Files

T

roboomp df3018e89b fix(coding-agent): source auth-gateway catalog from ModelRegistry

runServe built /v1/models and the resolveModel behind /v1/chat/completions from getBundledModels only, freezing the gateway catalog on the compiled-in snapshot. Every discovery-only model omp itself reaches (ids released after the build date) was unroutable through the gateway while the same broker credential answered it in the TUI.

Source the catalog from ModelRegistry (bundled + cached + discovered) like every other omp surface, via a shared indexModelsByRequestId helper that preserves the credential scoping and qualified/bare-id registration. Rebuild it every 15m so a long-lived serve tracks newly discovered models without a restart; a failed refresh keeps serving the previous catalog.

Fixes #6615

2026-07-25 13:22:32 +00:00

bench

Merge PR #5947 : perf(session): memoize convertToLlm and estimateTokens over settled history (@roboomp)

2026-07-18 19:42:52 +02:00

examples

refactor(coding-agent): consolidated tool surface onto xd:// devices and hub

2026-07-15 15:16:29 +02:00

scripts

Merge PR #6349 : support light, dark, and system themes in HTML exports (@anatoli-tsinovoy)

2026-07-23 17:30:32 +02:00

src

fix(coding-agent): source auth-gateway catalog from ModelRegistry

2026-07-25 13:22:32 +00:00

test

Merge PR #6529 : fix(coding-agent): guard retain renderer streaming args (@roboomp)

2026-07-25 00:59:14 +02:00

CHANGELOG.md

fix(coding-agent): source auth-gateway catalog from ModelRegistry

2026-07-25 13:22:32 +00:00

DEVELOPMENT.md

feat(coding-agent): added opt-in task prewalk and tightened --tools and xdev behavior

2026-07-15 18:39:36 +02:00

package.json

chore: bump version to 17.1.3

2026-07-25 01:10:32 +02:00

README.md

fix(memory): synchronized live backend lifecycle

2026-07-23 19:52:09 +00:00

tsconfig.examples.json

…

tsconfig.json

…

tsconfig.publish.json

…

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 immediately replaces the live backend, memory tools, listeners, and system-prompt context. Existing users with memories.enabled = true|false are migrated to memory.backend = "local"|"off" exactly once on first launch; afterward, memory.backend is the sole runtime selector.