Merge integration/rpa-dashboard-skills into ticket 04

Keeps both sides: frontend detection and bot wiring from tickets 02/03, optional
sections from ticket 04. The a-empty-sections eval now uses the shared "fixture" key.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

rpa-dashboard-no-ai/SKILL.md

@@ -11,11 +11,14 @@ source projects.
 | File | What it is |
 |---|---|
 | `templates/dashboard.html` | The single-file page: theme tokens, shell, KPI, donut, run panel, report, sample data. Works in PyQt (QWebChannel) or on the web (polling). |
-| `templates/bridge.py` | Minimal PyQt6 host. It runs the bot as a child process and tails its output. |
+| `templates/bridge.py` | Minimal PyQt6 host: the window, the bridge slots, and the saved dark-mode choice. |
+| `templates/bot_runner.py` | The bot wiring, without Qt. It runs the bot as a child process, tails its output, and turns lines into step and log events. |
 | `templates/contract.md` | The data contract: events the bot sends, actions the page sends. |
 | `templates/themes.md` | Theme presets (Tebra Sky, Superbill Ember) and the custom-colour steps. |
 | `templates/palette.py` | Derives a custom palette from one brand hex and checks contrast. |
 | `templates/sections.py`, `templates/sections.md` | Keeps the chosen optional sections in the page and deletes the rest; what each section needs from the host. |
+| `templates/frontend.md` | Existing frontend: detect it, report it, then keep or restyle. Shared with `rpa-dashboard-ai`. |
+| `templates/detect_frontend.py` | Finds an existing frontend and prints its location, stack and token blocks. |
 | `templates/reference/` | Raw Tebra extracts, for reference only. The optional sections are already in `dashboard.html`. |
 
 Follow the steps in order. Ask one question at a time, and wait for the answer.
@@ -24,22 +27,24 @@ If the user's request already answers a question, don't ask it again.
 ## 1. Scan the project
 
 Before asking anything, look at the project:
-- **Frontend:** `*.html` files outside `node_modules`, `.venv` and build output; a
+- **Frontend:** run `python templates/detect_frontend.py <project root>`. It finds
-  `web/`, `frontend/` or `static/` folder; `package.json` with react, vue, angular or
+  plain HTML, React/Vue/Angular/Svelte apps and PyQt web views, and prints each
-  svelte; a PyQt `QWebEngineView`. For any you find, note the location, the stack and
+  one's location, stack and colour tokens. `templates/frontend.md` says what it
-  the main colour tokens (CSS custom properties or the Tailwind theme).
+  covers and what to do with its report.
 - **Bot:** the entry point (for example `main.py`, a `__main__` module or a run
   script), what it prints (step markers, status and error lines), and how it starts.
 
 ## 2. Report the frontend, then ask keep or restyle
 
+Follow `templates/frontend.md` sections 2 to 5. In short:
 - **No frontend:** say "No existing frontend found." and go to step 3. Don't
   describe a frontend that isn't there.
 - **Frontend found:** say "Frontend found at `<path>`, stack `<stack>`, colours
   `<main tokens>`." Then ask: **keep its look**, or **restyle** it?
   - Keep: skip step 3. Build the page with the project's own tokens and fonts, and
-    change none of its existing styles.
+    change no existing file.
-  - Restyle: go to step 3. Change only the theme tokens, never layout or logic.
+  - Restyle: go to step 3. In the existing files, change only the token blocks,
+    never layout or logic, and show the user the diff.
 
 ## 3. Ask for colours
 
@@ -51,6 +56,8 @@ Skip this if the user chose to keep the existing look. Offer:
 ## 4. Ask desktop or web
 
 Ask only if there is no frontend. If there is one, use its stack.
+Don't ask if the project already uses PyQt (`PyQt6` or `PyQt5` in its requirements,
+`pyproject.toml` or imports): choose desktop and say so.
 - **Desktop:** a PyQt6 window with the page embedded. The page talks to Python
   through a bridge, so no web server is needed.
 - **Web:** the same page, served by a backend that it polls.
@@ -81,6 +88,7 @@ to answer.
    - Desktop: put it next to the host, for example `dashboard/dashboard.html`.
    - Web: put it in the backend's static folder. With no backend yet, use
      `dashboard/dashboard.html`.
+   - Existing frontend: put it where `templates/frontend.md` section 3 says.
 2. Fill every `{{...}}` placeholder:
 
    | Placeholder | Value |
@@ -94,10 +102,12 @@ to answer.
 3. Apply the theme by replacing the `body{...}` and `body.dark{...}` token blocks
    with the preset from `templates/themes.md`. For Ember, also add its font link.
    For a custom colour, run `python templates/palette.py "<hex>"`, paste the
-   tokens it prints, and show the user its contrast table.
+   tokens it prints, and show the user its contrast table. If the user chose keep,
-4. Desktop: also copy `templates/bridge.py` next to the page, and fill
+   fill the blocks from the project's tokens instead (`templates/frontend.md`
-   `{{BOT_MODULE}}`, the `STEPS` list (the same steps as the page), `{{ORG}}` and
+   section 4).
-   `{{APP_NAME}}`.
+4. Desktop: also copy `templates/bridge.py` and `templates/bot_runner.py` next to
+   the page. Fill `{{ORG}}` and `{{APP_NAME}}` in `bridge.py`, and `{{BOT_MODULE}}` in
+   `bot_runner.py` (with no bot yet, use the module the bot will have, for example `bot`).
 5. Search the output for `{{`. None may be left.
 
 ## 7. Wire the data
@@ -108,10 +118,22 @@ both directions.
   answers its own data actions, so it opens with sample batches and report rows,
   and Run plays a demo run. Tell the user which events their bot must send later.
 - **Bot exists:** set `SAMPLE_DATA = false` and delete the `SAMPLE DATA` block. Then:
-  - Desktop: in `bridge.py`, set `BOT_CMD` to start the bot as a child process.
+  - Desktop: all the wiring is in `bot_runner.py`.
-    Fill `STEP_MARKERS` and `FRIENDLY_RULES` from lines the bot really prints. Use
+    1. Get the bot's real output: run it once (for example `python -m bot`), or read
-    specific substrings (for example `[step 3]`, not a bare word); the first match
+       its `print` and logging calls. Never invent lines it doesn't print.
-    wins. Unmatched error lines must always reach the log.
+    2. Set `BOT_CMD` to start the bot as a child process, and `BOT_CWD` to the folder
+       it runs from.
+    3. Set `STEPS_JSON` in the page to the bot's real stages. Fill `STEP_MARKERS` with
+       `(substring, step label, pct)`: one specific substring per stage (for example
+       `[step 3]`, never a bare word like `login`), each label exactly one of the
+       page's STEPS, and pct rising to 100 on the bot's last line. The first match wins.
+    4. Fill `FRIENDLY_RULES` with `(substring, plain-English message, type)` for the
+       lines an operator should see. Unmatched lines are hidden, except error lines
+       (any line with a word from `ERROR_WORDS`), which are always shown as they are.
+       Add the bot's own failure words to `ERROR_WORDS` if it uses others.
+    5. Dry run without the window: `python dashboard/bot_runner.py`. It prints each
+       event the page would get. Check that the steps arrive in order and end at
+       100, and that the bot's error lines appear as `error` log events.
   - Web: the backend serves `GET {API_BASE}/dashboard`, `GET {API_BASE}/run/status`
     (returning `{running, events[]}`) and `POST {API_BASE}/<action-with-dashes>`.
   - Apply the contract's derived rules: batch state from Pending plus date, and
@@ -119,7 +141,10 @@ both directions.
 
 ## 8. Verify
 
-Open the page. On desktop run the host; otherwise open the file or the served URL.
+Open the page. On desktop run the host (`python dashboard/bridge.py`), click Run,
+and check that the Run button stays disabled until the bot finishes, and that the
+dark-mode choice is still set after you close and reopen the window. Otherwise
+open the file or the served URL.
 With sample data, opening the file in a browser is enough. Check:
 - the light theme, the dark theme (use the toggle), and a window 820px wide or less;
 - KPI cards, donut and legend, the Run tab's steps and log, and the Report tab's

rpa-dashboard-no-ai/templates/bot_runner.py

@@ -0,0 +1,64 @@
+"""Bot wiring for the desktop host: runs the bot and turns its output into page events.
+
+No Qt here, so it can be tested and dry-run on its own. Fill BOT_CMD, STEP_MARKERS and
+FRIENDLY_RULES from lines the bot really prints.
+
+Dry run, no window:  python bot_runner.py   (prints each event the page would get)
+"""
+import json, os, subprocess, sys
+from pathlib import Path
+
+BOT_CMD = [sys.executable, "-m", "{{BOT_MODULE}}"]   # the bot, started as a child process
+BOT_CWD = Path(__file__).resolve().parents[1]        # folder BOT_CMD runs in (the project root)
+RAW_LOG = Path(__file__).with_name("bot_raw.log")    # every raw bot line, kept for audit
+# (specific substring, step label from STEPS in dashboard.html, pct). First match wins.
+# e.g. ("[step 2]", "Login", 40). Never a bare word like "login": it matches unrelated lines.
+STEP_MARKERS = []
+# (specific substring, plain-English message, type: info|success|warn|error). First match wins.
+# e.g. ("[login] done", "Logged in.", "success"). Unmatched lines are hidden, except error lines.
+FRIENDLY_RULES = []
+# A line holding any of these is an error line. Unmatched error lines are shown raw, never hidden.
+ERROR_WORDS = ("error", "exception", "traceback", "fatal", "failed")
+
+
+def _first(rules, line):
+    low = line.lower()
+    return next((r for r in rules if r[0].lower() in low), None)
+
+
+def events_for(line):
+    """The page events, as (event, data) pairs, for one raw bot line."""
+    out = []
+    if marker := _first(STEP_MARKERS, line):
+        out.append(("step", {"label": marker[1], "pct": marker[2]}))
+    if rule := _first(FRIENDLY_RULES, line):
+        out.append(("log", {"msg": rule[1], "type": rule[2]}))
+    elif any(w in line.lower() for w in ERROR_WORDS):   # never hide a real failure
+        out.append(("log", {"msg": line, "type": "error"}))
+    return out
+
+
+def run(send):
+    """Run the bot in its own process and send(event, data) for each line it prints, as it prints it."""
+    send("status", {"state": "running", "msg": "Running…"})
+    env = {**os.environ, "PYTHONUNBUFFERED": "1", "PYTHONIOENCODING": "utf-8"}  # live lines; no cp1252 crash
+    try:
+        raw = open(RAW_LOG, "a", encoding="utf-8")
+        p = subprocess.Popen(BOT_CMD, cwd=BOT_CWD, env=env, stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
+                             text=True, encoding="utf-8", errors="replace")
+    except OSError as e:
+        send("log", {"msg": f"Could not start the bot: {e}", "type": "error"})
+        send("status", {"state": "error", "msg": "Could not start the bot"})
+        return
+    with p, raw:
+        for line in p.stdout:
+            raw.write(line)
+            for event, data in events_for(line.rstrip()):
+                send(event, data)
+    ok = p.returncode == 0
+    send("status", {"state": "done", "msg": "Completed"} if ok else
+         {"state": "error", "msg": f"Failed (exit code {p.returncode})"})
+
+
+if __name__ == "__main__":
+    run(lambda event, data: print(json.dumps({"event": event, "data": data}), flush=True))

rpa-dashboard-no-ai/templates/bridge.py

@@ -1,25 +1,23 @@
 """Minimal PyQt6 host for dashboard.html (desktop mode). Pattern from Tebra main_window.py.
 
-The bot runs as a child process that prints lines, and this window tails them.
+The bot runs as a child process and this window shows its progress. The bot wiring
-Fill in STEP_MARKERS, FRIENDLY_RULES and BOT_CMD for the project.
+(command, step markers, friendly rules) lives in bot_runner.py, next to this file.
+Run it with:  python dashboard/bridge.py
 """
-import json, subprocess, sys, threading
+import json, sys, threading
 from pathlib import Path
 from PyQt6.QtCore import QObject, pyqtSlot, pyqtSignal, QUrl, QSettings
 from PyQt6.QtWidgets import QApplication, QMainWindow
 from PyQt6.QtWebEngineWidgets import QWebEngineView
 from PyQt6.QtWebChannel import QWebChannel
 
+import bot_runner
+
 HTML_PATH = Path(__file__).with_name("dashboard.html")
-BOT_CMD = [sys.executable, "-m", "{{BOT_MODULE}}"]           # child process
-STEPS = ["{{STEP_1}}", "{{STEP_2}}"]                           # same list as STEPS in dashboard.html
-STEP_MARKERS = [("[step 1]", 0, 10), ("[all done]", len(STEPS) - 1, 100)]  # (substring, step idx, pct)
-FRIENDLY_RULES = [("[login] done", "Logged in.", "success")]  # (substring, friendly msg | None, type)
 
 
-def classify(line):
+def settings():
-    s = line.lower()
+    return QSettings("{{ORG}}", "{{APP_NAME}}")
-    return "error" if ("error" in s or "traceback" in s) else "warn" if "warn" in s else "info"
 
 
 class Bridge(QObject):
@@ -27,8 +25,10 @@ class Bridge(QObject):
 
     def __init__(self, view):
         super().__init__()
-        self.view = view
+        self.view, self._one_run = view, threading.Lock()
         self._emit.connect(lambda js: self.view.page().runJavaScript(f"window.__pyMsg({js})"))
+        # Restore the saved dark-mode choice on every page load, sample-data mode included.
+        view.loadFinished.connect(lambda _ok: self.send_to_js("apply_dark", {"on": settings().value("dark", False, bool)}))
 
     def send_to_js(self, event, data):
         self._emit.emit(json.dumps(json.dumps({"event": event, "data": data})))
@@ -36,38 +36,29 @@ class Bridge(QObject):
     @pyqtSlot()
     def load_dashboard(self):
         self.send_to_js("dashboard_data", {"batches": []})       # TODO: read from DB on a worker thread
-        self.send_to_js("apply_dark", {"on": QSettings("{{ORG}}", "{{APP_NAME}}").value("dark", False, bool)})
+
+    @pyqtSlot()
+    def load_latest_report(self):
+        self.send_to_js("report_data", {"rows": []})             # TODO: read the latest report rows
+
+    @pyqtSlot()
+    def download_report(self):
+        pass                                                     # TODO: export the report rows to .xlsx
 
     @pyqtSlot(bool)
     def set_dark(self, on):
-        QSettings("{{ORG}}", "{{APP_NAME}}").setValue("dark", on)
+        settings().setValue("dark", on)
 
     @pyqtSlot()
     def start_automation(self):
+        if self._one_run.acquire(blocking=False):                # a second click can't start a second bot
             threading.Thread(target=self._run, daemon=True).start()
 
     def _run(self):
-        self.send_to_js("status", {"state": "running", "msg": "Running…"})
+        try:
-        p = subprocess.Popen(BOT_CMD, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True, bufsize=1)
+            bot_runner.run(self.send_to_js)
-        for raw in p.stdout:
+        finally:
-            self._on_line(raw.rstrip())
+            self._one_run.release()
-        ok = p.wait() == 0
-        self.send_to_js("status", {"state": "done" if ok else "error", "msg": "Completed" if ok else "Failed"})
-
-    def _on_line(self, line):
-        # ponytail: raw line only printed here; persist to file/DB if audit is needed
-        low, kind = line.lower(), classify(line)
-        for marker, idx, pct in STEP_MARKERS:
-            if marker in low:
-                self.send_to_js("step", {"label": STEPS[idx], "pct": pct})
-                break
-        for marker, msg, t in FRIENDLY_RULES:
-            if marker in low:
-                if msg:
-                    self.send_to_js("log", {"msg": msg, "type": t})
-                return
-        if kind == "error":                                       # never hide a real failure
-            self.send_to_js("log", {"msg": line, "type": "error"})
 
 
 if __name__ == "__main__":

rpa-dashboard-no-ai/templates/contract.md

@@ -2,6 +2,7 @@
 
 All updates use one envelope: `{"event": "<name>", "data": {...}}`.
 - **Desktop (PyQt):** Python calls `window.__pyMsg(json)` via `runJavaScript` (see `bridge.py`).
+  `bot_runner.py` turns the bot's output lines into `status`, `step` and `log` events, and keeps every raw line in `bot_raw.log`.
 - **Web:** the page polls `GET {API_BASE}/dashboard` (returns `dashboard_data`) and
   `GET {API_BASE}/run/status` → `{"running": bool, "events": [envelope, ...]}`. Poll fast (2s) only while running.
 - **No bot yet:** with `SAMPLE_DATA = true`, the page answers its own data actions with sample envelopes.

