---
title: "Glossary"
description: "Definitions of key terms used throughout the Orchid documentation."
package: cross-cutting
section: meta
html_url: https://orchestratorindex.com/glossary
markdown_url: https://orchestratorindex.com/glossary.md
---

# Glossary

A quick-reference dictionary of terms used across the Orchid documentation. Each entry links to the page where the concept is explained in depth.

| Term | Definition |
|---|---|
| **Agent** | A named, YAML-configured unit of intelligence that handles a specific domain. Each agent has a description, a set of tools, and an optional custom class. See [Agents](/concepts/agents). |
| **Agentic loop** | The inner reasoning cycle where an LLM issues `tool_calls`, the framework executes them, and the results are fed back until the LLM produces a final answer. See [Agents](/concepts/agents). |
| **AGENTS.md** | A per-package Markdown file containing AI-specific context: structure, rules, patterns, and pitfalls. |
| **Bearer token** | An HTTP `Authorization: Bearer <token>` credential. Orchid resolves it to an `OrchidAuthContext` at the API entry point via `OrchidIdentityResolver`. See [OAuth & Auth](/concepts/oauth). |
| **Boilerplate** | The minimal code needed to wire a new consumer agent into Orchid — typically a YAML entry plus an optional Python subclass of `OrchidAgent`. |
| **DCR (Dynamic Client Registration)** | RFC 7591 — the protocol Orchid uses in `oauth` MCP auth mode to register a new OAuth client with a server's authorisation server at runtime, without pre-provisioned credentials. See [OAuth & Auth](/concepts/oauth). |
| **Embedding** | A fixed-length numeric vector that encodes the semantic meaning of a text chunk. Orchid uses embeddings to index and retrieve documents in the vector store (Qdrant or ChromaDB). See [Embeddings](/concepts/embeddings). |
| **Hierarchical RAG** | Orchid's five-level scoping system (root → tenant → user → chat → agent) that controls which vector collections an agent can read from. See [Hierarchical RAG](/concepts/rag). |
| **Bloom** | The execution layer of Pollen + Bloom. Triggers match incoming Signals and run them through the LangGraph supervisor as `JobRun`s. See [Pollen + Bloom](/concepts/pollen-bloom). |
| **Chat model** | A LangChain `BaseChatModel` injected into every agent by the graph builder via `build_chat_model()` (`llm_factory.py`). Consumer agents call `self.summarise()` rather than depending on a concrete provider. |
| **Decision model** | A dedicated LLM that returns typed answers (boolean, choice, score) with calibrated confidence for internal judgements, instead of generated prose. Bound to decision points via the `decisions:` YAML block. See [Decision Models](/concepts/decision-models). |
| **Decision point** | A named seam (e.g. `routing`, `guardrails`, `retrieval_strategy`) where a decision model is asked to judge. Points are declared in a registry, bound via YAML, and fall back to pre-existing behaviour on any failure. See [Decision Models](/concepts/decision-models). |
| **Fallback policy** | The per-point mode that describes the behaviour used when a decision is unavailable, refused, or not confident (e.g. `all_tools`, `configured_strategy`, `no_delegation`). The legacy path is always preserved. See [Decision Models](/concepts/decision-models). |
| **Mini-agent** | A parallel sub-agent forked by an opt-in parent during a single turn. The parent decomposes the request, N minis run focused agentic loops in parallel, and an aggregator synthesises the outcomes. See [Mini-Agents](/concepts/mini-agents). |
| **`OrchidAgent`** | The base ABC (`orchid_ai.core.agent`) that every agent class extends. Provides `run()`, `summarise()`, `extract_conversation_history()`, and RAG helpers. See [Agents](/concepts/agents). |
| **`OrchidAuthContext`** | A context object (`orchid_ai.core.state`) carrying `tenant_key`, `user_id`, and `bearer_header`. Resolved once at the API entry point and passed via the LangGraph run configuration — never persisted in graph state. See [OAuth & Auth](/concepts/oauth). |
| **`OrchidChatStorage`** | The ABC (`orchid_ai.persistence.base`) for chat session and message persistence. The framework ships a dependency-free in-memory implementation as the default; durable SQLite and PostgreSQL implementations live in the `orchid-storage-sqlite` and `orchid-storage-postgres` plugins. See [Persistence](/concepts/persistence). |
| **`OrchidMCPClient`** | The abstract MCP client (`orchid_ai.core.mcp`) combining `OrchidMCPToolCaller` and `OrchidMCPDiscoverable`. Handles capability discovery, caching, and tool invocation. See [MCP Integration](/concepts/mcp). |
| **`OrchidRAGScope`** | A frozen dataclass (`orchid_ai.rag.scopes`) that constructs typed, hierarchical filter objects for the vector store backend. Always use this — never pass raw `tenant_id` strings. See [Hierarchical RAG](/concepts/rag). |
| **Parse-once** | The pattern of calling `extract_text()` exactly once per document and passing the result to both the prompt builder and `ingest_document(pre_extracted_text=...)`. Avoids double-parsing cost. See [Document Parsing](/concepts/document-parsing). |
| **Pollen** | The event-ingestion substrate of Pollen + Bloom. Ingests, persists, and dispatches immutable `Signal`s from webhooks, schedulers, agents, or custom producers. See [Pollen + Bloom](/concepts/pollen-bloom). |
| **Passthrough auth** | MCP auth mode where the user's bearer token is forwarded unchanged to the MCP server. The server must trust the same identity provider as the Orchid API. See [MCP Integration](/concepts/mcp). |
| **Scope (RAG)** | A level in the five-level hierarchy (root / tenant / user / chat / agent) that determines which vector collections are visible to a retrieval query. See [Hierarchical RAG](/concepts/rag). |
| **Sliding-window summarization** | A supervisor feature (enabled by default) that compresses older conversation turns into a summary, keeping only the most recent exchanges verbatim. Reduces token usage for long sessions. See [Supervisor](/concepts/supervisor). |
| **Supervisor** | The LangGraph node that routes user messages to the correct agent, manages conversation history, and assembles the final response. Configurable via the `supervisor:` YAML section. See [Supervisor](/concepts/supervisor). |
| **Tool strategy** | The algorithm used by `GenericAgent` to invoke tools during skill execution: `all` (parallel), `sequential`, or `llm_decides`. See [Tool Strategies](/concepts/tool-strategies). |
| **Vector store** | A database optimised for approximate nearest-neighbour search over embedding vectors. Orchid supports Qdrant (full-featured, containerised) and ChromaDB (embedded, on-disk, zero-infra CLI default). See [Hierarchical RAG](/concepts/rag). |
| **YAML-first** | Orchid's design principle that new agents, tool strategies, and parser registrations are added via YAML configuration rather than code changes, following the Open/Closed principle. See [Configuration](/configuration). |
