AI desktop path: plain-HTML Review and Cost tabs over the Qt bridge, gate in Python

ai_sections.html pastes into the no-AI dashboard.html; ai_bridge.py adds one
ai_request slot that hands every AI contract request (incl. GET /roi) to the
review backend's dispatch(). Desktop page check reruns the web review and cost
cases plus a tampered-page gate case. Eval fixture e-pyqt-ai added.

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

tests/README.md

@@ -29,6 +29,12 @@ uv run --with pytest --with playwright pytest tests
   by-hand assumptions), plus every no-AI case. Tests set run and review state on the stub
   directly (the `stub` fixture). To check a generated dashboard folder instead, set
   `PAGE_CHECK_AI_DIR=path/to/dashboard`. Needs npm on PATH, else it skips.
+- `page_check_ai_desktop/`: **Seam 1, AI desktop page.** The no-AI `dashboard.html` with
+  `ai_sections.html` pasted in, loaded from `file://` with a fake Qt bridge whose
+  `ai_request` slot goes to `server_stub.dispatch()` in this process (what `ai_bridge.py`
+  does). Runs the AI web page's review and cost cases and the no-AI cases unchanged, plus
+  a tampered page calling the slot directly (still refused). To check a generated folder,
+  set `PAGE_CHECK_AI_DESKTOP_DIR=path/to/dashboard`; `PAGE_CHECK_WIRED=1` as above.
 - `test_pricing.py`: the AI cost function (normal, long-context, thinking tokens,
   unknown model).
 - `test_reference_scan.py`: no patient data, internal IPs, credentials or keys in any
@@ -45,7 +51,9 @@ uv run --with pytest --with playwright pytest tests
   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.
   An `"ai": True` entry (`d-ai-extraction`) expects the AI skill's React starter and
-  runs `page_check_ai/` on the folder it built.
+  runs `page_check_ai/` on the folder it built. An `"ai_desktop": True` entry
+  (`e-pyqt-ai`) expects the desktop AI page and runs `page_check/` (with the bot replay)
+  and `page_check_ai_desktop/` on it.
   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.

tests/evals/run_eval.py

@@ -80,6 +80,17 @@ FIXTURES = {
         "page_has": ["--accent:#ff3049"],
         "ai": True,
     },
+    # (e) PyQt bot with an LLM extraction call: the AI skill's desktop path, no web server.
+    "e-pyqt-ai": {
+        "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,
+        "ai_desktop": True,
+    },
 }
 # 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*$"
@@ -171,6 +182,11 @@ def main(fixture):
             html += css.read_text(encoding="utf-8") if css.exists() else ""
             checks["AI path: review starter and server stub built"] = all(
                 (pages[0].parent / f).exists() for f in ["server_stub.py", "bands.py", "src/components/Review.tsx"])
+        if cfg.get("ai_desktop"):  # the no-AI page with the plain-HTML AI sections, hosted by ai_bridge.py
+            host = pages[0].with_name("ai_bridge.py")
+            checks["AI desktop path: sections, ai_bridge and review backend built"] = 'id="ai-review-tab"' in html and all(
+                pages[0].with_name(f).exists() for f in ["ai_bridge.py", "server_stub.py", "bands.py", "pricing.py"])
+            checks["no placeholders left in ai_bridge.py"] = host.exists() and "{{" not in host.read_text(encoding="utf-8")
         shutil.copy(pages[0], results / f"{fixture}.dashboard.html")
         checks["no placeholders left"] = "{{" not in html
         if cfg.get("brand"):
@@ -186,8 +202,11 @@ def main(fixture):
             env.update(bot_checks(project, html, checks, results / f"{fixture}.run.jsonl"))
         if cfg.get("ai"):
             env["PAGE_CHECK_AI_DIR"] = str(pages[0].parent)
-        check_dir = ROOT / "tests" / ("page_check_ai" if cfg.get("ai") else "page_check")
-        pc = subprocess.run([sys.executable, "-m", "pytest", str(check_dir), "-q"],
+        check_dirs = [ROOT / "tests" / ("page_check_ai" if cfg.get("ai") else "page_check")]
+        if cfg.get("ai_desktop"):
+            env["PAGE_CHECK_AI_DESKTOP_DIR"] = str(pages[0].parent)
+            check_dirs.append(ROOT / "tests" / "page_check_ai_desktop")
+        pc = subprocess.run([sys.executable, "-m", "pytest", *map(str, check_dirs), "-q"],
                             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:]]

tests/fixtures/e-pyqt-ai/README.md

@@ -0,0 +1,11 @@
+# Invoice intake bot
+
+A desktop RPA bot. It reads each scanned invoice in `inbox/` with an LLM
+(`extractor.py`) and queues the fields for a person to review.
+The operator window will be a PyQt6 app.
+
+Run the bot on its own:
+
+```
+python -m bot
+```

