lidge-jun · lidge-jun · Sep 16, 2026 · Sep 14, 2026 · Sep 14, 2026 · Sep 15, 2026
@@ -159,8 +159,9 @@ Support/Claude/configLibrary` sur macOS, `%APPDATA%\Claude\configLibrary` sur Wi
 `CLAUDE_USER_DATA_DIR` pour utiliser une autre racine de données Claude Desktop. L'ancien répertoire `Claude-3p` n'est
 ni lu ni supprimé automatiquement.
 
-Les routes non Anthropic reçoivent des alias stables comme `claude-opus-4-8-2026MMDD`. La partie qui ressemble à une date
-est un emplacement synthétique de route, et non la date de publication du modèle. Les véritables routes Anthropic Claude conservent
+Les routes non Anthropic reçoivent des alias stables comme `claude-opus-4-8-YYYYMMDD`, dont l'année va de 2026 à 2035. La partie qui ressemble à une date
+est un emplacement synthétique de route, et non la date de publication du modèle. Les emplacements de 2026 sont attribués en premier, de sorte que les alias
+existants conservent leur identifiant ; les années suivantes ne sont utilisées qu'une fois 2026 saturée. Les véritables routes Anthropic Claude conservent
 leur identité. Les nouvelles routes appartiennent par défaut à la famille Opus, mais déplacer une route ne change ni le
 fournisseur ni le modèle qu'elle appelle. Les anciens indicateurs `--static`, `--hybrid` et `--discovery-only`
 restent disponibles pour les scripts existants.

@@ -131,7 +131,12 @@ Si Kiro s’arrête sans appeler l’outil d’achèvement, l’adaptateur effec
 
 ### Effort de raisonnement
 
-`gpt-5.6-sol` et `claude-opus-5` prennent en charge nativement un niveau d’effort vérifié, mais chaque famille de modèles nomme différemment le champ de la requête. La valeur sélectionnée `low`, `medium`, `high`, `xhigh` ou `max` est envoyée dans `additionalModelRequestFields.reasoning.effort` pour `gpt-5.6-sol`, et dans `additionalModelRequestFields.output_config.effort` pour `claude-opus-5`. Les autres modèles Kiro utilisent actuellement un raisonnement émulé : opencodex convertit le niveau choisi en instructions de réflexion bornées dans le contenu utilisateur, car leur champ d’effort natif n’a pas été vérifié. La présence d’un contrôle d’effort annoncé sur ces modèles ne prouve donc pas la prise en charge native du raisonnement en amont.
+Les modèles GPT-5.6 utilisent `additionalModelRequestFields.reasoning.effort`, et `claude-opus-5`
+utilise `additionalModelRequestFields.output_config.effort`. Pour `gpt-5.6-luna` et `gpt-5.6-terra`,
+seuls `low`, `medium`, `high` et `max` empruntent le chemin natif vérifié. Leur niveau `xhigh`
+conserve les instructions de réflexion bornées existantes, car ce niveau natif n’a pas été vérifié.
+`gpt-5.6-sol` et `claude-opus-5` conservent leurs niveaux natifs existants : `low`, `medium`, `high`,
+`xhigh` et `max`. Les autres modèles Kiro utilisent une émulation ; un réglage d’effort ne prouve pas une prise en charge native.
 
 ## `cursor`
 

@@ -181,8 +181,11 @@ Support/Claude/configLibrary` on macOS, `%APPDATA%\Claude\configLibrary` on Wind
 `CLAUDE_USER_DATA_DIR` for an alternate Desktop user-data root. The legacy `Claude-3p` directory is
 not read or deleted automatically.
 
-Non-Anthropic routes receive stable aliases such as `claude-opus-4-8-2026MMDD`. The date-looking
-part is a synthetic route slot, not the model's release date. Real Anthropic Claude routes keep
+Non-Anthropic routes receive stable aliases such as `claude-opus-4-8-YYYYMMDD`, where the year runs
+from 2026 to 2035. The date-looking
+part is a synthetic route slot, not the model's release date. 2026 slots are allocated first, so
+existing aliases keep their ids; the later years are reached only once 2026 fills.
+Real Anthropic Claude routes keep
 their real ids. New routes default to the Opus family, but moving a route does not change the
 provider or model it calls. The legacy apply flags `--static`, `--hybrid`, and `--discovery-only`
 remain available for existing scripts.

