feat(kanban): attach images referenced in task bodies to worker vision (#34210)

Kanban workers now scan the task body for local image paths and
http(s) image URLs and attach them to the worker's first user turn —
matching the CLI/gateway behaviour for inbound images. Before, a
user pasting `/home/me/screenshot.png` or `https://example.com/img.png`
into a kanban task description had it sent to the model as plain
text and the pixels were never seen.

How it works:
* agent/image_routing.py gains extract_image_refs(text) → (paths, urls)
  that mirrors gateway/platforms/base.py:extract_local_files (absolute /
  ~-relative paths, image extensions only, ignores fenced/inline code).
* build_native_content_parts() accepts an optional image_urls= kwarg
  and emits passthrough image_url parts for remote URLs alongside the
  base64 data: URLs used for local paths.
* cli.py (single-query/quiet branch — the path every dispatcher-spawned
  worker takes) detects HERMES_KANBAN_TASK, reads the task body via
  kanban_db.get_task, runs extract_image_refs, and threads the results
  into the existing image-routing decision (native vs text). Best-effort:
  enrichment failures never block worker startup.

Tested:
* tests/agent/test_image_routing.py — 22 new tests for extract_image_refs
  and URL pass-through in build_native_content_parts.
* tests/hermes_cli/test_kanban_worker_image_extraction.py — 10 new tests
  driving real kanban_db round-trip (create task → read body → extract
  refs → build parts).
* E2E: created a fake kanban task with a body referencing both a local
  PNG and an https URL; verified the worker pipeline produces a
  multimodal user turn with 1 text part + 2 image_url parts (data URL
  for the local file, passthrough URL for the remote).

agent/image_routing.py

@@ -37,6 +37,8 @@ from __future__ import annotations
 import base64
 import logging
 import mimetypes
+import os
+import re
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -46,6 +48,102 @@ logger = logging.getLogger(__name__)
 _VALID_MODES = frozenset({"auto", "native", "text"})
 
