open/portfolio-optimiser
1
0
Fork 0
Code Issues Releases 4 Activity

refactor(examples): replace sector-specific example material with generic, fictitious examples

Browse source 
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>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-23 15:04:21 +02:00
commit 37547fe292
Signed by: ktg
SSH key fingerprint: SHA256:JakMjO6FTBBzN0Bhfj9saOoEjaFxlSdYuZQQpM/lF9Q
1147 changed files with 24138 additions and 9503 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tests/test_proposal_review_loop_loadbearing.py
View file

@ -52,6 +52,7 @@ from portfolio_optimiser.verdicts import VerdictStore
_REPO = Path(__file__).resolve().parents[1]
_EXAMPLES = _REPO / "shared" / "examples"
_BUNDLE_DIR = _EXAMPLES / "bygg-energi-mikro"
_DELIVERED = _REPO / "src" / "portfolio_optimiser" / "data" / "bundles"
_PID = "BYGG-KONTOR-NORD"
_RUN_ID = "proposal-review-door"
@ -229,7 +230,7 @@ def test_the_payload_carries_every_field_and_takes_its_key_from_the_injected_fun
@pytest.fixture(scope="module")
def project():
return load_reference_projects()[0] # FV42-GSV-E1
return load_reference_projects()[0] # KONTOR-IT-E1
def test_prior_feedback_none_keeps_the_base_prompt_byte_identical(project) -> None:
@ -294,7 +295,7 @@ def test_the_feedback_sentinel_cannot_arrive_from_the_knowledge_base() -> None:
# Group A (Step 3) — the reviewer INSIDE the attempt loop. Driven at ``generate_via_llm``.
# ---------------------------------------------------------------------------------------------
# FV42-GSV-E1 cost codes 05.2 + 03.1 -> affected total 1_482_500, degenerate Monte Carlo
# KONTOR-IT-E1 cost codes 05.2 + 03.1 -> affected total 1_482_500, degenerate Monte Carlo
# P90 = 0.30 x 1_482_500 = 444_750 (the ``test_step5_refine_loadbearing`` fixture, reused).
_CODES = ["05.2", "03.1"]
_BAD_CLAIM = 800_000 # parseable, but above P90 -> the DETERMINISTIC validator rejects it
@ -1733,11 +1734,11 @@ async def test_t22_the_dispatcher_threads_one_reviewer_into_every_base(
Mandate(
objective="o",
approaches=(
Approach(id="a", label="A", bundle_id="tunnel-hauglia"),
Approach(id="b", label="B", bundle_id="veglys-fv-soer"),
Approach(id="a", label="A", bundle_id="driftssenter-kjoling"),
Approach(id="b", label="B", bundle_id="klientpark-energi"),
),
),
(str(_EXAMPLES / "tunnel-hauglia"), str(_EXAMPLES / "veglys-fv-soer")),
(str(_DELIVERED / "driftssenter-kjoling"), str(_DELIVERED / "klientpark-energi")),
proposal_reviewer=reviewer,
)
assert calls, "the dispatcher must have reached run_project at least once"