v0.12.0

🎉 Release v0.12.0

Changes included in the first tagged release.

Features

• feat: add workflow_dispatch trigger to publish workflow (849e16f)
• feat: update package structure and configuration for GitHub Packages (62b0be1)
• feat: add configuration helper command (80260c6)
• feat: add legacy config migration command (393d1f2)
• feat: add Level 4 prefix-based matching for model variants (98e79a2)
• feat: extend models.dev fallback with all metadata fields (55703af)
• feat: add models.dev fallback with 3-level matching (dbb14e6)
• feat: add default fallback values for model limits (7dfa5e9)
• feat: support connect-backed model discovery (1a76980)
• feat: enable model info discovery by default (0329004)
• feat: enrich LiteLLM discovered models (20dc482)
• feat: allow discovery overrides to bypass provider detection (09e6d19)
• feat: support provider-specific models endpoints (a4d55c4)
• feat: add provider-level discovery overrides (8fe6297)
• feat: add regex model filtering (ab5c42c)
• feat: universal OpenAI-compatible model discovery plugin (ba1d448)
• feat: add GitHub Actions workflow for automated releases (65d3438)
• feat: support NPM_TOKEN environment variable in release script (aa66734)
• feat: add automated release script (14f7011)
• feat: implement model status caching system (c709eda)
• feat: integrate enhanced error handling into chat.params hook (b257749)
• feat: add enhanced error handling utilities (42a7776)
• feat: implement chat.params hook for LM Studio model validation (d053fc7)
• feat: enhance LM Studio plugin with model preloading and smart detection (b16c198)
• feat: initial LM Studio plugin implementation (9885139)

Fixes

• fix: ensure default context limits are always set with correct fallback sequence (f7e48bd)
• fix: fallback when fetch fails during discovery (cc77cdf)
• fix: align plugin peer dependency with opencode engine (ea623a9)
• fix: allow manual publish workflow reruns (5fbf472)
• fix: fail release when npm publish fails (6ce19e5)
• fix: make release flow branch-protection compatible (b58a8a2)
• fix: skip embedding model discovery (952d18f)
• fix: improve release note generation (9344ea8)
• fix: prefer provider model filters over global config (00fee02)
• fix: apply provider discovery overrides consistently (eab00c7)
• fix: default discovered models to raw ids (e61f92f)
• fix: use package metadata in release script (f71e597)
• fix: configure git identity for release workflow (c3d7d40)
• fix: route plugin logs through structured app logger (a9ccf72)
• fix: improve npm publish error handling - don't exit on failure (3345734)
• fix: normalize repository URL format for npm (64c3762)
• fix: remove problematic chat.params hook to resolve TypeScript errors (4c74e62)

Documentation

• docs: clarify provider-level configuration transition (4f13cbe)
• docs: reorganize README and guides (06127f0)
• docs: update discovery configuration examples (f305b01)
• docs: document provider discovery overrides (4f151f0)
• docs: add repository badges (9033ebd)
• docs: clarify smart model name behavior (8736901)
• docs: add project disclaimer (b0473df)
• docs: add npm badges and update provider table with CLIProxyAPI (7ee78bb)
• docs: remove unimplemented auto-detection feature from README (a98c36a)
• docs: add comprehensive release documentation (a161e7b)
• docs: update README with new features and add prepublishOnly script (ab9fa5a)
• docs: add comprehensive TASKS.md with project roadmap (d1f9d17)

Maintenance

• Merge pull request yuhp#33 from yuhp/release/v0.12.0 (53c0104)
• Merge pull request yuhp#31 from yuhp/feat/v0.12-provider-config-migration (d31e9af)
• ci: use publish title for release prs (63136bb)
• ci: sync lockfile version during release (7de1c1b)
• refactor: remove unused chat params hook (2f10d60)
• chore: update opencode plugin dev dependency (3e96f09)
• Merge pull request yuhp#30 from yuhp/release/v0.11.1 (b344470)
• Merge pull request yuhp#29 from yuhp/refactor/openai-discovery-http-client (6fa40ee)
• ci: release from dev by default (5458a54)
• refactor: remove unused provider auto-detection (c114872)
• refactor: use low-level http client for discovery (86b6b33)
• Merge pull request yuhp#28 from yuhp/release/v0.11.0 (44a492b)
• Merge remote-tracking branch 'origin/main' into release/v0.11.0 (89d9f5a)
• Merge pull request yuhp#26 from rajebdev/feat/upgrade-features (e151121)
• refactor: make models.dev metadata enrichment explicit (19bb4c7)
• chore: update gitignore and dependencies - Update .gitignore patterns - Refresh package-lock.json with latest dependencies (e20e2d0)
• Merge pull request yuhp#23 from yuhp/release/v0.10.3 (6345868)
• Merge pull request yuhp#22 from yuhp/pr-20-fetch-fallback-patch (e06eac3)
• Merge pull request yuhp#17 from yuhp/release/v0.10.2 (726f553)
• Merge pull request yuhp#16 from yuhp/host-env-auth-store (d57f12c)
• Support host-specific auth stores for Mimocode compatibility (3290d14)
• Merge pull request yuhp#15 from yuhp/release/v0.10.1 (d2847d5)
• Merge pull request yuhp#14 from yuhp/dev (811f09d)
• refactor(deps): move @opencode-ai/plugin to peerDependencies (48ac86f)
• Merge pull request yuhp#12 from yuhp/release/v0.10.0 (3ec0e14)
• Merge pull request yuhp#10 from yuhp/issue-5-auth-discovery-investigation (2c53878)
• Merge pull request yuhp#4 from yuhp/release/v0.9.0 (0210508)
• Merge pull request yuhp#3 from xz-dev/litellm-model-info-discovery (ae3cee5)
• refactor: make model info enrichment provider-specific (0b3ec10)
• Merge branch 'feature/provider-models-fetch-path' (982eb16)
• Merge branch 'config-by-provider-options' (3a2482e)
• chore: align plugin naming and logging (ed80c86)
• chore: update release workflow for trusted publishing (62f8f19)
• chore: switch npm release to trusted publishing (7180de9)
• merge: release v0.5.0 regex model filtering (047df57)
• chore: remove .tgz packaging artifact from repository (44b381e)
• chore: rename package to opencode-models-discovery (plural) (ab88214)
• chore(deps): bump esbuild, vitest and @vitest/coverage-v8 (yuhp#6) (7c022de)
• refactor: modularize codebase and improve model discovery (1481f9d)
• Merge pull request yuhp#5 from agustif/feat/task-1-4-loading-state-monitoring (0cd6c29)
• Merge pull request yuhp#4 from agustif/feat/task-1-3-model-status-caching (0cc7de0)
• Merge pull request yuhp#3 from agustif/feat/task-1-2-enhanced-error-handling (9d51555)
• Merge pull request yuhp#2 from agustif/feat/task-1-1-chat-params-hook (8311a45)
• refactor: create modular structure for better maintainability (c507ca4)
• Merge branch 'feat/task-1-1-chat-params-hook' into feat/task-1-2-enhanced-error-handling (24b1461)
• chore: add MIT license (0771b2e)

Installation

echo "//npm.pkg.github.com/:_authToken=${GH_TOKEN}" > ~/.npmrc
echo "@AI-Trash:registry=https://npm.pkg.github.com" >> ~/.npmrc
npm install @AI-Trash/opencode-models-discovery@0.12.0