BatchTicket (CLI: adt) es un transductor determinista de datos estructurados para flujos de trabajo de agentes. Como el pequeño ticket que viaja con un lote de producción o de envío, cada ejecución lleva un plan versionado y un registro explícito de lo que la ejecución cambió. Ese registro no afirma que el mapeo fuera semánticamente correcto.
No es otro dialecto de jq o SQL. DuckDB, JSON Schema, PyYAML y los analizadores estándar se encargan del trabajo de ejecución establecido. Este proyecto es el responsable del contrato de agente en torno a ellos.
La versión 0.2.0 es un candidato a lanzamiento de código fuente aún no publicado. El proyecto está licenciado bajo la
Apache License 2.0. Los identificadores técnicos estables siguen siendo
agent-data-transformer, data-transformer, adt y las cuatro herramientas MCP data_*.
Inspecciona JSON, JSONL, CSV, TSV, YAML y Parquet sin devolver las cargas útiles completas.
Descubre conjuntos de registros anidados acotados en envolturas JSON/YAML y perfila sus campos lógicos.
Compara la forma de un registro fuente con un JSON Schema de destino, muestra solo los candidatos de mapeo estructural y emite un borrador de plan ejecutable solo después de mapeos compatibles explícitos.
Transformation Plan v1 seguro, sin ejecución de código crudo, SQL, shell, jq, regex ni plantillas.
Filtrado, proyección, eliminación, renombrado, ordenación, limitación, deduplicación, conversión de tipos, derivación, explosión, unión, agrupación, pivote, despivote, aplanado, desaplanado y mutación de árbol.
JSON Schema más aserciones de no nulo, unicidad, recuento de filas, campo y tipo.
Diff con o sin clave que tiene en cuenta el esquema.
Ejecución en seco con verificación previa del destino real, publicación atómica por etapas y protección contra sobrescritura.
Aislamiento del worker durante toda la llamada con límites acumulativos de fuente/byte/fila/ítem/profundidad/tiempo/RSS/temp.
Un límite máximo de bytes sobre la respuesta serializada completa, incluyendo muestras, formas, efectos de ejecución, diffs, fallos de validación y errores.
Un único modelo de Plan v1 estricto y tipado genera la validación en tiempo de ejecución, el JSON Schema publicado y el esquema MCP en vivo.
Un único núcleo compartido con CLI y cuatro herramientas MCP a nivel de tarea.
Related MCP server: MCP Data Integration Server
Clonado para desarrollo:
git clone https://github.com/tetracoralla/BatchTicket.git
cd BatchTicket
uv sync --frozen --extra dev
uv run adt inspect examples/users.json --select 'data.users[*]'
uv run adt inspect examples/users.json --select 'data.users[*]' \
--target-schema target.schema.json --mappings mappings.json
uv run adt transform examples/adults.plan.yaml
uv run adt transform examples/adults.plan.yaml --dry-run
uv run adt validate examples/users.json --select 'data.users[*]' \
--assertions examples/users.assertions.json
ADT_WORKSPACE_ROOT=/absolute/granted/workspace uv run adt mcpConstruye un plugin específico de plataforma que no necesita el repositorio, uv, una instalación de Python ni una conexión de red en tiempo de ejecución:
uv run python scripts/build_plugin.py
uv run python scripts/probe_plugin.py \
dist/plugin/data-transformer-0.2.0-darwin-arm64
codex plugin marketplace add dist/plugin
codex plugin add data-transformer@data-transformer-localLa compilación produce un directorio de plugin, un archivo .tar.gz y una suma de verificación SHA-256 en dist/plugin/. Instala o copia el directorio generado completo; el .mcp.json de la raíz del repositorio es configuración de desarrollo, mientras que el .mcp.json del plugin generado invoca directamente su ejecutable empaquetado. El marketplace local generado apunta Codex a ese directorio autocontenido. Reconstruir con --replace rechaza raíces de salida con enlaces simbólicos o destinos generados antes de eliminar o sobrescribir cualquier cosa.
El paquete autocontenido generado es actualmente un artefacto de validación local, no un activo de lanzamiento público. Incorpora un runtime de Python, paquetes de Python y bibliotecas nativas cuyos materiales de licencia de terceros aún no están ensamblados en el archivo. No subas el directorio del plugin, el archivo ni la suma de verificación a un GitHub Release. Esto no restringe la publicación ni el uso del repositorio de código fuente Apache-2.0; consulta la lista de verificación de lanzamiento.
