token-goat 2.8.0 → 2.8.2

package/dist/{token-goat-chunk-FBGBTICM.mjs → token-goat-chunk-AL644JUV.mjs}

@@ -25,7 +25,7 @@ import {
   runSkeleton,
   runSymbol,
   withPinnedReads
-} from "./token-goat-chunk-SRAR6DOK.mjs";
+} from "./token-goat-chunk-LILS6TIU.mjs";
 import {
   buildProjectMap,
   embeddingsDepsAvailable,
@@ -34,7 +34,7 @@ import {
   getProjectIndexCounts,
   isWorkerRunning,
   mapLookupBytesSaved
-} from "./token-goat-chunk-2F6TFBZE.mjs";
+} from "./token-goat-chunk-AM23GDIS.mjs";
 import {
   VERSION,
   dataDir,
@@ -45,7 +45,7 @@ import {
   normalizePath,
   recordStat,
   resolveProjectRoot
-} from "./token-goat-chunk-44Y77VHR.mjs";
+} from "./token-goat-chunk-IVCTQPZD.mjs";
 import "./token-goat-chunk-AO2QD2AG.mjs";
 import "./token-goat-chunk-AEX54RUZ.mjs";
 

package/dist/{token-goat-chunk-2F6TFBZE.mjs → token-goat-chunk-AM23GDIS.mjs}

@@ -59,6 +59,7 @@ import {
   propagateEndLinesToSymbols,
   pushAll,
   recordStat,
+  recordUnmappedTool,
   redactIfDotenv,
   redactSecrets,
   resolveIndexPath,
@@ -90,7 +91,7 @@ import {
   withFileLock,
   writeIfDifferent,
   writeJsonSettings
-} from "./token-goat-chunk-44Y77VHR.mjs";
+} from "./token-goat-chunk-IVCTQPZD.mjs";
 import {
   registerReset
 } from "./token-goat-chunk-AO2QD2AG.mjs";
@@ -2331,10 +2332,18 @@ var parse2 = function(data, opts = {}) {
 function parseRecords(content, opts) {
   const delimiter = opts.delimiter ?? ",";
   if (opts.noHeader === true) {
-    const rows = parse2(content, { columns: false, skip_empty_lines: true, trim: true, delimiter, bom: true });
+    const rows = parse2(content, { columns: false, skip_empty_lines: true, trim: true, delimiter, bom: true, relax_column_count: true });
     return rows.map((row) => Object.fromEntries(row.map((cell, i) => [`col${i + 1}`, cell])));
   }
-  return parse2(content, { columns: true, skip_empty_lines: true, trim: true, delimiter, bom: true });
+  const header = csvHeader(content, opts);
+  const dupes = header.filter((name, i) => name !== "" && header.indexOf(name) !== i);
+  if (dupes.length > 0) {
+    const unique = [...new Set(dupes)];
+    throw new Error(
+      `duplicate column ${unique.length === 1 ? "name" : "names"} in header: ${unique.join(", ")} \u2014 rename the duplicates or pass --no-header to address columns positionally as col1, col2, \u2026`
+    );
+  }
+  return parse2(content, { columns: true, skip_empty_lines: true, trim: true, delimiter, bom: true, relax_column_count: true });
 }
 function csvHeader(content, opts) {
   if (opts.noHeader === true) return [];
@@ -2828,8 +2837,10 @@ function usedRange(ws) {
   }
   const rows = rowCount;
   const cols = maxCol;
-  const ref2 = rows > 0 && cols > 0 ? `A1:${indexToColLetters(cols)}${rows}` : "A1:A1";
-  return { ref: ref2, rows: Math.max(rows, 1), cols: Math.max(cols, 1) };
+  if (rows === 0 || cols === 0) {
+    return { ref: "(empty)", rows: 0, cols: 0 };
+  }
+  return { ref: `A1:${indexToColLetters(cols)}${rows}`, rows, cols };
 }
 async function listSheets(filePath) {
   const wb = await loadWorkbook(filePath);
@@ -2993,6 +3004,40 @@ async function extractPdfText(data, pagesSpec, layout = false) {
     return { text: pages.join("\n\n"), pageCount: doc.numPages, pagesExtracted: end - start + 1 };
   });
 }
+async function locatePdfPages(data, pattern, opts) {
+  let re;
+  try {
