@nanonets/graft 0.13.0 → 0.15.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@nanonets/graft",
-  "version": "0.13.0",
+  "version": "0.15.0",
   "description": "Build a repo's context graph as a folder of linked markdown files: a local, regenerable cache that every query keeps in sync with your code.",
   "keywords": [
     "ai",
@@ -67,8 +67,9 @@
     "tree-sitter-php": "^0.23.4",
     "tree-sitter-python": "^0.21.0",
     "tree-sitter-r": "npm:@davisvaughan/tree-sitter-r@^1.3.0",
+    "tree-sitter-swift": "^0.7.1",
     "tree-sitter-typescript": "^0.23.2",
-    "tree-sitter-wasm": "^1.1.4",
+    "tree-sitter-wasm": "^1.1.6",
     "vscode-jsonrpc": "^8.2.1",
     "vscode-languageserver-protocol": "^3.18.2",
     "web-tree-sitter": "^0.25.10"
@@ -78,6 +79,7 @@
     "@types/node": "^26.1.0",
     "d3-force": "^3.0.0",
     "esbuild": "^0.28.1",
+    "node-gyp": "^12.4.0",
     "tsx": "^4.22.4",
     "typescript": "^6.0.3"
   },
@@ -92,6 +94,12 @@
     "fsevents@2.3.3": true,
     "tree-sitter-kotlin@0.3.8": true,
     "tree-sitter-php@0.23.12": true,
-    "tree-sitter-r@1.3.0": true
+    "@davisvaughan/tree-sitter-r@1.3.0": true,
+    "tree-sitter-swift@0.7.1": true
+  },
+  "overrides": {
+    "tree-sitter-swift": {
+      "tree-sitter": "$tree-sitter"
+    }
   }
 }

package/scripts/graph-quality.mjs

@@ -48,8 +48,8 @@ for (const n of nodes) {
   else if (Number(m[1]) > Number(m[2])) problems.push(`inverted span ${n.span}: ${n.id}`);
 }
 // an edge target may be a node id OR a deliberately-unresolved external string
-// (import specifier / bare heritage name); only calls/references/contains must
-// point at real nodes.
+// (import specifier / bare heritage name / unresolved Java annotation type);
+// only calls/contains must point at real nodes.
 let dangling = 0, selfLoops = 0, unresolvedExternal = 0;
 for (const e of edges) {
   if (!RELATIONS.has(e.relation)) problems.push(`bad relation '${e.relation}'`);
@@ -57,7 +57,7 @@ for (const e of edges) {
   if (!ids.has(e.source)) { problems.push(`dangling source: ${e.source}`); dangling++; }
   const targetIsNode = ids.has(e.target);
   if (!targetIsNode) {
-    if (e.relation === "imports" || e.relation === "extends" || e.relation === "implements") unresolvedExternal++;
+    if (e.relation === "imports" || e.relation === "extends" || e.relation === "implements" || e.relation === "references") unresolvedExternal++;
     else { problems.push(`dangling ${e.relation} target: ${e.source} → ${e.target}`); dangling++; }
   }
   if (e.relation === "calls" && e.source === e.target) selfLoops++;