rpa-dashboard-no-ai/templates/detect_frontend.py

@@ -0,0 +1,134 @@
+"""Find an existing frontend in a project: where it is, its stack and its colour tokens.
+
+Usage:  python detect_frontend.py [project dir]
+
+Prints "No existing frontend found.", or one "Frontend found at ..." line per
+frontend followed by its token blocks (file, selector, tokens). The keep and
+restyle steps in frontend.md work from those blocks.
+"""
+import json
+import os
+import re
+import sys
+from pathlib import Path
+
+# Not the project's own frontend: dependencies, build output, coverage, docs. Dot folders
+# (.git, .venv, .claude with the installed skills) are skipped too.
+SKIP = {"node_modules", "venv", "env", "site-packages", "__pycache__", "dist", "build", "out",
+        "coverage", "htmlcov", "docs"}
+PAGE = {".html", ".htm"}
+STYLE = {".css", ".scss", ".sass", ".less"}
+MARKUP = PAGE | {".vue", ".svelte"}  # files whose <style> tags hold CSS
+# A colour value: hex, a colour function, or a bare HSL triplet (shadcn/ui style "222 47% 11%").
+COLOUR = re.compile(r"#[0-9a-f]{3,8}\b|\b(rgba?|hsla?|oklch|oklab|lab|lch|color-mix)\(|^[\d.]+(deg)?\s+[\d.]+%\s+[\d.]+%", re.IGNORECASE)
+BRAND = re.compile(r"primary|brand|accent", re.IGNORECASE)
+FONT_TOKEN = re.compile(r"font(?!.*(size|weight|height))", re.IGNORECASE)
+FRAMEWORKS = [("@angular/core", "Angular"), ("vue", "Vue"), ("svelte", "Svelte"), ("react", "React")]
+TOOLS = [("next", "Next.js"), ("nuxt", "Nuxt"), ("vite", "Vite"), ("tailwindcss", "Tailwind")]
+
+
+def walk(root):
+    for d, dirs, names in os.walk(root):
+        dirs[:] = sorted(x for x in dirs if x not in SKIP and not x.startswith("."))
+        for n in sorted(names):
+            yield Path(d, n)
+
+
+def css_of(path):
+    text = path.read_text(encoding="utf-8", errors="replace")
+    if path.suffix.lower() in STYLE:
+        return text
+    return "\n".join(re.findall(r"<style[^>]*>(.*?)</style>", text, re.DOTALL | re.IGNORECASE))
+
+
+def token_blocks(css):
+    """[(selector path, {token: value})] for each innermost rule that declares custom properties."""
+    css = re.sub(r"/\*.*?\*/", "", css, flags=re.DOTALL)
+    out, stack, last = [], [], 0
+    for m in re.finditer(r"[{}]", css):
+        if m[0] == "{":
+            if stack:
+                stack[-1][2] = True  # has a nested rule
+            stack.append([css[last:m.start()].split(";")[-1].strip(), m.end(), False])
+        elif stack:
+            sel, start, nested = stack.pop()
+            # ponytail: declarations next to a nested rule (CSS nesting) are skipped; token blocks rarely nest
+            tokens = {} if nested else {k: v.strip() for k, v in re.findall(r"(--[\w-]+)\s*:\s*([^;]+)", css[start:m.start()])}
+            if tokens:
+                out.append((" ".join([s for s, *_ in stack] + [sel]), tokens))
+        last = m.end()
+    return out
+
+
+def rel(root, p):
+    r = p.relative_to(root).as_posix()
+    return "./" if r == "." else r + "/" if (root / r).is_dir() else r
+
+
+def tailwind_colours(path):
+    """Quoted hex colours in a Tailwind v3 config, by key."""
+    # ponytail: regex, not a JS parser; nested shades keep only their own key (e.g. "500")
+    return dict(re.findall(r"""['"]?([\w-]+)['"]?\s*:\s*['"](#[0-9a-fA-F]{3,8})['"]""", path.read_text(encoding="utf-8")))
+
+
+def styled(p):
+    return p.suffix.lower() in MARKUP | STYLE or p.name.startswith("tailwind.config.")
+
+
+def frontend(root, path, stack, files):
+    """files: the frontend's style-bearing files (see styled) plus any PyQt host."""
+    blocks = []
+    for f in files:
+        found = [("theme", tailwind_colours(f))] if f.name.startswith("tailwind.config.") else token_blocks(css_of(f))
+        blocks += [{"file": rel(root, f), "selector": sel, "dark": "dark" in sel.lower(), "tokens": t} for sel, t in found if t]
+    return {"path": rel(root, path), "stack": stack, "blocks": blocks}
+
+
+def detect(root):
+    root = Path(root).resolve()
+    files = list(walk(root))
+    found = []
+    for p in files:
+        if p.name != "package.json":
+            continue
+        try:
+            pkg = json.loads(p.read_text(encoding="utf-8"))
+        except ValueError:
+            continue
+        deps = {**pkg.get("dependencies", {}), **pkg.get("devDependencies", {})}
+        name = next((n for k, n in FRAMEWORKS if k in deps), None)
+        if name:
+            stack = f"{name} ({', '.join([n for k, n in TOOLS if k in deps] + ['web'])})"
+            found.append(frontend(root, p.parent, stack, [f for f in files if p.parent in f.parents and styled(f)]))
+    apps = [root / f["path"] for f in found]
+    rest = [p for p in files if not any(a in p.parents for a in apps)]
+    pages = [p for p in rest if p.suffix.lower() in PAGE]
+    hosts = [p for p in rest if p.suffix == ".py" and "QWebEngineView" in p.read_text(encoding="utf-8", errors="replace")]
+    if pages or hosts:
+        styles = [p for p in rest if styled(p) and p not in pages]
+        # ponytail: one plain-HTML/PyQt frontend per project, at the common folder of its pages and styles
+        home = Path(os.path.commonpath([p.parent for p in pages + styles])) if pages else hosts[0]
+        stack = f"PyQt web view (desktop, host `{rel(root, hosts[0])}`)" if hosts else "plain HTML (web)"
+        found.append(frontend(root, home, stack, pages + styles + hosts))
+    return found
+
+
+def report(found):
+    if not found:
+        return "No existing frontend found."
+    lines = []
+    for f in found:
+        light = [b["tokens"] for b in f["blocks"] if not b["dark"]]
+        colours = sorted(((k, v) for t in light for k, v in t.items() if COLOUR.search(v)), key=lambda kv: not BRAND.search(kv[0]))
+        fonts = [v for t in light for k, v in t.items() if FONT_TOKEN.search(k)]
+        shown = ", ".join(f"{k} {v}" for k, v in colours[:6]) + (f" (+{len(colours) - 6} more)" if len(colours) > 6 else "")
+        lines.append(f"Frontend found at `{f['path']}`, stack `{f['stack']}`, colours `{shown or 'none found'}`"
+                     + (f", fonts `{fonts[0]}`" if fonts else "") + ".")
+        for b in f["blocks"]:
+            lines.append(f"  {b['file']}  {b['selector']}{'  (dark)' if b['dark'] else ''}")
+            lines.append("    " + "; ".join(f"{k}:{v}" for k, v in b["tokens"].items()))
+    return "\n".join(lines)
+
+
+if __name__ == "__main__":
+    print(report(detect(sys.argv[1] if len(sys.argv) > 1 else ".")))

rpa-dashboard-no-ai/templates/frontend.md

@@ -0,0 +1,114 @@
+# Existing frontend: detect, report, keep or restyle
+
+Shared by `rpa-dashboard-no-ai` and `rpa-dashboard-ai`. The files named here sit
+next to this one, in `rpa-dashboard-no-ai/templates/`. From the AI skill, reach them
+through `../rpa-dashboard-no-ai/templates/`.
+
+## 1. Detect
+
+Run this before asking anything:
+
+```
+python <rpa-dashboard-no-ai>/templates/detect_frontend.py <project root>
+```
+
+It finds:
+- React, Vue, Angular and Svelte apps (a `package.json` that lists one);
+- a PyQt `QWebEngineView` host and the pages it shows;
+- plain HTML pages and their stylesheets.
+
+It skips `node_modules`, virtualenvs, dot folders (including `.claude`), build
+output, coverage and `docs`. For each frontend it prints:
+- one line: location, stack (with `web` or `desktop`), main colours and font;
+- then every token block: the file, the selector (dark blocks are marked) and
+  the tokens.
+
+Tokens come from:
+- CSS custom properties, including Tailwind v4 `@theme`;
+- `<style>` tags in pages, components and PyQt hosts;
+- the colours in a Tailwind v3 config.
+
+It doesn't read theme objects in JS/TS (MUI, styled-components). If it prints
+`colours none found`, look for one of those, or for colours hard-coded in rules,
+before you report.
+
+## 2. Report, then ask keep or restyle
+
+- **No frontend:** say "No existing frontend found." Don't ask keep or restyle.
+- **Frontend found:** say the script's first line: "Frontend found at `<path>`,
+  stack `<stack>`, colours `<main tokens>`." If it found more than one, report
+  each and ask which one the dashboard joins.
+- Then ask one question: **keep its look, or restyle it?** Don't name presets in
+  this question. Colours are asked next, and only for restyle.
+- Never ask desktop or web. The stack comes from the report: `web` means the
+  web path, `desktop` means the PyQt path.
+- **No token blocks** (every colour is hard-coded): say so. A restyle can't be
+  token-only then, so recommend keep, or ask before you pull the colours into a
+  new token block.
+
+## 3. Where the page goes
+
+| Stack | Put the page |
+|---|---|
+| plain HTML | Next to the existing pages, for example `web/dashboard.html`. |
+| React, Vue, Angular, Svelte | In the app's `public/` folder (`public/dashboard.html`), so it is served as-is. Port it into the app's components only if the user asks: best effort, with the page as reference. |
+| PyQt web view | Next to the host's page. Use the desktop path (`bridge.py`). |
+
+Don't edit existing pages to link to it. Tell the user the path to link from
+their nav.
+
+## 4. Keep
+
+The new page uses the project's look. **No existing file changes.** Skip the colour
+question.
+
+- Fill the page's `body{}` block from the project's light tokens, and `body.dark{}`
+  from its dark tokens. Copy the **values**, not `var(--…)` references: the page
+  turns dark mode on with `body.dark`, which the project's own dark selector
+  doesn't match. Above each block, note where the values came from, for example
+  `/* kept from web/css/theme.css */`.
+- Map each page token to the project token with the same role:
+
+  | Page token | Project token for |
+  |---|---|
+  | `--accent`, `--accent-2` | the primary/brand colour, and its lighter or hover shade |
+  | `--accent-dark` | the darkest brand shade (the log box background) |
+  | `--accent-soft`, `--accent-soft-2` | the brand tint (secondary buttons) and its border |
+  | `--bg-top`, `--bg-mid`, `--bg-bottom` | the page background; use the same value three times for a flat page |
+  | `--glass`, `--glass-strong` | the card surface, and the raised or alternate surface |
+  | `--border`, `--ink`, `--muted` | the border, the text and the muted text |
+  | `--ok`, `--warn`, `--bad` and their `-bg` | success, warning and danger; keep the template's values if the project has none |
+  | `--font`, `--font-display` | the body font and the heading font |
+  | `--header-*`, `--primary-bg`, `--nav-active-bg`, `--progress-bg` | wherever the project shows its brand. A solid brand top bar, for example, is `--header-bg:<brand>; --header-ink:#ffffff`. |
+  | `--blur` | `none`, unless the project uses frosted glass |
+
+- **No match:** run `palette.py` on the brand colour to get the accent family.
+  Keep the Tebra Sky value for anything else.
+- **No dark tokens:** put `palette.py`'s dark accents on the Tebra Sky dark block.
+- **Web fonts:** if the project loads its font with a `<link>` or `@import`, add
+  the same line to the page's `<head>`.
+
+## 5. Restyle
+
+The existing files change **only inside their token blocks**.
+
+1. Ask for colours (the skill's colour step): Tebra Sky, Superbill Ember or a
+   custom hex.
+2. Edit only the token lines that the detect report listed. Give each project
+   token the chosen palette's value for its role (read the keep table from right
+   to left):
+   - the light block gets values from the palette's `body{}` block;
+   - the dark block gets values from its `body.dark{}` block.
+
+   Keep every token name, and keep any token the palette has no match for. Don't
+   add blocks the project doesn't have.
+3. **Fonts:** change only the font tokens. If the new font needs loading (Ember),
+   add its `<link>` next to the project's other stylesheet links. That is the
+   only other line that may change.
+4. Leave hard-coded colours outside the token blocks alone, and list them for
+   the user.
+5. Build the new page with the palette's blocks from `themes.md`, the same way as
+   when there is no frontend.
+6. Show the user the diff of the existing files: `git diff` in a repo, otherwise
+   each changed line. It must show only token lines, plus the font link if one
+   was added.

