6 Commits

Include renames

Author	SHA1	Message	Date
m1saka	ecdf0c44d1	Fix upstream 400: flatten multi-part content arrays and sanitize invalid tool_calls ... The Zhanlu upstream gateway returns HTTP 400 (请求消息格式错误) for two message-structure issues that AI coding tools like MiMoCode produce: 1. Multi-part content arrays — OpenAI SDKs send content as [{type:"text",text:"…"}] arrays; the gateway only accepts string content. normalizeMessages now flattens text-only arrays into a concatenated string (non-text parts like images are preserved). 2. Invalid tool_calls — when a tool call fails, MiMoCode emits {name:"invalid", arguments:{"tool":"task","error":"…"}} placeholders. The gateway rejects function names not in the tools list and non-object arguments (e.g. "-1"). normalizeMessages now sanitizes these in place: the real tool name is extracted from the arguments' "tool" field (falling back to an arbitrary declared tool), and non-JSON-object arguments are replaced with "{}". No messages or tool results are removed, preserving the full conversation context including error feedback. Verified with the exact error.md request: 0/10 400 errors after fix (vs 10/10 before). Model returns valid streaming responses with task tool calls.	2026-08-23 22:16:32 +08:00
m1saka	f988c47fec	Fix silent data loss in function_call arguments/output non-string JSON parsing ... responsesInputToMessages unmarshaled function_call.arguments and function_call_output.output as bare strings, silently dropping the value when it arrived as an object or content-parts array. This caused the model to lose tool-call context in multi-turn conversations, increasing the likelihood of malformed tool-call JSON. Add rawJSONToString (re-encodes non-string values as JSON strings) and outputToString (extracts text from content-parts arrays, re-encodes other non-string values). Add 3 regression tests covering object arguments, array output, and object output.	2026-08-23 14:15:01 +08:00
m1saka	b9a3f8d5cd	Mirror Zhanlu client: GLM tool_stream, shared v4 UUID request id, drop chat state:ERROR	2026-08-21 14:27:37 +08:00
m1saka	2517b4f730	Add OpenAI Responses API (/v1/responses) endpoint ... Translate Responses API requests (input→messages, instructions→system, max_output_tokens→max_tokens, text.format→response_format, flat tools→nested {function:{…}}) to upstream chat/completions, then convert responses back to Responses format (streaming SSE event lifecycle + non-streaming JSON). Verified against OpenAI migration guide and Python SDK Response model: - Echo back required fields parallel_tool_calls/tool_choice/tools - Include content:[] in reasoning items, logprobs:[] in output_text parts - Support function_call/function_call_output multi-turn input items - Map usage fields prompt_tokens→input_tokens, completion_tokens→output_tokens	2026-08-20 10:02:11 +08:00
m1saka	7d8a5b6f74	Update proxy to Zhanlu v1.4.2 provider flow ... The 1.4.2 extension replaced the old signed/encrypted chat gateway with an OpenAI-compatible aigateway. Align the proxy with the new flow: - Use ecloud.10086.cn login/model base URLs, zhanlu_ide plugin headers and v1.4.2 plugin version - Provision the model API key via SM2-signed get-or-create after v1/login profile fetch; store api_key/model_base_url/email in credentials - Chat via Bearer apiKey against {modelBaseUrl}/chat/completions with plain OpenAI SSE passthrough; fetch /v1/models from the gateway model-info endpoint - Force HTTP/1.1 upstream (gateway drops HTTP/2 ALPN negotiation with EOF) - Drop obsolete AES body encryption, model name mapping and vscode headers	2026-08-05 14:55:28 +08:00
M1saka	d4dd3a0f1b	Initial zhanlu OpenAI proxy	2026-07-08 09:13:45 +08:00