fix(ai): own Anthropic SSE parsing to avoid SDK JSON.parse hard-failures

Bypass the Anthropic SDK streaming parser entirely. Use
client.messages.create().asResponse() and decode the SSE stream
ourselves with defensive JSON parsing that repairs invalid escape
sequences and control characters inside string literals.

- Switch from SDK .stream() to .asResponse() + pi-owned SSE decoder
- Add repairJson() / parseJsonWithRepair() to json-parse.ts
- Add anthropic-sse-parsing.test.ts regression for malformed tool deltas
- Update github-copilot-anthropic.test.ts mock to match new call path
- Update deprecated claude-3-5-haiku-20241022 refs to claude-haiku-4-5
- Remove stale non-reasoning model test

fixes #3175
This commit is contained in:
Mario Zechner
2026-04-21 23:00:56 +02:00
parent a0a16c7762
commit 4b926a30a2
12 changed files with 430 additions and 124 deletions

View File

@@ -1,5 +1,99 @@
import { parse as partialParse } from "partial-json";
const VALID_JSON_ESCAPES = new Set(['"', "\\", "/", "b", "f", "n", "r", "t", "u"]);
function isControlCharacter(char: string): boolean {
const codePoint = char.codePointAt(0);
return codePoint !== undefined && codePoint >= 0x00 && codePoint <= 0x1f;
}
function escapeControlCharacter(char: string): string {
switch (char) {
case "\b":
return "\\b";
case "\f":
return "\\f";
case "\n":
return "\\n";
case "\r":
return "\\r";
case "\t":
return "\\t";
default:
return `\\u${char.codePointAt(0)?.toString(16).padStart(4, "0") ?? "0000"}`;
}
}
/**
* Repairs malformed JSON string literals by:
* - escaping raw control characters inside strings
* - doubling backslashes before invalid escape characters
*/
export function repairJson(json: string): string {
let repaired = "";
let inString = false;
for (let index = 0; index < json.length; index++) {
const char = json[index];
if (!inString) {
repaired += char;
if (char === '"') {
inString = true;
}
continue;
}
if (char === '"') {
repaired += char;
inString = false;
continue;
}
if (char === "\\") {
const nextChar = json[index + 1];
if (nextChar === undefined) {
repaired += "\\\\";
continue;
}
if (nextChar === "u") {
const unicodeDigits = json.slice(index + 2, index + 6);
if (/^[0-9a-fA-F]{4}$/.test(unicodeDigits)) {
repaired += `\\u${unicodeDigits}`;
index += 5;
continue;
}
}
if (VALID_JSON_ESCAPES.has(nextChar)) {
repaired += `\\${nextChar}`;
index += 1;
continue;
}
repaired += "\\\\";
continue;
}
repaired += isControlCharacter(char) ? escapeControlCharacter(char) : char;
}
return repaired;
}
export function parseJsonWithRepair<T>(json: string): T {
try {
return JSON.parse(json) as T;
} catch (error) {
const repairedJson = repairJson(json);
if (repairedJson !== json) {
return JSON.parse(repairedJson) as T;
}
throw error;
}
}
/**
* Attempts to parse potentially incomplete JSON during streaming.
* Always returns a valid object, even if the JSON is incomplete.
@@ -7,22 +101,24 @@ import { parse as partialParse } from "partial-json";
* @param partialJson The partial JSON string from streaming
* @returns Parsed object or empty object if parsing fails
*/
export function parseStreamingJson<T = any>(partialJson: string | undefined): T {
export function parseStreamingJson<T = Record<string, unknown>>(partialJson: string | undefined): T {
if (!partialJson || partialJson.trim() === "") {
return {} as T;
}
// Try standard parsing first (fastest for complete JSON)
try {
return JSON.parse(partialJson) as T;
return parseJsonWithRepair<T>(partialJson);
} catch {
// Try partial-json for incomplete JSON
try {
const result = partialParse(partialJson);
return (result ?? {}) as T;
} catch {
// If all parsing fails, return empty object
return {} as T;
try {
const result = partialParse(repairJson(partialJson));
return (result ?? {}) as T;
} catch {
return {} as T;
}
}
}
}