dsh-opencode-go 0.1.3 → 0.1.5

package/README.md

@@ -9,6 +9,10 @@
 
 ## 安装与使用
 
+插件 `0.1.5` 起支持 DSH `0.1.5-rc.1`、`0.1.5-rc.2` 和 `0.1.6-alpha.1`。使用 DSH `0.1.5` 的用户可直接升级插件，无需升级 DSH。
+
+npm 包通过 `engines.dsh` 明确声明宿主版本要求，并保留 DSH 组件的 peerDependencies。dshmarket 中本插件的安装来源也是该 npm 包，市场会将其安装到选定的 DSH profile。
+
 ### Web
 
 ```sh
@@ -78,6 +82,29 @@ Web 用户可直接在 **设置 → OpenCode Go** 中修改配置。启用开关
 
 ## 常见问题
 
+### DSH 0.1.5 安装插件后无法启动
+
+插件 `0.1.0`–`0.1.4` 使用了 DSH `0.1.6` 新增的图片接口，在旧版 DSH 上可能出现 `IMAGE_OFFLOAD_REQUIRED_CODE` 导出不存在的启动错误。升级插件到 `0.1.5` 或更新版本后重启即可：
+
+```sh
+dsh plugin --profile web add dsh-opencode-go@0.1.5
+```
+
+Headless 用户将 `web` 换成 `headless`。修复保留了两版宿主的图片处理方式：DSH `0.1.5` 在请求超过图片预算时将最旧图片转成占位文本，DSH `0.1.6` 继续由宿主记录并处理图片卸载。
+
+### 新版本是否必须等待一天才能安装
+
+npm 本身没有统一的 24 小时安装等待期。DSH 插件命令底层使用 pnpm；pnpm 11 起默认设置 `minimumReleaseAge: 1440`，按包名或 `latest` 安装、升级时可能继续选中发布满一天的旧版本。默认的非严格策略允许上面显式指定 `@0.1.5` 的安装；如果 profile 显式配置了严格的发布时间限制，则仍会被阻止。
+
+需要立即安装该修复时，可在对应 profile 的 `pnpm-workspace.yaml`（默认位于 `~/.dsh/profiles/web/`）中，将此版本合并到已有的例外列表，再运行上面的安装命令：
+
+```yaml
+minimumReleaseAgeExclude:
+  - dsh-opencode-go@0.1.5
+```
+
+保留文件中的其他设置和已有例外。此项仅豁免本插件的 `0.1.5`，不改变其他依赖的等待策略。参见 [pnpm 发布时间限制文档](https://pnpm.io/settings/dependency-resolution#minimumreleaseage)。市场目录、兼容性缓存或 npm 镜像也可能晚于官方 registry 更新；页面仍显示旧版本不代表新版尚未发布。
+
 
 ### 提示 `opencode-go` 路由已被占用
 
@@ -89,7 +116,9 @@ Web 用户可直接在 **设置 → OpenCode Go** 中修改配置。启用开关
 
 网关和在线配置已收录、且使用 Anthropic Messages、OpenAI Chat Completions 或 OpenAI Responses 协议的新模型，在下次读取或刷新列表时即可使用。刷新会绕过已有会话的目录缓存；直接请求尚未缓存的新模型也会立即重新同步。设置页显示完整模型列表。
 
-网关已公布 ID 但尚无有效协议/能力配置的模型仍会显示，并标注配置暂不可用；调用时会说明原因。仅凭模型 ID 无法可靠推断调用方式。上游新增全新协议或协议特例时，仍可能需要适配。
+网关已公布 ID 但尚无有效协议/能力配置的模型会在设置页的发现结果中标注配置暂不可用，暂不进入对话模型选择器，避免一个未配置的模型阻断整个列表；直接调用时会说明原因。配置补齐后，刷新列表即可使用。仅凭模型 ID 无法可靠推断调用方式。上游新增全新协议或协议特例时，仍可能需要适配。
+
+模型具有推理能力但没有可调节的推理档位时（如 `union-alpha`），仍可正常选择和使用，只是不显示推理强度选项。
 
 在线配置暂时不可达时，优先复用本次运行中成功获取的配置，以 pi-ai 内置配置作为备用。网关目录不可达时，已有请求可以使用上次目录；设置页刷新会显示失败，避免把旧目录误认为最新结果。`refreshMinutes` 只控制已有模型请求的缓存时长，不阻止主动读取列表获取新模型。
 

package/docs/verification.md

@@ -59,4 +59,18 @@ A read-only check against the live OpenCode Go listing and models.dev resolved 3
 
 ## Remaining limits
 
-Real paid OpenCode Go completions, Desktop, non-macOS platforms, and other DSH releases are not verified. The automated gateway tests preserve the adapter's request and replay semantics but cannot establish account validity or live provider availability.
