opencode-zen-freex 0.2.14 → 0.2.15

package/MAINTAINING.md

@@ -296,6 +296,17 @@ it. Rewriting the parameters as well looks tidier and breaks the agent.
 **Replacing the wording with something of your own.** That is what 0.1.5 and
 earlier did, and it is a guaranteed refusal.
 
+**Merging a tool call's frames over its id.** The route puts `"id": null` on
+the continuation frames of a call whose first frame named it (measured
+2026-10-17 on `deepseek-v4.1-flash-free`), and a host that keys a tool result
+by the id — dsh writes `tool/result` records keyed by it — fails its turn on
+an empty one and cannot reload the session afterwards ("tool call id requires
+a nonempty string"). Merging frames must read the id as a name that only
+replaces itself, and a call the route never names has to leave with an
+invented one. Both live in `tool-response.mjs` — the merge's keep, and
+`ensureCallIDs` at the two places a call is published — and `stream.mjs`'s
+collapse reads the same rule.
+
 **Trusting one observation.** The gate is not steady: it moved more than once in
 a day while this was being worked out, and identical requests were answered both
 ways minutes apart. Anything measured once is not a fact. Measure it three times,

package/README.md

@@ -84,7 +84,7 @@ bun run check:gate
 
 请求发往 `https://opencode.ai/inference/v1`，按每个模型原生的 Chat Completions、Responses 或 Anthropic Messages 接口来走。流式和普通 JSON 两种回复都支持。
 
-宿主自己的工具会被完整保留。Zen 的模型经常去调 OpenCode 的工具名；这种调用会被对上宿主那个只差大小写的工具（`bash` 对 `Bash`），或者只差大小写和 `_`/`-` 的那个（`todowrite` 对 `todo_write`、`webfetch` 对 `web_fetch`），前提是恰好只有一个对得上。找不到对应工具（或者调用根本没有名字）的，不放进回复里，回复的正文会说明哪个名字被略去了；如果这一轮所有调用都被略去，这一轮就以一段普通回答结束。工具仍然在宿主里执行。
+宿主自己的工具会被完整保留。Zen 的模型经常去调 OpenCode 的工具名；这种调用会被对上宿主那个只差大小写的工具（`bash` 对 `Bash`），或者只差大小写和 `_`/`-` 的那个（`todowrite` 对 `todo_write`、`webfetch` 对 `web_fetch`），前提是恰好只有一个对得上。找不到对应工具（或者调用根本没有名字）的，不放进回复里，回复的正文会说明哪个名字被略去了；如果这一轮所有调用都被略去，这一轮就以一段普通回答结束。上游偶尔还会在工具调用的续帧里发 `"id": null`（实测 2026-10-17），或者整条回复都不给调用 id——插件保证交到宿主手里的调用一律带非空 id（没给的补一个，已有的不会被后来的帧抹掉），因为宿主是靠这个 id 把工具结果对回调用的。工具仍然在宿主里执行。
 
 Zen 的免费层读请求体，也读请求头，只有当整个请求都属于 OpenCode 的同一代时才作答：User-Agent、请求头和工具三者必须一致。当前一共有两代，请求带的工具说明是哪一代：`shell` 和 `read` 属于 2.x，`bash`、`glob`、`grep` 和 `read` 属于 1.x。如果宿主本身就是 OpenCode，它自己的 User-Agent 已经说明是哪一代，这个值会被原样传出去，而不是被钉死，所以永远不会落后。没有任何一方说明时，以工具为准，User-Agent 跟着工具走。
 
@@ -142,6 +142,16 @@ Zen 的免费层会检查 session id 是否是 OpenCode 能生成的那种：时
 
 模型的可用性和限流归 Zen 管，插件拿不到剩余额度可显示。同一个地址反复被拒，也可能被放进一个冷却期，表现得和被拒很像。
 
+## 鸣谢
+
+| 类别 | 项目 |
+| --- | --- |
+| 本插件前身 | [zen-free](https://github.com/magpie-community/plugins/tree/main/packages/zen-free) |
+| 插件载体 | [magpie](https://github.com/yetone/magpie) |
+| 模型提供者 | [anomalyco/opencode](https://github.com/anomalyco/opencode) |
+| 本仓库常用 Agent | [deepseek-harness](https://github.com/deepseek-ai/deepseek-harness) · [hermes-agent](https://github.com/NousResearch/hermes-agent) |
+| 灵感来源 | [9router](https://github.com/decolua/9router) · [opencode2api](https://github.com/jasonxu114514/opencode2api) · [zen-gate](https://github.com/LAGcomcom/zen-gate) |
+
 ## 许可
 
