Glossary
Every kdeps term defined in one place. The first mention of any term on other docs pages links here. A workflow is the one way to run kdeps; the agent loop is a chat with loop: inside it.
| Term | Definition | More |
|---|---|---|
actionId | A unique string that identifies a resource within a workflow. Used as the target of requires: dependencies. | Resources overview |
| agent | A workflow whose chat has a loop: block: the model calls tools over many rounds and keeps one conversation per loop.session id. There is no kind: Agent - kind: is Workflow, Component, or Agency. | Agent loop |
| input source | How requests reach a workflow: api (HTTP), bot, file, or interactive (a terminal prompt where each line is one request). Set under deploy.input.sources. | Input sources |
| 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 |
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 |
| component | A reusable, packaged resource bundle. Installed from the registry or built in a components/ directory. Declared as kind: Component. | Components |
tools.components | 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 | The shipped component around the native embedding executor: a local SQLite keyword store (index, search, upsert, delete), an embedding backend (vectorize, embed_query), and Cohere rerank. Keyword matching is SQL LIKE, not vector similarity. | Embedding |
exec | The kdeps component that runs a shell command through the kdeps API and returns the structured result (success, exitCode, stdout, stderr, command, result, timedOut). | exec |
| eval | The judge panel. A chat turns it on with judges: or judges: auto under guardrails. It reviews the answer on its own. | Judge panel |
| expr | Short for expression: a statement evaluated by the expr-lang engine. Used in before: / after: blocks, validations, and string interpolation. | 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 | A kdeps component (component: file) 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 kdeps component (component: git) for version control: status, diff, log, commit, branch, push, pull. | Git |
| grader | A check attached to a judge with graders:. Kinds: exact, contains, not_contains, regex, json, expr. It runs on the answer in process. A failure rejects that judge before it calls the model. | Judge panel |
http_request | A kdeps component (component: http_request) for HTTP requests. Supports all methods, headers, query params, body, retry, caching, and named connections. | 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 |
harness.output.json | A boolean field on chat resources. When true, forces the LLM to return valid JSON with no markdown wrapping. | LLM (chat) |
| judge | One reviewer on the eval. The name stays judge: judges:, judge_verdict, the harness prompts. The items are filed on the evals shelf. | Judge panel |
| kdeps API | The process control listener of kdeps run. It binds 127.0.0.1, requires KDEPS_API_TOKEN, and serves discovery, tool calls (read_file, write_file, bash_exec, bash_job_list, bash_job_wait, sql_ops, memory_save, memory_search, memory_delete, memory_query, http_request, search_local, load_document, embedding, embedding_search, embedding_vectorize, the four approval_* tools, instruct, and the asset-declared tools (calculator, edit_file, file_ops, git_ops, google_cache_*, list_files, md5_file, sql_list_tables, sql_describe_table, sql_query, tail_file, web_search, web_scraper, wikipedia, the rerankers, exa_search, ocr_image, retrieve_context, transcribe_audio, transcribe_audio_offline, wolfram_alpha, zapier_*)). It is not the workflow apiServer and it is not /_kdeps/. | kdeps API |
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, kept as markdown notes in the knowledge vault, that survives across sessions. Built-in tools: memory_save, memory_search, memory_delete, memory_query. The graph is injected into the prompt. Workflow resources can still call memory_list(). | 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 | The kdeps component that runs a Python script through the kdeps API and returns stdout parsed as JSON when possible. Supports inline scripts, file paths, packages, and virtualenvs. | 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 |
search_local | A kdeps component (component: search_local) that searches local files by keyword and glob, optionally with a TF-IDF index and graph boost. | search_local |
| session | HTTP session storage across requests from the same client. Set with set('key', value, 'session'). Not the agent loop conversation (loop.session). | Session configuration |
set() | Stores a value in memory (this request) or session (across requests). | Unified API |
| shelf | The engineering word an asset is filed under: model, context, harness, tools, memory, rag, agent, guardrails, evals, workflow, deploy. The path stays the id (harness/safety). kdeps list <shelf> shows one. Install profiles are a separate axis. | Installation |
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 kdeps component (component: sql) for SQL against PostgreSQL, MySQL, SQLite, SQL Server or Oracle. Parameterized queries prevent injection. | SQL |
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 as targetActionId: under metadata:. Execution resolves the dependency graph backward from here. | workflow.yaml |
| tools | Functions registered with the LLM. On a chat resource, tools are the functions in tools:. | Built-in tools. Function calling |
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