tests/README.md

@@ -15,6 +15,11 @@ uv run --with pytest --with playwright pytest tests
     generated page instead, set `PAGE_CHECK_HTML=path/to/dashboard.html`.
   - The page sees a fake Qt bridge. Every action the page sends is recorded in
     `window.__calls` as `[slot, ...args]`.
+  - `PAGE_CHECK_WIRED=1`: the page is wired to a bot (sample data off). Sample-data
+    cases skip, and a case checks that the page's actions go to the bot. With no
+    `PAGE_CHECK_HTML`, the template is checked with `SAMPLE_DATA` switched off.
+  - `PAGE_CHECK_REPLAY=run.jsonl`: replay a real bot run (the JSON lines that
+    `python dashboard/bot_runner.py` prints) instead of the built-in run.
   - To add a case, write a `test_*.py` file in `page_check/` that uses the `page`
     and `push(event, data)` fixtures from `conftest.py`.
   - Optional-section cases (`test_optional_sections.py`) skip on a generated page
@@ -30,5 +35,10 @@ uv run --with pytest --with playwright pytest tests
   ```
 
   Results go to `evals/results/<fixture>.json`. To add a fixture, add an entry to
-  `FIXTURES` in `run_eval.py`.
+  `FIXTURES` in `run_eval.py`. An entry with a `"fixture"` key reuses another
+  fixture folder with different answers: `c-keep` and `c-restyle` both run on
+  `c-web-existing-frontend`, and also check what changed in the files it already had.
+  For a bot fixture (`b-pyqt-bot`), the eval also dry-runs the generated
+  `bot_runner.py`, saves its events to `evals/results/<fixture>.run.jsonl`, and
+  replays them in the page check.
 - `fixtures/<letter>-<name>/`: small test projects for the evals.

tests/evals/results/b-pyqt-bot.dashboard.html

@@ -0,0 +1,287 @@
+<!DOCTYPE html>
+<!--
+  Generic RPA dashboard (no AI). Derived from Tebra ERA (reference/tebra_dashboard.html).
+  One file: works inside PyQt6 QWebEngineView (QWebChannel bridge) OR served by any web
+  backend (falls back to polling GET /dashboard and /run/status).
+-->
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Work-item follow-up bot</title>
+<script src="qrc:///qtwebchannel/qwebchannel.js"></script>
+<style>
+/* ===== THEME TOKENS (swap these for a preset/custom palette, see themes.md) ===== */
+body{
+  --bg-top:#8fc9e8; --bg-mid:#bfe3f2; --bg-bottom:#eaf6fb;
+  --glass:rgba(255,255,255,.60); --glass-strong:rgba(255,255,255,.78); --border:rgba(255,255,255,.9);
+  --ink:#1c2b33; --muted:#5c7382; --accent-dark:#16202a;
+  --accent:#3d9bd0; --accent-2:#5cb2e2; --accent-soft:#d4edfa; --accent-soft-2:#a9d8ee;
+  --ok:#1f9d57; --ok-bg:#e6f6ec; --warn:#b7791f; --warn-bg:#fbf1dd; --bad:#c0392b; --bad-bg:#fdecea;
+  --font:'Segoe UI',-apple-system,BlinkMacSystemFont,sans-serif; --font-display:var(--font);
+  --header-bg:var(--glass-strong); --header-ink:var(--ink); --header-muted:var(--muted);
+  --primary-bg:linear-gradient(180deg,var(--accent-2),var(--accent));
+  --nav-active-bg:linear-gradient(135deg,var(--accent),var(--accent-dark));
+  --progress-bg:var(--ok); --blur:blur(14px);
+}
+body.dark{
+  --bg-top:#0f1b26; --bg-mid:#13212e; --bg-bottom:#182a38;
+  --glass:rgba(22,34,44,.72); --glass-strong:rgba(30,45,58,.85); --border:rgba(120,160,190,.22);
+  --ink:#e6eef4; --muted:#8fa6b4; --accent-dark:#2e5d80;
+  --accent-soft:#2e5d90; --accent-soft-2:#1d3d5e;
+  --ok:#2fbf72; --ok-bg:rgba(31,157,87,.16); --warn:#d9a13c; --warn-bg:rgba(183,121,31,.16);
+  --bad:#e05a4b; --bad-bg:rgba(192,57,43,.16);
+}
+/* ===== BASE ===== */
+*{box-sizing:border-box;margin:0;padding:0}
+html,body{height:100%;overflow:hidden}
+body{font-family:var(--font);color:var(--ink);
+  background:linear-gradient(180deg,var(--bg-top) 0%,var(--bg-mid) 45%,var(--bg-bottom) 100%)}
+.app{display:flex;height:100vh}
+.hidden{display:none!important}
+/* sidebar */
+.sidebar{width:230px;min-width:230px;background:var(--glass);border-right:1px solid var(--border);backdrop-filter:var(--blur);display:flex;flex-direction:column}
+.logo-area{padding:22px 20px;display:flex;align-items:center;gap:11px;border-bottom:1px solid var(--border)}
+.logo-box{width:40px;height:40px;border-radius:12px;background:var(--glass-strong);display:flex;align-items:center;justify-content:center;border:1px solid var(--border)}
+.logo-box img{width:28px;height:28px;object-fit:contain}
+.logo-title{font-size:15px;font-weight:700}
+.logo-sub{font-size:10px;color:var(--muted);margin-top:2px;letter-spacing:.5px;text-transform:uppercase;font-weight:600}
+.nav{padding:16px 12px;flex:1}
+.nav-item{border:0;background:none;width:100%;font:inherit;text-align:left;display:flex;align-items:center;gap:11px;padding:11px 13px;border-radius:10px;cursor:pointer;margin-bottom:3px;color:var(--muted);font-size:13.5px;font-weight:600;transition:all .15s;user-select:none}
+.nav-item svg{width:18px;height:18px;stroke:currentColor;fill:none;stroke-width:2}
+.nav-item:hover{background:var(--glass-strong);color:var(--ink)}
+.nav-item.active{background:var(--nav-active-bg);color:#fff;box-shadow:0 4px 12px rgba(20,50,70,.22)}
+.sidebar-foot{padding:14px;border-top:1px solid var(--border);display:flex;align-items:center;gap:10px}
+.avatar{width:34px;height:34px;border-radius:50%;background:var(--nav-active-bg);display:flex;align-items:center;justify-content:center;font-size:12px;font-weight:700;color:#fff}
+.u-name{font-size:13px;font-weight:700}.u-role{font-size:10.5px;color:var(--muted)}
+/* main + topbar */
+.main{flex:1;display:flex;flex-direction:column;overflow:hidden}
+.topbar{background:var(--header-bg);color:var(--header-ink);border-bottom:1px solid var(--border);backdrop-filter:var(--blur);padding:20px 28px;display:flex;align-items:center;gap:14px;box-shadow:0 6px 18px rgba(20,50,70,.10)}
+.tb-title{font-size:21px;font-weight:800}.tb-sub{font-size:12.5px;color:var(--header-muted);margin-top:3px}
+.tb-right{margin-left:auto;display:flex;align-items:center;gap:12px}
+.indicator{color:var(--ink);display:flex;align-items:center;gap:7px;background:var(--glass-strong);padding:7px 13px;border-radius:20px;border:1px solid var(--border);font-size:12px;font-weight:700}
+.dot{width:8px;height:8px;border-radius:50%}
+.dot.ready,.dot.done{background:var(--ok);box-shadow:0 0 7px var(--ok)}
+.dot.running{background:var(--warn);box-shadow:0 0 7px var(--warn);animation:blink 1.2s infinite}
+.dot.error{background:var(--bad);box-shadow:0 0 7px var(--bad)}
+@keyframes blink{50%{opacity:.4}}
+.mode-btn{color:var(--ink);width:38px;height:38px;border-radius:11px;border:1px solid var(--border);background:var(--glass-strong);cursor:pointer;font-size:16px}
+.content{flex:1;overflow-y:auto;padding:26px 28px;border-top-left-radius:30px}
+/* cards, buttons, pills */
+.section-label{font-size:11px;text-transform:uppercase;letter-spacing:1px;color:var(--muted);font-weight:700;margin-bottom:14px}
+.card{background:var(--glass);border:1px solid var(--border);border-radius:16px;padding:22px;margin-bottom:16px;backdrop-filter:var(--blur);box-shadow:0 10px 30px rgba(20,50,70,.08)}
+.c-title{font-size:15px;font-weight:700;margin-bottom:14px}
+.btn{padding:9px 15px;border-radius:11px;border:1px solid var(--accent-soft-2);background:linear-gradient(180deg,var(--accent-soft),var(--accent-soft-2));color:var(--ink);font-size:12.5px;font-weight:600;cursor:pointer;transition:all .18s}
+.btn:hover{transform:translateY(-1px);box-shadow:0 4px 12px rgba(20,50,70,.2)}
+.btn.primary{background:var(--primary-bg);color:#fff;border-color:var(--accent)}
+.btn:disabled{opacity:.45;cursor:not-allowed;transform:none;box-shadow:none}
+.pill{display:inline-block;padding:4px 11px;border-radius:20px;font-size:11px;font-weight:700;color:#fff}
+.pill.success{background:var(--ok)}.pill.attention{background:var(--warn)}.pill.failed{background:var(--bad)}.pill.cleared{background:var(--muted)}
+ul,ol{list-style:none}
+.logo-title,.tb-title,.c-title,.kpi-val,.dh-num,.btn{font-family:var(--font-display)}
+/* KPI */
+.kpi-row{display:grid;grid-template-columns:repeat(4,1fr);gap:14px;margin-bottom:16px}
+.kpi{display:flex;align-items:center;gap:13px;padding:16px 18px;border-radius:16px;background:var(--glass-strong);border:1px solid var(--border);box-shadow:0 4px 14px rgba(20,50,70,.10)}
+.kpi-ic{width:42px;height:42px;border-radius:12px;position:relative}
+.kpi.total .kpi-ic{background:var(--accent)}
+.kpi.done .kpi-ic{background:var(--ok)}.kpi.prog .kpi-ic{background:var(--warn)}.kpi.notdone .kpi-ic{background:var(--bad)}
+.kpi.prog.live .kpi-ic::after{content:'';position:absolute;inset:-3px;border-radius:14px;border:2px solid var(--warn);animation:kpulse 1.6s ease-out infinite}
+@keyframes kpulse{0%{transform:scale(.9);opacity:.6}100%{transform:scale(1.25);opacity:0}}
+.kpi-val{font-size:26px;font-weight:800;line-height:1.1;font-variant-numeric:tabular-nums}
+.kpi-lbl{font-size:11.5px;color:var(--muted);font-weight:600;margin-top:2px}
+/* donut */
+.dash-grid{display:grid;grid-template-columns:1fr 1fr;gap:14px}
+.donut-wrap{display:flex;align-items:center;gap:26px;flex-wrap:wrap}
+.donut{width:150px;height:150px;border-radius:50%;position:relative;background:conic-gradient(var(--border) 0 100%)}
+.donut-hole{position:absolute;inset:22px;border-radius:50%;background:var(--bg-bottom);display:flex;flex-direction:column;align-items:center;justify-content:center}
+.dh-num{font-size:26px;font-weight:800}.dh-lbl{font-size:10px;color:var(--muted);font-weight:700;text-transform:uppercase}
+.dl-row{display:flex;align-items:center;gap:9px;font-size:12.5px;font-weight:600;margin-bottom:9px}
+.dl-dot{width:10px;height:10px;border-radius:3px}
+/* run panel */
+.prog-head{display:flex;gap:12px;margin-bottom:8px;font-size:13px;font-weight:700}
+.prog-head .pct{margin-left:auto;color:var(--accent)}
+.prog-bg{height:8px;background:var(--glass-strong);border-radius:8px;overflow:hidden;margin-bottom:18px}
+.prog-fill{height:100%;width:0;background:var(--progress-bg);transition:width .5s}
+.step{display:flex;align-items:center;gap:12px;padding:10px 13px;border-radius:10px;margin-bottom:6px;font-size:13px;font-weight:600}
+.step.done{background:var(--ok-bg);color:var(--ok)}.step.active{background:var(--warn-bg);color:var(--warn)}.step.pending{opacity:.5}
+.step-dot{width:22px;height:22px;border-radius:50%;display:flex;align-items:center;justify-content:center;font-size:11px;background:var(--glass-strong)}
+.step.done .step-dot{background:var(--ok);color:#fff}.step.active .step-dot{background:var(--warn);color:#fff}
+.log{background:var(--accent-dark);border-radius:12px;padding:12px 14px;max-height:220px;overflow-y:auto;font-family:Consolas,'Courier New',monospace;font-size:13px;line-height:1.85;color:#9fb6c4}
+.log .info{color:#7fc4f0}.log .success{color:#5fe0a0}.log .warn{color:#f5c563}.log .error{color:#f68c82}
+/* report table */
+.toolbar{display:flex;gap:10px;align-items:center;margin-bottom:14px;flex-wrap:wrap}
+.toolbar input{padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:var(--glass-strong);color:var(--ink);font:inherit;font-size:12.5px}
+.tbl-wrap{border:1px solid var(--border);border-radius:14px;overflow:auto;max-height:60vh;background:var(--glass)}
+table{border-collapse:collapse;width:100%;font-size:12px;white-space:nowrap}
+th{background:var(--glass-strong);text-align:left;padding:11px 14px;position:sticky;top:0;font-weight:700}
+td{padding:10px 14px;border-bottom:1px solid var(--border)}
+.empty{text-align:center;padding:40px;color:var(--muted);font-size:13px}
+@media (max-width:820px){.sidebar{width:66px;min-width:66px}.logo-title,.logo-sub,.nav-item span,.u-name,.u-role{display:none}.kpi-row{grid-template-columns:1fr 1fr}.dash-grid{grid-template-columns:1fr}}
+</style>
+</head>
+<body>
+<div class="app">
+  <aside class="sidebar">
+    <div class="logo-area">
+      <div class="logo-box"><img src="" alt="" onerror="this.remove()"></div>
+      <div><div class="logo-title">Work-item follow-up bot</div><div class="logo-sub">Portal work-item updates</div></div>
+    </div>
+    <nav class="nav">
+      <button class="nav-item active" data-tab="dashboard" title="Dashboard"><svg viewBox="0 0 24 24"><rect x="3" y="3" width="7" height="7"/><rect x="14" y="3" width="7" height="7"/><rect x="3" y="14" width="7" height="7"/><rect x="14" y="14" width="7" height="7"/></svg><span>Dashboard</span></button>
+      <button class="nav-item" data-tab="run" title="Run"><svg viewBox="0 0 24 24"><polygon points="6 4 20 12 6 20 6 4"/></svg><span>Run</span></button>
+      <button class="nav-item" data-tab="report" title="Report"><svg viewBox="0 0 24 24"><path d="M4 4h16v16H4z"/><path d="M8 9h8M8 13h8M8 17h5"/></svg><span>Report</span></button>
+    </nav>
+    <div class="sidebar-foot"><div class="avatar" id="avatar">U</div><div><div class="u-name" id="u-name">User</div><div class="u-role" id="u-role">Operator</div></div></div>
+  </aside>
+
+  <main class="main">
+    <header class="topbar">
+      <div><div class="tb-title" id="tb-title">Dashboard</div><div class="tb-sub" id="tb-sub">Overview of every batch</div></div>
+      <div class="tb-right">
+        <button class="btn primary" id="run-btn" onclick="startRun()">▶ Run</button>
+        <button class="mode-btn" id="mode-btn" title="Dark mode" aria-label="Dark mode" aria-pressed="false" onclick="toggleDark()">🌙</button>
+        <div class="indicator"><span class="dot ready" id="st-dot"></span><span id="st-text">System ready</span></div>
+      </div>
+    </header>
+
+    <section class="content">
+      <!-- DASHBOARD -->
+      <div id="tab-dashboard">
+        <div class="kpi-row">
+          <div class="kpi total" role="group" aria-label="Total batches"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-total">0</div><div class="kpi-lbl">Total batches</div></div></div>
+          <div class="kpi done" role="group" aria-label="Completed"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-done">0</div><div class="kpi-lbl">Completed</div></div></div>
+          <div class="kpi prog" id="kpi-prog" role="group" aria-label="In progress"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-prog">0</div><div class="kpi-lbl">In progress</div></div></div>
+          <div class="kpi notdone" role="group" aria-label="Not completed"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-fail">0</div><div class="kpi-lbl">Not completed</div></div></div>
+        </div>
+        <div class="dash-grid">
+          <div class="card"><div class="c-title">Batch status split</div>
+            <div class="donut-wrap"><div class="donut" id="donut" role="img" aria-label="Batch status: no batches yet"><div class="donut-hole"><div class="dh-num" id="dh-num">0</div><div class="dh-lbl">batches</div></div></div><ul id="legend" aria-label="Batch status"></ul></div>
+          </div>
+          <div class="card"><div class="c-title">Recent batches</div><div id="recent" class="empty">No batches yet</div></div>
+        </div>
+      </div>
+
+      <!-- RUN -->
+      <div id="tab-run" class="hidden">
+        <div class="card"><div class="c-title">Run automation</div>
+          <div class="prog-head"><span id="p-label">Waiting to start</span><span id="p-time"></span><span class="pct" id="p-pct">0%</span></div>
+          <div class="prog-bg"><div class="prog-fill" id="p-fill"></div></div>
+          <ol id="steps" aria-label="Steps"></ol>
+          <div class="log" id="log" role="log" aria-label="Run log"></div>
+        </div>
+      </div>
+
+      <!-- REPORT -->
+      <div id="tab-report" class="hidden">
+        <div class="card">
+          <div class="toolbar"><input id="r-search" type="search" aria-label="Search report" placeholder="Search…" oninput="renderReport()"><span style="margin-left:auto"></span><button class="btn primary" onclick="api('download_report')">⬇ Download Excel</button></div>
+          <div class="tbl-wrap"><table><thead id="r-head"></thead><tbody id="r-body"></tbody></table></div>
+        </div>
+      </div>
+    </section>
+  </main>
+</div>
+
+<script>
+// ===== CONFIG (fill per project) =====
+const STEPS = ["Initializing", "Login", "Process work items", "Write summary", "Completed"];            // e.g. ["Initializing","Login","Process items","Completed"]
+const REPORT_COLUMNS = [{"key": "item", "label": "Work item"}, {"key": "status", "label": "Status"}]; // e.g. [{key:"item",label:"Item"},{key:"status",label:"Status"}]
+const API_BASE = "";         // web mode only, e.g. "/api"
+const SAMPLE_DATA = false;               // wired to bot.py through bot_runner.py
+const TABS = {dashboard:["Dashboard","Overview of every batch"],run:["Run","Live progress and log"],report:["Report","Result of every processed item"]};
+
+// ===== TRANSPORT: sample data, else Qt bridge, else HTTP polling =====
+let bridge = null, reportRows = [];
+function api(slot, ...args){
+  if(SAMPLE_DATA && SAMPLE[slot]) return SAMPLE[slot](...args);
+  if(bridge) return bridge[slot](...args);
+  return fetch(`${API_BASE}/${slot.replace(/_/g,'-')}`,{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify(args)}).catch(()=>{});
+}
+window.__pyMsg = (json)=>{ const m=JSON.parse(json); handle(m.event,m.data); };
+function startTransport(){
+  if(window.qt && window.qt.webChannelTransport){
+    new QWebChannel(qt.webChannelTransport, ch=>{ bridge=ch.objects.pyBridge; api('load_dashboard'); });
+  }else if(SAMPLE_DATA){
+    api('load_dashboard');
+  }else{
+    const poll = async()=>{
+      try{
+        const d = await (await fetch(`${API_BASE}/dashboard`)).json(); handle('dashboard_data',d);
+        const s = await (await fetch(`${API_BASE}/run/status`)).json();
+        (s.events||[]).forEach(e=>handle(e.event,e.data));
+        setTimeout(poll, s.running ? 2000 : 10000);   // poll fast only while busy
+      }catch(e){ setTimeout(poll, 10000); }
+    };
+    poll();
+  }
+}
+
+// ===== EVENT DISPATCH (see contract.md) =====
+function handle(event, d){
+  switch(event){
+    case 'status': setStatus(d.state, d.msg); break;
+    case 'step': setStep(d.label, d.pct); break;
+    case 'log': addLog(d.msg, d.type); break;
+    case 'dashboard_data': renderDashboard(d.batches||[]); break;
+    case 'report_data': reportRows = d.rows||[]; renderReport(); break;
+    case 'set_user': setUser(d); break;
+    case 'apply_dark': setDark(!!d.on); break;
+  }
+}
+
+// ===== UI =====
+document.querySelectorAll('.nav-item').forEach(n=>n.onclick=()=>showTab(n.dataset.tab));
+function showTab(t){
+  document.querySelectorAll('.nav-item').forEach(n=>n.classList.toggle('active',n.dataset.tab===t));
