fix(agents): make tool call ID sanitization conditional with standard/strict modes

- Add ToolCallIdMode type ('standard' | 'strict') for provider compatibility
- Standard mode (default): allows [a-zA-Z0-9_-] for readable session logs
- Strict mode: only [a-zA-Z0-9] for Mistral via OpenRouter
- Update sanitizeSessionMessagesImages to accept toolCallIdMode option
- Export ToolCallIdMode from pi-embedded-helpers barrel

Addresses review feedback on PR #1372 about readability.
This commit is contained in:
zerone0x
2026-01-21 21:32:53 +08:00
committed by Peter Steinberger
parent d0f9e22a4b
commit d51eca64cc
7 changed files with 369 additions and 180 deletions

View File

@@ -2,46 +2,70 @@ import { createHash } from "node:crypto";
import type { AgentMessage } from "@mariozechner/pi-agent-core";
export function sanitizeToolCallId(id: string): string {
if (!id || typeof id !== "string") return "defaulttoolid";
export type ToolCallIdMode = "standard" | "strict";
// Some providers (e.g. Mistral via OpenRouter) require strictly alphanumeric tool call IDs.
// Strip all non-alphanumeric characters to ensure maximum compatibility.
const alphanumericOnly = id.replace(/[^a-zA-Z0-9]/g, "");
/**
* Sanitize a tool call ID to be compatible with various providers.
*
* - "standard" mode: allows [a-zA-Z0-9_-], better readability (default)
* - "strict" mode: only [a-zA-Z0-9], required for Mistral via OpenRouter
*/
export function sanitizeToolCallId(id: string, mode: ToolCallIdMode = "standard"): string {
if (!id || typeof id !== "string") {
return mode === "strict" ? "defaulttoolid" : "default_tool_id";
}
return alphanumericOnly.length > 0 ? alphanumericOnly : "sanitizedtoolid";
if (mode === "strict") {
// Some providers (e.g. Mistral via OpenRouter) require strictly alphanumeric tool call IDs.
const alphanumericOnly = id.replace(/[^a-zA-Z0-9]/g, "");
return alphanumericOnly.length > 0 ? alphanumericOnly : "sanitizedtoolid";
}
// Standard mode: allow underscores and hyphens for better readability in logs
const sanitized = id.replace(/[^a-zA-Z0-9_-]/g, "_");
const trimmed = sanitized.replace(/^[^a-zA-Z0-9_-]+/, "");
return trimmed.length > 0 ? trimmed : "sanitized_tool_id";
}
export function isValidCloudCodeAssistToolId(id: string): boolean {
export function isValidCloudCodeAssistToolId(id: string, mode: ToolCallIdMode = "standard"): boolean {
if (!id || typeof id !== "string") return false;
// Strictly alphanumeric for maximum provider compatibility (e.g. Mistral via OpenRouter).
return /^[a-zA-Z0-9]+$/.test(id);
if (mode === "strict") {
// Strictly alphanumeric for providers like Mistral via OpenRouter
return /^[a-zA-Z0-9]+$/.test(id);
}
// Standard mode allows underscores and hyphens
return /^[a-zA-Z0-9_-]+$/.test(id);
}
function shortHash(text: string): string {
return createHash("sha1").update(text).digest("hex").slice(0, 8);
}
function makeUniqueToolId(params: { id: string; used: Set<string> }): string {
function makeUniqueToolId(params: {
id: string;
used: Set<string>;
mode: ToolCallIdMode;
}): string {
const MAX_LEN = 40;
const base = sanitizeToolCallId(params.id).slice(0, MAX_LEN);
const base = sanitizeToolCallId(params.id, params.mode).slice(0, MAX_LEN);
if (!params.used.has(base)) return base;
// Use alphanumeric-only suffixes to maintain strict compatibility.
const hash = shortHash(params.id);
const maxBaseLen = MAX_LEN - hash.length;
// Use separator based on mode: underscore for standard (readable), none for strict
const separator = params.mode === "strict" ? "" : "_";
const maxBaseLen = MAX_LEN - separator.length - hash.length;
const clippedBase = base.length > maxBaseLen ? base.slice(0, maxBaseLen) : base;
const candidate = `${clippedBase}${hash}`;
const candidate = `${clippedBase}${separator}${hash}`;
if (!params.used.has(candidate)) return candidate;
for (let i = 2; i < 1000; i += 1) {
const suffix = `x${i}`;
const suffix = params.mode === "strict" ? `x${i}` : `_${i}`;
const next = `${candidate.slice(0, MAX_LEN - suffix.length)}${suffix}`;
if (!params.used.has(next)) return next;
}
const ts = `t${Date.now()}`;
const ts = params.mode === "strict" ? `t${Date.now()}` : `_${Date.now()}`;
return `${candidate.slice(0, MAX_LEN - ts.length)}${ts}`;
}
@@ -100,18 +124,27 @@ function rewriteToolResultIds(params: {
} as Extract<AgentMessage, { role: "toolResult" }>;
}
export function sanitizeToolCallIdsForCloudCodeAssist(messages: AgentMessage[]): AgentMessage[] {
// Some providers (e.g. Mistral via OpenRouter) require strictly alphanumeric tool IDs.
// Use ^[a-zA-Z0-9]+$ pattern for maximum compatibility across all providers.
// Sanitization can introduce collisions (e.g. `a|b` and `a:b` -> `ab`).
// Fix by applying a stable, transcript-wide mapping and de-duping via hash suffix.
/**
* Sanitize tool call IDs for provider compatibility.
*
* @param messages - The messages to sanitize
* @param mode - "standard" (default, allows _-) or "strict" (alphanumeric only for Mistral/OpenRouter)
*/
export function sanitizeToolCallIdsForCloudCodeAssist(
messages: AgentMessage[],
mode: ToolCallIdMode = "standard",
): AgentMessage[] {
// Standard mode: allows [a-zA-Z0-9_-] for better readability in session logs
// Strict mode: only [a-zA-Z0-9] for providers like Mistral via OpenRouter
// Sanitization can introduce collisions (e.g. `a|b` and `a:b` -> `a_b` or `ab`).
// Fix by applying a stable, transcript-wide mapping and de-duping via suffix.
const map = new Map<string, string>();
const used = new Set<string>();
const resolve = (id: string) => {
const existing = map.get(id);
if (existing) return existing;
const next = makeUniqueToolId({ id, used });
const next = makeUniqueToolId({ id, used, mode });
map.set(id, next);
used.add(next);
return next;