498 lines
21 KiB
HTML
498 lines
21 KiB
HTML
<!DOCTYPE HTML>
|
|
<html lang="en" class="light sidebar-visible" dir="ltr">
|
|
<head>
|
|
<!-- Book generated using mdBook -->
|
|
<meta charset="UTF-8">
|
|
<title>0015: Budget Enforcement - VAPORA Platform Documentation</title>
|
|
|
|
|
|
<!-- Custom HTML head -->
|
|
|
|
<meta name="description" content="Comprehensive documentation for VAPORA, an intelligent development orchestration platform built entirely in Rust.">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<meta name="theme-color" content="#ffffff">
|
|
|
|
<link rel="icon" href="../favicon.svg">
|
|
<link rel="shortcut icon" href="../favicon.png">
|
|
<link rel="stylesheet" href="../css/variables.css">
|
|
<link rel="stylesheet" href="../css/general.css">
|
|
<link rel="stylesheet" href="../css/chrome.css">
|
|
<link rel="stylesheet" href="../css/print.css" media="print">
|
|
|
|
<!-- Fonts -->
|
|
<link rel="stylesheet" href="../FontAwesome/css/font-awesome.css">
|
|
<link rel="stylesheet" href="../fonts/fonts.css">
|
|
|
|
<!-- Highlight.js Stylesheets -->
|
|
<link rel="stylesheet" id="highlight-css" href="../highlight.css">
|
|
<link rel="stylesheet" id="tomorrow-night-css" href="../tomorrow-night.css">
|
|
<link rel="stylesheet" id="ayu-highlight-css" href="../ayu-highlight.css">
|
|
|
|
<!-- Custom theme stylesheets -->
|
|
|
|
|
|
<!-- Provide site root and default themes to javascript -->
|
|
<script>
|
|
const path_to_root = "../";
|
|
const default_light_theme = "light";
|
|
const default_dark_theme = "dark";
|
|
</script>
|
|
<!-- Start loading toc.js asap -->
|
|
<script src="../toc.js"></script>
|
|
</head>
|
|
<body>
|
|
<div id="mdbook-help-container">
|
|
<div id="mdbook-help-popup">
|
|
<h2 class="mdbook-help-title">Keyboard shortcuts</h2>
|
|
<div>
|
|
<p>Press <kbd>←</kbd> or <kbd>→</kbd> to navigate between chapters</p>
|
|
<p>Press <kbd>S</kbd> or <kbd>/</kbd> to search in the book</p>
|
|
<p>Press <kbd>?</kbd> to show this help</p>
|
|
<p>Press <kbd>Esc</kbd> to hide this help</p>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div id="body-container">
|
|
<!-- Work around some values being stored in localStorage wrapped in quotes -->
|
|
<script>
|
|
try {
|
|
let theme = localStorage.getItem('mdbook-theme');
|
|
let sidebar = localStorage.getItem('mdbook-sidebar');
|
|
|
|
if (theme.startsWith('"') && theme.endsWith('"')) {
|
|
localStorage.setItem('mdbook-theme', theme.slice(1, theme.length - 1));
|
|
}
|
|
|
|
if (sidebar.startsWith('"') && sidebar.endsWith('"')) {
|
|
localStorage.setItem('mdbook-sidebar', sidebar.slice(1, sidebar.length - 1));
|
|
}
|
|
} catch (e) { }
|
|
</script>
|
|
|
|
<!-- Set the theme before any content is loaded, prevents flash -->
|
|
<script>
|
|
const default_theme = window.matchMedia("(prefers-color-scheme: dark)").matches ? default_dark_theme : default_light_theme;
|
|
let theme;
|
|
try { theme = localStorage.getItem('mdbook-theme'); } catch(e) { }
|
|
if (theme === null || theme === undefined) { theme = default_theme; }
|
|
const html = document.documentElement;
|
|
html.classList.remove('light')
|
|
html.classList.add(theme);
|
|
html.classList.add("js");
|
|
</script>
|
|
|
|
<input type="checkbox" id="sidebar-toggle-anchor" class="hidden">
