feat: OCR scans with tesseract, drop docling from the default path.

pdftotext still wins on born-digital PDFs. Empty text layers go through
pdftoppm + tesseract eng+deu. Optional OCR_ENGINE=paddle. Gitea #6.

.github/workflows/ci.yml

@@ -72,10 +72,26 @@ jobs:
           uv run python bin/kb/index --rebuild --json
           KB_ROOT="$PWD" /tmp/brain-eval --json
 
+  ocr:
+    name: OCR (tesseract fixture)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+      - name: Install tesseract + poppler
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            tesseract-ocr tesseract-ocr-eng tesseract-ocr-deu poppler-utils
+      - name: Go OCR tests (synthetic HELLO PNG)
+        run: go test ./internal/ocr -count=1
+
   release:
     name: Release (semver)
     if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-    needs: test
+    needs: [test, ocr]
     runs-on: ubuntu-latest
     permissions:
       contents: write

AGENTS.md

@@ -42,7 +42,7 @@ skills/       in-project agent skills (vendored, no external links)
 bin/          self-describing tools bin/{subject}/{method}.go (shebang)
 bin/brain/    search.go serve.go index.go add.go get.go stats.go eval.go watch.go
 bin/chats/    sync.go import.go facts.go apply.go; libs in internal/chats
-bin/mail/     sync.go import.go (index_mail → brain/index.go)
+bin/mail/     sync.go import.go ocr.go (index_mail → brain/index.go)
 bin/markdown/ import.go (H2 leaf split; Python bin/md/import fallback)
 bin/postgres/ query.go (read-only YAML)
 bin/git/      import.go (go-git history; Python shim execs it)
@@ -71,9 +71,9 @@ bin/brain/index.go --rebuild --with-facts --with-chats
 - `sync` (Go) downloads messages + attachments; Gmail uses paginated list +
   `body.attachmentId` (not partId) for attachments.
 - `import` converts body + attachments to markdown. PDFs use poppler
-  `pdftotext -layout` fast path (~15ms); textless/scanned PDFs fall back to
-  docling (isolated subprocess — its native onnx can segfault the parent).
-  Conversion never touches the brain DB (crash safety).
+  `pdftotext -layout` fast path (~15ms); textless/scanned PDFs use
+  `pdftoppm` + tesseract `eng+deu` (`bin/mail/ocr.go`). Optional
+  `OCR_ENGINE=paddle`. Conversion never touches the brain DB (crash safety).
 - `index_mail` is a deprecation shim for `bin/brain/index.go --rebuild`. Bulk
   rebuild still deletes `var/kb.lbug` and creates FTS/HNSW last. Single-leaf
   write is `bin/brain/add.go` (safe while indexes exist; do not DROP INDEX).
@@ -101,6 +101,7 @@ bin/git/import.go [REPO] [--json] [--limit N]     # go-git history → commit le
 bin/web/search.go "query" [--json]                # SearXNG; throttled ≠ absence
 bin/reasoner/bakeoff.go [--model ID] [--json]     # D18 CPU tool-call bake-off
 bin/postgres/query.go --profile onlyoffice -c 'SELECT 1'
+bin/mail/ocr.go <image|pdf>                      # tesseract eng+deu (scans)
 bin/md/tables                                     # what the graph holds → YAML
 bin/brain/deduce "question"                       # thinking wrapper
 ```

Dockerfile

@@ -16,6 +16,10 @@ ENV PYTHONUNBUFFERED=1 \
 
 WORKDIR /app
 RUN id -u 2dph 2>/dev/null || useradd --create-home --uid 1001 2dph
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+         poppler-utils tesseract-ocr tesseract-ocr-eng tesseract-ocr-deu \
+    && rm -rf /var/lib/apt/lists/*
 
 COPY requirements.lock.txt /tmp/requirements.lock.txt
 RUN python -m pip install --no-cache-dir -r /tmp/requirements.lock.txt \

PLAN.md

@@ -4,8 +4,9 @@ A brain that loves facts and deduction. Evidence-first knowledge graph + hybrid
 RAG over the operational Brain/ops/eSlider stack. Built like Sherlock
 Holmes: nothing is asserted unless it has proof.
 
-Status: **in progress** — read path + MCP work; v1 goal is [epic #16](https://git.produktor.io/eSlider/2dph/issues/16)
-(milestone [v1 detective brain](https://git.produktor.io/eSlider/2dph/milestone/12)).
+Status: **v1 in** (epic [#16](https://git.produktor.io/eSlider/2dph/issues/16) closed).
