OmniRoute/@omniroute/opencode-provider
Mourad Maatoug 57354ac6d7 feat(@omniroute/opencode-provider): model capabilities, agent block, mode block (UI helpers)
Adds three UI-surface helpers on top of T1–T8 in PR #2375:

A) Model capability flags
   - ModelCapabilities interface (label, attachment, reasoning, temperature, tool_call)
   - OMNIROUTE_DEFAULT_MODEL_CAPABILITIES seeds capabilities for all 7 default
     model ids
   - OmniRouteProviderOptions.modelCapabilities merges over defaults per id
   - createOmniRouteProvider emits capability flags inline in models[id], per
     OpenCode's ProviderConfig.models schema (snake_case JSON keys, optional)
   - Label precedence: modelCapabilities[id].label > modelLabels[id] > id

B) createOmniRouteAgentBlock
   - OmniRouteAgentRole + OmniRouteAgentBlockOptions + OpenCodeAgentEntry
   - Emits Record<role, { model: 'omniroute/<id>', temperature?, top_p?,
     tools?: Record<string, boolean>, prompt? }>
   - Only fields present in OpenCode's AgentConfig schema are emitted
   - Tools normalized to Record<string, boolean> per schema (not string[])
   - Roles with empty modelId are skipped

C) createOmniRouteModesBlock (deprecated alias)
   - Same shape as createOmniRouteAgentBlock since OpenCode treats top-level
     'mode' block identically to 'agent' (both reference AgentConfig)
   - Helper kept for back-compat; @deprecated tags steer callers to agent

Shared helper buildAgentEntry eliminates duplication between A/B helpers.

Schema validation
- All emitted keys verified against https://opencode.ai/config.json
- Removed initially-considered reasoningEffort + max_tokens fields (not in
  AgentConfig schema)
- tools shape changed from string[] to Record<string, boolean> per schema

Build hygiene
- tsconfig.json narrowed to lib: ['ES2022'] + types: ['node'] (no DOM lib
  leakage); @types/node added as devDep
- Tests: 32 → 45 green (+13 net)
- Build: ESM 10.39 KB / CJS 11.01 KB / DTS 18.87 KB
2026-05-18 17:06:13 +02:00
..
src feat(@omniroute/opencode-provider): model capabilities, agent block, mode block (UI helpers) 2026-05-18 17:06:13 +02:00
tests feat(@omniroute/opencode-provider): model capabilities, agent block, mode block (UI helpers) 2026-05-18 17:06:13 +02:00
.gitignore refactor(@omniroute/opencode-provider): rewrite for schema correctness + publishability 2026-05-14 16:58:33 -03:00
.npmignore refactor(@omniroute/opencode-provider): rewrite for schema correctness + publishability 2026-05-14 16:58:33 -03:00
LICENSE refactor(@omniroute/opencode-provider): rewrite for schema correctness + publishability 2026-05-14 16:58:33 -03:00
package-lock.json feat(@omniroute/opencode-provider): model capabilities, agent block, mode block (UI helpers) 2026-05-18 17:06:13 +02:00
package.json feat(@omniroute/opencode-provider): model capabilities, agent block, mode block (UI helpers) 2026-05-18 17:06:13 +02:00
README.md refactor(@omniroute/opencode-provider): rewrite for schema correctness + publishability 2026-05-14 16:58:33 -03:00
tsconfig.json feat(@omniroute/opencode-provider): model capabilities, agent block, mode block (UI helpers) 2026-05-18 17:06:13 +02:00
tsup.config.ts refactor(@omniroute/opencode-provider): rewrite for schema correctness + publishability 2026-05-14 16:58:33 -03:00

@omniroute/opencode-provider

Helper for connecting OpenCode to a running OmniRoute AI gateway.

The package emits a schema-valid entry for opencode.json (https://opencode.ai/config.json) that delegates the actual runtime to @ai-sdk/openai-compatible. It does not ship any new HTTP client — OmniRoute already exposes an OpenAI-compatible surface, and OpenCode already speaks it through the AI SDK.

Pre-1.0. The API may still change. See CHANGELOG in the OmniRoute repo for breaking notes.

Installation

npm install --save-dev @omniroute/opencode-provider
# or
pnpm add -D @omniroute/opencode-provider

You also need OpenCode's own runtime dep, but that's a transitive concern — OpenCode itself ships with @ai-sdk/openai-compatible. This package only generates configuration.