+    re = new RegExp(pattern, opts.ignoreCase === true ? "i" : "");
+  } catch (e) {
+    throw new Error(`invalid regex pattern: ${pattern} (${e instanceof Error ? e.message : String(e)})`, { cause: e });
+  }
+  const pdfjs = await loadPdfjs();
+  if (!pdfjs) throw new Error("pdfjs-dist is not installed; run `npm install pdfjs-dist` to enable pdf-extract");
+  const maxMatches = opts.maxMatches ?? 50;
+  const context = opts.context ?? 80;
+  return withPdfDocument(pdfjs, data, async (doc) => {
+    const range = parsePageRange(opts.pages, doc.numPages);
+    const start = range ? range.start : 1;
+    const end = range ? range.end : doc.numPages;
+    const matches = [];
+    for (let i = start; i <= end && matches.length < maxMatches; i++) {
+      const page = await doc.getPage(i);
+      const content = await page.getTextContent();
+      const textItems = content.items.filter((item) => "str" in item);
+      const pageText = textItems.map((item) => item.str).join(" ");
+      const m = re.exec(pageText);
+      if (m === null) continue;
+      matches.push({ page: i, snippet: locateSnippet(pageText, m.index, m[0].length, context) });
+    }
+    return matches;
+  });
+}
+function locateSnippet(text, index, matchLen, context) {
+  const pad = Math.max(0, context - matchLen);
+  const from = Math.max(0, index - Math.floor(pad / 2));
+  const to = Math.min(text.length, index + matchLen + Math.ceil(pad / 2));
+  return text.slice(from, to).replace(/\s+/g, " ").trim();
+}
 async function resolveDestPage(doc, dest) {
   let explicitDest = dest;
   if (typeof explicitDest === "string") {
@@ -3190,9 +3235,27 @@ function toolMatcherFor(eventName) {
   if (parts.length === 0) return null;
   return parts.join("|");
 }
+function foldToolName(name) {
+  return name.toLowerCase().replace(/[_-]/g, "");
+}
+function noteUnrecognizedTool(event, list) {
+  const toolName = event.toolName;
+  if (typeof toolName !== "string" || toolName === "") return;
+  const named = [];
+  for (const { toolName: want } of list) {
+    if (want === void 0) continue;
+    if (want === toolName) return;
+    named.push(want);
+  }
+  if (named.length === 0) return;
+  const folded = foldToolName(toolName);
+  const nearMiss = named.find((n) => foldToolName(n) === folded) ?? null;
+  recordUnmappedTool(toolName, event.eventName, nearMiss);
+}
 async function runHook(event) {
   const list = _handlers.get(event.eventName);
   if (list === void 0) return { hookType: "pass" };
+  noteUnrecognizedTool(event, list);
   let advisoryResult;
   for (const { handler, toolName, advisory } of list) {
     if (toolName !== void 0 && toolName !== event.toolName) continue;
@@ -4237,9 +4300,9 @@ function buildGuidanceBody(fallbackToolClause, opts = {}) {
     "- pulling one value or subtree out of a JSON/YAML/XML file (manifest, lockfile, spec, config) \u2192 `json-query file 'a.b.c'` / `yaml-query file 'a.b.c'` / `xml-query file 'a.b.c'`",
     "- opening an image to check its dimensions, format, or size \u2192 `image-meta file`",
     "- opening a screenshot, diagram, or scan to read the text in it \u2192 `image-text file`",
-    "- opening a PDF or Office document \u2192 inspect its format first, then read a narrow slice: PDF `pdf-meta`/`pdf-outline` then `pdf-extract`; Word `docx-outline` then `docx-text`; PowerPoint `pptx-outline` then `pptx-slide`/`pptx-notes`; Excel `xlsx-sheets` then `xlsx-head`/`xlsx-range`/`xlsx-query`",
