portfolio-optimiser-claude/tests/test_portfolio_learning_loadbearing.py
Kjell Tore Guttormsen 9bae4fb563 feat(portfolio): K3 — portfolio learning loop (shared verdict store, parity row 5) [skip-docs]
A single VerdictStore threaded through run_portfolio: a verdict available when
project k composes survives into project k+1's fold (method-spec §5 cross-project
threading). The optional verdict_dir is the portfolio-level expert inbox, read
before each fold (role split §3 Step 7 — the portfolio never writes a run's own
verdict back; §1/§6 — no self-contamination, only expert/seed verdicts cross).
compose_run_context gains an optional passed-in store (None = fresh; every
existing caller composes exactly as before).

Load-bearing (tests/test_portfolio_learning_loadbearing.py), 2 detach proofs +
control + §4.2 idempotency:
- cross-project threading: project 1's bundle seed survives into project 2's
  prompt via the shared store; detach (compose ignores the passed-in store,
  always fresh) -> red.
- portfolio inbox fold: a verdict_dir marker reaches the project's fold; detach
  (drop the run_portfolio merge) -> red; control (no verdict_dir) -> marker absent.
- double-merge idempotency: a verdict merged before every project folds exactly
  once (first-write-wins on id).

437->442 green, golden byte-exact, full gate clean (ruff + format + mypy strict).
run_s10.py and runs/ byte-untouched. README synced (test count, portfolio block,
load-bearing list). K2 re-entrancy test stays green — the shared store threads
verdict fold lines only, never bundle context markers.

[skip-docs]: no invariant changed (CLAUDE.md untouched); the run_portfolio and
compose_run_context docstrings + README carry the doc need.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RiTwaKLesgcwXx2mDviqpt
2026-07-23 22:08:02 +02:00

