feat(profiler/behave_shell): emit cognitive.inter_command_latency_class

BEHAVE-EXTRACTOR.md Phase A Step 5. Classifies the operator's
thinking pace between commands. Splits LW-sim / CLAUDE-FF /
CLAUDE-CL.

* _features/cognitive.py:inter_command_latency_class(ctx) emits one
  Observation in {instant, typing_speed, deliberate,
  llm_lightweight, llm_heavyweight, long}, computed as the median
  of ctx.inter_cmd_iats bucketed against the prototype thresholds
  (v0.2 split: lightweight 2-8s, heavyweight 8-30s).
* Sample-size honesty: < 5 commands halves confidence (0.40 vs
  0.80) per BEHAVE-EXTRACTOR.md.
* Threshold consts (INTER_CMD_*_MAX, MIN_COMMANDS_FOR_FULL_CONFIDENCE,
  plus parked Step 6/7/8 thresholds for the next three commits)
  added to _thresholds.py.

Tests cover all six buckets at empirically-anchored IATs (15s ≈
Claude Opus driving recon via tmux send-keys), plus the
single-command no-IAT and low-sample-count paths.

decnet/profiler/behave_shell/_features/__init__.py

@@ -11,6 +11,9 @@ from typing import Callable, Iterable
 from decnet_behave_core.spec.envelope import Observation
 
 from decnet.profiler.behave_shell._ctx import SessionContext
+from decnet.profiler.behave_shell._features.cognitive import (
+    inter_command_latency_class,
+)
 from decnet.profiler.behave_shell._features.motor import (
     input_modality,
     paste_burst_rate,
@@ -21,4 +24,5 @@ FeatureFn = Callable[[SessionContext], Iterable[Observation]]
 FEATURES: tuple[FeatureFn, ...] = (
     input_modality,
     paste_burst_rate,
+    inter_command_latency_class,
 )