 MIT，分叉自 [zen-free](https://github.com/magpie-community/plugins/tree/main/packages/zen-free)。`LICENSE` 的 MIT 正文原样未改，版权行有两条：上游原作者的 `Copyright (c) 2026 xiaozhou26`，和本分支贡献者的 `Copyright (c) 2026 OpenCode-Zen-FreeX contributors`。本分支的来源与维护缘由写在 [NOTICE](https://github.com/tkhs101/OpenCode-Zen-FreeX/blob/main/NOTICE)，这样许可证扫描器读到的是一份标准的 MIT 文件，而想知道这个分支为什么存在的人仍然找得到答案。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-zen-freex",
-  "version": "0.2.14",
+  "version": "0.2.15",
   "description": "OpenCode Zen's free models, for hosts that are not OpenCode: the public credential, automatic discovery and native streaming protocols",
   "type": "module",
   "main": "./index.mjs",

package/stream.mjs

@@ -132,7 +132,13 @@ function chatAccumulator() {
             calls.set(toolIndex, { type: "function", function: { name: "", arguments: "" } });
           const call = calls.get(toolIndex);
           for (const key of ["id", "type"]) {
-            if (fragment[key] !== undefined) call[key] = fragment[key];
+            // `"id": null` arrives on the continuation frames of a call this
+            // route named on the first one (see ensureCallIDs in
+            // tool-response.mjs): a fragment may leave the id as it stands,
+            // but a null or empty one does not take it away.
+            if (fragment[key] === undefined) continue;
+            if (key === "id" && (fragment[key] === null || fragment[key] === "")) continue;
+            call[key] = fragment[key];
           }
           if (fragment.function) appendFunction(call.function, fragment.function);
         }

package/tool-response.mjs

@@ -194,6 +194,25 @@ function inPlaceOf(protocol, call, note, at) {
   };
 }
 
+// A tool call needs an id its host can key the result by, and this route has
+// been measured leaving calls without one: 2026-10-17, through this plugin, a
+// reply's flushed frame carried `{"index":0,"id":null,"name":"bash"}` — the
+// route puts `"id": null` on a continuation frame of a call it named on the
+// first one, and a reply can also leave the call unnamed to the end. OpenAI's
+// shape requires the field, and a host it reaches has nothing to match its
+// result against without it: dsh keys its tool/result records by this id and
+// fails the whole turn — and then the whole session, on reload — when the id
+// is empty ("toolCallId matching its tool source"). So a call that reaches
+// the wire leaves with an id: the last-resort kind, process-unique under the
+// same counter the invented item ids use, so two invented calls cannot share
+// one.
+function ensureCallIDs(calls) {
+  for (const call of calls) {
+    if (typeof call.id === "string" && call.id !== "") continue;
+    call.id = `call_${++synthesized}`;
+  }
+}
+
 // checkSnapshots checks every call in a reply or event: renamed to the
 // agent's tool, or (Responses, Messages) put in place of by a note. It
 // answers whether data changed, how many calls it kept and how many it
@@ -342,6 +361,7 @@ function chatBuffer(checkName) {
     }
     if (state.legacy) delta.function_call = state.legacy;
     const { notes } = checkChatMessage(delta, checkName);
+    if (Array.isArray(delta.tool_calls)) ensureCallIDs(delta.tool_calls);
     if (notes.length) {
       delta.tool_calls?.forEach((call, i) => {
         call.index = i;
@@ -399,6 +419,16 @@ function chatBuffer(checkName) {
           const index = position(fragment.index);
           const previous = state.calls.get(index) ?? { index, function: {} };
           const value = { ...previous, ...fragment, index, function: previous.function };
+          // A continuation frame may carry `"id": null` — measured on this
+          // route — and a spread would let it clobber the id that named the
+          // call. A fragment that says nothing about the id leaves the one
+          // already there; one that carries a real id still wins, as it did.
+          if (
+            (typeof value.id !== "string" || value.id === "") &&
+            typeof previous.id === "string" &&
+            previous.id !== ""
+          )
+            value.id = previous.id;
           if (fragment.function != null) appendFunction(value.function, fragment.function);
           state.calls.set(index, value);
         }
@@ -1016,6 +1046,12 @@ export async function guardToolResponse(response, protocol, policy, options = {}
   try {
     value = parseJSON(await readBounded(response));
     checkSnapshots(value, protocol, checkName);
+    if (protocol === "chat") {
+      for (const choice of list(value.choices)) {
+        const message = object(choice) ? choice.message : undefined;
+        if (object(message)) ensureCallIDs(list(message.tool_calls));
+      }
+    }
   } catch (error) {
     if (!(error instanceof GuardError)) throw error;
     status = 502;