+    "- opening a PDF or Office document \u2192 inspect its format first, then read a narrow slice: PDF `pdf-meta`/`pdf-outline` then `pdf-locate` to find the pages and `pdf-extract` only those; Word `docx-outline` then `docx-text`; PowerPoint `pptx-outline` then `pptx-slide`/`pptx-notes`; Excel `xlsx-sheets` then `xlsx-head`/`xlsx-range`/`xlsx-query`",
     "",
-    'Commands: `symbol NAME`, `read "file::symbol"`, `brief "file::symbol"`, `section "file::Heading"`, `semantic "description"`, `outline file`/`skeleton file`, `map --compact`, `refs file::symbol --callers`, `changed --symbol`, `config-get file KEY`, `json-query file \'a.b.c\'`/`yaml-query`/`xml-query`, `json-outline file`/`yaml-outline`/`xml-outline`, `bash-output`/`web-output`/`mcp-output`, ' + (gdrive ? "`gdrive-sections <file-id>`, " : "") + "`image-meta file`/`image-text file`, `pdf-meta`/`pdf-outline`/`pdf-extract`, `docx-outline`/`docx-text`, `pptx-outline`/`pptx-slide`/`pptx-notes`/`pptx-text`, `xlsx-sheets`/`xlsx-head`/`xlsx-range`/`xlsx-query`.",
+    'Commands: `symbol NAME`, `read "file::symbol"`, `brief "file::symbol"`, `section "file::Heading"`, `semantic "description"`, `outline file`/`skeleton file`, `map --compact`, `refs file::symbol --callers`, `changed --symbol`, `config-get file KEY`, `json-query file \'a.b.c\'`/`yaml-query`/`xml-query`, `json-outline file`/`yaml-outline`/`xml-outline`, `bash-output`/`web-output`/`mcp-output`, ' + (gdrive ? "`gdrive-sections <file-id>`, " : "") + "`image-meta file`/`image-text file`, `pdf-meta`/`pdf-outline`/`pdf-locate`/`pdf-extract`, `docx-outline`/`docx-text`, `pptx-outline`/`pptx-slide`/`pptx-notes`/`pptx-text`, `xlsx-sheets`/`xlsx-head`/`xlsx-range`/`xlsx-query`.",
     "",
     "Sub-agent briefs must carry this gate verbatim: a sub-agent inherits none of this context and its reads spend the same token budget.",
     "",
@@ -5107,7 +5170,14 @@ const POLL_ID_ARG_KEY = {
 // the same session, since process.pid varies per invocation -- breaking token-goat's
 // session-based dedup/state ledger, which never accumulates across calls as a result. Derive a
 // stable id instead from the one thing that's actually constant across calls for the same
-// session: the working directory Copilot reports in \`payload.cwd\`.
+// session: the working directory Copilot reports. That field is \`workingDirectory\`, declared
+// required on BaseHookInput in copilot-sdk/types.d.ts since 1.0.76, so it is present on EVERY
+// hook event. This previously read \`payload.cwd\`, which Copilot has never sent under any name in
+// any version -- the key simply did not exist, so this derived every fallback id from
+// process.cwd() instead and \`canonical.cwd\` below was undefined on every single call. It went
+// unnoticed because process.cwd() happens to be the project directory Copilot spawns the hook in,
+// so the fallback was accidentally right; nothing about that was by design. \`cwd\` is still read
+// as a secondary in case a future version adds it under the shorter name.
 function stableFallbackSessionId(cwd) {
   const key = typeof cwd === 'string' && cwd ? cwd : process.cwd()
   const hash = require('node:crypto').createHash('sha256').update(key).digest('hex').slice(0, 16)
@@ -5177,8 +5247,19 @@ async function main() {
 