+Real paid OpenCode Go completions, Desktop, non-macOS platforms, and DSH releases outside the versions documented here are not verified. The automated gateway tests preserve the adapter's request and replay semantics but cannot establish account validity or live provider availability.
+
+## DSH 0.1.5 compatibility (plugin 0.1.5)
+
+Issue #1 reproduced as an ESM import failure before plugin activation: DSH 0.1.5 lacks `IMAGE_OFFLOAD_REQUIRED_CODE`, `requiredImageOffload`, and `projectOffloadedImages`. The regression test failed against both actual published `dsh-llm` 0.1.5 release candidates before the fix.
+
+`npm test` builds the distributed artifact and runs `tests/host-compatibility.spec.ts` in fresh Node processes against the published LLM packages `0.1.5-rc.1`, `0.1.5-rc.2`, and `0.1.6-alpha.1`. The two older versions are pinned npm aliases in development dependencies. A resolution hook selects the LLM package for both the plugin and Cordis Loader; it does not mock that package's exports. This focused matrix does not replace full CLI/profile checks.
+
+The fixture verifies native ESM loading, Loader activation, model listing, streamed text, image transport, repeated-image byte accounting, nested oldest-image offloading, immutable history, and a second check against encoded image sizes. All external model metadata is replaced by an offline fixture, and completions go to a loopback gateway with a fake credential.
+
+The compatibility bridge uses the host's own functions. On 0.1.5 it preserves the stock adapter's two-pass transient projection (estimated bytes before reading images, exact encoded bytes afterward). On 0.1.6 it preserves durable offload marks and the `IMAGE_OFFLOAD_REQUIRED` retry signal; it never silently substitutes legacy offloading on a modern host. The existing conversion suite additionally checks surface-marked images, path descriptions, and unsupported image roles.
+
+Validation: 146 tests passed, Host and Client type checks passed, and the package built successfully on Node.js 24.14.1.
+
+Full installed checks also passed against separate npm CLI installations whose entire DSH dependency closures were pinned to `0.1.5-rc.1` and `0.1.5-rc.2` respectively (not just the CLI version). The `0.1.5` plugin tarball was installed through `dsh plugin` into each installation's Web and Headless profiles under isolated `DSH_HOME` directories. Both versions passed `verify:installed` for package resolution, catalog, streaming, request headers, and unload; both passed `verify:headless` through the official launcher and loopback gateway. Browser checks confirmed the Web shell and OpenCode Go settings section load, including the API-key field, advanced settings, and enable switch, with no page errors.

package/lib/client.js

@@ -40,7 +40,7 @@ if (!document.querySelector("style[data-plugin-css=" + JSON.stringify(id) + "]")
   style.textContent = ".BtKYva_field{flex-direction:column;gap:6px;padding:12px 0;display:flex}.BtKYva_field+.BtKYva_field{border-top:.5px solid var(--dsw-alias-border-l2)}.BtKYva_head{align-items:center;gap:8px;display:flex}.BtKYva_label{min-width:0;color:var(--dsw-alias-label-primary);flex:1;font-size:13px;font-weight:500;line-height:1.5}.BtKYva_badges{align-items:center;gap:8px;display:inline-flex}.BtKYva_reset{font:inherit;color:var(--dsw-alias-label-secondary);cursor:pointer;background:0 0;border:none;padding:0;font-size:12px;line-height:1.5}.BtKYva_reset:hover:not(:disabled){color:var(--dsw-alias-label-primary)}.BtKYva_reset:disabled{cursor:default}.BtKYva_input{border:.5px solid var(--dsw-alias-border-l4);background:var(--dsw-alias-bg-layer-3);height:34px;font:inherit;color:var(--dsw-alias-label-primary);border-radius:8px;padding:0 12px;font-size:13px;line-height:1.5}.BtKYva_input:focus-visible{border-color:var(--dsw-alias-brand-primary);outline:none}.BtKYva_input:disabled{color:var(--dsw-alias-label-tertiary);cursor:default}.BtKYva_inputInvalid{border-color:var(--dsw-alias-label-error);}.BtKYva_invalid{color:var(--dsw-alias-label-error);margin:0;font-size:12px;line-height:1.5}.BtKYva_hint{color:var(--dsw-alias-label-tertiary);margin:0;font-size:12px;line-height:1.5}.BtKYva_intro{color:var(--dsw-alias-label-secondary);margin:0 0 8px;font-size:13px;line-height:1.5}.BtKYva_disclosure{font:inherit;text-align:left;cursor:pointer;background:0 0;border:none;align-items:center;gap:8px;margin:0;padding:0;display:flex}.BtKYva_disclosure:hover .BtKYva_label{color:var(--dsw-alias-brand-primary)}.BtKYva_chevron,.BtKYva_chevronOpen{color:var(--dsw-alias-label-tertiary);flex:none}.BtKYva_chevron{transform:rotate(-90deg)}.BtKYva_advanced{flex-direction:column;gap:4px;padding:4px 0 0 22px;display:flex}.BtKYva_advanced .BtKYva_field+.BtKYva_field{border-top:none}.BtKYva_chips{flex-wrap:wrap;gap:6px;display:flex}.BtKYva_actions{align-items:center;gap:8px;padding-top:12px;display:flex}.BtKYva_failedNote{color:var(--dsw-alias-label-error);margin:0;font-size:12px;line-height:1.5}";
