Files

T

can1357 375d100555 feat(model-registry): added proxy discovery type for mixed Anthropic/OpenAI proxies

- Added `discovery.type: proxy` that hits `GET /v1/models` and routes each model via `supported_endpoint_types` (`anthropic` → `/v1/messages`, `openai` → `/v1/chat/completions`).
- Made provider-level `api` optional when `discovery.type` is `proxy`, since wire protocol is derived per-model.
- Increased discovery fetch timeout from 250ms to 10s to accommodate remote proxies.
- Documented proxy discovery configuration in `docs/models.md`.

2026-05-30 03:53:36 +02:00

bench

perf(coding-agent): dedupe buildSessionContext walk on session-tree navigation

2026-04-27 03:55:14 +00:00

examples

fix(read): fixed column truncation mutating snapshot with display content

2026-05-29 06:42:46 +02:00

scripts

fix(cli): routed legacy pi-coding-agent imports through a sibling shim

2026-05-29 06:42:46 +02:00

src

feat(model-registry): added proxy discovery type for mixed Anthropic/OpenAI proxies

2026-05-30 03:53:36 +02:00

test

fix(session): extended dangling tool_use stripping to all mid-path assistant turns

2026-05-30 03:52:55 +02:00

.gitignore

refactor: extract local:// URL normalization to shared utility

2026-04-18 22:40:07 +02:00

CHANGELOG.md

fix(session): extended dangling tool_use stripping to all mid-path assistant turns

2026-05-30 03:52:55 +02:00

DEVELOPMENT.md

feat(coding-agent): added resolve-based plan approval flow in coding-agent

2026-05-14 05:33:30 +02:00

package.json

chore: bump version to 15.5.14

2026-05-30 01:25:28 +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.