+v2 board: milestone [v2](https://git.produktor.io/eSlider/2dph/milestone/13) — OCR [#6](https://git.produktor.io/eSlider/2dph/issues/6),
+[#29](https://git.produktor.io/eSlider/2dph/issues/29) OQ1, [#30](https://git.produktor.io/eSlider/2dph/issues/30) OQ3.
 Gap: [docs/roadmap.md](docs/roadmap.md).
 
 ## What
@@ -74,6 +75,7 @@ detective method: **a fact needs ≥2 independent sources or it is
     reasoner/bakeoff.go     CPU tool-call bake-off (D18; OpenAI tools)
     chats/sync.go import.go facts.go apply.go
                             (libs in internal/chats; no chats index)
+    mail/ocr.go             tesseract eng+deu (pdftoppm scans)
     md/import               (deprecated; bin/markdown/import.go)
     brain/extract  brain/audit   brain/deduce    (thinking wrapper)
     web/search               (deprecated shim → web/search.go)
@@ -115,10 +117,13 @@ Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
 ## Open questions (v2)
 
 - OQ1: mutually-contradicting evidence — how to resolve (authority weighting,
-  temporal freshness, audit adjudication). **v2**; does not block epic #16.
-- OQ2: OCR — poppler `pdftotext` fast-path exists; scans still docling.
-  [#6](https://git.produktor.io/eSlider/2dph/issues/6) (v2, does not block #16).
+  temporal freshness, audit adjudication). **v2**; [#29](https://git.produktor.io/eSlider/2dph/issues/29).
+- OQ2: OCR — **in**. `pdftotext -layout` first; scans `pdftoppm` + tesseract
+  `eng+deu` (`bin/mail/ocr.go`, `internal/ocr`). No gocv, no gosseract CGO
+  (D21 Zig owns Ladybug CGO). Optional `OCR_ENGINE=paddle` / compose profile
+  `ocr-paddle`. Docling left the default path. [#6](https://git.produktor.io/eSlider/2dph/issues/6).
 - OQ3: optional duckdb-md layer for `SELECT … FORMAT MARKDOWN` export/write-back.
+  [#30](https://git.produktor.io/eSlider/2dph/issues/30).
 - OQ4: YAML-first storage for leafs — deferred: JSON is ~10x faster to
   serialize and unambiguous; YAML only where humans edit files.
 
@@ -127,7 +132,8 @@ Common props on every node/edge: `root`, `confidence`, `evidence[]`, `how`,
 1. `bin/mail/sync.go` (Go, 8 workers) — paginated Gmail/OnlyOffice download.
    Gmail attachments key off `body.attachmentId`, not MIME `partId`.
 2. `bin/mail/import.go --from-raw` — message.json → message.md; PDFs via
-   `pdftotext -layout` (~15ms) with docling subprocess fallback; ICS sidecars
+   `pdftotext -layout` (~15ms); textless/scanned PDFs `pdftoppm` + tesseract
+   `eng+deu`. ICS sidecars
    Latin-1→UTF-8 normalized.
 3. `bin/brain/index.go --rebuild` — fresh rebuild (repo corpus + mail) because ladybug
    corrupts its WAL on bulk-insert into an already-indexed DB. Conversion and
@@ -177,4 +183,4 @@ Narrative: [docs/roadmap.md](docs/roadmap.md).
 | 4 | [#15](https://git.produktor.io/eSlider/2dph/issues/15) | **in** — lever/loop documented (`search` → `get` → `audit`). |
 | 5 | [#19](https://git.produktor.io/eSlider/2dph/issues/19) | **in** — CI recall SoT is `bin/brain/eval.go` via Zig. Python `bin/kb/eval` stays as an explicit fallback. |
 
-Does **not** block epic close: [#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR, OQ1, OQ3, OQ4.
+Does **not** block epic close: OQ1 [#29](https://git.produktor.io/eSlider/2dph/issues/29), OQ3 [#30](https://git.produktor.io/eSlider/2dph/issues/30), OQ4. OCR [#6](https://git.produktor.io/eSlider/2dph/issues/6) is **in**.

bin/mail/import

@@ -7,7 +7,7 @@
   bin/mail/import --since 2026-01-01    only messages after a date
   bin/mail/import --limit 50            cap messages per run
   bin/mail/import --no-attachments      body only, skip attachment conversion
-  bin/mail/import --ocr                OCR scanned PDFs/images via docling
+  bin/mail/import --ocr                OCR images (PDFs OCR when textless)
   bin/mail/import --dry-run            list messages without writing anything
 
 Writes one directory per message: var/mail/{folder}/{message_id}/
@@ -16,10 +16,11 @@ Writes one directory per message: var/mail/{folder}/{message_id}/
   attachments/*.md          converted attachment content
 
 Indexing is a separate step (`bin/brain/index.go --rebuild`): conversion can
-crash in native docling and must not leave the brain DB mid-transaction.
