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:
+1
-3
@@ -193,9 +193,7 @@ export function streamQoder(
|
||||
// model never sees it). Inject the system prompt as a leading
|
||||
// role:system message instead, which the server does honor.
|
||||
system: "",
|
||||
messages: systemText
|
||||
? [{ role: "system", content: systemText }, ...normalizedMessages]
|
||||
: normalizedMessages,
|
||||
messages: systemText ? [{ role: "system", content: systemText }, ...normalizedMessages] : normalizedMessages,
|
||||
tools: toolsRaw || [],
|
||||
parameters: { max_tokens: maxTokens },
|
||||
chat_context: {
|
||||
|
||||
Reference in New Issue
Block a user