fix(gateway): support image_url in OpenAI chat completions (#34068)

* fix(gateway): parse image_url in openai chat completions

* test(gateway): cover openai chat completions image_url flows

* docs(changelog): note openai image_url chat completions fix (#17685)

* fix(gateway): harden openai image_url parsing and limits

* test(gateway): add openai image_url regression coverage

* docs(changelog): expand #17685 openai chat completions note

* Gateway: make OpenAI image_url URL fetch opt-in and configurable

* Diagnostics: redact image base64 payload data in trace logs

* Changelog: note OpenAI image_url hardening follow-ups

* Gateway: enforce OpenAI image_url total budget incrementally

* Gateway: scope OpenAI image_url extraction to the active turn

* Update CHANGELOG.md
This commit is contained in:
Vincent Koc
2026-03-06 00:35:50 -05:00
committed by GitHub
parent 36e2e04a32
commit 9c86a9fd23
16 changed files with 764 additions and 18 deletions

View File

@@ -0,0 +1,49 @@
import crypto from "node:crypto";
import type { StreamFn } from "@mariozechner/pi-agent-core";
import { describe, expect, it } from "vitest";
import { createAnthropicPayloadLogger } from "./anthropic-payload-log.js";
describe("createAnthropicPayloadLogger", () => {
it("redacts image base64 payload data before writing logs", async () => {
const lines: string[] = [];
const logger = createAnthropicPayloadLogger({
env: { OPENCLAW_ANTHROPIC_PAYLOAD_LOG: "1" },
writer: {
filePath: "memory",
write: (line) => lines.push(line),
},
});
expect(logger).not.toBeNull();
const payload = {
messages: [
{
role: "user",
content: [
{
type: "image",
source: { type: "base64", media_type: "image/png", data: "QUJDRA==" },
},
],
},
],
};
const streamFn: StreamFn = ((_, __, options) => {
options?.onPayload?.(payload);
return {} as never;
}) as StreamFn;
const wrapped = logger?.wrapStreamFn(streamFn);
await wrapped?.({ api: "anthropic-messages" } as never, { messages: [] } as never, {});
const event = JSON.parse(lines[0]?.trim() ?? "{}") as Record<string, unknown>;
const message = ((event.payload as { messages?: unknown[] } | undefined)?.messages ??
[]) as Array<Record<string, unknown>>;
const source = (((message[0]?.content as Array<Record<string, unknown>> | undefined) ?? [])[0]
?.source ?? {}) as Record<string, unknown>;
expect(source.data).toBe("<redacted>");
expect(source.bytes).toBe(4);
expect(source.sha256).toBe(crypto.createHash("sha256").update("QUJDRA==").digest("hex"));
expect(event.payloadDigest).toBeDefined();
});
});

View File

@@ -7,6 +7,7 @@ import { createSubsystemLogger } from "../logging/subsystem.js";
import { resolveUserPath } from "../utils.js";
import { parseBooleanValue } from "../utils/boolean.js";
import { safeJsonStringify } from "../utils/safe-json.js";
import { redactImageDataForDiagnostics } from "./payload-redaction.js";
import { getQueuedFileWriter, type QueuedFileWriter } from "./queued-file-writer.js";
type PayloadLogStage = "request" | "usage";
@@ -103,6 +104,7 @@ export function createAnthropicPayloadLogger(params: {
modelId?: string;
modelApi?: string | null;
workspaceDir?: string;
writer?: PayloadLogWriter;
}): AnthropicPayloadLogger | null {
const env = params.env ?? process.env;
const cfg = resolvePayloadLogConfig(env);
@@ -110,7 +112,7 @@ export function createAnthropicPayloadLogger(params: {
return null;
}
const writer = getWriter(cfg.filePath);
const writer = params.writer ?? getWriter(cfg.filePath);
const base: Omit<PayloadLogEvent, "ts" | "stage"> = {
runId: params.runId,
sessionId: params.sessionId,
@@ -135,12 +137,13 @@ export function createAnthropicPayloadLogger(params: {
return streamFn(model, context, options);
}
const nextOnPayload = (payload: unknown) => {
const redactedPayload = redactImageDataForDiagnostics(payload);
record({
...base,
ts: new Date().toISOString(),
stage: "request",
payload,
payloadDigest: digest(payload),
payload: redactedPayload,
payloadDigest: digest(redactedPayload),
});
options?.onPayload?.(payload);
};

