ceos/opencode
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

refactor(llm): remove the provider-error stream event

Browse source 
Delete the provider-error LLMEvent so streams carry output only and
every provider-reported failure exits through the typed error channel.
Anthropic SSE error events, OpenAI Responses response.failed/error
events, and Bedrock exception frames now fail the stream with an
LLMError from the shared classifier (carrying the provider code, e.g.
rate_limit_exceeded -> LLM.RateLimit).

Core follows: the publisher drops its provider-error case, the runner
drops held-back overflow events (overflow recovery keys off a thrown
LLM.ContextOverflow), compaction and title stop scanning events for
failures, and isContextOverflowFailure is deleted with its last
consumer. V1 packages/opencode gets minimal compile fixes only (dead
switch case, one test stream).
This commit is contained in:
Aiden Cline 2026-07-13 10:49:43 -05:00
commit 5d87c7ad1f
18 changed files with 167 additions and 240 deletions
Download patch file Download diff file Expand all files Collapse all files

5
packages/core/src/session/compaction.ts
View file

@ -247,11 +247,6 @@ const make = (dependencies: Dependencies) => {
)
.pipe(
Stream.runForEach((event) => {
if (LLMEvent.is.providerError(event))
failure = {
type: event.classification === "context-overflow" ? "provider.invalid-request" : "provider.error",
message: event.message,
}
if (LLMEvent.is.textDelta(event)) {
chunks.push(event.text)
return dependencies.events.publish(SessionEvent.Compaction.Delta, {

34
packages/core/src/session/runner/llm.ts
View file

@ -1,15 +1,6 @@
export * as SessionRunnerLLM from "./llm"
import {
LLM,
LLMClient,
LLMEvent,
Message,
SystemPart,
isContextOverflowFailure,
isLLMError,
type ProviderErrorEvent,
} from "@opencode-ai/llm"
import { LLM, LLMClient, LLMEvent, Message, SystemPart, isLLMError, type LLMError } from "@opencode-ai/llm"
import { SessionError } from "@opencode-ai/schema/session-error"
import { Money } from "@opencode-ai/schema/money"
import { Cause, Effect, Exit, Fiber, FiberSet, Layer, Option, Semaphore, Stream } from "effect"
@ -227,17 +218,10 @@ const layer = Layer.effect(
// mid-event.
const serialized = <A, E, R>(effect: Effect.Effect<A, E, R>) => publication.withPermit(effect)
const publish = (event: LLMEvent, error?: SessionError.Error) => serialized(publisher.publish(event, error))
let overflowFailure: ProviderErrorEvent | undefined
const providerStream = llm.stream(request).pipe(
Stream.runForEach((event) =>
Effect.gen(function* () {
if (overflowFailure || publisher.hasProviderError()) return
if (LLMEvent.is.providerError(event)) {
if (isContextOverflowFailure(event) && !publisher.hasRetryEvidence()) {
overflowFailure = event
return
}
}
if (publisher.hasProviderError()) return
yield* publish(event)
if (event.type !== "tool-call" || event.providerExecuted) return
if (!toolMaterialization) {
@ -317,22 +301,21 @@ const layer = Layer.effect(
// away non-interrupt failures, so both interrupt checks stay Cause-based.
const streamInterrupted = stream._tag === "Failure" && Cause.hasInterrupts(stream.cause)
const llmFailure = streamFailure !== undefined && isLLMError(streamFailure) ? streamFailure : undefined
// A context overflow before any assistant output is recoverable: compact and
// restart the step instead of surfacing the provider error.
if (
recoverOverflow &&
!publisher.hasRetryEvidence() &&
isContextOverflowFailure(overflowFailure ?? streamFailure) &&
llmFailure?._tag === "LLM.ContextOverflow" &&
(yield* restore(recoverOverflow({ sessionID: session.id, messages: context, model }))).status ===
"completed"
)
return { _tag: "RestartAfterOverflowCompaction", step: currentStep } as const
// An unrecovered held-back overflow becomes the step's durable provider error. A
// thrown LLM failure records the assistant failure unless a provider error was
// already recorded from the stream. Terminal publication waits for owned tools.
if (overflowFailure) yield* publish(overflowFailure)
const llmFailure = streamFailure !== undefined && isLLMError(streamFailure) ? streamFailure : undefined
// A thrown LLM failure records the assistant failure unless a provider failure
// was already recorded from the stream. Terminal publication waits for owned tools.
if (llmFailure && !publisher.hasProviderError()) {
const error = toSessionError(llmFailure)
if (
@ -349,7 +332,8 @@ const layer = Layer.effect(
}
yield* serialized(publisher.failAssistant(error))
}
// Provider error events only arrive from the stream, so the flag is final here.
// The provider-failed flag is only set while consuming the stream (content-filter
// step finish), so it is final here.
const providerFailed = publisher.hasProviderError()
// Settle every owned tool fiber. FiberSet.join returns on the first failure, so retain

