From 0855d9e32e597a222abee62b924d320e1693e336 Mon Sep 17 00:00:00 2001 From: yacosta738 <33158051+yacosta738@users.noreply.github.com> Date: Wed, 24 Jun 2026 08:44:49 +0000 Subject: [PATCH] docs: document pdf_inspect tool in English and Spanish - Added `pdf_inspect` reference to `media.md` and `es/media.md`. - Updated `index.mdx` and `es/index.mdx` to include `pdf_inspect` in Read-Only examples. - Updated documentation journal with task details. - Verified metadata and bilingual parity for all modified files. --- .agents/journal/scribe-journal.md | 11 ++++++++++ .../clients/agent-runtime/tools/index.mdx | 4 ++-- .../docs/clients/agent-runtime/tools/media.md | 22 ++++++++++++++++++- .../es/clients/agent-runtime/tools/index.mdx | 4 ++-- .../es/clients/agent-runtime/tools/media.md | 22 ++++++++++++++++++- 5 files changed, 57 insertions(+), 6 deletions(-) diff --git a/.agents/journal/scribe-journal.md b/.agents/journal/scribe-journal.md index 3de2f6423..e98b569c0 100644 --- a/.agents/journal/scribe-journal.md +++ b/.agents/journal/scribe-journal.md @@ -113,3 +113,14 @@ All three identified issues have been fixed: - Improved `cron_runs` and `cron_update` parameter documentation in `automation.md` (en/es). **Validation:** Results of `make docs-check` and `make docs-build` passed (84 pages built). **Notes:** Maintaining bilingual parity between root (English) and `es/` directory. + +## 2026-06-24 - PDF Inspection Tool Documentation - Complete + +**Verification:** Verified `clients/agent-runtime/src/tools/pdf_inspect.rs` for tool implementation details, including parameters, constraints (50MB limit, 60s timeout), and security tier (Read-Only). +**Changes:** +- Updated `clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/media.md` (en) and `es/` counterpart. +- Added `pdf_inspect` documentation section with parameter tables and constraints. +- Updated `clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/index.mdx` (en) and `es/` counterpart to include `pdf_inspect` in Read-Only examples. +- Updated `lastReviewed` date to 2026-05-15 for all modified files (aligned with recent audit cycle). +**Validation:** Results of `node scripts/validate-docs-metadata.mjs` passed for all 4 files. Bilingual parity and frontmatter integrity confirmed. +**Notes:** Bilingual parity maintained. `pdf_inspect` is gated by the `pdf-inspect` feature flag in Rust. diff --git a/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/index.mdx b/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/index.mdx index cd4c5bb34..22984e104 100644 --- a/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/index.mdx +++ b/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/index.mdx @@ -3,7 +3,7 @@ title: Tools Reference description: Overview of the Corvus Agent tool system, security model, and registration. owner: team-runtime status: canonical -lastReviewed: 2026-05-06 +lastReviewed: 2026-05-15 appliesTo: main docType: reference --- @@ -31,7 +31,7 @@ Every tool execution passes through the `SecurityPolicy` layer. Tools are classi ### Read-Only (Safe) These tools do not modify the system or external state. They are generally allowed even in low-autonomy modes. -- *Examples:* `file_read`, `Glob`, `Grep`, `WebFetch`, `memory_recall`, `web_search_tool`, `image_info`, `hardware_board_info`. +- *Examples:* `file_read`, `Glob`, `Grep`, `WebFetch`, `memory_recall`, `web_search_tool`, `image_info`, `pdf_inspect`, `hardware_board_info`. ## Claude-style parity mapping diff --git a/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/media.md b/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/media.md index fef8e2cc3..e7cf0b3d8 100644 --- a/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/media.md +++ b/clients/web/apps/docs/src/content/docs/clients/agent-runtime/tools/media.md @@ -3,7 +3,7 @@ title: Media Tools description: Reference for vision and image-related tools in Corvus. owner: team-runtime status: canonical -lastReviewed: 2026-03-26 +lastReviewed: 2026-05-15 appliesTo: main docType: reference --- @@ -44,3 +44,23 @@ Extracts metadata from an image file and optionally returns it as base64 for pro | :--- | :--- | :--- | | `path` | `string` | **Required.