What does Spiritual Quotient, Prior Conditioning and RAG Agents conclude, in numbers, about “The Context Budget: Lagrangian Water-Filling and the Best Number of Passages”?
Answer: Under diminishing returns, the optimal division of the context is a water-filling solution: from 32k the profile stays at its 8 KB cap, and the rest goes to retrieval and history by weight. The best number of passages is set jointly by retrieval quality and distraction: a good retriever needs only 7, and a poor one cannot catch up however many it takes.
Scope of the numbers: Marked boxes separate evidence, 16 runnable Python programs, classical sources and hypotheses.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 32
window budget profile retrieval history nu x 1e4 gain vs equal
8192 6144 1508 3424 1212 5.531 0.2134
32768 30720 2048 19448 9224 1.399 0.2321
131072 129024 2048 84984 41992 0.345 0.2491
Reading: at 8k the profile already takes a quarter of the
budget; from 32k it sits at its 8 KB cap, and every further
token goes to retrieval and history in the ratio of their
weights. A larger window makes the profile's share shrink,
and the value of the last token (nu) falls sixteen-fold.Show the full program
# Chapter 4. p07: Splitting a context window: a Lagrangian water-filling.
# A context of T tokens, less 2,048 kept for the answer, is shared by
# the profile (P), retrieved passages (R) and conversation history (H).
# Each part has diminishing returns, U_i = a_i ln(1 + t_i / s_i), with
# weights a = (1.0, 3.0, 1.5) and half-saturation sizes s = (300,
# 2,000, 1,500) tokens; the profile cannot exceed its 8 KB file, about
# 2,048 tokens. Maximising sum U_i subject to sum t_i = B gives the
# Karush-Kuhn-Tucker solution t_i = clip(a_i / nu - s_i, 0, cap_i), with
# the multiplier nu (the value of one more token) found by bisection.
# Compared with an equal three-way split (the profile's surplus over
# its cap shared by the other two).
import math
A = (1.0, 3.0, 1.5)
S = (300.0, 2000.0, 1500.0)
CAP = (2048.0, math.inf, math.inf)
NAMES = ("profile", "retrieval", "history")
def alloc(nu):
return [min(c, max(0.0, a / nu - s)) for a, s, c in zip(A, S, CAP)]
def solve(budget):
lo, hi = 1e-9, 10.0
for _ in range(200):
mid = math.sqrt(lo * hi)
if sum(alloc(mid)) > budget:
lo = mid
else:
hi = mid
return alloc(hi), hi
def utility(t):
return sum(a * math.log(1 + x / s) for a, s, x in zip(A, S, t))
if __name__ == "__main__":
print(" window budget profile retrieval history"
" nu x 1e4 gain vs equal")
for T in (8192, 32768, 131072):
b = T - 2048
t, nu = solve(b)
p0 = min(b / 3, CAP[0])
eq = [p0, (b - p0) / 2, (b - p0) / 2]
print(" {:6d} {:8d} {:8.0f} {:10.0f} {:8.0f} {:11.3f} {:13.4f}"
.format(T, b, t[0], t[1], t[2], 1e4 * nu,
utility(t) - utility(eq)))
print("\nReading: at 8k the profile already takes a quarter of the")
print("budget; from 32k it sits at its 8 KB cap, and every further")
print("token goes to retrieval and history in the ratio of their")
print("weights. A larger window makes the profile's share shrink,")
print("and the value of the last token (nu) falls sixteen-fold.")Single source and citation
Fan, Y. (2026). Spiritual Quotient Quantification, Prior-Conditioned Generation and Retrieval-Augmented Cognitive Agents (Version 1.0.0), Chapter 4: The Context Budget: Lagrangian Water-Filling and the Best Number of Passages. 5D Library. https://doi.org/10.5281/zenodo.24090203
DOI: 10.5281/zenodo.24090203 · Read the monograph · 5DL-B-076 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026076,
author = {Fan, Yafu},
title = {Spiritual Quotient Quantification, Prior-Conditioned Generation and Retrieval-Augmented Cognitive Agents},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
doi = {10.5281/zenodo.24090203},
url = {https://doi.org/10.5281/zenodo.24090203}
}Other chapter answers in this book
- Chapter 1 · Five Dimensions or One: The Spectrum and Information of an SQ Scale
- Chapter 2 · Reliability, the "Shape" of a Profile and a Blind-Pick Test
- Chapter 3 · Prior Conditioning: How Much Uncertainty Can a Profile Remove?
- Chapter 5 · Retrieval Augmentation: One-Book Recall and Cross-Book Synthesis
- Chapter 6 · The Library Graph: Islands, the Fiedler Value and a Small World
- Chapter 7 · Looking Up and Looking Down, and Shao Yong's Observing of Things
- Chapter 8 · A Seven-Flag Audit and a Blind Comparison