+  Object.keys(TABS).forEach(k=>document.getElementById('tab-'+k).classList.toggle('hidden',k!==t));
+  tbTitle.textContent=TABS[t][0]; tbSub.textContent=TABS[t][1];
+  if(t==='dashboard') api('load_dashboard');
+  if(t==='report') api('load_latest_report');
+}
+const $=id=>document.getElementById(id), tbTitle=$('tb-title'), tbSub=$('tb-sub');
+function esc(s){return String(s??'').replace(/[&<>"]/g,c=>({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;'}[c]));}
+function setDark(on){ document.body.classList.toggle('dark',on); $('mode-btn').setAttribute('aria-pressed',on); $('mode-btn').textContent=on?'☀':'🌙'; }
+function toggleDark(){ const on=!document.body.classList.contains('dark'); setDark(on); api('set_dark',on); }
+function setUser(u){ $('u-name').textContent=u.username; $('u-role').textContent=u.role; $('avatar').textContent=(u.username||'U')[0].toUpperCase(); }
+function setStatus(state,msg){ $('st-dot').className='dot '+state; $('st-text').textContent=msg||state; $('run-btn').disabled=state==='running'; }
+function startRun(){ showTab('run'); $('log').innerHTML=''; setStep(STEPS[0],0); api('start_automation'); }
+
+function renderSteps(active=-1){
+  $('steps').innerHTML=STEPS.map((s,i)=>{const c=i<active?'done':i===active?'active':'pending';
+    return `<li class="step ${c}"${c==='active'?' aria-current="step"':''}><span class="step-dot">${c==='done'?'✓':i+1}</span>${esc(s)}</li>`}).join('');
+}
+function setStep(label,pct){ $('p-label').textContent=label; $('p-pct').textContent=pct+'%'; $('p-fill').style.width=pct+'%';
+  renderSteps(pct>=100?STEPS.length:STEPS.indexOf(label)); }
+function addLog(msg,type='info'){ const l=$('log'); l.insertAdjacentHTML('beforeend',`<div class="${type}">${esc(msg)}</div>`); l.scrollTop=l.scrollHeight; }
+
+function countUp(el,to){ const from=+el.textContent||0,t0=performance.now();
+  const f=t=>{const p=Math.min((t-t0)/500,1); el.textContent=Math.round(from+(to-from)*p); if(p<1)requestAnimationFrame(f)}; requestAnimationFrame(f); }
+// batch state -> [label, colour token, pill class]
+const STATES={completed:['Completed','var(--ok)','success'],inprogress:['In progress','var(--warn)','attention'],
+  notcompleted:['Not completed','var(--bad)','failed'],cleared:['Cleared','var(--muted)','cleared']};
+function renderDashboard(b){
+  const c={}; Object.keys(STATES).forEach(k=>c[k]=b.filter(x=>x.state===k).length);
+  countUp($('k-total'),b.length); countUp($('k-done'),c.completed); countUp($('k-prog'),c.inprogress); countUp($('k-fail'),c.notcompleted);
+  $('kpi-prog').classList.toggle('live',c.inprogress>0); $('dh-num').textContent=b.length;
+  const tot=Object.values(c).reduce((a,x)=>a+x,0); let acc=0; const stops=[];
+  Object.keys(c).forEach(k=>{ if(!c[k])return; const a=acc/tot*100; acc+=c[k]; stops.push(`${STATES[k][1]} ${a}% ${acc/tot*100}%`); });
+  $('donut').style.background = tot?`conic-gradient(${stops.join(',')})`:'conic-gradient(var(--border) 0 100%)';
+  $('donut').setAttribute('aria-label','Batch status: '+Object.keys(c).map(k=>`${STATES[k][0]} ${c[k]}`).join(', '));
+  $('legend').innerHTML=Object.keys(c).map(k=>`<li class="dl-row"><span class="dl-dot" style="background:${STATES[k][1]}"></span>${STATES[k][0]} · ${c[k]}</li>`).join('');
+  $('recent').className = b.length?'':'empty';
+  $('recent').innerHTML = b.length? b.slice(0,6).map(x=>{const s=STATES[x.state]||[esc(x.state),'','attention'];
+    return `<div class="dl-row">#${esc(x.batch_id)} · ${esc(x.date)} <span class="pill ${s[2]}" style="margin-left:auto">${s[0]}</span></div>`}).join('') : 'No batches yet';
+}
+function renderReport(){
+  const q=$('r-search').value.toLowerCase();
+  $('r-head').innerHTML='<tr>'+REPORT_COLUMNS.map(c=>`<th>${esc(c.label)}</th>`).join('')+'</tr>';
+  const rows=reportRows.filter(r=>!q||Object.values(r).join(' ').toLowerCase().includes(q));
+  $('r-body').innerHTML = rows.length? rows.map(r=>'<tr>'+REPORT_COLUMNS.map(c=>c.key==='status'
+      ?`<td><span class="pill ${esc(r.bucket||'attention')}">${esc(r.status)}</span></td>`:`<td>${esc(r[c.key])}</td>`).join('')+'</tr>').join('')
+    : `<tr><td class="empty" colspan="${REPORT_COLUMNS.length}">No rows yet</td></tr>`;
+}
+renderSteps();
+startTransport();
+</script>
+</body>
+</html>

tests/evals/results/b-pyqt-bot.json

@@ -0,0 +1,33 @@
+{
+  "fixture": "b-pyqt-bot",
+  "passed": true,
+  "checks": {
+    "frontend reported correctly": true,
+    "asks /colou?r/": true,
+    "asks /section/": true,
+    "never asks /\\bkeep\\b|restyle/": true,
+    "never asks /desktop|web/": true,
+    "exactly one page built": true,
+    "no placeholders left": true,
+    "page wired to the bot (sample data off)": true,
+    "bot_runner.py built": true,
+    "no placeholders left in the host": true,
+    "bot dry run ends done": true,
+    "real steps reach the page": true,
+    "bot error line reaches the log": true,
+    "page check passes": true
+  },
+  "page_check": [
+    "27 passed, 4 skipped in 13.24s"
+  ],
+  "files": [
+    "README.md",
+    "bot.py",
+    "dashboard\\bot_raw.log",
+    "dashboard\\bot_runner.py",
+    "dashboard\\bridge.py",
+    "dashboard\\dashboard.html",
+    "requirements.txt"
+  ],
+  "reply": "Dashboard ready aachu, PyQt bot-oda wire pannirukken. Ithu desktop app (PyQt6), local project mattum; cloud/deploy edhuvum illa. Neenga work pannumbothu answer panna mudiyaathu-nu sonneenga, adhaan 3-file change-ku \"go\" wait pannala.\n\n| Item | Result |\n|---|---|\n| Files | `dashboard/dashboard.html`, `dashboard/bridge.py`, `dashboard/bot_runner.py` |\n| Theme / extras | Tebra Sky / onnum illa (optional markers ellam remove pannitten) |\n| Data | Sample data illa. `bot_runner.py` `python -m bot`-a child process-aa run pannum |\n| Steps | Initializing \u2192 Login \u2192 Process work items \u2192 Write summary \u2192 Completed (bot-oda `[step 1-4]`, `[all done]` lines-la irundhu) |\n| Dry run | 5/5 steps order-la vandhuchu, 100%-la end aachu; `ERROR: could not attach\u2026` line `error` log-aa vandhuchu |\n| Qt host (offscreen) | Run click pannadhum button disable aachu, bot mudinjadhum enable; status \"Completed\", 100%; dark mode reopen pannappuram-um on-la irundhuchu |\n| Screenshots | Light, dark, 800px width: KPI, donut, steps, log, report pills ellam correct-aa render aachu; horizontal scroll illa; `{{` onnum meedhi illa |\n\nRun panna: `python dashboard/bridge.py`\n\nAlso noticed (fix pannala):\n- `load_dashboard` / `load_latest_report` empty list-dhaan anuppudhu, bot DB-yo report-o ezhudhala. Adhanaala live data-vula KPI-yum Report tab-um empty-aa irukkum. Test pannumbothu sample rows inject panni dhaan check panninen.\n- `bot.py` `ERROR` print pannaalum exit code 0-dhaan, so status \"Completed\"-nu dhaan kaattum.\n- \"Work item updated.\" log line-la WI number varaadhu; raw line `dashboard/bot_raw.log`-la save aagum.\n- Browser-la file-aa direct-aa open panna fetch errors varum, aana Qt-kulla avai varaadhu.\n\nFRONTEND: none\nQUESTIONS: Which colours: Tebra Sky, Superbill Ember, or Custom (one brand hex)? | Which optional sections to build: checkpoint tracker, admin/roles screen, login page, or none?"
+}

tests/evals/results/b-pyqt-bot.run.jsonl

@@ -0,0 +1,19 @@
+{"event": "status", "data": {"state": "running", "msg": "Running\u2026"}}
+{"event": "step", "data": {"label": "Initializing", "pct": 10}}
+{"event": "log", "data": {"msg": "Starting up.", "type": "info"}}
+{"event": "log", "data": {"msg": "Work items loaded.", "type": "info"}}
+{"event": "step", "data": {"label": "Login", "pct": 30}}
+{"event": "log", "data": {"msg": "Logging in to the portal.", "type": "info"}}
+{"event": "log", "data": {"msg": "Logged in.", "type": "success"}}
+{"event": "step", "data": {"label": "Process work items", "pct": 50}}
+{"event": "log", "data": {"msg": "Processing work items.", "type": "info"}}
+{"event": "log", "data": {"msg": "Work item updated.", "type": "success"}}
+{"event": "log", "data": {"msg": "Work item updated.", "type": "success"}}
+{"event": "log", "data": {"msg": "Work item updated.", "type": "success"}}
+{"event": "log", "data": {"msg": "The portal is slow to respond.", "type": "warn"}}
+{"event": "log", "data": {"msg": "ERROR: could not attach the note to WI-1003", "type": "error"}}
+{"event": "step", "data": {"label": "Write summary", "pct": 85}}
+{"event": "log", "data": {"msg": "Writing the summary.", "type": "info"}}
+{"event": "step", "data": {"label": "Completed", "pct": 100}}
+{"event": "log", "data": {"msg": "All work items processed.", "type": "success"}}
+{"event": "status", "data": {"state": "done", "msg": "Completed"}}

tests/evals/results/c-keep.dashboard.html

@@ -0,0 +1,312 @@
+<!DOCTYPE html>
+<!--
+  Generic RPA dashboard (no AI). Derived from Tebra ERA (reference/tebra_dashboard.html).
+  One file: works inside PyQt6 QWebEngineView (QWebChannel bridge) OR served by any web
+  backend (falls back to polling GET /api/dashboard and /run/status).
+  Theme = the body / body.dark token blocks only (see themes.md).
+-->
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Field Ops Portal</title>
+<script src="qrc:///qtwebchannel/qwebchannel.js"></script>
+<style>
+/* ===== THEME TOKENS ===== */
+/* kept from web/css/theme.css :root (accent-2, accent-dark, accent-soft-2 from palette.py "#0f766e": no project match) */
+body{
+  --bg-top:#f8fafc; --bg-mid:#f8fafc; --bg-bottom:#f8fafc;
+  --glass:#ffffff; --glass-strong:#f1f5f9; --border:#e2e8f0;
+  --ink:#0f172a; --muted:#64748b; --accent-dark:#041e1c;
+  --accent:#0f766e; --accent-2:#338b84; --accent-soft:#ccfbf1; --accent-soft-2:#a4cbc8;
+  --ok:#15803d; --ok-bg:#e6f6ec; --warn:#b45309; --warn-bg:#fbf1dd; --bad:#b91c1c; --bad-bg:#fdecea;
+  --font:"Trebuchet MS","Segoe UI",sans-serif; --font-display:Georgia,"Times New Roman",serif;
+  --header-bg:#0f766e; --header-ink:#ffffff; --header-muted:#ccfbf1;
+  --primary-bg:#115e59;
+  --nav-active-bg:#0f766e;
+  --progress-bg:var(--ok); --blur:none;
+}
+/* kept from web/css/theme.css [data-theme="dark"] (accent-2, accent-dark, accent-soft-2 from palette.py) */
+body.dark{
+  --bg-top:#0b1120; --bg-mid:#0b1120; --bg-bottom:#0b1120;
+  --glass:#111827; --glass-strong:#1f2937; --border:#334155;
+  --ink:#e2e8f0; --muted:#94a3b8; --accent-dark:#104541;
+  --accent:#0d9488; --accent-2:#348b85; --accent-soft:#134e4a; --accent-soft-2:#0c3230;
+  --ok:#22c55e; --ok-bg:rgba(31,157,87,.16); --warn:#f59e0b; --warn-bg:rgba(183,121,31,.16);
+  --bad:#ef4444; --bad-bg:rgba(192,57,43,.16);
+  --header-bg:#0d9488; --header-muted:#ccfbf1;
+  --primary-bg:#134e4a; --nav-active-bg:#0d9488;
+}
+/* ===== BASE ===== */
+*{box-sizing:border-box;margin:0;padding:0}
+html,body{height:100%;overflow:hidden}
+body{font-family:var(--font);color:var(--ink);
+  background:linear-gradient(180deg,var(--bg-top) 0%,var(--bg-mid) 45%,var(--bg-bottom) 100%)}
+.app{display:flex;height:100vh}
+.hidden{display:none!important}
+/* sidebar */
+.sidebar{width:230px;min-width:230px;background:var(--glass);border-right:1px solid var(--border);backdrop-filter:var(--blur);display:flex;flex-direction:column}
+.logo-area{padding:22px 20px;display:flex;align-items:center;gap:11px;border-bottom:1px solid var(--border)}
+.logo-box{width:40px;height:40px;border-radius:12px;background:var(--glass-strong);display:flex;align-items:center;justify-content:center;border:1px solid var(--border)}
+.logo-box img{width:28px;height:28px;object-fit:contain}
+.logo-title{font-size:15px;font-weight:700}
+.logo-sub{font-size:10px;color:var(--muted);margin-top:2px;letter-spacing:.5px;text-transform:uppercase;font-weight:600}
+.nav{padding:16px 12px;flex:1}
+.nav-item{border:0;background:none;width:100%;font:inherit;text-align:left;display:flex;align-items:center;gap:11px;padding:11px 13px;border-radius:10px;cursor:pointer;margin-bottom:3px;color:var(--muted);font-size:13.5px;font-weight:600;transition:all .15s;user-select:none}
+.nav-item svg{width:18px;height:18px;stroke:currentColor;fill:none;stroke-width:2}
+.nav-item:hover{background:var(--glass-strong);color:var(--ink)}
+.nav-item.active{background:var(--nav-active-bg);color:#fff;box-shadow:0 4px 12px rgba(20,50,70,.22)}
+.sidebar-foot{padding:14px;border-top:1px solid var(--border);display:flex;align-items:center;gap:10px}
+.avatar{width:34px;height:34px;border-radius:50%;background:var(--nav-active-bg);display:flex;align-items:center;justify-content:center;font-size:12px;font-weight:700;color:#fff}
+.u-name{font-size:13px;font-weight:700}.u-role{font-size:10.5px;color:var(--muted)}
+/* main + topbar */
+.main{flex:1;display:flex;flex-direction:column;overflow:hidden}
+.topbar{background:var(--header-bg);color:var(--header-ink);border-bottom:1px solid var(--border);backdrop-filter:var(--blur);padding:20px 28px;display:flex;align-items:center;gap:14px;box-shadow:0 6px 18px rgba(20,50,70,.10)}
+.tb-title{font-size:21px;font-weight:800}.tb-sub{font-size:12.5px;color:var(--header-muted);margin-top:3px}
+.tb-right{margin-left:auto;display:flex;align-items:center;gap:12px}
+.indicator{color:var(--ink);display:flex;align-items:center;gap:7px;background:var(--glass-strong);padding:7px 13px;border-radius:20px;border:1px solid var(--border);font-size:12px;font-weight:700}
+.dot{width:8px;height:8px;border-radius:50%}
+.dot.ready,.dot.done{background:var(--ok);box-shadow:0 0 7px var(--ok)}
+.dot.running{background:var(--warn);box-shadow:0 0 7px var(--warn);animation:blink 1.2s infinite}
+.dot.error{background:var(--bad);box-shadow:0 0 7px var(--bad)}
+@keyframes blink{50%{opacity:.4}}
+.mode-btn{color:var(--ink);width:38px;height:38px;border-radius:11px;border:1px solid var(--border);background:var(--glass-strong);cursor:pointer;font-size:16px}
+.content{flex:1;overflow-y:auto;padding:26px 28px;border-top-left-radius:30px}
+/* cards, buttons, pills */
+.section-label{font-size:11px;text-transform:uppercase;letter-spacing:1px;color:var(--muted);font-weight:700;margin-bottom:14px}
+.card{background:var(--glass);border:1px solid var(--border);border-radius:16px;padding:22px;margin-bottom:16px;backdrop-filter:var(--blur);box-shadow:0 10px 30px rgba(20,50,70,.08)}
+.c-title{font-size:15px;font-weight:700;margin-bottom:14px}
+.btn{padding:9px 15px;border-radius:11px;border:1px solid var(--accent-soft-2);background:linear-gradient(180deg,var(--accent-soft),var(--accent-soft-2));color:var(--ink);font-size:12.5px;font-weight:600;cursor:pointer;transition:all .18s}
+.btn:hover{transform:translateY(-1px);box-shadow:0 4px 12px rgba(20,50,70,.2)}
+.btn.primary{background:var(--primary-bg);color:#fff;border-color:var(--accent)}
+.btn:disabled{opacity:.45;cursor:not-allowed;transform:none;box-shadow:none}
+.pill{display:inline-block;padding:4px 11px;border-radius:20px;font-size:11px;font-weight:700;color:#fff}
+.pill.success{background:var(--ok)}.pill.attention{background:var(--warn)}.pill.failed{background:var(--bad)}.pill.cleared{background:var(--muted)}
+ul,ol{list-style:none}
+.logo-title,.tb-title,.c-title,.kpi-val,.dh-num,.btn{font-family:var(--font-display)}
+/* KPI */
+.kpi-row{display:grid;grid-template-columns:repeat(4,1fr);gap:14px;margin-bottom:16px}
+.kpi{display:flex;align-items:center;gap:13px;padding:16px 18px;border-radius:16px;background:var(--glass-strong);border:1px solid var(--border);box-shadow:0 4px 14px rgba(20,50,70,.10)}
+.kpi-ic{width:42px;height:42px;border-radius:12px;position:relative}
+.kpi.total .kpi-ic{background:var(--accent)}
+.kpi.done .kpi-ic{background:var(--ok)}.kpi.prog .kpi-ic{background:var(--warn)}.kpi.notdone .kpi-ic{background:var(--bad)}
+.kpi.prog.live .kpi-ic::after{content:'';position:absolute;inset:-3px;border-radius:14px;border:2px solid var(--warn);animation:kpulse 1.6s ease-out infinite}
+@keyframes kpulse{0%{transform:scale(.9);opacity:.6}100%{transform:scale(1.25);opacity:0}}
+.kpi-val{font-size:26px;font-weight:800;line-height:1.1;font-variant-numeric:tabular-nums}
+.kpi-lbl{font-size:11.5px;color:var(--muted);font-weight:600;margin-top:2px}
+/* donut */
+.dash-grid{display:grid;grid-template-columns:1fr 1fr;gap:14px}
+.donut-wrap{display:flex;align-items:center;gap:26px;flex-wrap:wrap}
+.donut{width:150px;height:150px;border-radius:50%;position:relative;background:conic-gradient(var(--border) 0 100%)}
+.donut-hole{position:absolute;inset:22px;border-radius:50%;background:var(--bg-bottom);display:flex;flex-direction:column;align-items:center;justify-content:center}
+.dh-num{font-size:26px;font-weight:800}.dh-lbl{font-size:10px;color:var(--muted);font-weight:700;text-transform:uppercase}
+.dl-row{display:flex;align-items:center;gap:9px;font-size:12.5px;font-weight:600;margin-bottom:9px}
+.dl-dot{width:10px;height:10px;border-radius:3px}
+/* run panel */
+.prog-head{display:flex;gap:12px;margin-bottom:8px;font-size:13px;font-weight:700}
+.prog-head .pct{margin-left:auto;color:var(--accent)}
+.prog-bg{height:8px;background:var(--glass-strong);border-radius:8px;overflow:hidden;margin-bottom:18px}
+.prog-fill{height:100%;width:0;background:var(--progress-bg);transition:width .5s}
+.step{display:flex;align-items:center;gap:12px;padding:10px 13px;border-radius:10px;margin-bottom:6px;font-size:13px;font-weight:600}
+.step.done{background:var(--ok-bg);color:var(--ok)}.step.active{background:var(--warn-bg);color:var(--warn)}.step.pending{opacity:.5}
+.step-dot{width:22px;height:22px;border-radius:50%;display:flex;align-items:center;justify-content:center;font-size:11px;background:var(--glass-strong)}
+.step.done .step-dot{background:var(--ok);color:#fff}.step.active .step-dot{background:var(--warn);color:#fff}
+.log{background:var(--accent-dark);border-radius:12px;padding:12px 14px;max-height:220px;overflow-y:auto;font-family:Consolas,'Courier New',monospace;font-size:13px;line-height:1.85;color:#9fb6c4}
+.log .info{color:#7fc4f0}.log .success{color:#5fe0a0}.log .warn{color:#f5c563}.log .error{color:#f68c82}
+/* report table */
+.toolbar{display:flex;gap:10px;align-items:center;margin-bottom:14px;flex-wrap:wrap}
+.toolbar input{padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:var(--glass-strong);color:var(--ink);font:inherit;font-size:12.5px}
+.tbl-wrap{border:1px solid var(--border);border-radius:14px;overflow:auto;max-height:60vh;background:var(--glass)}
+table{border-collapse:collapse;width:100%;font-size:12px;white-space:nowrap}
