@mars-sea/dsh-commandcode-provider 0.14.3 → 0.14.5

package/CHANGELOG.md

@@ -4,6 +4,45 @@ 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).
 
+## [0.14.5] - 2026-10-21
+
+### Changed
+
+- **同步 Command Code CLI `1.84.0` → `1.86.1`（纯请求头同步）。** 10-20 一晚连发 4 个补丁版本（`1.85.0`／`1.85.1`／`1.86.0`／`1.86.1`，UTC 17:54Z 起），**官方变更日志页面仍停在 `1.84.0`、CLI 通道没有任何新条目**，结论全部来自产物级静态比对。协议面零变化：请求头集合、`/provider/v1/*` 端点、`/alpha/generate` 的 `mode`／`permissionMode` 枚举、reasoning 重放与 `promptCache` 字面量逐项相同；唯一新增端点是 CLI 自身的 `POST /alpha/artifacts`（把报告/图表/页面发布成链接，2 MB 上限、`private`/`public`），插件不经过该路径。因此 `COMMAND_CODE_CLI_VERSION` 只随请求头更新，运行时行为不变；产物内嵌 `catalogVersion` 更新为 `2a2c334e…`，与实时目录一致。
+
+- **ZDR（零数据保留）例外集 25 → 18，首次做到两个来源逐条一致。** `1.86.1` 产物的 `modelSupportsZdr` 集合与实时目录的 `zdr:false` 行是同一批 18 个 id（`knownModelSupportsZdr` 已从产物删除）。**新增 3**：`claude-fable-5`、`claude-fable-5-1`、`tencent/hy4-preview`。**移除 10**：9 个模型被目录改判 `zdr:true`（`meta/muse-spark-1.1`／`1.2`／`1.3`、`meta/muse-wonder-1.0`、`xai/grok-4.5`／`4.6`、`xiaomi/mimo-v2.6-flash`／`pro`、`zai-org/GLM-5.2-Fast`），另加已从两个目录视图、定价页与文档页整体下架的 `stealth/cat-jam:free`。**`cat-jam` 是用户显式决定移除**，不是「从产物消失即视为已覆盖」：保留它只是对老会话的猜测，且会与官方 18 条长期分叉，理由见[《决策记录》第七章第 14 条](docs/决策记录.md#七上游快照同步边界)。`tests/zdr.test.ts` 的成员断言按新集合有意反转，并把 9 个改判模型的「返回 true」路径补进用例。
+
+- **MiniMax M3.1 Flash 免费促销延期一天。** 定价页到期时间由 `2026-10-21T10:45Z` 改为 `2026-10-22T10:45Z`（北京时间 10-22 18:45），`KNOWN_DEALS` 的 `expiresAt` 随之上移，FREE 徽标随之多显示一天；`tests/model-prices.test.ts` 的到期边界断言同步改到新时刻。
+
+- **`deepseek-v4.1-flash` 月额度上调（费率不变）。** 价格表重生成：GOAT $80 → **$100**、Pro $90 → **$110**；该行仍是 $0.15/$0.60/$0.003，峰谷窗口与倍率不变。
+
+### Added
+
+- **新增 Ornith 1.5 122B：付费 `ornith/ornith-1.5-122b` 与限时免费 `ornith/ornith-1.5-122b:free`。** 262,144 上下文、文本 + 图像（Vision）、`reasoning:true` 但无 `reasoningEfforts`（自动推理，选择器不提供档位）、Go 起、ZDR 覆盖。付费行 $0.16 输入 / $0.64 输出 / $0.02 缓存读（每百万 token），月额度 Go $6 / GOAT $20 / Pro $30，价格表 93 → 94 行；免费行 100% off 至 `2026-10-22T06:00Z`（北京时间 10-22 14:00，官方文案 "until 11:00 PM PT on October 21"），无每日请求上限。快照同步：`KNOWN_PLANS` 94 → 96、`KNOWN_IMAGE_MODELS` 72 → 74、`KNOWN_THINKING_MODELS` 15 → 17、`KNOWN_DEALS` 7 → 8；`KNOWN_EFFORTS` 不变（无档位）。
+
+- **输出上限表新增 `mistral/mistral-large-4`（262,144）。** 由 `scripts/sync-output-limits.mjs` 重生成，80 → 81 行；同时 `minimax` 三行由 512,000 修正为 **524,288**（供应商元数据把十进制 512K 改成二进制）。
+
+### Verification
+
+- `npm run typecheck` 退出码 0；`npm test` **1058／1058**；`npm run build` 两段通过、`lib/` 产物已重建。
+- **证据边界**：公开 GET 采集（14 个源全部 HTTP 200，2026-10-21 08:34 北京时间）；审计 `incomplete` 的 4 条 error 是 Ornith／MiniMax 四个 id 缺定价映射别名（目录侧单源，不是抓取失败），已按定价页人工核对。**未做**：真实账号登录、付费生成、服务端协议验证与浏览器渲染。