+crash and must not leave the brain DB mid-transaction.
 
-Requires ONLYOFFICE_URL/USER/PASS in .env (or env). Idempotent: a message
-already present (message.md exists) is skipped unless --force.
+Requires ONLYOFFICE_URL/USER/PASS in .env (or env) except `--from-raw`.
+Idempotent: a message already present (message.md exists) is skipped unless
+--force.
 """
 from __future__ import annotations
 
@@ -41,10 +42,10 @@ from mailconv import (  # noqa: E402
     IMAGE_SUFFIXES,
     LEGACY_OFFICE_SUFFIXES,
     TEXT_SUFFIXES,
+    convert_pdf,
     html_to_markdown,
-    is_convertible,
     normalize_markdown,
-    subject_to_filename,
+    ocr_image,
     zip_extract_safe,
 )
 
@@ -147,9 +148,9 @@ def convert_file_to_md(path: Path, ocr: bool) -> str | None:
         except Exception as e:
             return f"\n<!-- conversion failed: {e} -->\n"
     if suffix == ".pdf":
-        return _convert_pdf(path, ocr)
+        return convert_pdf(path, ocr)
     if suffix in IMAGE_SUFFIXES and ocr:
-        return _convert_pdf(path, ocr)
+        return ocr_image(path) or "\n<!-- ocr unavailable -->\n"
     if suffix in LEGACY_OFFICE_SUFFIXES:
         return _convert_legacy(path)
     if suffix in ARCHIVE_SUFFIXES:
@@ -157,67 +158,6 @@ def convert_file_to_md(path: Path, ocr: bool) -> str | None:
     return None
 
 
-def _convert_pdf(path: Path, ocr: bool) -> str:
-    """Convert one PDF to markdown.
-
-    Fast path: poppler's pdftotext (-layout) extracts exact text from
-    born-digital PDFs in ~15ms vs docling's 1-3s. Only textless PDFs (scanned
-    pages, layout-heavy) fall back to docling, which runs isolated in a
-    subprocess because its native onnx/RT-DETR has segfaulted the main process.
-    """
-    text = _pdf_fast_text(path)
-    if ocr or text is None or not text.strip():
-        return _convert_pdf_docling(path, ocr)
-    return normalize_markdown(text)
-
-
-def _pdf_fast_text(path: Path) -> str | None:
-    """pdftotext -layout; None when poppler is unavailable (or the PDF has no text layer)."""
-    try:
-        proc = subprocess.run(
-            ["pdftotext", "-layout", str(path), "-"],
-            capture_output=True, timeout=60)
-    except (OSError, subprocess.TimeoutExpired):
-        return None
-    if proc.returncode != 0:
-        return None
-    return proc.stdout.decode("utf-8", errors="replace")
-
-
-def _convert_pdf_docling(path: Path, ocr: bool) -> str:
-    try:
-        proc = subprocess.run(
-            [sys.executable, os.path.abspath(__file__), "--pdf-worker", str(path),
-             "--ocr" if ocr else "--no-ocr"],
-            capture_output=True, text=True, timeout=600)
-    except subprocess.TimeoutExpired:
-        return "\n<!-- pdf conversion timed out -->\n"
-    if proc.returncode != 0:
-        tail = proc.stderr.strip().splitlines()[-3:]
-        return f"\n<!-- pdf conversion failed: {proc.returncode}: {' | '.join(tail)} -->\n"
-    return proc.stdout
-
-
-def _pdf_worker(path: Path, ocr: bool) -> None:
-    """docling worker entry: prints converted markdown on stdout, exits non-zero on error."""
-    try:
-        from docling.document_converter import DocumentConverter, PdfFormatOption
-        from docling.datamodel.pipeline_options import PdfPipelineOptions
-        opts = PdfPipelineOptions()
-        opts.do_ocr = bool(ocr)
-        opts.do_table_structure = True
-        conv = DocumentConverter(format_options={"pdf": PdfFormatOption(pipeline_options=opts)})
-        res = conv.convert(str(path))
-        sys.stdout.write(normalize_markdown(res.document.export_to_markdown()))
-        sys.exit(0)
-    except Exception as e:
-        # errors/stacktraces to stderr; the caller only reports a one-liner
-        print(f"pdf-worker: {e}", file=sys.stderr)
-        import traceback
-        traceback.print_exc(file=sys.stderr)
-        sys.exit(1)
-
-
 def _convert_legacy(path: Path) -> str:
     """Legacy .doc/.xls/.ppt -> md via pandoc (installed) or a stub."""
