@mars-sea/dsh-commandcode-provider 0.12.6 → 0.12.7

package/CHANGELOG.md

@@ -4,6 +4,19 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.12.7] - 2026-10-08
+
+### Added
+
+- 同步官方 command-code@1.78.0 新增的 `claude-haiku-5-5`（Claude Haiku 5.5）：最低套餐 Pro，支持视觉与推理，五档思考强度 `low`/`medium`/`high`/`xhigh`/`max`，1 000 000 上下文；价格按提示长度分档，`≤100K` tokens 为 $0.10 入 / $0.50 出 / $0.01 缓存读 / $0.125 缓存写每 1M，`>100K` 为 $0.50 / $2.50 / $0.05 / $0.625。该模型在公开目录、定价页与 CLI 注册表三处同步出现，各记 +1。
+- 同步官方 command-code@1.79.0 新增的 `stealth/glyph-cluster:free`（Glyph Cluster）隐身预览：最低套餐 Go（全部套餐可用），纯文本、支持推理，四档思考强度 `low`/`medium`/`high`/`xhigh`，256 000 上下文；隐身预览期内免费、每天 100 次请求，官方标为 100% 折扣且没有公布结束日期，因此按「永久型」促销处理、不带 `expiresAt`，并排在模型选择器最前。
+
+### Changed
+
+- 同步官方 command-code@1.79.1：请求头 `x-command-code-version` 升至 `1.79.1`。官方日志覆盖到 1.79.0——1.78.0 是「新增 Claude Haiku 5.5（Pro 及以上）」、CLI 中文本地化（新增 `/language` 命令）与 Windows 上 Taste learning 归类崩溃的修复，1.79.0 是「新增 Glyph Cluster 免费模型，每天 100 次请求」；1.79.1 没有日志条目，逐字节比对 1.79.0 → 1.79.1 的 `dist/cli.mjs` 后确认唯一差异是 `resolveKittyKeyboard` 在 `win32` 平台跳过 Kitty 键盘协议探测（Windows 终端兼容修复）。协议面静态复核无变化：13 个请求头集合完全一致，`toWireMessages`／`toWireTools`／`toWirePermissionMode`／`knownModelSupportsZdr`／`getSupportedEfforts`／`buildModelGroups`／`listSelectableModelIds` 的调用点计数与形态不变，接口路径里唯一的新增是 CLI 自己的 `/language` 斜杠命令。
+- 零数据保留例外名单新增 `stealth/glyph-cluster:free`（20 → 21 项）：官方定价页在该行写明「Not routed under ZDR」，CLI 的排除集合同样列出它，两处证据一致。
+- 定价页额度与其余各行逐条复核对齐，价格表本次只有 `claude-haiku-5-5` 一行新增（含 `≤100K`／`>100K` 两个上下文分档），无其他行漂移。
+
 ## [0.12.6] - 2026-10-07
 
 ### Added

package/README.md

@@ -231,7 +231,7 @@ Command Code can serve a request only through upstreams that retain no prompts o
 
 **Off by default.** Turn it on with the *"Zero data retention (ZDR)"* toggle (`zdr`) in the Privacy & security card, or in your profile config. How this plugin implements it:
 
-- The header is sent on **every chat request** while ZDR is on. The plugin maintains an informational exception list (`KNOWN_NON_ZDR_MODELS`, synced from the official CLI — 23 models as of 2026-09-29, e.g. `xai/grok-4.5`, `stepfun/Step-3.7-Flash`, `meta/muse-spark-1.3`). A model without an available ZDR upstream fails with `422 cmd_zdr_no_providers`; the request is never retried without the header.
+- The header is sent on **every chat request** while ZDR is on. The plugin maintains an informational exception list (`KNOWN_NON_ZDR_MODELS`, synced from the official CLI — 21 models as of 2026-10-08, e.g. `xai/grok-4.5`, `stealth/glyph-cluster:free`, `stepfun/Step-3.7-Flash`, `meta/muse-spark-1.3`). A model without an available ZDR upstream fails with `422 cmd_zdr_no_providers`; the request is never retried without the header.
 - If a refusal still happens (coverage churn, or no ZDR upstream with spare capacity at that moment), the error names the cause and how to turn ZDR off, instead of surfacing as a bare HTTP 422.
 - **ZDR usually costs more**: capacity is limited and billed at each upstream's pass-through rates, and which upstream serves a request can change per request. The session-cost readout keeps quoting the ordinary catalog rates; the real per-request price shows in Command Code's Studio usage page.
 - Works on every plan; plan credits meter ZDR requests at the plan's default allowance.

