Files
OmniRoute/tests/unit/responses-passthrough-openai-compatible.test.ts
GiauPhan 548316a2c4 fix(translator): Normalize tool call names from lowercase to PascalCase when translating upstream responses to Claude Messages API format (#10392)
* fix(translator): Normalize tool call names from lowercase to PascalCase (#1)

* Fix: Map lowercase tool names from Antigravity (Gemini format) to Claude Code expected PascalCase

* Fix: toolNameMap in fun restoreClaudePassthroughToolUseName

* fix(translator): Normalize tool call names from lowercase to PascalCase when translating upstream responses (OpenAI, Gemini, Antigravity) to Claude Messages API format

This resolves `Error: No such tool available: read`/`bash`/`write` errors when using Claude Code CLI with third-party providers that emit lowercase tool names. The fix adds case-insensitive tool name lookups in `openai-to-claude.ts`, `gemini-to-claude.ts`, and related translators, ensuring tool names like `read`/`bash` are mapped to `Read`/`Bash` before being sent to Claude Code. Includes unit tests and comprehensive changelog notes ([#10250](https://github.com/diegosouzapw/OmniRoute/pull/10250))

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

* fix(translator): Parse <tool_call> JSON and TOOL_CALL text formats fr… (#2)

* fix(translator): Parse <tool_call> JSON and TOOL_CALL text formats from model output

Some models (DeepSeek, Qwen) emit tool calls as text instead of proper
tool_calls JSON: either <tool_call>{...}</tool_call> or TOOL_CALL Name: {...}.
Extend extractXmlInvokeBlocks to handle all 3 formats in a single scan pass,
picking whichever pattern appears first. Includes unit tests for all formats.

* fix(translator): Parse text-format tool calls in gemini-to-claude translator

Extend the Gemini->Claude translator to detect <invoke>, <tool_call> JSON,
and TOOL_CALL text formats emitted inline in text parts (Antigravity/Gemini
models), converting them to proper tool_use content blocks instead of leaking
raw text to Claude Code.

* docs(changelog): Add changelog entry for text tool call parsing fix

* fix(translator): consolidate tool name casing normalization and restore thought-signature persistence (#3)

* fix(translator): sanitize tool_use.id and tool_result.tool_use_id to match Anthropic schema (#4)

Ensure tool IDs from OpenAI-compatible upstreams (which may contain dots, colons, or special characters) are sanitized to ^[a-zA-Z0-9_-]+$ in response translators and passthrough requests before reaching Claude endpoints.

* fix(responses): preserve native tools for openai-compatible Responses targets (#5)

A Responses-shaped request to a custom openai-compatible connection whose
outbound protocol is Responses took a Responses -> Chat -> Responses round
trip, so Codex custom tools lost their grammar (`exec`), namespace groups were
flattened (`collaboration`), and tool invocations failed upstream.

Gate a native Responses passthrough on the connection's configured protocol
(`apiType: "responses"` / `_omnirouteForceResponsesUpstream`) so the original
tool definitions reach a Responses-capable upstream unchanged. Chat-only
connections keep the existing downgrade.

Closes #10374

* fix(translator): add support for 'applypatch' tool name in tool call checks

* test(translator): add unit test for apply_patch and applypatch tool name remapping

* fix(translator): remove no-explicit-any lint errors in tool-use-id-sanitization test

Type the openaiToClaudeResponse/translateNonStreamingResponse return
values with narrow local shapes instead of `any`, satisfying the
repo's no-explicit-any = error rule for tests/. No behavior change —
the same 3 assertions still pass.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* test: update 9568 casing regression to match #10392's consolidated fix

restoreClaudeToolName's static casing map now normalizes known
lowercase tool names to canonical PascalCase unconditionally on the
gemini-to-claude and openai-to-claude Claude Messages API paths (not
gated behind toolNameMap), superseding the earlier per-map-only fix
that the original #9568 regression test locked in as "expected" (it
was previously labeled a known bug case). The gemini-to-openai
passthrough path is unaffected by #10392 and keeps its original
pass-through assertion.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
2026-08-18 10:49:48 -03:00

74 lines
2.8 KiB
TypeScript

import { test } from "node:test";
import assert from "node:assert/strict";
import {
shouldUseNativeOpenAICompatibleResponsesPassthrough,
stampNativeResponsesPassthroughBody,
} from "../../open-sse/handlers/chatCore/passthroughHelpers.ts";
import { resolveChatCoreTargetFormat } from "../../open-sse/handlers/chatCore/targetFormat.ts";
import { FORMATS } from "../../open-sse/translator/formats.ts";
test("shouldUseNativeOpenAICompatibleResponsesPassthrough detects valid passthrough candidate", () => {
const result = shouldUseNativeOpenAICompatibleResponsesPassthrough({
provider: "openai-compatible-custom-123",
sourceFormat: FORMATS.OPENAI_RESPONSES,
providerSpecificData: { apiType: "responses" },
});
assert.equal(result, true);
});
test("shouldUseNativeOpenAICompatibleResponsesPassthrough rejects non-openai-compatible providers", () => {
const result = shouldUseNativeOpenAICompatibleResponsesPassthrough({
provider: "openai",
sourceFormat: FORMATS.OPENAI_RESPONSES,
providerSpecificData: { apiType: "responses" },
});
assert.equal(result, false);
});
test("shouldUseNativeOpenAICompatibleResponsesPassthrough rejects chat apiType", () => {
const result = shouldUseNativeOpenAICompatibleResponsesPassthrough({
provider: "openai-compatible-custom-123",
sourceFormat: FORMATS.OPENAI_RESPONSES,
providerSpecificData: { apiType: "chat" },
});
assert.equal(result, false);
});
test("shouldUseNativeOpenAICompatibleResponsesPassthrough respects forceResponses flag", () => {
const result = shouldUseNativeOpenAICompatibleResponsesPassthrough({
provider: "openai-compatible-custom-123",
sourceFormat: FORMATS.OPENAI_RESPONSES,
providerSpecificData: { _omnirouteForceResponsesUpstream: true },
});
assert.equal(result, true);
});
test("resolveChatCoreTargetFormat sets targetFormat to OPENAI_RESPONSES for passthrough", () => {
const { targetFormat } = resolveChatCoreTargetFormat({
provider: "openai-compatible-custom-123",
resolvedModel: "gpt-5.6-sol",
apiFormat: "responses",
sourceFormat: FORMATS.OPENAI_RESPONSES,
customModelTargetFormat: undefined,
providerSpecificData: { apiType: "responses" },
nativeOpenAICompatibleResponsesPassthrough: true,
});
assert.equal(targetFormat, FORMATS.OPENAI_RESPONSES);
});
test("stampNativeResponsesPassthroughBody stamps _nativeOpenAICompatibleResponsesPassthrough", () => {
const body = {
model: "gpt-5.6-sol",
tools: [
{
name: "exec",
type: "custom",
format: { syntax: "lark", type: "grammar", definition: "..." },
},
],
};
const stamped = stampNativeResponsesPassthroughBody(body, "openai-compatible");
assert.equal(stamped._nativeOpenAICompatibleResponsesPassthrough, true);
assert.deepEqual(stamped.tools, body.tools);
});