opencode/AGENTS.md
2026-07-09 22:47:37 -04:00

11 KiB

  • To regenerate the legacy JavaScript SDK, run ./packages/sdk/js/script/build.ts.
  • After changing the public Protocol or Server HttpApi, run bun run generate from packages/client. Do not edit src/generated or src/generated-effect directly.
  • Keep runtime dependencies directed from Schema to Core and Protocol, then from Core and Protocol to Server. Client runtime code may depend on Schema and Protocol but never Core or Server; sdk-next composes Client, Core, and Server.
  • Do not modify packages/opencode unless the user explicitly asks for V1 work. packages/opencode is the V1 implementation and is present for reference only. New implementation changes should land in the V2 package set: packages/core, packages/cli, packages/server, packages/protocol, packages/schema, and related generated client surfaces when required.
  • The default branch in this repo is dev.
  • Local main ref may not exist; use dev or origin/dev for diffs.

Branch Names

Use a short branch name of at most three words, separated by hyphens. Do not use slashes or type prefixes such as feat/ or fix/.

Examples: session-recovery, fix-scroll-state, regenerate-sdk.

Commits and PR Titles

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.

Never bypass Git hooks. Do not use --no-verify or otherwise disable, skip, or circumvent commit or push hooks. If a hook fails, fix the failure or stop and report it to the user.

Style Guide

General Principles

  • 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.
  • In Effect generators, bind services to named variables before calling methods. Do not use nested service yields such as yield* (yield* Foo.Service).bar().

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()

Destructuring

Avoid unnecessary destructuring. Use dot notation to preserve context.

// Good
obj.a
obj.b

// Bad
const { a, b } = obj

Imports

  • 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.

Variables

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

Control Flow

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
}

Complex Logic

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.

Schema Definitions (Drizzle)

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(),
})

Testing

  • Avoid mocks as much as possible, you shouldn't be using globalThis.* at all unless it's the only option.
  • 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.

Type Checking

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

V2 Session Core

  • Keep durable events minimal: record irreducible new facts and do not repeat state derivable by folding the ordered aggregate history. Enrich projections and read models with previous or derived state when consumers need self-contained views.
  • Keep durable prompt admission separate from model execution. SessionV2.prompt(...) admits one durable session_pending 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, consuming the pending row in the same event transaction; session_pending stores only unconsumed work.
  • 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. Retry of an already-promoted input reconciles against the projected message and the durable admitted event rather than a retained row.
  • Keep SessionExecution process-global and Session-ID based. Its local implementation owns the process-local Session coordinator and discovers placement through SessionStore plus LocationServiceMap.get(session.location) only when a drain starts; no layer should take a Session ID. V2 interruption targets the active process-local ownership chain for that Session; interruption of a known but idle or locally unowned Session is a no-op, while the public API rejects an unknown Session.
  • 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 Physical Attempt and reload projected history before durable continuation. Most Steps have one Physical Attempt; overflow-triggered compaction recovery may rebuild one Step for a second attempt. 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 continuation recovery requires a separate explicit design before it may retry provider work. A drain has no durable identity or transcript boundary.
  • Keep delivery vocabulary explicit. Prompts steer by default and promote at the next safe step boundary while the current drain requires continuation. An explicit queue input remains pending until the Session would otherwise become idle; promote one queued input at that boundary, then reevaluate continuation before promoting another. Promoting any new user input resets the selected agent's step allowance; a batch of steers resets it once.
  • One step is one logical LLM call; its durable record covers only the model-visible span. Do not write "provider turn", and do not use bare "turn" for a single call: "turn" is reserved for the future assistant-turn unit containing all steps from prompt promotion until the session would go idle.
  • Keep EventV2 replay owner claims separate from clustered Session execution ownership.
  • Keep the Instructions algebra and built-ins in src/instructions; keep instruction producers with their observed domains, and keep Session History selection plus InstructionCheckpoint and InstructionEntry persistence Session-owned. InstructionDiscovery observes ambient global and upward-project instructions. The runner composes built-ins, discovery, guidance, and entries explicitly in loadInstructions; there is no instruction registry.
  • The durable Instructions.Applied record is what the model was last told, per instruction source. Reconciliation narrates drift through session.instructions.updated and never rewrites the baseline; only completed compaction rebaselines, while Session movement or committed revert resets the InstructionCheckpoint. Unavailable sources keep the model's prior belief, blocking only a Session's first instruction baseline.