+
+## [0.14.4] - 2026-10-20
+
+### Changed
+
+- **同步 2026-10-20 的目录侧漂移（CLI 产物不变，仍是 1.84.0）。** 官方 CLI 的 npm `latest` 与变更日志本轮都没有新内容（`1.84.0` 于 2026-10-16T18:29Z 发布，日志顶部仍停在它），但实时模型目录在 10-19 晚变了：默认视图（`GET /provider/v1/models`）93 → 94 个 id，`?view=client` 101 → 102。快照随默认视图投影：`KNOWN_PLANS` 93 → 94、`KNOWN_EFFORTS` 65 → 66、`KNOWN_IMAGE_MODELS` 70 → 72、`KNOWN_DEALS` 7 → 7、`KNOWN_NON_ZDR_MODELS` 25 → 25；`COMMAND_CODE_CLI_VERSION` 与运行时代码不变（纯数据同步）。审计状态 `incomplete` 是预期形态：3 个 error 全是「目录比 1.84.0 产物新」的目录侧单源行（MiniMax M3.1 Flash 两行 + 既有的 `reflection/beam:free`），不是抓取失败。
+
+### Added
+
+- **MiniMax M3.1 Flash：付费 `minimax/minimax-m3.1-flash` 与限时免费 `minimax/minimax-m3.1-flash:free`。** 100 万上下文、文本 + 图像（Vision）、五档推理强度（`low`／`medium`／`high`／`xhigh`／`max`）、ZDR 覆盖、Go 起（全部套餐可见）。付费行 $0.15 输入／$0.60 输出／$0.015 缓存读（每百万 token，Go $6／GOAT $20／Pro $30 月额度）；免费行 100% off，促销期为 `2026-10-19T11:00Z` → `2026-10-21T10:45Z`（北京时间 10-19 19:00 → 10-21 18:45），官方说明「限时、无每日请求上限、账户需有 $1 余额」。**免费行是 `KNOWN_DEALS` 里第一个带 `expiresAt` 的免费促销**：到期后 FREE 徽标由 `dealLabel()` 自动消失，`:free` 行仍按 id 后缀 0 价，不会把过期折扣当成现价。
+
+- **定价页渲染表的「同一显示名多行」解析。** 上游自该模型上线起把付费行与免费行用同一个显示名 `MiniMax M3.1 Flash` 发布，`scripts/sync-model-prices.mjs` 原先「一个显示名一行」的唯一键假设因此让 `--check` 直接失败（`价格表模型名称重复，无法确定对应行：minimax m3.1 flash`）。现改为：渲染行按显示名分组，再按「免费 / 数值」形态唯一配对——同名同形态仍然拒绝生成，配到数值行后照旧逐项交叉校验三档费率与划线价。价格表随之新增一行 `minimax-m3.1-flash`（92 → 93 行）。同时给 `scripts/sync-output-limits.mjs` 的供应商映射补上小写 `minimax` 命名空间：新模型的目录 id 用的是小写前缀，缺这一项会退回聚合共识，把付费 id 的输出上限丢给运行时学习；补齐后两个 id 都落到供应商行（512000），表 78 → 80 行。
+
+### Removed
+
+- **Stealth Cat Jam 预览（`stealth/cat-jam:free`）从模型表下线。** 2026-10-20 检查时两个目录视图、定价页、模型文档页与 Go 套餐页都不再服务该行；`KNOWN_PLANS`／`KNOWN_EFFORTS`／`KNOWN_IMAGE_MODELS`／`KNOWN_DEALS` 移除，`tests/adapter.test.ts` 的免费模型排序夹具改用 Glyph Cluster。**保留在 `KNOWN_NON_ZDR_MODELS`**：1.84.0 产物的 ZDR 排除集仍点名它，而该表是「artifact 排除集 ∪ 目录 `zdr:false`」的并集，删条目会让老会话的 ZDR 判定偏乐观（判据见[《决策记录》第七章第 13 条](docs/决策记录.md#七上游快照同步边界)）。集合仍为 25 条。
+
 ## [0.14.3] - 2026-10-19
 
 ### Changed

package/README.md

@@ -274,7 +274,7 @@ 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 — 22 models as of 2026-10-14, e.g. `xai/grok-4.5`, `stealth/glyph-cluster:free`, `stepfun/Step-3.7-Flash`, `meta/muse-wonder-1.0`). 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 — 18 models as of 2026-10-21, e.g. `claude-fable-5`, `stealth/glyph-cluster:free`, `stepfun/Step-3.7-Flash`, `tencent/hy4-preview`). 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

