feat: add persona runtime demo with multiple personas

[joy7758]

Summary

• add researcher and marketing persona JSON files
• add a lightweight persona loader for runtime use
• add a runnable demo that loads the selected personas and prints their runtime summaries

Validation

• ran Loaded personas:

---

Design Persona (Designer)
skills: UI Design, UX Research, Prototyping, Adobe XD, Figma

Research Persona (Researcher)
skills: literature search, information synthesis, technical explanation

Marketing Persona (Marketing Manager)
skills: copywriting, campaign design, product positioning

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 40e63ee082

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Add required persona_id to new persona file

This JSON is placed in personas/, and the registry code (pop.registry) iterates that directory and loads each file with pop.loader.load_persona(), which requires a non-empty persona_id. Because this file omits persona_id, calls like list_persona_ids() (and resolve_persona() for refs that scan past this entry) now raise ValueError and break registry/CLI flows whenever these demo personas are present.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

Resolve demo persona paths from project root

run_demo() calls load_all_personas() without a folder, so the loader defaults to relative personas/ under the current working directory. If the script is launched from outside the repo root (for example python /workspace/persona-object-protocol/demos/persona_agent_demo.py), it fails with FileNotFoundError for personas/design_persona.json despite already computing PROJECT_ROOT.

Useful? React with 👍 / 👎.