#7432: Comprehensive Ollama Support PR

Takes most/all of the Ollama PRs and merges them into 1 more managable PR. <!-- greptile_comment --> <h2>Greptile Overview</h2> <h3>Greptile Summary</h3> This PR consolidates Ollama onboarding and provider support by: - Adding an interactive auth choice handler for Ollama plus a non-interactive `--ollama-base-url` path. - Introducing a native Ollama client (`/api/chat` + `/api/tags`) with unit tests. - Changing provider resolution to auto-discover a local Ollama instance and populate an `ollama` provider when models are detected. The changes fit into the existing onboarding/auth-choice flow (`src/commands/onboard-*`) and provider discovery (`src/agents/models-config.providers.ts`) by treating Ollama as an OpenAI-compatible provider and wiring it into the same config/profile mechanisms used by other providers. <h3>Confidence Score: 3/5</h3> - This PR looks reasonably safe to merge, but has a few integration mismatches that could cause confusing behavior in real Ollama setups. - Core changes are straightforward and covered by unit tests for the new native client, but there’s a likely sentinel mismatch for the local API key (`ollama` vs `ollama-local`) and provider discovery now introduces a network probe during implicit provider resolution, which could degrade UX when Ollama isn’t running. - src/commands/onboard-auth.models.ts, src/agents/models-config.providers.ts, src/commands/onboard-auth.config-core.ts <!-- greptile_other_comments_section --> _{(2/5) Greptile learns from your feedback when you react with thumbs up/down!} **Context used:** - Context from `dashboard` - CLAUDE.md ([source](https://app.greptile.com/review/custom-context?memory=fd949e91-5c3a-4ab5-90a1-cbe184fd6ce8)) - Context from `dashboard` - AGENTS.md ([source](https://app.greptile.com/review/custom-context?memory=0d0c8278-ef8e-4d6c-ab21-f5527e322f13)) <!-- /greptile_comment -->