Compare commits

..

2 Commits

Author SHA1 Message Date
Aiden Cline e99f505187 refactor(core): clarify catalog replacement name 2026-07-24 21:01:09 -05:00
Aiden Cline 2e7390f29f fix(core): keep execute tool cache stable 2026-07-24 20:36:26 -05:00
21 changed files with 223 additions and 767 deletions
-1
View File
@@ -63,7 +63,6 @@ const layer = Layer.effect(
if (rule?.resource === "*" && rule.effect === "deny") continue
registrations.set(name, registration)
}
if (registrations.size === 0) return {}
const executeRule = rules.findLast((rule) => Wildcard.match("execute", rule.action))
if (executeRule?.resource === "*" && executeRule.effect === "deny") return {}
return {
+17 -13
View File
@@ -6,7 +6,9 @@ import { Instructions } from "../instructions/index"
import { CodeModeCatalog } from "./catalog"
// prettier-ignore
const prompt = (hasMoreTools: boolean) => `The Code Mode tool catalog below is ${hasMoreTools ? "partial" : "complete"}.${hasMoreTools ? `
const prompt = (hasMoreTools: boolean) => `The Code Mode tool catalog below is ${hasMoreTools ? "partial" : "complete"}.
Inside Code Mode, \`tools\` contains only the tools shown below${hasMoreTools ? " or returned by `search`" : ""}; surrounding top-level agent tools are not available and must not be called from the code.${hasMoreTools ? `
## Search
@@ -17,7 +19,8 @@ Use \`search\` to discover exact paths and signatures for additional tools:
## Available tools`
export function render(catalog: CodeModeCatalog.Summary) {
if (catalog.total === 0) return "No tools are currently available."
if (catalog.total === 0)
return "No Code Mode tools are currently available. Do not call `execute` until a later system update announces available tools."
const tools = catalog.namespaces.flatMap((namespace) => {
const count = namespace.count === 1 ? "1 tool" : `${namespace.count} tools`
@@ -36,12 +39,13 @@ ${tools.join("\n")}`
}
export function update(previous: CodeModeCatalog.Summary, current: CodeModeCatalog.Summary) {
const full = `The Code Mode tool catalog has changed. This catalog supersedes the previous Code Mode tool catalog.
const replacement = `The Code Mode tool catalog has changed. This catalog supersedes the previous Code Mode tool catalog.
${render(current)}`
if (current.total === 0) return replacement
const previousComplete = previous.shown === previous.total
const currentComplete = current.shown === current.total
if (previousComplete !== currentComplete) return full
if (previousComplete !== currentComplete) return replacement
const diff = Instructions.diffByKey(
previous.namespaces.flatMap((namespace) => namespace.entries),
@@ -52,7 +56,7 @@ ${render(current)}`
const entriesChanged = diff.added.length > 0 || diff.removed.length > 0 || diff.changed.length > 0
if (!currentComplete) {
if (entriesChanged) return full
if (entriesChanged) return replacement
const namespaces = Instructions.diffByKey(
previous.namespaces,
current.namespaces,
@@ -60,7 +64,7 @@ ${render(current)}`
(before, after) => before.count !== after.count,
)
const changed = namespaces.added.length > 0 || namespaces.removed.length > 0 || namespaces.changed.length > 0
if (!changed) return full
if (!changed) return replacement
const parts = ["The Code Mode tool catalog has changed."]
if (namespaces.added.length > 0) {
@@ -85,11 +89,11 @@ ${render(current)}`
)
}
const delta = parts.join("\n\n")
if (delta.length < full.length) return delta
return full
if (delta.length < replacement.length) return delta
return replacement
}
if (!entriesChanged) return full
if (!entriesChanged) return replacement
const parts = ["The Code Mode tool catalog has changed."]
if (diff.added.length > 0) {
parts.push(
@@ -115,19 +119,19 @@ ${render(current)}`
)
}
const delta = parts.join("\n\n")
if (delta.length < full.length) return delta
return full
if (delta.length < replacement.length) return delta
return replacement
}
const key = Instructions.Key.make("core/codemode")
const codec = Schema.toCodecJson(CodeModeCatalog.Summary)
export const make = (entries?: ReadonlyArray<CodeModeCatalog.Entry>): Instructions.Instructions => {
const catalog = CodeModeCatalog.summarize(entries ?? [])
const catalog = entries === undefined ? Instructions.removed : CodeModeCatalog.summarize(entries)
return Instructions.make({
key,
codec,
read: Effect.succeed(catalog.total === 0 ? Instructions.removed : catalog),
read: Effect.succeed(catalog),
render: {
initial: render,
changed: update,
+1 -2
View File
@@ -36,8 +36,7 @@ type CollectedFiles = {
const description = [
"Run JavaScript to orchestrate tool calls and compose their results through `{ code }` in a confined Code Mode runtime.",
"Imports, direct filesystem access, and timers are unavailable. Do not use `fetch`; all external access goes through `tools`.",
"Within `{ code }`, the only callable tools are those explicitly listed in the Code Mode catalog instructions or returned by `search`. Inside `{ code }`, ignore tools shown outside the Code Mode catalog. They are not available in the Code Mode runtime.",
'Call tools through `tools` using only exact paths and signatures from the catalog. Do not infer or normalize tool names; preserve bracket notation such as `tools.<namespace>["tool-name"](input)`.',
'Call Code Mode tools through `tools` using only exact paths and signatures from the current catalog or `search`. Do not infer or normalize tool names; preserve bracket notation such as `tools.<namespace>["tool-name"](input)`.',
"Prefer an explicit `return`; if omitted, the final top-level expression becomes the result.",
"Await every call whose completion matters; pending calls are interrupted when execution ends. Run independent calls concurrently with `Promise.all`.",
].join("\n")
+10 -5
View File
@@ -67,7 +67,9 @@ describe("CodeModeInstructions.render", () => {
expect(instructions).toContain(` - ${lookup.signature} // Look up an order by ID`)
expect(instructions).not.toContain("## Search")
expect(instructions).toContain("The Code Mode tool catalog below is complete.")