package/scripts/tally-audit.mjs

@@ -0,0 +1,140 @@
+/**
+ * "Saved vs said": how often does the agent actually TELL the user what graft saved?
+ *
+ *   node scripts/tally-audit.mjs [transcript-dir] [--json]
+ *
+ * `savedTokens` (src/claude/state.ts) counts what graft *computed* — every
+ * `[graft] tokens saved ≈ N` footer the PostToolUse accumulator swept up. This
+ * script measures the other half, offline and in full detail: of the turns that
+ * used graft, how many closed with the one-line tally SKILL.md asks for, was the
+ * number right, and did it name the call count.
+ *
+ * The shipped metric (`graft_turns_bucket` / `reported_turns_bucket` on
+ * `session_summary`) is the same ratio at bucket resolution, which is all that
+ * can cross the wire. Run this locally when the aggregate says something
+ * surprising and you need to see which turns and why.
+ *
+ * Reads Claude Code's own transcript JSONL, which defaults to
+ * ~/.claude/projects/<slugified-cwd>/. Nothing leaves the machine.
+ */
+import { readFileSync, readdirSync, existsSync } from "node:fs";
+import { join } from "node:path";
+import { homedir } from "node:os";
+
+const SAVED_FOOTER = /\[graft\] tokens saved ≈ ([\d,]+)/g;
+const TALLY = /graft\s+saved\s*[~≈]?\s*([\d,.]+)\s*(k|m)?\s*(?:tok|tokens)/i;
+const CALLS = /(\d+)\s*calls?/i;
+/** How far past the tally to look for its call count. The tally is one line
+ * ("🌱 graft saved ~12,400 tokens this turn (3 calls)"); scanning the rest of
+ * the reply instead would match any unrelated "3 calls" further down and report
+ * near-perfect compliance for a field the agent mostly omits. */
+const TALLY_WINDOW = 60;
+/** Above this, a per-turn "saved" figure is an estimator artifact rather than a
+ * saving — a `--depth all` closure or a vendored tree summing whole-file
+ * baselines nobody would have read. Reported separately, never averaged in. */
+const IMPLAUSIBLE_TOKENS = 1_000_000;
+
+const args = process.argv.slice(2).filter((a) => a !== "--json");
+const asJson = process.argv.includes("--json");
+const dir = args[0] ?? defaultTranscriptDir();
+
+function defaultTranscriptDir() {
+  const slug = process.cwd().replace(/[/.]/g, "-");
+  return join(homedir(), ".claude", "projects", slug);
+}
+function textOf(content) {
+  if (typeof content === "string") return content;
+  if (!Array.isArray(content)) return "";
+  return content.map((p) => (p?.type === "text" ? p.text ?? "" : "")).join("\n");
+}
+function isUserPrompt(o) {
+  if (o.type !== "user" || o.isSidechain || o.isMeta) return false;
+  const c = o.message?.content;
+  if (typeof c === "string") return true;
+  return Array.isArray(c) && !c.some((p) => p?.type === "tool_result");
+}
+function median(ns) {
+  if (!ns.length) return 0;
+  const s = [...ns].sort((a, b) => a - b);
+  const mid = s.length >> 1;
+  return s.length % 2 ? s[mid] : Math.round((s[mid - 1] + s[mid]) / 2);
+}
+
+if (!existsSync(dir)) {
+  console.error(`no transcripts at ${dir}`);
+  process.exit(1);
+}
+
+const turns = [];
+for (const file of readdirSync(dir).filter((f) => f.endsWith(".jsonl"))) {
+  let turn = null;
+  const flush = () => { if (turn?.calls > 0) turns.push(turn); };
