- review model: opencode-go/claude-haiku-5-5#medium instead of deepseek-v4.1-flash#max; flash has no medium variant - merge lint and typecheck into one job with a single pnpm install - cache the pnpm store and opencode binary via actions/cache@v4.1.0, keyed on a sha256 of the lockfile (hashFiles is empty on this runner) - update the decision records and log
4.8 KiB
type, title, description, tags, status, generated, verified, sources
| type | title | description | tags | status | generated | verified | sources | |||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Decision | AI code review setup | The review job runs opencode with a cheap medium-effort opencode-go model, env-only auth, a read-only permission set, and posts only reviews that end with a verdict line. |
|
draft |
|
|
|
Decision
The review job installs opencode v2 from the dedicated v2 installer,
authenticates with OPENCODE_API_KEY from the environment only, runs
opencode-go/claude-haiku-5-5#medium (covered by the Go plan subscription,
no per-token cost), denies edit/shell/webfetch/websearch via a
global permission config written outside the checkout, and posts the
review as a PR comment only if the output ends with a VERDICT: line.
Why each piece
| Piece | Why |
|---|---|
Provider prefix opencode-go, not opencode |
opencode is the pay-per-call Console gateway; the Go plan lives under its own provider id. The wrong prefix failed every run with "Insufficient account funds". |
Model claude-haiku-5-5#medium |
Cheap per token and cheap in the usage window, with a real #medium reasoning level. deepseek-v4.1-flash only exposes low/high/max, so its reviews always paid for the maximum effort. |
The v2 installer (/v2/install) |
The classic installer ships OpenCode 1.x (v1.19.3 on arm64), which cannot resolve model variants and failed with ProviderModelNotFoundError for #max. |
Env-only auth, no opencode.json in the checkout |
A config file in the workspace holds the API key in plaintext where the review agent can read it; a malicious PR diff could prompt-inject the agent into quoting the key in the publicly visible review comment. Environment variables are invisible to file reads. |
| Deny write tools via a global config outside the checkout | Headless runs cannot answer permission prompts; denials prevent both hangs and repo modification. The config file itself holds no secret, so its location leaks nothing. |
| Verdict line as the posting gate | opencode can exit non-zero after a fully completed review (observed: benign permission denials). A completed review always ends with a verdict line; error dumps never do. The verdict, not the exit code, decides whether a comment is posted. |
--print-logs |
Provider and auth errors otherwise die inside the captured output file, invisible in the job log. |
| Diff passed as a file, lockfile excluded | The diff as a CLI argument exceeded MAX_ARG_STRLEN (128 KiB per argument; the diff was 190 KB, mostly pnpm-lock.yaml). The agent reads .pr-review-diff.patch with its file tools. |
The review prompt
The prompt names the stack (Nuxt 4 frontend, Go backends to come), lists
what the other CI jobs already catch so the model does not repeat them,
and focuses on SSR/hydration pitfalls, reactivity bugs, injection and
authz gaps, runtime-config leaks, and Go error/concurrency hygiene. It
prescribes the output format ([BLOCKER]/[WARN]/[NIT] file:line) and
derives the verdict from the findings, so the gate and the prompt agree.
Evidence
- First real review on PR #5 (2026-10-18): produced five findings,
including a genuine regression in the workflow itself (a lost
chmod +xon the droast binary), verified upstream release assets and the v2 permission schema live, and returnedVERDICT: REQUEST_CHANGES. - Fresh-container replica test (node:22-bookworm, key-only auth)
reproduced the CI failure exactly, then confirmed the v2 +
#maxfix before it was pushed. - Model history:
deepseek-v4-pro#maxwas replaced bydeepseek-v4.1-flash#maxafter two consecutive endpoint outages, then byclaude-haiku-5-5#medium(2026-10-20) to stop paying maximum reasoning effort on every review. The flash model had no#mediumvariant to fall back to.
Not verified
- Whether
#mediumstill resolves after a future CLI upgrade — the variant list comes from the model catalog, not a contract. - Whether the smaller model still catches the same class of findings as the first flash review. The PR #14 findings are the baseline; re-run the eval on the next few PRs.
- Long-run behaviour of Go plan usage windows under real review frequency, now that the model is cheaper.
Revisit when
- A PR review fails again with a new error class — check the provider prefix, the CLI version, and the usage limits first; they caused every failure so far.
- A flash-tier model gains a
#mediumvariant and beats the current model on the PR #14 eval set — the present pick is a cost/quality compromise, not a permanent one. - Go Plus or pay-as-you-go balance becomes relevant.