4
packages/core/src/session/runner/publish-llm-event.ts
View file

@ -438,10 +438,6 @@ export const createLLMEventPublisher = (events: Pick<EventV2.Interface, "publish
return
case "finish":
return
case "provider-error":
providerFailed = true
yield* failAssistant({ type: "provider.unknown", message: event.message }, true)
return
}
})

4
packages/core/src/session/title.ts
View file

@ -49,7 +49,6 @@ const make = (dependencies: Dependencies) => {
).pipe(Effect.catch(() => Effect.succeed(undefined)))
if (!resolved) return
const chunks: string[] = []
let failed = false
const streamed = yield* dependencies.llm
.stream(
LLM.request({
@ -61,14 +60,13 @@ const make = (dependencies: Dependencies) => {
)
.pipe(
Stream.runForEach((event) => {
if (LLMEvent.is.providerError(event)) failed = true
if (LLMEvent.is.textDelta(event)) chunks.push(event.text)
return Effect.void
}),
Effect.as(true),
Effect.catchIf(isLLMError, () => Effect.succeed(false)),
)
if (!streamed || failed) return
if (!streamed) return
const title = chunks
.join("")
.split("\n")

104
packages/core/test/session-runner.test.ts
View file

@ -1,5 +1,6 @@
import { describe, expect, test } from "bun:test"
import {
APIError,
BadRequest,
ConnectionError,
ContextOverflow,
@ -70,8 +71,9 @@ import { asc, eq } from "drizzle-orm"
import { testEffect } from "./lib/effect"
const requests: LLMRequest[] = []
type ScriptedResponse = LLMEvent[] | Stream.Stream<LLMEvent, LLMError>
let response: LLMEvent[] = []
let responses: LLMEvent[][] | undefined
let responses: ScriptedResponse[] | undefined
let responseStream: Stream.Stream<LLMEvent, LLMError> | undefined
let responseStreams: Stream.Stream<LLMEvent, LLMError>[] | undefined
let streamGate: Deferred.Deferred<void> | undefined
@ -94,9 +96,12 @@ const client = Layer.succeed(
responseStream = undefined
return stream
}
const scripted = responses === undefined ? response : (responses.shift() ?? [])
const events = streamFailure
? Stream.fail(streamFailure)
: Stream.fromIterable(responses === undefined ? response : (responses.shift() ?? []))
: Array.isArray(scripted)
? Stream.fromIterable(scripted)
: scripted
if (!streamGate) return events
return Stream.unwrap(
(streamStarted ? Deferred.succeed(streamStarted, undefined) : Effect.void).pipe(
@ -486,6 +491,11 @@ const setup = Effect.gen(function* () {
const providerUnavailable = () => new ConnectionError({ message: "Provider unavailable" })
const contextOverflow = () => new ContextOverflow({ message: "prompt too long" })
const failingResponse = (events: LLMEvent[], failure: LLMError): Stream.Stream<LLMEvent, LLMError> =>
Stream.fromIterable(events).pipe(Stream.concat(Stream.fail(failure)))
const invalidRequest = () => new BadRequest({ message: "Invalid request" })
const rateLimited = (retryAfterMs?: number) => new RateLimit({ message: "Rate limited", retryAfterMs })
@ -1744,14 +1754,14 @@ describe("SessionRunnerLLM", () => {
yield* admit(session, "Earlier question")
yield* session.resume(sessionID)
response = [LLMEvent.providerError({ message: "summary unavailable" })]
responseStream = Stream.fail(new APIError({ message: "summary unavailable" }))
const compaction = yield* session.compact({ sessionID })
yield* session.resume(sessionID)
expect((yield* session.messages({ sessionID })).find((message) => message.id === compaction.id)).toMatchObject({
type: "compaction",
status: "failed",
error: { type: "provider.error", message: "summary unavailable" },
error: { type: "provider.unknown", message: "summary unavailable" },
})
}),
)
@ -1861,7 +1871,7 @@ describe("SessionRunnerLLM", () => {
currentModel = compactModel
requests.length = 0
responses = [
[LLMEvent.providerError({ message: "Unsupported parameter: max_output_tokens" })],
Stream.fail(new BadRequest({ message: "Unsupported parameter: max_output_tokens" })),
reply.text("Must not run", "text-after-failed-compaction"),
]
yield* admit(session, "Recent exact request ".repeat(180))
@ -1884,10 +1894,7 @@ describe("SessionRunnerLLM", () => {
Effect.gen(function* () {
const session = yield* setupOverflowRecovery
responses = [
[
LLMEvent.stepStart({ index: 0 }),
LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" }),
],
failingResponse([LLMEvent.stepStart({ index: 0 })], contextOverflow()),
reply.text("## Objective\n- Recover overflow", "text-summary"),
reply.text("Recovered", "text-final"),
]
@ -1914,7 +1921,7 @@ describe("SessionRunnerLLM", () => {
const session = yield* setupOverflowRecovery
currentModel = model
responses = [
[LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" })],
Stream.fail(contextOverflow()),
reply.text("## Objective\n- Recover unknown limit", "text-summary-unknown-limit"),
reply.text("Recovered", "text-final-unknown-limit"),
]
@ -1934,7 +1941,7 @@ describe("SessionRunnerLLM", () => {
const session = yield* setupOverflowRecovery
currentModel = undersizedContextModel
responses = [
[LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" })],
Stream.fail(contextOverflow()),
reply.text("## Objective\n- Recover undersized limit", "text-summary-undersized-limit"),
reply.text("Recovered", "text-final-undersized-limit"),
]
@ -1952,10 +1959,7 @@ describe("SessionRunnerLLM", () => {
it.effect("persists a second context overflow after one recovery", () =>
Effect.gen(function* () {
const session = yield* setupOverflowRecovery
const overflow = () => [
LLMEvent.stepStart({ index: 0 }),
LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" }),
]
const overflow = () => failingResponse([LLMEvent.stepStart({ index: 0 })], contextOverflow())