   document.head.appendChild(style);
 }
-var Section_default = { "badges": "BtKYva_badges", "field": "BtKYva_field", "inputInvalid": "BtKYva_inputInvalid", "input": "BtKYva_input", "hint": "BtKYva_hint", "actions": "BtKYva_actions", "label": "BtKYva_label", "invalid": "BtKYva_invalid", "reset": "BtKYva_reset", "intro": "BtKYva_intro", "disclosure": "BtKYva_disclosure", "head": "BtKYva_head", "chevronOpen": "BtKYva_chevronOpen", "chips": "BtKYva_chips", "failedNote": "BtKYva_failedNote", "chevron": "BtKYva_chevron", "advanced": "BtKYva_advanced" };
+var Section_default = { "chevronOpen": "BtKYva_chevronOpen", "actions": "BtKYva_actions", "input": "BtKYva_input", "reset": "BtKYva_reset", "hint": "BtKYva_hint", "head": "BtKYva_head", "advanced": "BtKYva_advanced", "inputInvalid": "BtKYva_inputInvalid", "disclosure": "BtKYva_disclosure", "field": "BtKYva_field", "label": "BtKYva_label", "chevron": "BtKYva_chevron", "invalid": "BtKYva_invalid", "badges": "BtKYva_badges", "intro": "BtKYva_intro", "chips": "BtKYva_chips", "failedNote": "BtKYva_failedNote" };
 
 // src/client/Section.tsx
 var import_jsx_runtime = require("react/jsx-runtime");
@@ -885,7 +885,7 @@ if (!document.querySelector("style[data-plugin-css=" + JSON.stringify(id2) + "]"
   style.textContent = ".dmPm3q_root{min-width:0;display:inline-flex;position:relative}.dmPm3q_trigger{color:inherit;opacity:.75;font:inherit;cursor:pointer;white-space:nowrap;background:0 0;border:0;border-radius:6px;padding:4px 6px;font-size:12px}.dmPm3q_trigger:hover,.dmPm3q_trigger:focus-visible{opacity:1;background:color-mix(in srgb, currentColor 8%, transparent)}.dmPm3q_panel{z-index:100;border:1px solid color-mix(in srgb, currentColor 18%, transparent);width:280px;max-width:calc(100vw - 32px);color:var(--dsw-alias-label-primary,CanvasText);background:var(--dsw-specific-menu,Canvas);border-radius:12px;padding:16px;font-size:12px;position:absolute;bottom:calc(100% + 12px);right:0;box-shadow:0 8px 30px #0002}.dmPm3q_hint{opacity:.65;font-size:11px;line-height:1.6}.dmPm3q_window{margin-top:14px}.dmPm3q_row{justify-content:space-between;margin-bottom:5px;display:flex}.dmPm3q_window progress{accent-color:#39a878;width:100%;height:5px;margin-bottom:5px;display:block}.dmPm3q_window progress::-webkit-progress-bar{background:color-mix(in srgb, currentColor 15%, transparent);border-radius:4px}.dmPm3q_window progress::-webkit-progress-value{background:#39a878;border-radius:4px}.dmPm3q_window progress::-moz-progress-bar{background:#39a878;border-radius:4px}";
   document.head.appendChild(style);
 }
-var UsagePill_default = { "hint": "dmPm3q_hint", "row": "dmPm3q_row", "window": "dmPm3q_window", "root": "dmPm3q_root", "trigger": "dmPm3q_trigger", "panel": "dmPm3q_panel" };
+var UsagePill_default = { "window": "dmPm3q_window", "panel": "dmPm3q_panel", "hint": "dmPm3q_hint", "root": "dmPm3q_root", "row": "dmPm3q_row", "trigger": "dmPm3q_trigger" };
 
 // src/client/UsagePill.tsx
 var import_jsx_runtime2 = require("react/jsx-runtime");

package/lib/index.js

@@ -47,14 +47,14 @@ var __callDispose = (stack, error, hasError) => {
 // src/index.ts
 import { launchEnvironmentOf } from "@deepseek-ai/dsh-launch-environment";
 import { credentialRef } from "@deepseek-ai/dsh-credentials";
-import { LlmError as LlmError6, assertUsableApiKey, resolveImageAttachmentAccess } from "@deepseek-ai/dsh-llm";
+import { LlmError as LlmError7, assertUsableApiKey, resolveImageAttachmentAccess } from "@deepseek-ai/dsh-llm";
 
 // src/adapter.ts
 import { randomUUID } from "node:crypto";
 import { getSupportedThinkingLevels } from "@earendil-works/pi-ai";
 import {
   LlmAdapter,
-  LlmError as LlmError5,
+  LlmError as LlmError6,
   ReasoningEffortId,
   attributionHeaders as attributionHeaders2,
   contentHasImage as contentHasImage2
@@ -62,7 +62,7 @@ import {
 
 // src/conversion/context.ts
 import { brandString } from "@deepseek-ai/dsh-brand";
-import { contentHasImage, IMAGE_OFFLOAD_REQUIRED_CODE, LlmError as LlmError2, offloadedImageText, projectOffloadedImages, requestImageHandleText, requiredImageOffload } from "@deepseek-ai/dsh-llm";
