opencode2dsh

---

opencode2dsh registers a native DSH LlmAdapter that streams directly from OpenCode Zen's anonymous free lane — the same models OpenCode's own CLI uses without an account, served to your DSH model picker as a regular provider called opencode2dsh.

Requests leave your machine looking exactly like traffic from the OpenCode CLI (same user agent, same correlation headers), and the model catalog stays fresh through a three-tier fallback chain. There is nothing to log into and nothing to host.

Highlights

• Zero credential, zero setup — the anonymous lane needs no key; install, restart, chat
• Native adapter, no sidecar — one npm package, no child process, no binary, no local port (the legacy Go sidecar is not part of the published package; see legacy/)
• CLI-identical disguise — requests carry the OpenCode CLI user agent and its session/request/project header set, derived per conversation
• Selectable thinking levels — reasoning-capable free models expose an effort picker in DSH's model selector (declared ladders where the model metadata provides them, Off/Minimal/Low/Medium/High otherwise); Responses-only muse-spark-* models expose only upstream-supported effort levels, and no selection keeps the provider default
• Image input where it is declared — image attachments are accepted for every model whose models.dev entry lists image in modalities.input, and refused for the ones that declare text only; models.dev being silent falls back to the live-verified vision family
• Live catalog with a fallback chain — live upstream list ∩ free-by-metadata, falling back to offline cache and a verified static list
• Self-healing — fast startup retries, periodic refresh, and a written health snapshot for diagnostics
• Proper error surfaces — upstream failures (rate limit, auth, timeout, transport) arrive in DSH as classified finish reasons, and retries stay owned by DSH

Install

From the plugin market (recommended, once this repo is listed there): in DSH open Settings → Plugin Market, search opencode2dsh, one-click install.

From npm:

dsh plugin --profile web add @opencode2dsh/dsh-plugin

From source (build the tarball yourself):

git clone https://github.com/FishBottle7/opencode2dsh.git
cd opencode2dsh/packages/plugin
pnpm install && pnpm pack
dsh plugin --profile web add ./opencode2dsh-dsh-plugin-<version>.tgz

Verify: restart dsh web, open the model picker, and pick a model from the opencode2dsh group.

Requires DSH (DeepSeek Harness) 0.1.7 or newer with a web profile (the IP 池 settings page rides the 0.1.7 Plugins page contract); Node.js ≥ 20 (already present if DSH runs); outbound HTTPS to opencode.ai and models.dev.

Configuration

Defaults work out of the box. Override via the profile's cordis.patch.yml:

- id: opencode2dsh
  name: '@opencode2dsh/dsh-plugin'
  config:
    mode: adapter        # adapter (default) | sidecar
    providerId: opencode2dsh
    refreshSeconds: 300  # catalog refresh cadence

Local OpenCode delegation (plugin 0.3.x, docs/delegation.md, ref #76) — opt-in fallback for the persistent 403 FreeTierError credential gate. Disabled by default; the anonymous path is unchanged unless you enable it:

    delegation:
      enabled: true        # arm the delegate (default false)
      # opencodePath: ''   # explicit binary; else managed -> global -> npm
      # minVersion: '1.18.0'  # candidates below this are skipped
      # memLimit: '96MiB'  # GOMEMLIMIT for the child
      # gcPercent: 30      # GOGC for the child
      # trimIntervalMs: 60000  # Windows EmptyWorkingSet tick; 0 disables
      # startTimeoutMs: 60000  # health-wait budget

Enabling it makes the plugin custody your opencode credential (only the opencode entry, seeded 0600 into an isolated XDG root, never logged) and run a managed local opencode serve when — and only when — the anonymous lane and its sibling retry both refuse with the credential gate. Read docs/delegation.md §2 before enabling.

How it works

DSH session
   │  harness chunks (block-start / text-delta / usage / finish …)
   ▼
ZenAdapter (registered LlmAdapter)
   │  pi-ai openai-completions stream (chat models)
   │  pi-ai openai-responses stream (`muse-spark-*`, Responses-only on Zen)
   ▼
https://opencode.ai/zen/v1        ← Authorization: Bearer public
   with CLI-identical headers:
     user-agent: opencode/…
     x-opencode-client, x-opencode-session, x-session-affinity,
     X-Session-Id, x-opencode-request, x-opencode-project

• Session correlation — session/project ids are SHA-256 derived from the conversation's first user turn (stable per conversation, non-reversible), and each request gets a fresh random id, mirroring the CLI.
• Catalog fallback chain — S1: live GET /v1/models; S2: models.dev pricing metadata decides "free"; S3: a compile-time verified static list. A disk cache (~7-day TTL) covers upstream outages.
• Resilience — the adapter registers immediately at startup; if the first catalog fetch races your network (VPN/TUN reconnects, DNS), the plugin retries on a short cadence (~1 min) before settling into the periodic refresh.
• Sidecar mode (mode: sidecar, legacy) — spawns a local Go agent (a single-tenant port of opencode2api) on 127.0.0.1:<random>, token-authenticated, and registers a standard llm-pi-ai route. Not part of the published package; build it from legacy/agent (go build ./cmd/agent) and point agentPath at the binary.

Health & troubleshooting

The plugin writes a health snapshot after every refresh round:

~/.opencode2dsh/adapter-status.json

{
  "status": "ready",
  "total": 64,
  "exposed": 9,
  "lastError": "",
  "writtenAt": "2026-08-29T07:01:54.915Z"
}

Security

• No secrets involved: the anonymous lane's key is the literal string public; nothing is stored, nothing telemetry.
• Install paths restricted to lib/ only; no build scripts run from dependencies.
• All requests go directly from your machine to opencode.ai / models.dev.
• Local OpenCode delegation (docs/delegation.md, ref #76) is opt-in and off by default. Enabling it makes the plugin custody your opencode credential — only the opencode entry, seeded 0600 into an isolated XDG root, never logged, never sent anywhere but the local child — and proxy it through a managed local opencode serve. If upstream deems that abnormal use, your account bears the consequence. Tool execution on your machine is prevented in depth (ask-then-reject + response scan + isolated env); see the doc.

Development

git clone https://github.com/FishBottle7/opencode2dsh.git
cd opencode2dsh/packages/plugin
pnpm install
pnpm typecheck && pnpm test
pnpm build                    # bundle to lib/

The legacy Go sidecar lives in legacy/agent (go test ./...). Architecture notes and the porting record live in docs/.

Releasing: pnpm pack in packages/plugin (prepack builds and syncs docs).

Acknowledgments

• opencode2api by @jasonxu114514 — the legacy Go sidecar in legacy/agent is a port of its anonymous-lane implementation, and the catalog fallback chain and request-disguise details are derived from it. This project stands on its shoulders.
• OpenCode — for running the free anonymous Zen lane.
• @earendil-works/pi-ai — the wire layer used by adapter mode.
• DeepSeek Harness and the dsh-market community.

Friends

License

MIT © FishBottle7