unaltraweb 0.4.0 → 0.5.0

data/scripts/image_background_check.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+"""Run the packaged image background advisory without an MCP factory runtime."""
+from pathlib import Path
+import sys
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "src"))
+
+from unaltraweb_mcp.image_backgrounds import main
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

data/scripts/manual/build_pdf.py

@@ -45,11 +45,18 @@ DISPLAY_MATH_BLOCK_RE = re.compile(
     re.MULTILINE | re.DOTALL,
 )
 BASEURL_RE = re.compile(r"\{\{\s*site\.baseurl\s*\}\}")
+KRAMDOWN_ATTRS = r'''\{:(?:[^{}"'\n]|"(?:\\.|[^"\\\n])*"|'(?:\\.|[^'\\\n])*')*\}'''
+CAPTION_SOURCE_ATTR_RE = re.compile(
+    r'''(?:\A|\s)data-caption-source\s*=\s*(?:"(?P<double>(?:\\.|[^"\\])*)"|'(?P<single>(?:\\.|[^'\\])*)'|(?P<bare>[^\s}]+))'''
+)
 IMAGE_RE = re.compile(
     r"!\[(?P<alt>[^\]]*)\]\((?P<path>\S+?)(?:\s+(?:\"(?P<double_title>[^\"]*)\"|'(?P<single_title>[^']*)'))?\)"
-    r"(?P<attrs>\{:[^}\n]*\})?"
+    rf"(?:[ \t]*(?P<attrs>{KRAMDOWN_ATTRS}))?"
+)
+TABLE_DIV_RE = re.compile(
+    rf'''^:::\s*table\s+(?P<quote>["'])(?P<caption>[^\n]+?)(?P=quote)(?:[ \t]+(?P<attrs>{KRAMDOWN_ATTRS}))?[ \t]*\n(?P<body>.*?)^:::\s*$''',
+    re.MULTILINE | re.DOTALL,
 )
-TABLE_DIV_RE = re.compile(r'^::: table\s+["\'](.+?)["\']\s*\n(.*?)^:::\s*$', re.MULTILINE | re.DOTALL)
 LISTING_DIV_RE = re.compile(
     r'^:::\s*listing\s+"(?P<caption>[^"]+)"\s*\n(?P<body>.*?)^:::\s*$',
     re.MULTILINE | re.DOTALL,
@@ -61,7 +68,7 @@ TABLE_GUARD_AFTER_HEADING_RE = re.compile(
     re.MULTILINE,
 )
 SUBFIGURES_DIV_RE = re.compile(
-    r'^:::\s*subfigures(?:\s+(?P<layout>[^\s"]+))?(?:\s+"(?P<caption>[^"]*)")?\s*\n'
+    rf'^:::\s*subfigures(?:[ \t]+(?P<layout>[^\s"{{]+))?(?:[ \t]+"(?P<caption>[^"]*)")?(?:[ \t]+(?P<attrs>{KRAMDOWN_ATTRS}))?[ \t]*\n'
     r'(?P<body>.*?)^:::\s*$',
     re.MULTILINE | re.DOTALL,
 )
@@ -787,6 +794,60 @@ def resolve_visual_source(
     raise ManualPdfError(f"No printable SVG found for diagram source: {path}")
 
 
+def caption_source_attribute(raw: str) -> tuple[str, str]:
+    """Consume the caption-only field before emitting image attributes."""
+    source = raw.strip().removeprefix("{:").removesuffix("}").strip()
+    match = CAPTION_SOURCE_ATTR_RE.search(source)
+    if not match:
+        return "", raw
+    credit = next(value for value in match.group("double", "single", "bare") if value is not None)
+    credit = re.sub(r'''\\(["'\\])''', r"\1", credit).strip()
+    remaining = (source[:match.start()] + " " + source[match.end():]).strip()
+    return credit, "{: " + remaining + "}" if remaining else ""
+
+
+def caption_with_source(caption: str, source: str) -> str:
+    return caption + f" [{source}]{{.uw-caption-source}}" if source else caption
+
+
+def image_destinations(markdown: str) -> list[str]:
+    """Find assets after transformation, including nested caption spans/cites.
+
+    The source IMAGE_RE cannot represent arbitrary nested inline brackets. Asset
+    freshness must still include every image consumed by Pandoc, including an
+    inline image nested in another image's caption.
+    """
+    paths = []
+    for opening in re.finditer(r"(?<!\\)!\[", markdown):
+        index, depth = opening.end(), 1
+        while index < len(markdown) and depth:
+            character = markdown[index]
+            if character == "\\":
+                index += 2
+                continue
+            if character == "[":
+                depth += 1
+            elif character == "]":
+                depth -= 1
+            index += 1
+        if depth or index >= len(markdown) or markdown[index] != "(":
+            continue
+        start = index = index + 1
+        parentheses = 0
+        while index < len(markdown):
+            character = markdown[index]
+            if character.isspace() or (character == ")" and not parentheses):
+                break
+            if character == "(":
+                parentheses += 1
+            elif character == ")":
+                parentheses -= 1
+            index += 1
+        if index > start:
+            paths.append(markdown[start:index])
+    return paths
+
+
 def pandoc_image_attributes(raw: str) -> str:
     source = raw.strip()
     if not source:
@@ -887,7 +948,9 @@ def transform_markdown(
         return "[" + "; ".join(f"@{key}" for key in keys) + "]"
 
