@mars-sea/dsh-commandcode-provider 0.10.0 → 0.10.1

package/CHANGELOG.md

@@ -6,6 +6,20 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 
 ## [Unreleased]
 
+## [0.10.1] - 2026-09-07
+
+### Added
+
+- **Support the Command Code Provider Chat Completions API** ([#22](https://github.com/Mars-Sea/dsh-commandcode-provider/pull/22)). Accounts with Provider API access now use the documented `POST /provider/v1/chat/completions` transport (a flat OpenAI-compatible request body) instead of the legacy CLI transport. Historical reasoning is replayed as `reasoning_content` for tool-loop continuity, and OpenAI SSE chunks (`reasoning` / `reasoning_content` / `content` / `tool_calls` / `usage`) are parsed into stream output. The legacy `POST /alpha/generate` transport is unchanged (including its no-reasoning-replay behavior) and remains the route for Go-plan accounts plus the automatic fallback when the Provider API answers `upgrade_required`.
+
+### Fixed
+
+- **Switching to Command Code mid-session no longer fails with `input[N].call_id must be <= 64`** ([#23](https://github.com/Mars-Sea/dsh-commandcode-provider/issues/23)). Tool-call ids issued by another provider can exceed the Command Code gateway's 64-character limit and were replayed verbatim, so the stream was rejected once such history existed. Overlong paired ids are now remapped to short per-request aliases (`cc-1`, `cc-2`, …) on both transports, with each call and its result resolving through the same map so the pair stays correlated; ids within the limit still pass through unchanged.
+
+### Changed
+
+- **Synced with the official command-code@1.50.0 CLI** (2026-09-06: re-verified with no snapshot changes). `COMMAND_CODE_CLI_VERSION` is now `1.50.0`. Re-verified against the official sources: wire protocol (both the `/alpha/generate` CLI transport and the `/provider/v1/chat/completions` Provider transport), endpoints, auth flow, model catalog, subscription plan maps, deals, and peak/off-peak windows are all identical to 1.49.1.
+
 ## [0.10.0] - 2026-09-04
 
 > **First stable release for the dsh 0.1.2 line.** This release requires **dsh 0.1.2-rc.1 or later** and is published on the `latest` npm tag. It graduates the 0.10.0-alpha.x line (command-code syncs up to 1.47.0) to stable. The previous stable line — 0.9.1 for older Harness releases (the 0.5.0 era) — is no longer under active maintenance; it stays on npm for existing users but receives no further updates.

package/README.md

@@ -151,7 +151,7 @@ When your deployment's dsh shell mounts the web capability (`@deepseek-ai/dsh-we
 - **Image input is model-gated** — only Vision models accept images; text-only models refuse them.
 - Switching to a text-only model in an image-bearing session is rejected by dsh — pick a model marked *`Image`* or remove the images first.
 - **No `stop` sequences** — requests carrying one fail.
-- Reasoning blocks are not replayed into later turns; only tool calls with a paired tool result are replayed.
+- On the legacy `/alpha/generate` transport, reasoning blocks are not replayed into later turns; on the `/provider/v1/chat/completions` transport, historical reasoning is passed back as `reasoning_content` so tool-calling loops can keep their chain of thought. Only tool calls with a paired tool result are replayed on both transports.
 - The model catalog is browsable without a key; chat requests need one.
 
 ## Permissions & privacy

package/README.zh-CN.md

@@ -149,7 +149,7 @@ llm-commandcode:
 - **图片输入按模型能力限制**：仅 Vision 模型接受图片，纯文本模型会直接拒绝。
 - 含图片的会话切换到纯文本模型会被 dsh 拒绝——请改选带 *`Image`* 标记的模型，或先移除图片。
 - **不支持 `stop` 序列**：携带它的请求会报错。
-- 推理块不会重放到后续轮次；只有带配对工具结果的工具调用会被重放。
+- 在旧版 `/alpha/generate` 传输中，推理块不会重放到后续轮次；在 `/provider/v1/chat/completions` 传输中，历史推理会以 `reasoning_content` 回传，以便工具调用循环保留思维链。两种传输都只重放带配对工具结果的工具调用。
 - 模型目录无需 key 即可浏览；对话请求需要 key。
 