|
|
|
|
<!-- Hide / unhide sidebar before it is displayed -->
|
|
<script>
|
|
let sidebar = null;
|
|
const sidebar_toggle = document.getElementById("sidebar-toggle-anchor");
|
|
if (document.body.clientWidth >= 1080) {
|
|
try { sidebar = localStorage.getItem('mdbook-sidebar'); } catch(e) { }
|
|
sidebar = sidebar || 'visible';
|
|
} else {
|
|
sidebar = 'hidden';
|
|
}
|
|
sidebar_toggle.checked = sidebar === 'visible';
|
|
html.classList.remove('sidebar-visible');
|
|
html.classList.add("sidebar-" + sidebar);
|
|
</script>
|
|
|
|
<nav id="sidebar" class="sidebar" aria-label="Table of contents">
|
|
<!-- populated by js -->
|
|
<mdbook-sidebar-scrollbox class="sidebar-scrollbox"></mdbook-sidebar-scrollbox>
|
|
<noscript>
|
|
<iframe class="sidebar-iframe-outer" src="../toc.html"></iframe>
|
|
</noscript>
|
|
<div id="sidebar-resize-handle" class="sidebar-resize-handle">
|
|
<div class="sidebar-resize-indicator"></div>
|
|
</div>
|
|
</nav>
|
|
|
|
<div id="page-wrapper" class="page-wrapper">
|
|
|
|
<div class="page">
|
|
<div id="menu-bar-hover-placeholder"></div>
|
|
<div id="menu-bar" class="menu-bar sticky">
|
|
<div class="left-buttons">
|
|
<label id="sidebar-toggle" class="icon-button" for="sidebar-toggle-anchor" title="Toggle Table of Contents" aria-label="Toggle Table of Contents" aria-controls="sidebar">
|
|
<i class="fa fa-bars"></i>
|
|
</label>
|
|
<button id="theme-toggle" class="icon-button" type="button" title="Change theme" aria-label="Change theme" aria-haspopup="true" aria-expanded="false" aria-controls="theme-list">
|
|
<i class="fa fa-paint-brush"></i>
|
|
</button>
|
|
<ul id="theme-list" class="theme-popup" aria-label="Themes" role="menu">
|
|
<li role="none"><button role="menuitem" class="theme" id="default_theme">Auto</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="light">Light</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="rust">Rust</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="coal">Coal</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="navy">Navy</button></li>
|
|
<li role="none"><button role="menuitem" class="theme" id="ayu">Ayu</button></li>
|
|
</ul>
|
|
<button id="search-toggle" class="icon-button" type="button" title="Search (`/`)" aria-label="Toggle Searchbar" aria-expanded="false" aria-keyshortcuts="/ s" aria-controls="searchbar">
|
|
<i class="fa fa-search"></i>
|
|
</button>
|
|
</div>
|
|
|
|
<h1 class="menu-title">VAPORA Platform Documentation</h1>
|
|
|
|
<div class="right-buttons">
|
|
<a href="../print.html" title="Print this book" aria-label="Print this book">
|
|
<i id="print-button" class="fa fa-print"></i>
|
|
</a>
|
|
<a href="https://github.com/vapora-platform/vapora" title="Git repository" aria-label="Git repository">
|
|
<i id="git-repository-button" class="fa fa-github"></i>
|
|
</a>
|
|
<a href="https://github.com/vapora-platform/vapora/edit/main/docs/src/../adrs/0015-budget-enforcement.md" title="Suggest an edit" aria-label="Suggest an edit">
|
|
<i id="git-edit-button" class="fa fa-edit"></i>
|
|
</a>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
<div id="search-wrapper" class="hidden">
|
|
<form id="searchbar-outer" class="searchbar-outer">
|
|