@@ -255,7 +255,7 @@ 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 2026-10-14 共 22 个模型，例如 `xai/grok-4.5`、`stealth/glyph-cluster:free`、`stepfun/Step-3.7-Flash`、`meta/muse-wonder-1.0`）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 2026-10-21 共 18 个模型，例如 `claude-fable-5`、`stealth/glyph-cluster:free`、`stepfun/Step-3.7-Flash`、`tencent/hy4-preview`）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

@@ -3704,7 +3704,7 @@ window.__ModuleLoader__.load({
 		}
 		//#endregion
 		//#region package.json
-		var version = "0.14.3";
+		var version = "0.14.5";
 		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 = "1.84.0";
+declare const COMMAND_CODE_CLI_VERSION = "1.86.1";
 declare const DEFAULT_API_BASE = "https://api.commandcode.ai";
 /**
  * The output budget this bundle asks for, and the ceiling it will never exceed.
@@ -1047,8 +1047,10 @@ declare const KNOWN_IMAGE_MODELS: ReadonlySet<string>;
  * `minimax/minimax-m3-free` is the one entry the public catalog's default view
  * (`/provider/v1/models`) does not serve through the picker (it is CLI/pricing-visible
  * and hidden from the picker); it stays listed because the CLI carries it and a Go-plan
- * request can still name it. Both this row and `stealth/cat-jam:free` ARE served
- * by the `?view=client` catalog, which is where the 1.82.4 verdict comes from.
+ * request can still name it. At the 1.84.0 sync both this row and
+ * `stealth/cat-jam:free` were also served by the `?view=client` catalog, which
+ * is where the 1.82.4 verdict came from; the catalog stopped serving cat-jam on
+ * 2026-10-20, and the artifact followed at 1.86.1 (see the prune note below).
  *
  * command-code@1.82.4 moved the authority for this verdict: `knownModelSupportsZdr`
  * no longer negates a bundled Set, it returns `resolveKnownCatalogModel({model,
@@ -1086,6 +1088,25 @@ declare const KNOWN_IMAGE_MODELS: ReadonlySet<string>;
  * UNION of the artifact's exclusion set and the catalog's `zdr:false` list —
  * neither source alone is complete, which is why this set is not simply "what
  * the CLI says".
+ *
+ * The 2026-10-20 catalog-only sync changed no membership: `stealth/cat-jam:free`
+ * left both catalog views (its `zdr:false` verdict is no longer served), but the
+ * 1.84.0 artifact's exclusion set still named it and this set is the union, so
+ * membership stayed at 25. The MiniMax M3.1 Flash launch pair is ZDR-covered
+ * (`zdr:true` on both ids) and joins no set.
