uses to scan Common Crawl dumps — required before you can run a release sync or per-project extract."}),e.jsx("p",{className:"text-xs text-zinc-500 mt-1",children:"Installing doesn’t touch your project data. DuckDB only reads the downloaded CSV files; backlink results are written to the same SQLite database canonry already uses."}),a&&e.jsxs("p",{className:"text-xs text-zinc-500 mt-1",children:["Will be installed into ",e.jsx("code",{className:"text-zinc-300",children:a.pluginDir})," (~40 MB)."]}),e.jsx("div",{className:"mt-3",children:e.jsxs(z,{type:"button",size:"sm",disabled:C,onClick:A($),children:[e.jsx(te,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),C?"Installing…":"Install DuckDB"]})})]})]})})]}),e.jsxs("section",{className:"page-section-divider",children:[e.jsxs("div",{className:"section-head section-head-inline",children:[e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"Latest sync"}),e.jsxs("h2",{className:"flex items-center gap-2",children:["Release sync",e.jsx(h,{label:"What is a release sync?",children:"A release sync downloads one Common Crawl dump (~16 GB) and extracts backlinks for every project in this workspace in one pass. This is the heavy job — subsequent per-project re-runs skip the download and just re-query the cached files."})]})]}),t&&e.jsx(f,{tone:v(t.status),children:t.status})]}),e.jsxs(l,{className:"surface-card p-5",children:[e.jsxs("p",{className:"text-xs text-zinc-500 max-w-3xl mb-4",children:["A release is one Common Crawl dump (e.g. ",e.jsx("code",{className:"text-zinc-400",children:"cc-main-2026-jan-feb-mar"}),"). Syncing it downloads the graph and populates backlinks for every project in this workspace."]}),t?e.jsxs("div",{className:"space-y-2 text-sm",children:[e.jsxs("p",{className:"text-zinc-200",children:["Release ",e.jsx("code",{className:"text-zinc-300",children:t.release})]}),t.phaseDetail&&e.jsx("p",{className:"text-zinc-500",children:t.phaseDetail}),e.jsxs("div",{className:"grid grid-cols-2 md:grid-cols-4 gap-4 text-xs text-zinc-500 pt-2",children:[e.jsxs("div",{children:[e.jsx("p",{className:"text-zinc-600 uppercase tracking-wide",children:"Projects"}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:t.projectsProcessed??"—"})]}),e.jsxs("div",{children:[e.jsxs("p",{className:"text-zinc-600 uppercase tracking-wide flex items-center gap-1",children:["Rows",e.jsx(h,{label:"What are rows?",children:"Total number of (project, referring domain) pairs persisted in SQLite from this sync, across every project in the workspace."})]}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:t.domainsDiscovered??"—"})]}),e.jsxs("div",{children:[e.jsx("p",{className:"text-zinc-600 uppercase tracking-wide",children:"Started"}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:b(t.downloadStartedAt??t.createdAt)})]}),e.jsxs("div",{children:[e.jsx("p",{className:"text-zinc-600 uppercase tracking-wide",children:"Finished"}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:b(t.queryFinishedAt)})]})]}),t.error&&e.jsx("p",{className:"text-sm text-rose-400 pt-2",children:t.error})]}):e.jsx("p",{className:"text-sm text-zinc-500",children:"No release sync has run in this workspace yet."}),G&&e.jsx("div",{className:"mt-4 rounded border border-amber-800/60 bg-amber-950/20 p-3",children:e.jsxs("div",{className:"flex items-start gap-2",children:[e.jsx(L,{className:"h-4 w-4 text-amber-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{className:"text-xs text-zinc-300 leading-relaxed",children:[e.jsx("p",{className:"font-medium text-amber-200",children:"Cached files for this release are missing."}),e.jsxs("p",{className:"mt-1 text-zinc-400",children:["The sync record in the database says this release finished successfully, but the ~16 GB dump at"," ",e.jsxs("code",{className:"text-zinc-300",children:["~/.canonry/cache/commoncrawl/",t?.release,"/"]})," isn’t on disk. Your backlink data is still intact (it lives in SQLite), but per-project re-run extracts will fail until you either re-sync this release or start a new one."]})]})]})}),e.jsxs("div",{className:"mt-4 rounded border border-zinc-800 bg-zinc-900/40 p-3",children:[e.jsxs("div",{className:"flex items-start justify-between gap-3 mb-3",children:[e.jsxs("div",{children:[e.jsx("p",{className:"text-[10px] uppercase tracking-wide text-zinc-500",children:"Auto-detected release"}),u?e.jsxs("p",{className:"text-sm text-zinc-200 mt-0.5",children:[e.jsx("code",{className:"text-zinc-100",children:u.release}),e.jsxs("span",{className:"ml-2 text-xs text-zinc-500",children:["— vertex ",w(u.vertexBytes),", edges ",w(u.edgesBytes)]})]}):e.jsx("p",{className:"text-sm text-zinc-500 mt-0.5",children:D?"Probing Common Crawl…":"Could not auto-detect — pass an explicit release below."