+import { contentHasImage, LlmError as LlmError3, offloadedImageText, requestImageHandleText } from "@deepseek-ai/dsh-llm";
 
 // src/conversion/replay.ts
 import { LlmError } from "@deepseek-ai/dsh-llm";
@@ -267,6 +267,40 @@ var DEFAULT_MAX_REQUEST_IMAGE_BYTES = 20 * 1024 * 1024;
 var DEFAULT_REQUEST_IMAGE_PIXEL_BUDGET = 2048 * 2048;
 var DEFAULT_REQUEST_IMAGE_MAX_BYTES = 1024 * 1024;
 
+// src/conversion/image-offload.ts
+import * as llm from "@deepseek-ai/dsh-llm";
+var api = llm;
+function projectRequestImages(messages, policy) {
+  if (api.requiredImageOffload !== void 0 && api.projectOffloadedImages !== void 0) {
+    if (!policy.exact) return messages;
+    if (policy.maxBytes !== void 0) {
+      const offloadImages = api.requiredImageOffload(
+        messages,
+        { representation: "base64", maxBytes: policy.maxBytes },
+        (block) => policy.byteLength(block.attachment)
+      );
+      if (offloadImages > 0) {
+        throw new llm.LlmError(
+          `pi-ai request images exceed the ${policy.maxBytes}-byte base64 bound; ${offloadImages} more oldest occurrence(s) must be offloaded.`,
+          api.IMAGE_OFFLOAD_REQUIRED_CODE ?? "IMAGE_OFFLOAD_REQUIRED",
+          { offloadImages }
+        );
+      }
+    }
+    return api.projectOffloadedImages(messages, policy.placeholder);
+  }
+  if (api.offloadRequestImagesWithPolicy === void 0) {
+    throw new llm.LlmError("The DSH host has no supported image offload API", "UNSUPPORTED_CONTENT");
+  }
+  return api.offloadRequestImagesWithPolicy(messages, {
+    representation: "base64",
+    byteQuantum: 1,
+    maxBytes: policy.maxBytes,
+    byteLength: policy.byteLength,
+    placeholder: policy.placeholder
+  });
+}
+
 // src/conversion/context.ts
 function flattenText(message) {
   return message.content.filter((block) => block.type === "text").map((block) => block.text).join("");
@@ -277,7 +311,7 @@ function toolResultText(blocks) {
 function assertSupportedImageRoles(messages) {
   for (const message of messages) {
     if (message.role !== "user" && contentHasImage(message.content)) {
-      throw new LlmError2(
+      throw new LlmError3(
         `pi-ai cannot represent an image in an in-history ${message.role} message`,
         "UNSUPPORTED_CONTENT"
       );
@@ -381,7 +415,7 @@ function textOnlyContext(options, onReplayDegrade) {
   const messages = [];
   for (const message of split.messages) {
     if (contentHasImage(message.content)) {
-      throw new LlmError2("pi-ai image conversion requires the durable attachment service", "UNSUPPORTED_CONTENT");
+      throw new LlmError3("pi-ai image conversion requires the durable attachment service", "UNSUPPORTED_CONTENT");
     }
     if (message.role === "system") {
       messages.push({ role: "user", content: flattenText(message), timestamp: 0 });
@@ -424,25 +458,21 @@ async function toPiContextWithImages(options, images, onReplayDegrade) {
   };
   assertSupportedImageRoles(options.messages);
   const split = splitSystemPrompt(options);
-  const requestImages = await prepareRequestImages(split.messages, attachments, requestImagePolicy, options.signal);
-  if (maxRequestImageBytes !== void 0) {
-    const offloadImages = requiredImageOffload(
-      split.messages,
-      { representation: "base64", maxBytes: maxRequestImageBytes },
-      (block) => requestImages.get(block.attachment.attachmentId).bytes
-    );
-    if (offloadImages > 0) {
-      throw new LlmError2(
-        `pi-ai request images exceed the ${maxRequestImageBytes}-byte base64 bound; ${offloadImages} more oldest occurrence(s) must be offloaded.`,
-        IMAGE_OFFLOAD_REQUIRED_CODE,
-        { offloadImages }
-      );
-    }
-  }
-  const exactMessages = projectOffloadedImages(
-    split.messages,
-    (ref) => offloadedImageText(ref, resolveImageAccess(ref))
-  );
+  const projection = {
+    maxBytes: maxRequestImageBytes,
+    placeholder: (ref) => offloadedImageText(ref, resolveImageAccess(ref))
+  };
+  const requestMessages = projectRequestImages(split.messages, {
+    ...projection,
+    exact: false,
+    byteLength: (ref) => Math.min(ref.bytes, requestImagePolicy.maxBytes)
+  });
+  const requestImages = await prepareRequestImages(requestMessages, attachments, requestImagePolicy, options.signal);
+  const exactMessages = projectRequestImages(requestMessages, {
+    ...projection,
+    exact: true,
+    byteLength: (ref) => requestImages.get(ref.attachmentId).bytes
+  });
   const toolNames = /* @__PURE__ */ new Map();
   const messages = [];
