portfolio-optimiser/tests/test_parse_error_feedback_loadbearing.py
Kjell Tore Guttormsen 37547fe292
refactor(examples): replace sector-specific example material with generic, fictitious examples
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>
2026-09-23 15:04:21 +02:00

168 lines
7 KiB
Python

"""P20 DEL C — a parse failure that does not burn the round ledger, and an announcement that
names what it is about.
**C1, what was measured (P19 F4).** ``_fetch_parsed`` retried a malformed reply with the
BYTE-IDENTICAL prompt. One round-3 run, on the set priced by process number, left a
``{run_id}-parse-failures.json`` with ELEVEN rows, every one of them the same failure
(``claimed_saving_nok`` ≤ 0) — eleven of the run's twelve rounds, spent re-asking a question the
model had already answered the same wrong way, because nothing ever told it what was wrong. Step
5's ``prior_rejection`` carries VALIDATOR rejections; a reply that never parsed never reaches a
validator, so no existing block could carry it.
**C2, what was measured (P17b F5).** ``--across-bundle`` takes no ``--project-id``, so the
announcement — the one thing printed before the first paid call — said "Run mandate for the
portfolio" for a commission dispatched across two named knowledge bases.
What each arm pins:
(a) the reason reaches the NEXT attempt's prompt, verbatim, asserted on what the client received;
(b) attempt 1 is byte-identical: a run whose first reply parses sends the pre-P20 prompt;
(c) the block is per-RETRY — once a reply parses, the next attempt does not carry a stale reason;
(d) the evidence artefact is unchanged: the verbatim text is still captured (funn 1 stands);
(e) the announcement names the routed bases by their DECLARED ids;
(f) an unresolvable base falls back to its directory name rather than refusing — the
``dimension_label`` precedent, so announcing never changes which error an operator sees;
(g) a single-project run and a portfolio pass announce exactly as before.
"""
from __future__ import annotations
import asyncio
import json
from pathlib import Path
from typing import Any
import pytest
from portfolio_optimiser.budget import Budget, TokenMeter
from portfolio_optimiser.generate import ParseFailure, _build_messages, generate_via_llm
from portfolio_optimiser.reference_domain import Project
from portfolio_optimiser.run import announced_subject
from portfolio_optimiser.simulation import ScriptedChatClient
_BUNDLES = Path(__file__).resolve().parents[1] / "src" / "portfolio_optimiser" / "data" / "bundles"
_BASE = _BUNDLES / "driftssenter-kjoling"
#: The exact failure that round-3 run produced eleven times: a well-formed JSON object
#: whose ``claimed_saving_nok`` is 0, refused by pydantic before any validator sees it.
_UNPARSEABLE = (
'{"measure":"m","affected_items":[{"code":"C-1","quantity":1000,"unit_cost":100}],'
'"claimed_saving_nok":0}'
)
#: The grounding this loop declares: P7 requires the code to occur in the input verbatim.
_CONTEXT = "The project price schedule carries cost line C-1."
_VALID = (
'{"measure":"m","affected_items":[{"code":"C-1","quantity":1000,"unit_cost":100}],'
'"claimed_saving_nok":5000}'
)
def _project() -> Project:
return Project(id="p", name="n", description="d", currency="NOK", cost_items=(), docs_dir=".")
def _generate(replies: list[str]) -> tuple[Any, list[str], list[ParseFailure]]:
"""Drive the real loop with the repo's ONE scripted client, recording every prompt sent."""
sink: list[str] = []
failures: list[ParseFailure] = []
client = ScriptedChatClient(script=list(replies), sink=sink, role="proposer")
result = asyncio.run(
generate_via_llm(
client,
_project(),
_CONTEXT,
TokenMeter(Budget(max_tokens=100_000, max_rounds=8)),
parse_failures=failures,
)
)
return result, sink, failures
# ------------------------------------------------------------------------------- C1
def test_the_parse_reason_reaches_the_next_attempts_prompt() -> None:
"""(a) The retry is no longer blind — asserted on what the CLIENT received."""
_result, sink, _failures = _generate([_UNPARSEABLE, _VALID])
assert len(sink) >= 2, sink
assert "could not be PARSED" in sink[1]
assert "claimed_saving_nok" in sink[1]
def test_the_first_prompt_is_byte_identical_to_the_pre_p20_one() -> None:
"""(b) Without this, (a) could be satisfied by always appending the block."""
_result, sink, _failures = _generate([_VALID])
assert "could not be PARSED" not in sink[0]
assert sink[0] == _build_messages(_project(), _CONTEXT)[0].text
def test_a_reason_does_not_survive_a_reply_that_parsed() -> None:
"""(c) Per-RETRY, like ``prior_rejection`` is per-attempt: no stale instruction."""
assert "could not be PARSED" not in _build_messages(_project(), "c")[0].text
carried = _build_messages(_project(), "c", parse_error="ValueError: x")[0].text
assert "ValueError: x" in carried
def test_the_verbatim_evidence_is_still_captured() -> None:
"""(d) Fase 1b funn 1 stands: the paid reply's own text survives the retry."""
_result, _sink, failures = _generate([_UNPARSEABLE, _VALID])
assert len(failures) == 1
assert failures[0].text == _UNPARSEABLE
assert failures[0].error.startswith("ValidationError")
# ------------------------------------------------------------------------------- C2
def test_the_announcement_names_the_routed_bases() -> None:
"""(e) Two bases, two declared ids — not "the portfolio"."""
assert announced_subject(None, (str(_BASE),)) == "driftssenter-kjoling"
def test_an_unresolvable_base_falls_back_to_its_directory_name(tmp_path: Path) -> None:
"""(f) Naming never changes which error an operator sees (the dimension_label precedent)."""
missing = tmp_path / "not-a-base"
assert announced_subject(None, (str(missing),)) == "not-a-base"
def test_the_cli_prints_the_routed_bases(
tmp_path: Path, capsys: pytest.CaptureFixture[str]
) -> None:
"""(e2) The WIRING, not the renderer.
MEASURED: mutation C-iii reverted the call site to ``args.project_id or "the portfolio"`` and
the WHOLE suite stayed green (1808/5) — the renderer had three arms and the call site none, so
the seam C2 exists for was unwitnessed. This arm drives ``main()`` on a free dry run and reads
the announcement off stdout, which is where an operator reads it.
"""
from portfolio_optimiser.run import main
mandate = tmp_path / "m.json"
mandate.write_text(
json.dumps({"objective": "cut cost", "approaches": [], "allow_own_proposals": True}),
encoding="utf-8",
)
rc = main(
[
"--across-bundle",
str(_BASE),
"--mandate",
str(mandate),
"--run-id",
"r1",
"--outbox-dir",
str(tmp_path / "out"),
"--live-dry-run",
]
)
out = capsys.readouterr().out
assert rc == 0, out
assert "Run mandate for driftssenter-kjoling" in out
assert "the portfolio" not in out
def test_the_two_older_subjects_are_unchanged() -> None:
"""(g) A named project wins; no bases at all is still the portfolio."""
assert announced_subject("proj-1", ()) == "proj-1"
assert announced_subject("proj-1", ("ignored",)) == "proj-1"
assert announced_subject(None, ()) == "the portfolio"