clearotron 0.2.1 → 0.2.3

package/driver/skills/prelim-search/report-prose.md

@@ -19,6 +19,88 @@ writes lives in that stage's own file — the finding sentence and the grouped r
 [synthesis-rules.md](synthesis-rules.md), the card and section shape in
 [delivery-contract.md](delivery-contract.md). What is below is general and is stated only here.
 
+## Two registers, and the reader of the first one is not a lawyer
+
+**The reader is a lawyer who layers advice on top — and that lawyer's client reads the same page.** The
+band, the summary, the basis line and the one-liners are the whole product for the second reader, and
+they were the hardest text on it: single sentences of seventy-odd words in the vocabulary of the
+profession.
+
+So the page has two registers, and which one a line is written in is decided by whether the reader has
+to open something to see it.
+
+**DEFAULT-VISIBLE TEXT CARRIES NO LEGAL OR ENGINE VOCABULARY.** Default-visible means anything a reader
+meets before opening a fold: the summary and the opening line, the basis for the rating, the points for
+and against and what would soften them, the one sentence under each name, the four answers, the
+reviewer's notes, the caveats, the coverage rows and the lines saying what needs a decision. Ordinary
+nouns. One idea per sentence. **No visible sentence over 25 words.** The conclusion first.
+
+Which stored fields those are is not prose's business and is not listed here — `DEFAULT_VISIBLE_FIELDS`
+in `driver/plain-register.mjs` names them for both products, in one place, so a field renamed once does
+not leave a doctrine file quietly describing a shape that no longer exists.
+
+**INSIDE A FOLD THE PROFESSION'S VOCABULARY IS ALLOWED**, where a plain word would lose precision: the
+card's detail paragraph, provenance, the drill bullets. Even there a term is glossed at first use on the
+page. Nothing is removed from the drill and the workbook is unchanged.
+
+### The swaps, as worked examples rather than a banned list
+
+A list of forbidden words is not the mechanism and must never become one. These are what the plain form
+sounds like; the instruction is always to rewrite the sentence, never to substitute the word and leave
+the rest of a lawyer's sentence standing around it.
+
+| written for a lawyer | what the reader needs |
+|---|---|
+| proprietor | owner |
+| subsisting | live |
+| senior | earlier, or came first |
+| specification | goods list |
+| DELPH-formative | names built on DELPH- |
+| prevail | win |
+| citable prior rights | earlier marks the office can raise against you |
+| vulnerable to a non-use attack | could be cancelled for not being used |
+| on the record as it stands | on what we found |
+| the marks-and-goods comparison | same name, same goods |
+| the confusion comparison meets on every limb | same name, same goods, same shops |
+| belt-and-braces classes | extra classes |
+| dispatch, instructed | the request, what was asked |
+| lane | class, or channel — whichever is meant |
+| chunk | never; it is an engine word |
+
+### The standard, in full sentences
+
+A basis line, rewritten: *"ORBIT is already the name of two satellite-tracking apps on the same app
+stores, and of an established satellite-communications company. Any of them would likely win a dispute
+over this name for this software. The word is a weak mark for these goods, which is why this is High and
+not Very High."*
+
+An answer, rewritten: *"Blocked. An identical earlier mark for the same goods stops registration in
+Switzerland, the EU and the US. Below that, earlier DELPH- marks in EU class 5 and US class 42 can be
+raised against the application."*
+
+A card's detail — allowed the fold's vocabulary, still written plainly: *"Same name, same goods, and
+their Swiss filing came first in every territory we searched. We see no argument against it."*
+
+A note, rewritten: *"Ask the client whether it already uses ORBIT. Its own earlier use would change the
+picture and is not reflected here."*
+
+**Shortening by dropping the reason is not the fix.** The "why" stays, in plain words. A visible line
+that is short because it no longer says why is worse than the long one it replaced.
+
+### What reads this, and what does not
+
+**No delivery gate fails on any of it, and no report is ever marked for it.** The reviewing stage that
+already rejects engine vocabulary applies this test to the default-visible fields and hands back a
+rewrite, in the same pass and the same voice it uses for everything else. A hit is a sentence rewritten.
+It is never a disclosure to the client, never a run failure, and it moves no band, no evidence and
+nothing that is searched — this is presentation.
+
+The reviewer is helped by `driver/plain-register.mjs`, which offers the plain form beside the term it
+found and never decides anything. **It cannot flag the mark the run is clearing**: half of these words
+are ordinary English and several — PREVAIL, SENIOR, SPECIFICATION — are perfectly good trademarks, so
+every term the run is about is removed from the text before it is read. A check that could not tell a
+mark from the profession's vocabulary would put its noise on the one report where it matters most.
+
 ## Fact · assessment · prescription
 