responses = [overflow(), reply.text("## Objective\n- Recover once", "text-summary"), overflow()]
yield* admit(session, "Continue")
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("prompt too long")
@ -1971,7 +1975,7 @@ describe("SessionRunnerLLM", () => {
it.effect("recovers once from a raw context overflow failure", () =>
Effect.gen(function* () {
const session = yield* setupOverflowRecovery
responseStream = Stream.fail(new ContextOverflow({ message: "prompt too long" }))
responseStream = Stream.fail(contextOverflow())
responses = [
reply.text("## Objective\n- Recover raw overflow", "text-summary"),
reply.text("Recovered", "text-final"),
@ -1990,10 +1994,7 @@ describe("SessionRunnerLLM", () => {
it.effect("publishes the original overflow when recovery summarization fails", () =>
Effect.gen(function* () {
const session = yield* setupOverflowRecovery
responses = [
[LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" })],
[LLMEvent.providerError({ message: "summary unavailable" })],
]
responses = [Stream.fail(contextOverflow()), Stream.fail(new APIError({ message: "summary unavailable" }))]
yield* admit(session, "Continue")
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("prompt too long")
@ -2004,7 +2005,7 @@ describe("SessionRunnerLLM", () => {
type: "compaction",
status: "failed",
reason: "auto",
error: { type: "provider.error", message: "summary unavailable" },
error: { type: "provider.unknown", message: "summary unavailable" },
}),
)
expect(context.slice(-3)).toMatchObject([
@ -2018,10 +2019,7 @@ describe("SessionRunnerLLM", () => {
it.effect("interrupts overflow recovery while the summary provider is running", () =>
Effect.gen(function* () {
const session = yield* setupOverflowRecovery
responses = [
[LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" })],
reply.text("## Objective\n- Interrupted", "text-summary"),
]
responses = [Stream.fail(contextOverflow()), reply.text("## Objective\n- Interrupted", "text-summary")]
const firstGate = yield* Deferred.make<void>()
const summaryGate = yield* Deferred.make<void>()
streamGate = firstGate
@ -3604,7 +3602,10 @@ describe("SessionRunnerLLM", () => {
const session = yield* setup
yield* admit(session, "Fail durably")
response = [LLMEvent.stepStart({ index: 0 }), LLMEvent.providerError({ message: "Provider unavailable" })]
responseStream = failingResponse(
[LLMEvent.stepStart({ index: 0 })],
new APIError({ message: "Provider unavailable" }),
)
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("Provider unavailable")
@ -3621,7 +3622,7 @@ describe("SessionRunnerLLM", () => {
const session = yield* setup
yield* admit(session, "Fail before step")
response = [LLMEvent.providerError({ message: "Provider unavailable" })]
responseStream = Stream.fail(new APIError({ message: "Provider unavailable" }))
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("Provider unavailable")
@ -3709,13 +3710,15 @@ describe("SessionRunnerLLM", () => {
const session = yield* setup
yield* admit(session, "Fail after output")
response = [
LLMEvent.stepStart({ index: 0 }),
LLMEvent.textStart({ id: "text-partial" }),
LLMEvent.textDelta({ id: "text-partial", text: "Partial" }),
LLMEvent.textEnd({ id: "text-partial" }),
LLMEvent.providerError({ message: "prompt too long", classification: "context-overflow" }),
]
responseStream = failingResponse(
[
LLMEvent.stepStart({ index: 0 }),
LLMEvent.textStart({ id: "text-partial" }),
LLMEvent.textDelta({ id: "text-partial", text: "Partial" }),
LLMEvent.textEnd({ id: "text-partial" }),
],
contextOverflow(),
)
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("prompt too long")
expect(requests).toHaveLength(1)
@ -3908,11 +3911,13 @@ describe("SessionRunnerLLM", () => {
toolExecutionGate = yield* Deferred.make<void>()
toolExecutionsStarted = yield* Deferred.make<void>()
toolExecutionsReady = 1
response = [
LLMEvent.stepStart({ index: 0 }),
LLMEvent.toolCall({ id: "call-before-provider-error", name: "echo", input: { text: "settled" } }),
LLMEvent.providerError({ message: "Provider unavailable" }),
]
responseStream = failingResponse(
[
LLMEvent.stepStart({ index: 0 }),
LLMEvent.toolCall({ id: "call-before-provider-error", name: "echo", input: { text: "settled" } }),
],
new APIError({ message: "Provider unavailable" }),
)
const run = yield* session.resume(sessionID).pipe(Effect.forkChild)
yield* Deferred.await(toolExecutionsStarted)
@ -3939,11 +3944,10 @@ describe("SessionRunnerLLM", () => {
const session = yield* setup
yield* admit(session, "Fail hosted tool durably")
response = [
LLMEvent.stepStart({ index: 0 }),
hostedCall("call-hosted-provider-error", "effect"),
LLMEvent.providerError({ message: "Provider unavailable" }),
]
responseStream = failingResponse(
[LLMEvent.stepStart({ index: 0 }), hostedCall("call-hosted-provider-error", "effect")],
new APIError({ message: "Provider unavailable" }),
)
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("Provider unavailable")
@ -3970,11 +3974,13 @@ describe("SessionRunnerLLM", () => {
Effect.gen(function* () {
const session = yield* setup
yield* admit(session, "Defect while provider fails")
response = [
LLMEvent.stepStart({ index: 0 }),
LLMEvent.toolCall({ id: "call-defect-provider-error", name: "defect", input: {} }),
LLMEvent.providerError({ message: "Provider unavailable" }),
]
responseStream = failingResponse(
[
LLMEvent.stepStart({ index: 0 }),
LLMEvent.toolCall({ id: "call-defect-provider-error", name: "defect", input: {} }),
],
new APIError({ message: "Provider unavailable" }),
)
expect((yield* session.resume(sessionID).pipe(Effect.flip)).message).toBe("Provider unavailable")

