Changelog
New updates and improvements to OpenCode
v1.4.1 Fix
clangdchoosingCMakeLists.txtorMakefileas the project root in C and C++ workspacesImprovements
- CoreAdd permission prompts for GitLab Duo Workflow tool calls instead of auto-running them.@vglafirov
- CoreHide unsupported variants for Big Pickle models.
v1.4.0 Added OTLP observability export support
Improvements 8
- CoreFixed failed web fetches leaving stale timeouts behind.
- CoreImproved
opencode logintransport error messages. - CoreRetried Alibaba provider rate-limit errors instead of failing immediately.
- CoreKept model variants scoped to the selected model.
- CoreAdded full HTTP proxy support.
- CoreFixed OpenRouter provider issues.
- CoreAligned GitHub Copilot Anthropic reasoning levels and removed incorrect Qwen variants.
- CoreReduced TypeScript LSP memory use by using the native project config.@derekbar90
v1.3.17 Improvements
Improvements
- CoreCloudflare Workers AI and AI Gateway now prompt for missing account details and show clear setup errors when required Cloudflare variables are missing@mchenco
v1.3.16 Support Azure model options on both chat and responses paths
Improvements
- CoreExpose session model and mode config options through ACP@georgeharker
- CoreAdd a separating blank line before read tool file contents for clearer output
- CoreFix output token totals when reasoning tokens are reported separately
- ExtensionsFix plugin installs from npm aliases and git URLs, including Windows cache path issues
v1.3.15 v1.3.14 Restored git-backed review modes
Restored git-backed review modes, including uncommitted and branch diffs.
Improvements 7
- CoreFixed revert chains so restoring an earlier message also restores the right snapshot state.@natewill
- CoreAdded macOS managed preferences for MDM-enforced config.@lennyvaknine43
- CoreFixed sessions getting stuck after tool calls with OpenAI-compatible providers.@valenvivaldi
- CoreKept compaction summaries in the conversation's language.@aaron-he-zhu
- CoreAdded Venice AI as a provider.@dpuyosa
- CoreRespected model-specific
limit.inputoverrides.@ykswang - ExtensionsAdded support for theme-only plugin packages.
v1.3.12 Enabled prompt caching and cache token tracking for Google Vertex Anthropic
Improvements
- CoreFixed Azure provider options being forwarded correctly after the AI SDK v6 migration.
v1.3.11 Add a dedicated system prompt for Kimi models
Improvements
- ExtensionsSkip plugins that do not expose a matching server or TUI entrypoint, warn instead of failing, and apply default options from package exports on install.
- ExtensionsPin explicit plugin versions during install and block package install scripts from running.
v1.3.10 Subagent tool calls stay clickable while they are pending
Improvements
- CoreImproved storage migration reliability so malformed legacy records or failed migrations do not corrupt upgraded state.
v1.3.9