+ *
+ * 2026-10-21 (command-code@1.86.1 sync) prunes the set 25 -> 18, and for the
+ * first time the two sources agree exactly: the 1.86.1 artifact's
+ * `modelSupportsZdr` set and the live catalog's `zdr:false` rows are the same 18
+ * ids (`knownModelSupportsZdr` is gone from the artifact). +3: `claude-fable-5`,
+ * `claude-fable-5-1` and `tencent/hy4-preview`. -10: the nine models the catalog
+ * flipped to `zdr:true` (Muse Spark 1.1 / 1.2 / 1.3, Muse Wonder 1.0, Grok 4.5 /
+ * 4.6, MiMo V2.6 Flash / Pro, GLM-5.2 Fast) plus `stealth/cat-jam:free`, which
+ * no source serves any more. Cat-jam is removed by explicit decision (see the
+ * decision record, chapter 7 item 13): keeping a retired id in the negative set
+ * is defense for stale sessions, not evidence, and the 1.86.1 artifact itself
+ * dropped it. A verdict flip here is positive evidence, never "listed before,
+ * absent now".
  */
 declare const KNOWN_NON_ZDR_MODELS: ReadonlySet<string>;
 /**
@@ -1115,8 +1136,8 @@ 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@1.82.4 (2026-10-16) against the
- * live `?view=client` catalog: 93 ids, still a strict superset chain. Mistral
+ * Provider-tier. Re-verified at command-code@1.86.1 (2026-10-21) against the
+ * live `?view=client` catalog: 104 ids, still 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 Claude Haiku 5.5 at Pro and the free Glyph Cluster preview at Go.
@@ -1125,11 +1146,12 @@ declare const KNOWN_THINKING_MODELS: ReadonlySet<string>;
  * train adds Qwen 3.8 Max Prime at GOAT plus Muse Spark Open, Nemotron 3.5
  * Super VL and the free Cat Jam preview at Go, and drops Ling 3.0 Flash Sante,
  * which left the live catalog. Every other
- * tier is unchanged.
+ * tier is unchanged. The 1.86.1 sync (2026-10-21) adds only the Ornith 1.5 122B
+ * launch pair at Go.
  * 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) and Ling 3.0 Flash Sante
- * (2026-10-16). Per-entry tags below name the
- * releases that added or moved each row.
+ * Canary at 1.73.1, Space Bunny Alpha at 1.74.3), Ling 3.0 Flash Sante
+ * (2026-10-16) and the retired Cat Jam preview (2026-10-20). Per-entry tags
+ * below name the releases that added or moved 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

@@ -123,9 +123,13 @@ 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@1.84.0) and
-* the official plan/pricing/model docs; see the dsh-commandcode-upstream skill
-* for the extraction procedures. Keeping the snapshot in its own module
+* bundle's model table (`dist/cli.mjs`, re-verified at command-code@1.86.1), the
+* live model catalog (`GET /provider/v1/models?view=client`, the authority for
+* capability fields since 1.82.4), and the official plan/pricing/model docs; see
+* the dsh-commandcode-upstream skill for the extraction procedures. The
+* 2026-10-21 sync moves the CLI from 1.84.0 to 1.86.1 and picks up the Ornith
+* 1.5 122B launch pair in the catalog, the ZDR exclusion-set prune and the
+* MiniMax M3.1 Flash promo extension. Keeping the snapshot in its own module
 * confines those frequent sync diffs here: src/adapter.ts holds only the stable
 * wire/runtime logic. The read helpers live here too, for the same reason.
