opencode-zen-freex 0.2.17 → 0.2.18

package/MAINTAINING.md

@@ -173,6 +173,12 @@ bun run capture            # writes it
 bun run check:gate         # did that fix it
 ```
 
+`bun test` reads the tree; a running gateway does not. Magpie's plugin host
+imports the plugin once, when it starts, and no `magpie plugin` subcommand
+reloads it — pointing a gateway at this tree does not make it watch the tree, so
+a change to be measured through a live gateway needs that gateway restarted
+first.
+
 `check:gate` is the one that matters. It asks each generation twice, because the
 plugin sends two shapes and Zen does not answer them alike:
 
@@ -304,6 +310,22 @@ 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.
 
+**Leaving out a call the agent has no tool for.** A call whose name folded onto
+no declared tool was dropped from the reply with a note in its text, and a reply
+whose every call was dropped ended as a plain `stop`. An autonomous host reads
+that as an answer: DeepSeek Harness ended 16 of the 19 such turns one user
+measured and the model never saw an error it could correct
+(`magpie-community/plugins#209`; upstream made the same change in its 0.1.11).
+The name now goes on as the model wrote it — same name, same id, same arguments,
+a tool-call finish — and the host answers it with its own unknown-tool error,
+which is the correction signal. A name two declared tools fold to is still never
+guessed: it goes on as called. Only a call with **no name** is left out now, and
+`droppedNote` says so. Measured 2026-10-18 through a local magpie pointed at
+this tree, `deepseek-v4.1-flash-free`, declaring `pwsh` and calling `bash`:
+before, `200` + `finish_reason: "stop"` + the note; after, `200` + `tool_calls`
++ `bash` carrying its id. Do not put the drop back to "protect" a host —
+answering is the host's to do, and a silent `stop` is the failure this replaced.
+
 **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
@@ -315,6 +337,17 @@ 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.
 
+Both of those places publish the **chat** shape only. A Responses or Messages
+reply whose call carries no id of its own is handed on as it stands — no id, no
+`call_id` — and both protocols require the field. Measured 2026-10-18, no free
+model is served on either route: the tier's own `/models` listed none,
+`muse-spark-1.3-contributor-free` answered 410 `ModelDeprecated` and the four
+Messages models answered "Model is unavailable". So the gap is real but not
+reachable today, and the sentence above — every published call leaves with a
+non-empty id — is chat's. A free model on either route puts it back in scope,
+and then the id has to be minted once per call across its added, done and
+terminal copies, the way the dropped ones already are.
+
 **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

@@ -64,8 +64,8 @@ bun run capture             # 确认差异后才写入
 
 发往 `https://opencode.ai/inference/v1`，按每个模型原生协议走（Chat Completions / Responses / Anthropic Messages），流式与普通 JSON 都支持。
 
-- **宿主的工具不会被丢**：Zen 调 OpenCode 工具名时，按大小写与 `_`/`-` 对上唯一匹配的宿主工具（`bash`↔`Bash`、`todowrite`↔`todo_write`）；对不上就略去并在正文说明。工具仍在宿主执行，调用一律带非空 id。
-- **只借 OpenCode 的样子**：请求头、User-Agent、工具必须同属一代（`bash`/`glob`/`grep`/`read` 是 1.x，`shell`/`read` 是 2.x）；宿主缺的 `required` 工具由插件补发描述（背后没有实现，正文注明），宿主自带的 User-Agent 原样透传。
+- **对不上的名字照样交给宿主**：Zen 调 OpenCode 工具名时，按大小写与 `_`/`-` 对上唯一匹配的宿主工具（`bash`↔`Bash`、`todowrite`↔`todo_write`）；对不上或有歧义时**不猜也不丢**，按模型写的名字、原样的 id 与参数送达宿主，由宿主回它自己的"没有这个工具"，模型据此改名重来。只有**没有名字**的调用会被略去，并在正文说明。工具仍在宿主执行，调用一律带非空 id。
+- **只借 OpenCode 的样子**：请求头、User-Agent、工具必须同属一代（`bash`/`glob`/`grep`/`read` 是 1.x，`shell`/`read` 是 2.x）；宿主缺的 `required` 工具由插件补发描述（背后没有实现，描述里注明别调它），宿主自带的 User-Agent 原样透传。
 - **请求头是刻意挑出的最小集合**：`content-type`、`accept`、`user-agent`、`x-opencode-project`、`x-opencode-session(-id)`（同一 id）、`x-opencode-client: cli`、`authorization: Bearer public`（走 Messages 时 `x-api-key: public` + `anthropic-version`；`anthropic-beta` 这个头插件自己从不设置：只在宿主已经发了的时候原样透传）。**不要加别的头**：两个各自无害的组合起来也会被拒——单试一个得不出结论。
 - **会话 id** 按会话首条消息生成并记住，同一会话各轮共用；宿主的 id 形状合法就原样传。
 - **提前掐断的流**：有内容且无未完成调用 → 按普通回答收尾并注明截断，再问会续；否则请求失败，错误写明回复 id 与已收字节。Messages / Responses 被截断同样失败。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "opencode-zen-freex",
-  "version": "0.2.17",
+  "version": "0.2.18",
   "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/provider.mjs

@@ -339,10 +339,12 @@ function normalizeTools(body, protocol) {
       continue;
     }
     filled.push(name);
-    // A tool added here has nothing behind it: the agent has no such tool and
-    // a call to it is dropped. Describing it as OpenCode describes it is what
-    // Zen asks for, and it also makes the model want to call it, so the note
-    // goes after the opening Zen reads and before the closing it does not.