     try:
@@ -356,19 +296,12 @@ def main(argv: list[str]) -> int:
     p.add_argument("--from-raw", default="",
                    help="convert Go-synced dirs (var/mail/<folder>/<id>/message.json) to markdown")
     p.add_argument("--no-attachments", action="store_true", help="skip attachment download+convert")
-    p.add_argument("--ocr", action="store_true", help="OCR scanned PDFs/images via docling")
+    p.add_argument("--ocr", action="store_true", help="OCR images (PDFs OCR when textless)")
     p.add_argument("--force", action="store_true", help="re-import even if message.md exists")
     p.add_argument("--dry-run", action="store_true", help="list messages, write nothing")
     p.add_argument("--json", action="store_true")
-    p.add_argument("--pdf-worker", default="", help=argparse.SUPPRESS)
-    p.add_argument("--no-ocr", action="store_true", help=argparse.SUPPRESS)
     a = p.parse_args(argv)
 
-    if a.pdf_worker:
-        _pdf_worker(Path(a.pdf_worker), ocr=not a.no_ocr)
-        return 0
-
-    conf = load_env()
     fid = folder_id(a.folder)
     out_root = ROOT / "var" / "mail"
     summary: list[dict] = []
@@ -394,6 +327,7 @@ def main(argv: list[str]) -> int:
                                      target_dir=msg_dir.parent))
             summary.append(entry)
     else:
+        conf = load_env()
         OOCLIENT = OOClient(conf)
         if a.id:
             messages = [{"id": i} for i in a.id]

bin/mail/ocr.go

@@ -0,0 +1,48 @@
+//usr/bin/env go run -tags=mail_ocr "$0" "$@"; exit
+//go:build mail_ocr
+//
+// bin/mail/ocr.go - OCR an image or scanned PDF (tesseract eng+deu).
+//
+//	./bin/mail/ocr.go scan.png
+//	./bin/mail/ocr.go scan.pdf
+//	OCR_ENGINE=paddle ./bin/mail/ocr.go scan.png
+//
+// PDFs try pdftotext -layout first; empty text layer uses pdftoppm + tesseract.
+// No gocv. Tesseract CGO bindings are not used (D21 Zig owns Ladybug CGO).
+// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
+package main
+
+import (
+	"fmt"
+	"os"
+	"strings"
+
+	"github.com/eSlider/2dph/internal/ocr"
+)
+
+func main() {
+	os.Exit(run(os.Args[1:]))
+}
+
+func run(args []string) int {
+	if len(args) != 1 || strings.HasPrefix(args[0], "-") {
+		fmt.Fprintln(os.Stderr, `usage: bin/mail/ocr.go <image|pdf>`)
+		return 2
+	}
+	path := args[0]
+	var (
+		text string
+		err  error
+	)
+	if strings.HasSuffix(strings.ToLower(path), ".pdf") {
+		text, err = ocr.PDFFile(path)
+	} else {
+		text, err = ocr.ImageFile(path)
+	}
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "mail/ocr: %v\n", err)
+		return 1
+	}
+	fmt.Println(text)
+	return 0
+}

bin/tools/mailconv.py

@@ -7,7 +7,10 @@ offline against fixtures.
 from __future__ import annotations
 
 import html
+import os
 import re
+import subprocess
+import tempfile
 import zipfile
 from pathlib import Path
 
@@ -18,9 +21,10 @@ OFFICE_SUFFIXES = {".docx", ".pptx", ".xlsx", ".html", ".htm", ".epub", ".eml",
 PDF_SUFFIXES = {".pdf"}
 IMAGE_SUFFIXES = {".png", ".jpg", ".jpeg", ".gif", ".bmp", ".tiff", ".tif", ".webp"}
 ARCHIVE_SUFFIXES = {".zip"}
-# Legacy binary Office (doc/xls/ppt) — markitdown/docling skip them; we try
+# Legacy binary Office (doc/xls/ppt) — markitdown skip them; we try
 # pandoc first, else leave a stub.
 LEGACY_OFFICE_SUFFIXES = {".doc", ".xls", ".ppt"}
+TESS_LANG = "eng+deu"
 
 CONVERTIBLE_SUFFIXES = (
     TEXT_SUFFIXES | OFFICE_SUFFIXES | PDF_SUFFIXES | IMAGE_SUFFIXES | ARCHIVE_SUFFIXES | LEGACY_OFFICE_SUFFIXES
@@ -146,3 +150,82 @@ def zip_extract_safe(zip_path: Path, dest: Path) -> list[Path]:
 
 def is_convertible(suffix: str) -> bool:
     return suffix.lower() in CONVERTIBLE_SUFFIXES
+
+
+def convert_pdf(path: Path, ocr: bool = False) -> str:
+    """pdftotext -layout first; empty text layer → pdftoppm + tesseract.