}),e.jsxs("a",{href:oe,target:"_blank",rel:"noopener noreferrer",className:"mt-1 inline-flex items-center gap-1 text-xs text-zinc-400 hover:text-zinc-200 focus:text-zinc-200 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500 rounded",children:["Browse all Common Crawl web-graph releases",e.jsx(de,{className:"h-3 w-3","aria-hidden":!0})]})]}),e.jsxs("div",{className:"flex items-center gap-2 shrink-0",children:[e.jsxs(z,{type:"button",size:"sm",disabled:p||!a?.duckdbInstalled||!u&&!N.trim(),onClick:A(T),children:[e.jsx(J,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),p?"Queuing…":"Run sync"]}),e.jsxs(h,{label:"What does Run sync do?",children:[e.jsxs("span",{className:"block",children:["Downloads the auto-detected (or chosen) Common Crawl release (~16 GB) to"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/"}),", then runs a single DuckDB query that extracts referring domains for every project in this workspace."]}),e.jsxs("span",{className:"mt-2 block text-zinc-400",children:["First time for a release: ",e.jsx("span",{className:"text-zinc-200",children:"~10–20 min download + ~5 min query"}),". Re-running the same release later: ",e.jsx("span",{className:"text-zinc-200",children:"skips download, just re-queries"})," (~5 min)."]})]})]})]}),F?e.jsxs("div",{className:"flex flex-wrap items-center gap-2",children:[e.jsx("input",{type:"text",className:"flex-1 min-w-[240px] rounded border border-zinc-700 bg-transparent px-2.5 py-1.5 text-sm text-zinc-200 placeholder-zinc-600 focus:border-zinc-500 focus:outline-none",placeholder:"cc-main-2026-jan-feb-mar",value:N,onChange:s=>g(s.target.value),disabled:p,autoFocus:!0}),e.jsx("button",{type:"button",className:"text-xs text-zinc-500 hover:text-zinc-300 focus:text-zinc-300 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500 rounded",onClick:()=>{g(""),k(!1)},disabled:p,children:"Cancel"})]}):e.jsx("button",{type:"button",className:"text-xs text-zinc-500 hover:text-zinc-300 focus:text-zinc-300 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500 rounded",onClick:()=>k(!0),disabled:p,children:"Use a different release →"})]}),!a?.duckdbInstalled&&e.jsx("p",{className:"text-xs text-zinc-600 mt-2",children:"Install DuckDB first to enable sync."})]})]}),e.jsxs("section",{className:"page-section-divider",children:[e.jsx("div",{className:"section-head section-head-inline",children:e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"Cached releases"}),e.jsxs("h2",{className:"flex items-center gap-2",children:["Local disk cache",e.jsxs(h,{label:"What is this?",children:[e.jsxs("span",{className:"block",children:["Raw Common Crawl dumps stored at"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/<release>/"}),". Each release takes ~16 GB."]}),e.jsxs("span",{className:"mt-2 block text-zinc-400",children:["These files are needed to re-run per-project extracts against a release without re-downloading. Pruning here ",e.jsx("span",{className:"text-zinc-200",children:"does not delete your backlink data"})," — that lives in SQLite."]})]})]})]})}),e.jsx("p",{className:"text-xs text-zinc-500 mb-3 max-w-3xl",children:"Each cached release is a ~16 GB pair of gzipped files. They’re needed to re-query the graph (e.g. for a newly-added project) without re-downloading. Safe to prune — backlink results persist in SQLite."}),e.jsx(l,{className:"surface-card overflow-hidden",children:e.jsxs("table",{className:"w-full text-sm",children:[e.jsx("thead",{children:e.jsxs("tr",{className:"border-b border-zinc-800 text-left text-xs uppercase tracking-wide text-zinc-600",children:[e.jsx("th",{className:"px-4 py-2 font-medium",children:"Release"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Sync status"}),e.jsx("th",{className:"px-4 py-2 text-right font-medium",children:"Size"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Last used"}),e.jsx("th",{className:"px-4 py-2 font-medium sr-only",children:"Actions"})]})}),e.jsxs("tbody",{children:[r.map(s=>e.jsxs("tr",{className:"border-b border-zinc-900 last:border-0",children:[e.jsx("td",{className:"px-4 py-2 