Skip to main content

🇬🇧 English · 🇷🇺 Русский

vesma-vitals

Methodology and instrumentation for honest measurement of the Vesma memory server. Prove — or honestly refute — every promise: dynamic context, the right memory per request, token savings, the health of every subsystem.

Navigation · What it is · Why a separate project · Architecture · Documentation · Status

What it is

The Vesma owner framed the problem (2026-09-09): "in words and in docs everything looks great, but in practice there is no feeling that the context is REALLY composed dynamically. How many tokens do we actually save? Does the right instruction or a piece of memory get substituted on request?" The server stands (S1–S4) measure output quality and latency — none answers what memory gives the loop or whether every function actually works.

vesma-vitals closes this gap with two circuits:

Circuit Question Scope
Health "Does the function work?" Every server function: invoked / succeeded / latency / errors. Rule: no function ships in a release without its own circuit.
Value "What does the function contribute?" Only functions with a product promise. Causal value ("how many tokens saved") is proved only by the two-arm S5 replay stand — "saved X" claims from passive data are banned.

Both decisions were made by the Vesma Architectural Committee (2026-09-09, mnemos record 7ec9dda3 core + 061398fe addendum "full functionality"); ADR-0026 is the formal record. This repository is the implementation.

Why a separate project

  • Trust boundary: the metrics collector is a guest in the server. Code isolation rules out accidental coupling of telemetry with the assemble_context pipeline and the main store.
  • Embedding contract: vesma-vitals embeds into vesma at a minimal set of points (10 defined boundaries); the server does not depend on it.
  • Speed: its own CI, its own releases, its own review cycle — metrics do not wait for the server's release window.
  • Reusability: the methodology applies to any memory server with the same contract shape (harness → memory → model).

Navigation

Section Contents Audience
docs/methodology.md Full methodology: zones, circuits, metrics, statuses, phases Everyone — entry point
docs/token-economy.md Token economy — metric #1: schema rent, tokens-per-task, savings vs baseline, break-even N* Anyone comparing models/tools/methods
docs/architecture.md Components, data schema, collection points, Prometheus hybrid Implementers
docs/decisions/ Decision log (ArchCom canon carried over) Future contributors
docs/claims.md Claims ledger: promise → metric → status Owner — "what is already proven"
docs/experiments/ Pre-registrations (anti-HARKing, before the first run); template — TEMPLATE.md with a mandatory "Token savings" section before the verdict Analysts
src/vesma_vitals/ Code: sink, ledger, exposer, S5 stand Implementers
CHANGELOG.md Change history Everyone

Architecture

flowchart LR
    subgraph VESMA["Vesma server (unchanged)"]
        AC[assemble_context and others]
        EP[10 boundaries: MCP / REST / background / CLI]
    end
    subgraph VITALS["vesma-vitals"]
        SINK["MetricsSink<br/>allowlist, fail-closed"]
        LEDGER[("metrics.sqlite sidecar<br/>5 born-final tables")]
        S5["S5 memory-value stand<br/>two arms on/off"]
        EXP["Prometheus hybrid<br/>counters + p50/p95 from rollup"]
        REPORT["Report: F8/F9 traffic light<br/>PASS / FAIL / NO-DATA"]
    end
    EP -->|verb, status, latency, project| SINK
    SINK --> LEDGER
    LEDGER --> EXP
    LEDGER --> S5
    S5 --> REPORT
    EXP --> REPORT

Key properties: allowlist schema with no columns for raw text (privacy by structure, not by filtering), keyed-HMAC fingerprints, born no-federate, TTL 30/90 days fail-loud, status taxonomy — invariant / corridor / verdict.

Documentation

Document Role
docs/methodology.md Methodology canon: what and how we measure, thresholds, honesty
docs/architecture.md Technical specification of the implementation
docs/decisions/0001-two-circuits.md Why two circuits, not "value for everything"
docs/decisions/0002-sidecar-ledger.md Why a sidecar store, not tables in the main store
docs/decisions/0003-family-boundaries.md Metric-family boundary rule (theme, not tier)

Status

Foundation laid (2026-09-09); phase A in progress. The passive-collection library core is ready (born-final schema + C1 canary + MetricsStore); vesma integration is a separate PR in the server repo. Full status — docs/status.md. Promises and their measured status — docs/claims.md.

Critical actions

Action Command Safety
Reset metrics.sqlite (local metrics store) rm <data_dir>/metrics.sqlite Allowed: metrics are not audit records; the store is recreated born-final
Full re-install of the vitals surface rm -rf <data_dir>/vitals Allowed: does not touch the main vesma store
Disable collection vitals.enabled: false in config Allowed: non-fatal write refusal by design

Any action touching the main vesma store is performed only by vesma's own means — vesma-vitals has no write API into it.


Licensing is the owner's decision; the project inherits the canon of the Vesma ecosystem (vesma — the server, vesma-eyes — the web viewer).

Metadata

Release files for vesma-vitals 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for vesma-vitals 0.1.2
File Interpreter ABI Platform
vesma_vitals-0.1.2-py3-none-any.whl Python 3 none any Details

Release files / vesma_vitals-0.1.2-py3-none-any.whl

Download URL vesma_vitals-0.1.2-py3-none-any.whl
Size 33.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c75dccf5a9bae65a67b430a6257e11176e2d0a68c6f818f54269896c72306141
BLAKE2b-256 checksum
How to use checksums
aaa14c036fe004a9c06ecc85aa2feef5be30b84063ef31b20e02d816dfd0e52d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.12.23 {"installer":{"name":"uv","version":"0.12.23","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for vesma-vitals 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page