+  for (const line of readFileSync(join(dir, file), "utf8").split("\n")) {
+    if (!line.trim()) continue;
+    let o;
+    try { o = JSON.parse(line); } catch { continue; }
+    if (o.isSidechain) continue;                    // a subagent's prose is not what the user read
+    if (isUserPrompt(o)) { flush(); turn = { file, calls: 0, saved: 0, said: null, statedCalls: null }; continue; }
+    if (!turn) continue;
+    if (o.type === "user") {                        // a tool_result wearing the user role
+      for (const m of JSON.stringify(o.message?.content ?? "").matchAll(SAVED_FOOTER)) {
+        turn.calls++;
+        turn.saved += Number(m[1].replace(/,/g, "")) || 0;
+      }
+    }
+    if (o.type === "assistant") {
+      const m = TALLY.exec(textOf(o.message?.content));
+      if (m) {
+        let n = Number(m[1].replace(/,/g, ""));
+        if (m[2]?.toLowerCase() === "k") n *= 1e3;
+        if (m[2]?.toLowerCase() === "m") n *= 1e6;
+        turn.said = n;
+        const c = CALLS.exec(textOf(o.message?.content).slice(m.index, m.index + TALLY_WINDOW));
+        turn.statedCalls = c ? Number(c[1]) : null;
+      }
+    }
+  }
+  flush();
+}
+
+const said = turns.filter((t) => t.said !== null);
+const plausible = turns.filter((t) => t.saved < IMPLAUSIBLE_TOKENS);
+const outliers = turns.filter((t) => t.saved >= IMPLAUSIBLE_TOKENS);
+const fidelity = { exact: 0, over: 0, under: 0 };
+for (const t of said.filter((t) => t.saved > 0)) {
+  const r = t.said / t.saved;
+  if (r >= 0.9 && r <= 1.1) fidelity.exact++;
+  else if (r > 1.1) fidelity.over++;
+  else fidelity.under++;
+}
+
+const report = {
+  transcripts: readdirSync(dir).filter((f) => f.endsWith(".jsonl")).length,
+  graft_turns: turns.length,
+  reported: said.length,
+  silent: turns.length - said.length,
+  reported_pct: turns.length ? Number(((said.length / turns.length) * 100).toFixed(1)) : 0,
+  stated_call_count: said.filter((t) => t.statedCalls !== null).length,
+  median_saved_per_turn: median(plausible.map((t) => t.saved)),
+  fidelity,
+  implausible_turns: outliers.length,
+  implausible_max: outliers.length ? Math.max(...outliers.map((t) => t.saved)) : 0,
+};
+
+if (asJson) {
+  console.log(JSON.stringify(report, null, 2));
+} else {
+  const { graft_turns: n } = report;
+  console.log(`transcripts scanned:      ${report.transcripts}  (${dir})`);
+  console.log(`turns that used graft:    ${n}`);
+  console.log(`  ...reported a tally:    ${report.reported}  (${report.reported_pct}%)`);
+  console.log(`  ...silent:              ${report.silent}`);
+  console.log(`  ...named the call count ${report.stated_call_count}/${report.reported}`);
+  console.log(`median saved per turn:    ${report.median_saved_per_turn.toLocaleString()} tok`);
+  console.log(`reported number vs footer sum (±10%): exact ${fidelity.exact} · over ${fidelity.over} · under ${fidelity.under}`);
+  if (outliers.length) {
+    console.log(`\n⚠ ${outliers.length} turn(s) claim ≥${IMPLAUSIBLE_TOKENS.toLocaleString()} tokens saved ` +
+      `(max ${report.implausible_max.toLocaleString()}) — an estimator artifact, excluded from the median. ` +
+      `See savingsFor() in src/context/savings.ts.`);
+  }
+}