text-zinc-200",children:e.jsx("code",{children:s.release})}),e.jsx("td",{className:"px-4 py-2",children:s.syncStatus?e.jsx(f,{tone:v(s.syncStatus),children:s.syncStatus}):e.jsx("span",{className:"text-zinc-600",children:"—"})}),e.jsx("td",{className:"px-4 py-2 text-right text-zinc-400 tabular-nums",children:w(s.bytes)}),e.jsx("td",{className:"px-4 py-2 text-zinc-400",children:b(s.lastUsedAt)}),e.jsx("td",{className:"px-4 py-2 text-right",children:e.jsxs("div",{className:"inline-flex items-center gap-1",children:[e.jsxs(z,{type:"button",variant:"outline",size:"sm",onClick:()=>{Q(s.release)},children:[e.jsx(ne,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),"Prune"]}),e.jsx(h,{label:"What does Prune do?",placement:"top",children:"Deletes the ~16 GB cache for this release from disk. Backlink results already in SQLite remain untouched. To re-run extracts against this release, you’d have to sync it again (another ~16 GB download)."})]})})]},s.release)),r.length===0&&e.jsx("tr",{children:e.jsx("td",{className:"px-4 py-4 text-sm text-zinc-500",colSpan:5,children:"No cached releases on this machine. If you ran a sync from a different machine (or deleted the cache), the backlink data is still in the database — but you’ll need to re-sync a release to run new extracts."})})]})]})})]}),o.length>1&&e.jsxs("section",{className:"page-section-divider",children:[e.jsx("div",{className:"section-head section-head-inline",children:e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"History"}),e.jsx("h2",{children:"Past release syncs"})]})}),e.jsx(l,{className:"surface-card overflow-hidden",children:e.jsxs("table",{className:"w-full text-sm",children:[e.jsx("thead",{children:e.jsxs("tr",{className:"border-b border-zinc-800 text-left text-xs uppercase tracking-wide text-zinc-600",children:[e.jsx("th",{className:"px-4 py-2 font-medium",children:"Release"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Status"}),e.jsx("th",{className:"px-4 py-2 text-right font-medium",children:"Projects"}),e.jsx("th",{className:"px-4 py-2 text-right font-medium",children:"Rows"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Finished"})]})}),e.jsx("tbody",{children:o.map(s=>e.jsxs("tr",{className:"border-b border-zinc-900 last:border-0",children:[e.jsx("td",{className:"px-4 py-2 text-zinc-200",children:e.jsx("code",{children:s.release})}),e.jsx("td",{className:"px-4 py-2",children:e.jsx(f,{tone:v(s.status),children:s.status})}),e.jsx("td",{className:"px-4 py-2 text-right text-zinc-400 tabular-nums",children:s.projectsProcessed??"—"}),e.jsx("td",{className:"px-4 py-2 text-right text-zinc-400 tabular-nums",children:s.domainsDiscovered??"—"}),e.jsx("td",{className:"px-4 py-2 text-zinc-400",children:b(s.queryFinishedAt??s.updatedAt)})]},s.id))})]})})]})]})}export{fe as BacklinksPage};
+import{r as n,j as e}from"./vendor-tanstack-Dq7p98wZ.js";import{c as E,bO as O,ae as V,bP as U,bQ as Y,bR as K,g as l,aH as L,T as f,B as z,i as A,an as J,bS as X,bT as Z,ah as ee,bU as se}from"./index-DzzTt20n.js";import{C as ae,D as te,T as ne,a as ce}from"./trash-2-uSttujvh.js";import"./vendor-radix-B57xfQbP.js";import"./vendor-recharts-ClRVR6aX.js";import"./vendor-markdown-DK7fbRNb.js";const ie=[["circle",{cx:"12",cy:"12",r:"10",key:"1mglay"}],["line",{x1:"12",x2:"12",y1:"8",y2:"12",key:"1pkeuh"}],["line",{x1:"12",x2:"12.01",y1:"16",y2:"16",key:"4dfq90"}]],re=E("circle-alert",ie);const le=[["path",{d:"M15 3h6v6",key:"1q9fwt"}],["path",{d:"M10 14 21 3",key:"gplh6r"}],["path",{d:"M18 13v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6",key:"a6xqqp"}]],de=E("external-link",le);function h({children:a,label:m="More info",placement:t="top",className:d}){const o=n.useId(),[y,r]=n.useState(!1);return e.jsxs("span",{className:`relative inline-flex ${d??""}`,children:[e.jsx("button",{type:"button","aria-label":m,"aria-describedby":y?o:void 0,className:"inline-flex h-4 w-4 items-center justify-center rounded-full text-zinc-500 hover:text-zinc-200 focus:text-zinc-200 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500",onMouseEnter:()=>r(!0),onMouseLeave:()=>r(!1),onFocus:()=>r(!0),onBlur:()=>r(!1),children:e.jsx(ce,{className:"h-3.5 w-3.5","aria-hidden":!0})}),y&&e.jsx("span",{id:o,role:"tooltip",className:`absolute z-50 w-64 rounded border border-zinc-700 bg-zinc-900 px-3 py-2 text-xs font-normal leading-relaxed text-zinc-200 shadow-lg ${t==="top"?"bottom-full mb-2":"top-full mt-2"} left-1/2 -translate-x-1/2 whitespace-normal`,children:a})]})}const oe="https://commoncrawl.org/web-graphs";function w(a){return a==null?"