Files

T

Diogo Soares Rodrigues 6d42f6e52e fix(cursor): read pi_ls's entry cap from the shape read actually sets

The bridge looked for a flat `details.resultLimitReached`. `glob` sets
that alongside the structured meta, so `pi_find` worked; `read` - the
tool serving `pi_ls` - records the cap only through `OutputMeta`, at
`details.meta.limits.resultLimit.reached`. Every capped listing
therefore reached Cursor with `entry_limit_reached` unset, which reads
as a complete listing.

Both shapes are now checked, mirroring how `piTruncation` already
handles its two producers. Covered by running the real `ReadTool`
against a directory that trips the per-directory cap and asserting the
wire field, so a move in the producer's shape fails here instead of
silently sending clipped output as whole.

(cherry picked from commit cbfe7ca9d59faa2f967e2724744b58a96a9a1839)

2026-07-30 01:42:29 +02:00

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

fix(coding-agent): package lazy HTML export assets

2026-07-28 02:45:16 +00:00

src

fix(cursor): route MCP resource frames and gate native delete

2026-07-30 01:42:28 +02:00

test

fix(cursor): read pi_ls's entry cap from the shape read actually sets

2026-07-30 01:42:29 +02:00

CHANGELOG.md

fix(cursor): read pi_ls's entry cap from the shape read actually sets

2026-07-30 01:42:29 +02:00

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 17.1.8

2026-07-28 14:10:19 +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.