<input type="search" id="searchbar" name="searchbar" placeholder="Search this book ..." aria-controls="searchresults-outer" aria-describedby="searchresults-header">
|
|
</form>
|
|
<div id="searchresults-outer" class="searchresults-outer hidden">
|
|
<div id="searchresults-header" class="searchresults-header"></div>
|
|
<ul id="searchresults">
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
|
|
<!-- Apply ARIA attributes after the sidebar and the sidebar toggle button are added to the DOM -->
|
|
<script>
|
|
document.getElementById('sidebar-toggle').setAttribute('aria-expanded', sidebar === 'visible');
|
|
document.getElementById('sidebar').setAttribute('aria-hidden', sidebar !== 'visible');
|
|
Array.from(document.querySelectorAll('#sidebar a')).forEach(function(link) {
|
|
link.setAttribute('tabIndex', sidebar === 'visible' ? 0 : -1);
|
|
});
|
|
</script>
|
|
|
|
<div id="content" class="content">
|
|
<main>
|
|
<h1 id="adr-015-three-tier-budget-enforcement-con-auto-fallback"><a class="header" href="#adr-015-three-tier-budget-enforcement-con-auto-fallback">ADR-015: Three-Tier Budget Enforcement con Auto-Fallback</a></h1>
|
|
<p><strong>Status</strong>: Accepted | Implemented
|
|
<strong>Date</strong>: 2024-11-01
|
|
<strong>Deciders</strong>: Cost Architecture Team
|
|
<strong>Technical Story</strong>: Preventing LLM spend overruns with dual time windows and graceful degradation</p>
|
|
<hr />
|
|
<h2 id="decision"><a class="header" href="#decision">Decision</a></h2>
|
|
<p>Implementar <strong>three-tier budget enforcement</strong> con dual time windows (monthly + weekly) y automatic fallback a Ollama.</p>
|
|
<hr />
|
|
<h2 id="rationale"><a class="header" href="#rationale">Rationale</a></h2>
|
|
<ol>
|
|
<li><strong>Dual Windows</strong>: Previene tanto overspend a largo plazo (monthly) como picos (weekly)</li>
|
|
<li><strong>Three States</strong>: Normal → Near-threshold → Exceeded (progressive restriction)</li>
|
|
<li><strong>Auto-Fallback</strong>: Usar Ollama ($0) cuando budget exceeded (graceful degradation)</li>
|
|
<li><strong>Per-Role Limits</strong>: Budget distinto por rol (arquitecto vs developer vs reviewer)</li>
|
|
</ol>
|
|
<hr />
|
|
<h2 id="alternatives-considered"><a class="header" href="#alternatives-considered">Alternatives Considered</a></h2>
|
|
<h3 id="-monthly-only"><a class="header" href="#-monthly-only">❌ Monthly Only</a></h3>
|
|
<ul>
|
|
<li><strong>Pros</strong>: Simple</li>
|
|
<li><strong>Cons</strong>: Allow weekly spikes, late-month overspend</li>
|
|
</ul>
|
|
<h3 id="-weekly-only"><a class="header" href="#-weekly-only">❌ Weekly Only</a></h3>
|
|
<ul>
|
|
<li><strong>Pros</strong>: Catches spikes</li>
|
|
<li><strong>Cons</strong>: No protection for slow bleed, fragmented budget</li>
|
|
</ul>
|
|
<h3 id="-dual-windows--auto-fallback-chosen"><a class="header" href="#-dual-windows--auto-fallback-chosen">✅ Dual Windows + Auto-Fallback (CHOSEN)</a></h3>
|
|
<ul>
|
|
<li>Protege contra ambos spikes y long-term overspend</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="trade-offs"><a class="header" href="#trade-offs">Trade-offs</a></h2>
|
|
<p><strong>Pros</strong>:</p>
|
|
<ul>
|
|
<li>✅ Protection against both spike and gradual overspend</li>
|
|
