chore: merge released dev into PR #1690

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@kaitranntt/ccs",
-  "version": "8.8.1-dev.16",
+  "version": "8.8.1-dev.17",
   "description": "Claude Codex Switch - Instant profile switching between Claude, GLM, Kimi, and more",
   "keywords": [
     "cli",

src/proxy/transformers/request-transformer.ts

@@ -671,6 +671,52 @@ function transformMessages(messagesValue: unknown): OpenAIMessage[] {
   return translatedMessages;
 }
 
+/**
+ * Hoist every accepted `role: "system"` message to one leading system message.
+ *
+ * Claude Code sends the system prompt as the top-level `system` field *and*,
+ * separately, sends skill/plugin listings as `role: "system"` entries inside
+ * `messages` (see #1459). `ProxyRequestTransformer.transform` prepends the
+ * top-level `system` field unconditionally, so once both are present the
+ * resulting array holds two `system` messages that are not adjacent —
+ * `coalesceMessages` only merges *consecutive* same-role messages, so it
+ * cannot fix this case even if it did coalesce `system` (which it explicitly
+ * excludes below).
+ *
+ * Strict OpenAI-compatible backends (LiteLLM among them) reject any request
+ * where a `system` message is not alone at index 0:
+ * `400 A 'system' message can only appear at index 0 of the messages array.`
+ *
+ * Inline system messages may appear between complete turns, including after
+ * tool results. They may not interrupt a pending assistant tool-call/result
+ * sequence; `transformMessages` rejects that ambiguous placement before this
+ * pass. Accepted system messages are extracted in encounter order, joined with
+ * a blank line, and reinserted as the sole leading message. Everything else
+ * keeps its relative order before normal same-role coalescing.
+ */
+function hoistSystemMessages(messages: OpenAIMessage[]): OpenAIMessage[] {
+  const systemParts: string[] = [];
+  const rest: OpenAIMessage[] = [];
+
+  for (const message of messages) {
+    if (message.role !== 'system') {
+      rest.push(message);
+      continue;
+    }
+    const content = message.content;
+    const text = typeof content === 'string' ? content : '';
+    if (text.trim().length > 0) {
+      systemParts.push(text);
+    }
+  }
+
+  if (systemParts.length === 0) {
+    return rest;
+  }
+
+  return [{ role: 'system', content: systemParts.join('\n\n') }, ...rest];
+}
+
 /**
  * Coalesce consecutive messages of the same role.
  * OpenAI/vLLM/Ollama/Mistral require strict user<->assistant alternation.
@@ -741,7 +787,7 @@ export class ProxyRequestTransformer {
       // was billed. See:
       // https://platform.openai.com/docs/api-reference/chat-streaming
       ...(source.stream === true ? { stream_options: { include_usage: true } } : {}),
-      messages: coalesceMessages(allMessages),
+      messages: coalesceMessages(hoistSystemMessages(allMessages)),
       max_tokens: asNumber(source.max_tokens),
       temperature: asNumber(source.temperature),
       top_p: asNumber(source.top_p),

