refactor(gui): tool registry + components package for per-tool builds

Two low-risk seam moves to enable selling per-tool subsets without
breaking the existing all-in-one bundle. Behaviour identical; every
existing import still resolves; full pytest suite + every page returns
HTTP 200.

1. **Tool registry** (src/gui/tools_registry.py) — replaces the
   inline dict-of-dicts in app.py with a Tool dataclass and a TOOLS
   list. Adds a tier field ("core" today, "pro" / "enterprise" later)
   and tools_for_tier() / tool_by_id() / display_name() helpers. A
   per-tool build slices TOOLS at import time without code changes.

2. **components package** (src/gui/components/) — converts the former
   single components.py into a package with:
     _legacy.py        — original file, unchanged.
     __init__.py       — re-exports the legacy surface; existing
                         "from src.gui.components import …" calls
                         continue to work.
     shared.py         — hide_streamlit_chrome, pickup_or_upload
                         (every build needs these).
     gate.py           — require_normalization_gate (Pro / Suite SKUs).
     findings.py       — analyzer-finding widgets (drops out of a
                         standalone-Dedup build).
     dedup_review.py   — match-group cards + apply pipeline (drops out
                         of a non-dedup build).

   The seam modules are narrow re-exports today. As code migrates out
   of _legacy.py into the focused modules, the public import path
   stays stable via the shim.

E2E: 765 passed, 17 xfailed (unchanged); home page + all 9 tool pages
+ Review page render HTTP 200; full pipeline (analyze → auto_fix →
apply_decisions → output bytes) round-trips on the kitchen-sink
fixture with zero high-confidence findings remaining post-fix.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/gui/app.py

@@ -57,80 +57,7 @@ st.divider()
 # Tool cards
 # ---------------------------------------------------------------------------
 
-TOOLS = [
+from src.gui.tools_registry import TOOLS
-    {
-        "icon": "🔍",
-        "name": "Deduplicator",
-        "description": "Fuzzy matching, normalization, survivor selection, and interactive review.",
-        "status": "Ready",
-        "page": "1_Deduplicator",
-        "tool_id": "01_deduplicator",
-    },
-    {
-        "icon": "✂️",
-        "name": "Text Cleaner",
-        "description": "Whitespace trim, multi-space collapse, Unicode normalization, BOM and line-ending handling.",
-        "status": "Ready",
-        "page": "2_Text_Cleaner",
-        "tool_id": "02_text_cleaner",
-    },
-    {
-        "icon": "📐",
-        "name": "Format Standardizer",
-        "description": "Standardize dates, currencies, names, phone numbers, and addresses.",
-        "status": "Coming Soon",
-        "page": "3_Format_Standardizer",
-        "tool_id": "03_format_standardizer",
-    },
-    {
-        "icon": "🕳️",
-        "name": "Missing Value Handler",
-        "description": "Detect disguised nulls, missingness analysis, and imputation strategies.",
-        "status": "Coming Soon",
-        "page": "4_Missing_Values",
-        "tool_id": "04_missing_handler",
-    },
-    {
-        "icon": "🗂️",
-        "name": "Column Mapper",
-        "description": "Rename columns, enforce a target schema, and coerce types.",
-        "status": "Coming Soon",
-        "page": "5_Column_Mapper",
-        "tool_id": "05_column_mapper",
-    },
-    {
-        "icon": "📊",
-        "name": "Outlier Detector",
-        "description": "Z-score, IQR, and MAD detection with domain-rule violations and winsorization.",
-        "status": "Coming Soon",
-        "page": "6_Outlier_Detector",
-        "tool_id": "06_outlier_detector",
-    },
-    {
-        "icon": "📎",
-        "name": "Multi-File Merger",
-        "description": "Combine multiple CSV/Excel files with schema alignment.",
-        "status": "Coming Soon",
-        "page": "7_Multi_File_Merger",
-        "tool_id": "07_multi_file_merger",
-    },
-    {
-        "icon": "✅",
-        "name": "Validator & Reporter",
-        "description": "Validate against rules and generate PDF/Excel quality reports.",
-        "status": "Coming Soon",
-        "page": "8_Validator_Reporter",
-        "tool_id": "08_validator_reporter",
-    },
-    {
-        "icon": "⚙️",
-        "name": "Pipeline Runner",
-        "description": "Chain tools in recommended order and pass output between steps.",
-        "status": "Coming Soon",
-        "page": "9_Pipeline_Runner",
-        "tool_id": "09_pipeline_runner",
-    },
-]
 
