docs(diagnostics): R30 φ0 — fold in mask_neg (8/8 complete)

mask_neg recovered from the demo SSE stall; well-conditioned (φ_P 0.982, r²0.95),
confirms the verdict. 6 well-conditioned runs: φ_P=0.971±0.01 joint; empty-tail
nails 0.95 exact (joint carries a small push-under-attribution upward bias).
Config faithful; verdict unchanged.

docs/diagnostics/r30-phi0-findings.md

@@ -31,11 +31,13 @@ worldtree v1.0.0b14 `e1cdf82`).
 |---|---:|---:|---:|---:|---:|
 | lofn  | 0.809 | 0.954 / 0.967 (pos/neg) | ~0.000 | 0.93–0.94 | — (excursion faded pre-empty) |
 | mimir | 0.615 | 0.964 / 0.977 (pos/neg) | −0.012 / −0.015 | 0.97–0.99 | — (never emptied) |
-| mask  | 0.000 | 0.983 (pos) | +0.004 | 0.90 | — |
+| mask  | 0.000 | 0.983 / 0.982 (pos/neg) | +0.004 / +0.006 | 0.90 / 0.95 | — |
 | forseti | 0.239 | signal-poor (r²=0.46/0.61, excluded) | — | — | **0.95** (neg, r²=1.0) |
 
-- **Joint fit, 5 well-conditioned runs (3 baselines): φ_P = 0.969 ± 0.01**
-  (range 0.954–0.983).
+- **Joint fit, 6 well-conditioned runs (3 baselines; all 8 probes in): φ_P = 0.971
+  ± 0.01** (range 0.954–0.983). Consistently a hair above config 0.95 — the
+  empty-tail read (no push modeling) nails **0.95 exactly**, so the joint fit's
+  ~0.97 carries a small upward bias from push under-attribution; true φ0 ≈ 0.95.
 - **Empty-tail cross-check** (forseti_neg's clean pure-decay tail): **φ0_P = 0.95**,
   r²=1.0 — independently confirms the joint fit.
 - **config cross-check:** measured φ0 ≈ 0.95–0.97 vs config `1−0.05 = 0.95` →
@@ -69,9 +71,9 @@ operating point defines the cap; do NOT re-base the agents faster.
   conditioned regression (r² 0.46/0.61). Correctly excluded (its empty-tail
   still gave a clean 0.95). High/mid-baseline agents (lofn/mimir/mask) carry the
   joint-fit signal.
-- **mask_neg** stalled on a demo-side turn hang (SSE stall on turn 14);
-  proceeding with 7/8. Non-blocking — mask_pos already anchors the neutral (0.0)
-  trait point; mask_neg would be a second neutral-baseline run.
+- **mask_neg** recovered from a demo-side SSE stall (turn 14) and completed — all
+  8/8 in. It is well-conditioned (φ_P 0.982, r² 0.95) and confirms the verdict
+  (didn't move it). `stream_turn_resilient`'s reconnect handled the transient hang.
 
 Series: `r30-phi0-{lofn,mimir,forseti,mask}-{pos,neg}.json` (per-turn pad +
 emotions_active + wall-clock). sec/turn ≈ 19–25 (16s spacing + processing).