@bitkyc08/opencodex
Version:
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code
216 lines (205 loc) • 11.4 kB
text/typescript
import { carryProxyError, isProxyError, markProxyError } from "../lib/client-error-body";
import { sharedPoolContinuityDenial } from "../lib/spend-reservation-ledger";
import { markResponseNonReplayable } from "../lib/upstream-retry";
/**
* The one place that knows how this proxy refuses a turn on its own workflow budget.
*
* It is a module rather than two inline blocks because the two call sites -- the HTTP admission
* check in `src/server/index.ts` and the pre-dispatch ceiling check in
* `src/server/responses/core.ts` -- had drifted into saying different things about the same
* refusal, and because the non-obvious part below has to be stated once and not twice.
*
* The HTTP admission DECISION lives here too, for the same reason: the lane derivation and the
* refusal it produces are two halves of one answer, and keeping them in one file is what stops
* a denial from losing the detail that makes it legible on the way out.
*/
import { formatErrorResponse } from "../bridge";
import {
addFinalRequestLog,
markLocalRequestLogRefusal,
type RequestLogContext,
} from "./request-log";
import {
WORKFLOW_LOCAL_REFUSAL_HEADER,
admitWorkflowTurn,
workflowSendCeilingReached,
workflowDenialSummary,
recordWorkflowRefusalEvent,
type WorkflowDenial,
type WorkflowDecision,
type WorkflowLane,
type WorkflowSpendDenialDetail,
} from "../lib/workflow-budget";
import { currentWorkflowBudgetPolicy } from "../lib/workflow-budget-config";
import { SEND_BUDGET_EXHAUSTED_CODE } from "../lib/errors";
/**
* What a caller needs to hand over for the refusal to become a row on `/api/logs`.
*
* The HTTP admission check refuses before the body is parsed, so its `logCtx` still carries the
* `unknown` model and provider the caller seeded it with. That is the honest record -- this
* request genuinely never resolved either -- and it is the same placeholder the native
* passthrough path already writes. Skipping the row entirely was the worse option: an operator
* reading the logs saw no trace at all of a request the proxy had refused.
*/
export interface WorkflowRefusalLog {
readonly requestId: string;
readonly start: number;
readonly logCtx: RequestLogContext;
/** Receiving HTTP route's notification after this refusal's final-log call. */
readonly onLogged?: () => void;
}
/**
* Build the 429 for a refusal this proxy made itself.
*
* The status and type arguments below do not reach the client: `classifyError` rewrites every
* 429 to `rate_limit_error` / `rate_limit_exceeded`, so the body is shaped exactly like a
* provider rate limit. That is a deliberate wire contract -- changing it would change how every
* client retries -- which leaves two places to carry the truth. The message names the ceiling
* that fired and distinguishes admission from refusing a later send, and the header carries
* the machine-readable name. The in-process proxy marker establishes its local provenance.
*
* The row is where an operator actually looks, so it gets the same treatment #4639 established:
* `terminalSource: "synthetic"`, a local reason, and an error code naming the ceiling. Pass
* `logCtx` when the caller is inside a turn that will write its own row, or `refusalLog` when
* the refusal happens before any row exists and this is the only chance to write one.
*/
export function workflowRefusalResponse(
reason: WorkflowDenial,
logCtx?: RequestLogContext,
refusalLog?: WorkflowRefusalLog,
rootId?: string,
spend?: WorkflowSpendDenialDetail,
): Response {
// The denial detail, when the caller has it, is what turns "a token ceiling refused this"
// into "the account ceiling of 100,000 is spent". It reaches the message, the event ring and
// the log row through this one function, so the three cannot drift into saying different
// things about the same refusal -- which is what put this module here in the first place.
const summary = workflowDenialSummary(reason, spend);
// Only a caller that decided the refusal ITSELF passes a root id. admitWorkflowTurn already
// records its own denials, so passing one there would double-count them.
if (rootId) recordWorkflowRefusalEvent(rootId, reason, Date.now(), spend);
const recordOn = logCtx ?? refusalLog?.logCtx;
const sentPreviously = (recordOn?.activeAttempt?.sendCount ?? 0) > 0
|| recordOn?.attempts?.some(attempt => attempt.sendCount > 0) === true;
const message = sentPreviously ? summary.message
.replace("refused the request locally", "refused an additional send locally")
.replace("no provider was contacted", "no additional provider request was sent")
.replace("No provider was contacted", "No additional provider request was sent") : summary.message;
if (recordOn) {
markLocalRequestLogRefusal(recordOn, summary.code);
// A locally assigned code wins in addFinalRequestLog, so this is what names the ceiling in
// the logs column rather than the generic rate-limit classification a 429 would get.
recordOn.errorCode = summary.code;
}
if (refusalLog) {
addFinalRequestLog(refusalLog.requestId, refusalLog.start, refusalLog.logCtx, 429, {
closeReason: "terminal",
});
refusalLog.onLogged?.();
}
const refusal = formatErrorResponse(
429,
reason === "workflow-sends-exhausted" ? "workflow_budget_exhausted" : "queue_capacity_exceeded",
message,
);
refusal.headers.set(WORKFLOW_LOCAL_REFUSAL_HEADER, summary.code);
// Without this a browser dashboard cannot read the header at all: the data plane never sets
// Access-Control-Expose-Headers, so a cross-origin reader sees only the CORS-safelisted ones.
refusal.headers.set("Access-Control-Expose-Headers", WORKFLOW_LOCAL_REFUSAL_HEADER);
// No Combo target has an allowance after a root send denial; do not classify it as quota.