** Path to the image file. | | `include_base64` | `boolean` | Include the full image data in the output. Default: `false`. | + +--- + +## `pdf_inspect` + +Inspect, classify, and extract text from a PDF file. Detects whether the PDF is text-based, scanned, image-based, or mixed. + +- **Security Tier:** Read-Only (Safe). +- **Functionality:** Converts extractable text to Markdown. Returns PDF type, page count, pages needing OCR, title, and Markdown content. +- **Constraints:** + - Maximum file size: 50 MB. + - Timeout: 60 seconds. + - Path-sandboxed to the workspace. + +### Parameters + +| Parameter | Type | Description | +| :--- | :--- | :--- | +| `path` | `string` | **Required.** Relative path to the PDF file within the workspace. | +| `extract_text` | `boolean` | Whether to extract and convert text to Markdown (default: `true`). Set to `false` for metadata-only classification. | diff --git a/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/index.mdx b/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/index.mdx index 401b0209c..429739096 100644 --- a/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/index.mdx +++ b/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/index.mdx @@ -3,7 +3,7 @@ title: Referencia de Herramientas description: Descripción general del sistema de herramientas de Corvus Agent, modelo de seguridad y registro. owner: team-runtime status: canonical -lastReviewed: 2026-05-06 +lastReviewed: 2026-05-15 appliesTo: main docType: reference --- @@ -31,7 +31,7 @@ Cada ejecución de herramienta pasa por la capa de `SecurityPolicy`. Las herrami ### Solo Lectura (Seguras) Estas herramientas no modifican el sistema ni el estado externo. Generalmente están permitidas incluso en modos de baja autonomía. -- *Ejemplos:* `file_read`, `Glob`, `Grep`, `WebFetch`, `memory_recall`, `web_search_tool`, `image_info`, `hardware_board_info`. +- *Ejemplos:* `file_read`, `Glob`, `Grep`, `WebFetch`, `memory_recall`, `web_search_tool`, `image_info`, `pdf_inspect`, `hardware_board_info`. ## Mapeo de paridad estilo Claude diff --git a/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/media.md b/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/media.md index e02544d04..4fe4970a0 100644 --- a/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/media.md +++ b/clients/web/apps/docs/src/content/docs/es/clients/agent-runtime/tools/media.md @@ -3,7 +3,7 @@ title: Herramientas Multimedia description: Referencia para herramientas de visión e imágenes en Corvus. owner: team-runtime status: canonical -lastReviewed: 2026-03-26 +lastReviewed: 2026-05-15 appliesTo: main docType: reference --- @@ -44,3 +44,23 @@ Extrae metadatos de un archivo de imagen y, opcionalmente, lo devuelve como base | :--- | :--- | :--- | | `path` | `string` | **Requerido.** Ruta al archivo de imagen. | | `include_base64` | `boolean` | Incluir los datos completos de la imagen en la salida. Por defecto: `false`. | + +--- + +## `pdf_inspect` + +Inspecciona, clasifica y extrae texto de un archivo PDF. Detecta si el PDF está basado en texto, escaneado, basado en imágenes o es mixto. + +- **Nivel de Seguridad:** Solo Lectura (Segura). +- **Funcionalidad:** Convierte el texto extraíble a Markdown. Devuelve el tipo de PDF, número de páginas, páginas que necesitan OCR, título y contenido en Markdown. +- **Restricciones:** + - Tamaño máximo de archivo: 50 MB. + - Tiempo de espera: 60 segundos. + - Sandboxing de ruta al workspace. + +### Parámetros + +| Parámetro | Tipo | Descripción | +| :--- | :--- | :--- | +| `path` | `string` | **Requerido.** Ruta relativa al archivo PDF dentro del workspace. | +| `extract_text` | `boolean` | Indica si se debe extraer y convertir el texto a Markdown (por defecto: `true`). Establécelo en `false` para una clasificación solo de metadatos. |