 
+# Image extensions used by extract_image_refs(). Kept tight on purpose — we
+# only auto-attach things the model can actually see. Documents/archives are
+# excluded because the gateway's broader extract_local_files() also routes
+# them differently (send_document), and we don't want to attach a PDF as a
+# vision part.
+_IMAGE_EXTS = (
+    ".png", ".jpg", ".jpeg", ".gif", ".webp", ".bmp", ".tiff", ".tif", ".heic",
+)
+_IMAGE_EXT_PATTERN = "|".join(e.lstrip(".") for e in _IMAGE_EXTS)
+
+# Absolute / home-relative local image path. Matches the same shape gateway's
+# extract_local_files() uses: anchors to ``~/`` or ``/``, ignores matches inside
+# URLs (the ``(?<![/:\w.])`` lookbehind), and case-insensitive on the extension.
+_LOCAL_IMAGE_PATH_RE = re.compile(
+    r"(?<![/:\w.])(?:~/|/)(?:[\w.\-]+/)*[\w.\-]+\.(?:" + _IMAGE_EXT_PATTERN + r")\b",
+    re.IGNORECASE,
+)
+
+# http(s) URL ending in an image extension (optionally followed by a
+# query string). Case-insensitive on the extension. Strict ``http(s)://``
+# scheme so we don't accidentally grab ``file://`` URLs or other shapes.
+_IMAGE_URL_RE = re.compile(
+    r"https?://[^\s<>\"']+?\.(?:" + _IMAGE_EXT_PATTERN + r")(?:\?[^\s<>\"']*)?",
+    re.IGNORECASE,
+)
+
+
+def extract_image_refs(text: str) -> Tuple[List[str], List[str]]:
+    """Scan free-form text for image references the model should see.
+
+    Returns ``(local_paths, urls)``:
+
+      * ``local_paths`` — absolute (``/``) or home-relative (``~/``) paths
+        whose suffix is an image extension AND whose expanded form exists
+        on disk as a file. Order-preserving, deduplicated.
+      * ``urls`` — ``http(s)://…`` URLs whose path ends in an image
+        extension (a ``?query`` is allowed after the extension).
+        Order-preserving, deduplicated.
+
+    Matches inside fenced code blocks (``` ``` ```) and inline backticks
+    (`` `…` ``) are skipped so that snippets pasted into a task body for
+    reference aren't mistaken for live attachments. This mirrors the
+    behaviour of ``gateway.platforms.base.BaseAdapter.extract_local_files``.
+
+    Local paths are validated against the filesystem; URLs are not
+    (the provider fetches them at request time).
+    """
+    if not isinstance(text, str) or not text:
+        return [], []
+
+    # Build spans covered by fenced code blocks and inline code so we can
+    # ignore references the author embedded purely as example text.
+    code_spans: list[tuple[int, int]] = []
+    for m in re.finditer(r"```[^\n]*\n.*?```", text, re.DOTALL):
+        code_spans.append((m.start(), m.end()))
+    for m in re.finditer(r"`[^`\n]+`", text):
+        code_spans.append((m.start(), m.end()))
+
+    def _in_code(pos: int) -> bool:
+        return any(s <= pos < e for s, e in code_spans)
+
+    local_paths: list[str] = []
+    seen_paths: set[str] = set()
+    for match in _LOCAL_IMAGE_PATH_RE.finditer(text):
+        if _in_code(match.start()):
+            continue
+        raw = match.group(0)
+        expanded = os.path.expanduser(raw)
+        try:
+            if not os.path.isfile(expanded):
+                continue
+        except OSError:
+            # ENAMETOOLONG / EINVAL on pathological inputs — skip rather than crash.
+            continue
+        if expanded in seen_paths:
+            continue
+        seen_paths.add(expanded)
+        local_paths.append(expanded)
+
+    urls: list[str] = []
+    seen_urls: set[str] = set()
+    for match in _IMAGE_URL_RE.finditer(text):
+        if _in_code(match.start()):
+            continue
+        url = match.group(0)
+        # Strip trailing punctuation that's almost certainly prose, not part
+        # of the URL (e.g. "see https://x.com/a.png." or "/a.png)").
+        url = url.rstrip(".,;:!?)]>")
+        if url in seen_urls:
+            continue
+        seen_urls.add(url)
+        urls.append(url)
+
+    return local_paths, urls
+
+
 # Strict YAML/JSON boolean coercion for capability overrides.
 #
 # ``bool("false")`` is True in Python because non-empty strings are truthy, so
@@ -320,20 +418,29 @@ def _file_to_data_url(path: Path) -> Optional[str]:
 def build_native_content_parts(
     user_text: str,
     image_paths: List[str],
+    image_urls: Optional[List[str]] = None,
 ) -> Tuple[List[Dict[str, Any]], List[str]]:
     """Build an OpenAI-style ``content`` list for a user turn.
 
     Shape:
       [{"type": "text", "text": "...\\n\\n[Image attached at: /local/path]"},
        {"type": "image_url", "image_url": {"url": "data:image/png;base64,..."}},
+       {"type": "image_url", "image_url": {"url": "https://example.com/a.png"}},
        ...]
 
-    The local path of each successfully attached image is appended to the
-    text part as ``[Image attached at: <path>]``. The model still sees the
-    pixels via the ``image_url`` part (full native vision); the path note
-    just gives it a string handle so MCP/skill tools that take an image
-    path or URL argument can be invoked on the same image without an
-    extra round-trip. This parallels the text-mode hint produced by
+    Local paths are read from disk and embedded as base64 ``data:`` URLs.
+    Remote URLs (``http(s)://``) are passed through verbatim — the provider
+    fetches them server-side. The model still sees the pixels either way.
+
+    For each successfully attached image, a hint is appended to the text
+    part:
+
+      * local path → ``[Image attached at: <path>]``
+      * URL        → ``[Image attached: <url>]``
+
+    The hint gives the model a string handle so MCP/skill tools that take
+    an image path or URL argument can be invoked on the same image without
+    an extra round-trip. This parallels the text-mode hint produced by
     ``Runner._enrich_message_with_vision`` (``vision_analyze using image_url:
     <path>``) so behaviour is consistent across both image input modes.
 
@@ -342,12 +449,14 @@ def build_native_content_parts(
     ceiling), the agent's retry loop transparently shrinks and retries
     once — see ``run_agent._try_shrink_image_parts_in_messages``.
 
