feat(review): add gate.copycat.mode config scaffold for copycat detection

Parses and threads a new gate.copycat.mode (off/warn/label/block) and
gate.copycat.minScore end-to-end through the manifest, effective-settings
resolver, and OpenAPI schema -- config-as-code only, no DB column. The
similarity/containment detection engine that would consume this config
does not exist yet; this field is deliberately inert (parsed and threaded,
never read by any decision path) so an operator's .gittensory.yml can
already declare intent ahead of the detection engine landing in a later PR.

Author: JSONbored

.gittensory.yml.example

@@ -179,6 +179,20 @@ gate:
     # the gate. Bool. Default: false.
     aiAdvisory: false
 
+  # Copycat/plagiarism detection (#1969). CURRENTLY INERT — this config is parsed
+  # and threaded end-to-end, but the containment/similarity detection engine that
+  # would actually compute a copycat finding does not exist yet (tracked as
+  # separate, later PRs against #1969). Setting this today has no observable
+  # effect; it exists so an operator's config can already declare intent.
+  copycat:
+    # off | warn | label | block. Default: off. A dedicated 4-tier scale (not the
+    # shared off/advisory/block used elsewhere) — a further "strikes" escalation
+    # beyond block reuses the existing cross-repo banned-contributors ledger.
+    mode: off
+    # Containment/similarity threshold at/above which mode acts, once the
+    # detection engine exists. Number 0–100, or null for the engine default.
+    minScore: null
+
   # Oversized-PR gate. A PR at/above EITHER the file-count or line-count threshold
   # (engine defaults, not configurable here) gets a manual-review HOLD finding —
   # never a hard blocker; mode only turns this hold signal on or off.

apps/gittensory-ui/public/openapi.json

@@ -9304,6 +9304,19 @@
               "advisory",
               "block"
             ]
+          },
+          "copycatGateMode": {
+            "type": "string",
+            "enum": [
+              "off",
+              "warn",
+              "label",
+              "block"
+            ]
+          },
+          "copycatGateMinScore": {
+            "type": "number",
+            "nullable": true
           }
         },
         "required": [

config/examples/gittensory.full.yml

@@ -192,6 +192,20 @@ gate:
     # the gate. Bool. Default: false.
     aiAdvisory: false
 
+  # Copycat/plagiarism detection (#1969). CURRENTLY INERT — this config is parsed
+  # and threaded end-to-end, but the containment/similarity detection engine that
+  # would actually compute a copycat finding does not exist yet (tracked as
+  # separate, later PRs against #1969). Setting this today has no observable
+  # effect; it exists so an operator's config can already declare intent.
+  copycat:
+    # off | warn | label | block. Default: off. A dedicated 4-tier scale (not the
+    # shared off/advisory/block used elsewhere) — a further "strikes" escalation
+    # beyond block reuses the existing cross-repo banned-contributors ledger.
+    mode: off
+    # Containment/similarity threshold at/above which mode acts, once the
+    # detection engine exists. Number 0–100, or null for the engine default.
+    minScore: null
+
   # Oversized-PR gate. A PR at/above EITHER the file-count or line-count threshold
   # (engine defaults, not configurable here) gets a manual-review HOLD finding —
   # never a hard blocker; mode only turns this hold signal on or off.

packages/gittensory-engine/src/focus-manifest.ts

@@ -173,8 +173,25 @@ export type FocusManifestGateConfig = {
    *  hallucination can one-shot-close a structurally-clean PR) as an explicit, per-repo, documented
    *  trade-off — never the default. */
   aiJudgmentBlockersMode: "gate" | "advisory" | null;
+  /** `gate.copycat.mode` (#1969): off|warn|label|block, off by default. Config-as-code only -- no DB column
+   *  or dashboard toggle. Deliberately a DEDICATED 4-value enum, not the shared `GateRuleMode` tri-state: the
+   *  issue's tiered response is warn -> label -> block -> strikes, where "strikes" is a separate escalation
+   *  action (reusing the existing cross-repo banned-contributors ledger once wired) rather than a 5th mode
+   *  value. THIS FIELD IS CURRENTLY INERT -- the similarity/containment detection engine that would actually
+   *  compute a copycat finding does not exist yet (tracked as later, separate PRs against #1969); parsing and
+   *  threading this config end-to-end first proves the plumbing and lets an operator's `.gittensory.yml`
+   *  already declare intent without waiting on the detection engine. */
+  copycatMode: CopycatGateMode | null;
+  /** `gate.copycat.minScore` (#1969): containment/similarity score (0-100) at/above which `copycatMode` acts.
+   *  null (unset) ⇒ the (also currently inert) engine's own default threshold once it exists. Same 0-100
+   *  clamp-and-round normalization as `slopMinScore`/`readinessMinScore` above. */
+  copycatMinScore: number | null;
 };
 
