opencode-plugboard 0.4.0 → 0.4.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +57 -169
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,24 +1,36 @@
|
|
|
1
1
|
# opencode-plugboard
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
[](https://www.npmjs.com/package/opencode-plugboard)
|
|
4
|
+
[](https://github.com/jjjermiah/opencode-plugboard/blob/main/LICENSE)
|
|
5
|
+
[](https://github.com/jjjermiah/opencode-plugboard/actions/workflows/ci.yml)
|
|
4
6
|
|
|
5
|
-
|
|
7
|
+
An OpenCode V2 plugin that serves an OpenAI-compatible API from your OpenCode server, so your other apps reuse the provider logins you already made in OpenCode.
|
|
6
8
|
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
9
|
+
```
|
|
10
|
+
client ──▶ plugboard listener ──▶ OpenCode session ──▶ provider
|
|
11
|
+
▲ │
|
|
12
|
+
└──── reply; tool calls go back to the caller ◀──────────┘
|
|
13
|
+
```
|
|
10
14
|
|
|
11
|
-
|
|
15
|
+
Tools like n8n, Open WebUI or a Discord bot only speak the OpenAI API, so each wants its own key or its own gateway. Plugboard serves `/v1/chat/completions`, `/v1/responses` and `/v1/models` from inside OpenCode. OpenCode never runs your tools.
|
|
12
16
|
|
|
13
17
|
## Quick start
|
|
14
18
|
|
|
15
|
-
|
|
19
|
+
Tested on OpenCode 2.0.26. The peer range `>=2.0.26 <2.1` allows 2.0.x patch releases.
|
|
20
|
+
|
|
21
|
+
**1. Pick a key** for your app, in the environment OpenCode starts from:
|
|
22
|
+
|
|
23
|
+
```sh
|
|
24
|
+
export PLUGBOARD_KEY_MY_APP=choose-a-long-random-string
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
**2. Install it** in your global config (`~/.config/opencode/opencode.jsonc`). It has to be global, see [History](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/history.md). OpenCode installs it from npm the first time it loads.
|
|
16
28
|
|
|
17
29
|
```jsonc
|
|
18
30
|
{
|
|
19
31
|
"plugins": [
|
|
20
32
|
{
|
|
21
|
-
"package": "opencode-plugboard",
|
|
33
|
+
"package": "opencode-plugboard@0.4.1",
|
|
22
34
|
"options": {
|
|
23
35
|
"keys": { "my-app": "{env:PLUGBOARD_KEY_MY_APP}" },
|
|
24
36
|
"models": ["anthropic/claude-sonnet-4-6", "github-copilot/*", "opencode-go/glm-5.3-flash"],
|
|
@@ -29,43 +41,52 @@ Install it in your global OpenCode config (`~/.config/opencode/opencode.jsonc`).
|
|
|
29
41
|
}
|
|
30
42
|
```
|
|
31
43
|
|
|
32
|
-
Every alias target must also be allowed in `models
|
|
44
|
+
Every alias target must also be allowed in `models`. Pin the version as shown. A bare `"opencode-plugboard"` means `latest`, so a cache refresh or `opencode plugin update` can pull code you have not read. A global plugin runs inside OpenCode in every project, next to your provider logins, so update the number on purpose after reading the [changelog](https://github.com/jjjermiah/opencode-plugboard/blob/main/CHANGELOG.md).
|
|
45
|
+
|
|
46
|
+
**3. Restart OpenCode, then touch the server once.** OpenCode loads no plugin until a client connects, so the port stays closed until then:
|
|
33
47
|
|
|
34
48
|
```sh
|
|
35
|
-
|
|
49
|
+
opencode api get /api/agent
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
For an always-on server, run that from the service unit, see [warm-up](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/warm-up.md).
