claude-token-saver 3.26.0 → 3.26.2

package/README.en.md

@@ -62,6 +62,7 @@ By run (newest first):
 | 🚨 **No surprise rate limits** | Warns when the 5H/7D window hits 90%; `handoff` backs up your work |
 | 🧠 **Cache waste detection** | Hit rate, TTL, 1M-context detection — spikes diagnosed with issue codes |
 | 🇰🇷 **Korean writing guidance** | Offered at install time, defaulting to your locale ([below](#-korean-writing-guidance)) |
+| 📄 **Document conversion** | pptx/xlsx/pdf/docx become Markdown before the model reads them, so unreadable bytes never reach the context window ([below](#-doc2md--attached-documents-become-markdown-before-the-model-reads-them)) |
 
 ## Not a router — 60 seconds
 
@@ -163,6 +164,9 @@ Run these in your shell (inside Claude Code, the `/claude-token-saver` Skill is
 | `claude-token-saver korean on\|off\|status` | Inject Korean writing guidance at session start and install the write-time check (below) |
 | `claude-token-saver korean lint block\|warn\|off` | How the write-time check handles findings |
 | `claude-token-saver korean lint scope all\|prose` | Check every text file, or documents only |
+| `claude-token-saver doc2md on\|off` | Convert attached documents to Markdown before the model reads them (below) |
+| `claude-token-saver doc2md <file>` | Convert one file by hand. Diagnostic: it prints the refusal reason instead of swallowing it |
+| `claude-token-saver mode ttl=5m\|1h\|auto` | Pin the cache TTL bucket. The default `auto` trusts the measured split, then falls back to gateway detection |
 | `claude-token-saver --version` | Print the installed version |
 | `claude-token-saver update-check` | Is a newer version out? (`--refresh` to ask now, `--dismiss` to mute this version's offer) |
 | `claude-token-saver upgrade` | Install the latest release with the package manager that installed this copy (`--print` shows the command only) |
@@ -374,6 +378,50 @@ Installs with nobody attached — npm `postinstall`, CI, piped stdin — skip th
 > The guidance text comes from [fluent-korean](https://github.com/snflkd/fluent-korean). Copyright (c) 2026 snflkd, MIT License.
 > The wording is unmodified; only the output-style frontmatter was removed. The full license ships with the package at `presets/korean-style/LICENSE-fluent-korean`.
 