expect(instructions).not.toContain("surrounding top-level agent tools")
expect(instructions).toContain(
"`tools` contains only the tools shown below; surrounding top-level agent tools are not available and must not be called from the code.",
)
})
test("adds search guidance when the catalog exceeds the budget", () => {
@@ -76,7 +78,9 @@ describe("CodeModeInstructions.render", () => {
expect(partial).toContain("- orders (1 tool, none shown)")
expect(partial).toContain("## Search")
expect(partial).toContain("The Code Mode tool catalog below is partial.")
expect(partial).not.toContain("surrounding top-level agent tools")
expect(partial).toContain(
"`tools` contains only the tools shown below or returned by `search`; surrounding top-level agent tools are not available and must not be called from the code.",
)
expect(partial).toContain("- search(input: {")
expect(partial).toContain(" limit?: number,\n offset?: number,")
expect(partial).not.toContain("tools.orders.lookup(input:")
@@ -113,7 +117,9 @@ describe("CodeModeInstructions.render", () => {
})
test("renders only the no-tools notice for an empty catalog", () => {
expect(render([])).toBe("No tools are currently available.")
expect(render([])).toBe(
"No Code Mode tools are currently available. Do not call `execute` until a later system update announces available tools.",
)
})
})
@@ -123,8 +129,7 @@ describe("CodeModeInstructions.update", () => {
test("renders additions, changes, and removals as a compact semantic delta", () => {
const changed = { ...echo, signature: "tools.notes.echo(input: {\n text: string,\n}): Promise<string>" }
const added = entry("notes.list", "List notes")
const unchanged = Array.from({ length: 5 }, (_, index) => entry(`stable.tool${index}`, `Stable ${index}`))
const text = update([echo, lookup, ...unchanged], [changed, added, ...unchanged])
const text = update([echo, lookup], [changed, added])
expect(text).toContain("The Code Mode tool catalog has changed.")
expect(text).toContain(`New tools are available in addition to those previously listed:\n - ${added.signature}`)
expect(text).toContain(
@@ -21,6 +21,25 @@ const lookup: CodeModeCatalog.Entry = {
}
describe("CodeModeInstructions", () => {
it.effect("instructs the model not to call execute while the catalog is empty", () =>
Effect.gen(function* () {
const initialized = yield* readInitial(CodeModeInstructions.make([]))
expect(initialized.text).toBe(
"No Code Mode tools are currently available. Do not call `execute` until a later system update announces available tools.",
)
const added = yield* readUpdate(CodeModeInstructions.make([echo]), initialized)
expect(added.text).toContain("New tools are available in addition to those previously listed:")
expect(added.text).toContain(echo.signature)
expect(yield* readUpdate(CodeModeInstructions.make([]), { values: added.values })).toMatchObject({
text:
"The Code Mode tool catalog has changed. This catalog supersedes the previous Code Mode tool catalog.\n\n" +
"No Code Mode tools are currently available. Do not call `execute` until a later system update announces available tools.",
})
}),
)
it.effect("renders the initial catalog, semantic deltas, and removal", () =>
Effect.gen(function* () {
const initialized = yield* readInitial(CodeModeInstructions.make([echo]))
+16
View File
@@ -32,6 +32,22 @@ export function waitForTool(
})
}
export function waitForCodeModeTool(
registry: ToolRegistry.Interface,
path: string,
remaining = 1000,
): Effect.Effect<ToolRegistry.ToolSet, Error> {
return Effect.gen(function* () {
const toolSet = yield* registry.snapshot()
if (toolSet.codeModeCatalog?.some((tool) => tool.path === path)) return toolSet
if (remaining === 0) {
return yield* Effect.fail(new Error(`Timed out waiting for Code Mode tool: ${path}`))
}
yield* Effect.promise(() => Bun.sleep(1))
return yield* waitForCodeModeTool(registry, path, remaining - 1)
})
}
/**
* Registers a core tool plugin's tools against the real registry without booting the
* full plugin host. Only the tool domain is live; focused tool tests exercise
+14 -8
View File
@@ -33,7 +33,7 @@ import { Image } from "@opencode-ai/core/image"
import { testEffect } from "./lib/effect"
import { imagePassthrough } from "./lib/image"
import { location } from "./fixture/location"
import { executeTool, toolDefinitions, toolIdentity, waitForTool } from "./lib/tool"
import { executeTool, toolDefinitions, toolIdentity, waitForCodeModeTool, waitForTool } from "./lib/tool"
let assertion: Deferred.Deferred<PermissionV2.AssertInput> | undefined
let decision: Effect.Effect<void, PermissionV2.Error> = Effect.void
@@ -802,10 +802,16 @@ test("serializes concurrent MCP lifecycle operations", async () => {
it.effect("advertises MCP output schemas to Code Mode", () =>
Effect.gen(function* () {
const registry = yield* ToolRegistry.Service
yield* waitForTool(registry, "execute")
const definitions = yield* toolDefinitions(registry)
const execute = definitions.find((tool) => tool.name === "execute")
