ワンクリックで
recall
Thin Codex skill shim for node_recall_compute. Use when querying OmniNode runtime knowledge through the event bus.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Thin Codex skill shim for node_recall_compute. Use when querying OmniNode runtime knowledge through the event bus.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Thin Codex skill shim for node_ticket_pipeline. Use to run the bounded per-ticket pipeline slice through the OmniMarket runtime adapter.
Thin Codex skill shim for node_adversarial_pipeline_orchestrator. Use when running the adversarial plan-to-ticket pipeline through runtime truth.
Thin Codex skill shim for node_dep_cascade_dedup_orchestrator. Use when deduplicating dependency bump PR cascades through runtime truth.
Thin Codex skill shim for node_observability_sink_effect. Use when persisting OmniNode observability events through runtime adapters.
Thin Codex skill shim for node_bus_audit_compute. Use when auditing OmniNode event-bus topic registry and contract wiring health.
Thin Codex skill shim for node_gap_compute. Use when running OmniNode integration gap detection, report classification, or gap-cycle preflight.
| name | recall |
| description | Thin Codex skill shim for node_recall_compute. Use when querying OmniNode runtime knowledge through the event bus. |
This skill is a thin Codex runtime adapter shim over the OmniMarket
node_recall_compute node. The node owns backend federation and source
attribution. Do not add localhost HTTP calls, direct search clients, handler
imports, or retrieval fallbacks to this skill.
| Argument | Description | Default |
|---|---|---|
query | Free-text knowledge query | Required |
scope | learnings, architecture, antipatterns, or all | all |
filters | Optional object containing repo and/or task_type | Omitted |
max_results | Maximum results per backend | 5 |
target_runtime_address | Optional runtime://... runtime target | Uses ONEX_TARGET_RUNTIME_ADDRESS when set |
Run from the omnimarket repo or an omnimarket worktree:
env -u PYTHONPATH uv run python scripts/run_codex_runtime_request.py \
--command-name "recall_compute" \
--payload '<json-payload>' \
--timeout-ms 15000
If the user supplies a runtime://... target, add
--target-runtime-address '<runtime-address>' to the request command. If the
argument is omitted, the wrapper uses ONEX_TARGET_RUNTIME_ADDRESS when set.
For event-bus-free preflight, add --compile-only. This validates the payload,
command topic, response topic, correlation id, timeout, and target runtime
address without publishing to Kafka or starting a runtime.
Map user inputs into a JSON payload using the same field names:
queryscopefiltersmax_resultsIf ok is true and output_payloads is present, treat output_payloads[0]
as the primary node result.
If ok is false, surface error.code and error.message directly. A
node_not_implemented response is the current explicit stop state, not
permission to call a legacy localhost service.
src/omnimarket/nodes/node_recall_compute/scripts/run_codex_runtime_request.pyrecall_computeonex.cmd.omnimarket.recall-start.v1onex.evt.omnimarket.recall-completed.v1Prefer output_payloads[0]. Render confidence, sources, partial, and a
ranked result summary. All retrieval behavior is owned by node_recall_compute.