package/README.zh-CN.md

@@ -223,7 +223,7 @@ Command Code 可以让请求只经由「不留存提示词与回复、也不用
 
 **默认关闭。** 在「隐私与安全」卡片里打开「零数据保留（ZDR）」（`zdr`），或写进 profile 配置。本插件的实现方式：
 
-- 开启后，**每次聊天请求**都会带上 ZDR 请求头。插件仍维护官方 CLI 的例外名单（`KNOWN_NON_ZDR_MODELS`，截至 2026-09-29 共 23 个模型，例如 `xai/grok-4.5`、`stepfun/Step-3.7-Flash`、`meta/muse-spark-1.3`）供查询。没有可用 ZDR 上游时，服务端返回 `422 cmd_zdr_no_providers`；插件不会去掉请求头重试。
+- 开启后，**每次聊天请求**都会带上 ZDR 请求头。插件仍维护官方 CLI 的例外名单（`KNOWN_NON_ZDR_MODELS`，截至 2026-10-08 共 21 个模型，例如 `xai/grok-4.5`、`stealth/glyph-cluster:free`、`stepfun/Step-3.7-Flash`、`meta/muse-spark-1.3`）供查询。没有可用 ZDR 上游时，服务端返回 `422 cmd_zdr_no_providers`；插件不会去掉请求头重试。
 - 万一仍被拒绝（名单过期，或那一刻没有空闲的 ZDR 上游容量），错误信息会说明原因并给出关闭 ZDR 的办法，而不是抛出一个光秃秃的 HTTP 422。
 - **ZDR 通常更贵**：容量有限，按各上游实价透传计费，且每次请求落在哪个上游可能不同。会话费用读数仍按常规目录价估算；真实单价见 Command Code Studio 的用量页。
 - 各套餐均可使用；ZDR 请求按套餐的默认额度（而非提升额度）计量。

package/lib/client.js

@@ -3273,7 +3273,7 @@ window.__ModuleLoader__.load({
 		}
 		//#endregion
 		//#region package.json
-		var version = "0.12.6";
+		var version = "0.12.7";
 		var repository = {
 			"type": "git",
 			"url": "git+https://github.com/Mars-Sea/dsh-commandcode-provider.git"

package/lib/index.d.ts

@@ -61,7 +61,7 @@ type CommandCodeProtocol = 'cli' | 'openai' | 'messages';
 declare const DEFAULT_MAX_OUTPUT_TOKENS = 131072;
 //#endregion
 //#region src/adapter.d.ts
-declare const COMMAND_CODE_CLI_VERSION = "1.77.0";
+declare const COMMAND_CODE_CLI_VERSION = "1.79.1";
 declare const DEFAULT_API_BASE = "https://api.commandcode.ai";
 /**
  * The output budget this bundle asks for, and the ceiling it will never exceed.
@@ -978,7 +978,7 @@ declare const KNOWN_EFFORTS: Readonly<Record<string, readonly string[]>>;
 declare const KNOWN_IMAGE_MODELS: ReadonlySet<string>;
 /**
  * Models WITHOUT a zero-data-retention upstream, per the official CLI's own
- * registry (`command-code@1.77.0` `dist/cli.mjs`): `modelSupportsZdr(id)` is
+ * registry (`command-code@1.79.1` `dist/cli.mjs`): `modelSupportsZdr(id)` is
  * exactly `!nonZdrSet.has(canonicalize(id))`, and `knownModelSupportsZdr`
  * carries the same membership in the sibling route table — the UNION of both
  * is this set. Reading only the sibling route table dropped
@@ -1011,7 +1011,8 @@ declare const KNOWN_IMAGE_MODELS: ReadonlySet<string>;
  * (`deepseek/deepseek-v4.1-flash-fast`), 1.68.0 changed nothing, and 1.74.1
  * removed one (`meituan/LongCat-2.0`). The 1.74.2/1.74.3 pair changed nothing
  * here either (22 members as of 2026-10-06); 1.77.0 dropped the two retired
- * stealth previews, back to 20 members as of 2026-10-07.
+ * stealth previews, back to 20 members as of 2026-10-07, and 1.79.0 added the
+ * free `stealth/glyph-cluster:free` preview — 21 members as of 2026-10-08.
  *
  * 1.77.0 also settled the two retired stealth previews (see `KNOWN_EFFORTS`):
  * 1.74.3 still named both in the ZDR anchors, so they stayed listed here on
@@ -1049,12 +1050,13 @@ declare const KNOWN_THINKING_MODELS: ReadonlySet<string>;
  * `/docs/plans/max` and `/docs/resources/pricing-limits`). Each plan's model
  * list is a superset of the one below it: Go ⊂ GOAT ⊂ Pro ⊂ Provider/Max.
  * Models absent from every plan list (Claude Opus/Fable, Fugu Ultra) are
- * Provider-tier. Re-verified at command-code@1.77.0 (2026-10-07): 85 catalog
- * ids at 53/62/76/84 cumulative, a strict superset chain. Mistral Large 4
- * (1.75.0) is the only addition since the 1.74.3 check; the only removals since
- * 1.49.0 are the two retired stealth previews (Pixel Canary at 1.73.1, Space
- * Bunny Alpha at 1.74.3). No tier ever moved, and per-entry tags below name the
- * release that added each row.
+ * Provider-tier. Re-verified at command-code@1.79.1 (2026-10-08): 87 catalog
+ * ids at 54/63/78/86 cumulative, a strict superset chain. Mistral Large 4
+ * (1.75.0) was the only addition at the 1.77.0 check; the 1.78.0/1.79.0 pair
+ * added two more — Claude Haiku 5.5 at Pro and the free Glyph Cluster preview
+ * at Go — and the only removals since 1.49.0 are the two retired stealth
+ * previews (Pixel Canary at 1.73.1, Space Bunny Alpha at 1.74.3). No tier ever
+ * moved, and per-entry tags below name the release that added each row.
  *
  * The Provider API exposes no plan metadata, so this snapshot is the source of
  * truth for the picker's plan annotation — it answers "which plan do I need to