+## 📄 doc2md — attached documents become Markdown before the model reads them
+
+`Read` a pptx, xlsx, pdf or docx and the raw bytes go into the context window, where the model cannot read them. This intercepts that `Read`, converts the file once, and hands over the Markdown instead.
+
+**This is opt-in.** Installing the CLI does not turn it on: both commands below are required, and a registered hook with no converter behind it does nothing at all.
+
+```bash
+claude-token-saver doc2md install-converter   # markitdown into a dedicated venv
+claude-token-saver doc2md on                  # register the Read hook
+claude-token-saver doc2md                     # check converter + hook registration
+claude-token-saver doc2md report.pptx         # convert by hand and see the result
+```
+
+The converter goes into a venv this tool owns (`<state dir>/doc2md-venv`): no system interpreter is touched, and uninstalling the CLI takes it along. An existing markitdown on `uv tool` or `PATH` is preferred over building a new one.
+
+Conversion is [markitdown](https://github.com/microsoft/markitdown). Slide numbers, heading levels, tables, speaker notes and per-sheet headings all survive, and non-Latin text comes through intact.
+
+Several things it deliberately does not do:
+
+- **Images are not converted.** markitdown returns nothing for them, and OCR misread resource names in testing (`c5.xlarge` as `c.xlarge`). In a document where those names *are* the content, wrong text is worse than none. The model reads images natively anyway.
+- **A missing converter never fails silently.** The install command is shown once, then the original `Read` proceeds untouched. Repeating the notice on every read would be its own nuisance; saying nothing is how a broken converter hides. Run `doc2md` with no arguments to see the converter and hook registration together.
+- **Conversions never land in your project.** They go under the tool's own state directory with mode `0700`, so there is nothing to add to `.gitignore`. Filenames matching payroll/contract/secret patterns are skipped entirely.
+- **Zip bombs are refused.** pptx/xlsx/docx are zip containers: the declared sizes are checked first, and since those are written by whoever built the file, the real decompressed bytes are counted against a ceiling too.
+- **Spreadsheets are capped by rows, not bytes.** Conversion time tracks row count (measured: a 6.3MB PDF in 0.9s, a 5.8MB workbook in 47.75s). Past 50,000 rows only the head is converted, and **the truncation and the true row count are both stated** in what the model is told.
+
+`claude-token-saver doc2md --clean` empties the conversion cache; `doc2md off` removes the hook. Removal filters for this tool's own entry, so anything else you registered under `PreToolUse` stays.
+
+## 🌐 Behind a gateway (Bedrock / Vertex)
+
+A gateway reports the cache-creation total but never the 5m/1h split. That left the tool unable to tell "nothing cached yet" from "this provider does not say", and the fallback assumed an hour — for a window that is really five minutes on Bedrock, overstating it twelvefold.
+
+Since v3.26.0 the gateway is detected from the model ids in the transcript, which fixes:
+
+- The countdown falls back to 5 minutes, labelled `5m?`. Three grades of certainty get three labels: measured (`5m`), inferred (`5m?`), unknown (`?`).
+- In a 5-minute bucket the countdown colour follows absolute time rather than a percentage. 30% of five minutes is 90 seconds, and green there promised comfort that was not there.
+- The `⚠ 5m TTL` warning finally reaches these users — with different advice, since no subscription plan changes a gateway's TTL.
+- `Extra cost if 5m-only` is only asked of sessions that have 1h writes to lose. Elsewhere the arithmetically honest `+$0` read as an endorsement of the bucket you are already stuck in.
+- Delegated runs dropped for an unpriceable model id show as `🔀 N unresolved` instead of nothing, which used to be indistinguishable from never having delegated.
+- Environment variables set to a `foundation-model` ARN now resolve. An opaque `application-inference-profile` id still does not: guessing at it is how wrong prices enter the ledger.
+
+If the detection is wrong, pin it with `claude-token-saver mode ttl=5m` (or `ttl=1h`). An explicit value outranks the measurement.
+
+One related non-bug: if your session model is already sonnet, a sonnet-delegation (T1) rule can never save anything, because there is no price gap to capture. That is correct, but `route-scan rules` displayed it identically to "no delegations yet", so it now says outright that the rule does not apply at the current default model.
+
 ## Spike issue codes
 
 | Code | Meaning |
@@ -454,6 +502,17 @@ Also update `statusLine.command` in `~/.claude/settings.json` to `claude-token-s
 
 ## Release notes
 
+### v3.26.2 (2026-09-04)
+- **The converter installs itself.** The old instruction was `pip install`, which asks the user to modify a system interpreter — and if they skipped it, the hook sat registered and did nothing. `doc2md install-converter` builds a dedicated venv and puts markitdown in it.
+- **`doc2md` status now reports hook registration too.** Showing only the converter made "hook but no converter" and "converter but no hook" look identical, and both look like a broken feature.
+- **An unknown subcommand under `--hook` prints nothing.** A 3.25.0 global install meeting a settings.json written by 3.26.0 did not recognise `doc2md`, fell through to the default report, and pushed a full statistics table into the hook stream on every `Read`.
+
+### v3.26.0 (2026-09-04)
+- **Attached documents are converted to Markdown before the model reads them.** Reading a pptx/xlsx/pdf/docx put unreadable bytes into the context window. `doc2md on` registers a `Read` hook that converts the file once, caches it outside your project, and points the model at the Markdown. A missing converter is announced once and then gets out of the way, zip bombs are refused, and workbooks past 50,000 rows are converted head-first with the truncation stated. See [doc2md](#-doc2md--attached-documents-become-markdown-before-the-model-reads-them).
+- **TTL display fixed for Bedrock/Vertex sessions.** Gateways never report the per-bucket split, and the fallback assumed an hour — twelvefold too long for a 5-minute-only backend. The gateway is now detected from the model ids, the fallback follows that evidence, and the label reads `5m?` to mark it as inferred. Pin it manually with `mode ttl=5m` if the detection is wrong.
+- **Delegated runs are no longer discarded in silence.** Runs excluded for an unpriceable model id surface as `🔀 N unresolved` on the statusline; previously that was indistinguishable from never having delegated, so an entire tier of rules could report zero with no way to find out why. Environment variables set to a `foundation-model` ARN now resolve as well.
+- **The Korean guidance stopped contradicting itself.** The injected scope claimed code comments while the vendored text disclaimed them twice, leaving the model nothing to decide on. The vendored wording is untouched; the block now states which side wins. The em dash in the attribution line — a mark that guidance itself forbids — became a colon.
+
 ### v3.25.0 (2026-09-04)
 - **The statusline now shows which version is running** — until now the version lived only in the table report's footer, so "which version am I on" meant running a full report. A `--version` flag was added alongside it.
 - **A new release asks at session start** — a statusline cannot open a dialog, so telling and asking are split. The statusline only reports (`⬆ v3.24.0 → 3.25.0`); the SessionStart hook injects a line telling the model to ask the user whether to upgrade. On yes it runs `claude-token-saver upgrade`, which uses the package manager that installed this copy; on no, `update-check --dismiss` mutes that version until a newer one ships.