 Three different things, and only two of them belong in a report.

package/driver/skills/prelim-search/risk-framework-demo.manifest.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "framework_key": "demo",
   "title": "Demo Brand Owner risk framework",
-  "source_deck": "Demo Brand Owner risk framework, doc 50 shape",
+  "source_deck": "Demo Brand Owner risk framework, authored in-house for the demonstration account",
   "entity_label": "Demo Brand Owner",
   "bands": [
     { "label": "Very High", "tone": "severe" },

package/driver/skills/prelim-search/risk-framework-triage.manifest.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "framework_key": "house-triage",
   "title": "House knockout triage ladder (Stage 0)",
-  "source_deck": "Ported from the interactive knockout-searches skill's 5-tier rating system (SKILL.md rating table + calibration rules), doc 50 shape",
+  "source_deck": "Cordillera house triage scale for knockout screening, authored in-house; five rating tiers",
   "entity_label": "the client",
   "bands": [
     { "label": "Very High", "tone": "severe" },

package/driver/skills/prelim-search/risk-framework.manifest.json

@@ -2,7 +2,7 @@
   "schema_version": 1,
   "framework_key": "house-default",
   "title": "Generic default risk framework",
-  "source_deck": "Generic house default — IP Risk Assessment Framework.pptx (Privileged & Confidential), completed by the reviewing lawyer 2026-08-31; supersedes the 2026-07-05 transcription (doc 50), which was partial",
+  "source_deck": "Cordillera house risk framework, authored in-house and reviewed by counsel; 2026-08-31 revision",
   "entity_label": "the company",
   "bands": [
     { "label": "Very High", "tone": "severe" },

package/driver/skills/prelim-search/synthesis-rules.md

@@ -14,7 +14,7 @@ Across the synthesis, two postures are load-bearing:
 
 3. **Optics is annotation, not a rating.** Partner-relationship, channel-conflict, PR, and reputational concerns — however prominently `matter-context` or the manifest raise them — are surfaced as client-facing annotations (the separate PR / reputational section below; a "relationship-level heads-up"). PR is a separate category, **never rated on the framework's bands**, and an existing business relationship is an *either-way* practical factor, not a band multiplier. The rating answers what the framework in force asks — anchored in *if this party sued us, would they win?*, set by the consumer-confusion read (mark-as-whole × G&S). Never let optics/PR/partner/size move the band; annotate beside it.
 