package/dist/ai/llm/claude-cli.d.ts

@@ -1,60 +0,0 @@
-import type { ChatModel, ChatRequest, ChatResponse } from "./types.js";
-export interface ClaudeCliResult {
-    code: number | null;
-    stdout: string;
-    stderr: string;
-}
-/** Injectable process runner — tests pass a stub so nothing is ever spawned. */
-export type ClaudeCliRunner = (args: string[], stdin: string, timeoutMs: number) => Promise<ClaudeCliResult>;
-export interface ClaudeCliChatModelOptions {
-    /** Model alias or full id (`sonnet`, `opus`, `claude-sonnet-5`, …). */
-    model: string;
-    /** Path to the CLI. Default: resolved from PATH (env GRAFT_CLAUDE_BIN wins). */
-    bin?: string;
-    label?: string;
-    /** Per-call wall clock. Default 300s — a crux pass over a big file is slow. */
-    timeoutMs?: number;
-    /** Optional spend ceiling passed through as `--max-budget-usd`. */
-    maxBudgetUsd?: number;
-    /** Inject a runner (tests stub it; production omits it). */
-    run?: ClaudeCliRunner;
-}
-export declare class ClaudeCliChatModel implements ChatModel {
-    readonly label: string;
-    private model;
-    private runner;
-    private timeoutMs;
-    private maxBudgetUsd?;
-    constructor(opts: ClaudeCliChatModelOptions);
-    create(req: ChatRequest): Promise<ChatResponse>;
-    /**
-     * Transport-level retry. A `--deep` build is thousands of sequential calls over
-     * hours, so a single blip — an overloaded upstream, a dropped connection, one
-     * slow file hitting the wall clock — would otherwise silently cost that file its
-     * summary. Only failures classified transient are retried; a bad login or an
-     * exhausted quota fails immediately, because sleeping on those just turns a
-     * clear error into a slow one.
-     */
-    private invoke;
-    private invokeOnce;
-}
-export declare function isTransient(message: string): boolean;
-/**
- * Pull one JSON value out of a model reply. Handles the two ways a prompt-enforced
- * schema leaks: a markdown fence around the object, and prose either side of it.
- * Brace scanning is string- and escape-aware so a `}` inside a summary can't end
- * the object early. Returns undefined when nothing parses.
- */
-export declare function extractJson(text: string): unknown;
-/**
- * Resolve the CLI without a shell. Node's spawn only appends `.exe` on Windows,
- * so PATHEXT is walked by hand — the native installer ships `claude.exe` but an
- * `npm i -g` install leaves only the `claude.cmd` shim, and missing it would make
- * this provider look uninstalled on a machine where it works fine.
- */
-export declare function resolveClaudeBin(explicit?: string): string | undefined;
-/** True when the `claude` CLI is installed. Cached — this runs per build, not per file. */
-export declare function claudeCliAvailable(explicit?: string): boolean;
-/** Test seam: drop the memoized lookup so a test can flip PATH. */
-export declare function resetClaudeCliCache(): void;
-//# sourceMappingURL=claude-cli.d.ts.map

package/dist/ai/llm/claude-cli.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"claude-cli.d.ts","sourceRoot":"","sources":["../../../src/ai/llm/claude-cli.ts"],"names":[],"mappings":"AAuCA,OAAO,KAAK,EAAE,SAAS,EAAE,WAAW,EAAE,YAAY,EAA4B,MAAM,YAAY,CAAC;AAgBjG,MAAM,WAAW,eAAe;IAC9B,IAAI,EAAE,MAAM,GAAG,IAAI,CAAC;IACpB,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;CAChB;AAED,gFAAgF;AAChF,MAAM,MAAM,eAAe,GAAG,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,KAAK,OAAO,CAAC,eAAe,CAAC,CAAC;AAE7G,MAAM,WAAW,yBAAyB;IACxC,uEAAuE;IACvE,KAAK,EAAE,MAAM,CAAC;IACd,gFAAgF;IAChF,GAAG,CAAC,EAAE,MAAM,CAAC;IACb,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,+EAA+E;IAC/E,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,mEAAmE;IACnE,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,4DAA4D;IAC5D,GAAG,CAAC,EAAE,eAAe,CAAC;CACvB;AAiBD,qBAAa,kBAAmB,YAAW,SAAS;IAClD,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC;IACvB,OAAO,CAAC,KAAK,CAAS;IACtB,OAAO,CAAC,MAAM,CAAkB;IAChC,OAAO,CAAC,SAAS,CAAS;IAC1B,OAAO,CAAC,YAAY,CAAC,CAAS;gBAElB,IAAI,EAAE,yBAAyB;IAQrC,MAAM,CAAC,GAAG,EAAE,WAAW,GAAG,OAAO,CAAC,YAAY,CAAC;IAgDrD;;;;;;;OAOG;YACW,MAAM;YAeN,UAAU;CAmCzB;AAeD,wBAAgB,WAAW,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAGpD;AAkFD;;;;;GAKG;AACH,wBAAgB,WAAW,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CA0CjD;AAcD;;;;;GAKG;AACH,wBAAgB,gBAAgB,CAAC,QAAQ,CAAC,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAgBtE;AAID,2FAA2F;AAC3F,wBAAgB,kBAAkB,CAAC,QAAQ,CAAC,EAAE,MAAM,GAAG,OAAO,CAI7D;AAED,mEAAmE;AACnE,wBAAgB,mBAAmB,IAAI,IAAI,CAE1C"}