id = "collector"
version = "1.0.0"
name = "Collector Hand"
description = "Autonomous intelligence collector — monitors any target continuously with change detection and knowledge graphs"

category = "data"
icon = "🔍"

tools = [
  "shell_exec",
  "file_read",
  "file_write",
  "file_list",
  "web_fetch",
  "web_search",
  "memory_store",
  "memory_recall",
  "schedule_create",
  "schedule_list",
  "schedule_delete",
  "knowledge_add_entity",
  "knowledge_add_relation",
  "knowledge_query",
  "event_publish",
]

[routing]
aliases = [
  "monitor changes",
  "track updates",
  "collect intelligence",
  "osint",
  "change detection",
  "gather info",
  "market intelligence",
  "competitive analysis",
]
weak_aliases = [
  "watch",
  "signals",
  "continuous monitoring",
  "surveillance",
  "intel",
  "news monitoring",
]

# ─── Configurable settings ───────────────────────────────────────────────────

[[settings]]
key = "target_subject"
label = "Target Subject"
description = "What to monitor (company name, person, technology, market, topic)"
setting_type = "text"
default = ""

[[settings]]
key = "collection_depth"
label = "Collection Depth"
description = "How deep to dig on each cycle"
setting_type = "select"
default = "deep"

[[settings.options]]
value = "surface"
label = "Surface (headlines only)"

[[settings.options]]
value = "deep"
label = "Deep (full articles + sources)"

[[settings.options]]
value = "exhaustive"
label = "Exhaustive (multi-hop research)"

[[settings]]
key = "update_frequency"
label = "Update Frequency"
description = "How often to run collection sweeps"
setting_type = "select"
default = "daily"

[[settings.options]]
value = "hourly"
label = "Every hour"

[[settings.options]]
value = "every_6h"
label = "Every 6 hours"

[[settings.options]]
value = "daily"
label = "Daily"

[[settings.options]]
value = "weekly"
label = "Weekly"

[[settings]]
key = "focus_area"
label = "Focus Area"
description = "Lens through which to analyze collected intelligence"
setting_type = "select"
default = "general"

[[settings.options]]
value = "market"
label = "Market Intelligence"

[[settings.options]]
value = "business"
label = "Business Intelligence"

[[settings.options]]
value = "competitor"
label = "Competitor Analysis"

[[settings.options]]
value = "person"
label = "Person Tracking"

[[settings.options]]
value = "technology"
label = "Technology Monitoring"

[[settings.options]]
value = "general"
label = "General Intelligence"

[[settings]]
key = "alert_on_changes"
label = "Alert on Changes"
description = "Publish an event when significant changes are detected"
setting_type = "toggle"
default = "true"

[[settings]]
key = "report_format"
label = "Report Format"
description = "Output format for intelligence reports"
setting_type = "select"
default = "markdown"

[[settings.options]]
value = "markdown"
label = "Markdown"

[[settings.options]]
value = "json"
label = "JSON"

[[settings.options]]
value = "html"
label = "HTML"

[[settings]]
key = "max_sources_per_cycle"
label = "Max Sources Per Cycle"
description = "Maximum number of sources to process per collection sweep"
setting_type = "select"
default = "30"

[[settings.options]]
value = "10"
label = "10 sources"

[[settings.options]]
value = "30"
label = "30 sources"

[[settings.options]]
value = "50"
label = "50 sources"

[[settings.options]]
value = "100"
label = "100 sources"

[[settings]]
key = "track_sentiment"
label = "Track Sentiment"
description = "Analyze and track sentiment trends over time"
setting_type = "toggle"
default = "false"

# ─── Agent configuration ─────────────────────────────────────────────────────

[agent]
name = "collector-hand"
description = "AI intelligence collector — monitors any target continuously with OSINT techniques, knowledge graphs, and change detection"
module = "builtin:chat"
provider = "default"
model = "default"
max_tokens = 16384
temperature = 0.3
max_iterations = 60
system_prompt = """You are Collector Hand — an autonomous intelligence collector that monitors any target 24/7, building a living knowledge graph and detecting changes over time.

## Phase 0 — Platform Detection & State Recovery (ALWAYS DO THIS FIRST)

Detect the operating system:
```
python -c "import platform; print(platform.system())"
```

Then recover state:
1. memory_recall `collector_hand_state` — if it exists, load previous collection state
2. Read the **User Configuration** for target_subject, focus_area, collection_depth, etc.
3. file_read `collector_knowledge_base.json` if it exists — this is your cumulative intel
4. knowledge_query for existing entities related to the target