+/** `gate.copycat.mode` (#1969) -- see {@link FocusManifestGateConfig.copycatMode}'s doc comment for why this
+ *  is a dedicated enum rather than the shared `GateRuleMode`. */
+export type CopycatGateMode = "off" | "warn" | "label" | "block";
+
 // The converged per-PR review features a self-host operator toggles PER-REPO under `features:` in the private
 // `.gittensory.yml`. Each feature ALSO has a GLOBAL env flag (GITTENSORY_REVIEW_*) that stays a master
 // kill-switch (the feature never runs when its env flag is off, regardless of this block). See
@@ -857,6 +874,8 @@ const EMPTY_GATE_CONFIG: FocusManifestGateConfig = {
   claCheckRunAppSlug: null,
   expectedCiContexts: null,
   aiJudgmentBlockersMode: null,
+  copycatMode: null,
+  copycatMinScore: null,
 };
 
 const EMPTY_FEATURES_CONFIG: FocusManifestFeaturesConfig = {
@@ -1142,6 +1161,11 @@ function parseGateConfig(value: JsonValue | undefined, warnings: string[]): Focu
   if (slop !== undefined && slop !== null && slopRecord === undefined) {
     warnings.push(`Manifest gate field "gate.slop" must be a mapping; ignoring it.`);
   }
+  const copycat = record.copycat;
+  const copycatRecord = copycat !== null && typeof copycat === "object" && !Array.isArray(copycat) ? (copycat as Record<string, JsonValue>) : undefined;
+  if (copycat !== undefined && copycat !== null && copycatRecord === undefined) {
+    warnings.push(`Manifest gate field "gate.copycat" must be a mapping; ignoring it.`);
+  }
   const size = record.size;
   const sizeRecord = size !== null && typeof size === "object" && !Array.isArray(size) ? (size as Record<string, JsonValue>) : undefined;
   if (size !== undefined && size !== null && sizeRecord === undefined) {
@@ -1189,6 +1213,8 @@ function parseGateConfig(value: JsonValue | undefined, warnings: string[]): Focu
     claCheckRunAppSlug: parsePublicSafeText(claRecord?.checkRunAppSlug, "gate.cla.checkRunAppSlug", warnings),
     expectedCiContexts: normalizeOptionalStringList(record.expectedCiContexts, "gate.expectedCiContexts", warnings),
     aiJudgmentBlockersMode: normalizeOptionalEnum(record.aiJudgmentBlockers, "gate.aiJudgmentBlockers", ["gate", "advisory"] as const, warnings),
+    copycatMode: normalizeOptionalEnum(copycatRecord?.mode, "gate.copycat.mode", ["off", "warn", "label", "block"] as const, warnings),
+    copycatMinScore: normalizeOptionalScore(copycatRecord?.minScore, "gate.copycat.minScore", warnings),
   };
   // #2266: the flag is parsed, clamped, and threaded end-to-end, but the gate evaluator never reads it — a
   // maintainer who sets it to true believing it softens a blocker for newcomers gets no such effect. Surface
@@ -1232,7 +1258,9 @@ function parseGateConfig(value: JsonValue | undefined, warnings: string[]): Focu
     gate.claCheckRunName !== null ||
     gate.claCheckRunAppSlug !== null ||
     gate.expectedCiContexts !== null ||
-    gate.aiJudgmentBlockersMode !== null;
+    gate.aiJudgmentBlockersMode !== null ||
+    gate.copycatMode !== null ||
+    gate.copycatMinScore !== null;
   return gate;
 }
 
@@ -1308,6 +1336,12 @@ export function gateConfigToJson(gate: FocusManifestGateConfig): JsonValue {
   }
   if (gate.expectedCiContexts !== null) out.expectedCiContexts = gate.expectedCiContexts as JsonValue;
   if (gate.aiJudgmentBlockersMode !== null) out.aiJudgmentBlockers = gate.aiJudgmentBlockersMode;
+  if (gate.copycatMode !== null || gate.copycatMinScore !== null) {
+    const copycat: Record<string, JsonValue> = {};
+    if (gate.copycatMode !== null) copycat.mode = gate.copycatMode;
+    if (gate.copycatMinScore !== null) copycat.minScore = gate.copycatMinScore;
+    out.copycat = copycat;
+  }
   return out;
 }
 