const toolSet = yield* waitForCodeModeTool(registry, "demo.search")
const execute = toolSet.definitions.find((tool) => tool.name === "execute")
expect(toolSet.definitions.map((tool) => tool.name)).toEqual([
"direct_fail",
"direct_lookup",
"direct_media",
"execute",
])
expect(toolSet.codeModeCatalog?.find((tool) => tool.path === "demo.search")?.signature).toContain("ok: boolean")
expect(execute?.description).not.toContain("tools.demo.search")
}),
)
@@ -873,9 +879,9 @@ it.effect("waits for permission before calling an MCP tool", () =>
const permission = yield* Deferred.make<void>()
decision = Deferred.await(permission)
const registry = yield* ToolRegistry.Service
yield* waitForTool(registry, "execute")
const toolSet = yield* waitForCodeModeTool(registry, "demo.search")
const fiber = yield* executeTool(registry, {
const fiber = yield* toolSet.execute({
sessionID: SessionV2.ID.make("ses_mcp_permission"),
...toolIdentity,
call: {
@@ -912,9 +918,9 @@ it.effect("does not call MCP when permission is blocked", () =>
assertion = yield* Deferred.make<PermissionV2.AssertInput>()
decision = Effect.fail(new PermissionV2.BlockedError({ rules: [], permission: "demo_search", resources: ["*"] }))
const registry = yield* ToolRegistry.Service
yield* waitForTool(registry, "execute")
const toolSet = yield* waitForCodeModeTool(registry, "demo.search")
const execution = yield* executeTool(registry, {
const execution = yield* toolSet.execute({
sessionID: SessionV2.ID.make("ses_mcp_blocked"),
...toolIdentity,
call: {
@@ -186,6 +186,7 @@ describe("SessionRunnerLLM recorded", () => {
yield* agents.transform((draft) =>
draft.update(AgentV2.ID.make("build"), (agent) => {
agent.mode = "primary"
agent.permissions.push({ action: "execute", resource: "*", effect: "deny" })
}),
)
const pluginHost = host({
@@ -88,7 +88,7 @@ describe("ToolRegistry", () => {
expect(error).toBeInstanceOf(Tool.RegistrationError)
expect(error.message).toBe('Invalid tool namespace: "slack..admin"')
expect((yield* service.snapshot()).definitions).toEqual([])
expect((yield* service.snapshot()).definitions.map((tool) => tool.name)).toEqual(["execute"])
}),
)
@@ -102,7 +102,7 @@ describe("ToolRegistry", () => {
.register({ "echo.tool": make(), echo_tool: make() }, { codemode: false })
.pipe(Effect.flip)
expect(collision.message).toBe("Duplicate normalized tool name: echo_tool")
expect((yield* service.snapshot()).definitions).toEqual([])
expect((yield* service.snapshot()).definitions.map((tool) => tool.name)).toEqual(["execute"])
}),
)
@@ -117,7 +117,7 @@ describe("ToolRegistry", () => {
.pipe(Effect.flip)
expect(error).toBeInstanceOf(Tool.RegistrationError)
expect((yield* service.snapshot()).definitions).toEqual([])
expect((yield* service.snapshot()).definitions.map((tool) => tool.name)).toEqual(["execute"])
}),
)
@@ -148,6 +148,20 @@ describe("ToolRegistry", () => {
}),
)
it.effect("keeps execute available without Code Mode tools unless explicitly denied", () =>
Effect.gen(function* () {
const service = yield* ToolRegistry.Service
const available = yield* service.snapshot()
expect(available.definitions.map((tool) => tool.name)).toEqual(["execute"])
expect(available.codeModeCatalog).toEqual([])
const denied = yield* service.snapshot([{ action: "execute", resource: "*", effect: "deny" }])
expect(denied.definitions).toEqual([])
expect(denied.codeModeCatalog).toBeUndefined()
}),
)
it.effect("filters disabled tools with edit aliases and ordered wildcard precedence", () =>
Effect.gen(function* () {
const service = yield* ToolRegistry.Service
@@ -156,7 +170,12 @@ describe("ToolRegistry", () => {
const names = (permissions: PermissionV2.Ruleset) =>
toolDefinitions(service, permissions).pipe(Effect.map((definitions) => definitions.map((tool) => tool.name)))
expect(yield* names([{ action: "question", resource: "*", effect: "deny" }])).toEqual(["bash", "edit", "write"])
expect(yield* names([{ action: "question", resource: "*", effect: "deny" }])).toEqual([
"bash",
"edit",
"write",
"execute",
])
expect(
yield* names([
{ action: "*", resource: "*", effect: "deny" },
@@ -169,7 +188,11 @@ describe("ToolRegistry", () => {
{ action: "*", resource: "*", effect: "deny" },
]),
).toEqual([])
expect(yield* names([{ action: "edit", resource: "*", effect: "deny" }])).toEqual(["bash", "question"])
expect(yield* names([{ action: "edit", resource: "*", effect: "deny" }])).toEqual([
"bash",
"question",
"execute",
])
}),
)
@@ -182,7 +205,7 @@ describe("ToolRegistry", () => {
expect(
(yield* toolDefinitions(service, [{ action: "edit", resource: "*", effect: "deny" }])).map((tool) => tool.name),
).toEqual(["first"])
).toEqual(["first", "execute"])
}),
)
@@ -191,9 +214,9 @@ describe("ToolRegistry", () => {
const service = yield* ToolRegistry.Service
const scope = yield* Scope.make()
yield* service.register({ echo: make() }, { codemode: false }).pipe(Scope.provide(scope))
expect((yield* toolDefinitions(service)).map((tool) => tool.name)).toEqual(["echo"])
expect((yield* toolDefinitions(service)).map((tool) => tool.name)).toEqual(["echo", "execute"])
