Target Shape Tactic Routing Gate
Records an allow-or-reject decision and reason for each proof tactic before any proof runs.
Contract
Does Before a proof is attempted, this component checks a list of candidate proof tactics for a given goal and writes down an allow-or-reject decision, with a plain reason, for each one. Rejections fall into three kinds: the tactic isn't actually available in the declared environment, it was never listed in the environment's tested set of tactics, or it simply doesn't fit the kind of goal being proved. The resulting record shows, tactic by tactic, exactly what was admitted or blocked and why, instead of an opaque "we tried these" claim. It only inspects and records the routing decision over references that already exist; it never runs a prover or proves anything itself.
Scope limit It only inspects and records the projection mechanics of pre-execution tactic-routing references — emitting per-tactic allow/reject decisions with reasons. It does not run Lean/Lake, does not establish or judge the correctness of any goal, emits no proof bodies, makes no external model access, performs no post-execution route selection, reports no benchmark claims or maturity, and excludes launch.
Run
PYTHONPATH=src python3 -m microcosm_core.cli target-shape-tactic-routing-gate run-routing-bundle --input examples/target_shape_tactic_routing_gate/exported_target_shape_tactic_routing_bundle --out receipts/runtime_shell/demo_project/organs/target_shape_tactic_routing_gate
Evidence
ClassComputed projectionevidence 3/5Source-faithful refactor
Links to Formal Math Verifier Trace Repair Loop, Formal Evidence Cell Anchor Resolver, Proof Diagnostic Evidence Spine, Tactic Portfolio Availability Probe, Verifier Lab Kernel
Source
Paper module
Paper module Target Shape Tactic Routing