AI cost/ROI page: pricing table, cost per call, Cost tab, ROI endpoint

- templates/web/pricing.py: pricing table with source and as-of date; cost_for_call
  (input rate + (output + thinking) at output rate, long-context above threshold;
  unknown model raises naming the known models).
- Cost tab: coverage pill, total/this-month/tokens tiles, month-by-month table,
  per-run tokens and cost ("not priced", never $0), by-hand panel with editable
  assumptions labelled as such.
- Contract: RoiRun and GET /roi; optional GET /models and POST /runs/{id}/retry.
- SKILL.md: cost page wiring, model picker and retry-on-other-model as optional sections.
- Tests: test_pricing.py self-check, page_check_ai/test_ai_cost.py.

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

rpa-dashboard-ai/templates/web/server_stub.py

@@ -18,6 +18,7 @@ from pathlib import Path
 from urllib.parse import urlparse
 
 from bands import BANDS, field_band, needs_review
+from pricing import PRICING_AS_OF, PRICING_SOURCE, cost_for_call
 
 HERE = Path(__file__).resolve().parent
 API = "/api"  # same as API_BASE in index.html
@@ -34,6 +35,7 @@ SAMPLE_FIELDS = [
     ("Tax", "196.00", [], False),
 ]
 RUNS, ROWS = {}, {}
+ROI_RUNS = []  # [{job_id, document, created_at, model, input_tokens, output_tokens, thinking_tokens}]
 _next_row = [1]
 
 
@@ -56,6 +58,16 @@ def reset():
     ROWS.clear()
     put_run("job-1002", "invoice-1002.pdf", SAMPLE_FIELDS, status="running", pages_done=1, pages_total=3)
     put_run("job-1001", "invoice-1001.pdf", SAMPLE_FIELDS, pages_total=2, pages_done=2)
+    ROI_RUNS.clear()
+    now = time.time()
+    for i, (model, tokens) in enumerate([("gemini-2.5-flash", (21_000, 1_800, 900)),
+                                         ("gemini-2.5-flash", (18_500, 1_600, 0)),
+                                         ("gemini-2.5-pro", (240_000, 3_000, 2_500)),
+                                         ("gemini-2.5-flash-lite", (22_000, 1_700, 0)),
+                                         ("gemini-2.5-flash", (None, None, None))]):  # usage not recorded
+        ROI_RUNS.append({"job_id": f"job-{900 + i}", "document": f"invoice-{900 + i}.pdf",
+                         "created_at": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime(now - i * 12 * 864e2)),
+                         "model": model, **dict(zip(("input_tokens", "output_tokens", "thinking_tokens"), tokens))})
 
 
 def run_view(job_id):
@@ -104,6 +116,18 @@ def approve(job_id, body):
     return 200, {"ok": True}
 
 
+def roi(body):
+    """Cost per run. total_cost is null when the run recorded no token usage: unpriced, never zero.
+    An unknown model is an error (500 naming the known models), never a cost of zero."""
+    try:
+        runs = [{**r, "total_cost": None if r["input_tokens"] is None else
+                 cost_for_call(r["model"], r["input_tokens"], r["output_tokens"], r["thinking_tokens"] or 0)}
+                for r in ROI_RUNS]
+    except ValueError as e:
+        return 500, {"detail": str(e)}
+    return 200, {"runs": runs, "pricing": {"source": PRICING_SOURCE, "as_of": PRICING_AS_OF}}
+
+
 def document(job_id, body):
     """A stand-in for the source document. A real backend returns the PDF or page image."""
     lines = "".join(f'<text x="48" y="{150 + i * 46}" font-size="20">{escape(f)}: {escape(v)}</text>'
@@ -122,6 +146,7 @@ ROUTES = [
     ("PATCH", r"/review/(\d+)", patch_row),
     ("POST", r"/runs/([\w-]+)/verify-remaining", verify_remaining),
     ("POST", r"/runs/([\w-]+)/approve", approve),
+    ("GET", r"/roi", roi),
     ("POST", r"/set-dark", lambda body: (200, {})),
 ]