+th{background:var(--glass-strong);text-align:left;padding:11px 14px;position:sticky;top:0;font-weight:700}
+td{padding:10px 14px;border-bottom:1px solid var(--border)}
+.empty{text-align:center;padding:40px;color:var(--muted);font-size:13px}
+@media (max-width:820px){.sidebar{width:66px;min-width:66px}.logo-title,.logo-sub,.nav-item span,.u-name,.u-role{display:none}.kpi-row{grid-template-columns:1fr 1fr}.dash-grid{grid-template-columns:1fr}}
+</style>
+</head>
+<body>
+<div class="app">
+  <aside class="sidebar">
+    <div class="logo-area">
+      <div class="logo-box"><img src="" alt="" onerror="this.remove()"></div>
+      <div><div class="logo-title">Field Ops Portal</div><div class="logo-sub">Automation dashboard</div></div>
+    </div>
+    <nav class="nav">
+      <button class="nav-item active" data-tab="dashboard" title="Dashboard"><svg viewBox="0 0 24 24"><rect x="3" y="3" width="7" height="7"/><rect x="14" y="3" width="7" height="7"/><rect x="3" y="14" width="7" height="7"/><rect x="14" y="14" width="7" height="7"/></svg><span>Dashboard</span></button>
+      <button class="nav-item" data-tab="run" title="Run"><svg viewBox="0 0 24 24"><polygon points="6 4 20 12 6 20 6 4"/></svg><span>Run</span></button>
+      <button class="nav-item" data-tab="report" title="Report"><svg viewBox="0 0 24 24"><path d="M4 4h16v16H4z"/><path d="M8 9h8M8 13h8M8 17h5"/></svg><span>Report</span></button>
+    </nav>
+    <div class="sidebar-foot"><div class="avatar" id="avatar">U</div><div><div class="u-name" id="u-name">User</div><div class="u-role" id="u-role">Operator</div></div></div>
+  </aside>
+
+  <main class="main">
+    <header class="topbar">
+      <div><div class="tb-title" id="tb-title">Dashboard</div><div class="tb-sub" id="tb-sub">Overview of every batch</div></div>
+      <div class="tb-right">
+        <button class="btn primary" id="run-btn" onclick="startRun()">▶ Run</button>
+        <button class="mode-btn" id="mode-btn" title="Dark mode" aria-label="Dark mode" aria-pressed="false" onclick="toggleDark()">🌙</button>
+        <div class="indicator"><span class="dot ready" id="st-dot"></span><span id="st-text">System ready</span></div>
+      </div>
+    </header>
+
+    <section class="content">
+      <!-- DASHBOARD -->
+      <div id="tab-dashboard">
+        <div class="kpi-row">
+          <div class="kpi total" role="group" aria-label="Total batches"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-total">0</div><div class="kpi-lbl">Total batches</div></div></div>
+          <div class="kpi done" role="group" aria-label="Completed"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-done">0</div><div class="kpi-lbl">Completed</div></div></div>
+          <div class="kpi prog" id="kpi-prog" role="group" aria-label="In progress"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-prog">0</div><div class="kpi-lbl">In progress</div></div></div>
+          <div class="kpi notdone" role="group" aria-label="Not completed"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-fail">0</div><div class="kpi-lbl">Not completed</div></div></div>
+        </div>
+        <div class="dash-grid">
+          <div class="card"><div class="c-title">Batch status split</div>
+            <div class="donut-wrap"><div class="donut" id="donut" role="img" aria-label="Batch status: no batches yet"><div class="donut-hole"><div class="dh-num" id="dh-num">0</div><div class="dh-lbl">batches</div></div></div><ul id="legend" aria-label="Batch status"></ul></div>
+          </div>
+          <div class="card"><div class="c-title">Recent batches</div><div id="recent" class="empty">No batches yet</div></div>
+        </div>
+      </div>
+
+      <!-- RUN -->
+      <div id="tab-run" class="hidden">
+        <div class="card"><div class="c-title">Run automation</div>
+          <div class="prog-head"><span id="p-label">Waiting to start</span><span id="p-time"></span><span class="pct" id="p-pct">0%</span></div>
+          <div class="prog-bg"><div class="prog-fill" id="p-fill"></div></div>
+          <ol id="steps" aria-label="Steps"></ol>
+          <div class="log" id="log" role="log" aria-label="Run log"></div>
+        </div>
+      </div>
+
+      <!-- REPORT -->
+      <div id="tab-report" class="hidden">
+        <div class="card">
+          <div class="toolbar"><input id="r-search" type="search" aria-label="Search report" placeholder="Search…" oninput="renderReport()"><span style="margin-left:auto"></span><button class="btn primary" onclick="api('download_report')">⬇ Download Excel</button></div>
+          <div class="tbl-wrap"><table><thead id="r-head"></thead><tbody id="r-body"></tbody></table></div>
+        </div>
+      </div>
+    </section>
+  </main>
+</div>
+
+<script>
+// ===== CONFIG (fill per project) =====
+const STEPS = ["Initializing","Load jobs","Process jobs","Completed"];
+const REPORT_COLUMNS = [{"key":"job","label":"Job"},{"key":"site","label":"Site"},{"key":"status","label":"Status"}];
+const API_BASE = "/api";                 // web mode only
+const SAMPLE_DATA = true;                // no bot yet: the page answers its own data actions. Set false once wired.
+const TABS = {dashboard:["Dashboard","Overview of every batch"],run:["Run","Live progress and log"],report:["Report","Result of every processed item"]};
+
+// ===== TRANSPORT: sample data, else Qt bridge, else HTTP polling =====
+let bridge = null, reportRows = [];
+function api(slot, ...args){
+  if(SAMPLE_DATA && SAMPLE[slot]) return SAMPLE[slot](...args);
+  if(bridge) return bridge[slot](...args);
+  return fetch(`${API_BASE}/${slot.replace(/_/g,'-')}`,{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify(args)}).catch(()=>{});
+}
+window.__pyMsg = (json)=>{ const m=JSON.parse(json); handle(m.event,m.data); };
+function startTransport(){
+  if(window.qt && window.qt.webChannelTransport){
+    new QWebChannel(qt.webChannelTransport, ch=>{ bridge=ch.objects.pyBridge; api('load_dashboard'); });
+  }else if(SAMPLE_DATA){
+    api('load_dashboard');
+  }else{
+    const poll = async()=>{
+      try{
+        const d = await (await fetch(`${API_BASE}/dashboard`)).json(); handle('dashboard_data',d);
+        const s = await (await fetch(`${API_BASE}/run/status`)).json();
+        (s.events||[]).forEach(e=>handle(e.event,e.data));
+        setTimeout(poll, s.running ? 2000 : 10000);   // poll fast only while busy
+      }catch(e){ setTimeout(poll, 10000); }
+    };
+    poll();
+  }
+}
+
+// ===== SAMPLE DATA: delete this block and set SAMPLE_DATA=false once the bot is wired =====
+const SAMPLE = {
+  load_dashboard(){ const day=n=>new Date(Date.now()-n*864e5).toISOString().slice(0,10);
+    handle('dashboard_data',{batches:[
+      {batch_id:1006,date:day(0),state:'inprogress',items_total:40,items_done:18},
+      {batch_id:1005,date:day(1),state:'completed',items_total:35,items_done:35},
+      {batch_id:1004,date:day(2),state:'completed',items_total:52,items_done:52},
+      {batch_id:1003,date:day(3),state:'notcompleted',items_total:20,items_done:7},
+      {batch_id:1002,date:day(4),state:'completed',items_total:28,items_done:28},
+      {batch_id:1001,date:day(6),state:'cleared',items_total:12,items_done:0}]}); },
+  load_latest_report(){
+    handle('report_data',{rows:[['Processed successfully','success'],['Posted','success'],['Needs review','attention'],['Error','failed']]
+      .map(([status,bucket],i)=>({...Object.fromEntries(REPORT_COLUMNS.map(c=>[c.key,`${c.label} ${i+1}`])),status,bucket}))}); },
+  start_automation(){ let i=0; handle('status',{state:'running',msg:'Running (sample)'});
+    const t=setInterval(()=>{
+      if(i<STEPS.length){ handle('step',{label:STEPS[i],pct:Math.round((i+1)/STEPS.length*100)}); handle('log',{msg:`Sample step: ${STEPS[i++]}`,type:'info'}); }
+      else{ clearInterval(t); handle('log',{msg:'Sample run finished.',type:'success'}); handle('status',{state:'done',msg:'Completed'}); }
+    },400); },
+};
+
+// ===== EVENT DISPATCH (see contract.md) =====
+function handle(event, d){
+  switch(event){
+    case 'status': setStatus(d.state, d.msg); break;
+    case 'step': setStep(d.label, d.pct); break;
+    case 'log': addLog(d.msg, d.type); break;
+    case 'dashboard_data': renderDashboard(d.batches||[]); break;
+    case 'report_data': reportRows = d.rows||[]; renderReport(); break;
+    case 'set_user': setUser(d); break;
+    case 'apply_dark': setDark(!!d.on); break;
+  }
+}
+
+// ===== UI =====
+document.querySelectorAll('.nav-item').forEach(n=>n.onclick=()=>showTab(n.dataset.tab));
+function showTab(t){
+  document.querySelectorAll('.nav-item').forEach(n=>n.classList.toggle('active',n.dataset.tab===t));
+  Object.keys(TABS).forEach(k=>document.getElementById('tab-'+k).classList.toggle('hidden',k!==t));
+  tbTitle.textContent=TABS[t][0]; tbSub.textContent=TABS[t][1];
+  if(t==='dashboard') api('load_dashboard');
+  if(t==='report') api('load_latest_report');
+}
+const $=id=>document.getElementById(id), tbTitle=$('tb-title'), tbSub=$('tb-sub');
+function esc(s){return String(s??'').replace(/[&<>"]/g,c=>({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;'}[c]));}
+function setDark(on){ document.body.classList.toggle('dark',on); $('mode-btn').setAttribute('aria-pressed',on); $('mode-btn').textContent=on?'☀':'🌙'; }
+function toggleDark(){ const on=!document.body.classList.contains('dark'); setDark(on); api('set_dark',on); }
+function setUser(u){ $('u-name').textContent=u.username; $('u-role').textContent=u.role; $('avatar').textContent=(u.username||'U')[0].toUpperCase(); }
+function setStatus(state,msg){ $('st-dot').className='dot '+state; $('st-text').textContent=msg||state; $('run-btn').disabled=state==='running'; }
+function startRun(){ showTab('run'); $('log').innerHTML=''; setStep(STEPS[0],0); api('start_automation'); }
+
+function renderSteps(active=-1){
+  $('steps').innerHTML=STEPS.map((s,i)=>{const c=i<active?'done':i===active?'active':'pending';
+    return `<li class="step ${c}"${c==='active'?' aria-current="step"':''}><span class="step-dot">${c==='done'?'✓':i+1}</span>${esc(s)}</li>`}).join('');
+}
+function setStep(label,pct){ $('p-label').textContent=label; $('p-pct').textContent=pct+'%'; $('p-fill').style.width=pct+'%';
+  renderSteps(pct>=100?STEPS.length:STEPS.indexOf(label)); }
+function addLog(msg,type='info'){ const l=$('log'); l.insertAdjacentHTML('beforeend',`<div class="${type}">${esc(msg)}</div>`); l.scrollTop=l.scrollHeight; }
+
+function countUp(el,to){ const from=+el.textContent||0,t0=performance.now();
+  const f=t=>{const p=Math.min((t-t0)/500,1); el.textContent=Math.round(from+(to-from)*p); if(p<1)requestAnimationFrame(f)}; requestAnimationFrame(f); }
+// batch state -> [label, colour token, pill class]
+const STATES={completed:['Completed','var(--ok)','success'],inprogress:['In progress','var(--warn)','attention'],
+  notcompleted:['Not completed','var(--bad)','failed'],cleared:['Cleared','var(--muted)','cleared']};
+function renderDashboard(b){
+  const c={}; Object.keys(STATES).forEach(k=>c[k]=b.filter(x=>x.state===k).length);
+  countUp($('k-total'),b.length); countUp($('k-done'),c.completed); countUp($('k-prog'),c.inprogress); countUp($('k-fail'),c.notcompleted);
+  $('kpi-prog').classList.toggle('live',c.inprogress>0); $('dh-num').textContent=b.length;
+  const tot=Object.values(c).reduce((a,x)=>a+x,0); let acc=0; const stops=[];
+  Object.keys(c).forEach(k=>{ if(!c[k])return; const a=acc/tot*100; acc+=c[k]; stops.push(`${STATES[k][1]} ${a}% ${acc/tot*100}%`); });
+  $('donut').style.background = tot?`conic-gradient(${stops.join(',')})`:'conic-gradient(var(--border) 0 100%)';
+  $('donut').setAttribute('aria-label','Batch status: '+Object.keys(c).map(k=>`${STATES[k][0]} ${c[k]}`).join(', '));
+  $('legend').innerHTML=Object.keys(c).map(k=>`<li class="dl-row"><span class="dl-dot" style="background:${STATES[k][1]}"></span>${STATES[k][0]} · ${c[k]}</li>`).join('');
+  $('recent').className = b.length?'':'empty';
+  $('recent').innerHTML = b.length? b.slice(0,6).map(x=>{const s=STATES[x.state]||[esc(x.state),'','attention'];
+    return `<div class="dl-row">#${esc(x.batch_id)} · ${esc(x.date)} <span class="pill ${s[2]}" style="margin-left:auto">${s[0]}</span></div>`}).join('') : 'No batches yet';
+}
+function renderReport(){
+  const q=$('r-search').value.toLowerCase();
+  $('r-head').innerHTML='<tr>'+REPORT_COLUMNS.map(c=>`<th>${esc(c.label)}</th>`).join('')+'</tr>';
+  const rows=reportRows.filter(r=>!q||Object.values(r).join(' ').toLowerCase().includes(q));
+  $('r-body').innerHTML = rows.length? rows.map(r=>'<tr>'+REPORT_COLUMNS.map(c=>c.key==='status'
+      ?`<td><span class="pill ${esc(r.bucket||'attention')}">${esc(r.status)}</span></td>`:`<td>${esc(r[c.key])}</td>`).join('')+'</tr>').join('')
+    : `<tr><td class="empty" colspan="${REPORT_COLUMNS.length}">No rows yet</td></tr>`;
+}
+renderSteps();
+startTransport();
+</script>
+</body>
+</html>

tests/evals/results/c-keep.json

@@ -0,0 +1,29 @@
+{
+  "fixture": "c-keep",
+  "passed": true,
+  "checks": {
+    "frontend reported correctly": true,
+    "asks /keep|restyle/": true,
+    "asks /section/": true,
+    "never asks /^(?!.*(keep|restyle)).*(colou?r|Tebra Sky|Ember)/": true,
+    "never asks /desktop/": true,
+    "existing files unchanged": true,
+    "exactly one page built": true,
+    "no placeholders left": true,
+    "page has --accent:#0f766e": true,
+    "page has Trebuchet MS": true,
+    "page check passes": true
+  },
+  "page_check": [
+    "22 passed in 18.02s"
+  ],
+  "files": [
+    "README.md",
+    "web\\css\\app.css",
+    "web\\css\\theme.css",
+    "web\\dashboard.html",
+    "web\\index.html",
+    "web\\js\\app.js"
+  ],
+  "reply": "Dashboard ready \u2014 **`web/dashboard.html`** (web path, plain HTML, sample data).\n\n| Item | Status |\n|---|---|\n| Look | **Kept** \u2014 the colours and fonts come from `web/css/theme.css` (teal brand, Trebuchet/Georgia), for both light and dark |\n| Existing files | **Not touched** (index.html, theme.css, app.css, app.js are unchanged) |\n| Sections | Sidebar, top bar (dark mode toggle + status dot), KPI cards, status donut, Run panel (steps + log), Report table (search + Excel). No optional sections. |\n| Data | `SAMPLE_DATA = true` \u2014 there is no bot yet. Steps are `Initializing \u2192 Load jobs \u2192 Process jobs \u2192 Completed`. Report columns are Job / Site / Status. |\n\n**Checks (headless Playwright):** 6 KPI batches, 4 legend items, 4/4 steps done, 5 log lines, 4/4 report rows with pills. No `{{` left and no console errors. I checked light, dark and 800px wide.\n\n- **Small tweak:** the Run button was the same teal as the top bar, so it was hard to see. I set `--primary-bg` to the project's own `--color-brand-strong` (#115e59).\n- **Palette fill-ins:** the project has no token for `--accent-2`, `--accent-dark` or `--accent-soft-2`, so those come from `palette.py`. All contrast checks pass.\n- **When the bot exists:** it must send the `status`, `step`, `log`, `dashboard_data` and `report_data` events. Set `SAMPLE_DATA=false` and serve `/api/dashboard` and `/api/run/status`.\n- **Navigation:** add a link to `dashboard.html` from your nav in `index.html`. I didn't edit that file.\n\nFRONTEND: web/ \u2014 plain HTML (web), tokens in web/css/theme.css (:root + [data-theme=\"dark\"]), brand #0f766e, fonts \"Trebuchet MS\"/Georgia\nQUESTIONS: Keep its look, or restyle it? | Which optional sections should I add: checkpoint tracker, admin/roles screen, login page, or none?"
+}

tests/evals/results/c-restyle.dashboard.html

@@ -0,0 +1,309 @@
+<!DOCTYPE html>
+<!--
+  Generic RPA dashboard (no AI). Derived from Tebra ERA (reference/tebra_dashboard.html).
+  One file: works inside PyQt6 QWebEngineView (QWebChannel bridge) OR served by any web
+  backend (falls back to polling GET /api/dashboard and /run/status).
+  Theme = the body / body.dark token blocks only (see themes.md).
+-->
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Field Ops Portal</title>
+<script src="qrc:///qtwebchannel/qwebchannel.js"></script>
+<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=IBM+Plex+Sans:wght@400;500;600;700&family=Sora:wght@600;700;800&display=swap">
+<style>
+/* ===== THEME TOKENS: Superbill Ember (see themes.md) ===== */
+body{
+  --bg-top:#f4f3f7; --bg-mid:#f4f3f7; --bg-bottom:#f4f3f7;
+  --glass:#ffffff; --glass-strong:#f7f6fa; --border:#e2dfe9;
+  --ink:#18151f; --muted:#66607a; --accent-dark:#18151f;
+  --accent:#ff3049; --accent-2:#f26b21; --accent-soft:#f7f6fa; --accent-soft-2:#e2dfe9;
+  --ok:#1f9d57; --ok-bg:#e6f6ec; --warn:#b7791f; --warn-bg:#fbf1dd; --bad:#c0392b; --bad-bg:#fdecea;
+  --font:'IBM Plex Sans','Segoe UI',-apple-system,sans-serif; --font-display:'Sora','Segoe UI',sans-serif;
+  --header-bg:linear-gradient(100deg,#ff3049,#f26b21); --header-ink:#ffffff; --header-muted:rgba(255,255,255,.85);
+  --primary-bg:linear-gradient(115deg,#ff3049,#f26b21);
+  --nav-active-bg:linear-gradient(100deg,#ff3049,#f26b21);
+  --progress-bg:linear-gradient(90deg,#ff3049,#f26b21); --blur:none;
+}
+body.dark{
+  --bg-top:#0a0912; --bg-mid:#0a0912; --bg-bottom:#0a0912;
+  --glass:#151220; --glass-strong:#1b1727; --border:#2a2438;
+  --ink:#f3f1f8; --muted:#8d87a0; --accent-dark:#100e1a;
+  --accent-soft:#1b1727; --accent-soft-2:#2a2438;
+  --ok:#2fbf72; --ok-bg:rgba(31,157,87,.16); --warn:#d9a13c; --warn-bg:rgba(183,121,31,.16);
+  --bad:#e05a4b; --bad-bg:rgba(192,57,43,.16);
+}
+/* ===== BASE ===== */
+*{box-sizing:border-box;margin:0;padding:0}
+html,body{height:100%;overflow:hidden}
+body{font-family:var(--font);color:var(--ink);
+  background:linear-gradient(180deg,var(--bg-top) 0%,var(--bg-mid) 45%,var(--bg-bottom) 100%)}
+.app{display:flex;height:100vh}
+.hidden{display:none!important}
+/* sidebar */
+.sidebar{width:230px;min-width:230px;background:var(--glass);border-right:1px solid var(--border);backdrop-filter:var(--blur);display:flex;flex-direction:column}
+.logo-area{padding:22px 20px;display:flex;align-items:center;gap:11px;border-bottom:1px solid var(--border)}
+.logo-box{width:40px;height:40px;border-radius:12px;background:var(--glass-strong);display:flex;align-items:center;justify-content:center;border:1px solid var(--border)}
+.logo-box img{width:28px;height:28px;object-fit:contain}
+.logo-title{font-size:15px;font-weight:700}
+.logo-sub{font-size:10px;color:var(--muted);margin-top:2px;letter-spacing:.5px;text-transform:uppercase;font-weight:600}