   const toolName = payload && payload.toolName
   const canonical = {
-    session_id: (payload && payload.sessionId) || stableFallbackSessionId(payload && payload.cwd),
-    cwd: payload && payload.cwd,
+    session_id:
+      (payload && payload.sessionId) ||
+      stableFallbackSessionId(payload && (payload.workingDirectory || payload.cwd)),
+    cwd: payload && (payload.workingDirectory || payload.cwd),
+  }
+
+  // userPromptSubmitted only: Copilot declares \`prompt\` required on UserPromptSubmittedHookInput.
+  // hooks_session.ts's userPromptSubmitHandler reads it as \`event.raw['prompt']\` and gates every
+  // branch it has on the text, so without this it saw '' on every Copilot prompt and the
+  // embedded-skill dedup hint could never fire. Same shape as the postToolUseFailure \`error\`
+  // drop: a required field the canonical builder simply did not list.
+  if (typeof (payload && payload.prompt) === 'string' && payload.prompt !== '') {
+    canonical.prompt = payload.prompt
   }
   if (toolName) {
     canonical.tool_name = TOOL_TO_TG[toolName] || toolName
@@ -5193,6 +5274,16 @@ async function main() {
   // post-read/post-bash stats stay empty no matter how many tool calls happen. Extract the
   // LLM-facing text directly rather than forwarding the raw object, since textResultForLlm
   // isn't one of those recognized object keys.
+  // postToolUseFailure only: Copilot's PostToolUseFailureHookInput (copilot-sdk/types.d.ts:1042)
+  // carries {toolName, toolArgs, error} and no toolResult at all -- the failure text lives in
+  // \`error\`, a plain string. Without forwarding it, hooks_tool_failure.ts's extractFailureText
+  // finds nothing to key on and the repeat-failure brake returns pass on every single call: wired,
+  // green, and doing nothing. Found by driving the installed shim rather than by a test, because
+  // the handler's own tests hand it a raw payload that already has the field.
+  if (typeof (payload && payload.error) === 'string' && payload.error !== '') {
+    canonical.error = payload.error
+  }
+
   const rawResult = payload && payload.toolResult
   if (rawResult && typeof rawResult === 'object') {
     const tr = rawResult
@@ -7373,6 +7464,9 @@ function resolveTesseractEntry() {
   }
   return _tesseractEntryPath;
 }
+function isOcrEngineAvailable() {
+  return !_ocrUnavailableThisProcess && resolveTesseractEntry() !== null;
+}
 var _ocrUnavailableThisProcess = false;
 function buildChildScript(entryPath, cacheDir) {
   return [
@@ -7487,14 +7581,16 @@ var loadSharp = createLazyModuleLoader(async () => {
 function isImagePath(p) {
   return IMAGE_EXTENSIONS.has(path12.extname(p).toLowerCase());
 }
+var ImageDecodeError = class extends Error {
+};
 async function probeImageMeta(input) {
   const sharp = await loadSharp();
   if (sharp === null) return null;
   try {
     const meta = await sharp(input, { limitInputPixels: false }).metadata();
     return { width: meta.width ?? 0, height: meta.height ?? 0, format: meta.format ?? null, pages: meta.pages ?? 1 };
-  } catch {
-    return null;
+  } catch (e) {
+    throw new ImageDecodeError(e?.message ?? "image could not be decoded");
   }
 }
 async function imageQualifiesForShrink(input) {
@@ -7640,7 +7736,14 @@ async function preReadImageHandler(event) {
     } catch {
       cachedData = null;
     }
-    const meta = cachedData !== null ? await probeImageMeta(cachedData) : null;
+    let meta = null;
+    if (cachedData !== null) {
+      try {
+        meta = await probeImageMeta(cachedData);
+      } catch {
+        meta = null;
+      }
+    }
     if (cachedData !== null && meta !== null) {
       const result2 = {
         data: cachedData,
@@ -9819,7 +9922,7 @@ function extractMarkdownHeadings(content, limit = MAX_HEADINGS) {
   const lines2 = content.split("\n");
   for (const [i, line] of eachUnfencedLine(lines2)) {
     if (!line) continue;
-    const match = /^(#+)\s+(.+?)(?:\s+#+\s*)?$/.exec(line);
+    const match = /^(#+)\s+([^\r\n]+?)(?:\s+#+)?\s*$/.exec(line);
     if (!match || match.length < 3) continue;
     const hashes = match[1];
     const headingText = match[2];
@@ -9949,7 +10052,7 @@ function handleHtml(filePath, content, contentLengthHint) {
       message: `Large HTML file (${formatBytes(length)}) \u2014 too large to preview (exceeds the in-hook scan cap). Use token-goat section to extract a section by heading, or convert to text: pandoc "${filePath}" -t plain`
     };
   }
-  const title = content.match(/<title[^>]*>([^<]+)<\/title>/i)?.[1]?.trim();
+  const title = content.match(/<title[^>]*>([^<]*)<\/title>/i)?.[1]?.trim();
   const headings = findHtmlHeadingMatches(content).slice(0, 20).map(({ level, heading }) => {
     if (!heading) return "";
     return `${"  ".repeat(level - 1)}h${level}: ${heading}`;
@@ -18839,6 +18942,7 @@ function urlPolicyDenialReason(url, policy) {
 export {
   createLazyModuleLoader,
   extractPdfText,
+  locatePdfPages,
   extractPdfOutline,
   extractPdfMeta,
   docxOutline,
@@ -19005,10 +19109,12 @@ export {
   getSkillFilePath,
   installedSkillPath,
   pruneSkillOutputs,
+  isOcrEngineAvailable,
   ocrImage,
   isTextHeavy,
   formatShrinkSummary,
   isImagePath,
+  ImageDecodeError,
   probeImageMeta,
   imageQualifiesForShrink,
   shrinkImage,