Quick start

1. Scaffold a fresh opencode.json

import { writeFileSync } from "node:fs";
import { buildOmniRouteOpenCodeConfig } from "@omniroute/opencode-provider";

const config = buildOmniRouteOpenCodeConfig({
  baseURL: "http://localhost:20128", // or your OmniRoute deployment URL
  apiKey: process.env.OMNIROUTE_API_KEY ?? "sk_omniroute",
});

writeFileSync("opencode.json", JSON.stringify(config, null, 2));

The resulting opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "omniroute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "OmniRoute",
      "options": {
        "baseURL": "http://localhost:20128/v1",
        "apiKey": "sk_omniroute",
      },
      "models": {
        "claude-opus-4-5-thinking": { "name": "claude-opus-4-5-thinking" },
        "claude-sonnet-4-5-thinking": { "name": "claude-sonnet-4-5-thinking" },
        "gemini-3.1-pro-high": { "name": "gemini-3.1-pro-high" },
        "gemini-3-flash": { "name": "gemini-3-flash" },
      },
    },
  },
}

2. Merge into an existing opencode.json

import { createOmniRouteProvider } from "@omniroute/opencode-provider";

const provider = createOmniRouteProvider({
  baseURL: "http://localhost:20128",
  apiKey: process.env.OMNIROUTE_API_KEY!,
});

// Place `provider` under provider.omniroute in your opencode.json

If you already have an opencode.json on disk and want a non-destructive merge from the OmniRoute side, use omniroute config opencode from the CLI (ships with the main OmniRoute install) — it preserves comments and unrelated keys.

API

createOmniRouteProvider(options): OpenCodeProviderEntry

Returns the value to place under provider.omniroute inside opencode.json.

Option Type Required Description
baseURL string Yes OmniRoute base URL. Accepts http://host:port or http://host:port/v1. Trailing slashes are tolerated.
apiKey string Yes OmniRoute API key. Use sk_omniroute for local installs that have REQUIRE_API_KEY=false.
displayName string No Custom name shown in the OpenCode UI. Default: "OmniRoute".
models string[] No Override the surfaced model catalog. Default: 4 curated models — see OMNIROUTE_DEFAULT_OPENCODE_MODELS.
modelLabels Record<string,string> No Human-readable labels keyed by model id.

Throws on empty/invalid input — baseURL must be a real URL, apiKey must be a non-empty string.

buildOmniRouteOpenCodeConfig(options): OpenCodeConfigDocument

Same options as above, but returns a full document with $schema and the provider.omniroute wrapper, ready to write to opencode.json.

normalizeBaseURL(input): string

Exported for completeness. Strips trailing /, deduplicates a trailing /v1, and re-appends exactly one /v1. Throws on empty / non-URL input.

Constants

  • OMNIROUTE_PROVIDER_KEY"omniroute" (the key used under provider.*).
  • OMNIROUTE_PROVIDER_NPM"@ai-sdk/openai-compatible" (the runtime delegate).
  • OPENCODE_CONFIG_SCHEMA"https://opencode.ai/config.json".
  • OMNIROUTE_DEFAULT_OPENCODE_MODELS — readonly list of 4 default model ids.

Custom model catalog

import { createOmniRouteProvider } from "@omniroute/opencode-provider";

createOmniRouteProvider({
  baseURL: "http://localhost:20128",
  apiKey: "sk_omniroute",
  models: ["auto", "claude-opus-4-7", "gpt-5.5"],
  modelLabels: {
    auto: "Auto-Combo (recommended)",
    "claude-opus-4-7": "Claude Opus 4.7",
    "gpt-5.5": "GPT-5.5",
  },
});

Duplicates and empty strings are dropped automatically, and order is preserved.

Troubleshooting

  • Requests 404 with /v1/v1/... — you're on an old version (≤1.0.0). Update to ≥0.1.0 of this re-released package. The new build normalises baseURL automatically.
  • 401 Invalid API key — your OmniRoute instance has REQUIRE_API_KEY=true but the key you supplied doesn't exist there. Create one via the dashboard or set REQUIRE_API_KEY=false and use sk_omniroute.
  • OpenCode complains the provider has no models — supply an explicit models list; the default 4 may be hidden by your provider visibility settings.

License

MIT — see LICENSE.