 *
@@ -466,6 +470,20 @@ const KNOWN_EFFORTS = {
 		"medium",
 		"high"
 	],
+	"minimax/minimax-m3.1-flash": [
+		"low",
+		"medium",
+		"high",
+		"xhigh",
+		"max"
+	],
+	"minimax/minimax-m3.1-flash:free": [
+		"low",
+		"medium",
+		"high",
+		"xhigh",
+		"max"
+	],
 	"gpt-6.1-sol": [
 		"low",
 		"medium",
@@ -495,13 +513,6 @@ const KNOWN_EFFORTS = {
 		"medium",
 		"high",
 		"xhigh"
-	],
-	"stealth/cat-jam:free": [
-		"low",
-		"medium",
-		"high",
-		"xhigh",
-		"max"
 	]
 };
 /**
@@ -571,11 +582,15 @@ const KNOWN_IMAGE_MODELS = /* @__PURE__ */ new Set([
 	"meta/muse-spark-open",
 	"nvidia/nemotron-3.5-super-vl",
 	"mistral/mistral-large-4",
+	"minimax/minimax-m3.1-flash",
+	"minimax/minimax-m3.1-flash:free",
 	"moonshotai/Kimi-K2.5",
 	"moonshotai/Kimi-K2.6",
 	"moonshotai/Kimi-K2.7-Code",
 	"moonshotai/Kimi-K2.7-Code-Highspeed",
 	"moonshotai/Kimi-K3",
+	"ornith/ornith-1.5-122b",
+	"ornith/ornith-1.5-122b:free",
 	"sakana/fugu-ultra",
 	"stepfun/Step-3.7-Flash",
 	"stepfun/Step-5-Preview",
@@ -617,8 +632,10 @@ const KNOWN_IMAGE_MODELS = /* @__PURE__ */ new Set([
 * `minimax/minimax-m3-free` is the one entry the public catalog's default view
 * (`/provider/v1/models`) does not serve through the picker (it is CLI/pricing-visible
 * and hidden from the picker); it stays listed because the CLI carries it and a Go-plan
-* request can still name it. Both this row and `stealth/cat-jam:free` ARE served
-* by the `?view=client` catalog, which is where the 1.82.4 verdict comes from.
+* request can still name it. At the 1.84.0 sync both this row and
+* `stealth/cat-jam:free` were also served by the `?view=client` catalog, which
+* is where the 1.82.4 verdict came from; the catalog stopped serving cat-jam on
+* 2026-10-20, and the artifact followed at 1.86.1 (see the prune note below).
 *
 * command-code@1.82.4 moved the authority for this verdict: `knownModelSupportsZdr`
 * no longer negates a bundled Set, it returns `resolveKnownCatalogModel({model,
@@ -656,33 +673,45 @@ const KNOWN_IMAGE_MODELS = /* @__PURE__ */ new Set([
 * UNION of the artifact's exclusion set and the catalog's `zdr:false` list —
 * neither source alone is complete, which is why this set is not simply "what
 * the CLI says".
+*
+* The 2026-10-20 catalog-only sync changed no membership: `stealth/cat-jam:free`
+* left both catalog views (its `zdr:false` verdict is no longer served), but the
+* 1.84.0 artifact's exclusion set still named it and this set is the union, so
+* membership stayed at 25. The MiniMax M3.1 Flash launch pair is ZDR-covered
+* (`zdr:true` on both ids) and joins no set.
+*
+* 2026-10-21 (command-code@1.86.1 sync) prunes the set 25 -> 18, and for the
+* first time the two sources agree exactly: the 1.86.1 artifact's
+* `modelSupportsZdr` set and the live catalog's `zdr:false` rows are the same 18
+* ids (`knownModelSupportsZdr` is gone from the artifact). +3: `claude-fable-5`,
+* `claude-fable-5-1` and `tencent/hy4-preview`. -10: the nine models the catalog
+* flipped to `zdr:true` (Muse Spark 1.1 / 1.2 / 1.3, Muse Wonder 1.0, Grok 4.5 /
+* 4.6, MiMo V2.6 Flash / Pro, GLM-5.2 Fast) plus `stealth/cat-jam:free`, which
+* no source serves any more. Cat-jam is removed by explicit decision (see the
+* decision record, chapter 7 item 13): keeping a retired id in the negative set
+* is defense for stale sessions, not evidence, and the 1.86.1 artifact itself
+* dropped it. A verdict flip here is positive evidence, never "listed before,
+* absent now".
