Agent OS · Component · contextual-companion
Contextual spiritual companion responses
What it does
Combines emotional-state assessment, recent dialogue, preferences, relevant memories and curated scripture to produce supportive responses and continuation prompts; optional model-based structured generation augments deterministic templates.
Core pattern
Emotional cues and memory + supportive responses
- Input
- User text and stored context
- Output
- Structured response, state, scripture recall, prayer and follow-up metadata
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| message | string | — | — |
| locale | string | en | — |
| timezone | string | UTC | — |
| preferences | — | — | — |
| history_limit | integer | 20 | 0–1000 |
Maturity and limits
HTTP service, structured Zod model calls, fallback generation and domain tests exist. Source paths were inspected statically; tests and live integrations were not executed. This rating describes implemented code, not production validation.
Sensitive emotional/religious data; rule/model outputs are not clinical assessments; Credential-bearing configuration is excluded from this inventory.
Used in pipelines
Industry tags
- Lifestyle & consumer appsSource-supported industry
For work involving opt-in interactions, digital services and personal preferences, use emotional cues and memory followed by supportive responses.
- EducationTransferable use
For opt-in practice and role dialogue for adult learners, use emotional cues and memory followed by supportive responses.
Skills pack
Contract scaffold and deterministic mock
Download · 11KBSHA-256 66c254354cb581145d2f6ae6694a246de704e81df42ed0ea16fd02f4acb07510
Related components
-
Versioned agent memory and knowledge lifecycle
Scoped memory retrieval + versioning and forgetting
Working 1 pipeline -
Streaming travel concierge
Conversational intake + tool search and candidate cards
Working 1 pipeline -
Contextual streaming assistant with history
Input and retrieval chaining + streamed replies and session history
Working 2 pipelines -
Onboarding and adaptive preferences
Explicit preferences + historically tracked preference signals
Working 1 pipeline