     def table(match: re.Match[str]) -> str:
-        body = match.group(2).strip()
+        body = match.group("body").strip()
+        credit, _ = caption_source_attribute(match.group("attrs") or "")
+        caption = caption_with_source(match.group("caption").strip(), credit)
         rows = [
             re.sub(r"\s+", " ", line.strip().strip("|"))
             for line in body.splitlines()
@@ -898,7 +961,7 @@ def transform_markdown(
         page_guard = r"\clearpage" if required_baselines >= 40 else f"\\Needspace{{{required_baselines}\\baselineskip}}"
         return (
             f"```{{=latex}}\n{page_guard}\n```\n\n"
-            f"Table: {match.group(1).strip()}\n\n{body}"
+            f"Table: {caption}\n\n{body}"
         )
 
     def listing(match: re.Match[str]) -> str:
@@ -957,8 +1020,9 @@ def transform_markdown(
             default_language=visual_default_language,
             languages=[str(value) for value in configured_visual_languages],
         )
-        caption = title or alt
-        attributes = pandoc_image_attributes(match.group("attrs") or "")
+        credit, raw_attrs = caption_source_attribute(match.group("attrs") or "")
+        caption = caption_with_source(title or alt, credit)
+        attributes = pandoc_image_attributes(raw_attrs)
         return f"![{caption}]({printable}){attributes}"
 
     def callout(match: re.Match[str]) -> str:
@@ -991,6 +1055,14 @@ def transform_markdown(
             padding = " " if value.startswith("`") or value.endswith("`") else ""
             return f"{fence}{padding}{value}{padding}{fence}{{=latex}}"
 
+        def credited_caption(caption: str, credit: str) -> str:
+            # Leave credit-bearing captions as Pandoc inlines so citeproc and
+            # links see them before the figure filter styles the credit span.
+            # Separate an authored closing code fence from the generated raw
+            # fence; adjacent backticks would change the Markdown tokenisation.
+            return (raw_latex_inline(r"\caption[{") + caption + " " + raw_latex_inline("}]{")
+                    + caption_with_source(caption, credit) + raw_latex_inline("}"))
+
         images = list(IMAGE_RE.finditer(match.group("body")))
         if not images:
             raise ManualPdfError(f"Subfigures block contains no images in {source.relative_to(project)}")
@@ -1008,13 +1080,16 @@ def transform_markdown(
             )
 
