open/portfolio-optimiser
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions
Generic, open framework on Microsoft Agent Framework (MAF): multi-agent cost-saving proposals gated by a mandatory deterministic validator, with HITL learning.
16 commits 1 branch 0 tags 830 KiB
  • Python 100%
Find a file
Kjell Tore Guttormsen a2dff210ce fix(fase1): spike B fan-out measures real conversation bleed, not a counter 
/trekreview flagged the Spike B(b) fan-out experiment as BROKEN_SUCCESS_CRITERION
(BLOCKER): it asserted a per-client call_count reached 3 on a reused instance vs
1 on a fresh one — a tautology true for any un-reset mutable counter, independent
of MAF, that never exercised the real G2/B7 shared-Workflow state-corruption
footgun. It was a false-confirm of a de-risk assumption.

Rebuilt to observe genuine MAF thread state via the messages each participant
RECEIVES (new FakeChatClient.received_texts seam):
- shared_instance_conversation_bleed: a reused built ConcurrentBuilder Workflow
  accumulates the conversation across .run() calls — run N's participants receive
  runs 0..N-1's prompts/replies (measured [[p0],[p0,p1],[p0,p1,p2]], strictly
  monotonic) => genuine cross-run contamination.
- fresh_instance_conversation_isolation: a fresh instance per run gives each a
  clean thread => each participant sees only its own project ([[p0],[p1],[p2]]).

Assumption now CONFIRMED with a meaningful observable. findings-b.md gains a
Method note recording why it was rebuilt; README rows updated.

Also fixes the MINOR: a_groupchat.run_live now mkdirs the findings dir before
write_text so a post-disposal run does not lose the measured result.

Gate green: ruff check + format, mypy src, pytest 48 passed / 1 skipped.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
2026-06-24 11:09:55 +02:00
.claude/projects/2026-06-23-fase1-derisk-spikes docs(fase1): Voyage brief + plan for de-risk spikes (A-D) 2026-06-24 01:09:35 +02:00
docs fix(fase1): spike B fan-out measures real conversation bleed, not a counter 2026-06-24 11:09:55 +02:00
spikes fix(fase1): spike B fan-out measures real conversation bleed, not a counter 2026-06-24 11:09:55 +02:00
src/portfolio_optimiser feat(fase0): synthetic reference domain (D4) + backend profile skeleton (D2) 2026-06-23 22:38:41 +02:00
tests fix(fase1): spike B fan-out measures real conversation bleed, not a counter 2026-06-24 11:09:55 +02:00
.gitignore feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
.python-version feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
CHANGELOG.md feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
CLAUDE.md build(fase1): add dev orchestration + solver + async deps, scaffold spikes 2026-06-24 09:57:57 +02:00
pyproject.toml build(fase1): add dev orchestration + solver + async deps, scaffold spikes 2026-06-24 09:57:57 +02:00
README.md feat: initial scaffold (Python framework on Microsoft Agent Framework) 2026-06-23 22:01:22 +02:00
uv.lock build(fase1): add dev orchestration + solver + async deps, scaffold spikes 2026-06-24 09:57:57 +02:00

README.md

portfolio-optimiser

Generic, open framework on Microsoft Agent Framework (MAF) for finding cost-savings / efficiency proposals within each project of a portfolio of independent projects. Multiple agents collaborate to generate candidate proposals; a mandatory deterministic validator (solver + Monte Carlo) decides the numbers; domain experts review via human-in-the-loop, and the system learns from their verdicts.

Status: Early development (plan phase). Not yet usable.

Disclaimer — technical framework only. This project is a technical framework. Organizations that deploy it are themselves responsible for ensuring a valid processing purpose and for any required assessments (DPIA, risk/ROS, security reviews, etc.). The framework ships technical affordances (local-only mode, provenance/audit logging, no silent data egress) to enable compliant use, but makes no compliance guarantees.

Design philosophy

The result will never fit any single customer 100%. The goal is a ~90% genuinely generic core plus clear extension points, so competent people can configure the last mile per customer. We deliberately do not chase the final 10%.

Docs

Stack

Python ≥3.10 · MAF (agent-framework) · uv. Backend profiles: Azure/Foundry (full) + local (fallback).

Develop

uv sync
uv run pytest
uv run ruff check .