<li>✅ Progressive alerts (normal → near → exceeded)</li>
|
|
<li>✅ Automatic fallback prevents hard stops</li>
|
|
<li>✅ Per-role customization</li>
|
|
<li>✅ Quality degrades gracefully</li>
|
|
</ul>
|
|
<p><strong>Cons</strong>:</p>
|
|
<ul>
|
|
<li>⚠️ Alert fatigue possible if thresholds set too tight</li>
|
|
<li>⚠️ Fallback to Ollama may reduce quality</li>
|
|
<li>⚠️ Configuration complexity (two threshold sets)</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="implementation"><a class="header" href="#implementation">Implementation</a></h2>
|
|
<p><strong>Budget Configuration</strong>:</p>
|
|
<pre><code class="language-toml"># config/budget.toml
|
|
|
|
[[role_budgets]]
|
|
role = "architect"
|
|
monthly_budget_usd = 1000
|
|
weekly_budget_usd = 250
|
|
|
|
[[role_budgets]]
|
|
role = "developer"
|
|
monthly_budget_usd = 500
|
|
weekly_budget_usd = 125
|
|
|
|
[[role_budgets]]
|
|
role = "reviewer"
|
|
monthly_budget_usd = 200
|
|
weekly_budget_usd = 50
|
|
|
|
# Enforcement thresholds
|
|
[enforcement]
|
|
normal_threshold = 0.80 # < 80%: Use optimal provider
|
|
near_threshold = 1.0 # 80-100%: Cheaper providers
|
|
exceeded_threshold = 1.0 # > 100%: Fallback to Ollama
|
|
|
|
[alerts]
|
|
near_threshold_alert = true
|
|
exceeded_alert = true
|
|
alert_channels = ["slack", "email"]
|
|
</code></pre>
|
|
<p><strong>Budget Tracking Model</strong>:</p>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>// crates/vapora-llm-router/src/budget.rs
|
|
pub struct BudgetState {
|
|
pub role: String,
|
|
pub monthly_spent_cents: u32,
|
|
pub monthly_budget_cents: u32,
|
|
pub weekly_spent_cents: u32,
|
|
pub weekly_budget_cents: u32,
|
|
pub last_reset_week: Week,
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
|
pub enum EnforcementState {
|
|
Normal, // < 80%: Use optimal provider
|
|
NearThreshold, // 80-100%: Prefer cheaper
|
|
Exceeded, // > 100%: Fallback to Ollama
|
|
}
|
|
|
|
impl BudgetState {
|
|
pub fn monthly_percentage(&self) -> f32 {
|
|
(self.monthly_spent_cents as f32) / (self.monthly_budget_cents as f32)
|
|
}
|
|
|
|
pub fn weekly_percentage(&self) -> f32 {
|
|
(self.weekly_spent_cents as f32) / (self.weekly_budget_cents as f32)
|
|
}
|
|
|
|
pub fn enforcement_state(&self) -> EnforcementState {
|
|
let monthly_pct = self.monthly_percentage();
|
|
let weekly_pct = self.weekly_percentage();
|
|
|
|
// Use more restrictive of two
|
|
let most_restrictive = monthly_pct.max(weekly_pct);
|
|
|
|
if most_restrictive < 0.80 {
|
|
EnforcementState::Normal
|
|
} else if most_restrictive < 1.0 {
|
|
EnforcementState::NearThreshold
|
|
} else {
|
|
EnforcementState::Exceeded
|
|
}
|
|
}
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<p><strong>Budget Enforcement in Router</strong>:</p>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>pub async fn route_with_budget(
|
|
task: &Task,
|
|
user_role: &str,
|
|
budget_state: &mut BudgetState,
|
|
) -> Result<String> {
|
|
// Check budget state
|
|
let enforcement = budget_state.enforcement_state();
|
|
|
|
match enforcement {
|
|
EnforcementState::Normal => {
|
|
// Use optimal provider (Claude, GPT-4)
|
|
let provider = select_optimal_provider(task).await?;
|
|
execute_with_provider(task, &provider, budget_state).await