         overall_caption = latex_caption(match.group("caption") or "")
+        overall_credit, _ = caption_source_attribute(match.group("attrs") or "")
         figure_start = "```{=latex}\n\\begin{figure}[H]\n\\centering\n"
-        if overall_caption:
+        if overall_caption and not overall_credit:
             figure_start += (
                 f"\\caption{{{overall_caption}}}\n"
                 "{\\color{ManualMuted!45}\\rule{\\linewidth}{0.35pt}}\\par\\medskip\n"
             )
         rendered = [figure_start + "```"]
+        if overall_credit:
+            rendered.append(credited_caption(match.group("caption") or "", overall_credit))
         image_index = 0
         max_image_height = f"{0.52 / len(row_sizes):.3f}".rstrip("0").rstrip(".")
         for row_index, row_size in enumerate(row_sizes):
@@ -1031,7 +1106,8 @@ def transform_markdown(
                     default_language=visual_default_language,
                     languages=[str(value) for value in configured_visual_languages],
                 )
-                attributes = pandoc_image_attributes(item.group("attrs") or "")
+                credit, raw_attrs = caption_source_attribute(item.group("attrs") or "")
+                attributes = pandoc_image_attributes(raw_attrs)
                 row.extend([
                     raw_latex_inline(
                         f"\\begin{{subfigure}}[t]{{{panel_width}\\linewidth}}"
@@ -1041,10 +1117,11 @@ def transform_markdown(
                     f"![]({printable}){attributes}",
                 ])
                 separator = r"\hfill" if column_index < row_size - 1 else ""
-                row.append(raw_latex_inline(
-                    f"\\caption{{{latex_caption(caption)}}}"
-                    f"\\end{{subfigure}}{separator}"
-                ))
+                if credit:
+                    row.append(credited_caption(caption, credit))
+                else:
+                    row.append(raw_latex_inline(f"\\caption{{{latex_caption(caption)}}}"))
+                row.append(raw_latex_inline(f"\\end{{subfigure}}{separator}"))
             rendered.append("".join(row))
             if row_index < len(row_sizes) - 1:
                 rendered.append("```{=latex}\n\\par\\medskip\n```")
@@ -1246,7 +1323,9 @@ def assemble(project: Path, config: dict[str, Any], lang: str, paths: dict[str,
     metadata["include-home"] = includes_home
     metadata["has-listings"] = "data-listing-caption=" in assembled_markdown
     prose_markdown = FENCED_CODE_BLOCK_RE.sub("", assembled_markdown)
-    metadata["has-figures"] = bool(IMAGE_RE.search(prose_markdown) or r"\begin{figure}" in prose_markdown)
+    # Transformed image captions can contain nested credit spans/citations;
+    # IMAGE_RE is the source reader, not a parser for those Pandoc inlines.
+    metadata["has-figures"] = bool(image_destinations(MARKDOWN_INLINE_CODE_RE.sub("", prose_markdown)) or r"\begin{figure}" in prose_markdown)
     metadata["has-tables"] = bool(re.search(r"^Table:\s+\S", prose_markdown, re.MULTILINE))
     return metadata, source_paths, assembled_markdown
 
@@ -1410,8 +1489,7 @@ def build_dependencies(project: Path, metadata: dict[str, Any], source_paths: li
             dependencies.append((f"asset:{path.relative_to(project)}", path))
     dependency_markdown = FENCED_CODE_BLOCK_RE.sub("", markdown)
     dependency_markdown = MARKDOWN_INLINE_CODE_RE.sub("", dependency_markdown)
-    for match in IMAGE_RE.finditer(dependency_markdown):
-        raw = match.group("path")
+    for raw in image_destinations(dependency_markdown):
         if raw.startswith(("http://", "https://", "data:", "#")):
             continue
         local_path, _ = split_url_decoration(raw)

data/scripts/manual/filters/figure-captions.lua

@@ -4,22 +4,53 @@ local function append_all(destination, values)
   end
 end
 
-function Figure(figure)
-  if not FORMAT:match("latex") or #figure.caption.long == 0 then
-    return nil
-  end
-
-  local caption = {pandoc.RawInline("latex", "\\caption{")}
-  for index, block in ipairs(figure.caption.long) do
+local function caption_inlines(caption)
+  local result = pandoc.Inlines({})
+  for index, block in ipairs(caption.long) do
     if index > 1 then
-      table.insert(caption, pandoc.Space())
+      table.insert(result, pandoc.Space())
     end
     if block.content then
-      append_all(caption, block.content)
+      append_all(result, block.content)
     else
-      table.insert(caption, pandoc.Str(pandoc.utils.stringify(block)))
+      table.insert(result, pandoc.Str(pandoc.utils.stringify(block)))
+    end
+  end
+  return result
+end
+
+local function description_only(inlines)
+  local has_source = false
+  local description = inlines:walk({
+    Span = function(span)
+      if span.classes:includes("uw-caption-source") then
+        has_source = true
+        return {}
+      end
     end
+  })
+  while #description > 0 and (description[#description].t == "Space" or description[#description].t == "SoftBreak") do
+    table.remove(description)
+  end
+  return description, has_source
+end
+
+local function figure_caption(figure)
+  if not FORMAT:match("latex") or #figure.caption.long == 0 then
+    return nil
+  end
+
+  local full = caption_inlines(figure.caption)
+  local short, has_source = description_only(full)
+  local caption = {}
+  if has_source then
+    table.insert(caption, pandoc.RawInline("latex", "\\caption[{"))
+    append_all(caption, short)
+    table.insert(caption, pandoc.RawInline("latex", "}]{"))
+  else
+    table.insert(caption, pandoc.RawInline("latex", "\\caption{"))
   end
+  append_all(caption, full)
   table.insert(caption, pandoc.RawInline("latex", "}"))
   if figure.identifier and figure.identifier ~= "" then
     table.insert(caption, pandoc.RawInline("latex", "\\label{" .. figure.identifier .. "}"))
@@ -33,3 +64,27 @@ function Figure(figure)
   table.insert(blocks, pandoc.RawBlock("latex", "\\end{figure}"))
   return blocks
 end
+
+local function table_caption(element)
+  if not FORMAT:match("latex") then
+    return nil
+  end
+  local short, has_source = description_only(caption_inlines(element.caption))
+  if has_source then
+    element.caption.short = short
+    return element
+  end
+end
+
+local function source_style(span)
+  if FORMAT:match("latex") and span.classes:includes("uw-caption-source") then
+    local inlines = {pandoc.RawInline("latex", "{\\itshape ")}
+    append_all(inlines, span.content)
+    table.insert(inlines, pandoc.RawInline("latex", "}"))
+    return inlines
+  end
+end
+
+-- Preserve semantic credit spans until short captions have been computed.
+-- Citeproc runs before this filter, including citations inside the spans.
+return {{Figure = figure_caption, Table = table_caption}, {Span = source_style}}

