@alisio/plugin-opencode-go 0.1.0-alpha.6 → 0.1.0-alpha.8

package/README.md

@@ -1,6 +1,52 @@
 # @alisio/plugin-opencode-go
 
-Built-in OpenCode Go provider for Alisio. It discovers the unauthenticated Go catalog and routes
-only exact model IDs in the documented endpoint table: GPT, Grok and Muse through Responses; open
-compatible models through Chat Completions; MiniMax and Qwen through Anthropic Messages. Unknown
-catalog entries are hidden rather than guessed.
+**The built-in OpenCode Go model provider for [Alisio](https://github.com/GustavoGutierrez/alisio).**
+Discover the unauthenticated OpenCode Go catalog and route each model to the protocol OpenCode Go
+documents for it.
+
+## What it is
+
+A `model-provider` plugin that registers the `opencode-go` provider with the Alisio host. It ships
+as a built-in of the `alisio` CLI and is enabled by default. Model references use the canonical
+`opencode-go/<model-id>` form.
+
+## Installation
+
+Preinstalled in the `alisio` CLI. For an embedded host, register it through `createApplication`'s
+`builtins` list.
+
+## Using it: `/connect`
+
+1. Run `alisio`, then `/connect` and choose **OpenCode Go**.
+2. Enter the **API key** (secret, required). It is stored only in the global credentials store
+   (`credentials.json`, mode 0600) — never in the profile or configuration.
+3. Pick a model from the discovered catalog (`https://opencode.ai/zen/go/v1/models`).
+
+There is no hard-coded default API-key environment variable for this provider: the key is entered
+in `/connect` and kept out of configuration files.
+
+## Features
+
+- Unauthenticated catalog discovery of `opencode-go/<model-id>` entries.
+- Fail-closed routing from the documented endpoint table: GPT, Grok and Muse through **Responses**;
+  open compatible families through **Chat Completions**; MiniMax and Qwen through
+  **Anthropic Messages**.
+- Unknown catalog entries are hidden rather than guessed.
+- Requests send `user-agent: alisio/<version>` and an opaque, stable `x-opencode-session`
+  conversation ID that never includes a workspace path, prompt or credential.
+
+While registered, the provider also appears in `/model` and `alisio doctor`.
+
+## Docs
+
+[Configuration](https://gustavogutierrez.github.io/alisio/configuration) ·
+[Plugins](https://gustavogutierrez.github.io/alisio/plugins).
+
+## Requirements
+
+Node.js **>= 22.16** or Bun **>= 1.4.2**.
+
+## License
+
+MIT. Maintained by Gustavo Gutiérrez Mercado. Source: <https://github.com/GustavoGutierrez/alisio> ·
+npm: <https://www.npmjs.com/settings/alisio/packages>.

package/dist/provider.js

@@ -265,7 +265,7 @@ export class OpenCodeGatewayProvider {
         if (completed.some((call) => !call.id || !call.name))
             throw new Error("Incomplete tool call");
         if (finish === "length" && !text.trim())
-            throw new Error("OpenCode chat response cut off by max output tokens before any usable content; raise limits.maxOutputTokens");
+            throw new Error("OpenCode chat response cut off by max output tokens before any usable content; raise limits.maxOutputTokens (/settings → Agent max output tokens)");
         yield {
             type: "completed",
             message: {
@@ -341,7 +341,7 @@ export class OpenCodeGatewayProvider {
                     .map((item) => item.text)
                     .join("");
                 if (!text.trim())
-                    throw new Error("OpenCode Responses response cut off by max output tokens before any usable content; raise limits.maxOutputTokens");
+                    throw new Error("OpenCode Responses response cut off by max output tokens before any usable content; raise limits.maxOutputTokens (/settings → Agent max output tokens)");
                 if (calls.some((call) => !call.id || !call.name))
                     throw new Error("Incomplete tool call");
                 const u = event.response.usage;
@@ -522,7 +522,7 @@ export class OpenCodeGatewayProvider {
         }
         if (truncated) {
             if (!text.trim())
-                throw new Error("OpenCode Messages response cut off by max output tokens before any usable content; raise limits.maxOutputTokens");
+                throw new Error("OpenCode Messages response cut off by max output tokens before any usable content; raise limits.maxOutputTokens (/settings → Agent max output tokens)");
             yield {
                 type: "completed",
                 message: { role: "assistant", text, calls, providerData: blocks, truncated: true },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@alisio/plugin-opencode-go",
-  "version": "0.1.0-alpha.6",
+  "version": "0.1.0-alpha.8",
   "description": "Built-in OpenCode Go model provider for Alisio.",
   "license": "MIT",
   "type": "module",
@@ -21,10 +21,10 @@
     "node": ">=22.16"
   },
   "peerDependencies": {
-    "@alisio/sdk": "^0.1.0-alpha.5"
+    "@alisio/sdk": "^0.1.0-alpha.7"
   },
   "devDependencies": {
-    "@alisio/sdk": "0.1.0-alpha.5"
+    "@alisio/sdk": "0.1.0-alpha.7"
   },
   "publishConfig": {
     "access": "public",