yield* Scope.close(scope, Exit.void)
expect(yield* toolDefinitions(service)).toEqual([])
expect((yield* toolDefinitions(service)).map((tool) => tool.name)).toEqual(["execute"])
}),
)
@@ -213,9 +236,9 @@ describe("ToolRegistry", () => {
yield* Deferred.await(registered)
yield* Fiber.interrupt(fiber)
expect((yield* toolDefinitions(service)).map((tool) => tool.name)).toEqual(["echo"])
expect((yield* toolDefinitions(service)).map((tool) => tool.name)).toEqual(["echo", "execute"])
yield* Scope.close(scope, Exit.void)
expect(yield* toolDefinitions(service)).toEqual([])
expect((yield* toolDefinitions(service)).map((tool) => tool.name)).toEqual(["execute"])
}),
)
+40
View File
@@ -880,6 +880,46 @@ describe("SessionRunnerLLM", () => {
}),
)
it.effect("advertises execute and durable guidance for an empty Code Mode catalog", () =>
Effect.gen(function* () {
const session = yield* setup
const empty = {
catalog: [],
tool: Tool.make({
description: "Execute Code Mode",
input: Schema.Struct({ code: Schema.String }),
output: Schema.String,
execute: () => Effect.succeed({ output: "unused" }),
}),
}
codeModeMaterializations = [empty, empty, {}]
yield* admit(session, "Continue without Code Mode tools")
response = reply.stop()
yield* session.resume(sessionID)
yield* admit(session, "Still no Code Mode tools")
yield* session.resume(sessionID)
yield* admit(session, "Code Mode denied")
yield* session.resume(sessionID)
expect(requests).toHaveLength(3)
expect(requests[0]?.tools.map((tool) => tool.name)).toEqual(["defect", "echo", "storefail", "execute"])
expect(requests[0]?.system.some((part) => part.text.includes("Do not call `execute`"))).toBe(true)
expect(requests[1]?.tools.map((tool) => tool.name)).toEqual(["defect", "echo", "storefail", "execute"])
expect(requests[1]?.messages.filter((message) => message.role === "system")).toEqual([])
expect(requests[2]?.tools.map((tool) => tool.name)).toEqual(["defect", "echo", "storefail"])
expect(
requests[2]?.messages.some(
(message) =>
message.role === "system" &&
message.content.some(
(part) => part.type === "text" && part.text.includes("Code Mode tools are no longer available"),
),
),
).toBe(true)
}),
)
it.effect("applies session context hooks without exposing unavailable tools", () =>
Effect.gen(function* () {
const session = yield* setup
+6 -4
View File
@@ -137,10 +137,12 @@ describe("EditTool", () => {
Effect.andThen(
withTool(tmp.path, (registry) =>
Effect.gen(function* () {
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["edit"])
expect(yield* toolDefinitions(registry, [{ action: "edit", resource: "*", effect: "deny" }])).toEqual(
[],
)
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["edit", "execute"])
expect(
(yield* toolDefinitions(registry, [{ action: "edit", resource: "*", effect: "deny" }])).map(
(tool) => tool.name,
),
).toEqual(["execute"])
const settled = yield* executeTool(
registry,
call({ path: "hello.txt", oldString: "before", newString: "after" }),
+1 -2
View File
@@ -19,8 +19,7 @@ test("execute describes invariant Code Mode behavior", () => {
[
"Run JavaScript to orchestrate tool calls and compose their results through `{ code }` in a confined Code Mode runtime.",
"Imports, direct filesystem access, and timers are unavailable. Do not use `fetch`; all external access goes through `tools`.",
"Within `{ code }`, the only callable tools are those explicitly listed in the Code Mode catalog instructions or returned by `search`. Inside `{ code }`, ignore tools shown outside the Code Mode catalog. They are not available in the Code Mode runtime.",
'Call tools through `tools` using only exact paths and signatures from the catalog. Do not infer or normalize tool names; preserve bracket notation such as `tools.<namespace>["tool-name"](input)`.',
'Call Code Mode tools through `tools` using only exact paths and signatures from the current catalog or `search`. Do not infer or normalize tool names; preserve bracket notation such as `tools.<namespace>["tool-name"](input)`.',
"Prefer an explicit `return`; if omitted, the final top-level expression becomes the result.",
"Await every call whose completion matters; pending calls are interrupted when execution ends. Run independent calls concurrently with `Promise.all`.",
].join("\n"),
+1 -1
View File
@@ -181,7 +181,7 @@ describe("PatchTool", () => {
Effect.andThen(
withTool(tmp.path, (registry) =>
Effect.gen(function* () {
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["patch"])
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["patch", "execute"])
const settled = yield* executeTool(
registry,
call(
+6 -2
View File
@@ -97,7 +97,11 @@ describe("QuestionTool", () => {
deny = true
const registry = yield* ToolRegistry.Service
expect(yield* toolDefinitions(registry, [{ action: "question", resource: "*", effect: "deny" }])).toEqual([])
expect(
(yield* toolDefinitions(registry, [{ action: "question", resource: "*", effect: "deny" }])).map(
(tool) => tool.name,
),