data/scripts/manual/templates/manual.tex

@@ -85,7 +85,8 @@
   singlelinecheck=false
 }
 \captionsetup[figure]{position=top,margin=1em,aboveskip=0pt,belowskip=7pt}
-\captionsetup[table]{position=top,margin=1em,aboveskip=0pt,belowskip=7pt}
+% longtable uses the caption skip below a top caption; belowskip alone is ignored.
+\captionsetup[table]{position=top,margin=1em,skip=7pt}
 \captionsetup[lstlisting]{position=top,margin=0pt,aboveskip=0pt,belowskip=7pt}
 \captionsetup[subfigure]{
   font={manualsubcaption,color=ManualMuted},

data/scripts/test_gem_build.py

@@ -23,7 +23,7 @@ CONTRACT = json.loads((ROOT / "src/unaltraweb_mcp/component-contract.json").read
 RUNTIME_IMAGE = str(CONTRACT["components"]["runtime"]["reference"])
 
 
-def run(command: list[str], *, cwd: Path = ROOT) -> subprocess.CompletedProcess[str]:
+def run(command: list[str], *, cwd: Path = ROOT, expected: int = 0) -> subprocess.CompletedProcess[str]:
     completed = subprocess.run(
         command,
         cwd=cwd,
@@ -32,7 +32,7 @@ def run(command: list[str], *, cwd: Path = ROOT) -> subprocess.CompletedProcess[
         stderr=subprocess.PIPE,
         check=False,
     )
-    if completed.returncode != 0:
+    if completed.returncode != expected:
         raise RuntimeError(f"Command failed: {' '.join(command)}\n{completed.stdout}\n{completed.stderr}")
     return completed
 
@@ -61,12 +61,16 @@ def build(output: Path, *, source: Path = ROOT) -> str:
 
