OpenAI's export changed: conversations.json is now sharded into
conversations-000.json..NNN.json, each a JSON array of conversations with the
mapping tree and per-message create_time.
ingest now reads that format directly (supersedes the old convert/trim/split
scripts): walks each conversation's mapping ordered by create_time, keeps text
and multimodal_text (drops thoughts/reasoning_recap), captures real per-message
timestamps, and imports idempotently by conversation_id. `lyra-import <dir>`
auto-detects raw-export vs legacy {title,messages} dirs; optional limit arg.
Verified on 15 conversations: real dates, correct ordering, recall returns
dated poker history.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Import the parser's {title, messages} JSON into Lyra's memory so past
conversations seed recall (and, later, the era-rollup tier).
- lyra/ingest.py: one conversation -> one session, text messages -> exchanges;
skips non-text (image asset) messages and non user/assistant roles; embeddings
batched; idempotent by filename-derived session id; `lyra-import <dir>` CLI
- memory.add_exchanges_bulk: batched insert of pre-embedded rows
Format has no timestamps yet, so imports are stamped at import time; a future
dated export will let era memory group by real calendar time.
Verified on the 68-file lyra dev set: 7519 exchanges, idempotent re-run, recall
returns relevant history.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
serversdown