 # Render tool cards in a 3-column grid. Cards picked up by the analyzer get a
 # coloured "N findings" badge so the user can see at a glance which tools
@@ -143,15 +70,15 @@ for row_start in range(0, len(TOOLS), 3):
             break
         tool = TOOLS[idx]
         with col:
-            status_color = "green" if tool["status"] == "Ready" else "orange"
+            status_color = "green" if tool.status == "Ready" else "orange"
             badge = ""
-            n = findings_count_for_tool(tool.get("tool_id", ""))
+            n = findings_count_for_tool(tool.tool_id)
             if n:
                 badge = f" :red-background[**{n} finding{'s' if n != 1 else ''}**]"
             st.markdown(
-                f"### {tool['icon']} {tool['name']}{badge}\n\n"
+                f"### {tool.icon} {tool.name}{badge}\n\n"
-                f"{tool['description']}\n\n"
+                f"{tool.description}\n\n"
-                f":{status_color}[**{tool['status']}**]"
+                f":{status_color}[**{tool.status}**]"
             )
 
 

src/gui/components/__init__.py

@@ -0,0 +1,57 @@
+"""Reusable Streamlit widgets for the DataTools GUI.
+
+This package replaces the former single ``components.py`` module. Public
+behaviour is identical — every name that used to be importable from
+``src.gui.components`` is still importable from the same path because
+this ``__init__`` re-exports the legacy surface in full.
+
+The package layout exists so per-tool builds can ship only the seams
+they need without dragging the entire kitchen-sink module:
+
+    components/
+        __init__.py        ← compatibility shim (this file)
+        _legacy.py         ← original components.py, unchanged
+        gate.py            ← gate-only seam (require_normalization_gate)
+        findings.py        ← analyzer-finding rendering seam
+        dedup_review.py    ← dedup match-group cards + review pipeline
+        shared.py          ← chrome / file-pickup helpers used by every tool
+
+A standalone Deduplicator build, for example, can ship without
+``findings.py`` and ``gate.py`` — those modules import the analyzer /
+gate code that the Lite SKU does not include.
+
+Adding new tooling: drop new helpers into the appropriate seam module.
+Add their names to its ``__all__`` and to this file's ``__all__`` if
+they should remain importable from ``src.gui.components`` directly.
+"""
+
+from __future__ import annotations
+
+# Re-export the full legacy surface so existing pages continue to
+# import unchanged. Once individual tool packages start consuming
+# the focused seam modules directly, names can migrate out of
+# _legacy.py without breaking those imports — this shim is what
+# absorbs the move.
+from ._legacy import *  # noqa: F401,F403
+from . import _legacy as _legacy  # noqa: F401  (keep for direct access)
+
+# Names exported from _legacy.py that pages currently use. Kept here as
+# the canonical public list so a removal from _legacy is a visible
+# breaking change instead of a silent drop.
+__all__ = [
+    # Shared chrome / pickup / gate
+    "hide_streamlit_chrome",
+    "pickup_or_upload",
+    "require_normalization_gate",
+    # Dedup widgets
+    "config_panel",
+    "match_group_card",
+    "results_summary",
+    "apply_review_decisions",
+    # Analyzer widgets
+    "tool_display_name",
+    "render_findings_panel",
+    "render_hidden_aware_preview",
+    "upload_and_analyze_section",
+    "findings_count_for_tool",
+]