—":a>=1e12?`${(a/1e12).toFixed(1)} TB`:a>=1e9?`${(a/1e9).toFixed(1)} GB`:a>=1e6?`${(a/1e6).toFixed(1)} MB`:a>=1e3?`${(a/1e3).toFixed(1)} KB`:`${a} B`}function b(a){if(!a)return"—";const m=Date.now()-new Date(a).getTime(),t=Math.floor(m/6e4);if(t<1)return"just now";if(t<60)return`${t}m ago`;const d=Math.floor(t/60);return d<24?`${d}h ago`:`${Math.floor(d/24)}d ago`}function v(a){switch(a){case"ready":return"positive";case"failed":return"negative";case"downloading":case"querying":case"queued":return"caution"}}function fe(){const[a,m]=n.useState(null),[t,d]=n.useState(null),[o,y]=n.useState([]),[r,P]=n.useState([]),[u,M]=n.useState(null),[D,S]=n.useState(!0),[C,B]=n.useState(!1),[p,R]=n.useState(!1),[N,g]=n.useState(""),[F,k]=n.useState(!1),[q,i]=n.useState(null),[I,x]=n.useState(null),j=n.useCallback(async()=>{S(!0),i(null);try{const[s,c,_,H,W]=await Promise.all([O(),V().catch(()=>null),U().catch(()=>[]),Y().catch(()=>[]),K().catch(()=>null)]);m(s),d(c),y(_),P(H),M(W)}catch(s){i(s instanceof Error?s.message:"Failed to load backlinks status")}finally{S(!1)}},[]);n.useEffect(()=>{j()},[j]);async function T(){B(!0),i(null),x(null);try{const s=await X();x(s.alreadyPresent?`DuckDB already installed (${s.version}).`:`Installed DuckDB ${s.version}.`),await j()}catch(s){i(s instanceof Error?s.message:"Failed to install DuckDB")}finally{B(!1)}}async function $(){const s=N.trim()||void 0;R(!0),i(null),x(null);try{const c=await Z(s);x(s?`Queued sync for ${c.release}. Download + query runs in the background.`:`Queued sync for auto-discovered release ${c.release}. Download + query runs in the background.`),g(""),k(!1),await j()}catch(c){c instanceof ee&&c.code==="MISSING_DEPENDENCY"?i("DuckDB is not installed. Install it first."):i(c instanceof Error?c.message:"Failed to trigger sync")}finally{R(!1)}}async function Q(s){i(null),x(null);try{await se(s),x(`Pruned cached release ${s}.`),await j()}catch(c){i(c instanceof Error?c.message:"Failed to prune release")}}const G=t?.status==="ready"&&r.every(s=>s.release!==t.release);return e.jsxs("div",{className:"page-container",children:[e.jsx("div",{className:"page-header",children:e.jsxs("div",{className:"page-header-left",children:[e.jsx("h1",{className:"page-title",children:"Backlinks"}),e.jsx("p",{className:"page-subtitle",children:"Find domains that link to your projects, computed from the open Common Crawl web graph. Runs entirely on your machine — nothing is sent to third parties."})]})}),e.jsx(l,{className:"surface-card p-4 mb-6 border-amber-800/60",children:e.jsxs("div",{className:"flex items-start gap-3",children:[e.jsx(L,{className:"h-5 w-5 text-amber-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{className:"text-sm text-zinc-300 leading-relaxed",children:[e.jsx("p",{className:"font-medium text-amber-200",children:"Heads up — a release sync is a large download."}),e.jsxs("ul",{className:"mt-1.5 space-y-1 text-zinc-400",children:[e.jsxs("li",{children:[e.jsx("span",{className:"text-zinc-200",children:"~16 GB"})," of gzipped vertex + edge files per release, stored at"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/"}),"."]}),e.jsxs("li",{children:[e.jsx("span",{className:"text-zinc-200",children:"10–20 min on a fast connection"})," for the download, then ~5 min for the DuckDB query."]}),e.jsx("li",{children:"One sync covers every project in this workspace. Releases are immutable, so the download only happens once per release."})]})]})]})}),e.jsxs("section",{className:"page-section-divider",children:[e.jsx("div",{className:"section-head section-head-inline",children:e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"About"}),e.jsx("h2",{children:"How it works"})]})}),e.jsxs(l,{className:"surface-card p-5",children:[e.jsxs("p",{className:"text-sm text-zinc-400 leading-relaxed max-w-3xl mb-4",children:["Common Crawl publishes a quarterly snapshot of the public web’s hyperlink graph. Canonry downloads one"," ",e.jsx("span",{className:"text-zinc-200",children:"release"})," at a time and extracts backlinks for every project in this workspace in a single pass."]