Files

T

roboomp d256367b72 fix(agent): name billed output tokens on capped empty stops

An empty assistant `stop` that exhausts the retry cap always reported the
context/`/shake images` hint, even when the provider billed output tokens
for the turn. Billed output on a zero-block stop means content was generated
and then dropped downstream (a filter/refusal flattened to
`finish_reason: "stop"` by a proxy, or a lossy API translation), so the
images/context advice is actively misleading there.

Branch the capped `finalError` in `#handleEmptyAssistantStop` on
`assistantMessage.usage.output`: keep the context hint when nothing was
generated, and otherwise name the billed output-token count and point at a
provider-side filter/translation. Also log `outputTokens` alongside the
existing warning fields.

Fixes #8511

2026-08-14 04:51:06 +00:00

bench

feat: introduced omptype validation package and migrated workspace dependencies

2026-08-03 21:56:48 +02:00

examples

Merge PR #7735 : fix(coding-agent): return ToolInfo[] from getAllTools extension API (@roboomp)

2026-08-05 22:15:46 +02:00

scripts

feat: introduced nix packaging and path-based binary resolution

2026-08-13 03:52:47 +02:00

src

fix(agent): name billed output tokens on capped empty stops

2026-08-14 04:51:06 +00:00

test

fix(agent): name billed output tokens on capped empty stops

2026-08-14 04:51:06 +00:00

CHANGELOG.md

fix(agent): name billed output tokens on capped empty stops

2026-08-14 04:51:06 +00:00

DEVELOPMENT.md

…

package.json

chore: bump version to 17.3.3

2026-08-14 05:44:05 +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.