package/README.md

@@ -62,6 +62,7 @@ $ claude-token-saver route-scan savings      # 모든 금액을 룰 단위까지
 | 🚨 **한도 초과 예방** | 5시간·7일 rate-limit 윈도가 90%에 닿으면 경고하고, `handoff`로 작업을 백업합니다 |
 | 🧠 **캐시 낭비 감지** | 히트율·TTL·1M 컨텍스트를 감지해 토큰 급증 원인을 코드로 진단합니다 |
 | 🇰🇷 **한국어 문체 교정** | 한국어 환경이면 자동으로 켜집니다 ([아래](#-한국어-문체-지침)) |
+| 📄 **문서 자동 변환** | pptx·xlsx·pdf·docx 를 읽기 전에 Markdown 으로 바꿔 읽지 못하는 바이트가 컨텍스트에 올라가지 않게 합니다 ([아래](#-doc2md-첨부-문서를-읽기-전에-markdown-으로-바꿉니다)) |
 
 ## 라우터가 아닙니다: 60초 설명
 
@@ -371,18 +372,23 @@ npm의 `postinstall`이나 CI처럼 사람이 붙어 있지 않은 설치에서
 
 pptx·xlsx·pdf·docx 를 그대로 `Read` 하면 모델이 읽지 못하는 바이트가 컨텍스트에 그대로 올라갑니다. 이 기능은 그 `Read` 를 가로채 파일을 한 번 변환해 두고, 원본 대신 변환본을 읽게 합니다.
 
+**이 기능은 옵트인입니다.** 설치만으로는 켜지지 않고, 아래 두 명령을 모두 실행해야 동작합니다. 훅만 등록하고 변환기가 없으면 아무 일도 일어나지 않습니다.
+
 ```bash
-pip install "markitdown[pptx,pdf,xlsx,docx]"   # 변환기는 파이썬 패키지입니다
-claude-token-saver doc2md on                   # Read 훅 등록
-claude-token-saver doc2md 보고서.pptx           # 직접 변환해 결과 확인
+claude-token-saver doc2md install-converter   # 전용 venv에 markitdown 설치
+claude-token-saver doc2md on                  # Read 훅 등록
+claude-token-saver doc2md                     # 변환기·훅 등록 상태 확인
+claude-token-saver doc2md 보고서.pptx          # 직접 변환해 결과 확인
 ```
 
+변환기는 도구 전용 venv(`<상태 디렉터리>/doc2md-venv`)에 설치합니다. 시스템 파이썬을 건드리지 않고, CLI를 지우면 함께 사라집니다. 이미 `uv tool` 이나 다른 경로에 markitdown 이 있으면 그쪽을 먼저 씁니다.
+
 변환은 [markitdown](https://github.com/microsoft/markitdown)이 담당하며, 슬라이드 번호와 제목 계층, 표, 발표자 노트, 시트 구분이 모두 남습니다. 한글도 깨지지 않습니다.
 
 몇 가지는 의도적으로 하지 않습니다.
 