).toEqual(["execute"])
expect(
yield* executeTool(registry, {
sessionID,
@@ -142,7 +146,7 @@ describe("QuestionTool", () => {
},
]
expect((yield* toolDefinitions(registry)).map((definition) => definition.name)).toEqual(["question"])
expect((yield* toolDefinitions(registry)).map((definition) => definition.name)).toEqual(["question", "execute"])
expect(
yield* executeTool(registry, {
sessionID,
+6 -2
View File
@@ -197,8 +197,12 @@ describe("ReadTool", () => {
Effect.gen(function* () {
const registry = yield* ToolRegistry.Service
expect(yield* toolDefinitions(registry)).toMatchObject([{ name: "read" }])
expect(yield* toolDefinitions(registry, [{ action: "read", resource: "*", effect: "deny" }])).toEqual([])
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["read", "execute"])
expect(
(yield* toolDefinitions(registry, [{ action: "read", resource: "*", effect: "deny" }])).map(
(tool) => tool.name,
),
).toEqual(["execute"])
const execution = yield* executeTool(registry, {
sessionID,
...toolIdentity,
+1 -1
View File
@@ -92,7 +92,7 @@ describe("WebFetchTool registration", () => {
const registry = yield* ToolRegistry.Service
const url = "http://example.com/public"
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["webfetch"])
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["webfetch", "execute"])
expect(yield* executeTool(registry, call({ url, format: "text", timeout: 4 }))).toEqual({
status: "completed",
output: { url, contentType: "text/plain", format: "text", output: "hello" },
+1 -1
View File
@@ -154,7 +154,7 @@ describe("WebSearchTool registration", () => {
config = { provider: "exa", enableExa: false, enableParallel: false }
const registry = yield* ToolRegistry.Service
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["websearch"])
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["websearch", "execute"])
expect(
yield* executeTool(registry, {
sessionID,
+1 -1
View File
@@ -118,7 +118,7 @@ describe("WriteTool", () => {
reset()
return withTool(tmp.path, (registry) =>
Effect.gen(function* () {
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["write"])
expect((yield* toolDefinitions(registry)).map((tool) => tool.name)).toEqual(["write", "execute"])
const settled = yield* executeTool(registry, call({ path: "src/new.txt", content: "created" }))
expect(settled).toEqual({
status: "completed",
+4 -16
View File
@@ -1,9 +1,8 @@
import { RGBA } from "@opentui/core"
import { useTheme } from "../context/theme"
import { Spinner } from "./spinner"
export function Reconnecting() {
const { themeV2 } = useTheme().contextual("elevated")
const { themeV2 } = useTheme()
return (
<box
@@ -13,23 +12,12 @@ export function Reconnecting() {
right={0}
bottom={0}
left={0}
backgroundColor={RGBA.fromInts(0, 0, 0, 150)}
backgroundColor={themeV2.background.default}
alignItems="center"
justifyContent="center"
>
<box
width={48}
maxWidth="90%"
flexDirection="column"
backgroundColor={themeV2.background.default}
paddingTop={1}
paddingBottom={1}
paddingLeft={2}
paddingRight={2}
gap={1}
>
<Spinner color={themeV2.text.default}>Restarting service...</Spinner>
<text fg={themeV2.text.subdued}>Your session will resume automatically.</text>
<box width={62} maxWidth="90%" flexDirection="column" alignItems="center" gap={1}>
<Spinner color={themeV2.text.subdued}>Waiting for background service...</Spinner>
</box>
</box>
)
+45 -64
View File
@@ -49,67 +49,6 @@ export const { use: useClient, provider: ClientProvider } = createSimpleContext(
if (history.length > connectionHistoryLimit) history.shift()
}
async function connect(signal: AbortSignal, attempt: number) {
let connectedAt: number | undefined
// Bound the initial handshake and tie this request to the stream lifetime.
const request = new AbortController()
const cancel = () => request.abort(signal.reason)
const timeout = setTimeout(() => request.abort(new Error("Timed out connecting to server")), connectTimeout)
signal.addEventListener("abort", cancel, { once: true })
try {
// Open the event stream and validate its initial handshake.
record(attempt === 0 ? "connecting" : "reconnecting", attempt)
log.info("event stream connecting", { attempt })
const iterator = api.event.subscribe({ signal: request.signal })[Symbol.asyncIterator]()
const first = await iterator.next()
if (signal.aborted) return { error: undefined, connectedAt }
if (first.done) {
const error =
request.signal.reason instanceof Error ? request.signal.reason : new Error("Event stream disconnected")
return { error, connectedAt }
}
if (first.value.type !== "server.connected")
return { error: new Error("Event stream did not start with server.connected"), connectedAt }
// Publish the connected state before forwarding live events.
clearTimeout(timeout)
record("connected", attempt)
connectedAt = Date.now()
log.info("event stream connected")
events.emit(first.value.type, first.value)
setConnection({ status: "connected", attempt: 0, error: undefined })
// Forward events until the stream closes or this connection is cancelled.