|
|
53
|
+
|
|
54
|
+
**4. Call it.** The endpoint listens on `127.0.0.1:4010`. This prints `pong`:
|
|
36
55
|
|
|
37
|
-
|
|
56
|
+
```sh
|
|
57
|
+
curl -s http://127.0.0.1:4010/v1/chat/completions \
|
|
38
58
|
-H "Authorization: Bearer $PLUGBOARD_KEY_MY_APP" \
|
|
39
59
|
-H "Content-Type: application/json" \
|
|
40
|
-
-d '{"model": "fast", "messages": [{"role": "user", "content": "reply with exactly: pong"}]}'
|
|
60
|
+
-d '{"model": "fast", "messages": [{"role": "user", "content": "reply with exactly: pong"}]}' \
|
|
61
|
+
| jq -r '.choices[0].message.content'
|
|
41
62
|
```
|
|
42
63
|
|
|
43
|
-
Any OpenAI SDK works by changing the base URL and key:
|
|
64
|
+
Any OpenAI SDK works by changing the base URL (`http://127.0.0.1:4010/v1`) and the key. Next:
|
|
44
65
|
|
|
45
|
-
|
|
46
|
-
|
|
66
|
+
- [Clients](#clients): config for Python, JS, Vercel AI SDK, LangChain, pydantic-ai, Open WebUI, n8n.
|
|
67
|
+
- [Configuration](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/configuration.md): options, models, keys, errors.
|
|
68
|
+
- [Reaching plugboard from another host or container](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/clients/any-app.md#reaching-plugboard-from-another-host-or-container).
|
|
69
|
+
- [History](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/history.md): every request is kept as an OpenCode session.
|
|
70
|
+
- [Architecture](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/architecture.md) and [development](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/development.md).
|
|
47
71
|
|
|
48
|
-
|
|
49
|
-
reply = client.chat.completions.create(
|
|
50
|
-
model="anthropic/claude-sonnet-4-6",
|
|
51
|
-
messages=[{"role": "user", "content": "Say hi."}],
|
|
52
|
-
)
|
|
53
|
-
print(reply.choices[0].message.content)
|
|
54
|
-
```
|
|
72
|
+
`GET /healthz` returns OK when the listener is up and needs no key.
|
|
55
73
|
|
|
56
|
-
|
|
57
|
-
import OpenAI from "openai"
|
|
74
|
+
## What this is not
|
|
58
75
|
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
```
|
|
76
|
+
Plugboard is early (0.x) and narrow on purpose.
|
|
77
|
+
|
|
78
|
+
- **V2 only.** OpenCode V2 has no OpenAI endpoint, and the V1 plugins that had one stopped working when the plugin API changed. V1 is not planned.
|
|
79
|
+
- **Two formats:** Chat Completions and Responses. `/v1/responses` is a stateless subset, see [docs/responses.md](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/responses.md). Anthropic Messages and Gemini front-ends are on the [roadmap](#roadmap).
|
|
80
|
+
- **Not planned:** embeddings, audio, image generation. Only `n=1`, no `logprobs`.
|
|
81
|
+
- **No concurrency limit per app** yet ([#54](https://github.com/jjjermiah/opencode-plugboard/issues/54), [#86](https://github.com/jjjermiah/opencode-plugboard/issues/86)).
|
|
82
|
+
- **Not a gateway with its own provider keys.** It only reuses what OpenCode is logged in to.
|
|
67
83
|
|
|
68
|
-
|
|
84
|
+
How it differs from the alternatives:
|
|
85
|
+
|
|
86
|
+
- [KochC/opencode-llm-proxy](https://github.com/KochC/opencode-llm-proxy) serves more API formats but targets OpenCode V1 only. Plugboard is V2 only and adds per-app keys and history, an explicit model allowlist, and rules that keep it from freezing the host (see [AGENTS.md](https://github.com/jjjermiah/opencode-plugboard/blob/main/AGENTS.md)).
|
|
87
|
+
- [LiteLLM](https://github.com/BerriAI/litellm) is a separate gateway you run and give its own provider keys. It covers many more providers and API shapes. Pick it when you want a standalone service. Pick plugboard when OpenCode already holds the logins you want to reuse, such as a ChatGPT or Copilot subscription.
|
|
88
|
+
|
|
89
|
+
The most common first failure is an SDK defaulting to `/v1/responses` for newer models. Plugboard serves it, but some clients need `store: false` or a "use chat completions" switch. Check the client's page below.