tests/unit/proxy/transformers/request-transformer-regressions.test.ts

@@ -321,4 +321,100 @@ describe('ProxyRequestTransformer regressions', () => {
 
     expect(result.tool_choice).toBe('auto');
   });
+
+  it('merges the top-level system field with a mid-array system message into one leading system message', () => {
+    // Claude Code sends the main system prompt via the top-level `system`
+    // field AND a skill/plugin listing as a `role: "system"` message inside
+    // `messages` (see #1459). Prepending the top-level field unconditionally
+    // used to leave two non-adjacent `system` messages in the payload, which
+    // strict OpenAI-compatible backends (LiteLLM among them) reject with:
+    // `400 A 'system' message can only appear at index 0 of the messages array.`
+    const result = new ProxyRequestTransformer().transform({
+      system: [{ type: 'text', text: 'You are Claude Code, a CLI tool.' }],
+      messages: [
+        { role: 'user', content: 'ping' },
+        {
+          role: 'system',
+          content: 'The following skills are available for use with the Skill tool:\n- foo',
+        },
+        { role: 'user', content: 'pong' },
+      ],
+    });
+
+    const systemMessages = result.messages.filter((message) => message.role === 'system');
+    expect(systemMessages).toHaveLength(1);
+    expect(result.messages[0]).toEqual({
+      role: 'system',
+      content:
+        'You are Claude Code, a CLI tool.\n\nThe following skills are available for use with the Skill tool:\n- foo',
+    });
+    expect(result.messages[1]).toEqual({ role: 'user', content: 'ping\npong' });
+  });
+
+  it('hoists a late system message after complete parallel tool results without disturbing tool order', () => {
+    const result = new ProxyRequestTransformer().transform({
+      system: 'base instructions',
+      messages: [
+        { role: 'user', content: 'inspect both files' },
+        {
+          role: 'assistant',
+          content: [
+            { type: 'tool_use', id: 'toolu_1', name: 'read', input: { path: 'a.ts' } },
+            { type: 'tool_use', id: 'toolu_2', name: 'read', input: { path: 'b.ts' } },
+          ],
+        },
+        {
+          role: 'user',
+          content: [
+            { type: 'tool_result', tool_use_id: 'toolu_1', content: 'a contents' },
+            { type: 'tool_result', tool_use_id: 'toolu_2', content: 'b contents' },
+          ],
+        },
+        { role: 'system', content: 'late instructions' },
+        { role: 'user', content: 'compare them' },
+      ],
+    });
+
+    expect(result.messages).toEqual([
+      { role: 'system', content: 'base instructions\n\nlate instructions' },
+      { role: 'user', content: 'inspect both files' },
+      {
+        role: 'assistant',
+        content: '',
+        tool_calls: [
+          {
+            id: 'toolu_1',
+            type: 'function',
+            function: { name: 'read', arguments: '{"path":"a.ts"}' },
+          },
+          {
+            id: 'toolu_2',
+            type: 'function',
+            function: { name: 'read', arguments: '{"path":"b.ts"}' },
+          },
+        ],
+      },
+      { role: 'tool', tool_call_id: 'toolu_1', content: 'a contents' },
+      { role: 'tool', tool_call_id: 'toolu_2', content: 'b contents' },
+      { role: 'user', content: 'compare them' },
+    ]);
+  });
+
+  it('rejects a system message inserted before pending tool results', () => {
+    expect(() =>
+      new ProxyRequestTransformer().transform({
+        messages: [
+          {
+            role: 'assistant',
+            content: [{ type: 'tool_use', id: 'toolu_1', name: 'read', input: { path: 'a.ts' } }],
+          },
+          { role: 'system', content: 'interrupting instructions' },
+          {
+            role: 'user',
+            content: [{ type: 'tool_result', tool_use_id: 'toolu_1', content: 'a contents' }],
+          },
+        ],
+      })
+    ).toThrow('role must be "user" with tool_result blocks after assistant tool_use');
+  });
 });

tests/unit/proxy/transformers/request-transformer.test.ts

@@ -43,7 +43,7 @@ describe('ProxyRequestTransformer', () => {
     });
   });
 
-  it('accepts Claude Code system messages in the messages array', () => {
+  it('accepts Claude Code system messages in the messages array and hoists them to a single leading system message', () => {
     const transformer = new ProxyRequestTransformer();
     const result = transformer.transform({
       messages: [
@@ -53,10 +53,14 @@ describe('ProxyRequestTransformer', () => {
       ],
     });
 
+    // Strict OpenAI-compatible backends (e.g. LiteLLM) reject any payload
+    // where `system` is not alone at index 0, so a mid-array `system`
+    // message must be hoisted rather than left in place. See #1459 for why
+    // the message must be accepted at all, and the coalesce-duplicate-system
+    // fix for why it can't simply stay where it landed.
     expect(result.messages).toEqual([
-      { role: 'user', content: 'hello' },
       { role: 'system', content: 'answer tersely' },
-      { role: 'user', content: 'which model is this?' },
+      { role: 'user', content: 'hello\nwhich model is this?' },
     ]);
   });