@@ -64,6 +64,18 @@ Shipped v1 configs migrate automatically to marker 2 and one option-aware row. T
 is retained once at `~/.opencodex/config.json.pre-openai-tiers-v2.bak`; restore it with
 `cp ~/.opencodex/config.json.pre-openai-tiers-v2.bak ~/.opencodex/config.json`.
 
+## Anthropic image input
+
+The built-in Claude model seeds advertise text and image input for both `anthropic` (OAuth) and
+`anthropic-apikey`, consistent with [Anthropic's model overview](https://platform.claude.com/docs/en/models/overview).
+Explicit per-model input-modality overrides remain authoritative; unknown models are not assumed
+image-capable. This applies across integrations wherever the client's configuration supports image
+capability metadata: OpenClaw exports a declared `input` array, and Kimi Code exports
+`capabilities: ["image_in"]` only for image-capable models. OpenClaw omits `input` when no supported
+modalities are declared; Kimi omits `capabilities` for unknown or text-only models. Clients without
+a supported capability field keep their existing configuration shape. After updating opencodex,
+regenerate or refresh the client configuration managed by opencodex to receive the updated metadata.
+
 ## Auth modes
 
 Provider configs accept three `authMode` values (`key` is the default). The built-in registry also

@@ -154,10 +154,12 @@ filtered incomplete になります。実際のツール呼び出しを伴わな
 
 ### Reasoning effort
 
-`gpt-5.6-sol` と `claude-opus-5` はネイティブ effort をサポートし、リクエストフィールド名が異なります。
-`low` / `medium` / `high` / `xhigh` / `max` は、前者では
-`additionalModelRequestFields.reasoning.effort`、後者では `output_config.effort` として送信されます。
-
+GPT-5.6 系は `additionalModelRequestFields.reasoning.effort`、`claude-opus-5` は
+`additionalModelRequestFields.output_config.effort` を使用します。`gpt-5.6-luna` と
+`gpt-5.6-terra` では、検証済みの `low`、`medium`、`high`、`max` だけをネイティブフィールドで送信します。
+両モデルの `xhigh` は未検証のため、従来の上限付き thinking 指示によるエミュレーションを維持します。
+`gpt-5.6-sol` と `claude-opus-5` の既存のネイティブ段階（`low`、`medium`、`high`、`xhigh`、`max`）は変更しません。
+その他の Kiro モデルはエミュレーションを使用し、effort の選択肢だけではネイティブ対応を意味しません。
 
 ## `cursor`
 

@@ -167,10 +167,12 @@ commentary로 유지하고 비공개 완료 툴을 한 번 검증합니다.
 
 ### Reasoning effort
 
-`gpt-5.6-sol`과 `claude-opus-5`는 네이티브 effort를 지원하며 요청 필드 이름이 다릅니다.
-`low` / `medium` / `high` / `xhigh` / `max` 값은 각각
-`additionalModelRequestFields.reasoning.effort`와 `output_config.effort`로 전송됩니다.
-
+GPT-5.6 계열은 `additionalModelRequestFields.reasoning.effort`를, `claude-opus-5`는
+`additionalModelRequestFields.output_config.effort`를 사용합니다. `gpt-5.6-luna`와
+`gpt-5.6-terra`는 검증된 `low`, `medium`, `high`, `max`만 네이티브 필드로 전송합니다.
+두 모델의 `xhigh`는 네이티브 동작이 검증되지 않아 기존의 제한된 thinking 지시문 방식을 유지합니다.
+`gpt-5.6-sol`과 `claude-opus-5`의 기존 네이티브 단계(`low`, `medium`, `high`, `xhigh`, `max`)는
+바뀌지 않습니다. 다른 Kiro 모델의 effort는 에뮬레이션이며, 조절 항목이 있다고 네이티브 지원을 뜻하지는 않습니다.
 