while (!signal.aborted) {
const event = await iterator.next()
if (signal.aborted) return { error: undefined, connectedAt }
if (event.done) return { error: new Error("Event stream disconnected"), connectedAt }
if ("durable" in event.value)
log.debug("event", {
type: event.value.type,
aggregateID: event.value.durable.aggregateID,
seq: event.value.durable.seq,
})
events.emit(event.value.type, event.value)
}
return { error: undefined, connectedAt }
} catch (error) {
return { error, connectedAt }
} finally {
request.abort()
clearTimeout(timeout)
signal.removeEventListener("abort", cancel)
}
}
function start() {
stream?.abort()
const controller = new AbortController()
@@ -117,11 +56,53 @@ export const { use: useClient, provider: ClientProvider } = createSimpleContext(
void (async () => {
let attempt = 0
while (!abort.signal.aborted && !controller.signal.aborted) {
const result = await connect(controller.signal, attempt)
let connectedAt: number | undefined
const request = new AbortController()
const cancel = () => request.abort(controller.signal.reason)
const timeout = setTimeout(() => request.abort(new Error("Timed out connecting to server")), connectTimeout)
controller.signal.addEventListener("abort", cancel, { once: true })
const error = await (async () => {
record(attempt === 0 ? "connecting" : "reconnecting", attempt)
log.info("event stream connecting", { attempt })
const iterator = api.event.subscribe({ signal: request.signal })[Symbol.asyncIterator]()
const first = await iterator.next()
if (abort.signal.aborted || controller.signal.aborted) return undefined
if (first.done)
return request.signal.reason instanceof Error
? request.signal.reason
: new Error("Event stream disconnected")
if (first.value.type !== "server.connected")
return new Error("Event stream did not start with server.connected")
clearTimeout(timeout)
record("connected", attempt)
connectedAt = Date.now()
log.info("event stream connected")
events.emit(first.value.type, first.value)
setConnection({ status: "connected", attempt: 0, error: undefined })
while (!abort.signal.aborted && !controller.signal.aborted) {
const event = await iterator.next()
if (abort.signal.aborted || controller.signal.aborted) return undefined
if (event.done) return new Error("Event stream disconnected")
if ("durable" in event.value)
log.debug("event", {
type: event.value.type,
aggregateID: event.value.durable.aggregateID,
seq: event.value.durable.seq,
})
events.emit(event.value.type, event.value)
}
return undefined
})()
.catch((error) => error)
.finally(() => {
request.abort()
clearTimeout(timeout)
controller.signal.removeEventListener("abort", cancel)
})
if (abort.signal.aborted || controller.signal.aborted) return
if (result.connectedAt !== undefined && Date.now() - result.connectedAt >= 1_000) attempt = 0
if (connectedAt !== undefined && Date.now() - connectedAt >= 1_000) attempt = 0
attempt += 1
const message = errorMessage(result.error)
const message = errorMessage(error)
record("disconnected", attempt, message)
log.info("event stream disconnected", {
attempt,
@@ -1,634 +0,0 @@
/** @jsxImportSource @opentui/solid */
import { afterAll, describe, expect, test } from "bun:test"
import type { OpenCodeClient, OpenCodeEvent } from "@opencode-ai/client"
import { testRender } from "@opentui/solid"
import { onMount } from "solid-js"
import type { LogLevel, LogSink } from "../../../src/context/log"
import { createApi, createFetch } from "../../fixture/tui-client"
const packageRoot = process.env.OPENCODE_TUI_ROOT
const contextModule = packageRoot
? await import(`${packageRoot}/src/context/client.tsx`)
: await import("../../../src/context/client")
const environmentModule = packageRoot
? await import(`${packageRoot}/test/fixture/tui-environment.tsx`)
: await import("../../fixture/tui-environment")
const { ClientProvider, useClient } = contextModule as typeof import("../../../src/context/client")
const { TestTuiContexts } = environmentModule as typeof import("../../fixture/tui-environment")
type Client = ReturnType<typeof useClient>
type Service = {
reconnect: (signal: AbortSignal) => Promise<{ api: OpenCodeClient }>
restart: () => Promise<void>
}
type Observation = {
scenario: string
value: unknown
}
const observations: Observation[] = []
const connected = { id: "evt_connected", type: "server.connected", data: {} } as OpenCodeEvent
afterAll(async () => {
const output = process.env.CLIENT_BEHAVIOR_OUTPUT
if (output) await Bun.write(output, `${JSON.stringify(observations, null, 2)}\n`)
})
function observe(scenario: string, value: unknown) {
observations.push({ scenario, value })
}
function normalizeError(error: unknown) {
if (error instanceof Error) return `${error.name}:${error.message}`
return String(error)
}
function history(client: Client) {
return client.connection.internal.history().map((event) => ({
status: event.data.status,
attempt: event.data.attempt,
error: event.data.error,
}))
}
async function waitFor(check: () => boolean, timeout = 3_000) {
const started = Date.now()
while (!check()) {
if (Date.now() - started > timeout) throw new Error("timed out waiting for condition")
await Bun.sleep(5)
}
}
function event(type: "vcs" | "update" | "rename", suffix: string): OpenCodeEvent {
if (type === "vcs") {
return {
id: `evt_vcs_${suffix}`,
created: 1,
type: "vcs.branch.updated",
location: { directory: "/tmp/project" },
data: { branch: suffix },
}
}
if (type === "update") {
return {
id: `evt_update_${suffix}`,
created: 2,
type: "installation.update-available",
data: { version: suffix },
}
}
return {
id: `evt_rename_${suffix}`,
created: 3,
type: "session.renamed",
durable: { aggregateID: "ses_test", seq: 1, version: 1 },
location: { directory: "/tmp/project" },
data: { sessionID: "ses_test", title: suffix },
}
}
function createStream(options?: { first?: OpenCodeEvent; closeBeforeHandshake?: boolean }) {
const encoder = new TextEncoder()
const controllers = new Set<ReadableStreamDefaultController<Uint8Array>>()
const requests: Request[] = []
const aborts: string[] = []
let cancellations = 0
function response(request: Request) {
requests.push(request)
request.signal.addEventListener("abort", () => aborts.push(normalizeError(request.signal.reason)), { once: true })
let current: ReadableStreamDefaultController<Uint8Array> | undefined
return new Response(
new ReadableStream<Uint8Array>({
start(controller) {
current = controller
controllers.add(controller)
if (options?.closeBeforeHandshake) {
controllers.delete(controller)
controller.close()
return
}
controller.enqueue(encoder.encode(`data: ${JSON.stringify(options?.first ?? connected)}\n\n`))
},
cancel() {
cancellations += 1
if (current) controllers.delete(current)