 
 def inspect_gem(path: Path) -> None:
+    editorial_files = ["scripts/editorial_check.py", "src/unaltraweb_mcp/editorial.py", "src/unaltraweb_mcp/editorial_sources.py"]
+    inspection_files = editorial_files + ["scripts/image_background_check.py", "src/unaltraweb_mcp/image_backgrounds.py",
+                                          "src/unaltraweb_mcp/image_probe.py", "src/unaltraweb_mcp/processes.py"]
     with tarfile.open(path, mode="r") as package:
         data_member = package.extractfile("data.tar.gz")
         if data_member is None:
             raise RuntimeError("Built gem has no data.tar.gz payload.")
         with tarfile.open(fileobj=io.BytesIO(data_member.read()), mode="r:gz") as payload:
             names = set(payload.getnames())
+            editorial_bytes = {name: payload.extractfile(name).read() for name in inspection_files}
     required = {
         "LICENSE",
         "README.md",
@@ -97,6 +101,7 @@ def inspect_gem(path: Path) -> None:
         "src/unaltraweb_mcp/component-contract.json",
         "src/unaltraweb_mcp/component-contract.schema.json",
         "src/unaltraweb_mcp/docker_mount.py",
+        *inspection_files,
     }
     missing = sorted(required - names)
     if missing:
@@ -104,6 +109,31 @@ def inspect_gem(path: Path) -> None:
     unexpected_data = sorted(name for name in names if name.startswith("_data/") and not name.startswith("_data/i18n/"))
     if unexpected_data:
         raise RuntimeError(f"Built gem contains non-runtime data files: {unexpected_data}")
+    # Exercise only the actual gem payload with isolated Python: no factory,
+    # wheel, inherited PYTHONPATH, source checkout or MCP dependency may help.
+    with tempfile.TemporaryDirectory(prefix="unaltraweb-gem-editorial-") as temporary:
+        core = Path(temporary) / "core"
+        for name, content in editorial_bytes.items():
+            target = core / name
+            target.parent.mkdir(parents=True, exist_ok=True)
+            target.write_bytes(content)
+        site = Path(temporary) / "site"
+        (site / "_pages/en").mkdir(parents=True)
+        (site / "_config.yml").write_text("unaltraweb:\n  site_profile: unaltreselfie\n", encoding="utf-8")
+        page = site / "_pages/en/about.md"
+        page.write_text("I study spatial data.\n", encoding="utf-8")
+        command = [sys.executable, "-I", str(core / editorial_files[0]), "--project", str(site)]
+        if not json.loads(run(command, cwd=site).stdout)["ok"]:
+            raise RuntimeError("Gem-native editorial check rejected publication copy.")
+        page.write_text("As requested, I have added the biography.\n", encoding="utf-8")
+        if json.loads(run(command, cwd=site, expected=1).stdout)["ok"]:
+            raise RuntimeError("Gem-native editorial gate accepted chat-dependent copy.")
+        (site / "assets").mkdir()
+        (site / "assets/test.svg").write_text('<svg xmlns="http://www.w3.org/2000/svg" width="10" height="10"><circle cx="5" cy="5" r="2" fill="blue"/></svg>', encoding="utf-8")
+        image_command = [sys.executable, "-I", str(core / "scripts/image_background_check.py"), "--project", str(site), "--source", "assets/test.svg"]
+        inspection = json.loads(run(image_command, cwd=site).stdout)
+        if not inspection["ok"] or inspection["images"][0]["state"] != "transparent" or not inspection["warnings"]:
+            raise RuntimeError(f"Gem-native SVG background inspection failed: {inspection}")
 
 
 def main() -> int:

data/scripts/test_reproducible_jekyll_build.py

@@ -13,7 +13,7 @@ from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[1]
-IMAGE = os.environ.get("DOCKER_IMAGE", "ghcr.io/dosquartsdedocs/unaltraweb:0.4.0")
+IMAGE = os.environ.get("DOCKER_IMAGE", "ghcr.io/dosquartsdedocs/unaltraweb:0.5.0")
 SELECTOR = "v2026.09"
 EPOCH = "946684800"
 

data/scripts/test_wheel_install.py

@@ -75,6 +75,10 @@ def main() -> int:
             "unaltraweb_mcp/component-contract.schema.json",
             "unaltraweb_mcp/manual_pdf_preview.py",
             "unaltraweb_mcp/manual_release.py",
+            "unaltraweb_mcp/editorial.py",
+            "unaltraweb_mcp/editorial_sources.py",
+            "unaltraweb_mcp/image_backgrounds.py",
+            "unaltraweb_mcp/image_probe.py",
             "unaltraweb_mcp/scaffolds/common/AGENTS.md.tmpl",
             "unaltraweb_mcp/scaffolds/common/Makefile.tmpl",
             "unaltraweb_mcp/scaffolds/common/README.md.tmpl",
@@ -266,6 +270,9 @@ def main() -> int:
             if set(manifest["files"]) != expected_managed:
                 raise RuntimeError(f"generated {profile} scaffold baseline is incomplete: {manifest['files']}")
             sites[profile] = profile_site
+            checked = json.loads(run([str(cli), "--project", str(profile_site), "mcp", "prose-check"], cwd=temp).stdout)
+            if not checked["ok"] or checked["profile"] != profile:
+                raise RuntimeError(f"Package-only editorial check failed for {profile}: {checked}")
 
