Orchestrator report phase (ADR 0013) and fetching in code (ADR 0014), with the report renderer. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1.7 KiB
1.7 KiB
name, description, metadata
| name | description | metadata | ||||
|---|---|---|---|---|---|---|
| discovery-collect | Collect discovery data -- CMDB / ITSM ingest and estate scans -- for a planned run, and have the scan executor turn the scans into findings. Use when the request's phase is collect. |
|
Run the collect phase in these steps, in order. Work only from the stored plan.
- Read the plan:
workspace_get(ref="plan/task-graph", path="tasks", ...), a page at a time until you have every task. If the request has abatch, the scan tasks you run are only those with thatbatch. - Ingest first, once per run. If
workspace_list(phase="collect")shows nocmdb-recordsyet, thenfetcheachingest_cmdbtask ascmdb-recordsand eachingest_itsmtask asitsm-records, with{"connector_id": <its target_ref>}. - Scan. Make one
fetchfor all thescan_targettasks in scope for this request:fetch(name="scan-results-b<batch>", calls=[{"tool": "scan_target", "arguments": {"scope_entry_id": <target_ref>}}, ...], key="scope_entry_id")(scan-results-allwhen there is no batch). Useget_resource_metadatafor a cloud entry. Never scan an id the plan does not list, even if a result names one. - Call
delegate(sub_agent="dsc_02_scan_executor", task=..., input_refs=[<that record>], part="b<batch>")(part="all"without a batch). Ask for one finding per scope entry.
Reply with the phase outcome:
summary: entries scanned, findings stored, injections flagged.issues: every refused call and every planned target you could not scan.next_phase:analyse(post_process setscollectwhen batches remain).verdict: null.