Full-panel export

GET /v1/research/{run_id}/responses/export returns every stored model response in one request. The body is UTF-8 JSONL: one JSON object per line, not a JSON array.

curl -fS -H "Authorization: Bearer $SENECA_API_KEY" \
  "https://seneca-research.fly.dev/v1/research/$RUN_ID/responses/export" \
  -o seneca-responses.jsonl

Each line has model_id, display_name, laboratory, status, input_tokens, output_tokens, and text. text is the complete stored response, or null when that model stored none. The single-model 32000-character window does not apply. Error and timeout rows are included. A retired model keeps the id saved on the run. The response sets Content-Disposition: attachment; filename="seneca-{run_id}-responses.jsonl". Authorization and readiness match the single-model read, and they are decided before the stream starts.

HTTP	Code	When
409	`responses_not_ready`	The run is still `queued`, `running`, or `synthesizing`
409	`research_failed`	The run failed
404	`run_not_found`	The run belongs to another workspace, or it does not exist

The download does not start research, call a provider, or reserve credits.

Save the file for your own storage and analysis. Do not load every model response into an AI agent’s context. To inspect one finding, use the single-model read.

Getting started

Research

Operations

Full-panel export