• To regenerate the JavaScript SDK, run ./packages/sdk/js/script/build.ts.
• The default branch in this repo is dev.
• Local main ref may not exist; use dev or origin/dev for diffs.

Use conventional commit-style messages and PR titles: type(scope): summary.

Valid types are feat, fix, docs, chore, refactor, and test. Scopes are optional; use the affected package or area when helpful, e.g. core, opencode, tui, app, desktop, sdk, or plugin.

Examples: fix(tui): simplify thinking toggle styling, docs: update contributing guide, chore(sdk): regenerate types.

• Keep things in one function unless composable or reusable
• Do not extract single-use helpers preemptively. Inline the logic at the call site unless the helper is reused, hides a genuinely complex boundary, or has a clear independent name that improves the caller.
• Avoid try/catch where possible
• Avoid using the any type
• Use Bun APIs when possible, like Bun.file()
• Rely on type inference when possible; avoid explicit type annotations or interfaces unless necessary for exports or clarity
• Prefer functional array methods (flatMap, filter, map) over for loops; use type guards on filter to maintain type inference downstream
• In src/config, follow the existing self-export pattern at the top of the file (for example export * as ConfigAgent from "./agent") when adding a new config module.

Reduce total variable count by inlining when a value is only used once.

// Good
const journal = await Bun.file(path.join(dir, "journal.json")).json()

// Bad
const journalPath = path.join(dir, "journal.json")
const journal = await Bun.file(journalPath).json()

Avoid unnecessary destructuring. Use dot notation to preserve context.

// Good
obj.a
obj.b

// Bad
const { a, b } = obj

• Never alias imports. Do not use import { foo as bar } from "..." or renamed imports like resolve as pathResolve.
• Never use star imports. Do not use import * as Foo from "..." or import type * as Foo from "...".
• If a namespace-style value is needed, import the module's own exported namespace by name, for example import { Project } from "@opencode-ai/core/project", then reference Project.ID.
• Prefer dynamic imports for heavy modules that are only needed in selected code paths, especially in startup-sensitive entrypoints. Destructure dynamic import bindings near the top of the narrowest scope that needs them so they read like normal imports. Avoid inline chains such as await import("./module").then((mod) => mod.value()) or (await import("./module")).value(). Keep branch-specific imports inside the branch that needs them to preserve lazy loading.

Prefer const over let. Use ternaries or early returns instead of reassignment.

// Good
const foo = condition ? 1 : 2

// Bad
let foo
if (condition) foo = 1
else foo = 2

Avoid else statements. Prefer early returns.

// Good
function foo() {
  if (condition) return 1
  return 2
}

// Bad
function foo() {
  if (condition) return 1
  else return 2
}

When a function has several validation branches or supporting details, make the main function read as the happy path and move supporting details into small helpers below it.

// Good
export function loadThing(input: unknown) {
  const config = requireConfig(input)
  const metadata = readMetadata(input)
  return createThing({ config, metadata })
}

function requireConfig(input: unknown) {
  ...
}

• Keep helpers close to the code they support, below the main export when that improves readability.
• Do not over-abstract simple expressions into many single-use helpers; extract only when it names a real concept like requireConfig or readMetadata.
• Do not return Effect from helpers unless they actually perform effectful work. Synchronous parsing, validation, and option building should stay synchronous.
• Prefer Effect schema helpers such as Schema.UnknownFromJsonString and Schema.decodeUnknownOption over manual JSON.parse wrapped in Effect.try when parsing untrusted JSON strings.
• Add comments for non-obvious constraints and surprising behavior, not for obvious assignments or control flow.

Use snake_case for field names so column names don't need to be redefined as strings.

// Good
const table = sqliteTable("session", {
  id: text().primaryKey(),
  project_id: text().notNull(),
  created_at: integer().notNull(),
})

// Bad
const table = sqliteTable("session", {
  id: text("id").primaryKey(),
  projectID: text("project_id").notNull(),
  createdAt: integer("created_at").notNull(),
})

• Avoid mocks as much as possible
• Test actual implementation, do not duplicate logic into tests
• Tests cannot run from repo root (guard: do-not-run-tests-from-root); run from package dirs like packages/opencode.

• Always run bun typecheck from package directories (e.g., packages/opencode), never tsc directly.

• Keep durable prompt admission separate from model execution. SessionV2.prompt(...) admits one durable session_input row before scheduling advisory SessionExecution.wake(sessionID) unless resume: false requests admit-only behavior. The serialized runner promotes admitted inputs into visible user messages at safe boundaries.
• Reusing a Session ID adopts the existing Session. Reusing a prompt message ID reconciles an exact retry only when Session, prompt, and delivery mode match; conflicting reuse fails. Historical projected prompts lazily synthesize promoted inbox records during exact retry.
• Keep SessionExecution process-global and Session-ID based. It discovers placement through the read-side SessionStore and LocationServiceMap.get(session.location); no layer should take a Session ID.
• Keep SessionRunner, model resolution, tool registry, permissions, and filesystem Location-scoped. Omitted Location.workspaceID means implicit-local placement; explicit workspace identity remains reserved for future placement semantics.
• Preserve one explicit llm.stream(request) call per provider turn and reload projected history before durable continuation. Do not bridge through legacy SessionPrompt.loop(...) or delegate orchestration to an in-memory tool loop.
• Keep local Session drains process-local until clustering is implemented. SessionRunCoordinator joins explicit same-Session resumes, coalesces prompt wakeups, and allows different Sessions to run concurrently. Advisory wakes drain eligible durable inbox rows only; post-crash activity recovery requires a separate explicit design before it may retry provider work.
• Keep delivery vocabulary explicit. Prompts steer by default and coalesce into the active activity at the next safe provider-turn boundary. Explicit queue inputs open FIFO future activities one at a time after the active activity settles.
• Keep EventV2 replay owner claims separate from clustered Session execution ownership.