package/lib/index.js

@@ -103,7 +103,7 @@ const PLAN_ORDER = Object.fromEntries(PLAN_TIER_ORDER.map((tier, index) => [tier
 * subscription-plan labels, deals, and hourly (peak/off-peak) pricing.
 *
 * Everything here is synced from official sources — the command-code CLI
-* bundle's model table (`dist/cli.mjs`, re-verified at command-code@1.77.0) and
+* bundle's model table (`dist/cli.mjs`, re-verified at command-code@1.79.1) and
 * the official plan/pricing/model docs; see the dsh-commandcode-upstream skill
 * for the extraction procedures. Keeping the snapshot in its own module
 * confines those frequent sync diffs here: src/adapter.ts holds only the stable
@@ -429,6 +429,19 @@ const KNOWN_EFFORTS = {
 		"low",
 		"medium",
 		"high"
+	],
+	"claude-haiku-5-5": [
+		"low",
+		"medium",
+		"high",
+		"xhigh",
+		"max"
+	],
+	"stealth/glyph-cluster:free": [
+		"low",
+		"medium",
+		"high",
+		"xhigh"
 	]
 };
 /**
@@ -459,6 +472,7 @@ const KNOWN_IMAGE_MODELS = /* @__PURE__ */ new Set([
 	"claude-fable-5-1",
 	"claude-fable-5",
 	"claude-haiku-4-5-20251001",
+	"claude-haiku-5-5",
 	"claude-opus-4-7",
 	"claude-opus-4-8",
 	"claude-opus-5-5",
@@ -514,7 +528,7 @@ const KNOWN_IMAGE_MODELS = /* @__PURE__ */ new Set([
 ]);
 /**
 * Models WITHOUT a zero-data-retention upstream, per the official CLI's own
-* registry (`command-code@1.77.0` `dist/cli.mjs`): `modelSupportsZdr(id)` is
+* registry (`command-code@1.79.1` `dist/cli.mjs`): `modelSupportsZdr(id)` is
 * exactly `!nonZdrSet.has(canonicalize(id))`, and `knownModelSupportsZdr`
 * carries the same membership in the sibling route table — the UNION of both
 * is this set. Reading only the sibling route table dropped
@@ -547,7 +561,8 @@ const KNOWN_IMAGE_MODELS = /* @__PURE__ */ new Set([
 * (`deepseek/deepseek-v4.1-flash-fast`), 1.68.0 changed nothing, and 1.74.1
 * removed one (`meituan/LongCat-2.0`). The 1.74.2/1.74.3 pair changed nothing
 * here either (22 members as of 2026-10-06); 1.77.0 dropped the two retired
-* stealth previews, back to 20 members as of 2026-10-07.
+* stealth previews, back to 20 members as of 2026-10-07, and 1.79.0 added the
+* free `stealth/glyph-cluster:free` preview — 21 members as of 2026-10-08.
 *
 * 1.77.0 also settled the two retired stealth previews (see `KNOWN_EFFORTS`):
 * 1.74.3 still named both in the ZDR anchors, so they stayed listed here on
@@ -569,6 +584,7 @@ const KNOWN_NON_ZDR_MODELS = /* @__PURE__ */ new Set([
 	"minimax/minimax-m3-free",
 	"poolside/laguna-s-2.1-free",
 	"sakana/fugu-ultra",
+	"stealth/glyph-cluster:free",
 	"stepfun/Step-3.7-Flash",
 	"stepfun/Step-5-Preview",
 	"xai/grok-4.5",
@@ -788,12 +804,13 @@ const MODEL_OUTPUT_TOKEN_LIMITS = /* @__PURE__ */ new Map([
 * `/docs/plans/max` and `/docs/resources/pricing-limits`). Each plan's model
 * list is a superset of the one below it: Go ⊂ GOAT ⊂ Pro ⊂ Provider/Max.