+
+    `ocr` is unused for born-digital PDFs (text layer wins). Scans OCR
+    automatically. This path never execs an ONNX document converter.
+    """
+    del ocr  # scans OCR when the text layer is empty; flag is for images
+    text = pdf_fast_text(path)
+    if text and text.strip():
+        return normalize_markdown(text)
+    scanned = ocr_pdf(path)
+    if scanned and scanned.strip():
+        return normalize_markdown(scanned)
+    if text:
+        return normalize_markdown(text)
+    return "\n<!-- pdf has no text layer (ocr unavailable) -->\n"
+
+
+def pdf_fast_text(path: Path) -> str | None:
+    """pdftotext -layout; None when poppler is missing or the command fails."""
+    try:
+        proc = subprocess.run(
+            ["pdftotext", "-layout", str(path), "-"],
+            capture_output=True, timeout=60)
+    except (OSError, subprocess.TimeoutExpired):
+        return None
+    if proc.returncode != 0:
+        return None
+    return proc.stdout.decode("utf-8", errors="replace")
+
+
+def ocr_pdf(path: Path) -> str:
+    """Rasterize with pdftoppm and OCR each page (tesseract or paddle)."""
+    try:
+        with tempfile.TemporaryDirectory(prefix="2dph-ocr-") as tmp:
+            prefix = str(Path(tmp) / "page")
+            proc = subprocess.run(
+                ["pdftoppm", "-png", "-r", "200", str(path), prefix],
+                capture_output=True, timeout=120)
+            if proc.returncode != 0:
+                return ""
+            pages = sorted(Path(tmp).glob("page*.png"))
+            parts = [ocr_image(p) for p in pages]
+            return "\n\n".join(p for p in parts if p and p.strip())
+    except (OSError, subprocess.TimeoutExpired):
+        return ""
+
+
+def ocr_image(path: Path) -> str:
+    engine = os.environ.get("OCR_ENGINE", "tesseract")
+    if engine == "paddle":
+        return _ocr_paddle(path)
+    return _ocr_tesseract(path)
+
+
+def _ocr_tesseract(path: Path) -> str:
+    try:
+        proc = subprocess.run(
+            ["tesseract", str(path), "stdout", "-l", TESS_LANG, "--psm", "6"],
+            capture_output=True, timeout=120)
+    except (OSError, subprocess.TimeoutExpired):
+        return ""
+    if proc.returncode != 0:
+        return ""
+    return proc.stdout.decode("utf-8", errors="replace").strip()
+
+
+def _ocr_paddle(path: Path) -> str:
+    try:
+        proc = subprocess.run(
+            ["paddleocr", "ocr", "-i", str(path)],
+            capture_output=True, timeout=180)
+    except (OSError, subprocess.TimeoutExpired):
+        return ""
+    if proc.returncode != 0:
+        return ""
+    return proc.stdout.decode("utf-8", errors="replace").strip()

bin/tools/test_bin_layout.py

@@ -136,6 +136,33 @@ class BinLayoutTest(unittest.TestCase):
             "index_mail must point at bin/brain/index.go",
         )
 
+    def test_mail_ocr_is_tesseract_not_docling(self) -> None:
+        self._assert_shebang("bin/mail/ocr.go")
+        ocr = (ROOT / "bin" / "mail" / "ocr.go").read_text()
+        self.assertIn("internal/ocr", ocr)
+        self.assertIn("mail_ocr", ocr)
+        self.assertNotIn("github.com/otiai10/gosseract", ocr)
+        py = (ROOT / "bin" / "mail" / "import").read_text()
+        self.assertNotIn("from docling", py)
+        self.assertNotIn("import docling", py)
+        self.assertIn("convert_pdf", py)
+        conv = (ROOT / "bin" / "tools" / "mailconv.py").read_text()
+        self.assertIn("pdftotext", conv)
+        self.assertIn("pdftoppm", conv)
+        self.assertIn("tesseract", conv)
+        self.assertIn("eng+deu", conv)
+        self.assertNotIn("from docling", conv)
+        self.assertNotIn("import docling", conv)
+        self.assertNotIn("gocv", conv.lower())
+        proj = (ROOT / "pyproject.toml").read_text()
+        self.assertNotIn("docling", proj)
+        ci = (ROOT / ".github" / "workflows" / "ci.yml").read_text()
+        self.assertIn("tesseract-ocr", ci)
+        self.assertIn("./internal/ocr", ci)
+        compose = (ROOT / "compose.yaml").read_text()
+        self.assertIn("ocr-paddle", compose)
+        self.assertIn("OCR_ENGINE", compose)