 */
 const KNOWN_NON_ZDR_MODELS = /* @__PURE__ */ new Set([
 	"MiniMaxAI/MiniMax-M3",
 	"Qwen/Qwen3.8-Max-0902",
+	"claude-fable-5",
+	"claude-fable-5-1",
 	"deepseek/deepseek-v4.1-flash-fast",
-	"meta/muse-spark-1.1",
-	"meta/muse-spark-1.2",
+	"meituan/LongCat-2.0",
 	"meta/muse-spark-1.2-contributor",
-	"meta/muse-spark-1.3",
 	"meta/muse-spark-1.3-contributor",
-	"meta/muse-wonder-1.0",
-	"meituan/LongCat-2.0",
 	"minimax/minimax-m3-free",
 	"poolside/laguna-s-2.1-free",
 	"reflection/beam:free",
 	"sakana/fugu-ultra",
 	"stealth/glyph-cluster:free",
-	"stealth/cat-jam:free",
 	"stepfun/Step-3.7-Flash",
 	"stepfun/Step-5-Preview",
-	"xai/grok-4.5",
-	"xai/grok-4.6",
-	"xiaomi/mimo-v2.6-flash",
-	"xiaomi/mimo-v2.6-pro",
+	"tencent/hy4-preview",
 	"xiaomi/mimo-v2.6-pro-ultraspeed",
-	"z-ai/glm-5.3-flashx",
-	"zai-org/GLM-5.2-Fast"
+	"z-ai/glm-5.3-flashx"
 ]);
 /**
 * Whether the CLI snapshot lists a ZDR-capable upstream for `modelId`. This is
@@ -721,7 +750,9 @@ const KNOWN_THINKING_MODELS = /* @__PURE__ */ new Set([
 	"thinkingmachines/inkling",
 	"thinkingmachines/inkling-small",
 	"poolside/laguna-s-2.1-free",
-	"meituan/LongCat-2.0"
+	"meituan/LongCat-2.0",
+	"ornith/ornith-1.5-122b",
+	"ornith/ornith-1.5-122b:free"
 ]);
 /**
 * Catalog models the Provider API serves ONLY through `/provider/v1/messages`
@@ -852,9 +883,12 @@ const MODEL_OUTPUT_TOKEN_LIMITS = /* @__PURE__ */ new Map([
 	["meta/muse-spark-1.3", 131072],
 	["meta/muse-spark-1.3-contributor", 131072],
 	["meta/muse-wonder-1.0", 131072],
+	["minimax/minimax-m3.1-flash", 524288],
+	["minimax/minimax-m3.1-flash:free", 524288],
 	["MiniMaxAI/MiniMax-M2.5", 131072],
 	["MiniMaxAI/MiniMax-M2.7", 131072],
-	["MiniMaxAI/MiniMax-M3", 512e3],
+	["MiniMaxAI/MiniMax-M3", 524288],
+	["mistral/mistral-large-4", 262144],
 	["moonshotai/Kimi-K2.6", 262144],
 	["moonshotai/Kimi-K2.7-Code", 262144],
 	["moonshotai/Kimi-K2.7-Code-Highspeed", 262144],
@@ -897,8 +931,8 @@ 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@1.82.4 (2026-10-16) against the
-* live `?view=client` catalog: 93 ids, still a strict superset chain. Mistral
+* Provider-tier. Re-verified at command-code@1.86.1 (2026-10-21) against the
+* live `?view=client` catalog: 104 ids, still 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 Claude Haiku 5.5 at Pro and the free Glyph Cluster preview at Go.
@@ -907,11 +941,12 @@ const MODEL_OUTPUT_TOKEN_LIMITS = /* @__PURE__ */ new Map([
 * train adds Qwen 3.8 Max Prime at GOAT plus Muse Spark Open, Nemotron 3.5
 * Super VL and the free Cat Jam preview at Go, and drops Ling 3.0 Flash Sante,
 * which left the live catalog. Every other
-* tier is unchanged.
+* tier is unchanged. The 1.86.1 sync (2026-10-21) adds only the Ornith 1.5 122B
+* launch pair at Go.
 * 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) and Ling 3.0 Flash Sante
-* (2026-10-16). Per-entry tags below name the
-* releases that added or moved each row.