         site = sites["unaltredocs"]
         if not (site / ".unaltraweb/scaffold.json").is_file():
@@ -295,6 +302,9 @@ def main() -> int:
         detected = json.loads(run([str(cli), "--project", str(site), "mcp", "detect-site"], cwd=temp).stdout)
         if not detected["is_unaltraweb_site"]:
             raise RuntimeError(f"package-only inspection failed from clean wheel: {detected}")
+        backgrounds = json.loads(run([str(cli), "--project", str(site), "mcp", "image-background-check"], cwd=temp).stdout)
+        if not backgrounds["ok"] or not backgrounds["read_only"]:
+            raise RuntimeError(f"Factory-free background inspection failed: {backgrounds}")
         project_doctor = json.loads(run([str(cli), "doctor", "--project", str(site)], cwd=temp).stdout)
         if not project_doctor["ok"] or project_doctor["project"]["profile"] != "unaltredocs":
             raise RuntimeError(f"project doctor failed from clean wheel: {project_doctor}")
@@ -312,6 +322,24 @@ def main() -> int:
         scaffold = json.loads(run([str(cli), "--project", str(site), "mcp", "scaffold-sync"], cwd=temp).stdout)
         if not scaffold["ok"] or not scaffold["dry_run"]:
             raise RuntimeError(f"wheel scaffold sync dry-run failed: {scaffold}")
+        context = json.loads(run([str(cli), "--project", str(site), "mcp", "site-context"], cwd=temp).stdout)
+        if context["update_status"]["state"] != "current" or context["update_status"]["can_apply"]:
+            raise RuntimeError(f"wheel consumer update advisory failed: {context['update_status']}")
+        prepared = json.loads(run([str(cli), "--project", str(site), "mcp", "editorial-review-prepare"], cwd=temp).stdout)
+        report = {"id": "wheel-review", "source_digest": prepared["source_digest"], "reviewer": "Wheel smoke", "findings": []}
+        recorded = json.loads(run([
+            str(cli), "--project", str(site), "mcp", "editorial-review-record",
+            "--report-json", json.dumps(report), "--expected-revision", "0",
+        ], cwd=temp).stdout)
+        editorial = json.loads(run([str(cli), "--project", str(site), "mcp", "editorial-status"], cwd=temp).stdout)
+        if recorded["revision"] != 1 or editorial["reviews"]["wheel-review"]["stale"]:
+            raise RuntimeError("Factory-free wheel did not preserve a fresh editorial review.")
+        confirmed = json.loads(run([
+            str(cli), "--project", str(site), "mcp", "scaffold-sync", "--apply", "--confirm-sync",
+            "--expected-plan-sha256", scaffold["plan_sha256"],
+        ], cwd=temp).stdout)
+        if not confirmed["ok"] or not confirmed["applied"]:
+            raise RuntimeError(f"wheel reviewed scaffold synchronization failed: {confirmed}")
 
         factory_error = run([str(cli), "--project", str(site), "mcp", "prompts"], cwd=temp, expected=1)
         if "requires the unaltraweb factory checkout" not in factory_error.stderr:

data/scripts/unaltraweb-mcp-bootstrap.sh

@@ -10,7 +10,7 @@ If --project is omitted, MCP_CONSUMER_WORKSPACE is used, then the current direct
 USAGE
 }
 
-image="${UNALTRAWEB_MCP_IMAGE:-ghcr.io/dosquartsdedocs/unaltraweb-mcp:0.4.0}"
+image="${UNALTRAWEB_MCP_IMAGE:-ghcr.io/dosquartsdedocs/unaltraweb-mcp:0.5.0}"
 project="${MCP_CONSUMER_WORKSPACE:-${UNALTRAWEB_PROJECT:-}}"
 
 while [ "$#" -gt 0 ]; do

data/scripts/validate_distribution.py

@@ -71,6 +71,23 @@ def make_value(path: Path, variable: str) -> str:
     return match.group(1).strip('"\'') if match else ""
 
 
+def component_version_errors(contract: dict[str, Any]) -> list[str]:
+    """Retain the real version of already-published, digest-pinned workers."""
+    version = str(contract["release"]["version"])
+    errors = []
+    reusable_workers = {"compute_python", "compute_r", "web_capture"}
+    for component_id in ["gem", "wheel", "runtime", "mcp", "compute_python", "compute_r", "web_capture", "manual_pdf"]:
+        selected = contract["components"][component_id]
+        if (component_id in reusable_workers and selected["kind"] == "container"
+                and selected["release_status"] == "released"):
+            # Digest/repository/version-tag semantics remain independently checked
+            # by component_contract_semantic_errors; this is not a mutable fallback.
+            continue
+        if str(selected["version"]) != version:
+            errors.append(f"{component_id} version does not match release {version}")
+    return errors
+
+
 def validate(root: Path = ROOT) -> list[str]:
     errors: list[str] = []
     contract = distribution_contract()
@@ -87,9 +104,7 @@ def validate(root: Path = ROOT) -> list[str]:
         errors.append("release-candidates.json must be excluded from Docker build contexts")
     if __version__ != version:
         errors.append(f"wheel version {__version__} != contract version {version}")
-    for component_id in ["gem", "wheel", "runtime", "mcp", "compute_python", "compute_r", "web_capture", "manual_pdf"]:
-        if str(contract["components"][component_id]["version"]) != version:
-            errors.append(f"{component_id} version does not match release {version}")
+    errors.extend(component_version_errors(contract))
     included = {name for name, item in contract["components"].items() if item["included_in_wheel"]}
     if included != {"wheel"}:
         errors.append(f"wheel must not bundle external components: {sorted(included)}")

