metaphorics
0d23cb75c2
Plan-mode convergence (call `ask` or `resolve`) was enforced on only the non-synthetic `prompt()` return. Every other turn-ending path — `agent.continue()` drains, the IRC idle wake, and advisor steer delivery — settles via `agent_end` and bypassed it, so advisor/IRC/follow-on traffic could keep the agent producing non-converging turns indefinitely (the prompt() recovery wait never returns while continuations run, and agent-core re-drains late steering/asides before agent_end). Suppress non-user producers in plan mode: `#routeAdvice` preserves the advisor card (visible + persisted, no turn) and the idle IRC paths (`deliverIrcMessage`, `#resumeStrandedIrcAsides`) record into context without waking a turn. User steers/follow-ups are untouched and still resume planning. Enforce the decision at the universal `agent_end` terminal settle via a bounded-retry counter: a plan-mode turn that stops without `ask`/`resolve` gets the reminder plus a provider-neutral `required` choice (both tools stay available), up to a fixed cap, then yields to the user. A non-decision tool answer (e.g. `read`) does not reset the cap, so it cannot loop or silently end plan mode un-converged; `ask`/`resolve`, a fresh user prompt, or plan-mode exit reset the counter. Todo-completion reminders are gated off in plan mode so they cannot re-wake a turn the cap intends to yield. Removes the now-redundant post-`prompt()` enforcement to keep a single policy. Op: correct Restores: spec:plan-mode turns must converge to ask/resolve or yield after bounded reminders
@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; writesmemory_summary.mdand 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 exposesretain,recall, andreflect.
Hindsight quickstart
- Run a Hindsight server (Cloud or
docker run -p 8888:8888 ghcr.io/vectorize-io/hindsight:latest). - Set
memory.backend = "hindsight"andhindsight.apiUrl = "http://localhost:8888"(or your Cloud URL). - Optional environment overrides (env wins over settings):
HINDSIGHT_API_URL,HINDSIGHT_API_TOKEN— connectionHINDSIGHT_BANK_ID,HINDSIGHT_DYNAMIC_BANK_ID,HINDSIGHT_AGENT_NAME— bank addressingHINDSIGHT_AUTO_RECALL,HINDSIGHT_AUTO_RETAIN,HINDSIGHT_RETAIN_MODE— lifecycleHINDSIGHT_RECALL_BUDGET,HINDSIGHT_RECALL_MAX_TOKENS— recall sizingHINDSIGHT_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.