anti
3fc6ea5f75
BEHAVE-EXTRACTOR.md Phase A Step 6. Content-based playbook-vs-
adaptive split. Splits CLAUDE-FF (linear_playbook, ~10 distinct
tools) from CLAUDE-CL (adaptive_branching, 5-6 tools with curl
re-invoked) per the 2026-05-02 empirical anchor.
* _features/cognitive.py:command_branch_diversity(ctx) emits one
Observation in {linear_playbook, adaptive_branching, unknown}.
* unique_first_token_hashes / total_commands ratio. ≥ 0.80 →
linear_playbook, otherwise adaptive_branching (the doc instructs
bias-to-adaptive in the middle band — that's the discriminative
signal we actually want).
* < 5 commands → "unknown" at confidence 1.0 (the absence of data
is itself a high-confidence answer per the registry's allowed
vocabulary). Zero-command session skips emission entirely.
Tests cover unique-tokens → linear, repeated-tokens → adaptive,
middle band → adaptive (bias), under-floor → unknown @ 1.0, plus
PII regression: raw tokens never appear in the serialised
observation.
31 lines
852 B
Python
31 lines
852 B
Python
"""Registered feature functions.
|
|
|
|
Each entry takes a ``SessionContext`` and yields zero or more
|
|
``Observation`` instances. Adding a primitive = adding a function in a
|
|
sibling module and appending it to ``FEATURES``.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
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 (
|
|
command_branch_diversity,
|
|
inter_command_latency_class,
|
|
)
|
|
from decnet.profiler.behave_shell._features.motor import (
|
|
input_modality,
|
|
paste_burst_rate,
|
|
)
|
|
|
|
FeatureFn = Callable[[SessionContext], Iterable[Observation]]
|
|
|
|
FEATURES: tuple[FeatureFn, ...] = (
|
|
input_modality,
|
|
paste_burst_rate,
|
|
inter_command_latency_class,
|
|
command_branch_diversity,
|
|
)
|