opencode-models-discovery
A universal OpenCode plugin for dynamic model discovery with flexible configuration for OpenAI-compatible providers.
Runs with mockssource: GitHubTypeScriptMITcommit f0fefdf96361
TypeScript, MIT licensed. The project labels itself: api gateway, dynamic model discovery, llm gateway, lm studio, local ai, local llm, ollama and opencode.
opencode-models-discovery runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm run build passes all 343 tests under Node 22.22.0, the compiled plugin loads and is active in OpenCode v2.2.5, discovers two models from a local OpenAI-compatible mock, and completes an authenticated Hello chat turn using mock/alpha.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- npm ci under default Node 18.19.1 skipped the Rolldown native binary, and Vitest 5 failed importing styleText from node:util8 minutes
- First public npm OpenCode preview host failed to load the plugin because ctx.provider.transform was unavailable7 minutes
- Managed OpenCode service repeatedly failed to bind port 49374 and hung; debug config also hung5 minutes
- CLI invocation with --model mock/alpha reported provider.no-route4 minutes
- Host config was initially placed at XDG_CONFIG_HOME/opencode.json instead of the host-read XDG_CONFIG_HOME/opencode/opencode.json3 minutes
- Mock provider returned non-streaming JSON for streamed chat completions, causing provider.invalid-output retries3 minutes
- Install time
- under a minute
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- PATH=/tmp/node22/bin:$PATH npm run build exited 0 with 43 test files and 343 tests passed; official opencode v2.2.5 /api/model returned HTTP 200 with 2 mock models and /api/plugin showed opencode.models-discovery active; opencode run --server http://127.0.0.1:48775 --model mock/mock/alpha exited 0 with text Hello; mock logged authenticated POST /v1/chat/completions requests with model mock/alpha
- Model tokens used
- 606,761
- Exact commit tested
- f0fefdf96361
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- `npm run build` under Node 22.22.0: exit 0; lint had 0 errors and 20 warnings, typecheck passed, … - Official OpenCode v2 installer: produced `opencode v2.2.5`. - Live integration: plugin active at `/work/repo/dist`; `/api/model` returned `mock/alpha` and `moc… - End-to-end run: `opencode run --model mock/mock/alpha` exited 0 with text `Hello`; the mock recei… **Change** - Added the Node 22.12+ development requirement and explicit `npm ci` / `npm run build` instruction… **Checks and limits** - Default Node 18 cannot run Vitest 5: it fails importing `styleText` from `node:util`. Node 22 was… - Older public npm preview hosts failed with `ctx.provider.transform` unavailable. The official v2.… - The first mock returned non-streaming JSON for a streaming request, causing a retry; replacing it… - An earlier host attempt looped on managed-service port 49374; explicit foreground `serve` ports r… - All temporary services and ports were stopped; no test credentials or third-party keys were requi…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 0.5 minutes, faster than the median of the 31 comparable projects Argusic has measured.
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 32 api-gateway projects Argusic has installed and timed, opencode-models-discovery was the 7th fastest to reach a running state, and 21 of 32 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.35 |
Topics (from GitHub)
api-gatewaydynamic-model-discoveryllm-gatewaylm-studiolocal-ailocal-llmollamaopencodeopencode-pluginself-hosted-llmvllm
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opencode-models-discovery)Questions
- Does opencode-models-discovery run?
- opencode-models-discovery runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test opencode-models-discovery?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f0fefdf96361. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test opencode-models-discovery?
- The run that produced this verdict cost $0.35: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does opencode-models-discovery take to install?
- 0.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does opencode-models-discovery need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing opencode-models-discovery?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does opencode-models-discovery compare with the alternatives?
- Of the 32 api-gateway projects Argusic has installed and timed, opencode-models-discovery was the 7th fastest to reach a running state, and 21 of 32 reached one at all.
- Where is the evidence for opencode-models-discovery?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.