Search files, node content, Base records, and custom prompts with one pattern (unified grep)

Use when you need every exact occurrence of a string or regex, with line and column; for a ranked browse use search, and to find a skill or prompt for a job use playbooks search. Streaming regex/literal matches across every in-scope source — Drive/Skill files (each file match carries owner: the node it belongs to, e.g. which skill a SKILL.md hit is in, with its folder path), node content (Doc/HTML/whiteboard/workflow), Base records (canonical headCommit.payload, never the truncated search projection), and custom agent prompts (prompts: label and body in every locale; a match names nodeId, key, locale, field). Omitted sources scans all four. One shared maxMatches budget and one deadline for the whole call: each requested source gets a floor of floor(maxMatches / sources) and unused budget rolls forward, in the fixed order files → nodes → records → prompts. Per-source honest coverage (files keeps missing/stale/unsearchable/errored/notReached; nodes, records and prompts report scanned/errored/notReached). truncated is set when any source truncated or has notReached > 0 — then narrow with sources, scope.records.baseSlugs, or scope.files.drivePath rather than raising maxMatches.