2
packages/llm/AGENTS.md
View file

@ -291,7 +291,7 @@ Use this order for every protocol module:
- Keep protocol files focused on the protocol. Move provider-specific projection, signing, media normalization, or other bulky transformations into `src/protocols/utils/*`.
- Use `Effect.fn("Provider.fromRequest")` for request body construction entrypoints. Use `Effect.fn(...)` for event handlers that yield effects; keep purely synchronous handlers as plain functions returning a `StepResult` that the dispatcher lifts via `Effect.succeed(...)`.
- Parser state owns terminal information. The state machine records finish reason, usage, and pending tool calls; emit one terminal `finish` event (or `provider-error`) for each completed response. If a provider splits reason and usage across events, merge them in parser state before flushing.
- Parser state owns terminal information. The state machine records finish reason, usage, and pending tool calls; emit one terminal `finish` event for each completed response. Provider-reported failures (SSE error events, exception frames) fail the stream with a typed `LLMError` via `classifyApiFailure` — never an ordinary event. If a provider splits reason and usage across events, merge them in parser state before flushing.
- Emit exactly one terminal `finish` event for a completed response, normally after a matching `step-finish`. Use `stream.terminal` to stop reading when the provider has a completion sentinel; use `stream.onHalt` when the final event must be flushed after the framed stream ends.
- Use shared helpers for repeated protocol policy such as text joining, usage totals, JSON parsing, and tool-call accumulation. `ToolStream` (`protocols/utils/tool-stream.ts`) accumulates streamed tool-call arguments uniformly.
- Make intentional provider differences explicit in helper names or comments. If two protocol files differ visually, the reason should be obvious from the names.

2
packages/llm/src/index.ts
View file

@ -2,7 +2,7 @@ export { LLMClient } from "./route/client"
export { Auth } from "./route/auth"
export { Provider } from "./provider"
export { ProviderPackage } from "./provider-package"
export { classifyApiFailure, isContextOverflow, isContextOverflowFailure, type ApiFailure } from "./provider-error"
export { classifyApiFailure, isContextOverflow, type ApiFailure } from "./provider-error"
export type {
RouteModelInput,
RouteRoutedModelInput,

18
packages/llm/src/protocols/anthropic-messages.ts
View file

@ -19,7 +19,7 @@ import {
type ToolResultPart,
} from "../schema"
import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared"
import { isContextOverflow } from "../provider-error"
import { classifyApiFailure } from "../provider-error"
import * as Cache from "./utils/cache"
import { Lifecycle } from "./utils/lifecycle"
import { ToolSchemaProjection } from "./utils/tool-schema"
@ -832,15 +832,11 @@ const providerErrorMessage = (event: AnthropicEvent): string => {
return message || type || "Anthropic Messages stream error"
}
const onError = (state: ParserState, event: AnthropicEvent): StepResult => [
state,
[
LLMEvent.providerError({
message: providerErrorMessage(event),
classification: isContextOverflow(event.error?.message ?? "") ? "context-overflow" : undefined,
}),
],
]
const onError = (event: AnthropicEvent) =>
classifyApiFailure({
message: providerErrorMessage(event),
code: event.error?.type,
})
const step = (state: ParserState, event: AnthropicEvent) => {
if (event.type === "message_start") return Effect.succeed(onMessageStart(state, event))
@ -848,7 +844,7 @@ const step = (state: ParserState, event: AnthropicEvent) => {
if (event.type === "content_block_delta") return onContentBlockDelta(state, event)
if (event.type === "content_block_stop") return onContentBlockStop(state, event)
if (event.type === "message_delta") return Effect.succeed(onMessageDelta(state, event))
if (event.type === "error") return Effect.succeed(onError(state, event))
if (event.type === "error") return Effect.fail(onError(event))
return Effect.succeed<StepResult>([state, NO_EVENTS])
}