La transformación de ejemplo devuelve dos registros en línea e informa a través de execution_effects de que se eliminó una fila de entrada. La salida a archivo es opt-in mediante output.path; los archivos existentes nunca se reemplazan a menos que output.overwrite sea explícitamente verdadero.
Las rutas de la CLI son rutas de usuario explícitas y pueden ser absolutas. Las rutas de archivos MCP son una capacidad más restringida: el servidor utiliza primero los espacios de trabajo concedidos mediante el protocolo de raíces MCP. Se selecciona automáticamente una única raíz; cuando se conceden varias raíces, pasa el name exacto de cada raíz en el campo opcional workspace de la herramienta. Los hosts sin soporte de raíces pueden pasar un ADT_WORKSPACE_ROOT explícito como concesión de compatibilidad. Las rutas de las herramientas permanecen relativas a la raíz seleccionada, y se rechazan los escapes absolutos, de directorio padre, URI y de enlaces simbólicos. Las llamadas MCP exclusivamente en línea no requieren concesión de espacio de trabajo.
Codex CLI 0.148 no pasa actualmente raíces MCP a los servidores de plugins locales. Para una prueba en frío del host CLI, ejecuta Codex con ADT_WORKSPACE_ROOT establecido en el espacio de trabajo de prueba exacto. Las herramientas de solo lectura pueden ejecutarse con approval=never; data_transform tiene capacidad condicional de salida a archivo y, por lo tanto, requiere una política de host con capacidad de aprobación incluso cuando una llamada concreta devuelve datos en línea. Una llamada bloqueada es un resultado de autorización, no un permiso para recurrir a la shell ni a la reescritura de datos en el lado del modelo.
data_inspect acepta un target_schema opcional y un objeto mappings. Puede seleccionar un conjunto único de registros anidados basándose en evidencia estructural, sugerir coincidencias exactas o de nombre normalizado, e informar sobre campos incompatibles, faltantes, duplicados, omitidos o eliminados. No utiliza sinónimos difusos, conversiones de tipo ni valores predeterminados. El adaptador v1 mapea los campos de registro de nivel superior y admite un esquema de objeto o un array cuyo items es un esquema de objeto. Los esquemas compuestos/de referencia y los conjuntos de registros ambiguos permanecen explícitamente sin resolver.
Cuando cada campo obligatorio tiene un mapeo compatible explícito, adaptation.status es ready y adaptation.draft_plan es un Transformation Plan v1 normal. Ejecuta ese plan mediante data_transform; el adaptador no crea una ruta de ejecución separada ni una quinta herramienta pública.
from data_transformer import DataTransformer
result = DataTransformer().transform(
{
"version": "1",
"sources": {"rows": {"inline": [{"x": 2}, {"x": 4}]}},
"steps": [
{
"op": "derive",
"field": "doubled",
"expr": {"multiply": [{"field": "x"}, {"value": 2}]},
}
],
}
)Las llamadas públicas devuelven status: ok, status: dry_run o status: error con un error.code estable. Las transformaciones exitosas exponen los cambios observados en tiempo de ejecución en execution_effects; no filtran trazas de pila ni detalles internos de DuckDB.
Consulta el modelo de producto, Transformation Plan v1 y el contrato de revisión. Las contribuciones se describen en CONTRIBUTING.md, los informes de seguridad en SECURITY.md y los cambios notables en CHANGELOG.md.
Compare two structured datasets by schema and rows, optionally using stable key fields. Returns compact added, removed, and changed counts and samples.
