@ainyc/canonry 4.64.1 → 4.68.1

package/README.md

@@ -8,6 +8,7 @@
 - Watch AI engines crawl and refer traffic via [server-log ingestion](skills/canonry/references/server-side-traffic.md) — Cloud Run, Vercel, and the WordPress Traffic Logger plugin today
 - Diagnose against real traffic with built-in [GSC](docs/google-search-console-setup.md), [GA4](docs/google-analytics-setup.md), and [Bing Webmaster](docs/bing-webmaster-setup.md)
 - Track local AEO via [Google Business Profile](skills/canonry/references/google-business-profile.md) — search-term impressions, performance metrics, and hotel lodging + booking-CTA gaps
+- Discover who links to you with [Common Crawl backlinks](skills/canonry/references/canonry-cli.md#backlinks-common-crawl) — follows Common Crawl's rolling monthly hyperlink graph, auto-syncing each new window on a schedule, queried locally with DuckDB
 - Execute fixes via [WordPress](docs/wordpress-setup.md), JSON-LD schema, and indexing submissions
 - Manage many clients declaratively — config-as-code YAML + `cnry apply`
 - Schedule recurring visibility checks, traffic syncs, and Business Profile syncs, with webhook alerts on regressions

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

@@ -186,6 +186,7 @@ cnry competitor list <project>
 cnry schedule set <project> --preset daily     # or: weekly, twice-daily, daily@09
 cnry schedule set <project> --cron "0 9 * * *" --timezone America/New_York
 cnry schedule set <project> --kind data-refresh --preset daily   # refresh all connected GSC/Bing/GA/GBP integrations (no --source)
+cnry schedule set <project> --kind backlinks-sync --preset weekly # re-probe Common Crawl; sync only when a newer rolling window is published (no --source/--provider)
 cnry schedule show <project>
 cnry schedule enable <project>
 cnry schedule disable <project>
@@ -416,12 +417,16 @@ cnry gbp summary <project> [--location locations/{n}]
 