 * Models absent from every plan list (Claude Opus/Fable, Fugu Ultra) are
-* Provider-tier. Re-verified at command-code@1.77.0 (2026-10-07): 85 catalog
-* ids at 53/62/76/84 cumulative, a strict superset chain. Mistral Large 4
-* (1.75.0) is the only addition since the 1.74.3 check; the only removals since
-* 1.49.0 are the two retired stealth previews (Pixel Canary at 1.73.1, Space
-* Bunny Alpha at 1.74.3). No tier ever moved, and per-entry tags below name the
-* release that added each row.
+* Provider-tier. Re-verified at command-code@1.79.1 (2026-10-08): 87 catalog
+* ids at 54/63/78/86 cumulative, a strict superset chain. Mistral Large 4
+* (1.75.0) was the only addition at the 1.77.0 check; the 1.78.0/1.79.0 pair
+* added two more — Claude Haiku 5.5 at Pro and the free Glyph Cluster preview
+* at Go — and the only removals since 1.49.0 are the two retired stealth
+* previews (Pixel Canary at 1.73.1, Space Bunny Alpha at 1.74.3). No tier ever
+* moved, and per-entry tags below name the release that added each row.
 *
 * The Provider API exposes no plan metadata, so this snapshot is the source of
 * truth for the picker's plan annotation — it answers "which plan do I need to
@@ -841,6 +858,7 @@ const KNOWN_PLANS = {
 	"stepfun/Step-3.5-Flash": "go",
 	"stepfun/Step-3.7-Flash": "go",
 	"stepfun/Step-5-Preview": "go",
+	"stealth/glyph-cluster:free": "go",
 	"tencent/hy3-paid": "go",
 	"tencent/hy4-preview": "go",
 	"thinkingmachines/inkling": "go",
@@ -867,6 +885,7 @@ const KNOWN_PLANS = {
 	"xai/grok-4.7": "goat",
 	"xiaomi/mimo-v2.6-pro-ultraspeed": "goat",
 	"claude-haiku-4-5-20251001": "pro",
+	"claude-haiku-5-5": "pro",
 	"claude-sonnet-4-6": "pro",
 	"claude-sonnet-5": "pro",
 	"google/gemini-3.1-flash-lite": "pro",
@@ -1036,6 +1055,10 @@ const KNOWN_DEALS = {
 	"inclusionai/ling-3.1-flash:free": {
 		label: "FREE",
 		free: true
+	},
+	"stealth/glyph-cluster:free": {
+		label: "FREE",
+		free: true
 	}
 };
 /**
@@ -1252,6 +1275,34 @@ const MODEL_PRICE_ROWS = [
 			pro: 20
 		}
 	},
+	{
+		id: "claude-haiku-5-5",
+		rates: [
+			.1,
+			.5,
+			.01,
+			.125
+		],
+		allowance: {
+			go: 6,
+			goat: 20,
+			pro: 20
+		},
+		contextTiers: [{
+			"maxContext": 1e5,
+			"rates": [
+				.1,
+				.5,
+				.01,
+				.125
+			]
+		}, { "rates": [
+			.5,
+			2.5,
+			.05,
+			.625
+		] }]
+	},
 	{
 		id: "claude-opus-4-6",
 		rates: [
@@ -5276,7 +5327,7 @@ var GatewayFacts = class {
 * per-request options thunk and an API-key resolver from the plugin entry
 * (src/index.ts), so a settings change reaches the very next request.
 */
-const COMMAND_CODE_CLI_VERSION = "1.77.0";
+const COMMAND_CODE_CLI_VERSION = "1.79.1";
 const DEFAULT_API_BASE = "https://api.commandcode.ai";
 /**
 * The output budget this bundle asks for, and the ceiling it will never exceed.