| Name | Required | Description | Default |
|---|---|---|---|
| left | Yes | ||
| right | Yes | ||
| limits | No | ||
| workspace | No | ||
| key_fields | No | ||
| sample_rows | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context about the output being 'compact' and that it 'returns added, removed, and changed counts and samples', which goes beyond annotations. There is no contradiction, and the description adds value by clarifying the behavioral output characteristics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, compact sentence that front-loads the purpose and includes the key optional parameter (key fields) and the output nature. Every phrase earns its place, with no redundancy or fluff. This is ideal conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 6 parameters including complex source objects (PathSource/InlineSource) and a limits model, but the description does not mention that sources can be paths or inline, nor the limits concept. However, the schema provides rich detail on these, and the output is described. Given no output schema, the description covers the return format adequately. The main gap is not explaining how sources are specified, but the schema covers that, so a moderate score is fair.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, but the description explicitly mentions 'stable key fields' matching the key_fields parameter and 'compact counts and samples' relating to sample_rows. However, it does not explain the left/right source objects, limits, or workspace parameters. The description adds some meaning but not enough to fully compensate for low coverage; baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Compare two structured datasets by schema and rows' with 'optional stable key fields', and specifies the output as 'compact added, removed, and changed counts and samples'. This is a specific verb+resource combination that distinguishes it from siblings like data_transform (transforms), data_inspect (inspects), and data_validate (validates).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when two datasets need comparison, but it does not explicitly mention when not to use it or name alternatives. Sibling tools are obvious from their names, but the description could have added context about when to choose this over data_inspect or data_validate. Still, the purpose is clear enough that a moderate score is warranted.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Inspect JSON, JSONL, CSV, TSV, YAML, or Parquet shape, types, counts, and a small sample without returning the full payload. Use for 'what fields are in this data?' or unknown tool output. Optionally compare record fields with target_schema and return deterministic mapping candidates; a draft plan is returned only after explicit mappings are supplied. One successful call is sufficient for its recorded observations; never repeat the same arguments to confirm it.
| Name | Required | Description | Default |
|---|---|---|---|
| limits | No | ||
| source | Yes | ||
| mappings | No | ||
| workspace | No | ||
| sample_rows | No | ||
| target_schema | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes beyond the read-only/idempotent annotations by adding key behavioral details: no full payload returned, deterministic mapping candidates, draft plans only after explicit mappings, and a note that one successful call is sufficient for observations. These are meaningful traits not present in annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, front-loaded with the core purpose, and every sentence adds valuable context: formats, outputs, use cases, optional mapping behavior, and idempotence caution. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the tool's main purpose, use cases, and special behaviors well. It lacks detail on certain parameters (limits, workspace) and the two source variants, but for a read-only inspection tool with clear annotations, the provided context is sufficient for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It meaningfully explains target_schema and mappings, and implies sample behavior via 'small sample,' but it leaves limits, workspace, and source structure (path vs inline) undocumented. This is a partial but not full compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool inspects multiple data formats (JSON, JSONL, CSV, TSV, YAML, Parquet) and returns shape, types, counts, and a small sample without returning the full payload. It also clearly distinguishes itself from sibling tools by specifying its use case: 'what fields are in this data?' or unknown tool output.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit when-to-use guidance ('Use for...') and a strong behavioral instruction ('never repeat the same arguments to confirm it'). While it doesn't explicitly name alternative sibling tools as exclusions, the use case framing makes it clear when inspection is appropriate versus transform/validate/diff.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Transform or rewrite records: reshape, filter, join, aggregate, cast, flatten, or convert structured data with Transformation Plan v1. Do not use this tool for a validation-only request such as checking non-null or unique fields; use data_validate. Known transformation shape: {"version":"1","sources":{"input":{"path":"users.json","select":"data.users[*]"}},"steps":[{"id":"filtered","op":"filter","source":"input","where":{"field":"age","gte":18}},{"op":"select","source":"filtered","fields":[{"field":"userId","as":"id"}]}],"return":{"mode":"auto"}}. Omit workspace with ADT_WORKSPACE_ROOT; otherwise it is an exact granted root name, never a path. Returns a compact sample and explicit execution effects; large results require output.path.
