Files
oh-my-pi/packages/coding-agent
roboomp a28eb0f470 perf(session): memoized convertToLlm and estimateTokens over settled history
Long sessions re-walked the full live AgentMessage[] every turn: convertToLlm
re-converted the unchanged prefix and estimateTokens re-tokenized settled tool
results and assistants, redoing work only the newest suffix can change.

- Added a per-message estimate cache in agent-core keyed by identity, with a
  settle gate (assistants cache only with real usage + terminal non-error
  stopReason; streaming partials bypass) and dual option-split WeakMaps for the
  default vs compaction-floor estimates.
- Memoized convertToLlm per message identity + assistant interruptedNext flag,
  with an exact-repeat outer-array reuse and slice-on-growth for append-only
  turns, guarded by a boundary-identity check against interior splice-replaces.
- Invalidated both caches at the mutation seams: prune, shake, strip-images, and
  the prewalk plan-nudge scrub, via invalidateMessageCache /
  registerMessageCacheInvalidator across the package boundary.
- Added the llm-assembly bench (N=5000, robust MAD-noise gate): steady/append
  convert and repeat estimate are all >10x faster with noise under 20%.

Fixes #5934
2026-07-18 02:04:09 +00:00
..
2026-07-17 21:38:00 +02:00

@oh-my-pi/pi-coding-agent

Core implementation package for the omp coding agent in the oh-my-pi monorepo.

For installation, setup, provider configuration, model roles, slash commands, and full CLI reference, see:

Package-specific references:

Memory backends

The agent supports three mutually-exclusive memory backends, selected via the memory.backend setting (Settings → Memory tab, or ~/.omp/config.yml):

  • off (default) — no memory subsystem runs.
  • local — existing rollout-summarisation pipeline; writes memory_summary.md and consolidated artifacts under the agent dir.
  • hindsight — talks to a Hindsight server (Cloud or self-hosted Docker), retains transcripts every Nth user turn, recalls memories on the first turn of a session, and exposes retain, recall, and reflect.

Hindsight quickstart

  1. Run a Hindsight server (Cloud or docker run -p 8888:8888 ghcr.io/vectorize-io/hindsight:latest).
  2. Set memory.backend = "hindsight" and hindsight.apiUrl = "http://localhost:8888" (or your Cloud URL).
  3. Optional environment overrides (env wins over settings):
    • HINDSIGHT_API_URL, HINDSIGHT_API_TOKEN — connection
    • HINDSIGHT_BANK_ID, HINDSIGHT_DYNAMIC_BANK_ID, HINDSIGHT_AGENT_NAME — bank addressing
    • HINDSIGHT_AUTO_RECALL, HINDSIGHT_AUTO_RETAIN, HINDSIGHT_RETAIN_MODE — lifecycle
    • HINDSIGHT_RECALL_BUDGET, HINDSIGHT_RECALL_MAX_TOKENS — recall sizing
    • HINDSIGHT_BANK_MISSION, HINDSIGHT_DEBUG

Switching backends mid-session is honoured on the next system-prompt rebuild and the next /memory slash command. Existing users with memories.enabled = true|false are migrated to memory.backend = "local"|"off" exactly once on first launch.