Release v3.8.40

v3.8.40 cycle integration → main. All test gates green (Unit/Integration/Coverage/Node-compat/Quality-Ratchet). The only red check, 'PR Test Policy', is the test-masking heuristic firing on the cumulative ~57-commit release diff (legitimate assert consolidations already reviewed per-PR — Gemini CLI removal #5246, retired GPT models #5280, provider catalog refreshes); overridden with --admin per the documented release-PR convention. CodeQL/SonarQube advisory scans non-blocking; #5278's code already passed CodeQL on main. Homologated on VPS 192.168.0.15 (v3.8.40 healthy).

@omniroute/opencode-plugin/README.md

@@ -196,7 +196,7 @@ Every field is optional. Defaults mirror v0.1.0 behaviour so existing `opencode.
 | `combos`              | `boolean` | `true`  | Discover `/api/combos` and surface them as pseudo-models with LCD capabilities. Combos are keyed under the `combo/<slug>` namespace and labelled `Combo: <name>` in the model picker so they're distinguishable from raw provider/model pairs.                                                                                                                                                                                                                                                                                                                               |
 | `enrichment`          | `boolean` | `true`  | Pull display names from `/api/pricing/models` AND per-million-token pricing (`input`, `output`, `cached` → `cacheRead`, `cache_creation` → `cacheWrite`) from `/api/pricing`, then overlay both onto the live catalog (so the UI shows `Claude 4.7 Opus` with `cost.input: 5`, `cost.output: 25` instead of raw IDs and zeroed cost).                                                                                                                                                                                                                                        |
 | `compressionMetadata` | `boolean` | `false` | Pull `/api/context/combos` so combo names get tagged with their compression pipeline, e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`. Intensity tokens render as traffic-light emoji (🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra) so the picker advertises "how compressed" each combo is at a glance.                                                                                                                                                                                                                                                  |
-| `providerTag`         | `boolean` | `true`  | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models` → `GHM`, `Gemini-cli` → `GEMINI-CLI`). Idempotent. Combos intentionally skipped (the `Combo: ` prefix already conveys multi-upstream). |
+| `providerTag`         | `boolean` | `true`  | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models` → `GHM`, `Gemini` → `GEMINI`). Idempotent. Combos intentionally skipped (the `Combo: ` prefix already conveys multi-upstream). |
 | `usableOnly`          | `boolean` | `false` | Read `/api/providers` and filter the catalog to providers that have at least one connection with `isActive: true` AND `testStatus: 'active'`. Subtract-filter semantics: providers unknown to BOTH the pricing-models catalog AND the connection table pass through (so synthetic prefixes like `agentrouter/*` survive). On fetch failure the filter is disabled for the refresh — never hides the whole catalog.                                                                                                                                                           |
 | `diskCache`           | `boolean` | `true`  | Persist the last successful `/v1/models` + `/api/combos` + enrichment + connections + compression snapshot to `${OPENCODE_DATA_DIR ?? ~/.local/share/opencode}/plugins/omniroute-<providerId>.json`. On a subsequent cold start where `/v1/models` throws (network down / IP whitelist drop / 5xx) the static block hydrates from the snapshot so OC's model picker survives offline. Soft-fail on read/write — never blocks publishing.                                                                                                                                     |
 | `geminiSanitization`  | `boolean` | `true`  | Strip `$schema`/`$ref`/`additionalProperties` from tool params when the model id matches `gemini`                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |

@omniroute/opencode-plugin/src/index.ts

@@ -1225,7 +1225,7 @@ export interface OmniRouteEnrichmentEntry {
     cacheWrite?: number;
   };
   /**
-   * Provider alias prefix seen in `/v1/models` ids (e.g. `cc`, `gemini-cli`).
+   * Provider alias prefix seen in `/v1/models` ids (e.g. `cc`, `gemini`).
    * Populated by `defaultOmniRouteEnrichmentFetcher` from
    * `/api/pricing/models` keys. Drives the `usableOnly` alias↔canonical
    * resolution.
@@ -1233,7 +1233,7 @@ export interface OmniRouteEnrichmentEntry {
   providerAlias?: string;
   /**
    * Canonical provider id used by `/api/providers` connections (e.g.
-   * `claude`, `gemini-cli`, `kiro`). Populated from the per-provider
+   * `claude`, `gemini`, `kiro`). Populated from the per-provider
    * `entry.id` field inside `/api/pricing/models`.
    */
   providerCanonical?: string;
@@ -2046,7 +2046,7 @@ export function formatCompressionPipeline(pipeline: OmniRouteCompressionStep[]):
 export interface OmniRouteProviderConnection {
   /** Connection UUID. */
   id: string;
-  /** Canonical provider id, e.g. `claude`, `gemini-cli`, `kiro`. Matches `entry.id` in `/api/pricing/models`. */
+  /** Canonical provider id, e.g. `claude`, `gemini`, `kiro`. Matches `entry.id` in `/api/pricing/models`. */
   provider: string;
   /** Connection auth flavor, e.g. `apikey`, `oauth`, `cookie`. */
   authType?: string;
@@ -2125,7 +2125,7 @@ export const defaultOmniRouteProvidersFetcher: OmniRouteProvidersFetcher = async
  * walk only the namespaced keys to derive the alias↔canonical mapping).
  *
  * Returns:
- *   - `aliases`: set of alias prefixes safe to keep (e.g. `cc`, `gemini-cli`).
+ *   - `aliases`: set of alias prefixes safe to keep (e.g. `cc`, `gemini`).
  *   - `canonicals`: set of canonical provider ids (e.g. `claude`, `kiro`).
  *
  * Callers should treat membership in EITHER set as "usable" — raw model
@@ -2174,7 +2174,7 @@ export function usableProviderAliasSet(
   }
   // Always include every usable canonical as an alias too — handles the
   // common case where `/v1/models` ids use the canonical id directly
-  // (e.g. `gemini-cli/gemini-1.5-pro`).
+  // (e.g. `gemini/gemini-1.5-pro`).
   for (const canonical of usableCanonicals) aliases.add(canonical);
   return { aliases, canonicals: usableCanonicals, knownAliases };
 }
@@ -3174,7 +3174,6 @@ export function sanitizeGeminiToolSchemas(payload: unknown): unknown {
  *     `gemini-2.5-flash`, etc.)
  *   - `models/gemini-…` (Google Generative AI canonical id form)
  *   - `google-vertex/gemini-…` (OpenCode + AI-SDK Vertex routing prefix)
- *   - `gemini-cli/…` (real OmniRoute alias surfaced on b35 prod `/v1/models`)
  *
  * Liberal by design: a false positive (cleaning a payload that didn't
  * need cleaning) costs only a structuredClone + one walk; a false negative

@omniroute/opencode-plugin/tests/config-shim.test.ts

@@ -1311,9 +1311,9 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
         "gemini-3-flash",
         {
           name: "Gemini 3 Flash",
-          providerAlias: "gemini-cli",
-          providerCanonical: "gemini-cli",
-          providerDisplayName: "Gemini-cli",
+          providerAlias: "gemini",
+          providerCanonical: "gemini",
+          providerDisplayName: "Gemini",
         },
       ],
     ])
@@ -1335,10 +1335,7 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
     entry.models["opencode-omniroute/claude-sonnet-4-6"].name,
     "Claude - Claude Sonnet 4.6"
   );
-  assert.equal(
-    entry.models["opencode-omniroute/gemini-3-flash"].name,
-    "Gemini-cli - Gemini 3 Flash"
-  );
+  assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
   // Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
   assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
 });

@omniroute/opencode-plugin/tests/gemini-sanitize.test.ts

@@ -212,8 +212,8 @@ test("shouldSanitizeForGemini: google-vertex/gemini-1.5-flash → true", () => {
   assert.equal(shouldSanitizeForGemini({ model: "google-vertex/gemini-1.5-flash" }), true);
 });
 
-test("shouldSanitizeForGemini: gemini-cli/gemini-2.5-pro → true (real OmniRoute alias)", () => {
-  assert.equal(shouldSanitizeForGemini({ model: "gemini-cli/gemini-2.5-pro" }), true);
+test("shouldSanitizeForGemini: gemini/gemini-2.5-pro → true", () => {
+  assert.equal(shouldSanitizeForGemini({ model: "gemini/gemini-2.5-pro" }), true);
 });
 
 test("shouldSanitizeForGemini: claude-sonnet-4 → false", () => {