-4. **The framework in force rates the matter (doc 50).** Every run reads exactly one risk framework — **the customer's own framework if the profile has one on file, else the house default. Nothing in between.** That framework is the customer's own legal judgment written down: reason each conflict *with* it — its band definitions (Legal position × Practical position × Potential outcomes), or its matrix where it states one — and state the rating as **its band word, verbatim**. It is a reasoning authority, never a lookup table: no numeric thresholds, no score-to-band mapping, no vocabulary borrowed from another framework. **The band follows the words** — state the likelihood in plain words first (*"the prior owner is likely to win, though credible defences exist"*), then give the band those words require under the framework's own definitions; the prose read and the band are one judgment and may not disagree. Where the framework states **ceilings or matrix mappings, honour them exactly as written** — they are that framework's own anti-escalation mechanism, and no practical or optics factor lifts a rating past what its stated method yields. A conflict the client **clearly wins with no material risk is not a rated conflict at all** (most frameworks' lowest band still describes *real* residual risk — nuisance claims, weak strategic complaints, registration obstacles — never clear wins): surface it unrated as commercial awareness if worth knowing, else omit it. Voice the client side as the framework's **entity** names it (*"the company"*, *"Zephyr/Nimbus/Kestrel"*, *"Aurora Interactive"*). The three-question discipline stays: **legal risk** (*would they win?* — the confusion read net of merits defences), **practical risk** (*would they act?* — enforcement reality), and **impact** (*if they did, what follows?*). The framework's band definitions integrate the first two — reason both, in that order, through its own terms. **Impact stays client-surfaced, never rating-moving**: name the consequences for the client to weigh (we do not conclude acceptability), beside the band, exactly as before.
+4. **The framework in force rates the matter (doc 50).** Every run reads exactly one risk framework — **the customer's own framework if the profile has one on file, else the house default. Nothing in between.** That framework is the customer's own legal judgment written down: reason each conflict *with* it — its band definitions (Legal position × Practical position × Potential outcomes), or its matrix where it states one — and state the rating as **its band word, verbatim**. It is a reasoning authority, never a lookup table: no numeric thresholds, no score-to-band mapping, no vocabulary borrowed from another framework. **The band follows the words** — state the likelihood in plain words first (*"the prior owner is likely to win, though credible defences exist"*), then give the band those words require under the framework's own definitions; the prose read and the band are one judgment and may not disagree. Where the framework states **ceilings or matrix mappings, honour them exactly as written** — they are that framework's own anti-escalation mechanism, and no practical or optics factor lifts a rating past what its stated method yields. A conflict the client **clearly wins with no material risk is not a rated conflict at all** (most frameworks' lowest band still describes *real* residual risk — nuisance claims, weak strategic complaints, registration obstacles — never clear wins): surface it unrated as commercial awareness if worth knowing, else omit it. Voice the client side as the framework's **entity** names it (*"the company"*, *"Coastline/Nimbus/Kestrel"*, *"Foxglade Interactive"*). The three-question discipline stays: **legal risk** (*would they win?* — the confusion read net of merits defences), **practical risk** (*would they act?* — enforcement reality), and **impact** (*if they did, what follows?*). The framework's band definitions integrate the first two — reason both, in that order, through its own terms. **Impact stays client-surfaced, never rating-moving**: name the consequences for the client to weigh (we do not conclude acceptability), beside the band, exactly as before.
 
 ## Contents
 

package/driver/skills/prelim-search/template-formatting.md

@@ -1,4 +1,4 @@
-# Prelim Template — HTML Formatting Spec
+# Clearotron Template — HTML Formatting Spec
 
 > **THIS FILE IS HALF LIVE, AND THE HALVES HAVE DIFFERENT READERS. Check which half you are in before
 > you trust a line.**

package/driver/skills/prelim-search/templates/email/generic.md

@@ -20,7 +20,7 @@ The email body has these blocks, in this order:
 
 > "Hi [first name from request],
 >
-> Prelim for [mark name] complete — findings below; full audit Excel attached."
+> Clearotron for [mark name] complete — findings below; full audit Excel attached."
 
 (For internal test runs, use "Hi [forwarder first name]" and add a one-line context note: "v[N] test run — replied to you only, not forwarded to [client].")
 

package/driver/skills/prelim-search/worked-examples.md

@@ -5,7 +5,7 @@
   synthesis-rules.md.
 -->
 
-# Prelim synthesis — gold-standard worked examples
+# Clearotron synthesis — gold-standard worked examples
 
 ## Contents
 

package/driver/skills/prelim-variants/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: prelim-variants
-description: Shared strategy + variant generation for the v3 preliminary trademark search workflow. **Invoked exclusively by the `prelim-search` orchestrator** as the first stage of any v3 prelim run — do not call directly. Classifies the proposed mark into one of six analytical archetypes, derives a risk theory from that classification, then generates the variant set whose axes are shaped by the archetype. Emits a markdown variant manifest consumed by both common-law (`prelim-common-law`) and register (`prelim-register`) execution skills.
+description: Shared strategy + variant generation for the v3 preliminary trademark search workflow. **Invoked exclusively by the `prelim-search` orchestrator** as the first stage of any v3 clearotron run — do not call directly. Classifies the proposed mark into one of six analytical archetypes, derives a risk theory from that classification, then generates the variant set whose axes are shaped by the archetype. Emits a markdown variant manifest consumed by both common-law (`prelim-common-law`) and register (`prelim-register`) execution skills.
 ---
 