+
     def test_markdown_import_is_go_not_python_exec(self) -> None:
         self._assert_shebang("bin/markdown/import.go")
         text = (ROOT / "bin" / "markdown" / "import.go").read_text()

bin/tools/test_mailconv.py

@@ -8,10 +8,13 @@ from pathlib import Path
 sys.path.insert(0, os.path.dirname(__file__))
 
 from mailconv import (  # noqa: E402
+    TESS_LANG,
     clean_email_address,
+    convert_pdf,
     html_to_markdown,
     is_convertible,
     normalize_markdown,
+    ocr_image,
     split_zip_members,
     subject_to_filename,
     zip_extract_safe,
@@ -100,6 +103,92 @@ class TestMailConv(unittest.TestCase):
         self.assertFalse(is_convertible(".exe"))
         self.assertFalse(is_convertible(".unknown"))
 
+    def test_convert_pdf_prefers_pdftotext(self):
+        import mailconv as mc
+
+        calls: list[list[str]] = []
+
+        def fake_run(cmd, **kwargs):
+            calls.append(list(cmd))
+
+            class P:
+                returncode = 0
+                stdout = b"Invoice BM25 layout"
+                stderr = b""
+
+            return P()
+
+        self._patch_run(mc, fake_run)
+        out = convert_pdf(Path(self._tmp("born.pdf")))
+        self.assertIn("BM25", out)
+        self.assertEqual(calls[0][:2], ["pdftotext", "-layout"])
+        self.assertFalse(any(c[0] == "tesseract" for c in calls))
+        self.assertFalse(any(c[0] == "pdftoppm" for c in calls))
+
+    def test_convert_pdf_empty_layer_uses_pdftoppm_tesseract(self):
+        import mailconv as mc
+
+        calls: list[list[str]] = []
+
+        def fake_run(cmd, **kwargs):
+            calls.append(list(cmd))
+
+            class P:
+                returncode = 0
+                stdout = b""
+                stderr = b""
+
+            if cmd[0] == "pdftotext":
+                P.stdout = b"  \n"
+                return P()
+            if cmd[0] == "pdftoppm":
+                prefix = Path(cmd[-1])
+                (prefix.parent / "page-1.png").write_bytes(b"fake")
+                return P()
+            if cmd[0] == "tesseract":
+                P.stdout = b"scanned HELLO"
+                return P()
+            return P()
+
+        self._patch_run(mc, fake_run)
+        out = convert_pdf(Path(self._tmp("scan.pdf")))
+        self.assertIn("HELLO", out)
+        bins = [c[0] for c in calls]
+        self.assertIn("pdftotext", bins)
+        self.assertIn("pdftoppm", bins)
+        self.assertIn("tesseract", bins)
+        tess = next(c for c in calls if c[0] == "tesseract")
+        self.assertIn(TESS_LANG, tess)
+        self.assertNotIn("docling", " ".join(bins))
+
+    def test_ocr_image_paddle_engine(self):
+        import mailconv as mc
+
+        calls: list[list[str]] = []
+
+        def fake_run(cmd, **kwargs):
+            calls.append(list(cmd))
+
+            class P:
+                returncode = 0
+                stdout = b"paddle text"
+                stderr = b""
+
+            return P()
+
+        self._patch_run(mc, fake_run)
+        os.environ["OCR_ENGINE"] = "paddle"
+        try:
+            out = ocr_image(Path(self._tmp("x.png")))
+        finally:
+            os.environ.pop("OCR_ENGINE", None)
+        self.assertEqual(out, "paddle text")
+        self.assertEqual(calls[0][:2], ["paddleocr", "ocr"])
+
+    def _patch_run(self, mod, fn) -> None:
+        self.addCleanup(setattr, mod.subprocess, "run", mod.subprocess.run)
+        mod.subprocess.run = fn
+
     def _mk_zip(self, members):
         zpath = Path(self._tmp("arc.zip"))
         with zipfile.ZipFile(zpath, "w") as zf:

compose.yaml

@@ -5,6 +5,7 @@
 #   docker compose --profile picoclaw up brain-mcp
 #   docker compose --profile reasoner up -d reasoner   # CPU Ollama :11435
 #   docker compose --profile searxng up -d
+#   OCR_ENGINE=paddle docker compose --profile ocr-paddle run --rm ocr-paddle
 #
 # Secrets never baked in: search.env + db-profiles.yml from ~/.config/brain.
 
@@ -131,6 +132,15 @@ services:
       - reasoner-ollama:/root/.ollama
     restart: unless-stopped
 
+  # Optional PP-OCRv5 (not default). Default OCR is tesseract eng+deu.