|
|
69
90
|
|
|
70
91
|
## Clients
|
|
71
92
|
|
|
@@ -83,148 +104,15 @@ One short page per client, with a config snippet, a chat, a tool call, a structu
|
|
|
83
104
|
| n8n | [n8n](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/clients/n8n.md) | pass with "Use Responses API" off |
|
|
84
105
|
| Anything else | [any-app](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/clients/any-app.md) | base URL, key, model id |
|
|
85
106
|
|
|
86
|
-
Each run drove the client's own SDK or API against a dev server at an earlier commit: a plain chat, a tool round trip, streaming, an image and structured output on `fast`, a Claude model and a ChatGPT model. A pass
|
|
87
|
-
|
|
88
|
-
## Known gaps
|
|
89
|
-
|
|
90
|
-
- **`/v1/responses` is stateless.** `previous_response_id`, `conversation`, `item_reference`, `background` and hosted tools return 400. See [docs/responses.md](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/responses.md).
|
|
91
|
-
- Only `n=1`, no `logprobs`, no embeddings, audio or image generation.
|
|
92
|
-
- No per-app concurrency limit yet ([#54](https://github.com/jjjermiah/opencode-plugboard/issues/54), [#86](https://github.com/jjjermiah/opencode-plugboard/issues/86)).
|
|
93
|
-
|
|
94
|
-
## Options
|
|
95
|
-
|
|
96
|
-
Options live under `options` in the plugin entry. `{env:VAR}` is expanded by OpenCode.
|
|
97
|
-
|
|
98
|
-
| Option | Default | Meaning |
|
|
99
|
-
| --- | --- | --- |
|
|
100
|
-
| `listen.host` | `127.0.0.1` | Interface to bind. A non-loopback host without `keys` refuses to start. |
|
|
101
|
-
| `listen.port` | `4010` | Port to bind. |
|
|
102
|
-
| `keys` | none | Map of app name to API key. The app name groups that app's history sessions. Names match `[a-z0-9-]+`. `default` is reserved. |
|
|
103
|
-
| `models` | none (required) | Allowlist of models callers may use. See [Models](#models). |
|
|
104
|
-
| `aliases` | none | Map of alias to `provider/model[#variant]`. Each target must also pass `models`. |
|
|
105
|
-
| `maxTools` | `32` | Most tools one request may carry. Fixed when the plugin loads. |
|
|
106
|
-
| `requestTimeoutMs` | `600000` | A request that runs longer is interrupted. |
|
|
107
|
-
| `history` | none (keep forever) | `{ maxSessions, maxAgeDays }`. `maxSessions` keeps the newest N sessions per app, `maxAgeDays` deletes older ones; with both, the stricter wins. |
|
|
108
|
-
| `dropUnsupportedParams` | `true` | Drop `temperature`, `top_p` and penalties the target model is known to reject, and list them in the `x-plugboard-dropped-params` response header. `false` forwards them as sent. |
|
|
109
|
-
| `remoteImages` | `false` | Let the server fetch `http(s)` image URLs from requests (20 MB cap, no redirects, `image/*` only). Off by default because it lets callers make the host request internal addresses; callers can always send `data:` URLs. |
|
|
110
|
-
|
|
111
|
-
Changes to `listen` need a server restart; other option changes apply on config reload.
|
|
112
|
-
|
|
113
|
-
OpenCode loads the plugin once per project directory, and all of those loads share one listener. The first one to load decides the options. A load elsewhere with different options logs once and stays inert, so a project entry cannot serve with weaker auth than the live one. When none is live, for example during a config reload, the next load's options are adopted. Requests are served from plugboard's own data directory when it is loaded, so a project's provider config doesn't change what callers get. So install it in the global config, which every project loads, and don't repeat it per project.
|
|
114
|
-
|
|
115
|
-
On a loopback `listen.host`, requests with a `Host` header other than `127.0.0.1`, `localhost` or `[::1]` (on the listen port) get 403 `invalid_host`, and without `keys` a request with an `Origin` header gets 403 `cross_origin_forbidden`. The `Host` check only applies when `listen.host` is loopback. `POST` bodies must be `application/json` (415 otherwise).
|
|
116
|
-
|
|
117
|
-
Without `keys`, only a loopback `listen.host` is accepted and every caller is the app `default`. Once any key exists, every `/v1` request needs a valid key, loopback included, and `/healthz` stays open. Callers send the key as `Authorization: Bearer <key>`. They never see or need the OpenCode server password.