---

## Phase 1 — Schedule & Target Initialization

On first run:
1. Create collection schedule using schedule_create based on `update_frequency`
2. Parse the `target_subject` — identify what type of target it is:
   - Company: look for products, leadership, funding, partnerships, news
   - Person: look for publications, talks, job changes, social activity
   - Technology: look for releases, adoption, benchmarks, competitors
   - Market: look for trends, players, reports, regulations
   - Competitor: look for product launches, pricing, customer reviews, hiring
3. Build initial query set (10-20 queries tailored to target type and focus area)
4. Store target profile in knowledge graph

On subsequent runs:
1. Load previous query set and results
2. Check what's new since last collection

---

## Phase 2 — Source Discovery & Query Construction

Build targeted search queries based on focus_area:

**Market Intelligence**: "[target] market size", "[target] industry trends", "[target] competitive landscape"
**Business Intelligence**: "[target] revenue", "[target] partnerships", "[target] strategy", "[target] leadership"
**Competitor Analysis**: "[target] vs [competitor]", "[target] pricing", "[target] product launch", "[target] customer reviews"
**Person Tracking**: "[person] interview", "[person] talk", "[person] publication", "[person] [company]"
**Technology Monitoring**: "[target] release", "[target] benchmark", "[target] adoption", "[target] alternative"
**General**: "[target] news", "[target] latest", "[target] analysis", "[target] report"

Add temporal queries: "[target] this week", "[target] 2025"

---

## Phase 3 — Collection Sweep

For each query (up to `max_sources_per_cycle`):
1. web_search the query
2. For each promising result, web_fetch to extract full content
3. Extract key entities: people, companies, products, dates, numbers, events
4. Tag each data point with:
   - Source URL
   - Collection timestamp
   - Confidence level (high/medium/low based on source quality)
   - Relevance score (0-100)

Apply source quality heuristics:
- Official sources (company websites, SEC filings, press releases) = high confidence
- News outlets (established media) = medium-high confidence
- Blog posts, social media = medium confidence
- Forums, anonymous sources = low confidence

---

## Phase 4 — Knowledge Graph Construction

For each collected data point:
1. knowledge_add_entity for new entities (people, companies, products, events)
2. knowledge_add_relation for relationships between entities
3. Attach metadata: source, timestamp, confidence, focus_area

Entity types to track:
- Person (name, role, company, last_seen)
- Company (name, industry, size, funding_stage)
- Product (name, company, category, launch_date)
- Event (type, date, entities_involved, significance)
- Number (metric, value, date, context)

Relation types:
- works_at, founded, invested_in, partnered_with, competes_with
- launched, acquired, mentioned_in, related_to

---

## Phase 5 — Change Detection & Delta Analysis

Compare current collection against previous state:
1. Load `collector_knowledge_base.json` (previous snapshot)
2. Identify CHANGES:
   - New entities not in previous snapshot
   - Changed attributes (e.g., person changed company, new funding round)
   - New relationships between known entities
   - Disappeared entities (no longer mentioned)
3. Score each change by significance (critical/important/minor):
   - Critical: leadership change, acquisition, major funding, product launch
   - Important: new partnership, hiring surge, pricing change, competitor move
   - Minor: blog post, minor update, mention in article

If `alert_on_changes` is enabled and critical changes found:
- event_publish with change summary

If `track_sentiment` is enabled:
- Classify each source as positive/negative/neutral toward the target
- Track sentiment trend vs previous cycle
- Note significant sentiment shifts in the report

---

## Phase 6 — Report Generation

Generate an intelligence report in the configured `report_format`:

**Markdown format**:
```markdown
# Intelligence Report: [target_subject]
**Date**: YYYY-MM-DD | **Cycle**: N | **Sources Processed**: X

## Key Changes Since Last Report
- [Critical/Important changes with details]

## Intelligence Summary
[2-3 paragraph synthesis of collected intelligence]

## Entity Map
| Entity | Type | Status | Confidence |
|--------|------|--------|------------|

## Sources
1. [Source title](url) — confidence: high — extracted: [key facts]

## Sentiment Trend (if enabled)
Positive: X% | Neutral: Y% | Negative: Z% | Trend: [up/down/stable]
```

Save to: `collector_report_YYYY-MM-DD.{md,json,html}`

---

## Phase 7 — State Persistence

1. Save updated knowledge base to `collector_knowledge_base.json`
2. memory_store `collector_hand_state`: last_run, cycle_count, entities_tracked, total_sources
3. Update dashboard stats:
   - memory_store `collector_hand_data_points` — total data points collected
   - memory_store `collector_hand_entities_tracked` — unique entities in knowledge graph
   - memory_store `collector_hand_reports_generated` — increment report count
   - memory_store `collector_hand_last_update` — current timestamp

---

## Guidelines

- NEVER fabricate intelligence — every claim must be sourced
- Cross-reference critical claims across multiple sources before reporting
- Clearly distinguish facts from analysis/speculation in reports
- Respect rate limits — add delays between web fetches
- If a source is behind a paywall, note it as "paywalled" and extract what's visible
- Prioritize recency — newer information is generally more valuable
- If the user messages you directly, pause collection and respond to their question
- For competitor analysis, maintain objectivity — report facts, not opinions
"""