|
|
}
|
|
EnforcementState::NearThreshold => {
|
|
// Alert user, prefer cheaper providers
|
|
alert_near_threshold(user_role, budget_state)?;
|
|
let provider = select_cheap_provider(task).await?;
|
|
execute_with_provider(task, &provider, budget_state).await
|
|
}
|
|
EnforcementState::Exceeded => {
|
|
// Alert, fallback to Ollama
|
|
alert_exceeded(user_role, budget_state)?;
|
|
let provider = "ollama"; // Free
|
|
execute_with_provider(task, provider, budget_state).await
|
|
}
|
|
}
|
|
}
|
|
|
|
async fn execute_with_provider(
|
|
task: &Task,
|
|
provider: &str,
|
|
budget_state: &mut BudgetState,
|
|
) -> Result<String> {
|
|
let response = call_provider(task, provider).await?;
|
|
let cost_cents = estimate_cost(&response, provider)?;
|
|
|
|
// Update budget
|
|
budget_state.monthly_spent_cents += cost_cents;
|
|
budget_state.weekly_spent_cents += cost_cents;
|
|
|
|
// Log for audit
|
|
log_budget_usage(task.id, provider, cost_cents)?;
|
|
|
|
Ok(response)
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<p><strong>Reset Logic</strong>:</p>
|
|
<pre><pre class="playground"><code class="language-rust"><span class="boring">#![allow(unused)]
|
|
</span><span class="boring">fn main() {
|
|
</span>pub async fn reset_budget_weekly(db: &Surreal<Ws>) -> Result<()> {
|
|
let now = Utc::now();
|
|
let current_week = week_number(now);
|
|
|
|
let budgets = db.query(
|
|
"SELECT * FROM role_budgets WHERE last_reset_week < $1"
|
|
)
|
|
.bind(current_week)
|
|
.await?;
|
|
|
|
for mut budget in budgets {
|
|
budget.weekly_spent_cents = 0;
|
|
budget.last_reset_week = current_week;
|
|
db.update(&budget.id).content(&budget).await?;
|
|
}
|
|
|
|
Ok(())
|
|
}
|
|
<span class="boring">}</span></code></pre></pre>
|
|
<p><strong>Key Files</strong>:</p>
|
|
<ul>
|
|
<li><code>/crates/vapora-llm-router/src/budget.rs</code> (budget tracking)</li>
|
|
<li><code>/crates/vapora-llm-router/src/cost_tracker.rs</code> (cost calculation)</li>
|
|
<li><code>/crates/vapora-llm-router/src/router.rs</code> (enforcement logic)</li>
|
|
<li><code>/config/budget.toml</code> (configuration)</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="verification"><a class="header" href="#verification">Verification</a></h2>
|
|
<pre><code class="language-bash"># Test budget percentage calculation
|
|
cargo test -p vapora-llm-router test_budget_percentage
|
|
|
|
# Test enforcement states
|
|
cargo test -p vapora-llm-router test_enforcement_states
|
|
|
|
# Test normal → near-threshold transition
|
|
cargo test -p vapora-llm-router test_near_threshold_alert
|
|
|
|
# Test exceeded → fallback to Ollama
|
|
cargo test -p vapora-llm-router test_budget_exceeded_fallback
|
|
|
|
# Test weekly reset
|
|
cargo test -p vapora-llm-router test_weekly_budget_reset
|
|
|
|
# Integration: full budget lifecycle
|
|
cargo test -p vapora-llm-router test_budget_full_cycle
|
|
</code></pre>
|
|
<p><strong>Expected Output</strong>:</p>
|
|
<ul>
|
|
<li>Budget percentages calculated correctly</li>
|
|
<li>Enforcement state transitions as budget fills</li>
|
|
<li>Near-threshold alerts triggered at 80%</li>
|
|
<li>Fallback to Ollama when exceeded 100%</li>
|
|
<li>Weekly reset clears weekly budget</li>
|
|
