WebAI-API integration how-to

[gitricko]

Objective

Include WebAI-API which is proxy to gemini so that openclaw can use. it
Note, it does not support tool support

[Copilot]

Pull request overview

Adds a documented, opt-in WebAI-API (Gemini-Web proxy) service alongside the existing OpenClaw-WebTop setup, plus minor updates to default model instructions and container versions.

Changes:

• Add a webai-api docker-compose service behind a compose profile and a make start-webai-api target to run it on demand.
• Add a WebAI-API integration how-to document (cookie import + OpenClaw provider configuration prompt).
• Update README model pull/launch example and bump OpenClaw/Ollama versions in the Dockerfile.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 11 comments.

Show a summary per file

File	Description
README.md	Updates the example Ollama model used in the quick-start steps.
Makefile	Adds a new target to start the WebAI-API compose profile.
docs/webai-to-api-integration.md	Introduces step-by-step WebAI-API setup instructions and example config text.
docker/Dockerfile	Bumps OpenClaw and Ollama versions used in the image build.
docker-compose.yml	Pins the WebTop image tag and adds the opt-in webai-api service.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The start target exports PUID/PGID, but docker-compose.yml uses ${DOCKER_PUID}/${DOCKER_PGID} for substitution. As a result the container will fall back to the hard-coded defaults (501/20), which can cause permission issues on mounted volumes. Align the variable names (either set DOCKER_PUID/DOCKER_PGID here or change the compose file to read PUID/PGID).