feat: build step 4 — /mediation/, /arbitration/, /med-arb/; source ADRIC's rules

Three pages, five in the build, zero JavaScript. /arbitration/ carries §4's
paired-disclosure condition on four surfaces and Q39's struck universal appears
in no form. /med-arb/ meets the procedural-fairness objection at the level of
process design and ships deliberately without Pouya's own protocol commitments,
which are Q54.

docs/01 directed the mediation page to name the "ADRIC Model Mediation Rules".
No such document exists — 0 occurrences across all four of ADRIC's rules pages
against 10 for "National Mediation Rules"; "Model" belongs to the Model Dispute
Resolution Clause inside the rules. Caught only because R14 requires the source
before the claim. docs/reference/adric-rules.md + adric-extract/ carry it, with
the digest drift measured rather than assumed: the HTML changes per request, the
text extracts are byte-stable, so the extracts are the artefact.

Four review passes, 21 defects, and the pattern was mine: I wrote the Q54 gate
into the page and then breached it four times, then round 2 found two survivors
of round 1's own fixes and one defect round 1's fix created. Also removed a
<title> naming a practised role §4 does not grant, a habitual presupposing awards
issued, and a claim about what ADRIC's rules permit that my own reference doc
says is unsupported.

Two instrument failures caught before they became conclusions: touch targets
measured over file:// with no CSS loaded (uniform 18px, including on a .btn with
a 44px floor), and a schema.org validator call that parsed nothing and returned
0 warnings for everything. Both re-run with the instrument validated first.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0148NztQskLKKApP5SzAA78e

docs/01-architecture.md

@@ -203,13 +203,29 @@ neutral.
 
 1. What the service is; the neutral's role stated plainly.
 2. **Formats:** full-day, half-day, shuttle, remote, hybrid.
-3. **Rules:** ADRIC Model Mediation Rules, or a bespoke protocol agreed by the
-   parties.
+3. **Rules:** the **ADRIC National Mediation Rules**, or a bespoke protocol
+   agreed by the parties.
+   ⚠️ *This item read "ADRIC Model Mediation Rules" until 2026-08-28 and that is
+   not the name of anything ADRIC publishes* — **0 occurrences** across all four
+   of its rules pages, against **10** of "National Mediation Rules" on the
+   document's own page. "Model" belongs to the **Model Dispute Resolution
+   Clause**, a contract clause inside the rules. Sourced and reproducible:
+   `docs/reference/adric-rules.md` Finding 1. The spec would have put a wrong
+   institutional name on a public page, which is the `Chartered
+   Mediator-Arbitrator` shape a second time — caught here only because R14 sent
+   the fetch out before the copy was written.
 4. **What parties should bring** — briefs, documents, authority to settle.
 5. **Confidentiality and without-prejudice framing.**
 6. Practice areas → `/practice/*`.
 7. Fees → `/fees/`. Booking → `/contact/`.
 
+⚠️ **This page carries no first-person conduct commitment, and that is
+deliberate.** How Pouya handles caucus material, and what he undertakes about a
+bespoke protocol, are claims about his practice with no §4 row. Two of them
+shipped here for one pass and were removed. Drafted for his ruling as **Q54(d)**
+and **(e)**; until he rules, the Confidentiality and Rules sections describe what
+an *agreement* settles, not what he promises.
+
 ### `/arbitration/`
 
 **Job:** the same, for arbitration — and to state the Q.Arb position honestly.
@@ -220,6 +236,13 @@ neutral.
    appointments.
 2. **Tracks:** documents-only, expedited, full hearing.
 3. **Rules:** ADRIC, ADR Chambers, ad hoc.
+   ⚠️ *`/arbitration/` as built names the **ADRIC Arbitration Rules** (new
+   edition effective 1 March 2025, with an arbitrator appointment protocol) and
+   "ad hoc, or whatever the contract names". It does **not** name ADR
+   Chambers*: nothing in `docs/reference/` sources what rules ADR Chambers
+   publishes, and `docs/07-fees.md` cites it only for published **fee ranges**,
+   which is a different claim (R14). Name it on the page once a source is
+   committed.
 4. Awards — form, reasoning, timing.
 5. **Credentialing status, stated plainly.** The Q.Arb pathway **commenced
    August 2026**; the page says so in those words. *"In progress" was the
@@ -238,6 +261,13 @@ neutral.
    same one: an edit that was not re-read against the register.)*
 6. Fees, booking.
 
+⚠️ **No first-person conduct commitment on this page either.** The Rules and
+Awards sections say what a process and an award *should* settle and contain, not
+what Pouya undertakes to do — **Q54(e)** and **(f)** are drafted and unruled, and
+both shipped here in the first person for one pass. The `<title>` names a
+**service**, never "Sole Arbitrator": §4 grants exactly one practised role and it
+is "Mediator".
+
 ### `/med-arb/`
 
 **Job:** own a term few Canadian neutrals explain well, and frame the C.Med-Arb
@@ -245,9 +275,31 @@ endpoint.
 **Search intent:** `med-arb Canada`, `what is med-arb`, `arb-med`.
 
 1. What Med-Arb is; how it differs from Arb-Med.
+   ⚠️ *As built, the page flags the confusion and does **not define arb-med***.
+   No source for a definition of arb-med is committed, and this repository does
+   not publish a definition of a third party's process from recall (R14). The
+   page says only that the two are one syllable apart, that the processes are
+   not interchangeable, and that a reader should check which one their contract
+   names — against the rule set the contract adopts, not against this page. **It
+   states no differentia at all**, because on a page that defines med-arb as
+   mediation→arbitration, "the phases run in a different order" *is* a
+   definition of arb-med by inversion. That wording shipped for one pass and
+   `claims-auditor` caught it. Define arb-med when a source is committed, or add
+   an **Arb-Med** row to `AGENTS.md` §11 — not before.
 2. The procedural fairness objection, addressed head-on rather than elided.
+   ⚠️ *The page answers it at the level of **process design** — what a med-arb
+   agreement has to settle before the mediation phase begins. It does **not**
+   carry Pouya's own protocol commitments, which are claims about his practice
+   with no §4 row.* Three are drafted for his approval in **Q54**; the section is
+   incomplete until he rules.
 3. When it fits and when it does not.
 4. The C.Med-Arb designation and why it is the practice's stated endpoint.
+5. **The ADRIC Med-Arb Rules**, which this spec did not mention and which exist:
+   a published rule set, put to ADRIC's membership in 2019, drafted for domestic
+   commercial disputes and designed to work with its Mediation and Arbitration
+   Rules. Sourced: `docs/reference/adric-rules.md` Finding 2. Quote ADRIC's own
+   framing rather than paraphrasing it, and **keep its superlatives inside the
+   quotation marks** — Finding 5 lists the two not to lift.
 
 This page is a strong candidate for the best-performing page on the site.
 Search demand exists, competition is thin, and it maps exactly to the brand's