package/dist/{token-goat-chunk-4KZILRZN.mjs → token-goat-chunk-BTZSUIYA.mjs}

@@ -10,11 +10,11 @@ import {
   selectFilter,
   shlexSplit,
   wrappedShell
-} from "./token-goat-chunk-TUPJRK7R.mjs";
+} from "./token-goat-chunk-TF5NT3H5.mjs";
 import {
   loadConfig,
   recordStat
-} from "./token-goat-chunk-44Y77VHR.mjs";
+} from "./token-goat-chunk-IVCTQPZD.mjs";
 import "./token-goat-chunk-AO2QD2AG.mjs";
 import "./token-goat-chunk-AEX54RUZ.mjs";
 

package/dist/{token-goat-chunk-44Y77VHR.mjs → token-goat-chunk-IVCTQPZD.mjs}

@@ -8,7 +8,7 @@ import {
 import { createRequire } from "node:module";
 function resolveVersion() {
   if (true) {
-    return "2.8.0";
+    return "2.8.2";
   }
   const require2 = createRequire(import.meta.url);
   const pkg = require2("../package.json");
@@ -5801,6 +5801,30 @@ function _renderByCommandSection(stats) {
   }
   return lines;
 }
+function _renderByHarnessSection(stats) {
+  if (!stats.by_harness || stats.by_harness.length < 2) {
+    return [];
+  }
+  const lines = [..._sectionHeader("By harness"), _tableHeader("harness")];
+  const { grossBytes, shareBytesDenom, shareTokensDenom } = _computeShareDenominators(stats.by_harness);
+  function share(h) {
+    return _absShare(h.bytes, h.tokens, shareBytesDenom, shareTokensDenom);
+  }
+  for (const h of [...stats.by_harness].sort((a, b) => share(b) - share(a))) {
+    lines.push(
+      _tableRow({
+        name: h.harness,
+        fraction: _barFraction(h.bytes, grossBytes),
+        bytes: h.bytes,
+        tokens: h.tokens,
+        events: h.events,
+        share: share(h),
+        nameColor: C.TEXT_PRIMARY
+      })
+    );
+  }
+  return lines;
+}
 function _renderByDaySection(stats) {
   if (stats.by_day.length === 0) {
     return [];
@@ -5923,6 +5947,7 @@ function renderStats(stats, opts) {
     _renderByKindSection(stats),
     _renderBySourceSection(stats),
     _renderByCommandSection(stats),
+    _renderByHarnessSection(stats),
     _renderByDaySection(stats),
     _renderByProjectSection(stats),
     _renderInsightsSection(stats),
@@ -5932,6 +5957,7 @@ function renderStats(stats, opts) {
 }
 
