fix: prevent provider_error 400 on dmodel/ultimate by using content placeholder
When assistant messages contain only tool_calls (no text/thinking), transform.ts was setting content to null. Qoder's gateway drops these null-content assistant messages, orphaning the following tool_result and causing upstream rejections: - dmodel (OpenAI): 'tool must follow a message with tool_calls' - ultimate (Anthropic): 'unexpected tool_use_id in tool_result blocks' Analysis of 28 historical sessions showed 100% failure rate on dmodel and 75% on ultimate for this pattern, while auto/GLM5.2 (GLM upstream) tolerated it. Fix: inject a single-space placeholder when tool_calls are present but content is empty, so the gateway preserves the assistant message and tool pairing stays valid. Also fixes pre-existing lint formatting in stream.ts and package.json. Adds regression test for the full assistant+toolResult pairing scenario.
This commit is contained in:
+2
-2
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "pi-provider-qoder",
|
||||
"version": "0.2.9",
|
||||
"description": "Pi extension for Qoder AI — with OAuth authentication, COSY signatures and WAF bypass",
|
||||
"version": "0.2.9-fix.1",
|
||||
"description": "Pi extension for Qoder AI \u2014 with OAuth authentication, COSY signatures and WAF bypass",
|
||||
"type": "module",
|
||||
"license": "MIT",
|
||||
"publishConfig": {
|
||||
|
||||
Reference in New Issue
Block a user