}),e.jsxs("ol",{className:"space-y-3 text-sm text-zinc-400 max-w-3xl",children:[e.jsxs("li",{className:"flex gap-3",children:[e.jsx("span",{className:"shrink-0 inline-flex h-6 w-6 items-center justify-center rounded-full border border-zinc-700 bg-zinc-900 text-xs font-semibold text-zinc-300 tabular-nums",children:"1"}),e.jsxs("span",{children:[e.jsx("span",{className:"text-zinc-200 font-medium",children:"Download (one-time, ~16 GB)"})," — vertex + edge files cached to"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/"}),". Runs once per release; subsequent operations reuse the cache."]})]}),e.jsxs("li",{className:"flex gap-3",children:[e.jsx("span",{className:"shrink-0 inline-flex h-6 w-6 items-center justify-center rounded-full border border-zinc-700 bg-zinc-900 text-xs font-semibold text-zinc-300 tabular-nums",children:"2"}),e.jsxs("span",{children:[e.jsx("span",{className:"text-zinc-200 font-medium",children:"Query (~5 min)"})," — one DuckDB pass scans the cached files and extracts referring domains for every project’s canonical domain. DuckDB is only used to ",e.jsx("span",{className:"text-zinc-200",children:"read"})," these dumps; it doesn’t store any canonry state."]})]}),e.jsxs("li",{className:"flex gap-3",children:[e.jsx("span",{className:"shrink-0 inline-flex h-6 w-6 items-center justify-center rounded-full border border-zinc-700 bg-zinc-900 text-xs font-semibold text-zinc-300 tabular-nums",children:"3"}),e.jsxs("span",{children:[e.jsx("span",{className:"text-zinc-200 font-medium",children:"Persist"})," — results land in the same SQLite database the rest of canonry uses. After the first sync, per-project reads (and re-run extracts against the cached release) are instant."]})]})]})]})]}),q&&e.jsx(l,{className:"surface-card p-4 mb-4 border-rose-800/60",children:e.jsx("p",{className:"text-sm text-rose-300",children:q})}),I&&e.jsx(l,{className:"surface-card p-4 mb-4 border-emerald-800/60",children:e.jsx("p",{className:"text-sm text-emerald-300",children:I})}),e.jsxs("section",{className:"page-section-divider",children:[e.jsxs("div",{className:"section-head section-head-inline",children:[e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"Dependency"}),e.jsxs("h2",{className:"flex items-center gap-2",children:["DuckDB install status",e.jsxs(h,{label:"Why DuckDB?",children:[e.jsx("span",{className:"block",children:"DuckDB is a query engine canonry uses to scan the ~16 GB Common Crawl dumps and pull out your referring domains."}),e.jsxs("span",{className:"mt-2 block text-zinc-400",children:["It does ",e.jsx("span",{className:"text-zinc-200",children:"not"})," store any canonry data — your backlink results live in SQLite alongside the rest of your projects. DuckDB is purely a tool for processing the raw CSV files."]}),e.jsxs("span",{className:"mt-2 block text-zinc-500",children:["Installed on demand (not bundled) into ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/plugins/"})," so users who never run backlinks don’t pay the ~40 MB install cost."]})]})]})]}),a?.duckdbInstalled?e.jsx(f,{tone:"positive",children:"Installed"}):e.jsx(f,{tone:"caution",children:"Not installed"})]}),e.jsx(l,{className:"surface-card p-5",children:D?e.jsx("p",{className:"text-sm text-zinc-500",children:"Checking…"}):a?.duckdbInstalled?e.jsxs("div",{className:"flex items-start gap-3",children:[e.jsx(ae,{className:"h-5 w-5 text-emerald-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{children:[e.jsxs("p",{className:"text-sm text-zinc-200",children:["Version ",a.duckdbVersion??"unknown"," installed at"," ",e.jsx("code",{className:"text-zinc-300",children:a.pluginDir})]}),e.jsxs("p",{className:"text-xs text-zinc-500 mt-1",children:["Required spec: ",a.duckdbSpec]})]})]}):e.jsxs("div",{className:"flex items-start gap-3",children:[e.jsx(re,{className:"h-5 w-5 text-amber-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{className:"flex-1",children:[e.jsx("p",{className:"text-sm text-zinc-200",children:"DuckDB is not installed. It’s the query engine canonry uses to scan Common Crawl dumps — required before you can run a release sync or per-project extract."}),e.jsx("p",{className:"text-xs text-zinc-500 mt-1",children:"Installing doesn’t touch your project data. DuckDB only reads the downloaded CSV files; backlink results are written to the same SQLite database canonry already uses."}),a&&e.jsxs("p",{className:"text-xs text-zinc-500 mt-1",children:["Will be installed into ",e.jsx("code",{className:"text-zinc-300",children:a.pluginDir})," (~40 MB)."]