-    Returns (content_parts, skipped_paths). Skipped paths are files that
-    couldn't be read from disk and are NOT advertised in the path hints.
+    Returns (content_parts, skipped). Skipped entries are local paths
+    that couldn't be read from disk; URLs are never skipped (they're
+    not validated here).
     """
     skipped: List[str] = []
     image_parts: List[Dict[str, Any]] = []
     attached_paths: List[str] = []
+    attached_urls: List[str] = []
 
     for raw_path in image_paths:
         p = Path(raw_path)
@@ -364,16 +473,26 @@ def build_native_content_parts(
         })
         attached_paths.append(str(raw_path))
 
+    for url in image_urls or []:
+        url = (url or "").strip()
+        if not url:
+            continue
+        image_parts.append({
+            "type": "image_url",
+            "image_url": {"url": url},
+        })
+        attached_urls.append(url)
+
     text = (user_text or "").strip()
 
     # If at least one image attached, build a single text part that combines
-    # the user's caption (or a neutral default) with one path hint per image.
-    if attached_paths:
+    # the user's caption (or a neutral default) with one hint per image.
+    if attached_paths or attached_urls:
         base_text = text or "What do you see in this image?"
-        path_hints = "\n".join(
-            f"[Image attached at: {p}]" for p in attached_paths
-        )
-        combined_text = f"{base_text}\n\n{path_hints}"
+        hint_lines: List[str] = []
+        hint_lines.extend(f"[Image attached at: {p}]" for p in attached_paths)
+        hint_lines.extend(f"[Image attached: {u}]" for u in attached_urls)
+        combined_text = f"{base_text}\n\n" + "\n".join(hint_lines)
         parts: List[Dict[str, Any]] = [{"type": "text", "text": combined_text}]
         parts.extend(image_parts)
         return parts, skipped
@@ -388,4 +507,5 @@ def build_native_content_parts(
 __all__ = [
     "decide_image_input_mode",
     "build_native_content_parts",
+    "extract_image_refs",
 ]

cli.py

@@ -15125,13 +15125,50 @@ def main(
     # Handle single query mode
     if query or image:
         query, single_query_images = _collect_query_images(query, image)
+        # Kanban workers spawn with ``hermes chat -q "work kanban task <id>"``;
+        # the actual task description lives in the task body. Mirror the
+        # gateway/CLI behaviour for inbound images by scanning the body for
+        # local image paths and http(s) image URLs and attaching them to the
+        # worker's first turn. Without this, users who paste a screenshot
+        # path or URL into a kanban task body never get it routed to the
+        # model's vision input.
+        single_query_image_urls: list[str] = []
+        _kanban_task_id = os.environ.get("HERMES_KANBAN_TASK", "").strip()
+        if _kanban_task_id:
+            try:
+                from hermes_cli import kanban_db as _kb
+                from agent.image_routing import extract_image_refs as _extract_refs
+
+                _conn = _kb.connect()
+                try:
+                    _task = _kb.get_task(_conn, _kanban_task_id)
+                finally:
+                    try:
+                        _conn.close()
+                    except Exception:
+                        pass
+                _body = getattr(_task, "body", "") if _task is not None else ""
+                if _body:
+                    _kb_paths, _kb_urls = _extract_refs(_body)
+                    if _kb_paths:
+                        # Dedupe against any --image the user already passed.
+                        _seen = {str(p) for p in single_query_images}
+                        for _p in _kb_paths:
+                            if _p not in _seen:
+                                _seen.add(_p)
+                                single_query_images.append(Path(_p))
+                    if _kb_urls:
+                        single_query_image_urls.extend(_kb_urls)
+            except Exception as _exc:
+                # Best-effort enrichment; never block worker startup on it.
+                logger.debug("kanban image-ref extraction failed: %s", _exc)
         if quiet:
             # Quiet mode: suppress banner, spinner, tool previews.
             # Only print the final response and parseable session info.
             cli.tool_progress_mode = "off"
             if cli._ensure_runtime_credentials():
                 effective_query: Any = query
-                if single_query_images:
+                if single_query_images or single_query_image_urls:
                     # Honour the same image-routing decision used by the
                     # interactive path. With a vision-capable model (incl.
                     # custom-provider models declared via
@@ -15160,19 +15197,26 @@ def main(
                             _parts, _skipped = _build_parts(
                                 query if isinstance(query, str) else "",
                                 [str(p) for p in single_query_images],
+                                image_urls=list(single_query_image_urls) or None,
                             )
                             if any(p.get("type") == "image_url" for p in _parts):
                                 effective_query = _parts
                             else:
                                 # All images unreadable — text fallback.
+                                # ``_preprocess_images_with_vision`` only knows
+                                # about local files; URLs would be lost there,
+                                # so keep the original query text intact when
+                                # only URLs were supplied.
+                                if single_query_images:
+                                    effective_query = cli._preprocess_images_with_vision(
+                                        query, single_query_images, announce=False,
+                                    )
+                        except Exception:
+                            if single_query_images:
                                 effective_query = cli._preprocess_images_with_vision(
                                     query, single_query_images, announce=False,
                                 )
-                        except Exception:
-                            effective_query = cli._preprocess_images_with_vision(
-                                query, single_query_images, announce=False,
-                            )
-                    else:
+                    elif single_query_images:
                         effective_query = cli._preprocess_images_with_vision(
                             query,
                             single_query_images,