 ## 权限与隐私

package/lib/client.js

@@ -1736,7 +1736,7 @@ window.__ModuleLoader__.load({
 		}
 		//#endregion
 		//#region package.json
-		var version = "0.10.0";
+		var version = "0.10.1";
 		var repository = {
 			"type": "git",
 			"url": "git+https://github.com/Mars-Sea/dsh-commandcode-provider.git"

package/lib/index.d.ts

@@ -7,12 +7,14 @@ import { Context } from "@deepseek-ai/cordis";
 import { AttachmentStore } from "@deepseek-ai/dsh-attachment";
 import { CommandDefinition } from "@deepseek-ai/dsh-commands";
 //#region src/adapter.d.ts
-declare const COMMAND_CODE_CLI_VERSION = "1.47.0";
+declare const COMMAND_CODE_CLI_VERSION = "1.50.0";
 declare const DEFAULT_API_BASE = "https://api.commandcode.ai";
 declare const DEFAULT_GENERATE_MAX_TOKENS = 64000;
 declare const DEFAULT_MAX_OUTPUT_TOKENS = 65536;
 /** How long the picker's plan-filter billing facts stay cached before refetching. */
 declare const BILLING_ACCESS_TTL_MS: number;
+/** Endpoint protocol selected for one generate call. */
+type CommandCodeProtocol = 'cli' | 'openai';
 /** Head-of-request timeout: how long to wait for the first response byte. */
 declare const DEFAULT_REQUEST_TIMEOUT_MS = 60000;
 /** Stream idle timeout: a generation that stalls this long is a dead connection. */
@@ -43,6 +45,13 @@ interface CommandCodeConnectionOptions {
    * keep the full catalog visible. Set false to always list every model.
    */
   filterModelsByPlan?: boolean;
+  /**
+   * Optional protocol override. `'auto'` (default) uses billing/cache plus
+   * Provider API fallback; `'cli'` forces `/alpha/generate`; `'openai'` forces
+   * `/provider/v1/chat/completions`. This is a connection-level test/operator
+   * seam and is intentionally not part of the plugin's user settings schema.
+   */
+  protocol?: 'auto' | CommandCodeProtocol;
 }
 /**
  * Resolve the durable attachment service, or undefined when the host does not
@@ -154,6 +163,7 @@ declare class CommandCodeAdapter<C extends CommandCodeConnectionOptions = Comman
   private readonly resolveAttachments;
   private readonly billingAccess;
   private readonly billingAccessInflight;
+  private readonly protocolCache;
   constructor(deps: CommandCodeAdapterDeps<C>);
   /**
    * Display metadata for the picker's provider group header. The base class
@@ -203,6 +213,18 @@ declare class CommandCodeAdapter<C extends CommandCodeConnectionOptions = Comman
    * to `undefined` (fail-open) rather than breaking the picker.
    */
   private fetchBillingAccess;
+  /** Fresh cached billing tier weight for a key, or undefined when not known. */
+  private cachedBillingTierWeight;
+  /** Cached protocol decision for a key, or undefined when expired/unknown. */
+  private cachedProtocolUseCli;
+  private rememberProtocol;
+  /**
+   * Choose the initial protocol for one request. A fresh protocol cache entry
+   * wins; otherwise a cached (not network-fetched) billing tier of Go is
+   * treated as CLI-only. Unknown accounts default to Provider API and fall
+   * back only after an `upgrade_required` rejection.
+   */
+  private resolveProtocol;
   /**
    * Fetch account, usage, credit, and subscription state from the Command
    * Code account endpoints (`/alpha/whoami`, `/alpha/usage/summary`,
@@ -445,7 +467,7 @@ declare const KNOWN_EFFORTS: Readonly<Record<string, readonly string[]>>;
  */
 declare const KNOWN_IMAGE_MODELS: ReadonlySet<string>;
 /**
- * Models the official CLI's model table (command-code@1.46.0) marks
+ * Models the official CLI's model table (command-code@1.50.0) marks
  * `reasoning:!0` but defines no selectable `reasoning_effort` levels — they
  * think automatically, with Command Code driving the depth. This is the
  * authoritative "thinks, effort not adjustable" set: `KNOWN_EFFORTS` (which
@@ -453,7 +475,7 @@ declare const KNOWN_IMAGE_MODELS: ReadonlySet<string>;
  * effort levels, and this snapshot is not surfaced in the picker's compact
  * description — it exists for programmatic consumers.
  *
- * Source: the command-code@1.46.0 bundled model table (dist/cli.mjs),
+ * Source: the command-code@1.50.0 bundled model table (dist/cli.mjs),
  * cross-checked with https://commandcode.ai/docs/reference/cli/models.
  * (`stealth/ox-alpha` left this set in command-code@1.32.1, which gave it
  * selectable `['low', 'high', 'max']` efforts; the preview then ended in
@@ -515,8 +537,8 @@ declare function compareByPlan(a: {
 }): number;
 /**
  * Subscription plan table, synced from the official CLI bundle's plan maps
- * (`Nn`/`$n` in command-code@1.31.0 `dist/cli.mjs`, re-verified unchanged
- * against 1.32.2 where they appear as `Zn`/`er`): subscription `planId`
+ * (located by the `"individual-go"` key in command-code@1.50.0 `dist/cli.mjs`,
+ * re-verified unchanged through 1.50.0): subscription `planId`
  * prefix → display name and the plan's monthly credit total. This is the
  * account's own subscription (from `/alpha/billing/subscriptions`) — distinct
  * from {@link KNOWN_PLANS}, which maps catalog models to their minimum tier.