+.nav{padding:16px 12px;flex:1}
+.nav-item{border:0;background:none;width:100%;font:inherit;text-align:left;display:flex;align-items:center;gap:11px;padding:11px 13px;border-radius:10px;cursor:pointer;margin-bottom:3px;color:var(--muted);font-size:13.5px;font-weight:600;transition:all .15s;user-select:none}
+.nav-item svg{width:18px;height:18px;stroke:currentColor;fill:none;stroke-width:2}
+.nav-item:hover{background:var(--glass-strong);color:var(--ink)}
+.nav-item.active{background:var(--nav-active-bg);color:#fff;box-shadow:0 4px 12px rgba(20,50,70,.22)}
+.sidebar-foot{padding:14px;border-top:1px solid var(--border);display:flex;align-items:center;gap:10px}
+.avatar{width:34px;height:34px;border-radius:50%;background:var(--nav-active-bg);display:flex;align-items:center;justify-content:center;font-size:12px;font-weight:700;color:#fff}
+.u-name{font-size:13px;font-weight:700}.u-role{font-size:10.5px;color:var(--muted)}
+/* main + topbar */
+.main{flex:1;display:flex;flex-direction:column;overflow:hidden}
+.topbar{background:var(--header-bg);color:var(--header-ink);border-bottom:1px solid var(--border);backdrop-filter:var(--blur);padding:20px 28px;display:flex;align-items:center;gap:14px;box-shadow:0 6px 18px rgba(20,50,70,.10)}
+.tb-title{font-size:21px;font-weight:800}.tb-sub{font-size:12.5px;color:var(--header-muted);margin-top:3px}
+.tb-right{margin-left:auto;display:flex;align-items:center;gap:12px}
+.indicator{color:var(--ink);display:flex;align-items:center;gap:7px;background:var(--glass-strong);padding:7px 13px;border-radius:20px;border:1px solid var(--border);font-size:12px;font-weight:700}
+.dot{width:8px;height:8px;border-radius:50%}
+.dot.ready,.dot.done{background:var(--ok);box-shadow:0 0 7px var(--ok)}
+.dot.running{background:var(--warn);box-shadow:0 0 7px var(--warn);animation:blink 1.2s infinite}
+.dot.error{background:var(--bad);box-shadow:0 0 7px var(--bad)}
+@keyframes blink{50%{opacity:.4}}
+.mode-btn{color:var(--ink);width:38px;height:38px;border-radius:11px;border:1px solid var(--border);background:var(--glass-strong);cursor:pointer;font-size:16px}
+.content{flex:1;overflow-y:auto;padding:26px 28px;border-top-left-radius:30px}
+/* cards, buttons, pills */
+.section-label{font-size:11px;text-transform:uppercase;letter-spacing:1px;color:var(--muted);font-weight:700;margin-bottom:14px}
+.card{background:var(--glass);border:1px solid var(--border);border-radius:16px;padding:22px;margin-bottom:16px;backdrop-filter:var(--blur);box-shadow:0 10px 30px rgba(20,50,70,.08)}
+.c-title{font-size:15px;font-weight:700;margin-bottom:14px}
+.btn{padding:9px 15px;border-radius:11px;border:1px solid var(--accent-soft-2);background:linear-gradient(180deg,var(--accent-soft),var(--accent-soft-2));color:var(--ink);font-size:12.5px;font-weight:600;cursor:pointer;transition:all .18s}
+.btn:hover{transform:translateY(-1px);box-shadow:0 4px 12px rgba(20,50,70,.2)}
+.btn.primary{background:var(--primary-bg);color:#fff;border-color:var(--accent)}
+.btn:disabled{opacity:.45;cursor:not-allowed;transform:none;box-shadow:none}
+.pill{display:inline-block;padding:4px 11px;border-radius:20px;font-size:11px;font-weight:700;color:#fff}
+.pill.success{background:var(--ok)}.pill.attention{background:var(--warn)}.pill.failed{background:var(--bad)}.pill.cleared{background:var(--muted)}
+ul,ol{list-style:none}
+.logo-title,.tb-title,.c-title,.kpi-val,.dh-num,.btn{font-family:var(--font-display)}
+/* KPI */
+.kpi-row{display:grid;grid-template-columns:repeat(4,1fr);gap:14px;margin-bottom:16px}
+.kpi{display:flex;align-items:center;gap:13px;padding:16px 18px;border-radius:16px;background:var(--glass-strong);border:1px solid var(--border);box-shadow:0 4px 14px rgba(20,50,70,.10)}
+.kpi-ic{width:42px;height:42px;border-radius:12px;position:relative}
+.kpi.total .kpi-ic{background:var(--accent)}
+.kpi.done .kpi-ic{background:var(--ok)}.kpi.prog .kpi-ic{background:var(--warn)}.kpi.notdone .kpi-ic{background:var(--bad)}
+.kpi.prog.live .kpi-ic::after{content:'';position:absolute;inset:-3px;border-radius:14px;border:2px solid var(--warn);animation:kpulse 1.6s ease-out infinite}
+@keyframes kpulse{0%{transform:scale(.9);opacity:.6}100%{transform:scale(1.25);opacity:0}}
+.kpi-val{font-size:26px;font-weight:800;line-height:1.1;font-variant-numeric:tabular-nums}
+.kpi-lbl{font-size:11.5px;color:var(--muted);font-weight:600;margin-top:2px}
+/* donut */
+.dash-grid{display:grid;grid-template-columns:1fr 1fr;gap:14px}
+.donut-wrap{display:flex;align-items:center;gap:26px;flex-wrap:wrap}
+.donut{width:150px;height:150px;border-radius:50%;position:relative;background:conic-gradient(var(--border) 0 100%)}
+.donut-hole{position:absolute;inset:22px;border-radius:50%;background:var(--bg-bottom);display:flex;flex-direction:column;align-items:center;justify-content:center}
+.dh-num{font-size:26px;font-weight:800}.dh-lbl{font-size:10px;color:var(--muted);font-weight:700;text-transform:uppercase}
+.dl-row{display:flex;align-items:center;gap:9px;font-size:12.5px;font-weight:600;margin-bottom:9px}
+.dl-dot{width:10px;height:10px;border-radius:3px}
+/* run panel */
+.prog-head{display:flex;gap:12px;margin-bottom:8px;font-size:13px;font-weight:700}
+.prog-head .pct{margin-left:auto;color:var(--accent)}
+.prog-bg{height:8px;background:var(--glass-strong);border-radius:8px;overflow:hidden;margin-bottom:18px}
+.prog-fill{height:100%;width:0;background:var(--progress-bg);transition:width .5s}
+.step{display:flex;align-items:center;gap:12px;padding:10px 13px;border-radius:10px;margin-bottom:6px;font-size:13px;font-weight:600}
+.step.done{background:var(--ok-bg);color:var(--ok)}.step.active{background:var(--warn-bg);color:var(--warn)}.step.pending{opacity:.5}
+.step-dot{width:22px;height:22px;border-radius:50%;display:flex;align-items:center;justify-content:center;font-size:11px;background:var(--glass-strong)}
+.step.done .step-dot{background:var(--ok);color:#fff}.step.active .step-dot{background:var(--warn);color:#fff}
+.log{background:var(--accent-dark);border-radius:12px;padding:12px 14px;max-height:220px;overflow-y:auto;font-family:Consolas,'Courier New',monospace;font-size:13px;line-height:1.85;color:#9fb6c4}
+.log .info{color:#7fc4f0}.log .success{color:#5fe0a0}.log .warn{color:#f5c563}.log .error{color:#f68c82}
+/* report table */
+.toolbar{display:flex;gap:10px;align-items:center;margin-bottom:14px;flex-wrap:wrap}
+.toolbar input{padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:var(--glass-strong);color:var(--ink);font:inherit;font-size:12.5px}
+.tbl-wrap{border:1px solid var(--border);border-radius:14px;overflow:auto;max-height:60vh;background:var(--glass)}
+table{border-collapse:collapse;width:100%;font-size:12px;white-space:nowrap}
+th{background:var(--glass-strong);text-align:left;padding:11px 14px;position:sticky;top:0;font-weight:700}
+td{padding:10px 14px;border-bottom:1px solid var(--border)}
+.empty{text-align:center;padding:40px;color:var(--muted);font-size:13px}
+@media (max-width:820px){.sidebar{width:66px;min-width:66px}.logo-title,.logo-sub,.nav-item span,.u-name,.u-role{display:none}.kpi-row{grid-template-columns:1fr 1fr}.dash-grid{grid-template-columns:1fr}}
+</style>
+</head>
+<body>
+<div class="app">
+  <aside class="sidebar">
+    <div class="logo-area">
+      <div class="logo-box"><img src="" alt="" onerror="this.remove()"></div>
+      <div><div class="logo-title">Field Ops Portal</div><div class="logo-sub">Job automation</div></div>
+    </div>
+    <nav class="nav">
+      <button class="nav-item active" data-tab="dashboard" title="Dashboard"><svg viewBox="0 0 24 24"><rect x="3" y="3" width="7" height="7"/><rect x="14" y="3" width="7" height="7"/><rect x="3" y="14" width="7" height="7"/><rect x="14" y="14" width="7" height="7"/></svg><span>Dashboard</span></button>
+      <button class="nav-item" data-tab="run" title="Run"><svg viewBox="0 0 24 24"><polygon points="6 4 20 12 6 20 6 4"/></svg><span>Run</span></button>
+      <button class="nav-item" data-tab="report" title="Report"><svg viewBox="0 0 24 24"><path d="M4 4h16v16H4z"/><path d="M8 9h8M8 13h8M8 17h5"/></svg><span>Report</span></button>
+    </nav>
+    <div class="sidebar-foot"><div class="avatar" id="avatar">U</div><div><div class="u-name" id="u-name">User</div><div class="u-role" id="u-role">Operator</div></div></div>
+  </aside>
+
+  <main class="main">
+    <header class="topbar">
+      <div><div class="tb-title" id="tb-title">Dashboard</div><div class="tb-sub" id="tb-sub">Overview of every batch</div></div>
+      <div class="tb-right">
+        <button class="btn primary" id="run-btn" onclick="startRun()">▶ Run</button>
+        <button class="mode-btn" id="mode-btn" title="Dark mode" aria-label="Dark mode" aria-pressed="false" onclick="toggleDark()">🌙</button>
+        <div class="indicator"><span class="dot ready" id="st-dot"></span><span id="st-text">System ready</span></div>
+      </div>
+    </header>
+
+    <section class="content">
+      <!-- DASHBOARD -->
+      <div id="tab-dashboard">
+        <div class="kpi-row">
+          <div class="kpi total" role="group" aria-label="Total batches"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-total">0</div><div class="kpi-lbl">Total batches</div></div></div>
+          <div class="kpi done" role="group" aria-label="Completed"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-done">0</div><div class="kpi-lbl">Completed</div></div></div>
+          <div class="kpi prog" id="kpi-prog" role="group" aria-label="In progress"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-prog">0</div><div class="kpi-lbl">In progress</div></div></div>
+          <div class="kpi notdone" role="group" aria-label="Not completed"><div class="kpi-ic"></div><div><div class="kpi-val" id="k-fail">0</div><div class="kpi-lbl">Not completed</div></div></div>
+        </div>
+        <div class="dash-grid">
+          <div class="card"><div class="c-title">Batch status split</div>
+            <div class="donut-wrap"><div class="donut" id="donut" role="img" aria-label="Batch status: no batches yet"><div class="donut-hole"><div class="dh-num" id="dh-num">0</div><div class="dh-lbl">batches</div></div></div><ul id="legend" aria-label="Batch status"></ul></div>
+          </div>
+          <div class="card"><div class="c-title">Recent batches</div><div id="recent" class="empty">No batches yet</div></div>
+        </div>
+      </div>
+
+      <!-- RUN -->
+      <div id="tab-run" class="hidden">
+        <div class="card"><div class="c-title">Run automation</div>
+          <div class="prog-head"><span id="p-label">Waiting to start</span><span id="p-time"></span><span class="pct" id="p-pct">0%</span></div>
+          <div class="prog-bg"><div class="prog-fill" id="p-fill"></div></div>
+          <ol id="steps" aria-label="Steps"></ol>
+          <div class="log" id="log" role="log" aria-label="Run log"></div>
+        </div>
+      </div>
+
+      <!-- REPORT -->
+      <div id="tab-report" class="hidden">
+        <div class="card">
+          <div class="toolbar"><input id="r-search" type="search" aria-label="Search report" placeholder="Search…" oninput="renderReport()"><span style="margin-left:auto"></span><button class="btn primary" onclick="api('download_report')">⬇ Download Excel</button></div>
+          <div class="tbl-wrap"><table><thead id="r-head"></thead><tbody id="r-body"></tbody></table></div>
+        </div>
+      </div>
+    </section>
+  </main>
+</div>
+
+<script>
+// ===== CONFIG (fill per project) =====
+const STEPS = ["Initializing","Load jobs","Process jobs","Completed"];
+const REPORT_COLUMNS = [{"key":"job","label":"Job"},{"key":"site","label":"Site"},{"key":"status","label":"Status"}];
+const API_BASE = "/api";                 // web mode only
+const SAMPLE_DATA = true;                // no bot yet: the page answers its own data actions. Set false once wired.
+const TABS = {dashboard:["Dashboard","Overview of every batch"],run:["Run","Live progress and log"],report:["Report","Result of every processed item"]};
+
+// ===== TRANSPORT: sample data, else Qt bridge, else HTTP polling =====
+let bridge = null, reportRows = [];
+function api(slot, ...args){
+  if(SAMPLE_DATA && SAMPLE[slot]) return SAMPLE[slot](...args);
+  if(bridge) return bridge[slot](...args);
+  return fetch(`${API_BASE}/${slot.replace(/_/g,'-')}`,{method:'POST',headers:{'Content-Type':'application/json'},body:JSON.stringify(args)}).catch(()=>{});
+}
+window.__pyMsg = (json)=>{ const m=JSON.parse(json); handle(m.event,m.data); };
+function startTransport(){
+  if(window.qt && window.qt.webChannelTransport){
+    new QWebChannel(qt.webChannelTransport, ch=>{ bridge=ch.objects.pyBridge; api('load_dashboard'); });
+  }else if(SAMPLE_DATA){
+    api('load_dashboard');
+  }else{
+    const poll = async()=>{
+      try{
+        const d = await (await fetch(`${API_BASE}/dashboard`)).json(); handle('dashboard_data',d);
+        const s = await (await fetch(`${API_BASE}/run/status`)).json();
+        (s.events||[]).forEach(e=>handle(e.event,e.data));
+        setTimeout(poll, s.running ? 2000 : 10000);   // poll fast only while busy
+      }catch(e){ setTimeout(poll, 10000); }
+    };
+    poll();
+  }
+}
+
+// ===== SAMPLE DATA: delete this block and set SAMPLE_DATA=false once the bot is wired =====
+const SAMPLE = {
+  load_dashboard(){ const day=n=>new Date(Date.now()-n*864e5).toISOString().slice(0,10);
+    handle('dashboard_data',{batches:[
+      {batch_id:1006,date:day(0),state:'inprogress',items_total:40,items_done:18},
+      {batch_id:1005,date:day(1),state:'completed',items_total:35,items_done:35},
+      {batch_id:1004,date:day(2),state:'completed',items_total:52,items_done:52},
+      {batch_id:1003,date:day(3),state:'notcompleted',items_total:20,items_done:7},
+      {batch_id:1002,date:day(4),state:'completed',items_total:28,items_done:28},
+      {batch_id:1001,date:day(6),state:'cleared',items_total:12,items_done:0}]}); },
+  load_latest_report(){
+    handle('report_data',{rows:[['Processed successfully','success'],['Posted','success'],['Needs review','attention'],['Error','failed']]
+      .map(([status,bucket],i)=>({...Object.fromEntries(REPORT_COLUMNS.map(c=>[c.key,`${c.label} ${i+1}`])),status,bucket}))}); },
+  start_automation(){ let i=0; handle('status',{state:'running',msg:'Running (sample)'});
+    const t=setInterval(()=>{
+      if(i<STEPS.length){ handle('step',{label:STEPS[i],pct:Math.round((i+1)/STEPS.length*100)}); handle('log',{msg:`Sample step: ${STEPS[i++]}`,type:'info'}); }
+      else{ clearInterval(t); handle('log',{msg:'Sample run finished.',type:'success'}); handle('status',{state:'done',msg:'Completed'}); }
+    },400); },
+};
+
+// ===== EVENT DISPATCH (see contract.md) =====
+function handle(event, d){
+  switch(event){
+    case 'status': setStatus(d.state, d.msg); break;
+    case 'step': setStep(d.label, d.pct); break;
+    case 'log': addLog(d.msg, d.type); break;
+    case 'dashboard_data': renderDashboard(d.batches||[]); break;
+    case 'report_data': reportRows = d.rows||[]; renderReport(); break;
+    case 'set_user': setUser(d); break;
+    case 'apply_dark': setDark(!!d.on); break;
+  }
+}
+
+// ===== UI =====
+document.querySelectorAll('.nav-item').forEach(n=>n.onclick=()=>showTab(n.dataset.tab));
+function showTab(t){
+  document.querySelectorAll('.nav-item').forEach(n=>n.classList.toggle('active',n.dataset.tab===t));
+  Object.keys(TABS).forEach(k=>document.getElementById('tab-'+k).classList.toggle('hidden',k!==t));
+  tbTitle.textContent=TABS[t][0]; tbSub.textContent=TABS[t][1];
+  if(t==='dashboard') api('load_dashboard');
+  if(t==='report') api('load_latest_report');
+}
+const $=id=>document.getElementById(id), tbTitle=$('tb-title'), tbSub=$('tb-sub');
+function esc(s){return String(s??'').replace(/[&<>"]/g,c=>({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;'}[c]));}
+function setDark(on){ document.body.classList.toggle('dark',on); $('mode-btn').setAttribute('aria-pressed',on); $('mode-btn').textContent=on?'☀':'🌙'; }
+function toggleDark(){ const on=!document.body.classList.contains('dark'); setDark(on); api('set_dark',on); }
+function setUser(u){ $('u-name').textContent=u.username; $('u-role').textContent=u.role; $('avatar').textContent=(u.username||'U')[0].toUpperCase(); }
+function setStatus(state,msg){ $('st-dot').className='dot '+state; $('st-text').textContent=msg||state; $('run-btn').disabled=state==='running'; }
+function startRun(){ showTab('run'); $('log').innerHTML=''; setStep(STEPS[0],0); api('start_automation'); }
+
+function renderSteps(active=-1){
+  $('steps').innerHTML=STEPS.map((s,i)=>{const c=i<active?'done':i===active?'active':'pending';
+    return `<li class="step ${c}"${c==='active'?' aria-current="step"':''}><span class="step-dot">${c==='done'?'✓':i+1}</span>${esc(s)}</li>`}).join('');
+}
+function setStep(label,pct){ $('p-label').textContent=label; $('p-pct').textContent=pct+'%'; $('p-fill').style.width=pct+'%';
+  renderSteps(pct>=100?STEPS.length:STEPS.indexOf(label)); }
+function addLog(msg,type='info'){ const l=$('log'); l.insertAdjacentHTML('beforeend',`<div class="${type}">${esc(msg)}</div>`); l.scrollTop=l.scrollHeight; }
+
+function countUp(el,to){ const from=+el.textContent||0,t0=performance.now();
+  const f=t=>{const p=Math.min((t-t0)/500,1); el.textContent=Math.round(from+(to-from)*p); if(p<1)requestAnimationFrame(f)}; requestAnimationFrame(f); }
+// batch state -> [label, colour token, pill class]
+const STATES={completed:['Completed','var(--ok)','success'],inprogress:['In progress','var(--warn)','attention'],
+  notcompleted:['Not completed','var(--bad)','failed'],cleared:['Cleared','var(--muted)','cleared']};
+function renderDashboard(b){
+  const c={}; Object.keys(STATES).forEach(k=>c[k]=b.filter(x=>x.state===k).length);
+  countUp($('k-total'),b.length); countUp($('k-done'),c.completed); countUp($('k-prog'),c.inprogress); countUp($('k-fail'),c.notcompleted);
+  $('kpi-prog').classList.toggle('live',c.inprogress>0); $('dh-num').textContent=b.length;
+  const tot=Object.values(c).reduce((a,x)=>a+x,0); let acc=0; const stops=[];
+  Object.keys(c).forEach(k=>{ if(!c[k])return; const a=acc/tot*100; acc+=c[k]; stops.push(`${STATES[k][1]} ${a}% ${acc/tot*100}%`); });
+  $('donut').style.background = tot?`conic-gradient(${stops.join(',')})`:'conic-gradient(var(--border) 0 100%)';