View File

@@ -1,3 +1,4 @@
import crypto from "node:crypto";
import { describe, expect, it } from "vitest";
import type { OpenClawConfig } from "../config/config.js";
import { resolveUserPath } from "../utils.js";
@@ -89,4 +90,58 @@ describe("createCacheTrace", () => {
expect(trace).toBeNull();
});
it("redacts image data from options and messages before writing", () => {
const lines: string[] = [];
const trace = createCacheTrace({
cfg: {
diagnostics: {
cacheTrace: {
enabled: true,
},
},
},
env: {},
writer: {
filePath: "memory",
write: (line) => lines.push(line),
},
});
trace?.recordStage("stream:context", {
options: {
images: [{ type: "image", mimeType: "image/png", data: "QUJDRA==" }],
},
messages: [
{
role: "user",
content: [
{
type: "image",
source: { type: "base64", media_type: "image/jpeg", data: "U0VDUkVU" },
},
],
},
] as unknown as [],
});
const event = JSON.parse(lines[0]?.trim() ?? "{}") as Record<string, unknown>;
const optionsImages = (
((event.options as { images?: unknown[] } | undefined)?.images ?? []) as Array<
Record<string, unknown>
>
)[0];
expect(optionsImages?.data).toBe("<redacted>");
expect(optionsImages?.bytes).toBe(4);
expect(optionsImages?.sha256).toBe(
crypto.createHash("sha256").update("QUJDRA==").digest("hex"),
);
const firstMessage = ((event.messages as Array<Record<string, unknown>> | undefined) ?? [])[0];
const source = (((firstMessage?.content as Array<Record<string, unknown>> | undefined) ?? [])[0]
?.source ?? {}) as Record<string, unknown>;
expect(source.data).toBe("<redacted>");
expect(source.bytes).toBe(6);
expect(source.sha256).toBe(crypto.createHash("sha256").update("U0VDUkVU").digest("hex"));
});
});

View File

@@ -6,6 +6,7 @@ import { resolveStateDir } from "../config/paths.js";
import { resolveUserPath } from "../utils.js";
import { parseBooleanValue } from "../utils/boolean.js";
import { safeJsonStringify } from "../utils/safe-json.js";
import { redactImageDataForDiagnostics } from "./payload-redaction.js";
import { getQueuedFileWriter, type QueuedFileWriter } from "./queued-file-writer.js";
export type CacheTraceStage =
@@ -198,7 +199,7 @@ export function createCacheTrace(params: CacheTraceInit): CacheTrace | null {
event.systemDigest = digest(payload.system);
}
if (payload.options) {
event.options = payload.options;
event.options = redactImageDataForDiagnostics(payload.options) as Record<string, unknown>;
}
if (payload.model) {
event.model = payload.model;
@@ -212,7 +213,7 @@ export function createCacheTrace(params: CacheTraceInit): CacheTrace | null {
event.messageFingerprints = summary.messageFingerprints;
event.messagesDigest = summary.messagesDigest;
if (cfg.includeMessages) {
event.messages = messages;
event.messages = redactImageDataForDiagnostics(messages) as AgentMessage[];
}
}

View File

@@ -0,0 +1,64 @@
import crypto from "node:crypto";
import { estimateBase64DecodedBytes } from "../media/base64.js";
export const REDACTED_IMAGE_DATA = "<redacted>";
function toLowerTrimmed(value: unknown): string {
return typeof value === "string" ? value.trim().toLowerCase() : "";
}
function hasImageMime(record: Record<string, unknown>): boolean {
const candidates = [
toLowerTrimmed(record.mimeType),
toLowerTrimmed(record.media_type),
toLowerTrimmed(record.mime_type),
];
return candidates.some((value) => value.startsWith("image/"));
}
function shouldRedactImageData(record: Record<string, unknown>): record is Record<string, string> {
if (typeof record.data !== "string") {
return false;
}
const type = toLowerTrimmed(record.type);
return type === "image" || hasImageMime(record);
}
function digestBase64Payload(data: string): string {
return crypto.createHash("sha256").update(data).digest("hex");
}
/**
* Redacts image/base64 payload data from diagnostic objects before persistence.
*/
export function redactImageDataForDiagnostics(value: unknown): unknown {
const seen = new WeakSet<object>();
const visit = (input: unknown): unknown => {
if (Array.isArray(input)) {
return input.map((entry) => visit(entry));
}
if (!input || typeof input !== "object") {
return input;
}
if (seen.has(input)) {
return "[Circular]";
}
seen.add(input);
const record = input as Record<string, unknown>;
const out: Record<string, unknown> = {};
for (const [key, val] of Object.entries(record)) {
out[key] = visit(val);
}
if (shouldRedactImageData(record)) {
out.data = REDACTED_IMAGE_DATA;
out.bytes = estimateBase64DecodedBytes(record.data);
out.sha256 = digestBase64Payload(record.data);
}
return out;
};
return visit(value);
}