Files

T

roboomp c5c95ecd12 fix(tui): suppressed empty assistant token badges

Suppress token-usage rows for assistant turns that have no visible text, tool call, or terminal error anchor. Share the same decision across live rendering and transcript rebuilds so resume matches live output.

Fixes #4532

2026-07-04 16:40:09 +00:00

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(plugins): drain subprocess pipes concurrently with proc.exited

2026-07-02 08:33:32 +00:00

src

fix(tui): suppressed empty assistant token badges

2026-07-04 16:40:09 +00:00

test

test(coding-agent): updated job poll displacement tests to use TranscriptContainer

2026-07-04 14:48:41 +02:00

CHANGELOG.md

fix(tui): suppressed empty assistant token badges

2026-07-04 16:40:09 +00:00

DEVELOPMENT.md

feat: consolidated and automate changelog management

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

package.json

chore: bump version to 16.3.6

2026-07-04 14:00:53 +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.