tests/agent/test_image_routing.py

@@ -16,6 +16,7 @@ from agent.image_routing import (
     _supports_vision_override,
     build_native_content_parts,
     decide_image_input_mode,
+    extract_image_refs,
 )
 
 
@@ -449,3 +450,190 @@ class TestLargeImageHandling:
         assert len(parts) == 2
         assert parts[0]["type"] == "text"
         assert parts[1]["type"] == "image_url"
+
+
+# ─── extract_image_refs ──────────────────────────────────────────────────────
+
+
+class TestExtractImageRefs:
+    """Scan task body / inbound text for image paths and URLs (kanban worker
+    enrichment, issue raised May 2026)."""
+
+    def test_empty_or_none_returns_empty(self):
+        assert extract_image_refs("") == ([], [])
+        assert extract_image_refs(None) == ([], [])  # type: ignore[arg-type]
+
+    def test_finds_absolute_path(self, tmp_path: Path):
+        img = tmp_path / "screenshot.png"
+        img.write_bytes(_png_bytes())
+        body = f"Look at {img} and tell me what's wrong."
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == []
+
+    def test_finds_home_relative_path(self, tmp_path: Path, monkeypatch):
+        # Simulate ~/foo.png by pointing HOME at tmp_path and creating the file
+        monkeypatch.setenv("HOME", str(tmp_path))
+        img = tmp_path / "foo.png"
+        img.write_bytes(_png_bytes())
+        paths, urls = extract_image_refs("see ~/foo.png please")
+        assert paths == [str(img)]
+        assert urls == []
+
+    def test_skips_nonexistent_paths(self, tmp_path: Path):
+        # Path-shaped but no file on disk → skipped.
+        body = f"What's at {tmp_path}/never_created.png ?"
+        paths, urls = extract_image_refs(body)
+        assert paths == []
+        assert urls == []
+
+    def test_finds_http_image_url(self):
+        body = "Check out https://example.com/photos/cat.png — cute right?"
+        paths, urls = extract_image_refs(body)
+        assert paths == []
+        assert urls == ["https://example.com/photos/cat.png"]
+
+    def test_finds_https_url_with_query_string(self):
+        body = "Diagram: https://cdn.example.com/img.jpeg?size=large&v=2 here"
+        paths, urls = extract_image_refs(body)
+        assert urls == ["https://cdn.example.com/img.jpeg?size=large&v=2"]
+
+    def test_url_trailing_punctuation_stripped(self):
+        # Prose punctuation right after the URL must not be part of the URL.
+        body = "See https://example.com/a.png."
+        paths, urls = extract_image_refs(body)
+        assert urls == ["https://example.com/a.png"]
+
+    def test_ignores_non_image_urls(self):
+        body = "See https://example.com/page.html and https://x.com/y.pdf"
+        paths, urls = extract_image_refs(body)
+        assert urls == []
+
+    def test_dedupes_paths_and_urls(self, tmp_path: Path):
+        img = tmp_path / "dup.png"
+        img.write_bytes(_png_bytes())
+        body = (
+            f"First {img} then again {img}. "
+            "Also https://example.com/x.png and https://example.com/x.png again."
+        )
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == ["https://example.com/x.png"]
+
+    def test_ignores_paths_in_fenced_code_block(self, tmp_path: Path):
+        img = tmp_path / "real.png"
+        img.write_bytes(_png_bytes())
+        body = (
+            "Outside the block, attach this:\n"
+            f"{img}\n"
+            "But not these examples:\n"
+            "```\n"
+            f"some_other_image: /tmp/example.png\n"
+            f"url: https://example.com/example.png\n"
+            "```\n"
+        )
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == []
+
+    def test_ignores_paths_in_inline_code(self, tmp_path: Path):
+        img = tmp_path / "real.jpg"
+        img.write_bytes(_png_bytes())
+        body = (
+            f"Attach {img}, but ignore the example "
+            "`https://example.com/skip.png` in backticks."
+        )