tests/fixtures/e-pyqt-ai/bot.py

@@ -0,0 +1,31 @@
+"""Invoice intake bot: picks up scanned invoices and extracts their fields with an LLM.
+Start it with:  python -m bot"""
+import time
+from pathlib import Path
+
+INBOX = Path(__file__).with_name("inbox")
+
+
+def say(line):
+    print(line, flush=True)
+    time.sleep(0.2)
+
+
+def main():
+    say("[step 1] Initializing")
+    docs = sorted(INBOX.glob("*.pdf"))
+    say(f"[inbox] {len(docs)} invoices waiting")
+    say("[step 2] Extracting fields")
+    for i, doc in enumerate(docs, 1):
+        try:
+            from extractor import extract_invoice  # the LLM call
+            rows = extract_invoice(doc.read_bytes(), "application/pdf")
+            say(f"[extract] {doc.name}: {len(rows)} fields ({i}/{len(docs)})")
+        except Exception as e:  # one bad document must not stop the batch
+            say(f"ERROR: extraction failed for {doc.name}: {type(e).__name__}")
+    say("[step 3] Queueing for review")
+    say(f"[all done] {len(docs)} invoices processed")
+
+
+if __name__ == "__main__":
+    main()

tests/fixtures/e-pyqt-ai/extractor.py

@@ -0,0 +1,34 @@
+"""The LLM extraction call: one scanned invoice in, its fields out, each with word scores."""
+import json
+
+from google import genai
+from google.genai import types
+
+MODEL = "gemini-2.5-flash"
+FIELDS = {  # field name -> mandatory
+    "Invoice number": True,
+    "Invoice date": True,
+    "Vendor": True,
+    "PO number": False,
+    "Due date": True,
+    "Total": True,
+}
+PROMPT = (
+    "Read this invoice. Return JSON: a list of {field, value, word_scores}, one per field in "
+    + ", ".join(FIELDS)
+    + ". word_scores is your 0-1 legibility score for each word of the value. Use an empty "
+    "value and no scores when a field isn't on the page."
+)
+
+
+def extract_invoice(document: bytes, mime_type: str) -> list[dict]:
+    client = genai.Client()  # credentials come from the environment
+    response = client.models.generate_content(
+        model=MODEL,
+        contents=[types.Part.from_bytes(data=document, mime_type=mime_type), PROMPT],
+        config=types.GenerateContentConfig(response_mime_type="application/json"),
+    )
+    rows = json.loads(response.text)
+    for row in rows:
+        row["mandatory"] = FIELDS.get(row["field"], False)
+    return rows

tests/fixtures/e-pyqt-ai/inbox/invoice-2201.pdf

@@ -0,0 +1,2 @@
+%PDF-1.4
+% sample invoice placeholder

tests/fixtures/e-pyqt-ai/inbox/invoice-2202.pdf

@@ -0,0 +1,2 @@
+%PDF-1.4
+% sample invoice placeholder

tests/fixtures/e-pyqt-ai/requirements.txt

@@ -0,0 +1,3 @@
+PyQt6
+PyQt6-WebEngine
+google-genai

tests/page_check_ai_desktop/conftest.py

@@ -63,7 +63,7 @@ def site(tmp_path_factory):
     sections = (AI / "desktop" / "ai_sections.html").read_text(encoding="utf-8")
     out = tmp_path_factory.mktemp("desktop")
     (out / "dashboard.html").write_text(html.replace("</body>", sections + "\n</body>"), encoding="utf-8")
-    for f in ["server_stub.py", "bands.py"]:
+    for f in ["server_stub.py", "bands.py", "pricing.py"]:
         (out / f).write_bytes((AI / "web" / f).read_bytes())
     return out
 

tests/page_check_ai_desktop/test_ai_desktop.py

@@ -16,6 +16,14 @@ from test_ai_review import (  # noqa: E402,F401
     test_page_x_of_y_updates_while_running,
 )
 from test_ai_review import FIELDS, FLAGGED, open_review  # noqa: E402
+from test_ai_cost import (  # noqa: E402,F401
+    cost_page,
+    test_by_hand_panel_is_labelled_assumptions_and_recomputes,
+    test_coverage_pill_counts_priced_of_all_documents,
+    test_month_breakdown_groups_runs_by_month,
+    test_runs_show_tokens_and_cost_and_unpriced_is_not_zero,
+    test_spend_tiles_sum_the_priced_runs,
+)
 
 sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "page_check"))
 from test_contract import (  # noqa: E402,F401