35
packages/llm/src/protocols/bedrock-converse.ts
View file

@ -17,7 +17,7 @@ import {
type ToolResultPart,
} from "../schema"
import { BedrockEventStream } from "./bedrock-event-stream"
import { isContextOverflow } from "../provider-error"
import { classifyApiFailure } from "../provider-error"
import { JsonObject, optionalArray, ProviderShared } from "./shared"
import { BedrockAuth } from "./utils/bedrock-auth"
import { BedrockCache } from "./utils/bedrock-cache"
@ -586,27 +586,20 @@ const step = (state: ParserState, event: BedrockEvent) =>
return [{ ...state, pendingFinish: { reason: state.pendingFinish?.reason ?? "stop", usage } }, []] as const
}
if (event.internalServerException || event.modelStreamErrorException || event.serviceUnavailableException) {
const message =
event.internalServerException?.message ??
event.modelStreamErrorException?.message ??
event.serviceUnavailableException?.message ??
"Bedrock Converse stream error"
return [state, [LLMEvent.providerError({ message })]] as const
}
if (event.validationException || event.throttlingException) {
const message =
event.validationException?.message ?? event.throttlingException?.message ?? "Bedrock Converse error"
return [
state,
[
LLMEvent.providerError({
message,
classification: event.validationException && isContextOverflow(message) ? "context-overflow" : undefined,
}),
],
const exception = (
[
["internalServerException", event.internalServerException],
["modelStreamErrorException", event.modelStreamErrorException],
["serviceUnavailableException", event.serviceUnavailableException],
["throttlingException", event.throttlingException],
["validationException", event.validationException],
] as const
).find((entry) => entry[1] !== undefined)
if (exception) {
return yield* classifyApiFailure({
message: exception[1]?.message ?? "Bedrock Converse stream error",
code: exception[0],
})
}
return [state, []] as const

33
packages/llm/src/protocols/openai-responses.ts
View file

@ -19,7 +19,7 @@ import {
type ToolResultPart,
} from "../schema"
import { JsonObject, optionalArray, optionalNull, ProviderShared } from "./shared"
import { isContextOverflow } from "../provider-error"
import { classifyApiFailure } from "../provider-error"
import { OpenAIOptions } from "./utils/openai-options"
import { Lifecycle } from "./utils/lifecycle"
import { ToolSchemaProjection } from "./utils/tool-schema"
@ -606,9 +606,9 @@ type StepResult = readonly [ParserState, ReadonlyArray<LLMEvent>]
const NO_EVENTS: StepResult["1"] = []
// `response.completed` / `response.incomplete` are clean finishes that emit a
// `finish` event; `response.failed` is a hard failure that emits a
// `provider-error`. All three end the stream — kept in one set so `step` and
// the protocol's `terminal` predicate stay in sync.
// `finish` event; `response.failed` is a hard failure that fails the stream
// with a classified `LLMError`. All three end the stream — kept in one set so
// `step` and the protocol's `terminal` predicate stay in sync.
const TERMINAL_TYPES = new Set(["response.completed", "response.incomplete", "response.failed"])
const onOutputTextDelta = (state: ParserState, event: OpenAIResponsesEvent): StepResult => {
@ -907,24 +907,11 @@ const providerErrorMessage = (event: OpenAIResponsesEvent, fallback: string): st
return message || code || fallback
}
const providerError = (event: OpenAIResponsesEvent, fallback: string) => {
const code = event.code || event.error?.code || event.response?.error?.code || undefined
const message = providerErrorMessage(event, fallback)
return LLMEvent.providerError({
message,
classification: code === "context_length_exceeded" || isContextOverflow(message) ? "context-overflow" : undefined,
const providerError = (event: OpenAIResponsesEvent, fallback: string) =>
classifyApiFailure({
message: providerErrorMessage(event, fallback),
code: event.code || event.error?.code || event.response?.error?.code || undefined,
})
}
const onResponseFailed = (state: ParserState, event: OpenAIResponsesEvent): StepResult => [
state,
[providerError(event, "OpenAI Responses response failed")],
]
const onError = (state: ParserState, event: OpenAIResponsesEvent): StepResult => [
state,
[providerError(event, "OpenAI Responses stream error")],
]
const step = (state: ParserState, event: OpenAIResponsesEvent) => {
if (event.type === "response.output_text.delta") return Effect.succeed(onOutputTextDelta(state, event))
@ -950,8 +937,8 @@ const step = (state: ParserState, event: OpenAIResponsesEvent) => {
if (event.type === "response.output_item.done") return onOutputItemDone(state, event)
if (event.type === "response.completed" || event.type === "response.incomplete")
return Effect.succeed(onResponseFinish(state, event))
if (event.type === "response.failed") return Effect.succeed(onResponseFailed(state, event))
if (event.type === "error") return Effect.succeed(onError(state, event))
if (event.type === "response.failed") return Effect.fail(providerError(event, "OpenAI Responses response failed"))
if (event.type === "error") return Effect.fail(providerError(event, "OpenAI Responses stream error"))
return Effect.succeed<StepResult>([state, NO_EVENTS])
}