   for (const message of exactMessages) {
@@ -477,7 +507,7 @@ async function toPiContextWithImages(options, images, onReplayDegrade) {
 
 // src/conversion/stream.ts
 import { brandString as brandString2 } from "@deepseek-ai/dsh-brand";
-import { CONTEXT_WINDOW_EXCEEDED_CODE, EMPTY_RESPONSE_CODE, isContextWindowExceededError, isQuotaExceededError, LlmError as LlmError3, QUOTA_EXCEEDED_CODE } from "@deepseek-ai/dsh-llm";
+import { CONTEXT_WINDOW_EXCEEDED_CODE, EMPTY_RESPONSE_CODE, isContextWindowExceededError, isQuotaExceededError, LlmError as LlmError4, QUOTA_EXCEEDED_CODE } from "@deepseek-ai/dsh-llm";
 import { isContextOverflow } from "@earendil-works/pi-ai";
 function mapUsage(usage) {
   return {
@@ -628,7 +658,7 @@ async function* toStreamChunks(events, contextWindow, callerSignal, requestedMod
         return;
     }
   }
-  throw new LlmError3("pi-ai event stream ended without done/error", "STREAM_CLOSED");
+  throw new LlmError4("pi-ai event stream ended without done/error", "STREAM_CLOSED");
 }
 
 // src/adapter.ts
@@ -640,7 +670,7 @@ import { getBuiltinModels } from "@earendil-works/pi-ai/providers/all";
 import { anthropicMessagesApi } from "@earendil-works/pi-ai/api/anthropic-messages.lazy";
 import { openAICompletionsApi } from "@earendil-works/pi-ai/api/openai-completions.lazy";
 import { openAIResponsesApi } from "@earendil-works/pi-ai/api/openai-responses.lazy";
-import { attributionHeaders, LlmError as LlmError4 } from "@deepseek-ai/dsh-llm";
+import { attributionHeaders, LlmError as LlmError5 } from "@deepseek-ai/dsh-llm";
 
 // src/model-metadata.ts
 var MODEL_METADATA_URL = "https://models.dev/api.json";
@@ -680,9 +710,9 @@ function thinkingLevels(metadata, known) {
   if (known?.reasoning && known.thinkingLevelMap?.off !== null) map.off ??= known.thinkingLevelMap?.off ?? "off";
   return map;
 }
-function modelBaseURL(api, baseURL) {
+function modelBaseURL(api2, baseURL) {
   const base = baseURL.replace(/\/+$/, "");
-  return api === "anthropic-messages" ? base.replace(/\/v1$/, "") : base;
+  return api2 === "anthropic-messages" ? base.replace(/\/v1$/, "") : base;
 }
 function readModelMetadata(body, baseURL, builtin) {
   const provider = record(record(body)["opencode-go"]);
@@ -696,22 +726,22 @@ function readModelMetadata(body, baseURL, builtin) {
     try {
       const metadata = record(value);
       const npm = record(metadata.provider).npm ?? provider.npm;
-      const api = npm === "@ai-sdk/anthropic" ? "anthropic-messages" : npm === "@ai-sdk/openai" ? "openai-responses" : npm === "@ai-sdk/openai-compatible" ? "openai-completions" : void 0;
-      if (api === void 0) throw new Error(`unsupported model protocol ${String(npm)}`);
+      const api2 = npm === "@ai-sdk/anthropic" ? "anthropic-messages" : npm === "@ai-sdk/openai" ? "openai-responses" : npm === "@ai-sdk/openai-compatible" ? "openai-completions" : void 0;
+      if (api2 === void 0) throw new Error(`unsupported model protocol ${String(npm)}`);
       const limit = record(metadata.limit);
       const input = record(metadata.modalities).input;
       if (!Array.isArray(input) || !input.includes("text")) throw new Error("missing text input modality");
       if (typeof metadata.reasoning !== "boolean") throw new Error("missing reasoning capability");
       const exact = builtin.get(id);
-      const family = typeof metadata.family === "string" ? Object.keys(entries).find((key) => record(entries[key]).family === metadata.family && builtin.get(key)?.api === api) : void 0;
-      const known = exact?.api === api ? exact : family === void 0 ? void 0 : builtin.get(family);
-      const compat = api === "openai-completions" ? {
+      const family = typeof metadata.family === "string" ? Object.keys(entries).find((key) => record(entries[key]).family === metadata.family && builtin.get(key)?.api === api2) : void 0;
+      const known = exact?.api === api2 ? exact : family === void 0 ? void 0 : builtin.get(family);
+      const compat = api2 === "openai-completions" ? {
         supportsStore: false,
         supportsDeveloperRole: false,
         maxTokensField: "max_tokens",
         ...record(metadata.interleaved).field === "reasoning_content" ? { requiresReasoningContentOnAssistantMessages: true } : {},
         ...known?.compat
-      } : api === "openai-responses" ? { sessionAffinityFormat: "openai-nosession", ...known?.compat } : { ...known?.compat };
+      } : api2 === "openai-responses" ? { sessionAffinityFormat: "openai-nosession", ...known?.compat } : { ...known?.compat };