}),e.jsx("div",{className:"mt-3",children:e.jsxs(z,{type:"button",size:"sm",disabled:C,onClick:A(T),children:[e.jsx(te,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),C?"Installing…":"Install DuckDB"]})})]})]})})]}),e.jsxs("section",{className:"page-section-divider",children:[e.jsxs("div",{className:"section-head section-head-inline",children:[e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"Latest sync"}),e.jsxs("h2",{className:"flex items-center gap-2",children:["Release sync",e.jsx(h,{label:"What is a release sync?",children:"A release sync downloads one Common Crawl dump (~16 GB) and extracts backlinks for every project in this workspace in one pass. This is the heavy job — subsequent per-project re-runs skip the download and just re-query the cached files."})]})]}),t&&e.jsx(f,{tone:v(t.status),children:t.status})]}),e.jsxs(l,{className:"surface-card p-5",children:[e.jsxs("p",{className:"text-xs text-zinc-500 max-w-3xl mb-4",children:["A release is one Common Crawl dump (e.g. ",e.jsx("code",{className:"text-zinc-400",children:"cc-main-2026-jan-feb-mar"}),"). Syncing it downloads the graph and populates backlinks for every project in this workspace."]}),t?e.jsxs("div",{className:"space-y-2 text-sm",children:[e.jsxs("p",{className:"text-zinc-200",children:["Release ",e.jsx("code",{className:"text-zinc-300",children:t.release})]}),t.phaseDetail&&e.jsx("p",{className:"text-zinc-500",children:t.phaseDetail}),e.jsxs("div",{className:"grid grid-cols-2 md:grid-cols-4 gap-4 text-xs text-zinc-500 pt-2",children:[e.jsxs("div",{children:[e.jsx("p",{className:"text-zinc-600 uppercase tracking-wide",children:"Projects"}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:t.projectsProcessed??"—"})]}),e.jsxs("div",{children:[e.jsxs("p",{className:"text-zinc-600 uppercase tracking-wide flex items-center gap-1",children:["Rows",e.jsx(h,{label:"What are rows?",children:"Total number of (project, referring domain) pairs persisted in SQLite from this sync, across every project in the workspace."})]}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:t.domainsDiscovered??"—"})]}),e.jsxs("div",{children:[e.jsx("p",{className:"text-zinc-600 uppercase tracking-wide",children:"Started"}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:b(t.downloadStartedAt??t.createdAt)})]}),e.jsxs("div",{children:[e.jsx("p",{className:"text-zinc-600 uppercase tracking-wide",children:"Finished"}),e.jsx("p",{className:"text-zinc-300 mt-0.5",children:b(t.queryFinishedAt)})]})]}),t.error&&e.jsx("p",{className:"text-sm text-rose-400 pt-2",children:t.error})]}):e.jsx("p",{className:"text-sm text-zinc-500",children:"No release sync has run in this workspace yet."}),G&&e.jsx("div",{className:"mt-4 rounded border border-amber-800/60 bg-amber-950/20 p-3",children:e.jsxs("div",{className:"flex items-start gap-2",children:[e.jsx(L,{className:"h-4 w-4 text-amber-400 shrink-0 mt-0.5","aria-hidden":!0}),e.jsxs("div",{className:"text-xs text-zinc-300 leading-relaxed",children:[e.jsx("p",{className:"font-medium text-amber-200",children:"Cached files for this release are missing."}),e.jsxs("p",{className:"mt-1 text-zinc-400",children:["The sync record in the database says this release finished successfully, but the ~16 GB dump at"," ",e.jsxs("code",{className:"text-zinc-300",children:["~/.canonry/cache/commoncrawl/",t?.release,"/"]})," isn’t on disk. Your backlink data is still intact (it lives in SQLite), but per-project re-run extracts will fail until you either re-sync this release or start a new one."]})]})]})}),e.jsxs("div",{className:"mt-4 rounded border border-zinc-800 bg-zinc-900/40 p-3",children:[e.jsxs("div",{className:"flex items-start justify-between gap-3 mb-3",children:[e.jsxs("div",{children:[e.jsx("p",{className:"text-[10px] uppercase tracking-wide text-zinc-500",children:"Auto-detected release"}),u?e.jsxs("p",{className:"text-sm text-zinc-200 mt-0.5",children:[e.jsx("code",{className:"text-zinc-100",children:u.release}),e.jsxs("span",{className:"ml-2 text-xs text-zinc-500",children:["— vertex ",w(u.vertexBytes),", edges ",w(u.edgesBytes)]})]}):e.jsx("p",{className:"text-sm text-zinc-500 mt-0.5",children:D?"Probing Common Crawl…":"Could not auto-detect — pass an explicit release below."