<li>Monthly budget accumulates across weeks</li>
|
|
<li>All transitions logged for audit</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="consequences"><a class="header" href="#consequences">Consequences</a></h2>
|
|
<h3 id="financial"><a class="header" href="#financial">Financial</a></h3>
|
|
<ul>
|
|
<li>Predictable monthly costs (bounded by monthly_budget)</li>
|
|
<li>Alert on near-threshold prevents surprises</li>
|
|
<li>Auto-fallback protects against runaway spend</li>
|
|
</ul>
|
|
<h3 id="user-experience"><a class="header" href="#user-experience">User Experience</a></h3>
|
|
<ul>
|
|
<li>Quality degrades gracefully (not hard stop)</li>
|
|
<li>Users can continue working (Ollama fallback)</li>
|
|
<li>Alerts notify of budget status</li>
|
|
</ul>
|
|
<h3 id="operations"><a class="header" href="#operations">Operations</a></h3>
|
|
<ul>
|
|
<li>Budget resets automated (weekly)</li>
|
|
<li>Per-role customization allows differentiation</li>
|
|
<li>Cost reports broken down by role</li>
|
|
</ul>
|
|
<h3 id="monitoring"><a class="header" href="#monitoring">Monitoring</a></h3>
|
|
<ul>
|
|
<li>Track which roles consuming most budget</li>
|
|
<li>Identify unusual spend patterns</li>
|
|
<li>Forecast end-of-month spend</li>
|
|
</ul>
|
|
<hr />
|
|
<h2 id="references"><a class="header" href="#references">References</a></h2>
|
|
<ul>
|
|
<li><code>/crates/vapora-llm-router/src/budget.rs</code> (budget implementation)</li>
|
|
<li><code>/crates/vapora-llm-router/src/cost_tracker.rs</code> (cost tracking)</li>
|
|
<li><code>/config/budget.toml</code> (configuration)</li>
|
|
<li>ADR-007 (Multi-Provider LLM)</li>
|
|
<li>ADR-016 (Cost Efficiency Ranking)</li>
|
|
</ul>
|
|
<hr />
|
|
<p><strong>Related ADRs</strong>: ADR-007 (Multi-Provider), ADR-016 (Cost Efficiency), ADR-012 (Routing Tiers)</p>
|
|
|
|
</main>
|
|
|
|
<nav class="nav-wrapper" aria-label="Page navigation">
|
|
<!-- Mobile navigation buttons -->
|
|
<a rel="prev" href="../../adrs/0014-learning-profiles.html" class="mobile-nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../../adrs/0016-cost-efficiency-ranking.html" class="mobile-nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
|
|
<div style="clear: both"></div>
|
|
</nav>
|
|
</div>
|
|
</div>
|
|
|
|
<nav class="nav-wide-wrapper" aria-label="Page navigation">
|
|
<a rel="prev" href="../../adrs/0014-learning-profiles.html" class="nav-chapters previous" title="Previous chapter" aria-label="Previous chapter" aria-keyshortcuts="Left">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
<a rel="next prefetch" href="../../adrs/0016-cost-efficiency-ranking.html" class="nav-chapters next" title="Next chapter" aria-label="Next chapter" aria-keyshortcuts="Right">
|
|
<i class="fa fa-angle-right"></i>
|
|
</a>
|
|
</nav>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<script>
|
|
window.playground_copyable = true;
|
|
</script>
|
|
|
|
|
|
<script src="../elasticlunr.min.js"></script>
|
|
<script src="../mark.min.js"></script>
|
|
<script src="../searcher.js"></script>
|
|
|
|
<script src="../clipboard.min.js"></script>
|
|
<script src="../highlight.js"></script>
|
|
<script src="../book.js"></script>
|
|
|
|
<!-- Custom JS scripts -->
|
|
|
|
|
|
</div>
|
|
</body>
|
|
</html>
|