},
}),
{ headers: { "content-type": "text/event-stream" } },
)
}
return {
response,
emit(value: OpenCodeEvent) {
const chunk = encoder.encode(`data: ${JSON.stringify(value)}\n\n`)
for (const controller of controllers) controller.enqueue(chunk)
},
raw(value: string) {
const chunk = encoder.encode(value)
for (const controller of controllers) controller.enqueue(chunk)
},
close() {
for (const controller of [...controllers]) {
controllers.delete(controller)
controller.close()
}
},
fail(message: string) {
for (const controller of [...controllers]) {
controllers.delete(controller)
controller.error(new Error(message))
}
},
snapshot() {
return {
requests: requests.length,
requestAborted: requests.map((request) => request.signal.aborted),
aborts,
cancellations,
active: controllers.size,
}
},
}
}
function apiFor(stream: ReturnType<typeof createStream>) {
return createApi(
createFetch((url, request) => {
if (url.pathname === "/api/event") return stream.response(request)
}).fetch,
)
}
async function mount(input: {
api: OpenCodeClient
service?: Service
throwOn?: OpenCodeEvent["type"]
}) {
const seen: Array<{ type: string; status: string }> = []
const typed: string[] = []
const logs: Array<{ level: LogLevel; message: string; tags: Record<string, unknown> }> = []
let initialStatus = ""
let client!: Client
let ready!: () => void
const mounted = new Promise<void>((resolve) => {
ready = resolve
})
const log: LogSink = (level, message, tags) => {
logs.push({ level, message, tags: { ...tags } })
}
const app = await testRender(() => (
<TestTuiContexts log={log}>
<ClientProvider api={input.api} service={input.service}>
<Probe
onReady={(value) => {
client = value
initialStatus = value.connection.status()
ready()
}}
onEvent={(value) => {
seen.push({ type: value.type, status: client.connection.status() })
if (value.type === input.throwOn) throw new Error(`listener failed for ${value.type}`)
}}
onBranch={(branch) => typed.push(branch)}
/>
</ClientProvider>
</TestTuiContexts>
))
await mounted
return { app, client, initialStatus, seen, typed, logs }
}
function Probe(props: {
onReady: (client: Client) => void
onEvent: (event: OpenCodeEvent) => void
onBranch: (branch: string) => void
}) {
const client = useClient()
onMount(() => {
client.event.listen(({ details }) => props.onEvent(details))
client.event.on("vcs.branch.updated", (value) => props.onBranch(value.data.branch ?? ""))
props.onReady(client)
})
return <box />
}
describe("ClientProvider connection characterization", () => {
test("records handshake ordering, event delivery, logging, and active-stream cleanup", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "connected")
stream.emit(event("vcs", "main"))
stream.emit(event("rename", "renamed"))
stream.emit(event("update", "2.0.0"))
await waitFor(() => setup.seen.length === 4)
observe("healthy.connected", {
initialStatus: setup.initialStatus,
finalStatus: setup.client.connection.status(),
seen: setup.seen,
typed: setup.typed,
logs: setup.logs,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
await waitFor(() => stream.snapshot().requestAborted[0] === true)
await Bun.sleep(20)
observe("healthy.cleanup", {
history: history(setup.client),
stream: stream.snapshot(),
})
expect(setup.seen.map((item) => item.type)).toEqual([
"server.connected",
"vcs.branch.updated",
"session.renamed",
"installation.update-available",
])
expect(setup.seen.map((item) => item.status)).toEqual(["connecting", "connected", "connected", "connected"])
expect(setup.logs.filter((item) => item.message === "event")).toHaveLength(1)
})
test("records an invalid first event", async () => {
const stream = createStream({ first: event("vcs", "invalid-handshake") })
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("handshake.invalid", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("Event stream did not start with server.connected")
})
test("records EOF before the handshake", async () => {
const stream = createStream({ closeBeforeHandshake: true })
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("handshake.eof", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("Event stream disconnected")
})
test("records a fetch failure before the handshake", async () => {
const calls = createFetch((url) => {
if (url.pathname === "/api/event") throw new Error("network unavailable")
return undefined
})
const setup = await mount({ api: createApi(calls.fetch) })
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("handshake.fetch-error", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
history: history(setup.client),
logs: setup.logs,
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("Transport")
})
test("records the initial connection timeout and request cancellation", async () => {
const requests: Request[] = []
const calls = createFetch((url, request) => {
if (url.pathname !== "/api/event") return
requests.push(request)
return new Promise<Response>((_, reject) => {
request.signal.addEventListener("abort", () => reject(request.signal.reason), { once: true })
})
})
const setup = await mount({ api: createApi(calls.fetch) })
await waitFor(() => setup.client.connection.status() === "reconnecting", 3_000)
observe("handshake.timeout", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
requestCount: requests.length,
requestAborted: requests.map((request) => request.signal.aborted),
abortReasons: requests.map((request) => normalizeError(request.signal.reason)),
history: history(setup.client),
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("Transport")
})
test("records static transport reconnection after a connected stream closes", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "connected")
stream.close()
await waitFor(() => stream.snapshot().requests === 2, 2_000)
await waitFor(() => setup.client.connection.status() === "connected")
observe("reconnect.static", {
status: setup.client.connection.status(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
logs: setup.logs.filter((item) => item.message !== "event"),
})
setup.app.renderer.destroy()
expect(setup.seen.map((item) => item.type)).toEqual(["server.connected", "server.connected"])
})
test("records immediate managed-service replacement", async () => {
const initial = createStream()
const replacement = createStream()
const replacementApi = apiFor(replacement)
const reconnectSignals: boolean[] = []
const service: Service = {
reconnect(signal) {
reconnectSignals.push(signal.aborted)
return Promise.resolve({ api: replacementApi })
},
restart: () => Promise.resolve(),
}
const setup = await mount({ api: apiFor(initial), service })
await waitFor(() => setup.client.connection.status() === "connected")
initial.close()
await waitFor(() => replacement.snapshot().requests === 1)
await waitFor(() => setup.client.connection.status() === "connected")
replacement.emit(event("vcs", "replacement"))
await waitFor(() => setup.typed.includes("replacement"))
observe("reconnect.managed-replacement", {
status: setup.client.connection.status(),
apiReplaced: setup.client.api === replacementApi,
reconnectSignals,
seen: setup.seen,
typed: setup.typed,
history: history(setup.client),
initial: initial.snapshot(),
replacement: replacement.snapshot(),
})
setup.app.renderer.destroy()
expect(setup.client.api).toBe(replacementApi)
})
test("records managed-service resolution failure and delayed retry", async () => {
const stream = createStream()
let reconnects = 0
const service: Service = {
reconnect() {
reconnects += 1
return Promise.reject(new Error("service unavailable"))
},
restart: () => Promise.resolve(),
}
const setup = await mount({ api: apiFor(stream), service })
await waitFor(() => setup.client.connection.status() === "connected")
stream.close()
await waitFor(() => stream.snapshot().requests === 2, 2_000)
await waitFor(() => setup.client.connection.status() === "connected")
observe("reconnect.managed-failure", {
reconnects,
status: setup.client.connection.status(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
resolutionLogs: setup.logs.filter((item) => item.message === "server resolution failed"),
})
setup.app.renderer.destroy()
expect(reconnects).toBe(1)
})
test("records cleanup while the initial fetch is pending", async () => {
const requests: Request[] = []
const aborts: string[] = []
const calls = createFetch((url, request) => {
if (url.pathname !== "/api/event") return
requests.push(request)
return new Promise<Response>((_, reject) => {
request.signal.addEventListener(
"abort",
() => {
aborts.push(normalizeError(request.signal.reason))
reject(request.signal.reason)
},
{ once: true },
)
})
})
const setup = await mount({ api: createApi(calls.fetch) })
await waitFor(() => requests.length === 1)
setup.app.renderer.destroy()
await waitFor(() => requests[0].signal.aborted)
await Bun.sleep(20)
observe("cleanup.pending-handshake", {
status: setup.client.connection.status(),
requestAborted: requests[0].signal.aborted,
aborts,
history: history(setup.client),
logs: setup.logs,
})
expect(history(setup.client).map((item) => item.status)).toEqual(["connecting"])
})
test("records an event listener failure as a connection failure", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream), throwOn: "vcs.branch.updated" })
await waitFor(() => setup.client.connection.status() === "connected")
stream.emit(event("vcs", "throws"))
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("listener.failure", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
typed: setup.typed,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("listener failed for vcs.branch.updated")
})
test("records stream reader failure after connection", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "connected")
stream.fail("reader exploded")
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("stream.reader-failure", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("Transport")
})
test("records malformed SSE data after connection", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "connected")
stream.raw("data: not-json\n\n")
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("stream.malformed-data", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
expect(setup.client.connection.error()).toBe("MalformedResponse")
})
test("records a server.connected listener failure before connected state publication", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream), throwOn: "server.connected" })
await waitFor(() => setup.client.connection.status() === "reconnecting")
observe("listener.connected-failure", {
status: setup.client.connection.status(),
error: setup.client.connection.error(),
seen: setup.seen,
history: history(setup.client),
stream: stream.snapshot(),
})
setup.app.renderer.destroy()
expect(history(setup.client).map((item) => item.status)).toEqual(["connecting", "connected", "disconnected"])
})
test("records cleanup during static reconnect backoff", async () => {
const stream = createStream()
const setup = await mount({ api: apiFor(stream) })
await waitFor(() => setup.client.connection.status() === "connected")
stream.close()
await waitFor(() => setup.client.connection.status() === "reconnecting")
setup.app.renderer.destroy()
await Bun.sleep(1_050)
observe("cleanup.reconnect-backoff", {
status: setup.client.connection.status(),
history: history(setup.client),
stream: stream.snapshot(),
})
expect(stream.snapshot().requests).toBe(1)
})
test("records cleanup during managed-service resolution", async () => {
const stream = createStream()
let resolutionStarted = false
let resolutionAborted = false
const service: Service = {
reconnect(signal) {
resolutionStarted = true
return new Promise((_, reject) => {
signal.addEventListener(
"abort",
() => {
resolutionAborted = true
reject(signal.reason)
},
{ once: true },
)
})
},
restart: () => Promise.resolve(),
}
const setup = await mount({ api: apiFor(stream), service })
await waitFor(() => setup.client.connection.status() === "connected")
stream.close()
await waitFor(() => resolutionStarted)
setup.app.renderer.destroy()
await waitFor(() => resolutionAborted)
await Bun.sleep(20)
observe("cleanup.service-resolution", {
resolutionStarted,
resolutionAborted,
status: setup.client.connection.status(),
history: history(setup.client),
stream: stream.snapshot(),
logs: setup.logs,
})
expect(resolutionAborted).toBe(true)
})
test("records attempt reset after a stable connection", async () => {
const streams = [createStream(), createStream(), createStream()]
const apis = streams.map(apiFor)
let reconnects = 0
const service: Service = {
reconnect() {
const api = apis[Math.min(reconnects + 1, apis.length - 1)]
reconnects += 1
return Promise.resolve({ api })
},
restart: () => Promise.resolve(),
}
const setup = await mount({ api: apis[0], service })
await waitFor(() => setup.client.connection.status() === "connected")
streams[0].close()
await waitFor(() => streams[1].snapshot().requests === 1)
streams[1].close()
await waitFor(() => streams[2].snapshot().requests === 1)
await Bun.sleep(1_050)
streams[2].close()
await waitFor(() => reconnects === 3)
observe("reconnect.stable-reset", {
reconnects,
status: setup.client.connection.status(),
history: history(setup.client),
streams: streams.map((stream) => stream.snapshot()),
})
setup.app.renderer.destroy()
expect(history(setup.client).filter((item) => item.status === "disconnected").map((item) => item.attempt)).toEqual([
1, 2, 1,
])
})
})