feat: T8 run-cell + regen-dynamics recipes; spec T5 done, T8 in progress

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

docs/spec/20260529_gradient_routing_and_env_split.md

@@ -213,7 +213,15 @@ current env) -> Stage 2 env = T0,T1,T2,T4 -> Stage 3 cross-mechanism = T7
   - sneaky_fail: off-distribution (caught by len/compile comparison, R2)
   - UAT: "the pool breakdown shows a real M2 fraction in model style"
 
-- [ ] T5 (R3): eval-time ablation pass for the route arm
+- [x] T5 (R3): eval-time ablation pass for the route arm
+  DONE 2026-05-30: eval_hack_solve (student-only generate+grade on a fixed
+  subset) + ablate_quarantine ctx (zero delta_S_hack). Periodic ablated-eval
+  every --eval-ablate-every steps -> hack_abl/solve_abl cols (appended after
+  refr, so results.py positional indices unchanged). Final kept-vs-ablated
+  ROUTE EVAL BLUF. plot_dynamics remaps routing -> ablated series (coherence-gap
+  fix). smoke route prints periodic + final BLUF (all 0 on tiny-random, as
+  expected; behavioral evidence is the queued real run #182). M2 split is
+  Stage 3 (T7); T5 logs M1 (C) + solve only.
   - steps: after training, run an eval batch twice — with and without
     `delta_S_hack` (zeroed) — log hack_s (M1 and M2 separately) and solve.
   - verify: BLUF prints `ablated: hackM1=.. hackM2=.. solve=..` vs `kept: ..`
@@ -232,7 +240,11 @@ current env) -> Stage 2 env = T0,T1,T2,T4 -> Stage 3 cross-mechanism = T7
     mechanism-specific). Report which, don't bury a null.
   - UAT: "I see hack_M2 lower under route/erase than none, at matched solve"
 
-- [ ] T8 (R6): KEY GOAL — regenerate both plots from real 60-step runs
+- [/] T8 (R6): KEY GOAL — regenerate both plots from real 60-step runs
+  RECIPES DONE 2026-05-30: `just run-cell {none,erase,route} SEED` (60-step
+  fast, shared v_hack_21pairs, eval-ablate-5) + `just regen-dynamics GLOB`.
+  Cells tagged _cell_{intervention}_s{seed}. Gated on evidence run #182 (real-
+  scale route) passing before queuing the seed-41 cells.
   - justfile recipes (written in T3, once --intervention exists): one recipe per
     CELL so each is a separate pueue job, e.g. `just run-cell INTERVENTION SEED`
     -> `train ... --intervention={none,erase,route} --steps=60 --seed=SEED

justfile

@@ -101,6 +101,24 @@ fast-projected *ARGS:
         --teacher-pool-dir=out/probe_distill/teacher_pool \
         --grad-clip=500 {{ ARGS }}
 
+# T8 (KEY GOAL): one CELL of the dynamics-plot matrix as a separate pueue job.
+# INTERVENTION in {none, erase, route}; SEED an int. 60-step fast horizon,
+# shared v_hack_21pairs basis (vanilla uses it only for the cos_pre diagnostic),
+# eval-ablation on (no-op for none/erase; gives route its ablated series + BLUF).
+# Logs land as ..._cell_{intervention}_s{seed}.log -> regen-dynamics globs them.
+run-cell INTERVENTION SEED:
+    {{ TRAIN }} fast --intervention={{ INTERVENTION }} \
+        --v-hack-path=out/v_hack_21pairs.safetensors \
+        --teacher-pool-dir=out/probe_distill/teacher_pool \
+        --grad-clip=500 --steps=60 --seed={{ SEED }} \
+        --eval-ablate-every=5 \
+        --out-tag=_cell_{{ INTERVENTION }}_s{{ SEED }}
+
+# Regenerate both dynamics plots from the cell logs (default: all cells; pass a
+# narrower glob like 'logs/*_cell_*_s41.log' for the seed-41-only checkpoint).
+regen-dynamics GLOB='logs/*_cell_*.log':
+    uv run python scripts/plot_dynamics.py {{ GLOB }} --out out/dynamics.png
+
 # Sync the rl-rewardhacking external repo (Nanda's verl wrapper).
 sync-external:
     cd external/rl-rewardhacking && git pull --ff-only