The context sets, the packaged knowledge bases and the example bundles are
replaced by one fictitious example set about IT operations in an invented
organisation: three context sets (serverrom-2027, driftsavtale-2027 and the
two-base drift-og-avtale-2027), two synthetic knowledge bases under
src/portfolio_optimiser/data/kunnskapsbaser and two example bundles under
src/portfolio_optimiser/data/bundles. Numbers, codes and structural values in
tests and fixtures are kept; names, ids and wording change. Dated measurement
documents that only recorded runs on the replaced material are deleted.
Gate figures measured on the new set are not comparable with earlier ones.
The exclusion gate from the previous commit is green: 0 tracked files hit
outside the shared/ subtree.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The report's strongest evidence is that the debate's three context copies are
byte-identical before and after. It was established by comparing the per-prompt
proposer/checker token lists, NOT by the probe's carries flag -- which after the
change correctly reports no, because the listing's text is not in the debate's
prompts. A flag that flips for the right reason is not a proof of sameness; the
token counts are. Said once, where the claim is made.
And bygg's copy count was carried over from the middle-slice probe that the
section immediately below declares broken. All three bases are now re-measured
with the corrected ASCII probe; bygg confirms five copies and the same
exploration total. A cell sourced from an instrument you yourself retired is
what that paragraph exists to refuse.
[skip-docs]
S2c / MAJOR-3, order 20260902T151931Z-250257273. The measurement landed first
in ce7f687; this commit is the one seam it authorised, plus the after-table.
read_bundle returned okf.bundle_context -- the WHOLE navigated base. Because
the exploration's participants share one conversation history, that single
function_result rode in FIVE later prompts at full price without anyone asking
for it again: 54-59 percent of every prompt-token in a CLI --explore run.
It now returns the catalogue form one rung down the ladder -- one entry per
concept document (name, type, title, chars) -- with read_file as the next rung.
Tunnel base: 12 595 -> 259 o200k tokens, exploration prompt-tokens -91 percent.
The listing is built from Bundle.context_files and never from files: that is
the property which drops the type: verdict layer at every level, and a listing
built from files would route prior verdicts in front of the navigator around
the gated ExpeL fold while every cost arm stayed green.
A premise was felled before anything was built on it: the tunnel base's root
index body is 4 763 chars alone, nearly the whole ceiling, for a field the
catalogue already excerpts and read_file still returns whole. So read_bundle
carries the listing and not the index.
The tool description and the navigator's instruction both claimed "read its
navigated context" and were updated in the same move -- a description that lies
about the body IS the model's instruction. Two pre-existing asserts would have
gone vacuously true against a list and were strengthened rather than left.
Ceiling lives in the test, not in explore.py. Deviation stated there and in the
docs: it bounds CHARACTERS, not tokens, because tiktoken is not a project
dependency and a gate that skips when an optional package is missing is a gate
that can be silently absent; the conversion was measured (2.89 chars/token) and
the order's own token criterion verified once by the instrument.
Load-bearing measured: seven mutations, all red against the WHOLE suite; green
control 1195 passed / 5 skipped (from 1189/5, strict superset); golden
demo-transcript.stdout byte-unchanged; and the debate's three bundle_context
copies are byte-identical before and after, which proves run.py and the
nav-goldens were not touched rather than asserting it.
S2c / MAJOR-3, order 20260902T151931Z-250257273. The order's rule is MEASURE
FIRST, so the numbers land as their own commit before the seam is touched.
Instrument validated against a known positive before use: it reproduces
commons' own published bundle_context fasit exactly (3 861 / 10 406 / 12 595).
Prompts are measured as text + function_call + function_result -- .text alone
undercounts a prompt whose whole payload is a tool result.
Measured, per CLI --explore run: one read_bundle result rides in FIVE
exploration prompts (navigator 1, manager 3, hypothesiser 1), which is 54-59
percent of every prompt-token in the run. The debate's three copies come from
run.py's okf.bundle_context and are a separate decision; they are in the table
as denominator and as the after-control, never as the target.
One premise felled before building on it: the tunnel base's root index body is
4 763 chars alone, nearly the whole 1 500-token ceiling, so read_bundle carries
the concept listing and not the index body -- which the catalogue already
excerpts and read_file still returns whole.