 // src/stats.ts
+var HARNESS_UNRECORDED = "unrecorded (pre-2.8.1)";
 var SOURCE_IMAGE = "image";
 var SOURCE_HINT = "hint";
 var SOURCE_READ = "read";
@@ -5978,6 +6004,7 @@ var KIND_TO_SOURCE = {
   csv_query: SOURCE_READ,
   csv_profile: SOURCE_READ,
   pdf_extract: SOURCE_READ,
+  pdf_locate: SOURCE_READ,
   pdf_outline: SOURCE_READ,
   pdf_meta: SOURCE_READ,
   xlsx_sheets: SOURCE_READ,
@@ -6067,6 +6094,7 @@ var COMMAND_KINDS = {
   "csv-query": /* @__PURE__ */ new Set(["csv_query"]),
   "csv-profile": /* @__PURE__ */ new Set(["csv_profile"]),
   "pdf-extract": /* @__PURE__ */ new Set(["pdf_extract"]),
+  "pdf-locate": /* @__PURE__ */ new Set(["pdf_locate"]),
   "pdf-outline": /* @__PURE__ */ new Set(["pdf_outline"]),
   "pdf-meta": /* @__PURE__ */ new Set(["pdf_meta"]),
   "xlsx-sheets": /* @__PURE__ */ new Set(["xlsx_sheets"]),
@@ -6161,19 +6189,53 @@ CREATE TABLE IF NOT EXISTS stats (
   kind TEXT NOT NULL,
   tokens_saved INTEGER NOT NULL DEFAULT 0,
   bytes_saved INTEGER NOT NULL DEFAULT 0,
-  detail TEXT
+  detail TEXT,
+  harness TEXT
 );
 CREATE INDEX IF NOT EXISTS idx_stats_ts ON stats(ts);
 CREATE INDEX IF NOT EXISTS idx_stats_kind ON stats(kind);
+CREATE TABLE IF NOT EXISTS unmapped_tools (
+  harness TEXT NOT NULL,
+  tool_name TEXT NOT NULL,
+  event_name TEXT NOT NULL,
+  near_miss TEXT,
+  first_seen INTEGER NOT NULL,
+  last_seen INTEGER NOT NULL,
+  hits INTEGER NOT NULL DEFAULT 0,
+  PRIMARY KEY (harness, tool_name, event_name)
+);
 `;
 var _globalSchemaApplied = /* @__PURE__ */ new Set();
 registerReset(() => _globalSchemaApplied.clear());
+function migrateGlobalSchema(db) {
+  try {
+    db.exec("ALTER TABLE stats ADD COLUMN harness TEXT");
+  } catch (err) {
+    if (!(err instanceof Error) || !/duplicate column/i.test(err.message)) throw err;
+  }
+}
+var _harnessColumnByDb = /* @__PURE__ */ new WeakMap();
+function statsHasHarnessColumn(db) {
+  const cached = _harnessColumnByDb.get(db);
+  if (cached !== void 0) return cached;
+  let present;
+  try {
+    present = db.prepare("PRAGMA table_info(stats)").all().some(
+      (c) => c.name === "harness"
+    );
+  } catch {
+    present = false;
+  }
+  _harnessColumnByDb.set(db, present);
+  return present;
+}
 function getGlobalDb(homeDir) {
   const basePath = homeDir ? dataDirForHome(homeDir) : dataDir();
   const dbPath = path8.join(basePath, "global.db");
   const db = getDb(dbPath);
   if (!_globalSchemaApplied.has(dbPath)) {
     db.exec(GLOBAL_SCHEMA_SQL);
+    migrateGlobalSchema(db);
     _globalSchemaApplied.add(dbPath);
   }
   return db;
@@ -6188,10 +6250,44 @@ function noStatsMessage(windowDays, homeDir) {
 function recordStat(kind, bytesSaved = 0, tokensSaved = 0, _testDb, detail) {
   try {
     const db = _testDb ?? getGlobalDb();
+    const ts = Math.floor(Date.now() / 1e3);
+    if (statsHasHarnessColumn(db)) {
+      db.prepare(
+        "INSERT INTO stats (ts, kind, bytes_saved, tokens_saved, detail, harness) VALUES (?, ?, ?, ?, ?, ?)"
+      ).run(ts, kind, bytesSaved, tokensSaved, detail ?? null, getHarnessName());
+    } else {
+      db.prepare(
+        "INSERT INTO stats (ts, kind, bytes_saved, tokens_saved, detail) VALUES (?, ?, ?, ?, ?)"
+      ).run(ts, kind, bytesSaved, tokensSaved, detail ?? null);
+    }
+  } catch {
+  }
+}
+var MAX_TOOL_NAME_CHARS = 200;
+function recordUnmappedTool(toolName, eventName, nearMiss, _testDb) {
+  try {
+    if (!toolName) return;
+    const db = _testDb ?? getGlobalDb();
+    const now = Math.floor(Date.now() / 1e3);
     db.prepare(
-      "INSERT INTO stats (ts, kind, bytes_saved, tokens_saved, detail) VALUES (?, ?, ?, ?, ?)"
-    ).run(Math.floor(Date.now() / 1e3), kind, bytesSaved, tokensSaved, detail ?? null);
+      `INSERT INTO unmapped_tools (harness, tool_name, event_name, near_miss, first_seen, last_seen, hits)
+       VALUES (?, ?, ?, ?, ?, ?, 1)
+       ON CONFLICT(harness, tool_name, event_name) DO UPDATE SET
+         hits = hits + 1,
+         last_seen = excluded.last_seen,
+         near_miss = excluded.near_miss`
+    ).run(getHarnessName(), toolName.slice(0, MAX_TOOL_NAME_CHARS), eventName, nearMiss, now, now);
+  } catch {
+  }
+}
+function readUnmappedTools(dbPath, homeDir) {
+  try {
+    const db = dbPath ? getDb(dbPath) : getGlobalDb(homeDir);