8
packages/llm/src/provider-error.ts
View file

@ -1,4 +1,3 @@
import { Schema } from "effect"
import {
APIError,
Authentication,
@ -9,12 +8,10 @@ import {
HttpRateLimitDetails,
NotFound,
PermissionDenied,
ProviderErrorEvent,
ProviderMetadata,
QuotaExceeded,
RateLimit,
ServerError,
isLLMError,
type LLMError,
} from "./schema"
@ -44,11 +41,6 @@ const patterns = [
export const isContextOverflow = (message: string) =>
patterns.some((pattern) => pattern.test(message)) || /^4(00|13)\s*(status code)?\s*\(no body\)/i.test(message)
export const isContextOverflowFailure = (failure: unknown) =>
isLLMError(failure)
? failure._tag === "LLM.ContextOverflow"
: Schema.is(ProviderErrorEvent)(failure) && failure.classification === "context-overflow"
const OVERFLOW_CODES = new Set(["context_length_exceeded", "model_context_window_exceeded"])
const QUOTA_CODES = new Set(["insufficient_quota", "usage_not_included", "billing_error"])
const QUOTA_TEXT = /insufficient[-_\s]?quota|quota[-_\s]?exceeded/i

3
packages/llm/src/schema/errors.ts
View file

@ -1,9 +1,6 @@
import { Schema } from "effect"
import { ModelID, ProviderID, ProviderMetadata, RouteID } from "./ids"
export const ProviderFailureClassification = Schema.Literal("context-overflow")
export type ProviderFailureClassification = typeof ProviderFailureClassification.Type
export class HttpRequestDetails extends Schema.Class<HttpRequestDetails>("LLM.HttpRequestDetails")({
method: Schema.String,
url: Schema.String,

21
packages/llm/src/schema/events.ts
View file

@ -2,7 +2,6 @@ import { Schema } from "effect"
import { ContentBlockID, FinishReason, ProtocolID, ProviderMetadata, RouteID, ToolCallID } from "./ids"
import { ModelSchema } from "./options"
import { Message, ToolCallPart, ToolOutput, ToolResultPart, ToolResultValue, type ContentPart } from "./messages"
import { ProviderFailureClassification } from "./errors"
/**
* Token usage reported by an LLM provider.
@ -197,14 +196,6 @@ export const Finish = Schema.Struct({
}).annotate({ identifier: "LLM.Event.Finish" })
export type Finish = Schema.Schema.Type<typeof Finish>
export const ProviderErrorEvent = Schema.Struct({
type: Schema.tag("provider-error"),
message: Schema.String,
classification: Schema.optional(ProviderFailureClassification),
providerMetadata: Schema.optional(ProviderMetadata),
}).annotate({ identifier: "LLM.Event.ProviderError" })
export type ProviderErrorEvent = Schema.Schema.Type<typeof ProviderErrorEvent>
const llmEventTagged = Schema.Union([
StepStart,
TextStart,
@ -221,7 +212,6 @@ const llmEventTagged = Schema.Union([
ToolError,
StepFinish,
Finish,
ProviderErrorEvent,
]).pipe(Schema.toTaggedUnion("type"))
type WithID<Event extends { readonly id: unknown }, ID> = Omit<Event, "type" | "id"> & { readonly id: ID | string }
@ -271,7 +261,6 @@ export const LLMEvent = Object.assign(llmEventTagged, {
...input,
usage: input.usage === undefined ? undefined : Usage.from(input.usage),
}),
providerError: ProviderErrorEvent.make,
is: {
stepStart: llmEventTagged.guards["step-start"],
textStart: llmEventTagged.guards["text-start"],
@ -288,7 +277,6 @@ export const LLMEvent = Object.assign(llmEventTagged, {
toolError: llmEventTagged.guards["tool-error"],
stepFinish: llmEventTagged.guards["step-finish"],
finish: llmEventTagged.guards.finish,
providerError: llmEventTagged.guards["provider-error"],
},
})
export type LLMEvent = Schema.Schema.Type<typeof llmEventTagged>
@ -374,13 +362,6 @@ const appendEvent = (state: ResponseState, event: LLMEvent): ResponseState => {
finishReason: event.reason,
}
}
if (LLMEvent.is.providerError(event)) {
return {
...state,
events,
finishReason: state.finishReason ?? "error",
}
}
return {
...state,
events,
@ -589,7 +570,7 @@ export namespace LLMResponse {
/** Purely fold one provider-neutral event into the attempt assembly state. */
export const reduce = reduceResponseState
/** Return a completed response only after a terminal finish or provider error. */
/** Return a completed response only after a terminal finish event. */
export const complete = (state: State): LLMResponse | undefined =>
state.finishReason === undefined
? undefined