 ## `cursor`
 

@@ -370,13 +370,13 @@ important than cosmetic de-duplication. Tool-free requests retain normal text co
 
 ### Reasoning effort
 
-`gpt-5.6-sol` and `claude-opus-5` have verified native effort support, and each model family names
-the request field differently. A selected `low`, `medium`, `high`, `xhigh`, or `max` value is sent
-as `additionalModelRequestFields.reasoning.effort` for `gpt-5.6-sol` and as
-`additionalModelRequestFields.output_config.effort` for `claude-opus-5`. Other Kiro models currently
-use emulated reasoning: opencodex converts the selected level into bounded thinking instructions in
-the user content because their native effort field has not been verified. Do not interpret an
-advertised effort control on those models as proof of upstream-native reasoning support.
+The GPT-5.6 family uses `additionalModelRequestFields.reasoning.effort`; `claude-opus-5`
+uses `additionalModelRequestFields.output_config.effort`. For `gpt-5.6-luna` and
+`gpt-5.6-terra`, only `low`, `medium`, `high`, and `max` use the verified native path.
+Their `xhigh` selection retains the previous bounded thinking instructions in user content
+because that native rung has not been verified. `gpt-5.6-sol` and `claude-opus-5` keep
+their existing native `low`, `medium`, `high`, `xhigh`, and `max` behavior. Other Kiro
+models use emulated reasoning; an advertised effort control is not proof of native support.
 
 ## `cursor`
 

@@ -189,10 +189,12 @@ incomplete. `TOOL_USE` без фактического вызова инстру
 
 ### Reasoning effort
 
-`gpt-5.6-sol` и `claude-opus-5` поддерживают нативный effort, но называют поле запроса по-разному.
-Значения `low` / `medium` / `high` / `xhigh` / `max` отправляются как
-`additionalModelRequestFields.reasoning.effort` и `output_config.effort` соответственно.
-
+Семейство GPT-5.6 использует `additionalModelRequestFields.reasoning.effort`, а `claude-opus-5` —
+`additionalModelRequestFields.output_config.effort`. Для `gpt-5.6-luna` и `gpt-5.6-terra` нативный
+путь проверен только для `low`, `medium`, `high` и `max`. Их `xhigh` сохраняет прежнюю эмуляцию
+через ограниченные инструкции thinking, поскольку нативный уровень не проверен.
+Существующие нативные уровни `gpt-5.6-sol` и `claude-opus-5` (`low`, `medium`, `high`, `xhigh`, `max`)
+не меняются. Остальные модели Kiro используют эмуляцию; наличие настройки effort не доказывает нативную поддержку.
 
 ## `cursor`
 

@@ -189,9 +189,11 @@ alternatif bir Desktop kullanıcı verisi kökü için `CLAUDE_USER_DATA_DIR`
 değerini ayarlayın. Eski `Claude-3p` dizini otomatik olarak okunmaz veya
 silinmez.
 
-Anthropic harici rotalar, `claude-opus-4-8-2026MMDD` gibi kararlı takma adlar
-alır. Tarih benzeri kısım, modelin çıkış tarihi değil, sentetik bir rota
-yuvasıdır. Gerçek Anthropic Claude rotaları kendi gerçek kimliklerini korur.
+Anthropic harici rotalar, `claude-opus-4-8-YYYYMMDD` gibi kararlı takma adlar
+alır; yıl 2026 ile 2035 arasındadır. Tarih benzeri kısım, modelin çıkış tarihi
+değil, sentetik bir rota yuvasıdır. Önce 2026 yuvaları atanır, bu nedenle mevcut
+takma adlar kimliklerini korur; sonraki yıllara ancak 2026 dolduktan sonra
+geçilir. Gerçek Anthropic Claude rotaları kendi gerçek kimliklerini korur.
 Yeni rotalar varsayılan olarak Opus ailesine gider, ancak bir rotayı taşımak
 çağırdığı sağlayıcıyı veya modeli değiştirmez. Eski uygulama bayrakları
 `--static`, `--hybrid` ve `--discovery-only` mevcut betikler için kullanılabilir

@@ -268,15 +268,12 @@ tam olarak tekrarlasa bile, çünkü aşama doğruluğu kozmetik tekilleştirmed
 