+    return db.prepare(
+      "SELECT harness, tool_name, event_name, near_miss, hits, last_seen FROM unmapped_tools ORDER BY hits DESC, tool_name ASC"
+    ).all();
   } catch {
+    return [];
   }
 }
 function summarize(windowDays = 30, testDb, homeDir) {
@@ -6199,11 +6295,14 @@ function summarize(windowDays = 30, testDb, homeDir) {
   const sinceTs = windowDays > 0 ? Math.floor((Date.now() - windowDays * 24 * 60 * 60 * 1e3) / 1e3) : null;
   const byKind = {};
   const byDay = {};
+  const byHarness = {};
   let totalEvents = 0;
   let totalBytes = 0;
   let totalTokens = 0;
   const db = testDb ?? getGlobalDb(homeDir);
-  const query = sinceTs !== null ? "SELECT ts, kind, bytes_saved, tokens_saved FROM stats WHERE ts >= ? ORDER BY ts DESC" : "SELECT ts, kind, bytes_saved, tokens_saved FROM stats ORDER BY ts DESC";
+  const hasHarness = statsHasHarnessColumn(db);
+  const cols = hasHarness ? "ts, kind, bytes_saved, tokens_saved, harness" : "ts, kind, bytes_saved, tokens_saved";
+  const query = sinceTs !== null ? `SELECT ${cols} FROM stats WHERE ts >= ? ORDER BY ts DESC` : `SELECT ${cols} FROM stats ORDER BY ts DESC`;
   const stmt = db.prepare(query);
   const rows = sinceTs !== null ? stmt.all(sinceTs) : stmt.all();
   const tsToDateCache = {};
@@ -6227,6 +6326,11 @@ function summarize(windowDays = 30, testDb, homeDir) {
       byDay[dateKey] = zeroBucket();
     }
     incBucket(byDay[dateKey], bytesSaved, tokensSaved);
+    const harness = row.harness || HARNESS_UNRECORDED;
+    if (!byHarness[harness]) {
+      byHarness[harness] = zeroBucket();
+    }
+    incBucket(byHarness[harness], bytesSaved, tokensSaved);
   }
   const bySourceDict = {};
   for (const [kind, bucket] of Object.entries(byKind)) {
@@ -6263,6 +6367,7 @@ function summarize(windowDays = 30, testDb, homeDir) {
     by_day: byDayList,
     by_project: byProjectList,
     by_source: bySourceDict,
+    by_harness: byHarness,
     by_command: Object.entries(byCommandDict).map(([command, bucket]) => ({ ...bucket, command })).filter((r) => r.events > 0),
     window_days: windowDays
   };
@@ -6300,6 +6405,15 @@ function _plainTextStats(summary) {
       );
     }
   }
+  const harnesses = Object.entries(summary.by_harness).filter(([, b]) => b.events > 0).sort((a, b) => b[1].tokens_saved - a[1].tokens_saved);
+  if (harnesses.length > 1) {
+    lines.push("", "## By Harness");
+    for (const [harness, bucket] of harnesses) {
+      lines.push(
+        `  ${harness.padEnd(22)} ${bucket.events.toString().padStart(6)} events  ${fmtBytes(bucket.bytes_saved).padStart(8)}  ${bucket.tokens_saved.toString().padStart(8)} tokens`
+      );
+    }
+  }
   if (summary.by_command.length > 0) {
     lines.push("", "## By Command");
     for (const row of summary.by_command) {
@@ -6373,7 +6487,13 @@ function _buildStatsData(summary, windowDays) {
       bytes: c.bytes_saved,
       tokens: c.tokens_saved,
       events: c.events
-    }))
+    })),
+    by_harness: Object.entries(summary.by_harness).filter(([, b]) => b.events > 0).map(([harness, bucket]) => ({
+      harness,
+      bytes: bucket.bytes_saved,
+      tokens: bucket.tokens_saved,
+      events: bucket.events
+    })).sort((a, b) => b.bytes - a.bytes)
   };
 }
 function renderShortStats(opts) {
@@ -6537,7 +6657,7 @@ var SECRET_PATTERNS = [
   // identifier characters only, so prose that merely mentions a keyword still never reaches
   // a separator and stays unredacted. api[_-]?key covers the apikey and api-key spellings too.
   // `& ; # , :` play two incompatible roles. They separate one field from the next (a query
-  // string, a cookie header, an inline env list), and they are also perfectly ordinary password
+  // string, a cookie header, an inline env list), and they are also perfectly ordinary credential
   // characters. Rejecting them outright got the first role right and the second badly wrong: the
   // match stopped at the first one and left everything after it in plain text, so
   // `password=corr&horse&battery` redacted four characters and printed the rest, and
@@ -6770,6 +6890,8 @@ export {
   SOURCE_HINT,
   formatLocalTimestamp,
   recordStat,
+  recordUnmappedTool,
+  readUnmappedTools,
   summarize,
   _useRichStats,
   renderShortStats,

