Files
Mani Saint-Victor c7be701abf docs: add subscription OAuth recipe (Claude + ChatGPT/Codex) (#326)
* docs: add subscription OAuth recipe (Claude + ChatGPT/Codex)

Standalone guide for running EvoScientist on Claude Pro/Max and ChatGPT
Plus/Pro subscriptions via ccproxy OAuth, previously only partially
covered inside the macOS deployment recipe.

Documents the two Codex-route pitfalls from #323 with their exact error
strings — ccproxy's default model mappings silently rewriting gpt-* to
gpt-5.3-codex, and the backend's client-identity gate ('requires a newer
version of Codex') — plus the manual ccproxy TOML fix for self-managed
instances, account-tier model availability, verification probes, and a
troubleshooting table. Adds the recipe to the docs index.

* docs: correct subscription OAuth guidance

* docs: remove stale Codex client version guidance

* docs: show the config section to add instead of a clobbering heredoc

* docs: correct reasoning_effort default behavior on the Codex route

* docs: drop private helper import from the Codex probe

* docs: warn that local ccproxy config files shadow the global one

---------

Co-authored-by: Dinos Papakostas <dinospk1999@gmail.com>
2026-08-20 08:14:11 +01:00

2.6 KiB

🍪 Examples & Recipes

Customize your EvoScientist — harness it, make it yours.

Example Description
Survey literature Run EvoScientist with the paper-navigator skill to produce a bilingual, conference-grade literature survey
Recipe Description
macOS 24/7 Deployment Run EvoScientist as an always-on service on macOS with OAuth + Telegram + STT
Subscription OAuth (Claude + ChatGPT/Codex) Use Claude and GPT models through your existing subscriptions — no API keys, including Codex-route pitfalls & fixes
Guide Description
stream-json output protocol Line-delimited JSON event stream (--output-format stream-json) for driving EvoScientist headlessly from SDK / programmatic clients

Contributing a Recipe

See the Contributing Guide for general guidelines. When adding a new recipe:

  • Use EvoSci CLI — recipes should work with EvoSci serve, EvoSci config, or EvoSci onboard
  • Pin dependencies — specify EvoScientist extras (e.g., pip install -e ".[telegram,stt]")
  • Include a README with clear setup and usage instructions
  • Keep it focused — each recipe should demonstrate one deployment or integration scenario
  • Add to the table above so others can discover it