Import traces from a JSONL upload (deprecated path — use /traces/import)

Upload and parse a JSONL file. Supports two formats: 1. Chat messages: {"messages": [{"role": "...", "content": "..."}]} 2. Instruction pairs: {"input": "...", "output": "..."} Each line becomes a trace with source_type="manual". **Optional per-row fields.** Any row of either format may also carry the components that turn actually used: - `model` — the model name, e.g. `"gpt-4o"`. Omitted, the trace records the placeholder `"imported"`. - `tools` (or `tool_calls`) — the tools that turn called, either as plain names (`["search_docs"]`) or as the provider's own tool-call objects (`[{"function": {"name": "search_docs", "arguments": "{}"}}]`). - `system` — the system prompt that turn ran under. The chat-messages format can also carry it as a `{"role": "system"}` message, which wins. - `agent_name` — per-row override of the `agent_name` form field, so one file can hold traces for several agents. Supply them and the imported trace is scored against manifest changes like a live one: removing a tool it called moves it out of `keep` in the impact report. Omit them and only `model` is recorded, as the placeholder — the trace imports, but a manifest diff cannot tell whether it was affected. ```jsonl {"agent_name": "support-bot", "model": "gpt-4o", "tools": ["search_docs"], "system": "You are a support agent.", "messages": [{"role": "user", "content": "where is my order?"}, {"role": "assistant", "content": "Let me check."}]} {"agent_name": "support-bot", "input": "refund policy?", "output": "30 days."} ```