- Python 100%
Kjell Tore Guttormsen
22bfc80dda
- inbox.py (§4.2+§5): VerdictDocument med verbatim-id-regel; write_verdict
authoring-primitiv (deterministisk JSON); load_inbox tolerant (skip, aldri
raise; sortert på filnavn); merge_inbox_into_store first-write-wins,
idempotent, skriver aldri (rolle-splitt §3 steg 7)
- promotion.py (§6): promote fail-closed mot {approved,
approved_with_adjustment}; eksplisitt påkrevd timestamp; minimal frontmatter
(rationale → description, aldri strukturerte læringsfelt); path-safe token
med content-hash-fallback; idempotent index-lenking med fast nøytral label
- persona.py (§4.3): load_persona_example fail-fast (run-path-vokabular,
marker ⊆ rationale); drop_persona_verdict artefakt-sourced ved kalltid mot
delt shared/-artefakt
- experience.py (kirurgisk): seeding leser verdict_id VERBATIM fra frontmatter
— re-minting ville kollidert distinkte promoterte kandidater
- 43 nye load-bearing tester (step7/step8/persona), 164/164 uten API-nøkkel;
to-runs-bevis med fersk store + tom-inbox-kontroll; fire detach-bevis kjørt
røde og revertert grønne
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QdSfQdND84oeq2mbjueLTS
|
||
|---|---|---|
| shared | ||
| src/portfolio_optimiser_claude | ||
| tests | ||
| .gitignore | ||
| CHANGELOG.md | ||
| CLAUDE.md | ||
| pyproject.toml | ||
| README.md | ||
| uv.lock | ||
portfolio-optimiser-claude
Sibling implementation of the portfolio-optimiser method on the Claude Agent SDK (decision D7). An open, generic Python framework that finds cost savings inside each project in a portfolio of independent projects: agents generate candidate measures, a mandatory deterministic validator gates the numbers, domain experts judge via HITL, and the system learns from the verdicts.
The method itself is framework-neutral and lives in
portfolio-optimiser-commons
(consumed here as a git subtree under shared/): the method spec, the OKF bundle
navigation contract, the golden/conformance suite (the only oracle for the validator),
and the shared expert-reviewer persona skill. This repo implements that spec on the
Claude Agent SDK — it does not reverse-engineer the MAF sibling.
Disclaimer: this is a purely technical framework. The deployer owns DPIA, risk assessment, and the legal basis for any processing. The framework ships only the technical preconditions (local-only operation, provenance, no silent egress).
Status
Scaffold (S5): repo, contracts, and shared core in place — no agent runs yet.
Development
uv sync # install dependencies
uv run pytest # test suite (runs without any API key)
uv run ruff check . && uv run ruff format --check .
uv run mypy src