Files

T

can1357 ef126fd0f6 fix(ai): fixed Google empty STOP retries to emit a single stream start event

- Added shared Google empty-stream retry constants and reused them in CLI.
- Replaced local content checks with hasMeaningfulGoogleContent for retry gating.
- Refactored streamGoogleGenAI to bound empty STOP retries with state reset and reopen.
- Moved stream start emission before retry loops to avoid duplicate start events.

2026-06-13 16:58:04 +02:00

bench

perf(coding-agent): defer boot work and cut streaming/read CPU

2026-06-09 18:58:22 +09:00

examples

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

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

scripts

feat(coding-agent): sealed /share behind encrypted links and embedded subagent transcripts in exports

2026-06-12 15:00:41 +02:00

src

fix(coding-agent): switched startup model checks to configured auth validation

2026-06-13 16:52:23 +02:00

test

fix(coding-agent): switched startup model checks to configured auth validation

2026-06-13 16:52:23 +02:00

CHANGELOG.md

fix(ai): fixed Google empty STOP retries to emit a single stream start event

2026-06-13 16:58:04 +02:00

DEVELOPMENT.md

chore(coding-agent): composed HTML export template at runtime instead of committing generated artifacts

2026-06-12 15:00:16 +02:00

package.json

chore: bump version to 15.12.3

2026-06-12 18:13:09 +02:00

README.md

docs: clarify RenderMermaid usage

2026-05-09 03:11:18 +02:00

tsconfig.examples.json

refactor: restructured monorepo TypeScript config and build tasks for unified setup

2026-04-08 17:05:20 +02:00

tsconfig.json

refactor: restructured monorepo TypeScript config and build tasks for unified setup

2026-04-08 17:05:20 +02:00

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.