 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 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.
+
 ```bash
 cnry backlinks install                         # install bundled DuckDB binary
 cnry backlinks doctor                          # show install + plugin status
 cnry backlinks status                          # latest workspace release sync
 cnry backlinks releases                        # list cached releases on disk
-cnry backlinks sync --release <id>             # download + query a release (workspace-wide)
+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 list <project> --limit 100 --release <id>
@@ -432,6 +437,8 @@ cnry backlinks cache prune --release <id>      # delete cached release files fro
 
 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`.
 
+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).
+
 ## CDP / Browser Provider
 
 The CDP (Chrome DevTools Protocol) provider enables browser-based queries against AI chat interfaces (e.g., ChatGPT). This gives more accurate results than API-based providers for some use cases.
@@ -524,4 +531,33 @@ cnry agent detach <project> --format json              # JSON output
 
 ## Output Formats
 
-Most commands support `--format json` for machine-readable output.
+Every command takes `--format`:
+
+- **`text`** (default) — human-readable, decorated. Not a stable parse target.
+- **`json`** — one pretty-printed JSON document (the full envelope). Stable contract.
+- **`jsonl`** — newline-delimited JSON: the command's **primary collection**, one self-contained record per line. The agent-friendly machine format — no envelope key to guess (`.checks` vs `.results` vs `.rows`), no `jq` flattening, greppable line by line.
+
+`jsonl` is supported by every **collection** command — one whose primary output is a list: `insights`, `runs`, `evidence`, `history`, `query/keyword/competitor list`, `notify list/events`, `google` reads (`performance`, `performance-daily`, `inspections`, `coverage-history`, `deindexed`, `status`, `properties`, `list-sitemaps`), `bing` reads (`coverage-history`, `inspections`, `performance`, `sites`), `ga` reads (`ai-referral-history`, `social-referral-history`, `session-history`, `coverage`), `traffic events/sources/status`, `discover list/show`, `content targets/sources/gaps`, `backlinks list/releases`, `project list/locations`, `agent memory list`, `agent providers`, and `doctor`.
+
+Each `jsonl` line re-injects the envelope context it would otherwise lose, so a line lifted out still self-describes:
+
+- project-scoped lists stamp `{ "project": "<name>", …row }`;
+- `ga *-history` also stamps `window`; `traffic events` stamps `windowStart`/`windowEnd`; `backlinks list` stamps `release`/`targetDomain`; `discover show` stamps `sessionId`; `content targets` stamps `latestRunId`; `project locations` stamps `isDefault`;
+- global lists whose rows already self-identify (`project list`, `notify events`, `backlinks releases`) emit bare rows.
+
+Empty collection → **no output** (the exit code still conveys success, so "no records" stays distinct from "failure"). On failure a command prints its records (if any), then exits non-zero — branch on the **exit code**, never on parsing stderr. JSON field names and the `{ "error": { "code", "message" } }` envelope are a public contract.
+
+**Composite** commands return a single aggregate object (not a list), so there is nothing to stream — on them `--format jsonl` **degrades to the same JSON document** as `--format json`; it never falls through to decorated human text. So `--format jsonl` is safe to pass to *any* command: collection commands stream their records, every other command emits its JSON document. Composite shapes are below.
+
+## Output schema per command
+
+Compact reference for the composite / keyed commands agents read most (shapes can drift — the linked DTO source file is the source of truth; collection commands simply emit their primary array, see each command's own section above).
+
+| Command | JSON output shape (top-level keys → DTO) | `jsonl` |
+|---|---|---|
+| `cnry doctor [--project p] [--all]` | `{ scope, project, generatedAt, durationMs, summary{total,ok,warn,fail,skipped}, checks[] }` — `DoctorReportDto` @ `contracts/doctor.ts`. `checks[]` = `CheckResultDto{ id, category, scope, title, status(ok\|warn\|fail\|skipped), code, summary, remediation?, details?, durationMs }`. With `--all`: an object keyed by `__global__` + each project name, each value a full report. | ✅ one check / line as `{project, …check}`; still exits non-zero if any `fail` |
+| `cnry analytics <p> [--feature metrics\|gaps\|sources] [--window 7d\|30d\|90d\|all]` | Object **keyed by feature**: `{ metrics?, gaps?, sources? }` (all three present with no `--feature`; one with `--feature X`). `metrics`=`BrandMetricsDto{ window, buckets[], overall, byProvider, trend, mentionTrend, queryChanges[] }`; `gaps`=`GapAnalysisDto{ cited[], gap[], uncited[], mentionedQueries[], mentionGap[], notMentioned[], runId, window }` (each `[]`=`GapQuery`); `sources`=`SourceBreakdownDto{ overall[], byQuery, runId, window }`. @ `contracts/analytics.ts` | → degrades to the `json` document |