if (reason === "workflow-sends-exhausted") markResponseNonReplayable(refusal);
return markProxyError(refusal, reason === "workflow-spend-exhausted" && spend && Object.hasOwn({ root: 1, identity: 1, pool: 1 }, spend.scope) ? (spend.includesUnboundPoolHistory ? "workflow_unbound" : "workflow") : undefined);
}
/** Preserve only a locally constructed workflow refusal across response projections. */
export function carryWorkflowRefusal(source: Response, target: Response): Response {
const code = isProxyError(source) ? source.headers.get(WORKFLOW_LOCAL_REFUSAL_HEADER) : null;
if (!code) return target;
target.headers.set(WORKFLOW_LOCAL_REFUSAL_HEADER, code);
const exposed = target.headers.get("Access-Control-Expose-Headers");
if (!exposed?.split(",").some(name => name.trim().toLowerCase() === WORKFLOW_LOCAL_REFUSAL_HEADER)) {
target.headers.set("Access-Control-Expose-Headers", exposed ? `${exposed}, ${WORKFLOW_LOCAL_REFUSAL_HEADER}` : WORKFLOW_LOCAL_REFUSAL_HEADER);
}
return carryProxyError(source, target);
}
/** Distinguish an exhausted live root from the request's independent send allowance. */
export function workflowSendCeilingRefusalResponse(
logCtx: RequestLogContext,
rootId?: string,
recordedOn: Pick<RequestLogContext, "localTerminalReason"> = logCtx,
): Response | undefined {
if (!workflowSendCeilingReached(rootId, currentWorkflowBudgetPolicy())) return undefined;
// Observer-backed admission already records its denial; legacy budgets need the event here.
return workflowRefusalResponse("workflow-sends-exhausted", logCtx, undefined,
recordedOn.localTerminalReason === "workflow_sends_exhausted" ? undefined : rootId);
}
/** Render the approved conservative-overlay explanation after a dispatch reservation refuses. */
export function unboundPoolSpendRefusalMessage(
logCtx: Pick<RequestLogContext, "spendRefusalDetail">,
): string | undefined {
const detail = logCtx.spendRefusalDetail;
if (!detail?.includesUnboundPoolHistory) return undefined;
return workflowDenialSummary("workflow-spend-exhausted", detail).message;
}
/** HTTP form for pre-commit send-budget catches; the tracker already recorded the event. */
export function unboundPoolSpendRefusalResponse(logCtx: RequestLogContext): Response | undefined {
const detail = logCtx.spendRefusalDetail;
if (!detail?.includesUnboundPoolHistory) return undefined;
return workflowRefusalResponse("workflow-spend-exhausted", logCtx, undefined, undefined, detail);
}
/** Preserve affinity when the proxy, rather than the serving credential, refuses a send. */
export function adapterSendBudgetRefusal(logCtx: RequestLogContext, rootId: string | undefined, message: string): Response {
logCtx.terminalSource = "synthetic";
return unboundPoolSpendRefusalResponse(logCtx) ?? workflowSendCeilingRefusalResponse(logCtx, rootId)
?? markProxyError(formatErrorResponse(429, SEND_BUDGET_EXHAUSTED_CODE, message));
}
/**
* Admit one HTTP turn against its root workflow budget.
*
* A fan-out shares the conversation it serves. Without a reserve, a worker burst takes every
* slot under its own root and the interactive turn that started it waits behind its own
* children. A request that names a parent is treated as that fan-out; a top-level request is
* the conversation and may use the reserved slots.
*/
/** Read-only alias validation: keep replay corruption distinct from conflicting pool owners. */
export function poolContinuityRefusalReason(): WorkflowDenial | undefined {
const denial = sharedPoolContinuityDenial();
if (!denial) return undefined;
return denial.reason === "pool-history-unresolved" ? "workflow-pool-history-unresolved" : "workflow-spend-undurable";
}
export function admitHttpWorkflowTurn(headers: Headers): WorkflowDecision | undefined {
const rootId = headers.get("x-codex-parent-thread-id")?.trim() || undefined;
const continuityRefusal = poolContinuityRefusalReason();
if (continuityRefusal) {
recordWorkflowRefusalEvent(rootId, continuityRefusal);
return { admitted: false, reason: continuityRefusal, rootId: rootId ?? "" };
}
const threadId = headers.get("thread-id")?.trim() || undefined;
const lane: WorkflowLane = rootId !== undefined && threadId !== undefined && threadId !== rootId
? "worker"
: "interactive";
return admitWorkflowTurn(rootId, lane, currentWorkflowBudgetPolicy(), threadId);
}
/**
* The refusal for a decision {@link admitHttpWorkflowTurn} declined.
*
* It exists so the denial's own detail survives the trip to the wire. A token-ceiling denial
* arrives carrying the scope that refused and the number it refused against, and a caller that
* forwarded only `reason` would answer with a 429 that names no ceiling -- which is the
* illegible refusal this whole path is built to avoid. No root id is passed on: the admission
* check already recorded its own event, and passing one would count the refusal twice.
*/
export function workflowDecisionRefusalResponse(
decision: Extract<WorkflowDecision, { admitted: false }>,
logCtx?: RequestLogContext,
refusalLog?: WorkflowRefusalLog,
): Response {
const spend = decision.spendScope !== undefined && decision.spendLimit !== undefined
? {
scope: decision.spendScope,
limit: decision.spendLimit,
...(decision.spendProjected !== undefined ? { projected: decision.spendProjected } : {}),
...(decision.spendIncludesUnboundPoolHistory ? { includesUnboundPoolHistory: true } : {}),
}
: undefined;
return workflowRefusalResponse(decision.reason, logCtx, refusalLog, undefined, spend);
}