+  $('donut').setAttribute('aria-label','Batch status: '+Object.keys(c).map(k=>`${STATES[k][0]} ${c[k]}`).join(', '));
+  $('legend').innerHTML=Object.keys(c).map(k=>`<li class="dl-row"><span class="dl-dot" style="background:${STATES[k][1]}"></span>${STATES[k][0]} · ${c[k]}</li>`).join('');
+  $('recent').className = b.length?'':'empty';
+  $('recent').innerHTML = b.length? b.slice(0,6).map(x=>{const s=STATES[x.state]||[esc(x.state),'','attention'];
+    return `<div class="dl-row">#${esc(x.batch_id)} · ${esc(x.date)} <span class="pill ${s[2]}" style="margin-left:auto">${s[0]}</span></div>`}).join('') : 'No batches yet';
+}
+function renderReport(){
+  const q=$('r-search').value.toLowerCase();
+  $('r-head').innerHTML='<tr>'+REPORT_COLUMNS.map(c=>`<th>${esc(c.label)}</th>`).join('')+'</tr>';
+  const rows=reportRows.filter(r=>!q||Object.values(r).join(' ').toLowerCase().includes(q));
+  $('r-body').innerHTML = rows.length? rows.map(r=>'<tr>'+REPORT_COLUMNS.map(c=>c.key==='status'
+      ?`<td><span class="pill ${esc(r.bucket||'attention')}">${esc(r.status)}</span></td>`:`<td>${esc(r[c.key])}</td>`).join('')+'</tr>').join('')
+    : `<tr><td class="empty" colspan="${REPORT_COLUMNS.length}">No rows yet</td></tr>`;
+}
+renderSteps();
+startTransport();
+</script>
+</body>
+</html>

tests/evals/results/c-restyle.json

@@ -0,0 +1,29 @@
+{
+  "fixture": "c-restyle",
+  "passed": true,
+  "checks": {
+    "frontend reported correctly": true,
+    "asks /keep|restyle/": true,
+    "asks /Tebra Sky|Ember/": true,
+    "asks /section/": true,
+    "never asks /desktop/": true,
+    "existing files: only token lines changed": true,
+    "existing tokens now use #ff3049": true,
+    "exactly one page built": true,
+    "no placeholders left": true,
+    "page has --accent:#ff3049": true,
+    "page check passes": true
+  },
+  "page_check": [
+    "22 passed in 23.29s"
+  ],
+  "files": [
+    "README.md",
+    "web\\css\\app.css",
+    "web\\css\\theme.css",
+    "web\\dashboard.html",
+    "web\\index.html",
+    "web\\js\\app.js"
+  ],
+  "reply": "Dashboard ready, Superbill Ember theme-la restyle pannirukken. Frontend `web/`-la irundhudhu (plain HTML, web). Andha site-la token lines and oru font link mattum dhaan maathinen.\n\n| Item | Result |\n|---|---|\n| Pudhu page | `web/dashboard.html` (sample data, `SAMPLE_DATA = true`) |\n| Sections | Shell, KPI, donut, run panel, report. Optional sections edhuvum illa; `OPTIONAL` marker-um illa |\n| Restyle | `web/css/theme.css` token values + `web/index.html`-la font link |\n| Check | `{{` 0 left \u00b7 KPI total 6 \u00b7 legend 4 \u00b7 steps 4/4, log 5 lines, status \"Completed\" \u00b7 report 4 rows / 4 pills \u00b7 light, dark, 800px screenshots paathen, ellam correct-ah irukku |\n\n**Existing files-la changed lines:**\n```\ntheme.css :root   --color-brand #0f766e\u2192#ff3049 \u00b7 -strong #115e59\u2192#18151f \u00b7 -tint #ccfbf1\u2192#f7f6fa\n                  --color-bg \u2192#f4f3f7 \u00b7 -surface-alt \u2192#f7f6fa \u00b7 -border \u2192#e2dfe9 \u00b7 -text \u2192#18151f \u00b7 -text-muted \u2192#66607a\n                  -success \u2192#1f9d57 \u00b7 -warning \u2192#b7791f \u00b7 -danger \u2192#c0392b\n                  --font-sans \u2192'IBM Plex Sans',\u2026 \u00b7 --font-heading \u2192'Sora',\u2026   (--color-surface, --radius maarala)\ntheme.css [dark]  brand \u2192#ff3049 \u00b7 -strong \u2192#100e1a \u00b7 -tint \u2192#1b1727 \u00b7 bg \u2192#0a0912 \u00b7 surface \u2192#151220\n                  surface-alt \u2192#1b1727 \u00b7 border \u2192#2a2438 \u00b7 text \u2192#f3f1f8 \u00b7 muted \u2192#8d87a0 \u00b7 ok/warn/bad \u2192#2fbf72/#d9a13c/#e05a4b\nindex.html        + Google Fonts <link> (IBM Plex Sans + Sora), theme.css link-ku munnaadi\n```\n\nBot innum illa. Bot ready aana, backend-ah wire pannanum: `GET /api/dashboard`, `GET /api/run/status` (idhu `{running, events[]}` return pannanum), and `POST /api/<action>`. Bot anuppa vendiya events: `status`, `step`, `log`, `dashboard_data`, `report_data`. `index.html`-oda nav-la `dashboard.html`-ku link nee dhaan podanum; adha naan touch pannala.\n\n**Also noticed (fix pannala):**\n- `app.css`-la hard-coded `#ffffff` irukku: topbar text, links, `.button`, `.tag`. Token-only restyle-nala adhu maarala.\n- Portal dark mode-la \"Dark mode\" button text theriyala. Text-um background-um ore colour family (`brand-strong` on `brand-tint`). Idhu munnaadiye irundha issue; teal theme-la rendum `#134e4a` dhaan.\n- Dashboard-la file:// vazhiya open pannum bodhu dark toggle `set-dark`-ku POST anuppudhu, adhu console-la oru error kaattudhu. Page-ku edhuvum aagala; server vazhiya serve pannina indha error varaadhu.\n\nFRONTEND: web/ \u2014 plain HTML (web), tokens in web/css/theme.css (:root + [data-theme=\"dark\"]), brand #0f766e teal, fonts \"Trebuchet MS\" / Georgia\nQUESTIONS: Keep its look, or restyle it? | Which colours: Tebra Sky, Superbill Ember, or Custom (one brand hex)? | Which optional sections to add: checkpoint tracker, admin/roles screen, login page, or none?"
+}

tests/evals/run_eval.py

@@ -9,6 +9,7 @@ prompt (`-p` can't answer questions). It then grades the reply, runs the Seam 1
 check on the page it built, and writes tests/evals/results/<fixture>.json.
 Exit code 0 means every check passed.
 """
+import difflib
 import importlib.util
 import json
 import os
@@ -38,7 +39,7 @@ FIXTURES = {
         "sections": [],
     },
     "a-empty-sections": {
-        "dir": "a-empty",
+        "fixture": "a-empty",
         "prompt": "Build me an RPA dashboard for this project. I can't answer questions while you "
                   "work, so here are my answers to anything the skill asks. Colours: Superbill Ember. "
                   "Desktop or web: web. Optional sections: all three (checkpoint tracker, admin/roles "
@@ -48,14 +49,87 @@ FIXTURES = {
         "never_asks": [r"\bkeep\b|restyle"],
         "sections": ["checkpoints", "admin", "login"],
     },
+    "b-pyqt-bot": {
+        "prompt": "Build me an RPA dashboard for this project. I can't answer questions while you "
+                  "work, so here are my answers to anything the skill asks. Colours: Tebra Sky. "
+                  "Optional sections: none.",
+        "frontend": r"^\s*(none|no\b)",
+        "asks": [r"colou?r", r"section"],
+        "never_asks": [r"\bkeep\b|restyle", r"desktop|web"],
+        "bot": True,
+    },
+    # (c) existing teal frontend in web/, run once per answer to keep-or-restyle.
+    "c-keep": {
+        "fixture": "c-web-existing-frontend",
+        "prompt": "Build me an RPA dashboard for this project. I can't answer questions while you "
+                  "work, so here are my answers to anything the skill asks. Keep or restyle the "
+                  "existing frontend: keep its look. Optional sections: none.",
+        "frontend": r"(?=.*\bweb\b)(?=.*html)(?=.*(#0f766e|--color-brand))",
+        "asks": [r"keep|restyle", r"section"],
+        "never_asks": [r"^(?!.*(keep|restyle)).*(colou?r|Tebra Sky|Ember)", r"desktop"],
+        "page_has": ["--accent:#0f766e", "Trebuchet MS"],
+        "existing": "unchanged",
+    },
+    "c-restyle": {
+        "fixture": "c-web-existing-frontend",
+        "prompt": "Build me an RPA dashboard for this project. I can't answer questions while you "
+                  "work, so here are my answers to anything the skill asks. Keep or restyle the "
+                  "existing frontend: restyle it. Colours: Superbill Ember. Optional sections: none.",
+        "frontend": r"(?=.*\bweb\b)(?=.*html)(?=.*(#0f766e|--color-brand))",
+        "asks": [r"keep|restyle", r"Tebra Sky|Ember", r"section"],
+        "never_asks": [r"desktop"],
+        "page_has": ["--accent:#ff3049"],
+        "existing": "#ff3049",  # only token lines may change, and the theme now uses this colour
+    },
 }
+# A line a restyle may change: a custom property, a comment, a blank, or a web-font link.
+TOKEN_LINE = r"^\s*(--[\w-]+\s*:.*|/\*.*\*/|<link[^>]*fonts\.googleapis\.com.*|@import.*fonts\.googleapis\.com.*)?\s*$"
+
+
+def squash(s):
+    """Ignore spacing and case when looking for a token in the built page."""
+    return re.sub(r"\s+", "", s).lower()
+
+
+def changed_lines(src, project):
+    """Lines removed or added in the fixture's own files."""
+    out = []
+    for f in src.rglob("*"):
+        if f.is_file():
+            new = project / f.relative_to(src)
+            after = new.read_text(encoding="utf-8").splitlines() if new.exists() else []
+            out += [x[1:] for x in difflib.unified_diff(f.read_text(encoding="utf-8").splitlines(), after, lineterm="", n=0)
+                    if x[:1] in "+-" and x[:3] not in ("+++", "---")]
+    return out
+
+
+def bot_checks(project, html, checks, replay):
+    """Bot fixtures: the page is wired, and a dry run of the generated wiring gives real steps and logs.
+    Returns the env that points the page check at that run."""
+    checks["page wired to the bot (sample data off)"] = bool(re.search(r"SAMPLE_DATA\s*=\s*false", html))
+    runners = [p for p in project.rglob("bot_runner.py") if ".claude" not in p.parts]
+    checks["bot_runner.py built"] = len(runners) == 1
+    if not runners:
+        return {}
+    host = [runners[0], runners[0].with_name("bridge.py")]
+    checks["no placeholders left in the host"] = all(p.exists() and "{{" not in p.read_text(encoding="utf-8") for p in host)
+    dry = subprocess.run([sys.executable, str(runners[0])], cwd=project, capture_output=True, text=True,
+                         encoding="utf-8", timeout=300)
+    replay.write_text(dry.stdout, encoding="utf-8")
+    events = [json.loads(x) for x in dry.stdout.splitlines() if x.startswith("{")]
+    steps = [e["data"] for e in events if e["event"] == "step"]
+    checks["bot dry run ends done"] = bool(events) and events[-1]["data"].get("state") == "done"
+    checks["real steps reach the page"] = len({s["label"] for s in steps}) >= 3 and steps[-1]["pct"] == 100
+    checks["bot error line reaches the log"] = any(e["event"] == "log" and e["data"]["type"] == "error" for e in events)
+    return {"PAGE_CHECK_WIRED": "1", "PAGE_CHECK_REPLAY": str(replay)}
 
 
 def main(fixture):
     cfg = FIXTURES[fixture]
     work = Path(tempfile.mkdtemp(prefix=f"rpa-eval-{fixture}-"))
     project = work / "project"
-    shutil.copytree(ROOT / "tests" / "fixtures" / cfg.get("dir", fixture), project)
+    src = ROOT / "tests" / "fixtures" / cfg.get("fixture", fixture)
+    shutil.copytree(src, project)
     for skill in ROOT.glob("rpa-dashboard-*"):
         shutil.copytree(skill, project / ".claude" / "skills" / skill.name)
 
@@ -73,12 +147,21 @@ def main(fixture):
         return m[1] if m else ""
 
     checks = {"frontend reported correctly": bool(re.search(cfg["frontend"], line("FRONTEND"), re.I))}
+    questions = line("QUESTIONS").split("|")
     for pat in cfg["asks"]:
-        checks[f"asks /{pat}/"] = bool(re.search(pat, line("QUESTIONS"), re.I))
+        checks[f"asks /{pat}/"] = any(re.search(pat, q, re.I) for q in questions)
     for pat in cfg["never_asks"]:
-        checks[f"never asks /{pat}/"] = not re.search(pat, line("QUESTIONS"), re.I)
+        checks[f"never asks /{pat}/"] = not any(re.search(pat, q, re.I) for q in questions)
+    if "existing" in cfg:
+        changed = changed_lines(src, project)
+        if cfg["existing"] == "unchanged":
+            checks["existing files unchanged"] = not changed
+        else:
+            checks["existing files: only token lines changed"] = bool(changed) and all(re.match(TOKEN_LINE, x) for x in changed)
+            checks[f"existing tokens now use {cfg['existing']}"] = any(cfg["existing"] in x.lower() for x in changed)
 
-    pages = [p for p in project.rglob("*.html") if ".claude" not in p.parts]
+    pages = [p for p in project.rglob("*.html")
+             if ".claude" not in p.parts and not (src / p.relative_to(project)).exists()]  # new pages only
     checks["exactly one page built"] = len(pages) == 1
     results = ROOT / "tests" / "evals" / "results"
     results.mkdir(exist_ok=True)
@@ -99,8 +182,13 @@ def main(fixture):
             for name, trace in traces.TRACES.items():
                 want = name in cfg["sections"]
                 checks[f"{name} {'built' if want else 'left no trace'}"] = bool(trace.search(html)) == want
+        for needle in cfg.get("page_has", []):
+            checks[f"page has {needle}"] = squash(needle) in squash(html)
+        env = {**os.environ, "PAGE_CHECK_HTML": str(pages[0])}
+        if cfg.get("bot"):
+            env.update(bot_checks(project, html, checks, results / f"{fixture}.run.jsonl"))
         pc = subprocess.run([sys.executable, "-m", "pytest", str(ROOT / "tests" / "page_check"), "-q"],
-                            env={**os.environ, "PAGE_CHECK_HTML": str(pages[0])}, capture_output=True, text=True)
+                            env=env, capture_output=True, text=True)
         checks["page check passes"] = pc.returncode == 0
         page_check = pc.stdout.strip().splitlines()[-1:] if pc.stdout else [pc.stderr[-500:]]
         if cfg.get("sections"):  # every chosen section's page check ran

tests/fixtures/b-pyqt-bot/README.md

@@ -0,0 +1,10 @@
+# Work-item follow-up bot
+
+A desktop RPA bot. It logs in to the portal and updates each work item.
+The operator window will be a PyQt6 app.
+
+Run the bot on its own:
+
+```
+python -m bot
+```

tests/fixtures/b-pyqt-bot/bot.py

@@ -0,0 +1,29 @@
+"""Work-item follow-up bot. Start it with:  python -m bot"""
+import time
+
+ITEMS = ["WI-1001", "WI-1002", "WI-1003"]
+
+
+def say(line):
+    print(line)
+    time.sleep(0.2)
+
+
+def main():
+    say("[step 1] Initializing")
+    say("Loading settings from config.ini")
+    say("Completed loading 3 work items")
+    say("[step 2] Logging in to the portal")
+    say("Login page loaded")
+    say("[login] ok")
+    say("[step 3] Processing work items")
+    for i, item in enumerate(ITEMS, 1):
+        say(f"[item] {item} updated ({i}/{len(ITEMS)})")
+    say("WARNING: portal slow to respond, waited 5s")
+    say("ERROR: could not attach the note to WI-1003")
+    say("[step 4] Writing the summary")
+    say(f"[all done] {len(ITEMS)} items processed")
+
+
+if __name__ == "__main__":
+    main()

tests/fixtures/b-pyqt-bot/requirements.txt

@@ -0,0 +1,2 @@
+PyQt6
+PyQt6-WebEngine

tests/fixtures/c-web-existing-frontend/README.md

@@ -0,0 +1,10 @@
+# Fixture (c): web project with an existing frontend
+
+A plain HTML site in `web/` with its own teal theme: light and dark tokens in
+`web/css/theme.css`, layout in `web/css/app.css`, logic in `web/js/app.js`. No bot.
+
+The no-AI skill should report this frontend (location, stack, colours), ask keep or
+restyle, never ask desktop or web, and build a dashboard page on sample data.
+- Keep: no colour question; the page uses the theme's tokens and fonts; no existing
+  file changes.
+- Restyle: asks for colours; only token lines in the existing files change.

tests/fixtures/c-web-existing-frontend/web/css/app.css

@@ -0,0 +1,18 @@
+/* Layout and components. Colours and fonts come from theme.css. */
+* { box-sizing: border-box; margin: 0; }
+body { font-family: var(--font-sans); background: var(--color-bg); color: var(--color-text); }
+h1, h2 { font-family: var(--font-heading); }
+.topbar { display: flex; align-items: center; gap: 16px; padding: 14px 24px; background: var(--color-brand); color: #ffffff; }
+.topbar nav { margin-left: auto; display: flex; gap: 12px; }
+.topbar a { color: #ffffff; text-decoration: none; }
+.page { max-width: 960px; margin: 24px auto; padding: 0 16px; }
+.card { background: var(--color-surface); border: 1px solid var(--color-border); border-radius: var(--radius); padding: 20px; }
+.button { background: var(--color-brand); color: #ffffff; border: 0; border-radius: var(--radius); padding: 8px 14px; cursor: pointer; }
+.button.secondary { background: var(--color-brand-tint); color: var(--color-brand-strong); }
+table { width: 100%; border-collapse: collapse; margin-top: 12px; }
+th { text-align: left; background: var(--color-surface-alt); color: var(--color-text-muted); }
+th, td { padding: 8px 10px; border-bottom: 1px solid var(--color-border); }
+.tag { padding: 2px 8px; border-radius: 999px; color: #ffffff; font-size: 12px; }
+.tag.ok { background: var(--color-success); }
+.tag.late { background: var(--color-warning); }
+.tag.failed { background: var(--color-danger); }

tests/fixtures/c-web-existing-frontend/web/css/theme.css

@@ -0,0 +1,33 @@
+/* Field Ops Portal theme. Every colour and font the site uses comes from here. */
+:root {
+  --color-brand: #0f766e;
+  --color-brand-strong: #115e59;
+  --color-brand-tint: #ccfbf1;
+  --color-bg: #f8fafc;
+  --color-surface: #ffffff;
+  --color-surface-alt: #f1f5f9;
+  --color-border: #e2e8f0;
+  --color-text: #0f172a;
+  --color-text-muted: #64748b;
+  --color-success: #15803d;
+  --color-warning: #b45309;
+  --color-danger: #b91c1c;
+  --font-sans: "Trebuchet MS", "Segoe UI", sans-serif;
+  --font-heading: Georgia, "Times New Roman", serif;
+  --radius: 6px;
+}
+
+[data-theme="dark"] {
+  --color-brand: #0d9488;
+  --color-brand-strong: #134e4a;
+  --color-brand-tint: #134e4a;
+  --color-bg: #0b1120;
+  --color-surface: #111827;
+  --color-surface-alt: #1f2937;
+  --color-border: #334155;
+  --color-text: #e2e8f0;
+  --color-text-muted: #94a3b8;
+  --color-success: #22c55e;
+  --color-warning: #f59e0b;
+  --color-danger: #ef4444;
+}

tests/fixtures/c-web-existing-frontend/web/index.html

@@ -0,0 +1,26 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width,initial-scale=1">
+<title>Field Ops Portal</title>
+<link rel="stylesheet" href="css/theme.css">
+<link rel="stylesheet" href="css/app.css">
+</head>
+<body>
+<header class="topbar">
+  <h1>Field Ops Portal</h1>
+  <nav><a href="index.html">Jobs</a><button class="button secondary" id="theme-btn">Dark mode</button></nav>
+</header>
+<main class="page">
+  <section class="card">
+    <h2>Today's jobs</h2>
+    <table>
+      <thead><tr><th>Job</th><th>Site</th><th>Status</th></tr></thead>
+      <tbody id="jobs"></tbody>
+    </table>
+  </section>
+</main>
+<script src="js/app.js"></script>
+</body>
+</html>

tests/fixtures/c-web-existing-frontend/web/js/app.js

@@ -0,0 +1,15 @@
+// Field Ops Portal: job list and dark toggle.
+const JOBS = [