+  #   OCR_ENGINE=paddle docker compose --profile ocr-paddle run --rm ocr-paddle
+  ocr-paddle:
+    profiles: ["ocr-paddle"]
+    image: python:3.12-slim
+    environment:
+      OCR_ENGINE: paddle
+    command: ["python", "-c", "print('OCR_ENGINE=paddle; install paddleocr on PATH')"]
+
 volumes:
   kb-model:
   kb-var:

docs/roadmap.md

@@ -32,11 +32,18 @@ FROM_FILE / HAS_VERSION / AUTHORED.
 `--with-chats` on rebuild (WhatsApp out of v1).
 [#19](https://git.produktor.io/eSlider/2dph/issues/19) CI recall SoT =
 `bin/brain/eval.go` via Zig.
+Epic [#16](https://git.produktor.io/eSlider/2dph/issues/16) closed.
+
+## v2
+
+[#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR — `pdftotext` then
+`pdftoppm` + tesseract `eng+deu`. Optional `ocr-paddle`.
+[#29](https://git.produktor.io/eSlider/2dph/issues/29) OQ1 contradiction
+resolution. [#30](https://git.produktor.io/eSlider/2dph/issues/30) OQ3 duckdb-md.
 
 ## Blockers
 
-None for epic #16. v2: [#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR,
-OQ1 contradiction resolution, OQ3 duckdb-md, OQ4 YAML-first leafs.
+None for epic #16 (closed). Remaining v2: OQ1, OQ3, OQ4.
 
 ```
 question
@@ -51,8 +58,8 @@ question
 
 ## Not v1
 
-[#6](https://git.produktor.io/eSlider/2dph/issues/6) OCR (OQ2), OQ1
-contradiction resolution, OQ3 duckdb-md export, OQ4 YAML-first leafs.
+OQ1 contradiction resolution, OQ3 duckdb-md export, OQ4 YAML-first leafs.
+OCR (OQ2) is in: tesseract, not docling.
 
 ## Close epic #16 when
 

docs/runbook.md

@@ -16,6 +16,7 @@ No laptop-absolute paths. Config lives in env files under `$HOME/.config/brain/`
 - Go (see `go.mod`)
 - Python 3.12 + [uv](https://docs.astral.sh/uv)
 - Optional: Docker, Zig CGO via `bin/cgo/zig` (not gcc)
+- Optional: poppler (`pdftotext`/`pdftoppm`) + tesseract `eng+deu` for mail OCR
 
 ```bash
 uv venv .venv

internal/ocr/ocr.go

@@ -0,0 +1,162 @@
+// Package ocr runs Tesseract (eng+deu) on images and scanned PDFs.
+//
+// Default engine is the tesseract CLI, not gosseract CGO: Ladybug CGO stays
+// Zig-only (D21). Same engine, no gocv. OCR_ENGINE=paddle selects paddleocr
+// when that binary is on PATH (compose profile ocr-paddle).
+package ocr
+
+import (
+	"fmt"
+	"image"
+	"image/color"
+	"image/png"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+)
+
+const TessLang = "eng+deu"
+
+func ImageFile(path string) (string, error) {
+	engine := os.Getenv("OCR_ENGINE")
+	if engine == "paddle" {
+		return runPaddle(path)
+	}
+	return runTesseract(path)
+}
+
+func PDFFile(path string) (string, error) {
+	text, err := pdfToText(path)
+	if err == nil && strings.TrimSpace(text) != "" {
+		return strings.TrimSpace(text), nil
+	}
+	ocr, oerr := pdfPages(path)
+	if oerr != nil {
+		if err != nil {
+			return "", err
+		}
+		return "", oerr
+	}
+	if strings.TrimSpace(ocr) != "" {
+		return strings.TrimSpace(ocr), nil
+	}
+	if text != "" {
+		return strings.TrimSpace(text), nil
+	}
+	return "", fmt.Errorf("pdf has no text layer (ocr unavailable)")
+}
+
+func pdfToText(path string) (string, error) {
+	cmd := exec.Command("pdftotext", "-layout", path, "-")
+	out, err := cmd.Output()
+	if err != nil {
+		return "", err
+	}
+	return string(out), nil
+}
+
+func pdfPages(path string) (string, error) {
+	dir, err := os.MkdirTemp("", "2dph-ocr-")
+	if err != nil {
+		return "", err
+	}
+	defer os.RemoveAll(dir)
+	prefix := filepath.Join(dir, "page")
+	cmd := exec.Command("pdftoppm", "-png", "-r", "200", path, prefix)
+	if err := cmd.Run(); err != nil {
+		return "", err
+	}
+	matches, err := filepath.Glob(prefix + "*.png")
+	if err != nil {
+		return "", err
+	}
+	var parts []string
+	for _, img := range matches {
+		t, err := ImageFile(img)
+		if err != nil {
+			continue
+		}
+		if s := strings.TrimSpace(t); s != "" {
+			parts = append(parts, s)
+		}
+	}
+	return strings.Join(parts, "\n\n"), nil
+}
+
+func runTesseract(path string) (string, error) {
+	pre, err := preprocessFile(path)
+	if err != nil {
+		pre = path
+	} else {
+		defer os.Remove(pre)
+	}
+	cmd := exec.Command("tesseract", pre, "stdout", "-l", TessLang, "--psm", "6")
+	out, err := cmd.Output()
+	if err != nil {
+		return "", err
+	}
+	return strings.TrimSpace(string(out)), nil
+}
+
+func runPaddle(path string) (string, error) {
+	cmd := exec.Command("paddleocr", "ocr", "-i", path)
+	out, err := cmd.Output()
+	if err != nil {
+		return "", err
+	}
+	return strings.TrimSpace(string(out)), nil
+}
+
+func preprocessFile(path string) (string, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return "", err
+	}
+	defer f.Close()
+	img, err := png.Decode(f)
+	if err != nil {
+		return "", err
+	}
+	out := filepath.Join(os.TempDir(), filepath.Base(path)+".gray.png")
+	w, err := os.Create(out)
+	if err != nil {
+		return "", err
+	}
+	defer w.Close()
+	if err := png.Encode(w, GrayContrast(img)); err != nil {
+		os.Remove(out)
+		return "", err
+	}
+	return out, nil
+}
+
+// GrayContrast is a stdlib preprocess (no gocv): grayscale + stretch.
