OpenCode bug: custom provider config in opencode. ignored, breaking local Ollama
qhliyp · ghdev · 2026-10-09
A user reports that OpenCode 1.18.35 silently ignores custom provider definitions in opencode.: following the official docs to set up a local Ollama provider (@ai-sdk/openai-compatible, baseURL http://localhost:11434/v1) never shows up in opencode models, and running a model throws ProviderModelNotFoundError.
Key debugging details:
- Credentials configured in auth.; local Ollama is healthy (GET /v1/models returns 200 with qwen2.5:7b)
- DEBUG logs show no outbound network request before the error, indicating a config-loading issue rather than network/proxy trouble
- Environment: Windows 11, Windows Terminal, installed via npm opencode-ai
- Full reproduction steps included; issue has 5 comments
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23