 ## Contents
@@ -27,7 +27,7 @@ Companion files:
 
 ## Trigger
 
-Called by `prelim-search` at the start of any prelim run. Not invoked directly.
+Called by `prelim-search` at the start of any clearotron run. Not invoked directly.
 
 ## Model
 
@@ -125,8 +125,8 @@ LUMENGARDE is the distinctive anchor — risk concentrates on coined-word axes a
 
 **A variant VALUE is a mark term, never a note about one.** A parenthetical, sentence punctuation
 (`—`, `;`) or a space-flanked slash makes it a label, and a label dispatched verbatim returns a
-confident zero over marks that exist — a nil search that reads as a clean. Write `ZEPHYR`, not
-`ZEPHYR (root)`; the rationale column is where the note belongs. The compiler refuses annotated values
+confident zero over marks that exist — a nil search that reads as a clean. Write `COASTLINE`, not
+`COASTLINE (root)`; the rationale column is where the note belongs. The compiler refuses annotated values
 whatever their length, so a two-word one is caught the same way a long one is.
 
 **If a value genuinely IS a mark carrying that punctuation** — a device mark recorded with its Vienna
@@ -178,7 +178,7 @@ silently narrows what was searched, and the deferred row is the honest outcome.
 
 ### Watchlists
 
-- **Aggressive enforcers:** Nordwave, Aurora Interactive
+- **Aggressive enforcers:** Nordwave, Foxglade Interactive
 - **Major brand owners:** Sony, Aureon, Nintendo, HP, Activision, Take-Two, EA
 - **Competitors:** Epic Games, Valve, Unity, Riot Games
 

package/driver/stage-context.mjs

@@ -92,7 +92,7 @@ const DECLARED_KIND = {
     // — the placement form is CONTEXT, and deliberately NOT a freshness input. The driver writes it
     // before dispatch and rewrites it after every judgement (the union runs on each one), so it is always
     // newer than the md the seat just wrote — and adding it to stageInputs would make the largest stage in
-    // the run read stale on every resume and re-dispatch itself. 's ruling exactly: the fix is a
+    // the run read stale on every resume and re-dispatch itself. That ruling exactly: the fix is a
     // second view, not a wider freshness list.
     placementForm: ["driver-side",
       "written by the driver before dispatch and re-unioned on every judgement; the prompt names the path because the seat writes its selections there"],

package/driver/stages-knockout.mjs

@@ -5,7 +5,7 @@
 // kept in its OWN table: the knockout lane is a different product shape (a 5–15 mark triage batch), and
 // its stages must never leak into the clearance STAGE_ORDER. New-named stages get [] MCP tool groups
 // automatically (gather-config prefix map — the matter-frame precedent), so frame/assess run lean.
-import { existsSync } from "node:fs";
+import { existsSync, readFileSync } from "node:fs";
 import { join } from "node:path";
 import { driverDir } from "../shared/driver-dir.mjs";   //
 import { validators as koValidators } from "./verify-knockout.mjs";
@@ -19,6 +19,30 @@ export { kebab };   // one definition (search-policy) — re-exported for the la
 const lines = (...xs) => xs.filter(Boolean).join("\n");
 const reads = (skillReads) => `First, read and follow exactly: ${skillReads.join(", ")}.`;
 