+  { job: "J-101", site: "North depot", status: "Done", tag: "ok" },
+  { job: "J-102", site: "Harbour road", status: "Late", tag: "late" },
+  { job: "J-103", site: "West yard", status: "Failed", tag: "failed" },
+];
+
+document.getElementById("jobs").innerHTML = JOBS.map(
+  (j) => `<tr><td>${j.job}</td><td>${j.site}</td><td><span class="tag ${j.tag}">${j.status}</span></td></tr>`
+).join("");
+
+document.getElementById("theme-btn").onclick = () => {
+  const root = document.documentElement;
+  root.dataset.theme = root.dataset.theme === "dark" ? "light" : "dark";
+};

tests/page_check/conftest.py

@@ -4,6 +4,8 @@ through window.__pyMsg, and assert on what is visible.
 Page under test: set PAGE_CHECK_HTML to a generated dashboard.html. Without it, the
 no-AI template is filled with TEST_FILL. Every test runs in light, dark and narrow mode.
 The page sees a fake Qt bridge: each slot call lands in window.__calls as [slot, ...args].
+PAGE_CHECK_WIRED=1: the page is wired to a bot (SAMPLE_DATA off), so sample-data cases skip.
+PAGE_CHECK_REPLAY: a JSON-lines file of envelopes a real bot run produced (bot_runner.py's dry run).
 """
 import json
 import os
@@ -33,6 +35,14 @@ window.QWebChannel = function (_transport, ready) {
 };
 """
 MODES = {"light": (1280, 820, False), "dark": (1280, 820, True), "narrow": (800, 900, False)}
+WIRED = os.environ.get("PAGE_CHECK_WIRED") == "1"
+
+
+@pytest.fixture
+def sample_data():
+    """Use on cases that need the built-in sample data; they skip on a bot-wired page."""
+    if WIRED:
+        pytest.skip("page is wired to a bot, so it has no sample data")
 
 
 @pytest.fixture(scope="session")
@@ -40,6 +50,8 @@ def page_url(tmp_path_factory):
     if os.environ.get("PAGE_CHECK_HTML"):
         return Path(os.environ["PAGE_CHECK_HTML"]).resolve().as_uri()
     html = re.sub(r"\{\{(\w+)\}\}", lambda m: TEST_FILL[m[1]], TEMPLATE.read_text(encoding="utf-8"))
+    if WIRED:
+        html = html.replace("const SAMPLE_DATA = true", "const SAMPLE_DATA = false")
     out = tmp_path_factory.mktemp("page") / "dashboard.html"
     out.write_text(html, encoding="utf-8")
     return out.as_uri()

tests/page_check/test_bot_run.py

@@ -0,0 +1,84 @@
+"""A bot run as the page sees it: status, step and log envelopes in order, from a real bot
+run (PAGE_CHECK_REPLAY, the JSON lines bot_runner.py's dry run prints) or a built-in one."""
+import json
+import os
+import re
+from pathlib import Path
+
+import pytest
+from conftest import WIRED
+from playwright.sync_api import expect
+from test_contract import colour_of, kpi, open_tab
+
+LOG_COLOURS = {"info": "blue", "success": "green", "warn": "amber", "error": "red"}
+DOT_COLOURS = {"ready": "green", "running": "amber", "done": "green", "error": "red"}
+
+
+def built_in_run(steps):
+    run = [{"event": "status", "data": {"state": "running", "msg": "Running…"}}]
+    for i, label in enumerate(steps):
+        run.append({"event": "step", "data": {"label": label, "pct": round((i + 1) / len(steps) * 100)}})
+        run.append({"event": "log", "data": {"msg": f"Finished {label}.", "type": "success"}})
+    run.insert(4, {"event": "log", "data": {"msg": "ERROR: portal timed out, retrying", "type": "error"}})
+    return run + [{"event": "status", "data": {"state": "done", "msg": "Completed"}}]
+
+
+def recorded_run():
+    path = os.environ.get("PAGE_CHECK_REPLAY")
+    return [json.loads(x) for x in Path(path).read_text(encoding="utf-8-sig").splitlines() if x.strip()] if path else None
+
+
+def expect_status(page, state, msg):
+    # The status indicator has no role of its own, so it's found by its documented ids.
+    expect(page.locator("#st-text")).to_have_text(msg or state)
+    assert colour_of(page.locator("#st-dot"), "backgroundColor") == DOT_COLOURS[state], state
+    run = page.get_by_role("button", name="▶ Run", exact=True)
+    expect(run).to_be_disabled() if state == "running" else expect(run).to_be_enabled()
+
+
+def test_bot_run_shows_status_steps_and_log(page, push):
+    steps = page.evaluate("STEPS")
+    run = recorded_run() or built_in_run(steps)
+    open_tab(page, "Run")
+    expect_status(page, "ready", "System ready")
+    items = page.get_by_role("list", name="Steps").get_by_role("listitem")
+    log, last_step = page.get_by_role("log"), -1
+    for envelope in run:
+        event, d = envelope["event"], envelope["data"]
+        push(event, d)
+        if event == "status":
+            expect_status(page, d["state"], d.get("msg"))
+        elif event == "step":
+            assert d["label"] in steps, f"step label {d['label']!r} is not one of the page's STEPS {steps}"
+            idx = steps.index(d["label"])
+            assert idx >= last_step, f"progress went back from {steps[last_step]!r} to {d['label']!r}"
+            last_step = idx
+            expect(page.get_by_text(f"{d['pct']}%", exact=True)).to_be_visible()
+            if d["pct"] >= 100:
+                for i in range(len(steps)):
+                    expect(items.nth(i)).to_have_text(re.compile(r"^\s*✓"))
+            else:
+                expect(items.nth(idx)).to_have_attribute("aria-current", "step")
+        elif event == "log":
+            line = log.get_by_text(d["msg"], exact=True).last
+            expect(line).to_be_visible()
+            assert colour_of(line) == LOG_COLOURS[d["type"]], d["msg"]
+    assert any(e["event"] == "step" for e in run), "the run never moved the progress bar"
+
+
+def test_failed_run_shows_error_status(page, push):
+    push("status", {"state": "running", "msg": "Running…"})
+    expect_status(page, "running", "Running…")
+    push("status", {"state": "error", "msg": "Failed (exit code 1)"})
+    expect_status(page, "error", "Failed (exit code 1)")
+
+
+@pytest.mark.skipif(not WIRED, reason="only for a page wired to a bot (PAGE_CHECK_WIRED=1)")
+def test_wired_page_sends_its_actions_to_the_bot(page):
+    calls = lambda: page.evaluate("window.__calls")  # noqa: E731
+    assert ["load_dashboard"] in calls()
+    kpi(page, "Total batches", 0)                     # no sample batches on a wired page
+    page.get_by_role("button", name="▶ Run", exact=True).click()
+    assert ["start_automation"] in calls()
+    open_tab(page, "Report")
+    assert ["load_latest_report"] in calls()

tests/page_check/test_contract.py

@@ -1,6 +1,7 @@
 """No-AI contract cases: events in, visible result out (see templates/contract.md)."""
 import re
 
+import pytest
 from playwright.sync_api import expect
 
 
@@ -146,6 +147,7 @@ def expect_sample_dashboard(page):
     kpi(page, "Total batches", n)
 
 
+@pytest.mark.usefixtures("sample_data")
 def test_no_bot_page_runs_on_sample_data(page):
     """No bot yet: the page answers its own data actions, so it works on day one."""
     expect_sample_dashboard(page)
@@ -162,6 +164,7 @@ def test_no_bot_page_runs_on_sample_data(page):
     expect(run).to_be_enabled()
 
 
+@pytest.mark.usefixtures("sample_data")
 def test_plain_browser_first_open_shows_sample_data(browser, page_url):
     pg = browser.new_page()
     pg.goto(page_url)

tests/test_bot_runner.py

@@ -0,0 +1,112 @@
+"""Bot wiring self-check (templates/bot_runner.py): which page events each raw bot line makes."""
+import importlib.util
+import os
+import sys
+import time
+from pathlib import Path
+
+import pytest
+
+RUNNER = Path(__file__).resolve().parents[1] / "rpa-dashboard-no-ai" / "templates" / "bot_runner.py"
+
+
+@pytest.fixture
+def runner():
+    spec = importlib.util.spec_from_file_location("bot_runner", RUNNER)
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    mod.STEP_MARKERS = [("[step 1]", "Initializing", 10), ("[step 2]", "Login", 40),
+                        ("[step 3]", "Process items", 70), ("[all done]", "Completed", 100)]
+    mod.FRIENDLY_RULES = [("[login] done", "Logged in.", "success"), ("[login]", "Logging in...", "info"),
+                          ("could not save receipt", "Could not save the receipt.", "error")]
+    return mod
+
+
+def steps(runner, line):
+    return [d for e, d in runner.events_for(line) if e == "step"]
+
+
+def test_step_marker_moves_progress(runner):
+    assert steps(runner, "[step 2] Opening the login page") == [{"label": "Login", "pct": 40}]
+    assert steps(runner, "[STEP 3] Processing 12 items") == [{"label": "Process items", "pct": 70}]
+
+
+def test_common_word_does_not_move_progress(runner):
+    assert steps(runner, "Login page loaded slowly") == []
+    assert steps(runner, "Completed loading the config") == []
+
+
+def test_first_step_marker_wins(runner):
+    assert steps(runner, "[step 1] retry after [step 3] timed out") == [{"label": "Initializing", "pct": 10}]
+
+
+def logs(runner, line):
+    return [d for e, d in runner.events_for(line) if e == "log"]
+
+
+def test_friendly_rule_rewrites_the_line_and_first_rule_wins(runner):
+    assert logs(runner, "[login] done in 2.1s") == [{"msg": "Logged in.", "type": "success"}]
+    assert logs(runner, "[LOGIN] sending credentials") == [{"msg": "Logging in...", "type": "info"}]
+
+
+def test_unmatched_non_error_lines_are_hidden(runner):
+    for line in ["Loading config from settings.ini", "[step 2] Opening the login page", "warning: slow page"]:
+        assert logs(runner, line) == [], line
+
+
+@pytest.mark.parametrize("line", [
+    "ERROR: portal timed out", "Traceback (most recent call last):", "ValueError: bad date",
+    "Exception: boom", "FATAL disk full", "Login failed for user 3"])
+def test_unmatched_error_line_is_always_shown_raw(runner, line):
+    assert logs(runner, line) == [{"msg": line, "type": "error"}]
+
+
+def test_matched_error_line_shows_its_friendly_message(runner):
+    assert logs(runner, "ERROR could not save receipt 42") == [{"msg": "Could not save the receipt.", "type": "error"}]
+
+
+def test_error_on_a_step_line_moves_progress_and_is_shown(runner):
+    line = "[step 3] ERROR item 2 rejected"
+    assert runner.events_for(line) == [("step", {"label": "Process items", "pct": 70}),
+                                       ("log", {"msg": line, "type": "error"})]
+
+
+def run_bot(runner, tmp_path, script):
+    """Run a fake bot through runner.run(); return [(seconds since start, event, data)]."""
+    bot = tmp_path / "fake_bot.py"
+    bot.write_text(script, encoding="utf-8")
+    runner.BOT_CMD, runner.BOT_CWD, runner.RAW_LOG = [sys.executable, str(bot)], tmp_path, tmp_path / "raw.log"
+    t0, sent = time.monotonic(), []
+    runner.run(lambda event, data: sent.append((time.monotonic() - t0, event, data)))
+    return sent
+
+
+def test_run_streams_bot_output_live_from_a_child_process(runner, tmp_path):
+    sent = run_bot(runner, tmp_path, "import os, time\n"
+                   "print('[step 1] pid', os.getpid())\n"
+                   "print('[login] done')\n"
+                   "time.sleep(1)\n"
+                   "print('[all done] ✓ 3 items')\n")
+    events = [(e, d) for _, e, d in sent]
+    assert events == [("status", {"state": "running", "msg": "Running…"}),
+                      ("step", {"label": "Initializing", "pct": 10}),
+                      ("log", {"msg": "Logged in.", "type": "success"}),
+                      ("step", {"label": "Completed", "pct": 100}),
+                      ("status", {"state": "done", "msg": "Completed"})]
+    assert sent[3][0] - sent[1][0] > 0.5, "lines must reach the page while the bot runs, not at exit"
+    raw = (tmp_path / "raw.log").read_text(encoding="utf-8")
+    assert "[login] done" in raw and "✓ 3 items" in raw            # raw lines kept for audit
+    assert f"pid {os.getpid()}" not in raw                              # the bot ran in its own process
+
+
+def test_run_ends_in_error_when_the_bot_fails(runner, tmp_path):
+    sent = run_bot(runner, tmp_path, "print('[step 1] start')\nraise SystemExit(3)\n")
+    assert sent[-1][1:] == ("status", {"state": "error", "msg": "Failed (exit code 3)"})
+
+
+def test_run_ends_in_error_when_the_bot_cannot_start(runner, tmp_path):
+    runner.BOT_CMD, runner.BOT_CWD, runner.RAW_LOG = ["no-such-bot-xyz"], tmp_path, tmp_path / "raw.log"
+    sent = []
+    runner.run(lambda event, data: sent.append((event, data)))
+    assert sent[-2][0] == "log" and sent[-2][1]["type"] == "error"
+    assert sent[-1] == ("status", {"state": "error", "msg": "Could not start the bot"})

tests/test_detect_frontend.py

@@ -0,0 +1,105 @@
+"""Frontend detection: where an existing frontend is, its stack and its colour tokens."""
+import importlib.util
+import json
+import subprocess
+import sys
+from pathlib import Path
+
+DETECT = Path(__file__).resolve().parents[1] / "rpa-dashboard-no-ai" / "templates" / "detect_frontend.py"
+spec = importlib.util.spec_from_file_location("detect_frontend", DETECT)
+detect_frontend = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(detect_frontend)
+
+
+def project(tmp_path, files):
+    for name, text in files.items():
+        (tmp_path / name).parent.mkdir(parents=True, exist_ok=True)
+        (tmp_path / name).write_text(text, encoding="utf-8")
+    return tmp_path
+
+
+def cli(root):
+    return subprocess.run([sys.executable, str(DETECT), str(root)], capture_output=True, text=True, check=True).stdout
+
+
+def test_no_frontend_when_only_tooling_and_installed_skills_have_html(tmp_path):
+    root = project(tmp_path, {
+        "main.py": "print('[step 1] Login')\n",
+        "node_modules/pkg/index.html": "<style>:root{--x:#123456}</style>",
+        ".venv/lib/site.html": "<p>",
+        ".claude/skills/rpa-dashboard-no-ai/templates/dashboard.html": "<style>body{--accent:#3d9bd0}</style>",
+        "dist/index.html": "<p>",
+    })
+    assert detect_frontend.detect(root) == []
+    assert cli(root).strip() == "No existing frontend found."
+
+
+FIXTURE_C = Path(__file__).resolve().parent / "fixtures" / "c-web-existing-frontend"
+
+
+def test_plain_html_site_reports_location_stack_light_and_dark_tokens():
+    [f] = detect_frontend.detect(FIXTURE_C)
+    assert f["path"] == "web/"
+    assert f["stack"] == "plain HTML (web)"
+    light, dark = f["blocks"]
+    assert (light["file"], light["selector"], light["dark"]) == ("web/css/theme.css", ":root", False)
+    assert light["tokens"]["--color-brand"] == "#0f766e"
+    assert light["tokens"]["--font-sans"] == '"Trebuchet MS", "Segoe UI", sans-serif'
+    assert (dark["selector"], dark["dark"]) == ('[data-theme="dark"]', True)
+    assert dark["tokens"]["--color-brand"] == "#0d9488"
+
+    out = cli(FIXTURE_C)
+    first = out.splitlines()[0]
+    assert first.startswith("Frontend found at `web/`, stack `plain HTML (web)`, colours `--color-brand #0f766e,")
+    assert 'fonts `"Trebuchet MS", "Segoe UI", sans-serif`' in first
+    assert "web/css/theme.css" in out and '[data-theme="dark"]' in out
+
+
+def test_react_app_is_one_frontend_with_its_media_query_dark_tokens(tmp_path):
+    root = project(tmp_path, {
+        "server.py": "from fastapi import FastAPI\n",
+        "frontend/package.json": json.dumps({"dependencies": {"react": "^19.0.0", "react-dom": "^19.0.0"},
+                                             "devDependencies": {"vite": "^6.0.0"}}),
+        "frontend/index.html": '<div id="root"></div><script type="module" src="/src/main.jsx"></script>',
+        "frontend/src/index.css": ":root { --primary: 222.2 47.4% 11.2%; --radius: .5rem }\n"
+                                  "@media (prefers-color-scheme: dark) { :root { --primary: 210 40% 98% } }",
+        "frontend/node_modules/react/index.html": "<p>",
+    })
+    [f] = detect_frontend.detect(root)
+    assert (f["path"], f["stack"]) == ("frontend/", "React (Vite, web)")
+    light, dark = f["blocks"]
+    assert (light["file"], light["tokens"]["--primary"], light["dark"]) == ("frontend/src/index.css", "222.2 47.4% 11.2%", False)
+    assert (dark["selector"], dark["tokens"], dark["dark"]) == (
+        "@media (prefers-color-scheme: dark) :root", {"--primary": "210 40% 98%"}, True)
+    assert "colours `--primary 222.2 47.4% 11.2%`" in cli(root)
+
+
+def test_vue_app_reads_component_styles_and_tailwind_theme(tmp_path):
+    root = project(tmp_path, {
+        "package.json": json.dumps({"dependencies": {"vue": "^3.5.0"}, "devDependencies": {"tailwindcss": "^3.4.0"}}),
+        "tailwind.config.js": "module.exports = { theme: { extend: { colors: { brand: '#e11d48', 'brand-dark': \"#9f1239\" } } } }",
+        "src/App.vue": "<template><p>{{ msg }}</p></template>\n<style>:root { --surface: #ffffff; }</style>",
+    })
+    [f] = detect_frontend.detect(root)
+    assert (f["path"], f["stack"]) == ("./", "Vue (Tailwind, web)")
+    blocks = {b["file"]: b for b in f["blocks"]}
+    assert blocks["src/App.vue"]["tokens"] == {"--surface": "#ffffff"}
+    assert blocks["tailwind.config.js"]["tokens"] == {"brand": "#e11d48", "brand-dark": "#9f1239"}
+    assert "brand #e11d48" in cli(root).splitlines()[0]
+
+
+def test_pyqt_web_view_is_a_desktop_frontend(tmp_path):
+    host = "from PyQt6.QtWebEngineWidgets import QWebEngineView\nview = QWebEngineView()\n"
+    root = project(tmp_path / "file", {
+        "app.py": host + "view.load(QUrl.fromLocalFile('ui/page.html'))\n",
+        "bot.py": "print('[step 1] Login')\n",
+        "ui/page.html": "<style>:root { --accent: #2563eb; }</style>",
+    })
+    [f] = detect_frontend.detect(root)
+    assert (f["path"], f["stack"]) == ("ui/", "PyQt web view (desktop, host `app.py`)")
+    assert f["blocks"][0]["tokens"] == {"--accent": "#2563eb"}
+
+    inline = project(tmp_path / "inline", {"main.py": host + "view.setHtml('<style>body{--accent:#16a34a}</style><p>Hi</p>')\n"})
+    [f] = detect_frontend.detect(inline)
+    assert (f["path"], f["stack"]) == ("main.py", "PyQt web view (desktop, host `main.py`)")
+    assert f["blocks"][0]["tokens"] == {"--accent": "#16a34a"}

tests/test_templates.py

@@ -9,7 +9,8 @@ ROOT = Path(__file__).resolve().parents[1]
 HOOK_RULES = "E9,F63,F7,F82,F811"  # same rule set as the PostToolUse lint hook
 
 
-@pytest.mark.parametrize("template", ["rpa-dashboard-no-ai/templates/bridge.py"])
+@pytest.mark.parametrize("template", ["rpa-dashboard-no-ai/templates/bridge.py",
+                                      "rpa-dashboard-no-ai/templates/bot_runner.py"])
 def test_template_passes_lint_hook_unfilled(template):
     ruff = shutil.which("ruff") or pytest.skip("ruff not on PATH")
     r = subprocess.run([ruff, "check", "--select", HOOK_RULES, "--no-cache", str(ROOT / template)],