223 lines
10 KiB
Python

"""Portfolio learning loop — LOAD-BEARING (K3; method-spec §3 Step 1, §5, §11; paritetsrad 5).
The seam this file keeps alive: within ONE portfolio pass, a verdict available
when project k is composed SURVIVES into project k+1's hypothesis prompt. The
carrier is a SINGLE ``VerdictStore`` threaded through every project (§5: "a
passed-in store's existing verdicts survive — cross-project threading") plus a
portfolio-level ``verdict_dir`` (the expert inbox, merged read-only before each
run's fold). Honesty rule (§1): the crossing carries EXPERT / bundle-seed
verdicts only — never a run's own captured output. The role split is unwaivable
(§3 Step 7): the portfolio READS ``verdict_dir``; it NEVER writes a run's verdict
back into it, and the promotion gate / authoring primitive remain the only
writers.
Detach proofs (each restored from a copy of the implemented version, never
``git checkout`` — that would go to HEAD and erase the uncommitted src):
* Shared store (§5, cross-project threading): make ``compose_run_context`` ignore
its passed-in ``store`` and always build a fresh one (``store = VerdictStore()``
unconditionally) → project 2 seeds only its OWN bundle → project 1's seed id no
longer reaches project 2's prompt → ``test_earlier_project_seed_survives_into_
later_project`` goes red.
* Inbox threading (§5): drop the ``verdict_dir`` merge in ``run_portfolio`` (or stop
passing the shared store into ``compose_run_context``) → the portfolio inbox
verdict never reaches any fold → ``test_portfolio_inbox_verdict_folds_into_
project_prompt`` goes red.
"""
from __future__ import annotations
import json
from pathlib import Path
import pytest
from _scripted import ScriptedClient, reply
from portfolio_optimiser_claude.budget import BudgetMeter
from portfolio_optimiser_claude.contracts import (
ReferenceProjectsContract,
TerminationContract,
load_reference_projects,
)
from portfolio_optimiser_claude.experience import (
CandidateFeatures,
mint_verdict_id,
)
from portfolio_optimiser_claude.inbox import VerdictDocument, write_verdict
from portfolio_optimiser_claude.ir import load_validator_input
from portfolio_optimiser_claude.portfolio import run_portfolio
_REPO = Path(__file__).resolve().parents[1]
LED_BUNDLE = _REPO / "shared" / "examples" / "bygg-energi-mikro"
VFD_BUNDLE = _REPO / "tests" / "data" / "mini-bundle"
VFD_MARKER = "K2-VFD-CONTEXT-MARKER" # in the repo-local fixture's rendered context
# A token that lives NOWHERE in either bundle — its presence in a prompt can only
# come from the portfolio ``verdict_dir`` fold, never from context or seeding.
INBOX_MARKER = "K3-PORTFOLIO-LEARNING-MARKER"
def _meter(*, max_rounds: int = 100, max_tokens: int = 10_000) -> BudgetMeter:
return BudgetMeter(TerminationContract(max_rounds=max_rounds, max_tokens=max_tokens))
def _happy_replies(bundles: list[Path]) -> list[object]:
"""Three scripted replies per project: debate reasoning → APPROVE → candidate JSON."""
replies: list[object] = []
for bundle in bundles:
replies += [
reply("debate reasoning"),
reply("VERDICT: APPROVE"),
reply(json.dumps(load_validator_input(bundle).model_dump())),
]
return replies
def _config(entries: list[tuple[str, Path]]) -> ReferenceProjectsContract:
return load_reference_projects(
{"projects": [{"project_id": pid, "bundle_dir": str(path)} for pid, path in entries]}
)
def _seed_id(bundle: Path) -> str:
"""The id the bundle's ``type: verdict`` seed is keyed on (§3 Step 1 / §4.2)."""
return mint_verdict_id(CandidateFeatures.from_proposal(load_validator_input(bundle)))
def _author_inbox_verdict(verdict_dir: Path, marker: str) -> VerdictDocument:
"""Drop an EXPERT verdict into the portfolio inbox (§5 write side, expert-authored).
Keyed on features similar to the VFD candidate (same code + measure type, a
distinct saving so its id does not collide with the VFD seed), so it ranks
high for the VFD project. The marker rides in the rationale — the fold's
learning-signal carrier (§3 Step 1).
"""
vfd = CandidateFeatures.from_proposal(load_validator_input(VFD_BUNDLE))
features = CandidateFeatures(
affected_codes=vfd.affected_codes,
measure_type=vfd.measure_type,
claimed_saving_nok=vfd.claimed_saving_nok + 3000.0, # same bucket, distinct id
)
verdict = VerdictDocument.from_candidate(
features,
decision="approved",
rationale=f"prior portfolio verdict — realiseringskorreksjon [{marker}]",
description="K3 portfolio inbox fixture (surface text, excluded from ranking)",
)
write_verdict(verdict_dir, verdict)
return verdict
class TestCrossProjectThreading:
"""§5 cross-project threading: a passed-in store's verdicts survive into the next run.
The shared ``VerdictStore`` ``run_portfolio`` owns carries project 1's bundle
seed forward, so it is still retrievable when project 2 composes — the
portfolio learns across projects in a single pass (S2.0, paritetsrad 5).
"""
def test_earlier_project_seed_survives_into_later_project(self) -> None:
projects = _config([("BYGG-KONTOR-NORD", LED_BUNDLE), ("PUMPE-SOR", VFD_BUNDLE)])
client = ScriptedClient(replies=_happy_replies([LED_BUNDLE, VFD_BUNDLE]))
run_portfolio(projects, client, _meter(), top_k=3, max_debate_rounds=3, max_attempts=3)
led_seed_id = _seed_id(LED_BUNDLE)
vfd_prompts = [p for p in client.prompts("proposer") if VFD_MARKER in p]
assert vfd_prompts, "project 2's own context must reach its prompts"
# The shared store carried project 1's seed into project 2's fold.
assert any(led_seed_id in p for p in vfd_prompts), (
"project 1's seed must survive into project 2's prompt via the shared store"
)
def test_threading_is_order_directional(self) -> None:
# Reverse the config: now VFD is project 1 → its seed threads into LED's prompt,
# and LED's seed (project 2, composed last) is absent from project 1's prompt.
led_seed_id = _seed_id(LED_BUNDLE)
vfd_seed_id = _seed_id(VFD_BUNDLE)
projects = _config([("PUMPE-SOR", VFD_BUNDLE), ("BYGG-KONTOR-NORD", LED_BUNDLE)])
client = ScriptedClient(replies=_happy_replies([VFD_BUNDLE, LED_BUNDLE]))
run_portfolio(projects, client, _meter(), top_k=3, max_debate_rounds=3, max_attempts=3)
vfd_prompts = [p for p in client.prompts("proposer") if VFD_MARKER in p]
assert vfd_prompts
# Project 1 (VFD) ran before LED was ever seeded → LED's seed cannot appear.
assert not any(led_seed_id in p for p in vfd_prompts), (
"a later project's seed must not reach an earlier project's prompt"
)
# VFD's own seed is of course present in its own fold.
assert any(vfd_seed_id in p for p in vfd_prompts)
class TestPortfolioInboxFold:
"""A portfolio-level ``verdict_dir`` (expert inbox) folds into each project (§5, §3 Step 1)."""
def test_portfolio_inbox_verdict_folds_into_project_prompt(self, tmp_path: Path) -> None:
verdict_dir = tmp_path / "portfolio-inbox"
inbox_verdict = _author_inbox_verdict(verdict_dir, INBOX_MARKER)
projects = _config([("BYGG-KONTOR-NORD", LED_BUNDLE), ("PUMPE-SOR", VFD_BUNDLE)])
client = ScriptedClient(replies=_happy_replies([LED_BUNDLE, VFD_BUNDLE]))
run_portfolio(
projects,
client,
_meter(),
top_k=3,
max_debate_rounds=3,
max_attempts=3,
verdict_dir=verdict_dir,
)
vfd_prompts = [p for p in client.prompts("proposer") if VFD_MARKER in p]
assert vfd_prompts
assert any(INBOX_MARKER in p and inbox_verdict.id in p for p in vfd_prompts), (
"the portfolio inbox verdict (id + marker) must reach the project's fold"
)
def test_no_verdict_dir_leaves_the_marker_absent(self) -> None:
# Control: without a portfolio inbox, the marker appears in NO prompt — it
# has no other channel into the context (seeding and bundle context never
# carry it).
projects = _config([("BYGG-KONTOR-NORD", LED_BUNDLE), ("PUMPE-SOR", VFD_BUNDLE)])
client = ScriptedClient(replies=_happy_replies([LED_BUNDLE, VFD_BUNDLE]))
run_portfolio(projects, client, _meter(), top_k=3, max_debate_rounds=3, max_attempts=3)
assert not any(INBOX_MARKER in prompt for _role, prompt in client.calls)
class TestPortfolioMergeIdempotency:
"""§4.2 first-write-wins: repeated portfolio merges are idempotent (double-merge, §5).
``verdict_dir`` is merged before EVERY project's fold. Across a three-project
pass the same inbox verdict is merged three times, yet the shared store holds
it exactly ONCE — its fold line is not duplicated.
"""
def test_repeated_merges_keep_a_single_store_entry(self, tmp_path: Path) -> None:
verdict_dir = tmp_path / "portfolio-inbox"
inbox_verdict = _author_inbox_verdict(verdict_dir, INBOX_MARKER)
projects = _config(
[
("BYGG-KONTOR-NORD", LED_BUNDLE),
("PUMPE-SOR", VFD_BUNDLE),
("BYGG-KONTOR-NORD-2", LED_BUNDLE),
]
)
client = ScriptedClient(replies=_happy_replies([LED_BUNDLE, VFD_BUNDLE, LED_BUNDLE]))
run_portfolio(
projects,
client,
_meter(),
top_k=3,
max_debate_rounds=3,
max_attempts=3,
verdict_dir=verdict_dir,
)
vfd_prompts = [p for p in client.prompts("proposer") if VFD_MARKER in p]
assert vfd_prompts
# The verdict was merged three times (once before each project) but appears
# once per fold — first-write-wins deduplicates on id.
assert all(p.count(inbox_verdict.id) == 1 for p in vfd_prompts), (
"a verdict merged N times must fold exactly once (first-write-wins, §4.2)"
)
if __name__ == "__main__": # pragma: no cover
raise SystemExit(pytest.main([__file__, "-q"]))