|
|
118
|
-
|
|
119
|
-
## Models
|
|
120
|
-
|
|
121
|
-
Callers name models as `provider/model`, optionally `provider/model#variant` (for example `openai/gpt-6-luna#low`, since ChatGPT models need a variant). Nothing is exposed by accident, so you must list what callers may use in `models`:
|
|
122
|
-
|
|
123
|
-
- `provider/model` allows that model with any variant.
|
|
124
|
-
- `provider/model#variant` allows exactly that variant.
|
|
125
|
-
- `provider/*` allows every model of the provider.
|
|
126
|
-
|
|
127
|
-
With no `models`, `/v1/models` is empty and chat calls return 403. `/v1/models` lists the allowlist intersected with the models enabled on your server, plus your aliases. Each entry has `owned_by` set to the provider and an extra `plugboard` object (`capabilities`, `contextLimit`). The ids contain `/` and `#`, which some UIs mishandle, so define an alias for those.
|
|
128
|
-
|
|
129
|
-
`reasoning_effort` in a request picks a variant when the model name has none and the model has one by that name. An alias can point at a model with a variant, which is the easy way to give a client a fixed effort level.
|
|
130
|
-
|
|
131
|
-
## Apps and keys
|
|
132
|
-
|
|
133
|
-
Each key name is an app. A request made with the `sparkyfitness` key is the app `sparkyfitness`, and its sessions are grouped under that app. Give every tool its own key. You can tell their traffic apart, and revoking one means removing one line.
|
|
134
|
-
|
|
135
|
-
## History
|
|
136
|
-
|
|
137
|
-
Every request is kept as an OpenCode session, so you can see what each app asked and what the model answered. Plugboard keeps the full caller transcript in each session (system prompt, messages, images as attachments, tool calls and results) plus the reply. The title is the first user message. A ten-turn chat is ten sessions, each complete.
|
|
138
|
-
|
|
139
|
-
Each session is filed under a per-app directory, so it never shows up in your real projects:
|
|
140
|
-
|
|
141
|
-
```
|
|
142
|
-
$XDG_DATA_HOME/opencode-plugboard/<app>/ # default ~/.local/share/opencode-plugboard/<app>/
|
|
143
|
-
```
|
|
144
|
-
|
|
145
|
-
That directory only groups sessions: it is the `directory` a session is filed under. The prompts and replies are not stored in it. OpenCode keeps them in its own database, `opencode.db` in its data directory (`opencode debug paths` prints the exact location, and `OPENCODE_DB` can override it). So deleting, locking down or backing up the app directory removes, protects or saves no history. To back up, restrict or purge history, work on that database, or remove sessions through OpenCode ([`compat/tools/sessions.py`](https://github.com/jjjermiah/opencode-plugboard/blob/main/compat/tools/sessions.py) does that for one app).
|
|
146
|
-
|
|
147
|
-
In OpenCode the sessions appear as one group per app in the desktop and phone app home screen. In the TUI they are visible in the all-projects view (ctrl+a), not in a project's own list. Set `history` to delete old ones: sweeps run on requests, at most every 10 minutes, in bounded batches, and never touch a running session. Only sessions created while a limit is set are pruned; remove older ones with `compat/tools/sessions.py`.
|
|
148
|
-
|
|
149
|
-
OpenCode loads plugin hooks per directory, so plugboard has to be loaded in those app directories, which is why it needs the global config. Everywhere outside the data root it is inert: it only joins the shared listener and registers no hooks, tools or agent rules, so your real projects behave as before.
|
|
150
|
-
|
|
151
|
-
History records every prompt and reply, so treat OpenCode's database as sensitive.
|
|
152
|
-
|
|
153
|
-
## Warm-up for always-on servers
|
|
154
|
-
|
|
155
|
-
OpenCode loads no plugin until a client touches the server, so after a restart the port stays closed until something connects. On a machine that runs `opencode serve` all the time, add one call right after start. Any request that makes OpenCode load a project works. `opencode api get /api/agent` does.