src/gui/components/dedup_review.py

@@ -0,0 +1,24 @@
+"""Dedup match-group cards and review pipeline.
+
+The interactive dedup-review surface — config panel, match-group cards,
+results summary, and apply-decisions glue. This is the largest single
+chunk of the GUI by line count; isolating it in a seam module means a
+non-dedup SKU never has to import it (and never has to drag in
+``src.core.dedup`` along the way).
+"""
+
+from __future__ import annotations
+
+from ._legacy import (
+    apply_review_decisions,
+    config_panel,
+    match_group_card,
+    results_summary,
+)
+
+__all__ = [
+    "apply_review_decisions",
+    "config_panel",
+    "match_group_card",
+    "results_summary",
+]

src/gui/components/findings.py

@@ -0,0 +1,25 @@
+"""Analyzer-finding widgets.
+
+Surfaces for the analyzer's home-page section, the per-tool findings
+panel, and the hidden-character-aware preview table. A build that
+doesn't ship the analyzer (e.g. standalone Dedup-only) does not need
+this module — its import would drag ``src.core.analyze`` along with it.
+"""
+
+from __future__ import annotations
+
+from ._legacy import (
+    findings_count_for_tool,
+    render_findings_panel,
+    render_hidden_aware_preview,
+    tool_display_name,
+    upload_and_analyze_section,
+)
+
+__all__ = [
+    "findings_count_for_tool",
+    "render_findings_panel",
+    "render_hidden_aware_preview",
+    "tool_display_name",
+    "upload_and_analyze_section",
+]

src/gui/components/gate.py

@@ -0,0 +1,16 @@
+"""Normalization-gate guard for tool pages.
+
+``require_normalization_gate`` short-circuits a tool page when the
+current upload has not yet passed the gate, redirecting the user to the
+Review & Normalize page. Pulled into its own seam module so:
+
+* A build that includes the gate (Pro / Suite SKUs) imports this.
+* A standalone single-tool build that bypasses the gate can omit this
+  module entirely without removing the helper from a shared file.
+"""
+
+from __future__ import annotations
+
+from ._legacy import require_normalization_gate
+
+__all__ = ["require_normalization_gate"]

src/gui/components/shared.py

@@ -0,0 +1,14 @@
+"""Chrome and file-pickup helpers — every build needs these.
+
+This is the smallest seam: any DataTools build, regardless of which
+tools it bundles, needs ``hide_streamlit_chrome`` (the app-like UI
+polish) and ``pickup_or_upload`` (lets a tool page reuse the home-page
+upload). Importing from here instead of the kitchen-sink ``components``
+package keeps a Lite build's dependency graph tight.
+"""
+
+from __future__ import annotations
+
+from ._legacy import hide_streamlit_chrome, pickup_or_upload
+
+__all__ = ["hide_streamlit_chrome", "pickup_or_upload"]