+* Canary at 1.73.1, Space Bunny Alpha at 1.74.3), Ling 3.0 Flash Sante
+* (2026-10-16) and the retired Cat Jam preview (2026-10-20). Per-entry tags
+* below name the releases that added or moved 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
@@ -950,6 +985,8 @@ const KNOWN_PLANS = {
 	"meta/muse-spark-1.3-contributor": "go",
 	"meta/muse-spark-open": "go",
 	"mistral/mistral-large-4": "go",
+	"minimax/minimax-m3.1-flash": "go",
+	"minimax/minimax-m3.1-flash:free": "go",
 	"moonshotai/Kimi-K2.5": "go",
 	"moonshotai/Kimi-K2.6": "go",
 	"moonshotai/Kimi-K2.7-Code": "go",
@@ -957,12 +994,13 @@ const KNOWN_PLANS = {
 	"moonshotai/Kimi-K3": "go",
 	"nvidia/nemotron-3-ultra-550b-a55b": "go",
 	"nvidia/nemotron-3.5-super-vl": "go",
+	"ornith/ornith-1.5-122b": "go",
+	"ornith/ornith-1.5-122b:free": "go",
 	"poolside/laguna-s-2.1-free": "go",
 	"reflection/beam:free": "go",
 	"stepfun/Step-3.5-Flash": "go",
 	"stepfun/Step-3.7-Flash": "go",
 	"stepfun/Step-5-Preview": "go",
-	"stealth/cat-jam:free": "go",
 	"stealth/glyph-cluster:free": "go",
 	"tencent/hy3-paid": "go",
 	"tencent/hy4-preview": "go",
@@ -1149,6 +1187,11 @@ function modelVisibleForAnyAccount(modelId, accounts) {
 }
 const KNOWN_DEALS = {
 	"MiniMaxAI/MiniMax-M3": { label: "50% off" },
+	"minimax/minimax-m3.1-flash:free": {
+		label: "FREE",
+		free: true,
+		expiresAt: "2026-10-22T10:45:00Z"
+	},
 	"xiaomi/mimo-v2.5-pro": { label: "99% off" },
 	"xiaomi/mimo-v2.5": { label: "98% off" },
 	"poolside/laguna-s-2.1-free": {
@@ -1159,13 +1202,14 @@ const KNOWN_DEALS = {
 		label: "FREE",
 		free: true
 	},
-	"stealth/cat-jam:free": {
+	"stealth/glyph-cluster:free": {
 		label: "FREE",
 		free: true
 	},
-	"stealth/glyph-cluster:free": {
+	"ornith/ornith-1.5-122b:free": {
 		label: "FREE",
-		free: true
+		free: true,
+		expiresAt: "2026-10-22T06:00:00Z"
 	}
 };
 /**
@@ -1603,8 +1647,8 @@ const MODEL_PRICE_ROWS = [
 		],
 		allowance: {
 			go: 10,
-			goat: 80,
-			pro: 90
+			goat: 100,
+			pro: 110
 		}
 	},
 	{
@@ -2372,6 +2416,19 @@ const MODEL_PRICE_ROWS = [
 			pro: 57
 		}
 	},
+	{
+		id: "minimax-m3.1-flash",
+		rates: [
+			.15,
+			.6,
+			.015
+		],
+		allowance: {
+			go: 6,
+			goat: 20,
+			pro: 30
+		}
+	},
 	{
 		id: "mistral-large-4",
 		rates: [
@@ -2502,6 +2559,19 @@ const MODEL_PRICE_ROWS = [
 			pro: 30
 		}
 	},
+	{
+		id: "ornith-1.5-122b",
+		rates: [
+			.16,
+			.64,
+			.02
+		],
+		allowance: {
+			go: 6,
+			goat: 20,
+			pro: 30
+		}
+	},
 	{
 		id: "qwen-3.6-max",
 		rates: [
@@ -6323,7 +6393,7 @@ 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 = "1.84.0";
+const COMMAND_CODE_CLI_VERSION = "1.86.1";
 const DEFAULT_API_BASE = "https://api.commandcode.ai";
 /**
 * The output budget this bundle asks for, and the ceiling it will never exceed.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mars-sea/dsh-commandcode-provider",
-  "version": "0.14.3",
+  "version": "0.14.5",
   "description": "Unofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT). Registers the 'commandcode' provider route with a Models-page card and live model catalog.",
   "icon": "./icon.svg",
   "type": "module",