honcho/docs/v3/documentation/features
Eugene Eisenstein 451a864096 refactor(dialectic): drop message content from evidence
Evidence carried the first 200 characters of every message the agent read.
Remove it: messages now report identity and provenance only.

Message content is caller-supplied and unbounded -- up to MAX_MESSAGE_SIZE,
25k characters -- and a single answer can touch a few hundred messages across
its search, grep and date-range tools. Carrying even a slice of each invites
callers to read messages in bulk out of evidence rather than fetching the ones
they want, which is the opposite of what this is for: evidence is an audit and
analytics surface, not a read API and not something to sit in a hot path.

Conclusions keep their text, which is the asymmetry worth stating. A
conclusion is written by the deriver, is short, and is the thing being
audited; a message is raw input that already has endpoints of its own.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-03 16:43:39 -04:00
..
advanced refactor(dialectic): drop message content from evidence 2026-09-03 16:43:39 -04:00
chat.mdx feat(dialectic): return the evidence a chat answer was built from 2026-09-03 13:19:10 -04:00
get-context.mdx chore(docs): Add Documentation for Scopes (#1086) 2026-08-27 15:21:10 -04:00
storing-data.mdx Abigail/dev 1406 (#416) 2026-03-06 23:21:28 -05:00