[dashboard]
[[dashboard.metrics]]
label = "Data Points"
memory_key = "collector_hand_data_points"
format = "number"

[[dashboard.metrics]]
label = "Entities Tracked"
memory_key = "collector_hand_entities_tracked"
format = "number"

[[dashboard.metrics]]
label = "Reports Generated"
memory_key = "collector_hand_reports_generated"
format = "number"

[[dashboard.metrics]]
label = "Last Update"
memory_key = "collector_hand_last_update"
format = "text"

# ─── Token & Performance Metadata ─────────────────────────────────────────────

[metadata]
frequency = "continuous"
token_consumption = "high"
default_active = false
activation_warning = "Collector hand runs continuously and monitors targets, consuming tokens."

# ─── Internationalization (optional) ─────────────────────────────────────────
# All i18n sections are optional. Without them, the English values above are used.
# To localize, add [i18n.LANG] sections (e.g. zh, ja, ko, es, fr, de).
# Settings translations are also optional — omit to keep English labels.

# ─── Chinese (简体中文) ────────────────────────────────────────────────────

[i18n.zh]
name = "情报采集 Hand"
description = "自主情报采集智能体——持续监控目标，支持变更检测和知识图谱"
category = "数据"

[i18n.zh.settings.target_subject]
label = "监控目标"
description = "要监控的对象（公司名称、人物、技术、市场、话题）"

[i18n.zh.settings.collection_depth]
label = "采集深度"
description = "每个采集周期的挖掘深度"

[i18n.zh.settings.update_frequency]
label = "更新频率"
description = "执行采集扫描的频率"

[i18n.zh.settings.focus_area]
label = "关注领域"
description = "分析采集情报时的侧重角度"

[i18n.zh.settings.alert_on_changes]
label = "变更告警"
description = "检测到重大变更时发布事件通知"

[i18n.zh.settings.report_format]
label = "报告格式"
description = "情报报告的输出格式"

[i18n.zh.settings.max_sources_per_cycle]
label = "每周期最大来源数"
description = "每次采集扫描处理的最大来源数量"

[i18n.zh.settings.track_sentiment]
label = "情感追踪"
description = "分析并追踪随时间变化的情感趋势"

# ─── Japanese (日本語) ────────────────────────────────────────────────────

[i18n.ja]
name = "インテリジェンス収集 Hand"
description = "自律型インテリジェンス収集エージェント——変更検出とナレッジグラフによる対象の継続的監視"
category = "データ"

[i18n.ja.settings.target_subject]
label = "監視対象"
description = "監視する対象（企業名、人物、技術、市場、トピック）"

[i18n.ja.settings.collection_depth]
label = "収集深度"
description = "各収集サイクルでの調査の深さ"

[i18n.ja.settings.update_frequency]
label = "更新頻度"
description = "収集スキャンの実行頻度"

[i18n.ja.settings.focus_area]
label = "フォーカスエリア"
description = "収集したインテリジェンスを分析する際の視点"

[i18n.ja.settings.alert_on_changes]
label = "変更アラート"
description = "重大な変更が検出された場合にイベント通知を発行する"

[i18n.ja.settings.report_format]
label = "レポート形式"
description = "インテリジェンスレポートの出力形式"

[i18n.ja.settings.max_sources_per_cycle]
label = "サイクルあたりの最大ソース数"
description = "各収集スキャンで処理するソースの最大数"

[i18n.ja.settings.track_sentiment]
label = "センチメント追跡"
description = "時間の経過に伴うセンチメントの傾向を分析・追跡する"

# ─── Spanish (Español) ────────────────────────────────────────────────────

[i18n.es]
name = "Hand de Recopilación de Inteligencia"
description = "Recopilador autónomo de inteligencia — monitorea cualquier objetivo de forma continua con detección de cambios y grafos de conocimiento"
category = "Datos"

[i18n.es.settings.target_subject]
label = "Objetivo de monitoreo"
description = "Qué monitorear (nombre de empresa, persona, tecnología, mercado, tema)"

[i18n.es.settings.collection_depth]
label = "Profundidad de recopilación"
description = "Qué tan profundo investigar en cada ciclo"

[i18n.es.settings.update_frequency]
label = "Frecuencia de actualización"
description = "Con qué frecuencia ejecutar los barridos de recopilación"

[i18n.es.settings.focus_area]
label = "Área de enfoque"
description = "Perspectiva desde la cual analizar la inteligencia recopilada"

[i18n.es.settings.alert_on_changes]
label = "Alertar ante cambios"
description = "Publicar un evento cuando se detecten cambios significativos"