32
packages/llm/test/provider/anthropic-messages.test.ts
View file

@ -484,23 +484,25 @@ describe("Anthropic Messages route", () => {
}),
)
it.effect("emits provider-error events for mid-stream provider errors", () =>
it.effect("fails the stream for mid-stream provider errors", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(sseEvents({ type: "error", error: { type: "overloaded_error", message: "Overloaded" } })),
),
Effect.flip,
)
// Prefix the error type so consumers can distinguish overloads, rate
// limits, and quota errors without parsing the message string.
expect(response.events).toEqual([{ type: "provider-error", message: "overloaded_error: Overloaded" }])
expect(isLLMError(error)).toBe(true)
expect(error).toMatchObject({ _tag: "LLM.ServerError", message: "overloaded_error: Overloaded" })
}),
)
it.effect("classifies prompt-too-long provider errors", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(
sseEvents({
@ -509,35 +511,35 @@ describe("Anthropic Messages route", () => {
}),
),
),
Effect.flip,
)
expect(response.events).toEqual([
{
type: "provider-error",
message: "invalid_request_error: prompt is too long: 210000 tokens",
classification: "context-overflow",
},
])
expect(error).toMatchObject({
_tag: "LLM.ContextOverflow",
message: "invalid_request_error: prompt is too long: 210000 tokens",
})
}),
)
it.effect("falls back to error type when no message is present", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error", error: { type: "overloaded_error", message: "" } }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "overloaded_error" }])
expect(error).toMatchObject({ _tag: "LLM.ServerError", message: "overloaded_error" })
}),
)
it.effect("falls back to a stable default when error payload is absent", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error" }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "Anthropic Messages stream error" }])
expect(error).toMatchObject({ _tag: "LLM.APIError", message: "Anthropic Messages stream error" })
}),
)

20
packages/llm/test/provider/bedrock-converse.test.ts
View file

@ -2,7 +2,7 @@ import { EventStreamCodec } from "@smithy/eventstream-codec"
import { fromUtf8, toUtf8 } from "@smithy/util-utf8"
import { describe, expect } from "bun:test"
import { Effect } from "effect"
import { CacheHint, LLM, Message, ToolCallPart, ToolChoice } from "../../src"
import { CacheHint, isLLMError, LLM, Message, ToolCallPart, ToolChoice } from "../../src"
import { LLMClient } from "../../src/route"
import { AmazonBedrock } from "../../src/providers"
import * as BedrockConverse from "../../src/protocols/bedrock-converse"
@ -355,33 +355,31 @@ describe("Bedrock Converse route", () => {
}),
)
it.effect("emits provider-error for throttlingException", () =>
it.effect("fails the stream for throttlingException", () =>
Effect.gen(function* () {
const body = eventStreamBody(
["messageStart", { role: "assistant" }],
["throttlingException", { message: "Slow down" }],
)
const response = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)))
const error = yield* LLMClient.generate(baseRequest).pipe(Effect.provide(fixedBytes(body)), Effect.flip)
expect(response.events.find((event) => event.type === "provider-error")).toEqual({
type: "provider-error",
message: "Slow down",
})
expect(isLLMError(error)).toBe(true)
expect(error).toMatchObject({ _tag: "LLM.RateLimit", message: "Slow down" })
}),
)
it.effect("classifies input-too-long validation exceptions", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(baseRequest).pipe(
const error = yield* LLMClient.generate(baseRequest).pipe(
Effect.provide(
fixedBytes(eventStreamBody(["validationException", { message: "Input is too long for requested model" }])),
),
Effect.flip,
)
expect(response.events.find((event) => event.type === "provider-error")).toEqual({
type: "provider-error",
expect(error).toMatchObject({
_tag: "LLM.ContextOverflow",
message: "Input is too long for requested model",
classification: "context-overflow",
})
}),
)