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == []
+
+    def test_does_not_match_paths_inside_urls(self, tmp_path: Path):
+        # The lookbehind in the regex prevents matching the path-portion of
+        # a URL as a local path. Only the URL should be detected.
+        body = "Just the URL: https://example.com/some/dir/image.png"
+        paths, urls = extract_image_refs(body)
+        assert paths == []
+        assert urls == ["https://example.com/some/dir/image.png"]
+
+    def test_mixed_paths_and_urls(self, tmp_path: Path):
+        img = tmp_path / "local.png"
+        img.write_bytes(_png_bytes())
+        body = (
+            f"Compare local {img} against the design at "
+            "https://example.com/design/v2.png — does it match?"
+        )
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == ["https://example.com/design/v2.png"]
+
+    def test_case_insensitive_extension(self, tmp_path: Path):
+        img = tmp_path / "shouty.PNG"
+        img.write_bytes(_png_bytes())
+        body = f"see {img}"
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+
+
+# ─── build_native_content_parts with URLs ────────────────────────────────────
+
+
+class TestBuildNativeContentPartsURLs:
+    """URL pass-through support added so kanban task bodies (and other
+    inbound surfaces) can route remote image URLs straight to the model."""
+
+    def test_url_only_no_local_paths(self):
+        parts, skipped = build_native_content_parts(
+            "what is this?",
+            [],
+            image_urls=["https://example.com/diagram.png"],
+        )
+        assert skipped == []
+        assert len(parts) == 2
+        assert parts[0]["type"] == "text"
+        assert "[Image attached: https://example.com/diagram.png]" in parts[0]["text"]
+        assert parts[0]["text"].startswith("what is this?")
+        assert parts[1] == {
+            "type": "image_url",
+            "image_url": {"url": "https://example.com/diagram.png"},
+        }
+
+    def test_mixed_path_and_url(self, tmp_path: Path):
+        img = tmp_path / "local.png"
+        img.write_bytes(_png_bytes())
+        parts, skipped = build_native_content_parts(
+            "compare these",
+            [str(img)],
+            image_urls=["https://example.com/remote.jpg"],
+        )
+        assert skipped == []
+        # 1 text + 2 image parts (local data URL first, then remote URL).
+        image_parts = [p for p in parts if p.get("type") == "image_url"]
+        assert len(image_parts) == 2
+        assert image_parts[0]["image_url"]["url"].startswith("data:image/png;base64,")
+        assert image_parts[1]["image_url"]["url"] == "https://example.com/remote.jpg"
+        text = parts[0]["text"]
+        assert "[Image attached at:" in text
+        assert "[Image attached: https://example.com/remote.jpg]" in text
+
+    def test_empty_url_list_is_no_op(self, tmp_path: Path):
+        img = tmp_path / "x.png"
+        img.write_bytes(_png_bytes())
+        # image_urls=[] should behave the same as not passing it at all.
+        parts_no_urls, _ = build_native_content_parts("hi", [str(img)])
+        parts_empty_urls, _ = build_native_content_parts("hi", [str(img)], image_urls=[])
+        assert parts_no_urls == parts_empty_urls
+
+    def test_blank_url_strings_are_dropped(self):
+        parts, _ = build_native_content_parts(
+            "x", [], image_urls=["", "  ", "https://example.com/a.png"]
+        )
+        image_parts = [p for p in parts if p.get("type") == "image_url"]
+        assert len(image_parts) == 1
+        assert image_parts[0]["image_url"]["url"] == "https://example.com/a.png"
+
+    def test_url_only_inserts_default_prompt_when_text_empty(self):
+        parts, _ = build_native_content_parts(
+            "", [], image_urls=["https://example.com/a.png"]
+        )
+        assert parts[0]["type"] == "text"
+        assert parts[0]["text"].startswith("What do you see in this image?")

