Impact Analysis
Use the eight-tool core profile. Treat graph results as a lower bound wherever the tool reports heuristic resolution, dynamic dispatch, or coverage gaps.
For Rust caller or impact questions, request lsp: true in analyze_codebase
and make rust-analyzer available. Inspect lsp_status.state: disabled means
static-only analysis; failed means analysis continued and may retain partial
LSP results. Record the error and treat affected conclusions as unverified until
source checks or a successful rerun support them. completed means the pass
returned, not that every call resolved. Record unresolved sites and coverage gaps.
If a full-profile workflow supplies a check_security_gates receipt, inspect
both gates_passed and assessment_complete. A true pass with an incomplete
assessment is not security clearance: report skipped checks, unresolved symbols
and warnings. This core-profile workflow does not invoke that additional tool.
Workflow
- Call
health_check. Build or refresh the graph withanalyze_codebase, and keep the exact returnedgraph_path. - If an actual unified diff or base/head refs exist, call
detect_changes. Do not invent a diff for a proposal that has not been implemented. - Use
search_codebaseto resolve every proposed or changed symbol to an exact qualified name. Confirm important targets withget_symbolorget_context. - Call
get_impactfor each target. Page callers throughnext_offset. Treat importers, users, and implementors as capped summaries; usequery_graphwith an explicitORDER BYwhen a complete paged list matters. - Call
query_graphwithgraph="missed". Inspect flagged ranges and search relevant source, including unflagged files, even when no gaps are flagged before making a negative claim about callers, dependencies, or test coverage. Clean parsing can still miss relationships. - Follow high-risk dependents with
get_contextorget_symbol. Use sibling graphs only when the user supplies or authorizes those graph paths.
Deliverable
Separate direct graph evidence from inference. Report affected symbols, callers and dependency types, communities, graph-derived processes, co-change hints, coverage gaps, and unverified risks. Preserve the tool's epistemic qualifier instead of upgrading a lower-bound result into a completeness claim.