[i18n.es.settings.report_format]
label = "Formato de informe"
description = "Formato de salida para los informes de inteligencia"

[i18n.es.settings.max_sources_per_cycle]
label = "Máximo de fuentes por ciclo"
description = "Número máximo de fuentes a procesar por barrido de recopilación"

[i18n.es.settings.track_sentiment]
label = "Seguimiento de sentimiento"
description = "Analizar y rastrear las tendencias de sentimiento a lo largo del tiempo"

# ─── French (Français) ────────────────────────────────────────────────────

[i18n.fr]
name = "Hand Collecteur de Renseignements"
description = "Collecteur autonome de renseignements — surveille toute cible en continu avec détection de changements et graphes de connaissances"
category = "Données"

[i18n.fr.settings.target_subject]
label = "Sujet cible"
description = "Objet de la surveillance (nom d'entreprise, personne, technologie, marché, sujet)"

[i18n.fr.settings.collection_depth]
label = "Profondeur de collecte"
description = "Niveau d'approfondissement à chaque cycle de collecte"

[i18n.fr.settings.update_frequency]
label = "Fréquence de mise à jour"
description = "Fréquence d'exécution des cycles de collecte"

[i18n.fr.settings.focus_area]
label = "Domaine d'intérêt"
description = "Angle d'analyse des renseignements collectés"

[i18n.fr.settings.alert_on_changes]
label = "Alerte sur changements"
description = "Publier un événement lorsque des changements significatifs sont détectés"

[i18n.fr.settings.report_format]
label = "Format de rapport"
description = "Format de sortie pour les rapports de renseignements"

[i18n.fr.settings.max_sources_per_cycle]
label = "Sources maximum par cycle"
description = "Nombre maximum de sources à traiter par cycle de collecte"

[i18n.fr.settings.track_sentiment]
label = "Suivi du sentiment"
description = "Analyser et suivre les tendances de sentiment au fil du temps"

# ─── German (Deutsch) ────────────────────────────────────────────────────

[i18n.de]
name = "Informationssammlungs-Hand"
description = "Autonomer Informationssammler — überwacht jedes Ziel kontinuierlich mit Änderungserkennung und Wissensgraphen"
category = "Daten"

[i18n.de.settings.target_subject]
label = "Zielobjekt"
description = "Was überwacht werden soll (Firmenname, Person, Technologie, Markt, Thema)"

[i18n.de.settings.collection_depth]
label = "Sammlungstiefe"
description = "Wie tief in jedem Sammlungszyklus recherchiert wird"

[i18n.de.settings.update_frequency]
label = "Aktualisierungshäufigkeit"
description = "Wie oft Sammlungszyklen ausgeführt werden"

[i18n.de.settings.focus_area]
label = "Fokusbereich"
description = "Perspektive für die Analyse der gesammelten Informationen"

[i18n.de.settings.alert_on_changes]
label = "Warnung bei Änderungen"
description = "Ein Ereignis veröffentlichen, wenn bedeutende Änderungen erkannt werden"

[i18n.de.settings.report_format]
label = "Berichtsformat"
description = "Ausgabeformat für Informationsberichte"

[i18n.de.settings.max_sources_per_cycle]
label = "Maximale Quellen pro Zyklus"
description = "Maximale Anzahl der pro Sammlungszyklus zu verarbeitenden Quellen"

[i18n.de.settings.track_sentiment]
label = "Stimmungsverfolgung"
description = "Stimmungstrends im Zeitverlauf analysieren und verfolgen"

# ─── Korean (한국어) ────────────────────────────────────────────────────

[i18n.ko]
name = "정보 수집 Hand"
description = "자율 정보 수집 에이전트 — 대상을 지속적으로 모니터링하며 변경 감지 및 지식 그래프 지원"
category = "데이터"

[i18n.ko.settings.target_subject]
label = "모니터링 대상"
description = "모니터링할 대상 (회사명, 인물, 기술, 시장, 주제)"

[i18n.ko.settings.collection_depth]
label = "수집 깊이"
description = "각 수집 주기의 조사 깊이"

[i18n.ko.settings.update_frequency]
label = "업데이트 빈도"
description = "수집 스캔 실행 주기"

[i18n.ko.settings.focus_area]
label = "관심 분야"
description = "수집된 정보를 분석하는 관점"

[i18n.ko.settings.alert_on_changes]
label = "변경 알림"
description = "중요한 변경 사항 감지 시 이벤트 알림 발행"

[i18n.ko.settings.report_format]
label = "보고서 형식"
description = "정보 보고서의 출력 형식"

[i18n.ko.settings.max_sources_per_cycle]
label = "주기당 최대 소스 수"
description = "수집 스캔당 처리할 최대 소스 수"

[i18n.ko.settings.track_sentiment]
label = "감성 추적"
description = "시간에 따른 감성 추세 분석 및 추적"