tests/hermes_cli/test_kanban_worker_image_extraction.py

@@ -0,0 +1,238 @@
+"""Worker-side image enrichment for kanban tasks.
+
+When a kanban task body contains a local image path or an ``http(s)://``
+image URL, the worker must surface that image to the model on its first
+user turn — matching the CLI/gateway behaviour for inbound images.
+
+The dispatcher spawns the worker as
+``hermes -p <profile> chat -q "work kanban task <id>"``. The task body
+itself never appears in argv; the worker has to read it from the kanban
+DB during startup. These tests cover the round-trip:
+
+  task body  →  kanban_db.get_task  →  extract_image_refs  →
+  build_native_content_parts  →  multimodal user turn
+"""
+from __future__ import annotations
+
+import base64
+from pathlib import Path
+
+import pytest
+
+from hermes_cli import kanban_db as kb
+from agent.image_routing import (
+    build_native_content_parts,
+    extract_image_refs,
+)
+
+
+# Tiny 1×1 transparent PNG used to back any path the tests stick into a
+# task body. extract_image_refs validates the path exists on disk, so the
+# byte content has to be a real readable file (any image bytes will do).
+_PNG = base64.b64decode(
+    "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR4nGNgYGBgAAAABQABpfZFQAAAAABJRU5ErkJggg=="
+)
+
+
+@pytest.fixture
+def kanban_home(tmp_path: Path, monkeypatch):
+    """Isolated HERMES_HOME with a fresh kanban DB for each test."""
+    home = tmp_path / ".hermes"
+    home.mkdir()
+    monkeypatch.setenv("HERMES_HOME", str(home))
+    monkeypatch.setattr(Path, "home", lambda: tmp_path)
+    kb.init_db()
+    return home
+
+
+def _add_task_with_body(body: str, *, title: str = "Look at this") -> str:
+    conn = kb.connect()
+    try:
+        task_id = kb.create_task(
+            conn,
+            title=title,
+            body=body,
+            assignee="worker-a",
+            tenant=None,
+        )
+    finally:
+        conn.close()
+    return task_id
+
+
+def _read_body(task_id: str) -> str:
+    conn = kb.connect()
+    try:
+        task = kb.get_task(conn, task_id)
+        return (task.body if task is not None else "") or ""
+    finally:
+        conn.close()
+
+
+class TestExtractFromTaskBody:
+    """Read a real kanban task body and run it through extract_image_refs."""
+
+    def test_local_path_in_body_round_trips(self, kanban_home, tmp_path):
+        img = tmp_path / "screenshot.png"
+        img.write_bytes(_PNG)
+        tid = _add_task_with_body(
+            f"Please review the screenshot at {img} and confirm "
+            "the alignment is right."
+        )
+
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == []
+
+    def test_url_in_body_round_trips(self, kanban_home):
+        tid = _add_task_with_body(
+            "The design lives at https://example.com/mock/v3.png — "
+            "make the implementation match it."
+        )
+
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+        assert paths == []
+        assert urls == ["https://example.com/mock/v3.png"]
+
+    def test_mixed_path_and_url_in_body(self, kanban_home, tmp_path):
+        img = tmp_path / "current.png"
+        img.write_bytes(_PNG)
+        tid = _add_task_with_body(
+            f"Compare the current screenshot {img} against the design at "
+            "https://example.com/target.png and write a diff."
+        )
+
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+        assert paths == [str(img)]
+        assert urls == ["https://example.com/target.png"]
+
+    def test_body_without_images_yields_nothing(self, kanban_home):
+        tid = _add_task_with_body(
+            "Refactor the auth module to use the new session helper."
+        )
+
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+        assert paths == []
+        assert urls == []
+
+    def test_empty_body_is_safe(self, kanban_home):
+        tid = _add_task_with_body("")
+
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+        assert paths == []
+        assert urls == []
+
+
+class TestBuildPartsFromTaskBody:
+    """Verify the full pipeline produces a multimodal user turn."""
+
+    def test_local_path_becomes_native_image_part(self, kanban_home, tmp_path):
+        img = tmp_path / "design.png"
+        img.write_bytes(_PNG)
+        tid = _add_task_with_body(f"Check out {img} — what's broken?")
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+
+        # Mirrors the cli.py wiring: pass the worker's literal -q argument
+        # (the dispatcher uses ``"work kanban task <id>"``) plus the
+        # extracted refs through build_native_content_parts.
+        parts, skipped = build_native_content_parts(
+            f"work kanban task {tid}",
+            paths,
+            image_urls=urls or None,
+        )
+
+        assert skipped == []
+        # text part + one image_url part
+        assert len(parts) == 2
+        assert parts[0]["type"] == "text"
+        assert parts[0]["text"].startswith(f"work kanban task {tid}")
+        assert f"[Image attached at: {img}]" in parts[0]["text"]
+        assert parts[1]["type"] == "image_url"
+        assert parts[1]["image_url"]["url"].startswith("data:image/png;base64,")
+
+    def test_url_becomes_image_url_part(self, kanban_home):
+        tid = _add_task_with_body(
+            "Reference: https://example.com/target.jpg — match it."
+        )
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+
+        parts, skipped = build_native_content_parts(
+            f"work kanban task {tid}",
+            paths,
+            image_urls=urls or None,
+        )
+
+        assert skipped == []
+        assert len(parts) == 2
+        assert parts[0]["type"] == "text"
+        assert "[Image attached: https://example.com/target.jpg]" in parts[0]["text"]
+        assert parts[1] == {
+            "type": "image_url",
+            "image_url": {"url": "https://example.com/target.jpg"},
+        }
+
+    def test_body_with_both_yields_two_image_parts(self, kanban_home, tmp_path):
+        img = tmp_path / "local.png"
+        img.write_bytes(_PNG)
+        tid = _add_task_with_body(
+            f"Diff {img} vs https://example.com/target.png — explain it."
+        )
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+
+        parts, skipped = build_native_content_parts(
+            f"work kanban task {tid}",
+            paths,
+            image_urls=urls or None,
+        )
+
+        assert skipped == []
+        image_parts = [p for p in parts if p.get("type") == "image_url"]
+        assert len(image_parts) == 2
+        # Local file is embedded as a data URL; remote URL passes through.
+        assert image_parts[0]["image_url"]["url"].startswith("data:image/png;base64,")
+        assert image_parts[1]["image_url"]["url"] == "https://example.com/target.png"
+
+    def test_body_with_no_images_leaves_query_untouched(self, kanban_home):
+        tid = _add_task_with_body(
+            "Rewrite the README intro paragraph to focus on use cases."
+        )
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+
+        parts, skipped = build_native_content_parts(
+            f"work kanban task {tid}",
+            paths,
+            image_urls=urls or None,
+        )
+
+        # No images → plain text-only return (single part, no list mutation).
+        assert skipped == []
+        assert len(parts) == 1
+        assert parts[0]["type"] == "text"
+        assert parts[0]["text"] == f"work kanban task {tid}"
+
+    def test_code_block_example_is_not_attached(self, kanban_home, tmp_path):
+        # Only the real image outside the fenced code block should attach.
+        real = tmp_path / "real.png"
+        real.write_bytes(_PNG)
+        tid = _add_task_with_body(
+            f"Real screenshot:\n{real}\n\n"
+            "Example we DON'T want attached:\n"
+            "```\n"
+            "image: /tmp/example_only.png\n"
+            "url: https://example.com/example.png\n"
+            "```\n"
+        )
+        body = _read_body(tid)
+        paths, urls = extract_image_refs(body)
+
+        assert paths == [str(real)]
+        assert urls == []