src/gui/tools_registry.py

@@ -0,0 +1,152 @@
+"""Per-tool manifest registry.
+
+Single source of truth for what tools exist, their display strings, and
+the tier (which controls whether a tool ships in a given build SKU). The
+home-page sidebar consumes this list; future per-tool packaging will
+filter it via the ``tier`` field.
+
+Adding a tool: append one ``Tool`` entry. Page filenames must match the
+``page_slug`` so Streamlit's automatic page discovery picks them up.
+
+Selling subsets: builds can filter ``TOOLS`` by tier or tool_id at
+import time — no other code changes required, since pages key off
+``tool_id`` for findings badges and the home grid renders whatever's in
+the filtered list.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Literal
+
+
+Tier = Literal["core", "pro", "enterprise"]
+Status = Literal["Ready", "Coming Soon"]
+
+
+@dataclass(frozen=True)
+class Tool:
+    """One tool's manifest entry."""
+
+    tool_id: str           # Stable identifier matching the analyzer's tool field.
+    icon: str              # Single-glyph icon for the home grid card.
+    name: str              # Display name (sidebar + card title).
+    description: str       # One-sentence card body.
+    page_slug: str         # Streamlit page filename without ".py" (e.g. "1_Deduplicator").
+    status: Status         # "Ready" or "Coming Soon" — drives the card badge color.
+    tier: Tier = "core"    # Build-time gating hook; every tool is "core" today.
+
+
+TOOLS: list[Tool] = [
+    Tool(
+        tool_id="01_deduplicator",
+        icon="🔍",
+        name="Deduplicator",
+        description=(
+            "Fuzzy matching, normalization, survivor selection, and "
+            "interactive review."
+        ),
+        page_slug="1_Deduplicator",
+        status="Ready",
+    ),
+    Tool(
+        tool_id="02_text_cleaner",
+        icon="✂️",
+        name="Text Cleaner",
+        description=(
+            "Whitespace trim, multi-space collapse, Unicode normalization, "
+            "BOM and line-ending handling."
+        ),
+        page_slug="2_Text_Cleaner",
+        status="Ready",
+    ),
+    Tool(
+        tool_id="03_format_standardizer",
+        icon="📐",
+        name="Format Standardizer",
+        description=(
+            "Standardize dates, currencies, names, phone numbers, and addresses."
+        ),
+        page_slug="3_Format_Standardizer",
+        status="Coming Soon",
+    ),
+    Tool(
+        tool_id="04_missing_handler",
+        icon="🕳️",
+        name="Missing Value Handler",
+        description=(
+            "Detect disguised nulls, missingness analysis, and imputation strategies."
+        ),
+        page_slug="4_Missing_Values",
+        status="Coming Soon",
+    ),
+    Tool(
+        tool_id="05_column_mapper",
+        icon="🗂️",
+        name="Column Mapper",
+        description="Rename columns, enforce a target schema, and coerce types.",
+        page_slug="5_Column_Mapper",
+        status="Coming Soon",
+    ),
+    Tool(
+        tool_id="06_outlier_detector",
+        icon="📊",
+        name="Outlier Detector",
+        description=(
+            "Z-score, IQR, and MAD detection with domain-rule violations and "
+            "winsorization."
+        ),
+        page_slug="6_Outlier_Detector",
+        status="Coming Soon",
+    ),
+    Tool(
+        tool_id="07_multi_file_merger",
+        icon="📎",
+        name="Multi-File Merger",
+        description="Combine multiple CSV/Excel files with schema alignment.",
+        page_slug="7_Multi_File_Merger",
+        status="Coming Soon",
+    ),
+    Tool(
+        tool_id="08_validator_reporter",
+        icon="✅",
+        name="Validator & Reporter",
+        description=(
+            "Validate against rules and generate PDF/Excel quality reports."
+        ),
+        page_slug="8_Validator_Reporter",
+        status="Coming Soon",
+    ),
+    Tool(
+        tool_id="09_pipeline_runner",
+        icon="⚙️",
+        name="Pipeline Runner",
+        description=(
+            "Chain tools in recommended order and pass output between steps."
+        ),
+        page_slug="9_Pipeline_Runner",
+        status="Coming Soon",
+    ),
+]
+
+
+def tools_for_tier(*tiers: Tier) -> list[Tool]:
+    """Subset filter for build-time slicing.
+
+    Empty *tiers* returns every tool. Used by per-tool packaging to ship
+    only the relevant subset of pages and home-grid cards.
+    """
+    if not tiers:
+        return list(TOOLS)
+    keep = set(tiers)
+    return [t for t in TOOLS if t.tier in keep]
+
+
+def tool_by_id(tool_id: str) -> Tool | None:
+    return next((t for t in TOOLS if t.tool_id == tool_id), None)
+
+
+def display_name(tool_id: str) -> str:
+    """Return the human-readable name; fall back to the id when unknown."""
+    t = tool_by_id(tool_id)
+    return t.name if t else tool_id