}),e.jsxs("a",{href:oe,target:"_blank",rel:"noopener noreferrer",className:"mt-1 inline-flex items-center gap-1 text-xs text-zinc-400 hover:text-zinc-200 focus:text-zinc-200 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500 rounded",children:["Browse all Common Crawl web-graph releases",e.jsx(de,{className:"h-3 w-3","aria-hidden":!0})]})]}),e.jsxs("div",{className:"flex items-center gap-2 shrink-0",children:[e.jsxs(z,{type:"button",size:"sm",disabled:p||!a?.duckdbInstalled||!u&&!N.trim(),onClick:A($),children:[e.jsx(J,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),p?"Queuing…":"Run sync"]}),e.jsxs(h,{label:"What does Run sync do?",children:[e.jsxs("span",{className:"block",children:["Downloads the auto-detected (or chosen) Common Crawl release (~16 GB) to"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/"}),", then runs a single DuckDB query that extracts referring domains for every project in this workspace."]}),e.jsxs("span",{className:"mt-2 block text-zinc-400",children:["First time for a release: ",e.jsx("span",{className:"text-zinc-200",children:"~10–20 min download + ~5 min query"}),". Re-running the same release later: ",e.jsx("span",{className:"text-zinc-200",children:"skips download, just re-queries"})," (~5 min)."]})]})]})]}),F?e.jsxs("div",{className:"flex flex-wrap items-center gap-2",children:[e.jsx("input",{type:"text",className:"flex-1 min-w-[240px] rounded border border-zinc-700 bg-transparent px-2.5 py-1.5 text-sm text-zinc-200 placeholder-zinc-600 focus:border-zinc-500 focus:outline-none",placeholder:"cc-main-2026-jan-feb-mar",value:N,onChange:s=>g(s.target.value),disabled:p,autoFocus:!0}),e.jsx("button",{type:"button",className:"text-xs text-zinc-500 hover:text-zinc-300 focus:text-zinc-300 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500 rounded",onClick:()=>{g(""),k(!1)},disabled:p,children:"Cancel"})]}):e.jsx("button",{type:"button",className:"text-xs text-zinc-500 hover:text-zinc-300 focus:text-zinc-300 focus:outline-none focus-visible:ring-1 focus-visible:ring-zinc-500 rounded",onClick:()=>k(!0),disabled:p,children:"Use a different release →"})]}),!a?.duckdbInstalled&&e.jsx("p",{className:"text-xs text-zinc-600 mt-2",children:"Install DuckDB first to enable sync."})]})]}),e.jsxs("section",{className:"page-section-divider",children:[e.jsx("div",{className:"section-head section-head-inline",children:e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"Cached releases"}),e.jsxs("h2",{className:"flex items-center gap-2",children:["Local disk cache",e.jsxs(h,{label:"What is this?",children:[e.jsxs("span",{className:"block",children:["Raw Common Crawl dumps stored at"," ",e.jsx("code",{className:"text-zinc-300",children:"~/.canonry/cache/commoncrawl/<release>/"}),". Each release takes ~16 GB."]}),e.jsxs("span",{className:"mt-2 block text-zinc-400",children:["These files are needed to re-run per-project extracts against a release without re-downloading. Pruning here ",e.jsx("span",{className:"text-zinc-200",children:"does not delete your backlink data"})," — that lives in SQLite."]})]})]})]})}),e.jsx("p",{className:"text-xs text-zinc-500 mb-3 max-w-3xl",children:"Each cached release is a ~16 GB pair of gzipped files. They’re needed to re-query the graph (e.g. for a newly-added project) without re-downloading. Safe to prune — backlink results persist in SQLite."}),e.jsx(l,{className:"surface-card overflow-hidden",children:e.jsxs("table",{className:"w-full text-sm",children:[e.jsx("thead",{children:e.jsxs("tr",{className:"border-b border-zinc-800 text-left text-xs uppercase tracking-wide text-zinc-600",children:[e.jsx("th",{className:"px-4 py-2 font-medium",children:"Release"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Sync status"}),e.jsx("th",{className:"px-4 py-2 text-right font-medium",children:"Size"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Last used"}),e.jsx("th",{className:"px-4 py-2 font-medium sr-only",children:"Actions"})]})}),e.jsxs("tbody",{children:[r.map(s=>e.jsxs("tr",{className:"border-b border-zinc-900 last:border-0",children:[e.jsx("td",{className:"px-4 py-2 text-zinc-200",children:e.jsx("code",{children:s.release})}),e.jsx("td",{className:"px-4 py-2",children:s.syncStatus?e.jsx(f,{tone:v(s.syncStatus),children:s.syncStatus}):e.jsx("span",{className:"text-zinc-600",children:"—"})}),e.jsx("td",{className:"px-4 py-2 text-right text-zinc-400 tabular-nums",children:w(s.bytes)}),e.jsx("td",{className:"px-4 py-2 text-zinc-400",children:b(s.lastUsedAt)}),e.jsx("td",{className:"px-4 py-2 text-right",children:e.jsxs("div",{className:"inline-flex items-center gap-1",children:[e.jsxs(z,{type:"button",variant:"outline",size:"sm",onClick:()=>{Q(s.release)},children:[e.jsx(ne,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),"Prune"]}),e.jsx(h,{label:"What does Prune do?",placement:"top",children:"Deletes the ~16 GB cache for this release from disk. Backlink results already in SQLite remain untouched. To re-run extracts against this release, you’d have to sync it again (another ~16 GB download)."