|
|
156
|
-
|
|
157
|
-
On Linux, in the OpenCode systemd unit (retry until the server answers; pass the same server credentials your service uses, if you set any):
|
|
158
|
-
|
|
159
|
-
```ini
|
|
160
|
-
[Service]
|
|
161
|
-
ExecStartPost=-/bin/sh -c 'for i in $(seq 1 30); do opencode api get /api/agent >/dev/null 2>&1 && exit 0; sleep 1; done; exit 1'
|
|
162
|
-
```
|
|
163
|
-
|
|
164
|
-
On macOS, a launchd job (`~/Library/LaunchAgents/dev.plugboard.warmup.plist`). It runs once when launchd loads it, which is at login and after boot. It does not run again when OpenCode restarts by itself, so after an OpenCode restart on its own, touch the server yourself (`launchctl kickstart -k gui/$(id -u)/dev.plugboard.warmup` reruns it) or run the same command from whatever restarts OpenCode.
|
|
165
|
-
|
|
166
|
-
```xml
|
|
167
|
-
<?xml version="1.0" encoding="UTF-8"?>
|
|
168
|
-
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
|
|
169
|
-
<plist version="1.0">
|
|
170
|
-
<dict>
|
|
171
|
-
<key>Label</key><string>dev.plugboard.warmup</string>
|
|
172
|
-
<key>ProgramArguments</key>
|
|
173
|
-
<array>
|
|
174
|
-
<string>/bin/sh</string>
|
|
175
|
-
<string>-c</string>
|
|
176
|
-
<string>for i in $(seq 1 30); do opencode api get /api/agent >/dev/null 2>&1 && exit 0; sleep 1; done; exit 1</string>
|
|
177
|
-
</array>
|
|
178
|
-
<key>RunAtLoad</key><true/>
|
|
179
|
-
</dict>
|
|
180
|
-
</plist>
|
|
181
|
-
```
|
|
182
|
-
|
|
183
|
-
If `opencode` is not on the job's `PATH`, use its full path. A request to `/healthz` before the warm-up gets connection refused, which is expected. I'd like OpenCode to boot plugins at server start so none of this is needed ([upstream request](https://github.com/jjjermiah/opencode-plugboard/issues/2)).
|
|
184
|
-
|
|
185
|
-
When config reloads happen, plugboard keeps the port open through a short grace period, so a reload does not drop connections. If no plugboard generation is alive when a request arrives, the caller gets a 503.
|
|
186
|
-
|
|
187
|
-
## Limits and errors
|
|
188
|
-
|
|
189
|
-
Errors use the OpenAI error body shape with the matching HTTP status.
|
|
190
|
-
|
|
191
|
-
| Status | `code` | When | Message |
|
|
192
|
-
| --- | --- | --- | --- |
|
|
193
|
-
| 401 | `invalid_api_key` | Missing or wrong key | Missing or invalid API key |
|
|
194
|
-
| 404 | `model_not_found` | Unknown model or not on the allowlist | Model <m> is not available |
|
|
195
|
-
| 403 | `no_models_configured` | The `models` option is empty | No models are allowed: set the plugboard `models` option |
|
|
196
|
-
| 400 | `too_many_tools` | More tools than `maxTools` | Request has <n> tools; plugboard allows <max> (option `maxTools`) |
|
|
197
|
-
| 400 | `unsupported_parameter` | `n` above 1, `logprobs`, `top_logprobs` | names the parameter |
|
|
198
|
-
|
|
199
|
-
Provider errors map to an OpenAI error body with the provider's status, including a provider's own rejection of a sampling parameter (ChatGPT models reject `temperature`, for example). Once a stream has started, a failure arrives as an `error` event followed by `[DONE]`. A client that disconnects, SSE included, interrupts the request. There is no per-app concurrency limit in v0.1.
|
|
200
|
-
|
|
201
|
-
Supported request fields: messages with system, developer, user text and images, assistant `tool_calls` and tool results; `tools`, `tool_choice`, `response_format` (`json_object`, `json_schema`), `temperature`, `top_p`, `max_tokens`, `max_completion_tokens`, `stop`, `presence_penalty`, `frequency_penalty`, `reasoning_effort`, and streaming with a final usage chunk (`stream_options.include_usage`).
|
|
202
|
-
|
|
203
|
-
Behaviours worth knowing:
|
|
204
|
-
|
|
205
|
-
- `parallel_tool_calls` and `seed` are accepted and ignored.
|
|
206
|
-
- `tool_choice` `auto` and `none` work as expected. `required` and a named function are applied as an instruction to the model, because the OpenCode session API has no tool-choice control. A model can still answer in text.