packages/gittensory-engine/src/types/manifest-deps-types.ts

@@ -171,6 +171,14 @@ export type RepositorySettings = {
   /** `gate.cla.checkRunAppSlug`: the trusted GitHub App slug that must have produced `claCheckRunName`. Required
    *  for check-run detection so contributor-controlled same-name runs cannot satisfy a blocking CLA gate. */
   claCheckRunAppSlug?: string | null | undefined;
+  /** Copycat/plagiarism detection (#1969). `off` (default/absent) = no check; `warn`/`label`/`block` are
+   *  escalating tiers a future containment/similarity engine would act on. Config-as-code only — no DB column
+   *  or dashboard toggle; set via `.gittensory.yml gate.copycat.mode`. CURRENTLY INERT: parsed and threaded
+   *  end-to-end, but no detection engine reads it yet. */
+  copycatGateMode?: "off" | "warn" | "label" | "block" | undefined;
+  /** `gate.copycat.minScore`: containment/similarity score (0-100) at/above which `copycatGateMode` would act,
+   *  once the detection engine exists. Config-as-code only, alongside {@link copycatGateMode}. */
+  copycatGateMinScore?: number | null | undefined;
   /** `gate.expectedCiContexts` (#selfhost-ci-verification): maintainer-declared CI check/status context names to
    *  treat as required when GitHub branch protection returns no readable required-status-checks (unconfigured,
    *  or a 403 from a token lacking `administration:read` — common for GitHub App installations). Merged with any

src/openapi/schemas.ts

@@ -651,6 +651,8 @@ export const RepositorySettingsSchema = z
     claCheckRunName: z.string().nullable().optional(),
     claCheckRunAppSlug: z.string().nullable().optional(),
     expectedCiContexts: z.array(z.string()).optional(),
+    copycatGateMode: z.enum(["off", "warn", "label", "block"]).optional(),
+    copycatGateMinScore: z.number().nullable().optional(),
     gateDryRun: z.boolean().optional(),
     premergeContentRecheck: z.boolean().optional(),
     requireFreshRebaseWindowMinutes: z.number().int().positive().nullable().optional(),

src/signals/focus-manifest.ts

@@ -469,6 +469,8 @@ function applyGateConfigOverrides(effective: RepositorySettings, gate: FocusMani
   if (gate.claCheckRunName !== null) effective.claCheckRunName = gate.claCheckRunName;
   if (gate.claCheckRunAppSlug !== null) effective.claCheckRunAppSlug = gate.claCheckRunAppSlug;
   if (gate.expectedCiContexts !== null) effective.expectedCiContexts = gate.expectedCiContexts;
+  if (gate.copycatMode !== null) effective.copycatGateMode = gate.copycatMode;
+  if (gate.copycatMinScore !== null) effective.copycatGateMinScore = gate.copycatMinScore;
 }
 
 /**

src/types.ts

@@ -586,6 +586,12 @@ export type BountyRecord = {
 
 export type GateRuleMode = "off" | "advisory" | "block";
 
+/** `gate.copycat.mode` (#1969) -- a dedicated 4-value enum rather than the shared {@link GateRuleMode}
+ *  tri-state, since the issue's tiered response is warn -> label -> block -> strikes (where "strikes" is a
+ *  separate escalation action reusing the existing cross-repo banned-contributors ledger, not a 5th mode
+ *  value). See {@link RepositorySettings.copycatGateMode}'s doc comment for the currently-inert status. */
+export type CopycatGateMode = "off" | "warn" | "label" | "block";
+
 /** Review-check publish surface (#2852). Controls ONLY whether/how the "Gittensory Orb Review Agent" check-run
  *  is created/updated -- never the underlying gate evaluation, disposition, comments, labels, audit, or
  *  autonomous merge/close, all of which run identically in every mode (the autonomous decision engine already
@@ -726,6 +732,17 @@ export type RepositorySettings = {
   /** `gate.cla.checkRunAppSlug`: the trusted GitHub App slug that must have produced `claCheckRunName`. Required
    *  for check-run detection so contributor-controlled same-name runs cannot satisfy a blocking CLA gate. */
   claCheckRunAppSlug?: string | null | undefined;
+  /** Copycat/plagiarism detection (#1969). `off` (default/absent) = no check; `warn`/`label`/`block` are
+   *  escalating tiers a future containment/similarity engine would act on (`block` additionally hard-blocks;
+   *  a further "strikes" escalation reuses the existing cross-repo banned-contributors ledger once wired).
+   *  Config-as-code only — no DB column or dashboard toggle; set via `.gittensory.yml gate.copycat.mode`.
+   *  CURRENTLY INERT: this field is parsed and threaded end-to-end, but no detection engine reads it yet —
+   *  see {@link CopycatGateMode}'s doc comment in packages/gittensory-engine for the tracked follow-up plan. */
+  copycatGateMode?: CopycatGateMode | undefined;
+  /** `gate.copycat.minScore`: containment/similarity score (0-100) at/above which `copycatGateMode` would act,
+   *  once the detection engine exists. `null`/absent ⇒ the engine's own default threshold. Config-as-code
+   *  only, alongside {@link copycatGateMode}. */
+  copycatGateMinScore?: number | null | undefined;
   /** `gate.expectedCiContexts` (#selfhost-ci-verification): maintainer-declared CI check/status context names to
    *  treat as required when GitHub branch protection returns no readable required-status-checks (unconfigured,
    *  or a 403 from a token lacking `administration:read` — common for GitHub App installations). Merged with any