       const cost = rates(metadata.cost);
       const tiers = record(metadata.cost).tiers;
       if (Array.isArray(tiers)) {
@@ -724,8 +754,8 @@ function readModelMetadata(body, baseURL, builtin) {
         id,
         name: typeof metadata.name === "string" && metadata.name.length > 0 ? metadata.name : id,
         provider: "opencode-go",
-        api,
-        baseUrl: modelBaseURL(api, baseURL),
+        api: api2,
+        baseUrl: modelBaseURL(api2, baseURL),
         reasoning: metadata.reasoning,
         thinkingLevelMap: thinkingLevels(metadata, known),
         input: input.includes("image") ? ["text", "image"] : ["text"],
@@ -774,9 +804,9 @@ async function fetchLiveModelIds(baseURL) {
       signal: AbortSignal.timeout(MODELS_FETCH_TIMEOUT_MS)
     });
   } catch (error) {
-    throw new LlmError4(`could not reach ${url}`, "DISCOVERY_FAILED", { cause: error });
+    throw new LlmError5(`could not reach ${url}`, "DISCOVERY_FAILED", { cause: error });
   }
-  if (!response.ok) throw new LlmError4(`${url} answered ${response.status}`, "DISCOVERY_FAILED");
+  if (!response.ok) throw new LlmError5(`${url} answered ${response.status}`, "DISCOVERY_FAILED");
   return readLiveModelIds(await response.json());
 }
 function harnessApiKeyAuth() {
@@ -889,7 +919,7 @@ var OpencodeGoCatalog = class {
     let snapshot = await this.snapshot();
     if (!snapshot.models.has(id) && snapshot === cached) snapshot = await this.snapshot(true);
     if (snapshot.unavailable.has(id)) {
-      throw new LlmError4(
+      throw new LlmError5(
         `opencode-go model "${id}" is advertised but cannot be configured: ${snapshot.unavailable.get(id)}; refresh the model list to retry`,
         "MODEL_METADATA_UNAVAILABLE"
       );
@@ -900,7 +930,7 @@ var OpencodeGoCatalog = class {
 async function discoverCatalogModels(catalog) {
   const snapshot = await catalog.snapshot(true);
   if (!snapshot.live) {
-    throw new LlmError4("llm-opencode-go: the live model listing is unreachable; try again later", "DISCOVERY_FAILED");
+    throw new LlmError5("llm-opencode-go: the live model listing is unreachable; try again later", "DISCOVERY_FAILED");
   }
   return [
     ...[...snapshot.models.values()].map((model) => ({
@@ -995,32 +1025,28 @@ var OpencodeGoAdapter = class extends LlmAdapter {
   }
   async listModels(_provider) {
     const snapshot = await this.catalogOf(this.options.config()).snapshot(true);
-    return [...[...snapshot.models.values()].map((model) => ({
+    return [...snapshot.models.values()].map((model) => ({
       provider: PROVIDER_ID,
       id: model.id,
       name: model.name,
       inputModalities: [...model.input]
-    })), ...[...snapshot.unavailable].map(([id, reason]) => ({
-      provider: PROVIDER_ID,
-      id,
-      name: id,
-      description: `Metadata unavailable: ${reason}`
-    }))];
+    }));
   }
   async resolveModel(_provider, model, _signal) {
     const snapshot = await this.catalogOf(this.options.config()).forModel(model);
     const resolved = snapshot.models.get(model);
     if (resolved === void 0) {
-      throw new LlmError5(`opencode-go has no model "${model}"`, "UNKNOWN_MODEL");
+      throw new LlmError6(`opencode-go has no model "${model}"`, "UNKNOWN_MODEL");
     }
     return this.modelInfo(resolved);
   }
   /** Describe one model: capacities plus the reasoning levels it actually offers. */
   modelInfo(model) {
     const reasoning = {};
-    if (model.reasoning) {
+    const levels = model.reasoning ? getSupportedThinkingLevels(model) : [];
+    if (levels.length > 0) {
       reasoning.reasoning = {
-        efforts: getSupportedThinkingLevels(model).map((level) => ({
+        efforts: levels.map((level) => ({
           id: ReasoningEffortId(level),
           name: `${level.charAt(0).toUpperCase()}${level.slice(1)}`
         }))
@@ -1040,7 +1066,7 @@ var OpencodeGoAdapter = class extends LlmAdapter {
     if (effort === void 0) return void 0;
     const supported = getSupportedThinkingLevels(model);
     if (supported.some((level) => level === effort)) return effort;
-    throw new LlmError5(
+    throw new LlmError6(
       `opencode-go model "${model.id}" does not support reasoning effort "${effort}"`,
       "UNSUPPORTED_REASONING_EFFORT"
     );
@@ -1049,17 +1075,17 @@ var OpencodeGoAdapter = class extends LlmAdapter {
     var _stack = [];
     try {
       if (options.stop !== void 0) {
-        throw new LlmError5("llm-opencode-go does not support GenerateOptions.stop", "UNSUPPORTED_OPTION");