| Name | Required | Description | Default |
|---|---|---|---|
| plan | Yes | ||
| dry_run | No | ||
| workspace | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true), so the description's job is to add value beyond them. It does: it discloses that the tool 'Returns a compact sample and explicit execution effects,' warns that 'large results require output.path,' and explains workspace variable behavior (ADT_WORKSPACE_ROOT). Crucially, the description is consistent with the annotations—the described rewrite/transform behavior aligns with destructiveHint=true, so there's no contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long, but justifiably so given the tool's complexity—a full transformation DSL. It front-loads the purpose, uses a crisp exclusion, and packs workspace semantics and return behavior into tight sentences. The embedded JSON example is bulky but earns its place. It loses one point for the dense JSON blob being potentially hard to scan, but every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 3 top-level params, a huge nested schema (19 step types, multiple assertion types), and no output schema, the description covers the most critical gaps: workspace pathing rules, large-result handling (output.path), the full plan shape, and the validation sibling's boundary. It's slightly shy of a 5 because the 'compact sample and explicit execution effects' return semantics are never detailed, and error/limit behaviors aren't addressed—leaving some burden on the agent despite the otherwise strong guidance.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate, and it does extensively: it embeds a complete Transformation Plan v1 JSON example showing versions, sources with path/select, steps (filter with condition, select with aliases), and return mode. It also explicitly documents the workspace parameter semantics and the output.path behavior for large results. This is exactly the burden-shifting the rubric requires when the schema provides no narrative.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb phrase — 'Transform or rewrite records: reshape, filter, join, aggregate, cast, flatten, or convert structured data with Transformation Plan v1' — clearly naming the resource (Transformation Plan v1) and listing concrete operations. It differentiates from siblings by explicitly excluding validation tasks ('Do not use this tool for a validation-only request'). This is a strong purpose statement for a tool whose name alone would be ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives an explicit when-not-to-use directive with a named alternative: 'Do not use this tool for a validation-only request such as checking non-null or unique fields; use data_validate.' It also provides workspace usage guidance ('Omit workspace with ADT_WORKSPACE_ROOT; otherwise it is an exact granted root name, never a path') and large-result handling. This matches the exemplar behavior in the rubric—clear exclusion plus named alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Validate or check requirements on existing structured data (校验/检查非空、唯一、类型、字段或行数); choose data_validate, not data_transform, for validation-only requests. It accepts JSON Schema and deterministic assertions and returns valid true or false without rewriting the source. Known validation shape: {"source":{"path":"users.json","select":"data.users[*]"},"assertions":[{"type":"not_null","field":"userId"},{"type":"unique","field":"userId"}]}.
| Name | Required | Description | Default |
|---|---|---|---|
| limits | No | ||
| schema | No | ||
| source | Yes | ||
| workspace | No | ||
| assertions | No | ||
| sample_rows | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds useful context by stating it 'returns valid true or false without rewriting the source' and that assertions are deterministic, reinforcing that validation has no side effects. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with purpose and usage guidance, and the three sentences are efficient. The JSON shape example is practical and earns its place, though it slightly lengthens the description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex 6-parameter tool with no output schema, the description covers the main purpose, sibling differentiation, side-effect-free behavior, and return type. Yet optional parameters like limits, workspace, and sample_rows are not addressed, so the description is not fully complete despite the rich input schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate. It provides a concrete validation shape for source and assertions, and enumerates assertion type names, giving real semantic value for the core parameters. However, other parameters such as limits, workspace, and sample_rows are not described, leaving clear gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb ('Validate or check requirements') and clearly identifies the resource ('existing structured data'). It enumerates supported check types (non-null, unique, type, field, row count) and explicitly distinguishes from a sibling tool ('choose data_validate, not data_transform'), which is strong differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides an explicit usage rule: 'choose data_validate, not data_transform, for validation-only requests.' This named alternative and clear when/when-not guidance meets the highest bar, even though it does not mention data_inspect or data_diff.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.2.0data_diffdata_inspectdata_transformdata_validateScored across 4 tools
Each tool occupies a cleanly separated role: observe (inspect), modify (transform), check (validate), and compare (diff). The overlap risk between transform and validate is explicitly addressed with cross-references steering agents to the right tool. No ambiguity remains after reading the descriptions.
All tools follow the exact data_<verb> pattern in snake_case with uniform imperative verbs: transform, inspect, validate, diff. The convention is fully predictable with zero deviation.
At 4 tools, the surface is tightly scoped with no bloat, comfortably within the ideal range for a focused data utility. Every tool earns its place within the read/validate/write/compare lifecycle.
Core workflows are fully covered: reading, transforming/writing output, validating, and diffing data, with output paths already handled by the transform tool. Minor gaps like an explicit export/delete or data source listing tool prevent a perfect score, but agents can accomplish all primary tasks.
Remote MCP: JSON repair, JSON Schema validation, JSON to TypeScript, CSV to JSON and JSON to CSV.
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
JSON Schema validator for API payloads via MCP: bounded checks and structured pass/fail errors.
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
