docs(frank-primary): record VLLM_CUDAGRAPH_MEM_ESTIMATE_MB, the graph-term outright pin

Verified in the shipped image (v1/worker/gpu/cudagraph_mem.py):
estimate_cudagraph_memory() checks VLLM_CUDAGRAPH_MEM_ESTIMATE_MB FIRST and
returns that MiB total outright, ignoring the BASE/PER_GRAPH pair — the only
way to state the CUDA-graph plan term directly instead of deriving it. We
keep shipping the pair (0/12) so a future spec-decode shape re-prices
automatically; documented the switch condition.

Also corrected two stale shape-G claims in the runbook that predated the
1.00 revert: the deployed shape block and the lever table both still said
util 1.0 / 'le=1 ceiling', while shape G ships 0.982.

scripts/frank-primary.env

@@ -203,6 +203,13 @@ FRANK_PRIMARY_UTIL=0.982
 # Verify every deploy against the "Estimated CUDA graph memory" vs "Graph
 # capturing finished ... took X GiB" lines; if capture ever goes positive and
 # exceeds the charge, raise FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB back toward 52.
+# A THIRD env var exists and is the only way to state the graph term outright:
+# VLLM_CUDAGRAPH_MEM_ESTIMATE_MB pins the WHOLE term to an exact MiB total in
+# one knob — estimate_cudagraph_memory() checks it FIRST and returns base/
+# per-graph untouched when set (verified in the shipped image,
+# v1/worker/gpu/cudagraph_mem.py). We ship the BASE/PER_GRAPH pair instead so
+# a future spec-decode shape re-prices automatically; switch to ESTIMATE_MB
+# only if the drift check below ever shows the pair cannot track capture.
 FRANK_PRIMARY_CUDAGRAPH_BASE_MB=0
 FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB=12