Schema
Glossary
Glossary
Authoritative definitions for every LADR + Redeo term. Mirrors Appendix A of the master spec.
Core language terms
| Term | Definition |
|---|---|
| LADR | Language for Adaptive Deliberation and Reasoning. The declarative DSL for writing ladders. Config files use the .ladr extension. |
| Ladder | A complete reasoning program; a pipeline configuration written in LADR. Atomic unit a user authors, publishes, runs, and shares. Identified publicly as @author/name. |
| Step | Execution unit within a ladder. Type: normal, sequential, or group. Has fields, system prompt, optional gates, jumps, recursion, slate operations. |
| Node | A single LLM call within a step. nodes: 5 fans out into 5 calls (parallel for normal, sequential for sequential). |
| Field | A named prompt slot with a typed source. Rendered into the LLM call as Name: <value>. Types: text, ingest, multi_ingest, nodeInfo, knobInfo, slateRead, manifest. |
| Knob | Caller-tunable control declared at config time. Adjusted at call time. Categorized as loops, recursion, nodes, or generic; UI input is slider or numerical. |
| Loop | A full iteration of the step sequence. Multi-loop ladders run the sequence N times; later loops can read prior loops via loopRef. |
| Recursion | A step spawning a child instance of the same ladder; the child result bubbles up. Bounded by maxRecursion. |
| Group | Step type containing sibling steps that run in parallel. Cannot be nested. |
| Gate | The if block; typed predicate evaluated per node, with then/else actions. Eight condition kinds are supported. |
| Jump | Action under then/else that repositions the engine's mutable cursor to another step (within-ladder) or another ladder (cross-ladder handoff). |
| Dynamic step | A step whose config (systemPrompt/fields/nodes, and optionally if/jump/recursion/retrieve) is loaded at runtime from a declared source rather than declared statically. The primitive that enables self-improvement. |
| Manifest | Runtime index of everything readable at a given step (inputs, knobs, prior step outputs, slate state). Used to inform dynamic step generation. |
Memory terms
| Term | Definition |
|---|---|
| Slate | Persistent memory store; folders of .md files with metatags. Survives across ladder invocations. Per-user by default. |
| Folder | Named container inside a slate. Has its own token budget, access policy, eviction policy, and metatag schema. |
| File | Plain-text (typically Markdown) inside a folder. Can be prose OR structured JSON (arbitrary depth). |
| Metatag | Named, typed value attached to a file (or auto-maintained at folder level). The universal primitive for describing and retrieving file data. |
| System metatag | Engine-maintained metatag: index, tree, created, modified, size. Always present, read-only. |
| User metatag | Author-declared metatag with type (string, string[], number, boolean, object). Writable via slateWrite. |
| Effective schema | The union of folder-level and file-level metatags for a specific file. File-level wins on conflicts. |
| slateRead | Field source that reads file contents, a metatag value, or a system metatag from a slate. Shape: { slate, folder, file?, metatag?, depth? }. |
| slateWrite | Step-level directive that extracts JSON from LLM output, validates against a schema, and writes if valid. No-match is no-op, not error. |
| Gated write | Write action under if/then that writes unconditionally on gate match (no schema extraction). |
| mergeByKey | Write policy that maintains a structured JSON store by merging entries on a key field inside the JSON objects. |
| retrieve: | Step capability for on-demand bounded fetch. The LLM sees the slate index, requests specific files via JSON, and the engine fetches them within a maxRounds loop. |
| Cold-start retrieval | The problem of knowing what to read; solved by index/tree metatags + retrieve: capability. |
Runtime + safety terms
| Term | Definition |
|---|---|
| Runtime | The execution layer that loads a ladder config and runs it. Walks the steps array, dispatches LLM calls, evaluates gates, persists slates, enforces ceilings. |
| Gateway | OpenAI-compatible API surface for ladder execution. Accepts POST /v1/{author}/{ladder}/chat/completions and returns standard chat completion responses. |
| API | Internal Redeo API for auth, billing, providers, library, studio, and account management. |
| Worker | Background execution layer for asynchronous pipeline jobs. |
| Hop | Unit of execution count. Every step execution counts. Jumps don't increment separately; the step they lead to does. Bounded by maxHops. |
| Spend cap | The primary safety net. Hard dollar ceiling per execution. Default $5; platform max $50. Configurable per ladder via executionBudget.maxSpend. |
| Hop ceiling | Hard cap on total hops (loops + jumps + recursion). Default 200; platform max 10,000. |
| LLM-call ceiling | Hard cap on total LLM API calls. Default 500; platform max 5,000. |
| Recursion ceiling | Hard cap on recursion depth. Default 5; platform max 20. |
| Runtime-cap safety model | LADR's grammar is Turing-complete (declarative but unbounded). Safety is enforced at runtime via spend caps and resource ceilings, not via grammar restrictions. |
| Resource ceiling exhaustion | When a runtime ceiling is hit mid-execution. Engine gracefully exits with best-so-far output when a ceiling is hit. Treated as normal termination, not error. |
Product + platform terms
| Term | Definition |
|---|---|
| Foundry | The editor for ladders. Browser-based at foundry.redeo.io; an Electron desktop app is planned. |
| Studio | The consumer experience for running ladders; live timeline, per-step output inspection, threaded conversations. Browser-based at studio.redeo.io (or via /studio on the main app). |
| Library | The public directory of published ladders. Browser-based at library.redeo.io (or via /library on the main app). |
| Crucible | Reference ladder composing ToT + reflexion + self-refine + self-consistency + memory. |
| Visibility tier | One of: public-free (AGPL, full config disclosed), public-paid (creator-priced), hosted-private (callable via API, not listed), enterprise-local-licensed (deployed to customer sites), local (self-hosted only). |
| Ladder ID | Canonical identifier: @author/name for published, local/name for self-hosted. Version suffix: @author/name@v3. URL form: library.redeo.io/@author/name. |
| Corpus thesis | The strategy where publishing measured reasoning strategies creates a training-corpus asset as a side effect. Product → usage data → corpus → research flywheel. |