 ### Akıl yürütme çabası
 
-`gpt-5.6-sol` ve `claude-opus-5` doğrulanmış yerel çaba desteğine sahiptir ve
-her model ailesi istek alanını farklı şekilde adlandırır. Seçilen `low`,
-`medium`, `high`, `xhigh` veya `max` değeri `gpt-5.6-sol` için
-`additionalModelRequestFields.reasoning.effort` olarak ve `claude-opus-5` için
-`additionalModelRequestFields.output_config.effort` olarak gönderilir. Diğer
-Kiro modelleri şu anda öykünülmüş akıl yürütme kullanır: opencodex yerel çaba
-alanları doğrulanmadığı için seçilen seviyeyi kullanıcı içeriğinde sınırlı
-düşünme talimatlarına dönüştürür. Bu modellerde bildirilen bir çaba denetimini
-yukarı akış yerel akıl yürütme desteğinin kanıtı olarak yorumlamayın.
+GPT-5.6 ailesi `additionalModelRequestFields.reasoning.effort`, `claude-opus-5` ise
+`additionalModelRequestFields.output_config.effort` alanını kullanır. `gpt-5.6-luna` ve
+`gpt-5.6-terra` için yalnızca doğrulanmış `low`, `medium`, `high` ve `max` seviyeleri yerel alandan
+gönderilir. Bu iki modelin yerel `xhigh` seviyesi doğrulanmadığı için mevcut sınırlı düşünme
+talimatlarıyla öykünme korunur. `gpt-5.6-sol` ve `claude-opus-5` için mevcut yerel `low`, `medium`,
+`high`, `xhigh` ve `max` davranışı değişmez. Diğer Kiro modelleri öykünme kullanır; çaba seçeneği yerel desteğin kanıtı değildir.
 
 ## `cursor`
 

@@ -154,10 +154,12 @@ Kiro 的 assistant 文本本身没有可靠的回合结束标记，但终止的
 
 ### Reasoning effort
 
-`gpt-5.6-sol` 和 `claude-opus-5` 支持原生 effort，且请求字段名不同。`low` / `medium` / `high` /
-`xhigh` / `max` 分别通过 `additionalModelRequestFields.reasoning.effort` 和
-`output_config.effort` 发送。
-
+GPT-5.6 系列使用 `additionalModelRequestFields.reasoning.effort`，`claude-opus-5` 使用
+`additionalModelRequestFields.output_config.effort`。`gpt-5.6-luna` 和 `gpt-5.6-terra`
+仅通过原生字段发送已验证的 `low`、`medium`、`high` 和 `max`。
+这两个模型的原生 `xhigh` 尚未验证，因此仍使用原有的有界 thinking 指令模拟。
+`gpt-5.6-sol` 和 `claude-opus-5` 保留现有原生档位（`low`、`medium`、`high`、`xhigh`、`max`）。
+其他 Kiro 模型使用模拟推理；提供 effort 选项并不代表原生支持。
 
 ## `cursor`
 

@@ -129,8 +129,9 @@ ocx claude desktop import <path> [--apply]
 檔案，因此無效檔案不會改動目前設定檔。加上 `--apply` 可在匯入有效設定檔後立即寫入 Desktop。
 `none` 僅適用於空系列；每個非空系列都必須保留一個預設。
 
-非 Anthropic 路由會得到穩定別名，例如 `claude-opus-4-8-2026MMDD`。看起來像日期的部分是合成的
-路由槽位，不是模型釋出日期。真正的 Anthropic Claude 路由保留真實 id。新路由預設落在 Opus
+非 Anthropic 路由會得到穩定別名，例如 `claude-opus-4-8-YYYYMMDD`，年份範圍為 2026 至 2035。看起來像日期的部分是合成的
+路由槽位，不是模型釋出日期。系統會先配置 2026 的槽位，因此既有別名的 id 不變；2026 用盡後才會用到後續年份。
+真正的 Anthropic Claude 路由保留真實 id。新路由預設落在 Opus
 系列，但移動路由不會改變它所呼叫的供應商或模型。舊版 apply 旗標 `--static`、`--hybrid` 與
 `--discovery-only` 仍可供既有腳本使用。
 

