mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-09-16 20:02:45 +03:00
a86b9019a8
The weight table said stability accounts for "low latency stdDev / error rate". Grep errorRate in scoring.ts and you find it declared on ProviderCandidate and read nowhere — while combo.ts pulls 24 hours of usage history behind a ten-sample floor, falls back to real-time metrics, and hands every candidate an errorRate the scorer ignores. Two candidates, one failing 1% of calls and one failing 99%, scored identically at 0.459486. This declares reliability as a sixteenth factor: 1 - failureRate, using the same formula, field precedence and rate-bounding speedRanking.ts already applies, so a corrupt reading means "nothing observed" rather than "fails every call". It ships at weight 0, leaving the ranking unchanged to the digit — the honest default, since which weight this deserves is a product call backed by traffic the author does not have. Two declared-but-silent factors already ship (cacheAffinity, resetWindowAffinity), so the pattern is not new. The stability row now describes what that factor actually computes: latency variance. The rest is the mechanical 15 → 16 across nineteen documents and the forty-two llm.txt mirrors — sourced from check:docs-counts rather than a grep, the first real use of the gate #12316 extended. Protected-surface note: this PR touches AGENTS.md, llm.txt and its 42 mirrors, and skills/omni-combos-routing/SKILL.md. Every changed line in those 45 files is a digit substitution and nothing else — masking all digits makes the removed and added lines identical, with no sentence added, removed or reworded. Reviewed and approved on that basis before merging. Verified on the author's rebased head: check:docs-counts green (the gate that now enforces the count this PR moves), typecheck:core clean, and 71/71 focused tests across scoring-reliability-factor, combo-scoring-weights-schema-coverage, check-docs-counts-sync, lkgp-enabled-context, intelligent-routing-options and the combo-matrix auto integration suite. Thanks @maxmad64bis — shipping the factor at weight 0 and saying plainly that the weight is someone else's call is the right way to land this.
title, version, lastUpdated
| title | version | lastUpdated |
|---|---|---|
| Diagrams | 3.8.49 | 2026-07-17 |
Diagrams
Mermaid sources (.mmd) and exported SVGs for OmniRoute v3.8.0 architecture flows.
Canonical diagrams
| Source | Exported | Used in |
|---|---|---|
| request-pipeline.mmd | SVG | docs/architecture/ARCHITECTURE.md, docs/architecture/CODEBASE_DOCUMENTATION.md |
| auto-combo-scoring.mmd | SVG | docs/routing/AUTO-COMBO.md |
| resilience-3layers.mmd | SVG | docs/architecture/RESILIENCE_GUIDE.md, CLAUDE.md |
| i18n-flow.mmd | SVG | docs/guides/I18N.md |
| mcp-tools.mmd | SVG | docs/frameworks/MCP-SERVER.md |
| cloud-agent-flow.mmd | SVG | docs/frameworks/CLOUD_AGENT.md |
| authz-pipeline.mmd | SVG | docs/architecture/AUTHZ_GUIDE.md |
| db-schema-overview.mmd | SVG | docs/architecture/CODEBASE_DOCUMENTATION.md |
Hand-authored animated diagrams
Not every diagram comes from a .mmd source. Hand-authored SVGs live at this
directory's root and animate with SMIL only (no JS, no external fonts), so they play
inside GitHub's <img> sandbox:
| File | Used in | Notes |
|---|---|---|
| tier-cascade.svg | README.md (root) | Animated 4-tier auto-fallback cascade (16s loop, 4 acts). Edit the SVG directly — there is no .mmd source. |
| pool-fair-share.svg | — (unused) | Animated key-pool fair-share quota (generous → strict, 16s loop). Edit the SVG directly — there is no .mmd source. |
| combo-always-on.svg | style reference | Animated priority-combo fallback (4 layers, 16s loop). Edit the SVG directly — there is no .mmd source. |
| cli-terminal.svg | README.md (root) | Compact half-height animated terminal (1200×350): 3 real CLI commands cycling with typewriter + scrolling subcommand ticker; first frame = completed providers screen. Edit the SVG directly — there is no .mmd source. |
| compression-pipeline.svg | README.md (root) | Animated 12-engine compression funnel (8s loop). Edit the SVG directly — there is no .mmd source. |
| free-tier-budget.svg | README.md (root) | Animated free-tier budget card (~1.51B/mo quantified headline, 20-pool budget bar, per-pool grid, signup credits, 10s loop). Edit the SVG directly — there is no .mmd source. |
| readme-hero.svg | README.md (root) | Animated hero card (tagline, live provider/free-access headline, full-width compression bar demo, 6 stat chips). Edit the SVG directly — there is no .mmd source. |
| promise-pillars.svg | README.md (root) | Animated "The Promise" 6-pillar card (12s border-highlight sweep). Edit the SVG directly — there is no .mmd source. |
| why-pain-fix.svg | README.md (root) | Animated "Why OmniRoute" 10-row pain-vs-fix ledger (15s green row sweep). Edit the SVG directly — there is no .mmd source. |
| strategies-grid.svg | README.md (root) | Animated grid illustrating 18 of the 19 routing strategies; cache-optimized remains documented in the adjacent table. Edit the SVG directly — there is no .mmd source. |
| privacy-local.svg | README.md (root) | Animated "Private & Local-First" 11-row guarantee ledger with receipt chips (16s green row sweep). Edit the SVG directly — there is no .mmd source. |
| resilience-layers.svg | README.md (root) | Animated 3-layer resilience card (breaker states CLOSED→OPEN→HALF-OPEN, key cooldown with ×2 backoff, model lockout — 18s loops). Edit the SVG directly — there is no .mmd source. |
How to update
- Edit
*.mmd. - Re-render:
npm run docs:render-diagrams(uses@mermaid-js/mermaid-cli). - Commit both
.mmdand.svg.
If @mermaid-js/mermaid-cli is not available locally, install it once:
npm install -g @mermaid-js/mermaid-cli
The script renders every .mmd in docs/diagrams/ into docs/diagrams/exported/*.svg
with a white background, suitable for both dark and light themes.
Linking from a doc
From a doc in docs/<subfolder>/, the relative path becomes ../diagrams/...:
> Source: [../diagrams/request-pipeline.mmd](../diagrams/request-pipeline.mmd)
From the repo root (e.g. CLAUDE.md):
Conventions
- One concept per diagram. Don't try to fit the whole platform in one chart.
- Keep node labels short (3-6 words). Use
<br/>for line breaks inside nodes. - Prefer
flowchart LRfor pipelines andflowchart TBfor layered models. - Use
sequenceDiagramfor interactive (request/response) flows. - Use
erDiagramfor database schema overviews. - Update both
.mmdand.svgin the same commit. Keep them in lock-step.