 - **이미지는 변환하지 않습니다.** markitdown 이 빈 결과를 돌려주고, OCR 은 실측에서 리소스 이름을 틀리게 읽었습니다(`c5.xlarge` 를 `c.xlarge` 로). 이름 자체가 내용인 문서에서는 텍스트가 없느니만 못합니다. 모델이 이미지는 직접 읽습니다.
-- **markitdown 이 없으면 조용히 실패하지 않습니다.** 설치 명령을 한 번 안내한 뒤 원본 `Read` 를 그대로 통과시킵니다. 매번 알리면 그것대로 방해가 되고, 아무 말도 하지 않으면 고장을 숨기게 됩니다.
+- **변환기가 없으면 조용히 실패하지 않습니다.** 설치 명령을 한 번 안내한 뒤 원본 `Read` 를 그대로 통과시킵니다. 매번 알리면 그것대로 방해가 되고, 아무 말도 하지 않으면 고장을 숨기게 됩니다. `doc2md` 를 인자 없이 실행하면 변환기와 훅 등록 상태를 한 번에 확인할 수 있습니다.
 - **변환본은 프로젝트 안에 남기지 않습니다.** 도구의 상태 디렉터리 아래 권한 `0700` 으로 저장하므로 `.gitignore` 에 무엇을 추가할 필요가 없습니다. 파일명이 급여·계약·개인정보 같은 패턴에 걸리면 아예 변환하지 않습니다.
 - **압축 폭탄은 막습니다.** pptx·xlsx·docx 는 zip 컨테이너입니다. 선언된 크기를 먼저 걸러 내고, 선언은 조작될 수 있으므로 실제 해제 바이트도 상한과 대조합니다.
 - **엑셀은 행 수로 자릅니다.** 변환 시간은 파일 크기가 아니라 행 수를 따릅니다(실측: PDF 6.3MB 0.9초, 엑셀 5.8MB 47.75초). 5만 행을 넘으면 앞부분만 변환하고, **잘랐다는 사실과 전체 행 수를 안내에 함께 적습니다.**
@@ -462,6 +468,11 @@ npm uninstall -g claude-cache-monitor && npm i -g claude-token-saver
 
 ## 릴리스 노트
 
+### v3.26.2 (2026-09-04)
+- **doc2md 변환기를 도구가 직접 설치합니다.** 지금까지의 안내는 `pip install` 이었는데, 시스템 파이썬을 건드리라는 요구인 데다 실행하지 않으면 훅만 등록된 채 아무 일도 일어나지 않았습니다. `doc2md install-converter` 가 전용 venv 를 만들어 markitdown 을 넣습니다.
+- **`doc2md` 상태 출력에 훅 등록 여부를 함께 적습니다.** 변환기만 알려 주면 "훅은 있는데 변환기가 없다"와 "변환기는 있는데 훅이 없다"가 똑같이 아무 일도 안 하는 상태로 보여서, 어느 쪽이 빠졌는지 알 수 없었습니다.
+- **모르는 서브커맨드를 `--hook` 으로 부르면 아무것도 출력하지 않습니다.** 3.25.0 전역 설치본이 3.26.0 이 쓴 `settings.json` 을 만나면 `doc2md` 를 인식하지 못하고 기본 리포트로 흘러가, `Read` 할 때마다 통계 표 전문을 훅 스트림에 밀어 넣었습니다.
+
 ### v3.26.0 (2026-09-04)
 - **첨부 문서를 읽기 전에 Markdown 으로 변환합니다.** pptx·xlsx·pdf·docx 를 그대로 `Read` 하면 모델이 읽지 못하는 바이트가 컨텍스트에 올라갑니다. `doc2md on` 으로 `Read` 훅을 등록하면 파일을 한 번 변환해 캐시에 두고 변환본을 읽게 합니다. 변환기가 없으면 안내를 한 번만 하고 원본 `Read` 를 통과시키며, 압축 폭탄은 막고, 5만 행이 넘는 엑셀은 앞부분만 변환한 뒤 잘랐다는 사실을 함께 알립니다. 자세한 내용은 [doc2md](#-doc2md-첨부-문서를-읽기-전에-markdown-으로-바꿉니다) 절을 참고하십시오.
 - **Bedrock·Vertex 경유 환경의 TTL 표시를 바로잡았습니다.** 게이트웨이는 버킷별 분해 값을 내려보내지 않는데, 판정 불가일 때 1시간을 기본값으로 잡고 있었습니다. 5분 버킷만 제공하는 환경에서 남은 시간이 최대 12배로 부풀어 보였습니다. 이제 모델 ID로 게이트웨이를 감지해 5분을 기본값으로 쓰고, 라벨을 `5m?` 로 적어 추정임을 밝힙니다. `mode ttl=5m` 으로 직접 지정할 수도 있습니다.