})]})})]},s.release)),r.length===0&&e.jsx("tr",{children:e.jsx("td",{className:"px-4 py-4 text-sm text-zinc-500",colSpan:5,children:"No cached releases on this machine. If you ran a sync from a different machine (or deleted the cache), the backlink data is still in the database — but you’ll need to re-sync a release to run new extracts."})})]})]})})]}),o.length>1&&e.jsxs("section",{className:"page-section-divider",children:[e.jsx("div",{className:"section-head section-head-inline",children:e.jsxs("div",{children:[e.jsx("p",{className:"eyebrow eyebrow-soft",children:"History"}),e.jsx("h2",{children:"Past release syncs"})]})}),e.jsx(l,{className:"surface-card overflow-hidden",children:e.jsxs("table",{className:"w-full text-sm",children:[e.jsx("thead",{children:e.jsxs("tr",{className:"border-b border-zinc-800 text-left text-xs uppercase tracking-wide text-zinc-600",children:[e.jsx("th",{className:"px-4 py-2 font-medium",children:"Release"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Status"}),e.jsx("th",{className:"px-4 py-2 text-right font-medium",children:"Projects"}),e.jsx("th",{className:"px-4 py-2 text-right font-medium",children:"Rows"}),e.jsx("th",{className:"px-4 py-2 font-medium",children:"Finished"})]})}),e.jsx("tbody",{children:o.map(s=>e.jsxs("tr",{className:"border-b border-zinc-900 last:border-0",children:[e.jsx("td",{className:"px-4 py-2 text-zinc-200",children:e.jsx("code",{children:s.release})}),e.jsx("td",{className:"px-4 py-2",children:e.jsx(f,{tone:v(s.status),children:s.status})}),e.jsx("td",{className:"px-4 py-2 text-right text-zinc-400 tabular-nums",children:s.projectsProcessed??"—"}),e.jsx("td",{className:"px-4 py-2 text-right text-zinc-400 tabular-nums",children:s.domainsDiscovered??"—"}),e.jsx("td",{className:"px-4 py-2 text-zinc-400",children:b(s.queryFinishedAt??s.updatedAt)})]},s.id))})]})})]})]})}export{fe as BacklinksPage};

package/assets/assets/{ChartPrimitives-D2_IvTkk.js → ChartPrimitives-2Ub4vNWe.js}

@@ -1 +1 @@
-import{c as n}from"./index-EnY_OBRd.js";const r=[["path",{d:"m15 18-6-6 6-6",key:"1wnfg3"}]],s=n("chevron-left",r),f={contentStyle:{backgroundColor:"#18181b",border:"1px solid #3f3f46",borderRadius:8,fontSize:12},labelStyle:{color:"#e4e4e7"},itemStyle:{color:"#a1a1aa"}},d={fill:"#71717a",fontSize:11},l="#27272a",S="#27272a",a=["#34d399","#60a5fa","#f472b6","#facc15","#a78bfa","#fb923c","#22d3ee","#f87171"],c={gemini:"#60a5fa",openai:"#34d399",claude:"#fb923c",perplexity:"#22d3ee",local:"#a78bfa"};function R(t,e=0){return c[t]??a[e%a.length]}const T={text:"#a1a1aa",textDim:"#71717a",textFaint:"#52525b",surface:"#27272a"},u={positive:"#34d399",positiveDeep:"#10b981"};function o(t){const e=String(t);return e.includes("T")?new Date(e):new Date(e+"T00:00:00")}function C(t){return o(String(t)).toLocaleDateString(void 0,{month:"short",day:"numeric",year:"numeric"})}function _(t){const e=o(t);return`${e.getMonth()+1}/${e.getDate()}`}export{S as C,d as a,C as b,f as c,T as d,a as e,_ as f,u as g,s as h,l as i,R as p};
+import{c as n}from"./index-DzzTt20n.js";const r=[["path",{d:"m15 18-6-6 6-6",key:"1wnfg3"}]],s=n("chevron-left",r),f={contentStyle:{backgroundColor:"#18181b",border:"1px solid #3f3f46",borderRadius:8,fontSize:12},labelStyle:{color:"#e4e4e7"},itemStyle:{color:"#a1a1aa"}},d={fill:"#71717a",fontSize:11},l="#27272a",S="#27272a",a=["#34d399","#60a5fa","#f472b6","#facc15","#a78bfa","#fb923c","#22d3ee","#f87171"],c={gemini:"#60a5fa",openai:"#34d399",claude:"#fb923c",perplexity:"#22d3ee",local:"#a78bfa"};function R(t,e=0){return c[t]??a[e%a.length]}const T={text:"#a1a1aa",textDim:"#71717a",textFaint:"#52525b",surface:"#27272a"},u={positive:"#34d399",positiveDeep:"#10b981"};function o(t){const e=String(t);return e.includes("T")?new Date(e):new Date(e+"T00:00:00")}function C(t){return o(String(t)).toLocaleDateString(void 0,{month:"short",day:"numeric",year:"numeric"})}function _(t){const e=o(t);return`${e.getMonth()+1}/${e.getDate()}`}export{S as C,d as a,C as b,f as c,T as d,a as e,_ as f,u as g,s as h,l as i,R as p};