---

opencodezen4dsh is a maintained fork of FishBottle7/opencode2dsh (upstream 0.3.11, MIT), developed at defaver04/opencodezen4dsh. It keeps the upstream's native-adapter architecture and adds three fork-owned improvements — see CHANGELOG.md (fork.2) and CHANGELOG.md (fork.1):

1. xhigh and max thinking levels for every reasoning model. reasoningEfforts() unions the models.dev-declared ladder with FORCED_EFFORT_LEVELS = ['xhigh', 'max'], so models whose metadata declares no ladder (big-pickle, mimo-v2.6-flash-free, …) or a short one (step-5-preview-free, muse-spark-*-contributor-free) no longer hide levels the Zen gateway accepts (reasoning_effort: max and reasoning.effort: xhigh both answer 200 live).
2. muse-spark-1.2-contributor-free and muse-spark-1.3-contributor-free are unblocked. The 403 RegionError recorded upstream in issue #56 does not reproduce from every exit IP; both ids answer HTTP 200 on POST /zen/v1/responses, so they are back in the picker (7 → 9 exposed models on the live catalog). Still blocked, with re-probe evidence: jev-1.13-free (400 ModelProtocolUnsupported, SystemOne-only), exo-free and ling-3.0-flash-fin-free (gone from GET /v1/models).
3. Identity-less tool calls can no longer corrupt the session log (fork.2). When a free-lane model answers a tool turn with a text-shaped <tool_call><parameter=…> imitation instead of a native call, pi-ai assembles an id:""/name:"" tool call that used to be persisted verbatim — poisoning the whole history (tool call id requires a nonempty string, session unopenable). Such calls are now demoted to text with their arguments preserved, so the turn continues instead of corrupting the log.

Install from a build artifact instead of patching by hand:

# from this repo (builds lib/ via prepack)
git clone https://github.com/defaver04/opencodezen4dsh.git && cd opencodezen4dsh/packages/plugin
pnpm install && pnpm pack
dsh plugin --profile web add ./opencodezen4dsh-dsh-plugin-<version>.tgz

or grab the .tgz attached to the latest Release (the release workflow runs typecheck + the full test suite, packs, and uploads it). After installing, restart dsh web — Cordis imports plugin modules once per process, so a picker refresh alone never picks up a new bundle.

---

opencodezen4dsh 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 opencodezen4dsh.

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, plus xhigh/max forced by this fork); 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
• Session-log safe — identity-less tool-call lapses from free-lane models are demoted to text instead of poisoning the durable history (fork.2)

Install

From the plugin market (recommended, once this repo is listed there): in DSH open Settings → Plugin Market, search opencodezen4dsh, one-click install.

From a GitHub Release (recommended today):

# download the .tgz attached to the latest Release, then:
dsh plugin --profile web add ./opencodezen4dsh-dsh-plugin-<version>.tgz

From source (build the tarball yourself):

git clone https://github.com/defaver04/opencodezen4dsh.git
cd opencodezen4dsh/packages/plugin
pnpm install && pnpm pack
dsh plugin --profile web add ./opencodezen4dsh-dsh-plugin-<version>.tgz

Verify: restart dsh web, open the model picker, and pick a model from the opencodezen4dsh 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: opencodezen4dsh
  name: '@opencodezen4dsh/dsh-plugin'
  config:
    mode: adapter        # adapter (default) | sidecar
    providerId: opencodezen4dsh
    refreshSeconds: 300  # catalog refresh cadence

Option	Default	Description
mode	adapter	adapter: native LlmAdapter streaming straight from Zen. sidecar: legacy local-agent mode, not bundled — build the agent from legacy/agent and pass agentPath.
providerId	opencodezen4dsh	Provider name shown in DSH.
refreshSeconds	300	Live catalog refresh interval. Pricing metadata refreshes every 24 h.
agentPath	auto-resolved	Sidecar only: path to the agent binary.
agentArgs	—	Sidecar only: extra CLI args for the agent.
restartDelayMs / restartMaxDelayMs / maxConsecutiveCrashes	1000 / 60000 / 5	Sidecar only: restart backoff and circuit breaker.
firstEventMs / bodyIdleMs / responsesBodyIdleMs	30000 / 120000 / 300000	Adapter only: stream-liveness watchdogs, in ms (integers from 1 to 600000). Time to the first stream event, mid-response body silence, and the body-idle floor for Responses models (muse-spark-*). Increase firstEventMs for slow cold starts. Unset keeps the defaults; restart DSH after editing.

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:

~/.opencodezen4dsh/adapter-status.json

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

Symptom	Likely cause & fix
Boot screen shows Failed to load plugins … list slot "plugins.item" requires options.id, or the IP 池 entry has no configuration page	Your DSH predates the 0.1.7 Plugins page contract. Upgrade DSH to 0.1.7 (latest recommended). On 0.1.6 and older the page never mounts (it is gated on configForms.whileServed) — model routing is unaffected.
DSH 0.1.7/0.2 cannot start after plugin installation (pending … settingsScope)	Upgrade the plugin to 0.3.5+. On DSH 0.2, configure IP pooling through the installed opencodezen4dsh row on the Plugins page.
Only 3 models	Startup fetch raced your network; retries land within ~1 min. Check adapter-status.json for lastError.
lastError: "fetch failed" persisting	Outbound HTTPS to opencode.ai blocked; check proxy/VPN rules.
Rate-limit errors in chat (429 … Endpoint is unavailable)	The anonymous lane is quota-per-IP and free models are contended. The plugin's provider retry policy rides out 429 bursts silently (8 retries, ~1s→20s backoff, ≈90s worst case per step) instead of surfacing them; when contention still wins, lower the reasoning effort, pick a less contended -free model, or enable IP pooling (multi-exit rotation) on the plugin settings page.
Output limit reached after reasoning with no answer	The adapter retries once with thinking Off when the model supports it. Any answer text or tool-call event prevents replay. The retry preserves the original output cap and may still fail; both requests' usage is counted. Models without Off, including Muse, require a manual change of settings or model.
Muse reports REGION_BLOCKED / "This model is not available in your country"	Zen has rejected the current network region for this model. The adapter preserves that explanation rather than mislabeling the 403 as an invalid API key. The anonymous lane does not need a personal key. Use a model available in your region.
Connection error to 127.0.0.1:*	A stale sidecar route shadows the adapter; the plugin removes it at startup.
Install fails with ERR_PNPM_IGNORED_BUILDS	A transitive dependency of pi-ai (@google/genai, protobufjs) has build scripts that are not needed at runtime. Approve-or-decline them via the plugin market, or set both to false under allowBuilds: in the profile's pnpm-workspace.yaml.

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.

Development

git clone https://github.com/defaver04/opencodezen4dsh.git
cd opencodezen4dsh/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); push a v* tag and the release workflow typechecks, tests, packs, and attaches the .tgz to the GitHub Release.

Acknowledgments

• opencode2dsh by @FishBottle7 — the upstream project this fork builds on (0.3.11, MIT). Fork-owned changes are listed at the top of this file and in CHANGELOG.md.
• 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.
• 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.

License

MIT © FishBottle7 (upstream) and defaver04 (fork). See LICENSE.