+| `cnry google coverage <p>` (index coverage) | `{ summary{total,indexed,notIndexed,deindexed,percentage}, lastInspectedAt, lastSyncedAt, indexed[], notIndexed[], deindexed[], reasonGroups[] }` — `GscCoverageSummaryDto` @ `contracts/google.ts`. `indexed[]`/`notIndexed[]`=`GscUrlInspectionDto`, `deindexed[]`=`GscDeindexedRowDto`. | → degrades to the `json` document. The single-array reads `google inspections` / `coverage-history` / `deindexed` **stream** `jsonl`. |
+| `cnry ga traffic <p> [--window …]` | Object summary — `GA4TrafficSummaryDto` / `GaTrafficResponse` @ `contracts/ga.ts`: `{ totalSessions, totalOrganicSessions, totalDirectSessions, totalUsers, aiSessionsDeduped, aiUsersDeduped, aiSessionsBySession, aiUsersBySession, socialSessions, socialUsers, channelBreakdown{organic,social,direct,ai,other→{sessions,sharePct,sharePctDisplay}}, *SharePct (+ `*Display`), topPages[], aiReferrals[], aiReferralLandingPages[], socialReferrals[], lastSyncedAt, periodStart, periodEnd }`. | → degrades to the `json` document |
+| `cnry ga attribution <p> [--trend]` | Object — a **renamed projection** of `GaTrafficResponse` (⚠️ field names differ from the DTO): `aiSessions`(←`aiSessionsDeduped`), `organicSessions`(←`totalOrganicSessions`), `directSessions`(←`totalDirectSessions`), plus `totalSessions, totalUsers, aiUsers, aiSessionsBySession, aiUsersBySession, socialSessions, socialUsers, {ai,social,organic,direct}SharePct (+ `*Display`), otherSessions, otherSharePct, channelBreakdown, aiReferrals[], aiReferralLandingPages[], socialReferrals[], periodStart, periodEnd`. With `--trend`: drops `periodStart/End`, adds `trend` (`GaAttributionTrendResponse`). Assembled inline in `commands/ga.ts`. | → degrades to the `json` document |
+| `cnry gbp summary <p> [--location …]` | `{ scope{locationName,locationCount}, performance{totals,recent7d,prior7d,deltaPct} (metric-keyed maps; keys are raw `BUSINESS_*` / `WEBSITE_CLICKS` tokens — label via `formatGbpMetricLabel`), freshness{dataThroughDate,latestStoredDate,pendingDays}, timeseries[], keywords{total,thresholdedCount,thresholdedPct}, placeActions{total,hasReservationCta,hasBookingCta,hasDirectMerchantCta}, lodging{lodgingLocationCount,populatedLodgingCount,emptyLodgingCount} }` — `GbpSummaryDto` @ `contracts/gbp.ts`. `timeseries[]`=`{date,pending,metrics}`. | → degrades to the `json` document |

package/assets/assets/{BacklinksPage-B9oyoljV.js → BacklinksPage-B9Q2r9zM.js}

@@ -1 +1 @@
-import{r as n,j as e}from"./vendor-tanstack-Dq7p98wZ.js";import{c as E,bx as O,a8 as V,by as U,bz as Y,bA as K,g as l,bB as L,T as f,B as z,i as A,ah as J,bC as X,bD as Z,ab as ee,bE as se}from"./index-DiN_mzYU.js";import{C as ae,D as te,T as ne,a as ce}from"./trash-2-CVKno2W2.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,C]=n.useState(!0),[B,S]=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()=>{C(!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{C(!1)}},[]);n.useEffect(()=>{j()},[j]);async function $(){S(!0),i(null),x(null);try{const s=await X();x(s.alreadyPresent?`DuckDB already installed (${s.version}).`:`Installed DuckDB ${s.version}.`),await j()}catch(s){i(s instanceof Error?s.message:"Failed to install DuckDB")}finally{S(!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:B,onClick:A($),children:[e.jsx(te,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),B?"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,by as O,a8 as V,bz as U,bA as Y,bB as K,g as l,bC as L,T as f,B as z,i as A,ah as J,bD as X,bE as Z,ab as ee,bF as se}from"./index-DFo2OL9c.js";import{C as ae,D as te,T as ne,a as ce}from"./trash-2-C4sYVIa6.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,F]=n.useState([]),[u,M]=n.useState(null),[D,C]=n.useState(!0),[B,S]=n.useState(!1),[p,R]=n.useState(!1),[N,g]=n.useState(""),[P,k]=n.useState(!1),[q,i]=n.useState(null),[I,x]=n.useState(null),j=n.useCallback(async()=>{C(!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(_),F(W),M(H)}catch(s){i(s instanceof Error?s.message:"Failed to load backlinks status")}finally{C(!1)}},[]);n.useEffect(()=>{j()},[j]);async function $(){S(!0),i(null),x(null);try{const s=await X();x(s.alreadyPresent?`DuckDB already installed (${s.version}).`:`Installed DuckDB ${s.version}.`),await j()}catch(s){i(s instanceof Error?s.message:"Failed to install DuckDB")}finally{S(!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:B,onClick:A($),children:[e.jsx(te,{className:"h-4 w-4 mr-1.5","aria-hidden":!0}),B?"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)."]})]})]})]}),P?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-D-YWOWK-.js

@@ -0,0 +1 @@
+import{c as o}from"./index-DFo2OL9c.js";const n=[["path",{d:"m15 18-6-6 6-6",key:"1wnfg3"}]],c=o("chevron-left",n),s={contentStyle:{backgroundColor:"#18181b",border:"1px solid #3f3f46",borderRadius:8,fontSize:12},labelStyle:{color:"#e4e4e7"},itemStyle:{color:"#a1a1aa"}},i={fill:"#71717a",fontSize:11},f="#27272a",d="#27272a",T=["#34d399","#60a5fa","#f472b6","#facc15","#a78bfa","#fb923c","#22d3ee","#f87171"],S={text:"#a1a1aa",textDim:"#71717a",textFaint:"#52525b",surface:"#27272a"},l={positive:"#34d399",positiveDeep:"#10b981"};function a(e){const t=String(e);return t.includes("T")?new Date(t):new Date(t+"T00:00:00")}function C(e){return a(String(e)).toLocaleDateString(void 0,{month:"short",day:"numeric",year:"numeric"})}function u(e){const t=a(e);return`${t.getMonth()+1}/${t.getDate()}`}export{d as C,i as a,C as b,s as c,S as d,T as e,u as f,l as g,c as h,f as i};