+func GrayContrast(src image.Image) image.Image {
+	b := src.Bounds()
+	dst := image.NewGray(b)
+	var minL, maxL uint8 = 255, 0
+	for y := b.Min.Y; y < b.Max.Y; y++ {
+		for x := b.Min.X; x < b.Max.X; x++ {
+			g := color.GrayModel.Convert(src.At(x, y)).(color.Gray)
+			if g.Y < minL {
+				minL = g.Y
+			}
+			if g.Y > maxL {
+				maxL = g.Y
+			}
+		}
+	}
+	span := int(maxL) - int(minL)
+	if span < 1 {
+		span = 1
+	}
+	for y := b.Min.Y; y < b.Max.Y; y++ {
+		for x := b.Min.X; x < b.Max.X; x++ {
+			g := color.GrayModel.Convert(src.At(x, y)).(color.Gray)
+			v := uint8((int(g.Y) - int(minL)) * 255 / span)
+			dst.SetGray(x, y, color.Gray{Y: v})
+		}
+	}
+	return dst
+}

internal/ocr/ocr_test.go

@@ -0,0 +1,54 @@
+package ocr
+
+import (
+	"image"
+	"image/color"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+func TestGrayContrastStretches(t *testing.T) {
+	img := image.NewGray(image.Rect(0, 0, 2, 2))
+	img.SetGray(0, 0, color.Gray{Y: 64})
+	img.SetGray(0, 1, color.Gray{Y: 64})
+	img.SetGray(1, 0, color.Gray{Y: 64})
+	img.SetGray(1, 1, color.Gray{Y: 192})
+	out := GrayContrast(img).(*image.Gray)
+	if out.GrayAt(0, 0).Y != 0 {
+		t.Fatalf("min should map to 0, got %d", out.GrayAt(0, 0).Y)
+	}
+	if out.GrayAt(1, 1).Y != 255 {
+		t.Fatalf("max should map to 255, got %d", out.GrayAt(1, 1).Y)
+	}
+}
+
+func TestHelloPNGFixtureOCR(t *testing.T) {
+	if _, err := exec.LookPath("tesseract"); err != nil {
+		t.Skip("tesseract not installed")
+	}
+	path := filepath.Join("testdata", "hello.png")
+	got, err := ImageFile(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	up := strings.ToUpper(got)
+	if !strings.Contains(up, "HELLO") {
+		t.Fatalf("ocr %q missing HELLO", got)
+	}
+}
+
+func TestPaddleEngineUsesPaddleocrBinary(t *testing.T) {
+	t.Setenv("OCR_ENGINE", "paddle")
+	_, err := ImageFile(filepath.Join("testdata", "hello.png"))
+	if _, look := exec.LookPath("paddleocr"); look != nil {
+		if err == nil {
+			t.Fatal("expected error when paddleocr is missing")
+		}
+		return
+	}
+	if err != nil {
+		t.Fatal(err)
+	}
+}

pyproject.toml

@@ -6,7 +6,6 @@ readme = "README.md"
 requires-python = ">=3.12"
 license = { text = "MIT" }
 dependencies = [
-    "docling>=2.119.0",
     "ladybug==0.19.1",
     "markitdown[docx,epub,html,image-exif,pdf,pptx,xlsx,zip]>=0.1.7",
     "mistune==3.3.4",