Bot import: one folder per account, run records with steps

- the importer reads data/accounts/*/runs.jsonl and logs/accounts/*/encounters.jsonl;
  with account folders, the top-level files (a mirror of the first account) are skipped
- run records that carry their steps (schema 2) become trajectories directly, keeping
  what the bot saw (shadow, meadow dragons), propensities, decision mode and policy id;
  older runs are still rebuilt from the decision log; bonded runs without steps are kept
- account names become salted hashes (DK_ACCOUNT_SALT, or a private salt in data/raw)
- runs_clean.csv: new bot_mode column; saw_shadow and saw_blue_meadow from what the bot
  saw; deliberate burns say why
- crosswalk: the valley Red, leaving squadmates, squad direction, hold your ground,
  hide/approach reactions, the wounded cadet's other two choices

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UCzTd31GphpMXDhQqWrCMQ
This commit is contained in:
ekcSchiano
2026-11-10 02:08:57 +00:00
co-authored by Claude Opus 5.5
parent dd25dfaa32
commit 43066ad67f
13 changed files with 6292 additions and 6051 deletions
+7 -2
View File
@@ -15,8 +15,13 @@ When GitHub Pages is not available, the same files travel as zips:
- **Atlas → bot:** `python -m collection export-bot-kit` writes `exports/atlas-for-bot-<date>-<policy id>.zip`
(`policy.json`, `solver.js`, `graph.js`, a README with checksums). Unzip it into the bot's `vendor/threshing-atlas/`.
- **Bot → atlas:** zip the bot's `data/runs.jsonl`, `data/knowledge.json` and `logs/encounters.jsonl` (folder names
kept; a zip of the whole repo works too) and send it. Put it in the atlas's `inbox/` and run
- **Bot → atlas:** zip the bot's `data/` and `logs/` folders (folder names kept; a zip of the whole repo works too;
screenshots are not needed) and send it. The importer reads `data/knowledge.json` and, for every account,
`data/accounts/<account>/runs.jsonl` and `logs/accounts/<account>/encounters.jsonl` (with one folder per
account, the top-level `data/runs.jsonl` and `logs/encounters.jsonl` mirror the first account and are skipped).
Run records that carry their own steps (the bot's schema 2) are used as they are, including what the bot saw
(shadow, meadow dragons), its decision mode and the policy id; older runs are rebuilt from the decision log.
Account names become salted hashes. Put it in the atlas's `inbox/` and run
`python -m collection refresh --bot inbox/<the zip>`: it imports the runs (anonymised: no prose, no account names),
rebuilds everything, and then `export-bot-kit` makes the new zip to send back.