Skip to content

feat(memory): add durable conversation memory - #3

Merged
hochmannA1 merged 1 commit into
mainfrom
feat/chat-memory
Sep 4, 2026
Merged

hochmannA1 merged 1 commit into
mainfrom
feat/chat-memory

Conversation

@hochmannA1

Copy link
Copy Markdown
Owner

T3 Code currently loses useful preferences, decisions, project facts, and failure lessons when a conversation ends. This adds server-owned memory that is enabled by default, recalls a bounded relevant context on later turns, and remains available across web, desktop, mobile, remote connections, and server restarts.

On first use, the server reviews existing completed conversations from oldest to newest, including archived and settled conversations, with one bounded transcript per chat. Its queue, cursor, retries, quarantined failures, and processing lease live in SQLite; generated note bodies use content-addressed Markdown files under T3 home. Daily consolidation and a deeper weekly review run when the environment is idle, with overdue work resuming after a stopped server starts again. The dedicated memory model is configurable and defaults to Codex gpt-5.6-luna.

Recall is injected at the shared provider boundary and exposed through scoped memory_search, memory_read, memory_remember, and memory_forget tools. Codex, Claude, and OpenCode run unattended generation in isolated no-tool sessions; unsupported providers fail explicitly. Settings expose environment and conversation controls on web/desktop and mobile.

Fork migrations now use Fork_NNN_* names and an independent effect_sql_fork_migrations ledger. A compatibility bridge adopts the known earlier fork migration IDs without consuming later upstream IDs.

Validation:

  • 405 focused server, migration, contract, shared, client runtime, and web tests
  • 191 focused provider-process and server-socket tests
  • server, contracts, web, client runtime, and mobile typechecks
  • targeted lint with warnings denied
  • first-run regression covering 70 historical chats, 64-item pagination, restart recovery, archive inclusion, bounded compaction, poison-source quarantine/retry, and oldest-first order

Implemented with GPT-5.6 Sol in Codex.

@github-actions github-actions Bot added size:XXL vouch:trusted PR author is trusted by repo permissions or the VOUCHED list. labels Sep 4, 2026
@hochmannA1
hochmannA1 merged commit 96b5b6f into main Sep 4, 2026
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:XXL vouch:trusted PR author is trusted by repo permissions or the VOUCHED list.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant