Resource Management

Resources are external knowledge that agents can reference. This module provides functionality for adding, importing/exporting, and uploading temporary files for resources.

Core Concepts

Resource Types

OpenViking supports various resource types, categorized by functionality:

Documents

Spreadsheets & Presentations

Code

Media

Cloud Documents

Resource Processing Pipeline

Resources go through the following processing stages when added:

Source Input -> Parse -> Resource Tree Build -> Persistence -> Semantic Processing
    ↓           ↓            ↓                 ↓               ↓
  URL/File    Parser    TreeBuilder        AGFS       Summarizer/Vector

Stage 1: Parse

• Uses UnifiedResourceProcessor to parse content based on resource type
• Supports multiple formats: documents (PDF/Markdown/Word), spreadsheets (Excel/PPT), code, media files, etc.
• Parsed results are written to a temporary VikingFS directory
• Media files have descriptions generated via VLM (Vision Language Model)

Stage 2: Resource Tree Build (TreeBuilder)

• TreeBuilder.finalize_from_temp() scans the temporary directory structure
• Builds resource tree nodes, handles URI conflicts (auto-renames)
• Establishes relationships between directories and resources

Stage 3: Persistence

• Checks if target URI already exists
• New resources: moves temporary files to permanent AGFS location
• Existing resources: retains temporary tree for subsequent diff comparison
• Acquires lifecycle lock to prevent concurrent modifications
• Cleans up temporary directory

Stage 4: Semantic Processing

• Summary Generation: Summarizer generates L0 (abstract) and L1 (overview)
• Vector Index: Vectorizes content for semantic search
• Processed asynchronously via SemanticQueue, can wait for completion with wait=True

Incremental Updates for Resources

Resource incremental updates are implemented via the Watch Task mechanism:

Watch Task Creation

• Set watch_interval > 0 (in minutes) when calling add_resource to create a watch task
• Must specify the to parameter to define the target URI
• WatchManager handles task persistence
• Supports multi-tenant permission control (ROOT/ADMIN/USER permission levels)

Task Scheduling & Execution

• WatchScheduler checks for expired tasks every 60 seconds
• Default concurrency control prevents duplicate execution
• Expired tasks automatically re-invoke add_resource
• Updates task's last execution time and next execution time

Task Management Operations

• Create: Creates new task or reactivates disabled task when watch_interval > 0
• Update: Re-sets parameters for the same target URI
• Cancel: Disables task when watch_interval <= 0 for the same target URI
• Query: Queries task status by task ID or target URI

API Reference

add_resource

Add a resource to the knowledge base. The SDK supports local files/directories, URLs, and other sources. Raw HTTP calls accept remote URLs through path or uploaded local files through temp_file_id.

1. API Implementation Overview

This endpoint is the core entry point for resource management, supporting adding resources from various sources with optional waiting for semantic processing completion.

Processing Flow:

1. Identify resource source (URL or uploaded temporary file)
2. Call corresponding Parser to parse content
3. Build directory tree and write to AGFS
4. Set up scheduled update task if watch_interval is specified
5. Wait for semantic processing completion if wait=true

Code Entry Points:

• openviking/client/local.py:LocalClient.add_resource - SDK entry (embedded)
• openviking_cli/client/http.py:AsyncHTTPClient.add_resource - SDK entry (HTTP)
• openviking/server/routers/resources.py:add_resource - HTTP router
• openviking/service/resource_service.py - Core service implementation
• crates/ov_cli/src/handlers.rs:handle_add_resource - CLI handler

2. Interface and Parameter Description

Parameters

Additional Notes:

• to and parent cannot be specified together. Use create_parent=true with parent when the parent directory should be created automatically.
• path and temp_file_id cannot be specified together
• Raw HTTP calls for local files require first uploading via temp_upload to obtain temp_file_id
• When to is specified and the target already exists, triggers incremental update
• watch_interval only takes effect when to is provided
• For local directory inputs, scanning respects .gitignore files (root and nested) with standard Git semantics; ignore_dirs, include, and exclude further refine what is ingested.
• To create or update plain text directly, use content/write instead of add_resource. Semantic processing and embeddings are refreshed automatically after resource ingestion and content writes.

3. Usage Examples

HTTP API

POST /api/v1/resources
Content-Type: application/json

# Add resource from URL
curl -X POST http://localhost:1933/api/v1/resources \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-key" \
  -d '{
    "path": "https://example.com/guide.md",
    "reason": "User guide documentation",
    "wait": true
  }'

# Add from local file (requires temp_upload first)
TEMP_FILE_ID=$(
  curl -s -X POST http://localhost:1933/api/v1/resources/temp_upload \
    -H "X-API-Key: your-key" \
    -F "file=@./documents/guide.md" \
  | jq -r '.result.temp_file_id'
)

curl -X POST http://localhost:1933/api/v1/resources \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-key" \
  -d "{
    \"temp_file_id\": \"$TEMP_FILE_ID\",
    \"to\": \"viking://resources/guide.md\",
    \"reason\": \"User guide\"
  }"

Python SDK

import openviking as ov

# Using embedded mode
client = ov.OpenViking(path="./data")
client.initialize()

# Or using HTTP client
client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Add local file
result = client.add_resource(
    "./documents/guide.md",
    reason="User guide documentation"
)
print(f"Added: {result['root_uri']}")

# Add from URL to specific location
result = client.add_resource(
    "https://example.com/api-docs.md",
    to="viking://resources/external/api-docs.md",
    reason="External API documentation"
)

# Wait for processing to complete
client.wait_processed()

# Enable scheduled updates
client.add_resource(
    "./documents/guide.md",
    to="viking://resources/guide.md",
    watch_interval=60  # Update every 60 minutes
)

CLI

# Add local file
ov add-resource ./documents/guide.md --reason "User guide"

# Add from URL
ov add-resource https://example.com/guide.md --to viking://resources/guide.md

# Wait for processing to complete
ov add-resource ./documents/guide.md --wait

# Enable scheduled updates (check every 60 minutes)
ov add-resource https://github.com/example/repo.git --to viking://resources/guide.md --watch-interval 60

# Cancel scheduled updates
ov add-resource https://github.com/example/repo.git --to viking://resources/guide.md --watch-interval 0

# Add with parent directory (parent must exist)
ov add-resource ./documents/guide.md --parent viking://resources/docs

# Add with parent directory (auto-create parent if it doesn't exist)
ov add-resource ./documents/guide.md -p viking://resources/docs/2026/05/07
# Or using full flag
ov add-resource ./documents/guide.md --parent-auto-create viking://resources/docs/2026/05/07

# Using path variables with auto-create
ov add-resource ./documents/guide.md -p viking://resources/docs/{calendar:today}

Response Example

HTTP API Response (JSON)

{
  "status": "ok",
  "result": {
    "status": "success",
    "root_uri": "viking://resources/guide.md",
    "temp_uri": "viking://temp/username/04291108_b62dc7/guide.md",
    "source_path": "./documents/guide.md",
    "meta": {},
    "errors": [],
    "queue_status": {
      "pending": 5,
      "processing": 2,
      "completed": 10
    }
  },
  "telemetry": {
    "operation_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

CLI Response (Default Table Format)

Note: Resource is being processed in the background.
Use 'ov wait' to wait for completion, or 'ov observer queue' to check status.
status       success
errors       []
source_path  /Users/bytedance/workspace/github.com/OpenViking/docs/en/api/01-overview.md
meta         {}
root_uri     viking://resources/01-overview
temp_uri     viking://temp/shengmaojia/04291108_b62dc7/01-overview

CLI Response (JSON Format, using -o json)

{
  "status": "success",
  "root_uri": "viking://resources/01-overview",
  "temp_uri": "viking://temp/shengmaojia/04291108_b62dc7/01-overview",
  "source_path": "/Users/bytedance/workspace/github.com/OpenViking/docs/en/api/01-overview.md",
  "meta": {},
  "errors": []
}

Field Description

Watch Management

List, inspect, update, and trigger watch tasks created via add_resource with watch_interval > 0. The control plane is mirrored across REST (/api/v1/watches), the ov task watch CLI subcommand group, and a minimum-closure MCP surface (list_watches / cancel_watch) for agents.

1. API Implementation Overview

This control plane wraps the WatchManager primitives without changing any server-side behavior. Every endpoint and CLI command resolves the target task by either its task_id (path) or its to_uri (query). The two keys are interchangeable; if both are supplied they must refer to the same task, otherwise the request is rejected with 400.

Operations:

• List (GET /api/v1/watches) — returns {tasks, total}; pass ?active_only=true to filter; pass ?to_uri=... to collapse to a single-task lookup
• Show (GET /api/v1/watches/{task_id}) — inspect one task; optional ?to_uri= performs a cross-key sanity check
• Update (PATCH /api/v1/watches/{task_id} or PATCH /api/v1/watches?to_uri=...) — partial update of watch_interval, is_active, reason, instruction. is_active is orthogonal to watch_interval: flip is_active to pause/resume without losing the configured cadence.
• Delete (DELETE /api/v1/watches/{task_id} or DELETE /api/v1/watches?to_uri=...)
• Trigger (POST /api/v1/watches/{task_id}/trigger or POST /api/v1/watches/trigger?to_uri=...) — fire-and-forget refresh; returns immediately while the underlying re-ingest runs in the background

Code Entry Points:

• openviking/server/routers/watches.py — REST router for /api/v1/watches
• crates/ov_cli/src/commands/watch.rs — ov task watch CLI subcommand group
• openviking/server/mcp_endpoint.py — MCP list_watches / cancel_watch tools and the watch_interval / to parameters on add_resource
• openviking/resource/watch_manager.py:WatchManager — task persistence and scheduling primitives

2. Interface and Parameter Description

For every single-task endpoint the path {task_id} can be replaced with a ?to_uri= query argument. The CLI <key> argument is auto-classified: any value starting with viking:// routes to the by-URI path, anything else is treated as a task ID (other URI schemes such as http:// are rejected locally to avoid silent 404s).

PATCH /watches body (all fields optional; at least one is required)

Unrecognized fields are rejected with 422 (extra="forbid"). Fields left unset preserve their current values.

3. Usage Examples

HTTP API

# List active watch tasks (drop ?active_only to include paused ones)
curl -s "http://localhost:1933/api/v1/watches?active_only=true" \
  -H "X-API-Key: your-key"

# Pause a watch without losing its cadence
curl -X PATCH "http://localhost:1933/api/v1/watches/<task_id>" \
  -H "X-API-Key: your-key" -H "Content-Type: application/json" \
  -d '{"is_active": false}'

# Trigger an immediate refresh (fire-and-forget; returns before the re-ingest finishes)
curl -X POST "http://localhost:1933/api/v1/watches/<task_id>/trigger" \
  -H "X-API-Key: your-key"

# Resolve by URI instead of task ID
curl -X DELETE "http://localhost:1933/api/v1/watches?to_uri=viking://resources/guide.md" \
  -H "X-API-Key: your-key"

CLI (subcommands of ov task watch)

# List active watches (drop --active-only to include paused ones)
ov task watch ls --active-only

# Inspect a single watch (key may be either a viking:// URI or a task_id)
ov task watch show viking://resources/guide.md

# Pause / resume without losing the cadence
ov task watch pause viking://resources/guide.md
ov task watch resume viking://resources/guide.md

# Update the cadence (or any combination of --active / --reason / --instruction)
ov task watch update viking://resources/guide.md --interval 30

# Trigger an immediate fire-and-forget refresh
ov task watch trigger viking://resources/guide.md

# Remove a watch task entirely
ov task watch rm viking://resources/guide.md

MCP (agent control plane — minimum closure only)

list_watches()                                            # one line per task; URIs only, no task_ids surfaced
cancel_watch(to_uri="viking://resources/guide.md")        # idempotent removal by URI

Pause / resume / trigger / update are intentionally not exposed via MCP — those power-user operations live on the CLI/REST surface to keep the agent system prompt compact. Creating a watch or changing its cadence from the agent side still goes through add_resource with watch_interval and to.

add_skill

Add a skill to the knowledge base.

1. API Implementation Overview

Skills are special resources used to define operations or tools that agents can execute.

Processing Flow:

1. Receive skill data or uploaded temporary file
2. Parse skill definition
3. Store to skill directory
4. Wait for skill processing completion if wait=true

Code Entry Points:

• openviking/client/local.py:LocalClient.add_skill - SDK entry (embedded)
• openviking_cli/client/http.py:AsyncHTTPClient.add_skill - SDK entry (HTTP)
• openviking/server/routers/resources.py:add_skill - HTTP router
• openviking/service/resource_service.py - Core service implementation
• crates/ov_cli/src/handlers.rs:handle_add_skill - CLI handler

2. Interface and Parameter Description

Parameters

3. Usage Examples

HTTP API

POST /api/v1/skills
Content-Type: application/json

# Using inline data
curl -X POST http://localhost:1933/api/v1/skills \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-key" \
  -d '{
    "data": {
      "name": "my-skill",
      "description": "My custom skill",
      "steps": []
    }
  }'