+/**
+ * One line per owner the driver looked up, for the assess dispatch (tracker issue 276).
+ *
+ * BOTH OUTCOMES ARE NAMED, and that is the point. A row whose search answered gets its payload path; a
+ * row whose search did NOT answer says so in the dispatch itself. Listing only the answered ones would
+ * leave the seat unable to tell "nobody searched this owner" from "the search found nothing", and those
+ * two license completely different reads — the second is a fact about the owner's visibility, the first
+ * is a gap the seat would fill by inferring from the name, which is the defect this whole issue is about.
+ *
+ * Returns [] when the lane did not run or the store is unreadable, so the dispatch simply omits the block
+ * rather than naming a path that is not there.
+ */
+export function ownerCheckLines(K) {
+  let doc = null;
+  try { doc = existsSync(K.ownerChecks) ? JSON.parse(readFileSync(K.ownerChecks, "utf8")) : null; } catch { doc = null; }
+  const checks = Array.isArray(doc?.checks) ? doc.checks : [];
+  return checks.map((c) => {
+    const who = `${c.owner} (proprietor of a filing for ${c.mark})`;
+    return c.ok && c.payloadFile
+      ? `- ${who}: ${join(K.runDir, "research", c.payloadFile)}`
+      : `- ${who}: THE SEARCH RETURNED NOTHING. Say so in the read; do not infer the trade from the name.`;
+  });
+}
+
 // ── Paths (knockout-own; beside the standard _driver sidecars) ───────────────────────────────────────
 export function koPaths(runDir) {
   return {
@@ -39,10 +63,15 @@ export function koPaths(runDir) {
     // rows were left exactly as they were rather than gaining a matching marker: their shape is pinned
     // byte-for-byte by register-count.test.mjs, and a discriminator only one side needs is enough.
     registerRecords: driverDir(runDir, "register-records.json"),
+    // The scoped owner lookups this run owes its promoted filings, and their receipts (tracker issue
+    // 276). Both under `_driver/` because both are the DRIVER's own measurement of a call it made — the
+    // rule stated fourteen lines above. The seat reads the payloads under research/, never these.
+    ownerChecks: driverDir(runDir, "owner-checks.json"),
+    ownerCheckLedger: driverDir(runDir, "owner-check.jsonl"),
     researchDir: join(runDir, "research"),
     research: (markKebab) => join(runDir, "research", `${markKebab}.md`),
     sweepLedger: driverDir(runDir, "knockout-sweep.jsonl"),
-    // 's SHAPE, APPLIED: the WORK MOVES OUT OF THE GUARDED TREE — the hook is never weakened.
+    // That SHAPE, APPLIED: the WORK MOVES OUT OF THE GUARDED TREE — the hook is never weakened.
     //
     // This chunk is a MODEL OUTPUT, and it sat under `_driver/` in flat contradiction of the rule stated
     // fourteen lines above: those files "are the driver's own measurements, NEVER a model's output". So
@@ -289,6 +318,28 @@ export const KO_STAGES = {
       existsSync(K.registerRecords)
         ? `THE REGISTER FILINGS THIS RUN ALREADY FETCHED — ${K.registerRecords}. Real records, retrieved before you started: owner, jurisdiction, status, classes, dates. Read them and WEIGH them for the marks you are rating. A registration on this list is evidence about the name it names — treat its owner, its scope and its vulnerability the way the firm-wide reasoning tells you to (revocability above the lowest band; an enforcer's portfolio profile; a crowd as a mitigant under its gating precondition). What you may NOT do is describe the lane that fetched them — see the coverage rule below.`
         : "",
+      // ── WHAT THE OWNER ACTUALLY SELLS, ALREADY SEARCHED (tracker issue 276) ────────────────────────
+      //
+      // The defect this closes is not that the seat lacked an instruction — it is that the seat had no
+      // way to know. It was handed an owner's NAME and its class numbers and nothing else, so a read
+      // about what that owner sells could only ever be an inference from the string. The driver now runs
+      // the scoped query before this stage and hands the answer over.
+      //
+      // ORDERED, NOT OFFERED. Naming a payload the seat may read is what produces "read and not applied,
+      // no refusal" — a rule that names a downstream effect rather than the field the seat writes. This
+      // names the field: the read on that filing's registerReads row.
+      //
+      // AND THE NEGATIVE CASE IS ORDERED TOO, because it is the one that produced the original defect:
+      // where the lookup did not answer, the honest sentence is that it did not, NOT a fresh inference
+      // from the owner's name dressed as a finding.