@@ -145,10 +145,12 @@ Kiro 的 assistant 文字本身沒有可靠的回合結束標記，但終止的
 
 ### Reasoning effort
 
-`gpt-5.6-sol` 和 `claude-opus-5` 支援原生 effort，且請求欄位名不同。`low` / `medium` / `high` /
-`xhigh` / `max` 分別透過 `additionalModelRequestFields.reasoning.effort` 和
-`output_config.effort` 傳送。
-
+GPT-5.6 系列使用 `additionalModelRequestFields.reasoning.effort`，`claude-opus-5` 使用
+`additionalModelRequestFields.output_config.effort`。`gpt-5.6-luna` 和 `gpt-5.6-terra`
+只透過原生欄位傳送已驗證的 `low`、`medium`、`high` 和 `max`。
+這兩個模型的原生 `xhigh` 尚未驗證，因此仍使用原有的有界 thinking 指令模擬。
+`gpt-5.6-sol` 和 `claude-opus-5` 保留現有原生檔位（`low`、`medium`、`high`、`xhigh`、`max`）。
+其他 Kiro 模型使用模擬推理；提供 effort 選項不代表原生支援。
 
 ## `cursor`
 

@@ -217,7 +217,13 @@ export type RoutingCommentaryDecision =
   | { kind: "flush" }
   | { kind: "hallucination" };
 
-const ROUTING_NATIVE_TOOL_NAME = /\b(shell|read|grep|list|bash)\b/giu;
+// The Korean alternative is deliberately asymmetric: it has a left boundary and no right one.
+// Korean attaches particles directly to the noun, so the real sentences this detector exists to
+// catch read "네이티브 셸이 차단되어..." and "네이티브 셸과 Read가...". A mirrored
+// (?![\p{L}\p{M}\p{N}_]) lookahead would see the 이/과 particle as a letter and stop matching
+// every one of them, which is why the negative cases below only probe the left side. Adding the
+// right boundary looks like an obvious fix and disables the check; do not.
+const ROUTING_NATIVE_TOOL_NAME = /\b(shell|read|grep|list|bash)\b|(?<![\p{L}\p{M}\p{N}_])네이티브\s*(?:셸|쉘)/giu;
 const ROUTING_TOOL_HINT =
   /(?:\b(?:shell|read|grep|list|bash)\b|exec_command|shell_command|브리지|네이티브\s*(?:셸|쉘))/iu;
 const ROUTING_FAILURE_CLAIM =
@@ -276,7 +282,7 @@ export class CursorRoutingCommentarySniffer {
   private matchesHallucination(): boolean {
     if (!ROUTING_FAILURE_CLAIM.test(this.buffered)) return false;
     const nativeTools = new Set(
-      [...this.buffered.matchAll(ROUTING_NATIVE_TOOL_NAME)].map(match => match[1]?.toLowerCase()),
+      [...this.buffered.matchAll(ROUTING_NATIVE_TOOL_NAME)].map(match => match[1]?.toLowerCase() ?? "shell"),
     );
     if (nativeTools.size === 0) return false;
     return ROUTING_REDIRECT_CLAIM.test(this.buffered) || nativeTools.size >= 2;

@@ -796,14 +796,14 @@ export function createGoogleAdapter(provider: OcxProviderConfig): ProviderAdapte
       // body, URL or credential.
       const requestedTextFormat = parsed.options.textFormat;
       if (requestedTextFormat) {
-        if (provider.googleMode === "cloud-code-assist") {
-          // Not implemented or verified by opencodex for the Cloud Code Assist envelope,
-          // including Claude models served through it. This is not a claim that the
-          // upstream cannot do it — silence would return unconstrained prose as success,
-          // which is the failure this fix exists to remove.
+        if (provider.googleMode === "cloud-code-assist" && !parsed.modelId.startsWith("gemini-")) {
+          // Not implemented by opencodex for non-Gemini models (including Claude)
+          // served through the Cloud Code Assist envelope. This is not a claim that
+          // the upstream cannot do it — silence would return unconstrained prose as success,
+          // which is the failure this refusal exists to prevent.
           throw new Error(
-            "google cloud-code-assist structured output is not implemented by opencodex — "
-            + "remove response_format or route this model through AI Studio or Vertex",
+            "google cloud-code-assist structured output is not implemented by opencodex for non-Gemini models — "
+            + "remove response_format or route this model through a direct provider",
           );
         }
         if (isImageCapableModel(parsed.modelId)) {