# Using local file (requires temp_upload first)
TEMP_FILE_ID=$(
  curl -s -X POST http://localhost:1933/api/v1/resources/temp_upload \
    -H "X-API-Key: your-key" \
    -F "file=@./skills/my-skill.json" \
  | jq -r '.result.temp_file_id'
)

curl -X POST http://localhost:1933/api/v1/skills \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-key" \
  -d "{
    \"temp_file_id\": \"$TEMP_FILE_ID\"
  }"

Python SDK

import openviking as ov

client = ov.SyncHTTPClient(url="http://localhost:1933", api_key="your-key")
client.initialize()

# Add skill from local file
result = client.add_skill("./skills/my-skill.json")

# Wait for processing to complete
client.wait_processed()

CLI

# Add skill
ov add-skill ./skills/my-skill.json

# Wait for processing to complete
ov add-skill ./skills/my-skill.json --wait

4. Response Example

HTTP API Response (JSON)

{
  "status": "ok",
  "result": {
    "status": "success",
    "root_uri": "viking://agent/skills/my-skill",
    "uri": "viking://agent/skills/my-skill",
    "name": "my-skill",
    "auxiliary_files": 2,
    "queue_status": {
      "pending": 0,
      "processing": 0,
      "completed": 1
    }
  },
  "telemetry": {
    "operation_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

CLI Response (Default Table Format)

Note: Skill is being processed in the background.
Use 'ov wait' to wait for completion, or 'ov observer queue' to check status.
status          success
root_uri        viking://agent/skills/my-skill
uri             viking://agent/skills/my-skill
name            my-skill
auxiliary_files 2

CLI Response (JSON Format, using -o json)

{
  "status": "success",
  "root_uri": "viking://agent/skills/my-skill",
  "uri": "viking://agent/skills/my-skill",
  "name": "my-skill",
  "auxiliary_files": 2
}

Field Description

temp_upload

Upload a temporary file for subsequent importing of local files via add_resource or add_skill.

1. API Implementation Overview

This endpoint uploads a local file into temporary server-managed storage and returns a temp_file_id for subsequent API calls. This is a helper endpoint typically not called directly but used automatically via the SDK or CLI.

Processing Flow:

1. Receive uploaded file
2. Choose temporary upload backend based on upload_mode
3. Save the file and record original filename
4. Return temporary file ID

Code Entry Points:

• openviking/server/routers/resources.py:temp_upload - HTTP router
• openviking/service/resource_service.py - Service implementation

2. Interface and Parameter Description

Parameters

Notes:

• The default is local, so existing clients keep the original behavior unless they explicitly opt into shared.
• Use upload_mode=shared only when you explicitly want distributed shared temporary uploads.
• shared mode returns a one-time temp_file_id in the shared_<upload_id> form.
• Shared upload objects live under the internal viking://upload/... namespace and are not part of the normal filesystem browsing surface.

3. Usage Examples

HTTP API

POST /api/v1/resources/temp_upload
Content-Type: multipart/form-data

curl -X POST http://localhost:1933/api/v1/resources/temp_upload \
  -H "X-API-Key: your-key" \
  -F "file=@./documents/guide.md"

Distributed / shared upload:

curl -X POST http://localhost:1933/api/v1/resources/temp_upload \
  -H "X-API-Key: your-key" \
  -F "file=@./documents/guide.md" \
  -F "upload_mode=shared"

Python SDK

The add_resource, add_skill and other endpoints in the Python SDK automatically handle local file uploads, no need to call this endpoint manually. To opt into distributed shared temporary uploads in HTTP client mode, set upload.mode to "shared" in ovcli.conf.

CLI

CLI commands also automatically handle local file uploads, no need to call this endpoint manually.

Response Example

{
  "status": "ok",
  "result": {
    "temp_file_id": "upload_abc123def456.md"
  },
  "telemetry": {
    "operation_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

Possible shared response:

{
  "status": "ok",
  "result": {
    "temp_file_id": "shared_7f3c1b8d4f2e4b1bb0f6e8b2d9a4c123"
  }
}

Related Documentation

• File System - File and directory operations
• Skills - Skill management APIs
• Retrieval - Search and context acquisition
• ovpack Guide - Detailed ovpack import/export documentation