AI Narrative

How DevHunt turns a local profile into prompts, when it contacts a provider, and what it writes.

Input profile

narrate LOGIN reads out/LOGIN/profile.json and compresses selected profile fields into a prompt-oriented object. That material can include token-visible profile fields, tags, repository-derived summaries, and project-defined metric values. If the scan used a privileged token, the prompt can therefore contain material derived from private or internal-visible records.

Without OPENAI_API_KEY

When OPENAI_API_KEY is absent, the command does not call the provider path. It prints the generated system and user prompts and saves them to out/LOGIN/narrate_prompt.txt. Review that file before copying it elsewhere.

With a configured provider

When OPENAI_API_KEY is present, the command sends profile-derived system and user prompt material to an OpenAI-compatible chat-completions endpoint. OPENAI_BASE_URL and OPENAI_MODEL can change the configured endpoint and model. This source behavior does not establish any provider privacy or retention guarantee.

Local output

A successful provider response is printed and saved as out/LOGIN/narrative.md. Treat the narrative as generated interpretation: compare it with the profile, preserve unknowns, and do not turn descriptive heuristics into claims about a person.