bearing-enforcementlisted

# GitNexus Enforcement & Tool Router <!-- BEGIN GENERATED: graph-uncertainty — bearing regenerates this block; edits here are replaced on update --> ## The graph can be wrong A zero is not absence; a near-0.5 `r.confidence` edge is a lead, not proof (~92% of `USES`); a count can be a floor — `impact` says which in `epistemic`. Before a conclusion that matters, confirm with a scoped `Grep` (allowed here, not a gate violation) and say which check you ran. <!-- END GENERATED: graph-uncertainty --> ## Decision tree (follow in order) ``` START �� ├─ New session / new task? │ └─ npm run bearing:agent-brief OR READ context + schema (autonomous) │ stale or missing embeddings? → npm run bearing:agent-refresh (Shell, required_permissions: ["all"]) │ ├─ Reasoning about code (any point in task)? │ └─ query({search_query, task_context, goal, repo}) # graph + embeddings │ └─ context({name}) or context({uid}) │ └─ Structural precision needed? │ ├─ known A→B path → trace({from, to}) │ ├─ control/data flow → pdg_query({mode: "controls"|"flows"}) │ ├─ field read/write → pdg_query flows OR cypher ACCESSES │ ├─ fuzzy N-hop call chain → cypher CALLS path │ ├─ overrides / process steps → cypher (see schema) │ └─ READ process trace if cross-module │ └─ impact when considering edits │