package/dist/{token-goat-chunk-A62K4XW2.mjs → token-goat-chunk-JU7QESB3.mjs}

@@ -4,14 +4,14 @@ import {
   buildEvent,
   relay,
   relayInProcess
-} from "./token-goat-chunk-LVCBDJVE.mjs";
+} from "./token-goat-chunk-KBVN4ELV.mjs";
 import {
   MAX_STDIN_BYTES,
   readStdinJson
-} from "./token-goat-chunk-AO6MFFTW.mjs";
-import "./token-goat-chunk-2F6TFBZE.mjs";
-import "./token-goat-chunk-TUPJRK7R.mjs";
-import "./token-goat-chunk-44Y77VHR.mjs";
+} from "./token-goat-chunk-5MLXFSRI.mjs";
+import "./token-goat-chunk-AM23GDIS.mjs";
+import "./token-goat-chunk-TF5NT3H5.mjs";
+import "./token-goat-chunk-IVCTQPZD.mjs";
 import "./token-goat-chunk-AO2QD2AG.mjs";
 import "./token-goat-chunk-AEX54RUZ.mjs";
 export {

package/dist/{token-goat-chunk-LVCBDJVE.mjs → token-goat-chunk-KBVN4ELV.mjs}

@@ -23,7 +23,7 @@ import {
   summarizeOutputDelta,
   summarizeResidentContext,
   taskListPruneHint
-} from "./token-goat-chunk-AO6MFFTW.mjs";
+} from "./token-goat-chunk-5MLXFSRI.mjs";
 import {
   BODY_FIRST_TOOL_RESPONSE_KEYS,
   OUTPUT_FIRST_TOOL_RESPONSE_KEYS,
@@ -118,7 +118,7 @@ import {
   wasCliReadThisSession,
   wasFileReadThisSession,
   wasHintShown
-} from "./token-goat-chunk-2F6TFBZE.mjs";
+} from "./token-goat-chunk-AM23GDIS.mjs";
 import {
   canRunWrappedShell,
   compressOutput,
@@ -129,7 +129,7 @@ import {
   isRewriteWorthwhile,
   resolveMinNetSavingsBytes,
   shlexSplit
-} from "./token-goat-chunk-TUPJRK7R.mjs";
+} from "./token-goat-chunk-TF5NT3H5.mjs";
 import {
   VERSION,
   detectHarness,
@@ -149,7 +149,7 @@ import {
   runGit,
   shortFingerprint,
   toKB
-} from "./token-goat-chunk-44Y77VHR.mjs";
+} from "./token-goat-chunk-IVCTQPZD.mjs";
 
 // src/hooks_grep.ts
 function grepIntInput(toolInput, key) {
@@ -620,7 +620,7 @@ import crypto from "node:crypto";
 var TRACKED_SKILL = "token-goat";
 var MAX_COMMANDS_SHOWN = 8;
 async function currentCommandNames() {
-  const { buildProgram } = await import("./token-goat-chunk-J35AKWEQ.mjs");
+  const { buildProgram } = await import("./token-goat-chunk-SE6V7LUZ.mjs");
   return flattenCommandNames(buildCommandManifest(buildProgram()));
 }
 async function recordSkillVersionSnapshot(sessionId, skillName) {