data/src/unaltraweb_mcp/component-contract.json

@@ -2,16 +2,16 @@
   "$schema": "component-contract.schema.json",
   "schema_version": 1,
   "release": {
-    "version": "0.4.0",
-    "tag": "v0.4.0"
+    "version": "0.5.0",
+    "tag": "v0.5.0"
   },
   "consumer_integration": {
     "schema_version": 1,
     "core_repository": "https://github.com/dosquartsdedocs/unaltraweb.git",
-    "core_sha": "f7ac29070167917dec6b314ba0a1ba9db089e7ec",
+    "core_sha": "02af70001bf8085af860fd57f8d7e75ec96a89c7",
     "site_deploy_workflow": "dosquartsdedocs/unaltraweb/.github/workflows/site-deploy.yml",
-    "manual_pdf_image": "ghcr.io/dosquartsdedocs/unaltraweb-manual-pdf@sha256:bb3e373f8a512495eeed684c23ad904d298c2e20a6dc3ade0d0a60c7ec9a9f11",
-    "vegavisuals_sha": "44a2753ffbb7c0694a459db9744342f69c6e78b9"
+    "manual_pdf_image": "ghcr.io/dosquartsdedocs/unaltraweb-manual-pdf@sha256:9e0b3a45753c170b795e9a9d6df61580085c113436beac5bf6c8de69b6562097",
+    "vegavisuals_sha": "68c0b231402ae9485cc34ce530dc5239cb0ec194"
   },
   "receipt_contract": {
     "schema_version": 1,
@@ -28,7 +28,7 @@
     "role": "Modular control, scaffolding, and offline inspection plane for unaltraweb sites.",
     "package_only_commands": ["doctor", "import-calibre", "new-web", "version"],
     "factory_required_commands": ["factory-dir"],
-    "package_only_mcp": ["bibliography-add-entry", "bibliography-inventory", "build-health", "content-approval-inventory", "content-freshness-check", "content-inventory", "detect-site", "html-audit", "http-check", "initialize-site", "language-policy", "list-tools", "manual-authoring-capabilities", "manual-editorial-quality-check", "manual-pdf-preview-clean", "manual-source-quality-check", "new-web", "preview-start", "preview-status", "preview-stop", "profile-check", "profile-prune", "profile-prune-plan", "scaffold-sync", "site-context", "site-doctor", "site-source-delete", "site-source-read", "site-source-write", "starter-templates", "translation-plan"],
+    "package_only_mcp": ["bibliography-add-entry", "bibliography-inventory", "build-health", "content-approval-inventory", "content-freshness-check", "content-inventory", "detect-site", "editorial-policy", "editorial-publication-check", "editorial-review-prepare", "editorial-review-record", "editorial-review-resolve", "editorial-status", "html-audit", "http-check", "image-background-check", "initialize-site", "language-policy", "list-tools", "manual-authoring-capabilities", "manual-editorial-quality-check", "manual-pdf-preview-clean", "manual-source-quality-check", "new-web", "preview-start", "preview-status", "preview-stop", "profile-check", "profile-prune", "profile-prune-plan", "prose-check", "scaffold-sync", "site-context", "site-doctor", "site-source-delete", "site-source-read", "site-source-write", "starter-templates", "translation-plan"],
     "factory_required_mcp": ["bibliometrics-check", "bibliometrics-fetch-scimago", "bibliometrics-update", "build-site", "manual-computation-check", "manual-computation-render", "manual-computation-render-figures", "manual-computation-status", "manual-pdf-build", "manual-pdf-preview-prepare", "manual-pdf-publish", "manual-pdf-status", "manual-release-check", "manual-release-prepare", "manual-release-status", "prompts", "serve", "site-check", "web-capture-check", "web-capture-render", "web-capture-status"],
     "not_bundled": ["gem", "runtime", "mcp", "compute_python", "compute_r", "web_capture", "manual_pdf", "diavisuals", "vegavisuals"]
   },
@@ -36,10 +36,10 @@
     "gem": {
       "kind": "gem",
       "name": "unaltraweb",
-      "version": "0.4.0",
-      "release": "v0.4.0",
+      "version": "0.5.0",
+      "release": "v0.5.0",
       "release_status": "ready",
-      "reference": "unaltraweb (= 0.4.0)",
+      "reference": "unaltraweb (= 0.5.0)",