+    // A tool added here has nothing behind it: the agent has no such tool, so a
+    // call to it goes to the agent as called and comes back as the agent's own
+    // unknown-tool error, which the model corrects. Describing it as OpenCode
+    // describes it is what Zen asks for, and that description also makes the
+    // model want to call it, so the note goes after the opening Zen reads and
+    // before the closing it does not.
     body.tools.push(shapeOf({ ...spoken, description: `${spoken.description}\n\n${PLACEHOLDER}` }, protocol));
   }
   return { declared, filled, generation };

package/tool-response.mjs

@@ -19,8 +19,8 @@ function headersFor(response) {
 }
 
 // failure answers the error a client reads. `code` says what went wrong
-// where the shape has room for it: only a call of no tool the agent has is
-// an undeclared one, and a limit, a truncation or a malformed upstream is
+// where the shape has room for it: only a call the guard cannot name at all
+// is an undeclared one, and a limit, a truncation or a malformed upstream is
 // not.
 function failure(protocol, message, stream = false, code = "upstream_error") {
   if (protocol === "anthropic") return { type: "error", error: { type: "api_error", message } };
@@ -88,8 +88,15 @@ function declaredNames(policy) {
   return new Set(names);
 }
 
-// nameGuard answers the agent's name for a call, or null for a call of no
-// tool the agent has (a missing name included).
+// nameGuard answers the agent's name for a call: the agent's spelling when one
+// folds to it, else the name as the model wrote it. A call of a tool the agent
+// has no spelling of (bedit, psh, mcp__netcatcatty__unused) reaches the agent
+// as called, as it does on every other provider: the agent answers it with its
+// own unknown-tool error, and the model corrects the name and goes on (#209).
+// Leaving it out ended an agent's turn as a plain answer, which an autonomous
+// host reads as "the task is done" (#76 fixed the failure that came before
+// this one; that reply is not handed a turn's end any more, it is handed a
+// call). Only a call with no name answers null, and is left out.
 function nameGuard(policy) {
   const declared = declaredNames(policy);
   const lower = (name) => name.toLowerCase();
@@ -101,16 +108,16 @@ function nameGuard(policy) {
     if (declared.has(name)) return name;
     const match =
       byCase.get(lower(name)) ?? (byCase.has(lower(name)) ? null : byShape.get(bare(name)));
-    return match || null;
+    return match || name;
   };
 }
 
-// The models also call tools no agent has: bedit, bcp, ash, a mangled
-// mcp__netcatcatty__unused (#76). Such a call can't be run or named onto
-// one the agent has, and failing the reply for it threw away the whole
-// turn. It is left out instead, and the reply says so in its text, where
-// the agent's user and the model's next turn both read it. A reply left
-// with no call ends as a plain stop.
+// A call with no name can't be run, named onto one the agent has, or answered
+// by any agent: nothing keys a result by it and its own id names nothing. It
+// is left out instead of failing the reply — failing threw away the whole turn
+// (#76) — and the reply says so in its text, where the agent's user and the
+// model's next turn both read it. A reply left with no call ends as a plain
+// stop. Every named call, whatever the name, is handed on as called.
 export function droppedNote(name) {
   return typeof name === "string" && name
     ? `(The model called a tool this agent doesn't have: ${JSON.stringify(name.slice(0, 128))}. The call was left out.)`
@@ -785,11 +792,11 @@ function snapshotStream(protocol, checkName) {
           insideWords.clear();
           if (opens && nowhere[open]) nowhere[open].settled = true;
         }
-        // The item this frame carries, when it is a call of no tool the agent
-        // has: the walk below replaces it — opens or closes it, the copy is
-        // the same call — and its words are the ones a note takes the place
-        // of. Every other item the frame names is one the reply keeps, and the
-        // place it holds is a fact the suppression below reads before any word.
+        // The item this frame carries, when it is a call with no name: the
+        // walk below replaces it — opens or closes it, the copy is the same
+        // call — and its words are the ones a note takes the place of. Every
+        // other item the frame names is one the reply keeps, and the place it
+        // holds is a fact the suppression below reads before any word.
         const leaving =
           (opens || closes) &&
           object(item) &&