+        throw new LlmError6("llm-opencode-go does not support GenerateOptions.stop", "UNSUPPORTED_OPTION");
       }
       const config = this.options.config();
       const snapshot = await this.catalogOf(config).forModel(options.model);
       const model = snapshot.models.get(options.model);
       if (model === void 0) {
-        throw new LlmError5(`opencode-go has no model "${options.model}"`, "UNKNOWN_MODEL");
+        throw new LlmError6(`opencode-go has no model "${options.model}"`, "UNKNOWN_MODEL");
       }
       const apiKey = await this.options.resolveApiKey();
       if (apiKey === void 0 || apiKey.length === 0) {
-        throw new LlmError5("llm-opencode-go: no credential resolved for the route", "MISSING_CREDENTIAL");
+        throw new LlmError6("llm-opencode-go: no credential resolved for the route", "MISSING_CREDENTIAL");
       }
       const reasoning = this.resolveReasoningLevel(model, options.reasoningEffort);
       const consumer = new AbortController();
@@ -1068,14 +1094,14 @@ var OpencodeGoAdapter = class extends LlmAdapter {
       try {
         const containsImage = options.messages.some((message) => contentHasImage2(message.content));
         if (containsImage && !model.input.includes("image")) {
-          throw new LlmError5(`opencode-go model "${model.id}" does not support image input`, "UNSUPPORTED_CONTENT");
+          throw new LlmError6(`opencode-go model "${model.id}" does not support image input`, "UNSUPPORTED_CONTENT");
         }
         let imageRequest;
         if (containsImage) {
           const access = this.options.imageAccess;
           const store = access?.resolveAttachments();
           if (access === void 0 || store === void 0) {
-            throw new LlmError5("llm-opencode-go image input requires the durable attachment service", "UNSUPPORTED_CONTENT");
+            throw new LlmError6("llm-opencode-go image input requires the durable attachment service", "UNSUPPORTED_CONTENT");
           }
           imageRequest = {
             attachments: store,
@@ -1112,7 +1138,7 @@ var OpencodeGoAdapter = class extends LlmAdapter {
           while (true) {
             const result = await watchdog.next(iterator);
             if (timeoutOf(watchdog.signal, "LLM_STREAM_IDLE_TIMEOUT") !== void 0) {
-              throw new LlmError5("opencode-go stream idle timeout", "TIMEOUT");
+              throw new LlmError6("opencode-go stream idle timeout", "TIMEOUT");
             }
             if (result.done) {
               exhausted = true;
@@ -1131,10 +1157,10 @@ var OpencodeGoAdapter = class extends LlmAdapter {
         }
       } catch (error) {
         if (timeoutOf(watchdog.signal, "LLM_STREAM_IDLE_TIMEOUT") !== void 0) {
-          throw new LlmError5("opencode-go stream idle timeout", "TIMEOUT", { cause: error });
+          throw new LlmError6("opencode-go stream idle timeout", "TIMEOUT", { cause: error });
         }
         if (options.signal?.aborted) {
-          throw new LlmError5("opencode-go request aborted by caller", "ABORTED", { cause: error });
+          throw new LlmError6("opencode-go request aborted by caller", "ABORTED", { cause: error });
         }
         throw error;
       }
@@ -1226,7 +1252,7 @@ function apply(ctx, raw) {
     const credentials = ctx.get("credentials");
     const hit = credentials !== void 0 ? (await credentials.resolve(credentialRef(ref)))?.value : launchEnvironmentOf(ctx).get(ref)?.value;
     if (hit !== void 0 && hit.length > 0) return assertUsableApiKey(hit, name, ref);
-    throw new LlmError6(
+    throw new LlmError7(
       `llm-opencode-go: no credential; the profile resolves ${ref}, which is not set \u2014 store ${ref} through the credentials service or export it`,
       "MISSING_CREDENTIAL"
     );
@@ -1288,7 +1314,7 @@ function apply(ctx, raw) {
   syncRoute();
   const undiscover = ctx.llm.registerModelDiscovery(name, async (request) => {
     if (request.provider !== PROVIDER_ID && !(request.baseURL ?? "").includes("opencode.ai")) {
-      throw new LlmError6(
+      throw new LlmError7(
         "llm-opencode-go discovers only OpenCode zen/go endpoints; enter this provider's models by hand",
         "DISCOVERY_UNSUPPORTED"
       );

package/lib/types/conversion/context.d.ts

@@ -36,8 +36,9 @@ export interface PiImageRequestBudget {
 export declare function toPiContext(options: GenerateOptions, images?: undefined, onReplayDegrade?: (reason: string) => void): PiContext;
 /**
  * Convert harness history to a pi-ai Context while resolving durable images.
