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.
20 commits 1 branch 0 tags 830 KiB
  • Python 100%
Find a file
Kjell Tore Guttormsen c72730941e docs(fase2): 3 /trekresearch briefs — installed-source-verified [skip-docs] 
Topic 1 (HITL): native HITL is GA (ctx.request_info/@response_handler/
run(responses=); GroupChatBuilder.with_request_info → AgentApprovalExecutor),
but durable checkpoint-resume is fragile (open #5818/#6127/#6372 into 1.9.0)
→ capture verdict out-of-band in VerdictStore, defer checkpointing off MVP path.

Topic 2 (MCP citation): REVERSES brief lean — official server-filesystem cannot
cite (raw text + bare paths) → build thin custom local-folder MCP server
returning {file,locator,snippet,score} over a framework-agnostic in-process
retriever (D7 seam). Corrected docs error: ContextProvider(source_id) +
before_run/after_run + extend_instructions(source_id,...) DO exist in 1.9.0.

Topic 3 (local chat client): use OpenAIChatCompletionClient(base_url) NON-STREAMING
(not OpenAIChatClient/Responses) — installed, 0 new deps, UsageDetails None-safe
and populated non-streaming. Native OllamaChatClient is --pre fallback (spike-gated).
validator-as-retry mitigates weak small-model tool-calling; Intel-CPU = plumbing only.

All grounded in installed 1.9.0 source (source wins over Learn docs). Gemini
bridge unavailable (MCP SDK predates Google May-2026 API change).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Fif1r1En5W542HbZV88yMH
2026-06-24 12:33:42 +02:00
.claude/projects docs(fase2): 3 /trekresearch briefs — installed-source-verified [skip-docs] 2026-06-24 12:33:42 +02:00
docs docs(research): MAF 1.9.0 capability map — feature-utilization for Fase 2 [skip-docs] 2026-06-24 11:36:26 +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 docs(fase2): /trekbrief — gated MVP vertical-slice brief (6/6) [skip-docs] 2026-06-24 11:56:57 +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 .