feat(opencode): per-model timeout, permissions, and wildcard glob config#22185
feat(opencode): per-model timeout, permissions, and wildcard glob config#22185tobias-weiss-ai-xr wants to merge 1 commit intoanomalyco:devfrom
Conversation
…port - Add per-model timeout field on Config.Model and Provider.Model, used in bash tool execution - Add per-model permission overrides merged with priority: model > agent > global - Add fallback model mechanism with retry logic on 429/5xx/timeout errors - Replace manual regex wildcard matching with minimatch for proper glob support
|
The following comment was made by an LLM, it may be inaccurate: Based on my search, I found one potentially related PR: PR #13189: feat: add model fallback support with TTFT-based timeout This PR appears related because it also addresses model-specific timeout configuration with a fallback mechanism (TTFT-based timeout). While it may be from an earlier implementation or different approach, it overlaps with the timeout and fallback features in the current PR #22185. No other clear duplicates were found. The other results address different aspects like bash tool execution, permissions, or unrelated features. |
|
This PR doesn't fully meet our contributing guidelines and PR template. What needs to be fixed:
Please edit this PR description to address the above within 2 hours, or it will be automatically closed. If you believe this was flagged incorrectly, please let a maintainer know. |
|
This pull request has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window. Feel free to open a new pull request that follows our guidelines. |
Closes #22211
What
Tool execution uses a single global timeout. Slow models need longer, fast models waste time waiting. No per-model tool restrictions exist.
How
opencode.jsonwith fallback chain (explicit → model → global)glm-*matches all GLM models)Verification