Files

T

can1357 4e12e5bf76 fix(extensibility): read lazy graph modules from disk at import time

The consume-once source map kept entries for graph modules the initial
import never loaded (modules only reached via lazy dynamic imports).
Their first import - possibly long after load, and after an on-disk
edit - was served the boot-time snapshot instead of current file
content, and the unconsumed sources stayed in the plugin closure for
the process lifetime.

Clear the map once the entry import settles: everything Bun loaded at
startup was already consumed (keeping the read-once win), and anything
left must be read at its actual import time, matching pre-dedup
behavior for lazy modules. The new regression test passes on the
pre-dedup baseline and fails on the unfixed dedup.

2026-07-02 10:29:57 +02:00

bench

fix(coding-agent): wire reveal bench callbacks correctly

2026-07-01 21:47:54 +02:00

examples

feat: added standalone snapcompact package and model-specific frame shaping

2026-06-10 21:50:03 +02:00

scripts

fix(coding-agent): kept docs embed populated for bun pm pack

2026-07-01 00:25:24 +00:00

src

fix(extensibility): read lazy graph modules from disk at import time

2026-07-02 10:29:57 +02:00

test

fix(extensibility): read lazy graph modules from disk at import time

2026-07-02 10:29:57 +02:00

CHANGELOG.md

merge PR #4205 : perf(extensibility): read extension source graph once per load (@metaphorics)

2026-07-02 10:29:57 +02:00

DEVELOPMENT.md

feat: consolidated and automate changelog management

2026-06-27 03:08:52 +02:00

package.json

chore: bump version to 16.3.1

2026-07-02 09:00:04 +02:00

README.md

feat: removed render_mermaid tool and added width-aware Mermaid clipping

2026-06-16 21:32:39 +02:00

tsconfig.examples.json

…

tsconfig.json

…

tsconfig.publish.json

chore(config): organized publish type mapping from src to dist/types

2026-05-15 23:46:23 +02:00

README.md

@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

Run a Hindsight server (Cloud or docker run -p 8888:8888 ghcr.io/vectorize-io/hindsight:latest).
Set memory.backend = "hindsight" and hindsight.apiUrl = "http://localhost:8888" (or your Cloud URL).
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.