package/bin/cli.js

@@ -83,7 +83,23 @@ function readUpdateChip() {
   }
 }
 
+// Subcommands this build knows how to run. Used only by the guard below.
+const KNOWN_SUBCOMMANDS = new Set([
+  'last', 'brief', 'history', 'handoff', 'install', 'uninstall', 'mode', 'korean',
+  'doc2md', 'harness', 'route-scan', 'compact-window', 'update-check', 'upgrade',
+]);
+
 async function main() {
+  // A hook invocation names a subcommand and expects either silence or that
+  // subcommand's own protocol on stdout. If this build does not have the
+  // subcommand — an older global install against a newer settings.json, which
+  // is exactly what a mid-upgrade machine looks like — falling through to the
+  // default report would push a full table into the hook stream on every
+  // matching tool call. Say nothing instead.
+  if (hasFlag('--hook') && args[0] && !KNOWN_SUBCOMMANDS.has(args[0])) {
+    return;
+  }
+
   // Subcommand: last — print the most recent warning + how to handle it.
   // Designed for the auto-trigger skill so the user immediately sees
   // "what just fired and how to fix it" without having to read the whole

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-token-saver",
-  "version": "3.26.0",
+  "version": "3.26.2",
   "description": "Route the easy work your expensive Claude model keeps repeating down to haiku/sonnet — post-hoc session analysis, no realtime router, no extra LLM calls.",
   "type": "module",
   "bin": {

package/src/commands/doc2md.js

@@ -15,6 +15,27 @@ import { join } from 'node:path';
 
 const require = createRequire(import.meta.url);
 
+/**
+ * Whether the Read hook is actually in settings.json.
+ *
+ * Status output that reports only the converter is misleading: a working
+ * converter with no hook, and a hook with no converter, both add up to
+ * "nothing happens", and the user has no way to tell which half is missing.
+ */
+function hookRegistered() {
+  try {
+    const { homedir } = require('node:os');
+    const settings = JSON.parse(
+      require('node:fs').readFileSync(join(homedir(), '.claude', 'settings.json'), 'utf8'),
+    );
+    return (settings?.hooks?.PreToolUse || []).some((m) =>
+      (m.hooks || []).some((h) => typeof h.command === 'string' && h.command.includes('doc2md --hook')),
+    );
+  } catch {
+    return false;
+  }
+}
+
 export async function run({ args, hasFlag }) {
   const doc2md = require('../doc2md.cjs');
   const sub = args[1];
@@ -37,16 +58,30 @@ export async function run({ args, hasFlag }) {
     return;
   }
 
+  if (sub === 'install-converter') {
+    const res = doc2md.installConverter({ onProgress: (m) => console.log(`  ${m}`) });
+    if (res.ok) {
+      console.log(`✓ converter ready: ${res.python}`);
+      return;
+    }
+    console.error(`✗ ${res.reason}: ${res.detail}`);
+    process.exitCode = 1;
+    return;
+  }
+
   if (sub === 'on') {
     const { installDoc2mdHook } = await import('../installer.js');
     const res = installDoc2mdHook();
     console.log(res.action === 'skipped'
       ? `✗ ${res.reason}`
       : `✓ Read hook ${res.action} (${res.path})`);
+    // A registered hook with no converter behind it does nothing at all, and
+    // says nothing about it either, which reads as a broken feature. Offer the
+    // one command that closes the gap right where the gap is visible.
     const python = doc2md.findInterpreter();
     console.log(python
       ? `  converter: markitdown via ${python}`
-      : `  converter: not installed yet — ${doc2md.INSTALL_HINT}`);
+      : `  converter: missing — run \`${doc2md.INSTALL_HINT}\` or the hook will do nothing`);
     return;
   }
 
@@ -95,6 +130,8 @@ export async function run({ args, hasFlag }) {
   console.log(`  formats:   ${doc2md.TARGET_EXTENSIONS.join(' ')}`);
   console.log(`  converter: ${python ? `markitdown via ${python}` : `not installed — ${doc2md.INSTALL_HINT}`}`);
   console.log(`  cache:     ${dir} (${cached} file(s))`);
+  console.log(`  hook:      ${hookRegistered() ? 'registered on Read' : 'not registered'}`);
   console.log('');
+  if (!python) console.log(`Install the converter: ${doc2md.INSTALL_HINT}`);
   console.log('Enable with: claude-token-saver doc2md on');
 }

package/src/doc2md.cjs

@@ -158,6 +158,11 @@ function findInterpreter() {
   const candidates = [];
   if (process.env.CTS_DOC2MD_PYTHON) candidates.push(process.env.CTS_DOC2MD_PYTHON);
   candidates.push(
+    // The tool's own venv, created by `doc2md install-converter`. First
+    // because it is the only one this tool controls: telling people to
+    // `pip install` into the system interpreter is how a token-saving CLI
+    // ends up owning a break in someone else's project.
+    managedPython(),
     path.join(os.homedir(), '.local', 'share', 'uv', 'tools', 'markitdown', 'bin', 'python'),
     path.join(os.homedir(), '.local', 'bin', 'markitdown-python'),
     'python3',
@@ -178,6 +183,60 @@ function findInterpreter() {
 
 const CONVERTER = path.join(__dirname, '..', 'presets', 'doc2md', 'convert.py');
 
+/** Path to the interpreter inside the venv this tool manages. */
+function managedPython() {
+  const dir = path.join(userDataDir(), 'doc2md-venv');
+  return process.platform === 'win32'
+    ? path.join(dir, 'Scripts', 'python.exe')
+    : path.join(dir, 'bin', 'python');
+}
+
+const MARKITDOWN_SPEC = 'markitdown[pptx,pdf,xlsx,docx]';
+
+/**
+ * Build the managed venv and install markitdown into it.
+ *
+ * Kept behind an explicit command: creating a 300MB virtualenv is not
+ * something to do because somebody opened a spreadsheet once. But once asked
+ * for, it goes somewhere this tool owns, so uninstalling the CLI takes the
+ * whole thing with it and no system interpreter is touched.
+ */
+function installConverter({ onProgress = () => {} } = {}) {
+  const venv = path.join(userDataDir(), 'doc2md-venv');
+  const target = managedPython();
+
+  if (!fs.existsSync(target)) {
+    onProgress(`creating ${venv}`);
+    let created = false;
+    for (const base of ['python3', 'python']) {
+      const r = spawnSync(base, ['-m', 'venv', venv], { encoding: 'utf8', timeout: 180_000 });
+      if (r.status === 0) { created = true; break; }
+    }
+    if (!created) {
+      return { ok: false, reason: 'no-python', detail: 'no python3 with the venv module on PATH' };
+    }
+  }
+
+  onProgress(`installing ${MARKITDOWN_SPEC}`);
+  const install = spawnSync(target, ['-m', 'pip', 'install', '--quiet', MARKITDOWN_SPEC], {
+    encoding: 'utf8',
+    timeout: 900_000,
+  });
+  if (install.status !== 0) {
+    return { ok: false, reason: 'pip-failed', detail: (install.stderr || '').slice(0, 400) };
+  }
+
+  // The probe is the actual acceptance test: pip can exit 0 and still leave an
+  // interpreter that cannot import what was asked for.
+  const probe = spawnSync(target, ['-c', 'import markitdown'], { timeout: 60_000, stdio: 'ignore' });
+  if (probe.status !== 0) {
+    return { ok: false, reason: 'import-failed', detail: 'installed, but markitdown does not import' };
+  }
+  interpreterCache = target;
+  clearNotice();
+  return { ok: true, python: target };
+}
+
 /**
  * Convert one file. Returns `{ ok: true, cacheFile, meta }`, or
  * `{ ok: false, reason, detail }` where reason is one of:
@@ -258,6 +317,18 @@ function noticeAlreadyShown() {
   }
 }
 
+/**
+ * Forget that the notice was shown.
+ *
+ * Called after the converter is installed, so that if it later disappears the
+ * user is told once more instead of meeting permanent silence.
+ */
+function clearNotice() {
+  try {
+    fs.rmSync(noticePath(), { force: true });
+  } catch { /* nothing to forget */ }
+}
+
 function markNoticeShown() {
   try {
     fs.mkdirSync(userDataDir(), { recursive: true });
@@ -265,7 +336,7 @@ function markNoticeShown() {
   } catch { /* an unwritable state dir just means the notice repeats */ }
 }
 
-const INSTALL_HINT = 'pip install "markitdown[pptx,pdf,xlsx,docx]"';
+const INSTALL_HINT = 'claude-token-saver doc2md install-converter';
 
 /**
  * Decide what to tell Claude Code about one PreToolUse(Read) payload.
@@ -364,6 +435,10 @@ module.exports = {
   TARGET_EXTENSIONS,
   MAX_SOURCE_BYTES,
   INSTALL_HINT,
+  MARKITDOWN_SPEC,
+  managedPython,
+  installConverter,
+  clearNotice,
   cacheDir,
   cachePathFor,
   metaPathFor,