76
packages/llm/test/provider/openai-responses.test.ts
View file

@ -1368,37 +1368,41 @@ describe("OpenAI Responses route", () => {
}),
)
it.effect("emits provider-error events for mid-stream provider errors", () =>
it.effect("fails the stream for mid-stream provider errors", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error", code: "rate_limit_exceeded", message: "Slow down" }))),
Effect.flip,
)
// Prefix the code so consumers see the failure mode, not just the
// sometimes-generic provider message. The bare message alone meant
// production errors like rate limits were indistinguishable from
// unrelated stream failures.
expect(response.events).toEqual([{ type: "provider-error", message: "rate_limit_exceeded: Slow down" }])
expect(isLLMError(error)).toBe(true)
expect(error).toMatchObject({ _tag: "LLM.RateLimit", message: "rate_limit_exceeded: Slow down" })
}),
)
it.effect("falls back to error code when no message is present", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error", code: "internal_error" }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "internal_error" }])
expect(error).toMatchObject({ _tag: "LLM.ServerError", message: "internal_error" })
}),
)
it.effect("falls back to error code when message is empty", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error", code: "internal_error", message: "" }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "internal_error" }])
expect(error).toMatchObject({ _tag: "LLM.ServerError", message: "internal_error" })
}),
)
@ -1408,7 +1412,7 @@ describe("OpenAI Responses route", () => {
// "OpenAI Responses response failed" string, hiding the real cause.
it.effect("surfaces response.failed details from response.error", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(
sseEvents({
@ -1420,15 +1424,16 @@ describe("OpenAI Responses route", () => {
}),
),
),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "server_error: Upstream model unavailable" }])
expect(error).toMatchObject({ _tag: "LLM.ServerError", message: "server_error: Upstream model unavailable" })
}),
)
it.effect("surfaces response.failed code when no nested message is present", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(
sseEvents({
@ -1437,9 +1442,10 @@ describe("OpenAI Responses route", () => {
}),
),
),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "invalid_prompt" }])
expect(error).toMatchObject({ _tag: "LLM.BadRequest", message: "invalid_prompt" })
}),
)
@ -1450,7 +1456,7 @@ describe("OpenAI Responses route", () => {
// when they bubble up an HTTP error as an SSE `error` event. Honour
// both shapes so the user still sees the underlying cause instead
// of the catch-all string.
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(
sseEvents({
@ -1459,21 +1465,19 @@ describe("OpenAI Responses route", () => {
}),
),
),
Effect.flip,
)
expect(response.events).toEqual([
{
type: "provider-error",
message: "context_length_exceeded: prompt too long",
classification: "context-overflow",
},
])
expect(error).toMatchObject({
_tag: "LLM.ContextOverflow",
message: "context_length_exceeded: prompt too long",
})
}),
)
it.effect("surfaces error event details nested under error", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(
sseEvents({
@ -1488,21 +1492,19 @@ describe("OpenAI Responses route", () => {
}),
),
),
Effect.flip,
)
expect(response.events).toEqual([
{
type: "provider-error",
message: "context_length_exceeded: prompt too long",
classification: "context-overflow",
},
])
expect(error).toMatchObject({
_tag: "LLM.ContextOverflow",
message: "context_length_exceeded: prompt too long",
})
}),
)
it.effect("accepts nullable fields in spec-compliant error events", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(
fixedResponse(
sseEvents({
@ -1514,39 +1516,43 @@ describe("OpenAI Responses route", () => {
}),
),
),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "Something went wrong" }])
expect(error).toMatchObject({ _tag: "LLM.APIError", message: "Something went wrong" })
}),
)
it.effect("falls back to a stable default when error is null", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error", error: null }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "OpenAI Responses stream error" }])
expect(error).toMatchObject({ _tag: "LLM.APIError", message: "OpenAI Responses stream error" })
}),
)
it.effect("falls back to a stable default when both error and response are absent", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "error" }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "OpenAI Responses stream error" }])
expect(error).toMatchObject({ _tag: "LLM.APIError", message: "OpenAI Responses stream error" })
}),
)
it.effect("falls back to a stable default when response.failed has no error payload", () =>
Effect.gen(function* () {
const response = yield* LLMClient.generate(request).pipe(
const error = yield* LLMClient.generate(request).pipe(
Effect.provide(fixedResponse(sseEvents({ type: "response.failed", response: { id: "resp_failed_3" } }))),
Effect.flip,
)
expect(response.events).toEqual([{ type: "provider-error", message: "OpenAI Responses response failed" }])
expect(error).toMatchObject({ _tag: "LLM.APIError", message: "OpenAI Responses response failed" })
}),
)

3
packages/opencode/src/session/processor.ts
View file

@ -418,9 +418,6 @@ const layer = Layer.effect(
return
}
case "provider-error":
throw new Error(value.message)
case "step-start":
if (!ctx.snapshot) ctx.snapshot = yield* snapshot.track()
yield* session.updatePart({

3
packages/opencode/test/session/processor-effect.test.ts
View file

@ -219,8 +219,7 @@ const fragmentFailureLLM = Layer.succeed(
LLMEvent.reasoningDelta({ id: "reasoning-1", text: "thinking" }),
LLMEvent.textStart({ id: "text-1" }),
LLMEvent.textDelta({ id: "text-1", text: "partial" }),
LLMEvent.providerError({ message: "provider boom" }),
),
).pipe(Stream.concat(Stream.fail(new Error("provider boom")))),
}),
)
const fragmentFailureEnv = LayerNode.compile(root, [...replacements, [LLM.node, fragmentFailureLLM]])