       "repository": "https://github.com/dosquartsdedocs/unaltraweb",
       "included_in_wheel": false,
       "features": ["jekyll-core", "site-build"]
@@ -47,10 +47,10 @@
     "wheel": {
       "kind": "python-wheel",
       "name": "unaltraweb-mcp",
-      "version": "0.4.0",
-      "release": "v0.4.0",
+      "version": "0.5.0",
+      "release": "v0.5.0",
       "release_status": "ready",
-      "reference": "unaltraweb-mcp==0.4.0",
+      "reference": "unaltraweb-mcp==0.5.0",
       "repository": "https://github.com/dosquartsdedocs/unaltraweb",
       "included_in_wheel": true,
       "features": ["calibre-import", "doctor", "new-web", "offline-inspection", "mcp-control-plane"]
@@ -58,10 +58,10 @@
     "runtime": {
       "kind": "container",
       "name": "unaltraweb runtime",
-      "version": "0.4.0",
-      "release": "v0.4.0",
+      "version": "0.5.0",
+      "release": "v0.5.0",
       "release_status": "ready",
-      "reference": "ghcr.io/dosquartsdedocs/unaltraweb:0.4.0",
+      "reference": "ghcr.io/dosquartsdedocs/unaltraweb:0.5.0",
       "image_repository": "ghcr.io/dosquartsdedocs/unaltraweb",
       "repository": "https://github.com/dosquartsdedocs/unaltraweb",
       "included_in_wheel": false,
@@ -70,10 +70,10 @@
     "mcp": {
       "kind": "container",
       "name": "unaltraweb MCP runtime",
-      "version": "0.4.0",
-      "release": "v0.4.0",
+      "version": "0.5.0",
+      "release": "v0.5.0",
       "release_status": "ready",
-      "reference": "ghcr.io/dosquartsdedocs/unaltraweb-mcp:0.4.0",
+      "reference": "ghcr.io/dosquartsdedocs/unaltraweb-mcp:0.5.0",
       "image_repository": "ghcr.io/dosquartsdedocs/unaltraweb-mcp",
       "repository": "https://github.com/dosquartsdedocs/unaltraweb",
       "included_in_wheel": false,
@@ -118,10 +118,10 @@
     "manual_pdf": {
       "kind": "container",
       "name": "unaltraweb manual PDF worker",
-      "version": "0.4.0",
-      "release": "v0.4.0",
-      "release_status": "ready",
-      "reference": "ghcr.io/dosquartsdedocs/unaltraweb-manual-pdf:0.4.0",
+      "version": "0.5.0",
+      "release": "v0.5.0",
+      "release_status": "released",
+      "reference": "ghcr.io/dosquartsdedocs/unaltraweb-manual-pdf@sha256:9e0b3a45753c170b795e9a9d6df61580085c113436beac5bf6c8de69b6562097",
       "image_repository": "ghcr.io/dosquartsdedocs/unaltraweb-manual-pdf",
       "repository": "https://github.com/dosquartsdedocs/unaltraweb",
       "included_in_wheel": false,
@@ -130,10 +130,10 @@
     "diavisuals": {
       "kind": "companion",
       "name": "diavisuals",
-      "version": "0.3.1",
-      "release": "v0.3.1",
+      "version": "0.4.0",
+      "release": "v0.4.0",
       "release_status": "released",
-      "reference": "https://github.com/dosquartsdedocs/diavisuals.git@v0.3.1",
+      "reference": "https://github.com/dosquartsdedocs/diavisuals/releases/download/v0.4.0/diavisuals-0.4.0-py3-none-any.whl#sha256=bfedcc9e2554f25ce4a1c33e556f352210848fccb8da800d1c3900dd86c48c93",
       "repository": "https://github.com/dosquartsdedocs/diavisuals",
       "included_in_wheel": false,
       "features": ["mermaid", "plantuml"]
@@ -141,10 +141,10 @@
     "vegavisuals": {
       "kind": "companion",
       "name": "vegavisuals",
-      "version": "0.3.1",
-      "release": "v0.3.1",
+      "version": "0.4.0",
+      "release": "v0.4.0",
       "release_status": "released",
-      "reference": "https://github.com/dosquartsdedocs/vegavisuals.git@v0.3.1",
+      "reference": "https://github.com/dosquartsdedocs/vegavisuals/releases/download/v0.4.0/vegavisuals-0.4.0-py3-none-linux_x86_64.whl#sha256=b52ffa743643dd6b5e0320e7a9aa0cd500ea06262b7d5098c0c3f94a379bc0ea",
       "repository": "https://github.com/dosquartsdedocs/vegavisuals",
       "included_in_wheel": false,
       "features": ["vega", "vega-lite"]