- * Tool result names are recovered from preceding assistant tool calls. Image
- * occurrences the surface marks offloaded become text placeholders; when the
+ * Tool result names are recovered from preceding assistant tool calls. On DSH
+ * 0.1.5, oldest images over the request budget become transient placeholders.
+ * On newer hosts, occurrences the surface marks offloaded become placeholders; when the
  * retained occurrences' exact base64 payload still exceeds
  * `maxRequestImageBytes`, the call fails with `IMAGE_OFFLOAD_REQUIRED` naming
  * how many more oldest occurrences must be offloaded.

package/lib/types/conversion/image-offload.d.ts

@@ -0,0 +1,12 @@
+import type { Message } from '@deepseek-ai/dsh-llm';
+import type { ImageAttachmentRef } from '@deepseek-ai/dsh-attachment';
+interface ImageProjectionPolicy {
+    maxBytes?: number;
+    byteLength: (ref: ImageAttachmentRef) => number;
+    placeholder: (ref: ImageAttachmentRef) => string;
+    /** False before preparing image bytes, true once encoded sizes are known. */
+    exact: boolean;
+}
+/** Preserve the host generation's image policy, using estimates first and exact sizes second. */
+export declare function projectRequestImages(messages: readonly Message[], policy: ImageProjectionPolicy): readonly Message[];
+export {};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-opencode-go",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "description": "OpenCode Go model provider and settings UI for DeepSeek Harness",
   "type": "module",
   "license": "MIT",
@@ -13,7 +13,8 @@
     "url": "https://github.com/Duskriver/dsh-opencode-go/issues"
   },
   "engines": {
-    "node": "^22.19.0 || >=24.0.0"
+    "node": "^22.19.0 || >=24.0.0",
+    "dsh": ">=0.1.5-rc.1 <0.1.6-0 || 0.1.6-alpha.1"
   },
   "main": "./lib/index.js",
   "types": "./lib/types/index.d.ts",
@@ -60,25 +61,25 @@
   },
   "peerDependencies": {
     "@deepseek-ai/cordis": "4.0.2",
-    "@deepseek-ai/dsh-api-gateway": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-api-remotes": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-api-settings-controller": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-attachment": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-locale": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-store": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-ui-model-selection": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-ui-renderer": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-ui-settings": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-ui-slots": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-credentials": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-fs": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-launch-environment": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-llm": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-settings": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-timeout": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-typert-protocol": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-client-ui-conversation": "0.1.6-alpha.1",
-    "@deepseek-ai/dsh-typert-registry": "0.1.6-alpha.1"
+    "@deepseek-ai/dsh-api-gateway": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-api-remotes": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-api-settings-controller": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-attachment": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-locale": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-store": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-ui-conversation": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-ui-model-selection": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-ui-renderer": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-ui-settings": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-client-ui-slots": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-credentials": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-fs": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-launch-environment": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-llm": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-settings": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-timeout": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-typert-protocol": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1",
+    "@deepseek-ai/dsh-typert-registry": ">=0.1.5-rc.1 <0.1.6 || 0.1.6-alpha.1"
   },
   "dependencies": {
     "@deepseek-ai/dsh-brand": "0.1.6-alpha.1",
@@ -121,6 +122,8 @@
     "anser": "^2.3.5",
     "clsx": "^2.0.0",
     "diff": "^9.0.0",
+    "dsh-llm-v015-rc1": "npm:@deepseek-ai/dsh-llm@0.1.5-rc.1",
+    "dsh-llm-v015-rc2": "npm:@deepseek-ai/dsh-llm@0.1.5-rc.2",
     "esbuild": "^0.25.0",
     "immer": "^10.1.1",
     "jsdom": "29.1.1",