+      ownerCheckLines(K).length
+        ? [
+          `WHAT THESE OWNERS ACTUALLY SELL — the driver ran ONE scoped web search per promoted filing's proprietor BEFORE this stage, so you are not guessing from the company name. Payloads:`,
+          ...ownerCheckLines(K),
+          `USE THEM. When you write a registerReads row for one of these filings, your "read" must state what the owner actually sells ACCORDING TO THAT PAYLOAD, not what the company's name suggests and not what its class numbers imply. An owner's name is not evidence of its trade. A company name that reads as a line of business is a guess that happens to land sometimes, and the run where it lands is indistinguishable from the run where it does not — which is the reasoning this rule exists to stop.`,
+          `WHERE A PAYLOAD SAYS THE SEARCH FOUND NOTHING, say that plainly in the read — "a search for the proprietor's trade returned nothing" — and reason from the register record alone. Do NOT substitute an inference from the owner's name for the answer the search did not give. The report prints the source line itself, from the driver's own record of the call, so you never type a URL and never need to.`,
+        ].join("\n")
+        : "",
       // ── THE READ REACHES THE PAGE ────────────────────────────────────────────
       //
       // Until now nothing this seat concluded about an INDIVIDUAL filing could reach a reader. A filing
@@ -301,7 +352,7 @@ export const KO_STAGES = {
       // a finding with no register evidence. Omitting either field is always safe: the card keeps its
       // neutral line, which describes the card and is true.
       existsSync(K.registerRecords)
-        ? `WHEN YOU WEIGH ONE OF THOSE FILINGS, SAY SO BY ITS OWN ID — copy "recordId" verbatim from the file above. "registerReads" on the MARK: rows of {recordId, read} for a filing you weighed that did NOT become a findings[] record; "read" is what you concluded about THAT filing — whether it bears on the rating and why — and it prints on that filing's card in the reader's own report. "weighedFilings" on a FINDING: the recordIds whose evidence your reasoning for that conflict actually used, because the report derives that finding's source labelling from it. Both are optional and both are joined against the filings you were given, so an id we do not hold is refused by name. A filing you did not weigh simply gets no row: do not invent a read to fill one, and never write "not weighed" as a read.`
+        ? `WHEN YOU WEIGH ONE OF THOSE FILINGS, SAY SO BY ITS OWN ID — copy "recordId" verbatim from the file above. "registerReads" on the MARK: rows of {recordId, read, band?} for a filing you weighed that did NOT become a findings[] record; "read" is what you concluded about THAT filing — whether it bears on the rating and why — and it prints on that filing's card in the reader's own report. "band" is OPTIONAL and is your rating of THAT filing on its own, in the framework's band words: send it whenever you formed a view on the filing itself, because a registered right left unbanded is the only card on the page with no rating while softer uses beside it carry one, which reads as though the registration mattered least. Omit it and your read still prints, claiming no rating. "weighedFilings" on a FINDING: the recordIds whose evidence your reasoning for that conflict actually used, because the report derives that finding's source labelling from it. Both are optional and both are joined against the filings you were given, so an id we do not hold is refused by name. A filing you did not weigh simply gets no row: do not invent a read to fill one, and never write "not weighed" as a read.`
         : "",
       `A DEGRADED mark's row must carry degraded:true and the purple "Manual verification recommended"`,
       `note; a mark WITH a payload must never claim degraded (the validator joins both against the disk).`,
@@ -414,7 +465,7 @@ export const KO_STAGES = {
       `IT IS THE SHORTER DIGEST ABOVE THE PER-MARK ASSESSMENTS, not a rival to them. A reader opens this`,
       `to decide which name to read about; the mark's own page is where the full read lives. Keep it`,
       `tighter than any one mark's assessment.`,
-      // ── THE RETURN IS A CALL, NOT A FILE (, item B) ────────────────────────────
+      // ── THE RETURN IS A CALL, NOT A FILE (item B) ────────────────────────────
       //
       // THE DISPATCH NAMES NO PATH, and on this stage that is not merely the house pattern. This seat
       // spent 2026-08 writing its chunk through a Bash redirect because the Write tool was already