|
|
207
|
-
- `response_format` `json_schema` works through a `respond` tool the model is instructed to call, and the arguments come back as the message content. The provider does not enforce the schema, so validate the result. `json_object` adds a system instruction instead and carries no schema, so name the keys in your prompt; weak models may still ignore them.
|
|
208
|
-
- A request that carries both `tools` and a `json_schema` response format is changing: it will return the caller's tool calls ([#34](https://github.com/jjjermiah/opencode-plugboard/issues/34)). Don't rely on the current behaviour for that combination.
|
|
209
|
-
- A streamed tool call arrives as one delta carrying the whole arguments string.
|
|
107
|
+
Each run drove the client's own SDK or API against a dev server at an earlier commit: a plain chat, a tool round trip, streaming, an image and structured output on `fast`, a Claude model and a ChatGPT model. A pass is not a clean sweep, and the notes say where it was not. The latest full run is in [compat/results/release-candidate.md](https://github.com/jjjermiah/opencode-plugboard/blob/main/compat/results/release-candidate.md).
|
|
210
108
|
|
|
211
109
|
## How it works
|
|
212
110
|
|
|
213
|
-
Each request becomes
|
|
214
|
-
|
|
215
|
-
1. A front-end parses the OpenAI request into a format-neutral request, and the core checks the key and resolves the model.
|
|
216
|
-
2. The session backend creates a session in the app directory and swaps the caller's system prompt, messages and tools in for OpenCode's own with a `context` hook.
|
|
217
|
-
3. Caller tools map onto a pool of `maxTools` placeholder tools. A placeholder settles at once with a fixed no-op result, so history shows a completed call. Nothing of yours runs.
|
|
218
|
-
4. When the model has emitted its tool calls, the plugin interrupts the turn and returns the calls to the caller. Text streams out as it arrives.
|
|
219
|
-
5. The front-end encodes the events as JSON or SSE, and the session stays as history.
|
|
220
|
-
|
|
221
|
-
The model call sits behind one interface, `ModelCaller`, so a native backend can replace the session backend later without touching the front-ends ([roadmap](https://github.com/jjjermiah/opencode-plugboard/issues/3)). [docs/architecture.md](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/architecture.md) has the details: lifetimes, process-wide state and the freeze-safety rules.
|
|
111
|
+
Each request becomes an OpenCode session in the app's own directory, using OpenCode's request path, so provider fixes and auth plugins still apply. The plugin swaps the caller's prompt, messages and tools in for OpenCode's own. Caller tools map to placeholder tools that settle at once with a no-op result. When the model has emitted its tool calls, the plugin interrupts the turn and returns them to the caller. Text streams out as it arrives. [docs/architecture.md](https://github.com/jjjermiah/opencode-plugboard/blob/main/docs/architecture.md) has the lifetimes and the freeze-safety rules.
|
|
222
112
|
|
|
223
113
|
## Roadmap
|
|
224
114
|
|
|
225
|
-
Work is tracked in GitHub issues
|
|
226
|
-
|
|
227
|
-
Not planned: V1 support, embeddings, audio, image generation.
|
|
115
|
+
Work is tracked in GitHub issues: the [v0.1 milestone](https://github.com/jjjermiah/opencode-plugboard/milestone/1) and the [later milestone](https://github.com/jjjermiah/opencode-plugboard/milestone/2), which holds the `/v1/messages` and Gemini front-ends, agent mode, a native backend, usage accounting, rate limits and an upstream request to boot plugins at server start.
|
|
228
116
|
|
|
229
117
|
## License
|
|
230
118
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "opencode-plugboard",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.1",
|
|
4
4
|
"type": "module",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"description": "OpenCode V2 plugin that serves an OpenAI-compatible /v1/chat/completions and /v1/models from your OpenCode server, backed by the providers you already connected there.",
|
|
@@ -20,7 +20,7 @@
|
|
|
20
20
|
"files": ["index.ts", "src/", "README.md", "LICENSE"],
|
|
21
21
|
"scripts": {
|
|
22
22
|
"typecheck": "tsc --noEmit",
|
|
23
|
-
"release": "bun scripts/release.ts"
|
|
23
|
+
"release": "bun .github/scripts/release.ts"
|
|
24
24
|
},
|
|
25
25
|
"devDependencies": {
|
|
26
26
|
"@opencode/plugin": "2.0.26",
|