Glossary
Every kdeps term defined in one place. The first mention of any term on other docs pages links here. This is a reference page and applies to both workflow mode and agent mode.
| Term | Definition | More |
|---|---|---|
actionId | A unique string that identifies a resource within a workflow. Used as the target of requires: dependencies. In agent mode, resources are not exposed as tools; the whole workflow is the tool, named after metadata.name. | Resources overview |
| agent | A kind: Workflow (or a kind: Agency) started with kdeps [path]. The LLM calls the whole workflow as one tool named after metadata.name. There is no kind: Agent - kind: is Workflow, Component, or Agency. | Agent mode |
| agency | Multiple agents composed into one system. One agent delegates a task to another via the agent: action type; the callee runs its full pipeline and returns its output. | AI agencies |
apiResponse | A resource action type that returns a structured JSON response to the client. Usually the terminal node of a workflow. | API response |
before / after | Expression blocks that run before or after a resource's main action. Used for data preparation, normalization, and validation. Statements execute in order. | Expression blocks |
browser | A resource action type for browser automation. Navigates pages, clicks elements, fills forms, and extracts content. | Browser |
chat | A resource action type for LLM chat completion. Sends a prompt and returns the response. The most common action type. | LLM (chat) |
check | A list of boolean expressions in validations.check. All must be true or the resource fails and the workflow stops. | Validation and control flow |
codeIntelligence | A resource action type for code navigation: symbol search, definition lookup, reference finding, hover info, and diagnostics. | Code intelligence |
| component | A reusable, packaged resource bundle. Installed from the registry or built in a components/ directory. Declared as kind: Component. | Components |
componentTools | Tools provided by a component that are exposed to the calling agent or workflow for the LLM to invoke. | Components |
| deterministic | Same input, same output, every time. In kdeps this describes the workflow-mode pipeline - route matching, requires: ordering, validations, and response shaping all resolve the same way for a given request. It does not describe the LLM's text output. Contrast probabilistic. | Deterministic by design |
embedding | A resource action type for a local SQLite keyword store: index, search, upsert, delete. Matching is SQL LIKE, not vector similarity. For OpenAI vector embeddings, kdeps registry install embedding. | Embedding |
exec | A resource action type that runs shell commands and captures stdout, stderr, and exit code. | Exec |
| expr | Short for expression: a statement evaluated by the expr-lang engine. Used in before: / after: blocks, validations, and | Expressions |
file() | An expression function that reads uploaded or local files. Takes a glob pattern and an optional selector (first, last, count, all, mime:<type>). | Unified API |
file (resource) | A resource action type for filesystem operations: read, write, patch, list, delete, mkdir, copy, move, append. | File |
get() | The primary data access function. Reads from query params, headers, body, session, memory, environment, or resource outputs, with auto-detection. | Unified API |
git | A resource action type for version control: status, diff, log, commit, branch, push, pull. | Git |
httpClient | A resource action type for HTTP requests. Supports all methods, headers, query params, body, retry, and caching. | HTTP client |
info() | An expression function that returns request metadata: ID, timestamp, path, method, IP, sessionId, filecount, files, filetypes. | Unified API |
items | An array a resource iterates over. The resource runs once per item. Access the current item via item.current() or get('current'). | Items iteration |
jsonResponse | A boolean field on chat resources. When true, forces the LLM to return valid JSON with no markdown wrapping. | LLM (chat) |
loop | A while-loop on a resource. The body runs while the while expression is true, up to maxIterations. every: turns it into a scheduled ticker. | While-loop iteration |
| memory (expression) | Request-scoped key/value storage. Set with set('key', value, 'memory'); read with get('key', 'memory'). Cleared when the request completes. | Session and memory |
| memory (persistent) | Project-scoped storage for the agent loop in a bbolt database that survives across sessions. Built-in tools: memory_save, memory_search, memory_delete, memory_list, memory_query. | Persistent memory |
| memory graph | A directed graph of memory entries linked by their References fields and auto-linked by type. Inlined into the <memory> block in causal order. | Memory internals |
output() | An expression function that reads the output of a completed resource by its actionId. | Unified API |
| probabilistic | The same prompt can produce different output on each call. Every language model - Claude, GPT, Gemini, Groq, Ollama, local llamafile / GGUF - is probabilistic. A kdeps chat: resource inherits this; the pipeline around it stays deterministic. | LLM provider reference |
python | A resource action type that runs Python scripts. Supports inline scripts, file paths, packages, and virtual environments. | Python |
requires | A list of actionIds that must complete before this resource runs. Defines the DAG edges. Transitive dependencies resolve automatically. | Execution flow |
| resource | The fundamental building block of a workflow: an actionId, a primary action type, optional requires, and optional validations, loop, and error handling. | Resources overview |
| scenario | A test case for a resource or workflow: inputs and expected outputs, checked during kdeps validate. | Validation examples |
scraper | A resource action type for web scraping. Extracts structured data from HTML using CSS selectors. | Scraper |
searchLocal | A resource action type for local semantic search over indexed documents. | searchLocal |
searchWeb | A resource action type for web search via configured search APIs. | searchWeb |
| session | HTTP session storage across requests from the same client. Set with set('key', value, 'session'). Not the agent REPL conversation (--resume, ~/.kdeps/sessions/). | Session configuration |
set() | Stores a value in memory (this request) or session (across requests). | Unified API |
skip | A list of boolean expressions in validations.skip. If any is true, the resource is skipped silently and the workflow continues. | Validation and control flow |
sql | A resource action type for SQL queries against PostgreSQL, MySQL, or SQLite. Parameterized queries prevent injection. | SQL |
| stealth mode | A "Muted" agent-loop UI: the whole REPL renders in near-black dark grays and the model name is barely visible - for running kdeps in public. Enable with --stealth, KDEPS_STEALTH=1, or /stealth. Rendering only; prompts, responses, and logs are unchanged. | Agent loop REPL features |
streaming | A boolean field on chat resources. When true, the LLM response streams token by token. | LLM backends |
targetActionId | The entry-point resource of a workflow, set in metadata.targetActionId. Execution resolves the dependency graph backward from here. | workflow.yaml |
| tools | Functions registered with the LLM. In agent mode, tools are whole workflows and components. In workflow mode, tools are functions defined in chat.tools. | Tools |
validations | A resource-level block with skip, check, routes, methods, and error. Controls whether a resource runs and how it fails. | Validation and control flow |
| workflow | The top-level unit of execution: a YAML file defining resources, dependencies, and configuration. Declared as kind: Workflow. | workflow.yaml |
See also
- Execution flow - how the DAG resolves and runs
- Expression functions reference - every function available in expressions
- Expression operators - comparison and logical operators