Directory.Build.props

<Project>
  <PropertyGroup>
    <Copyright>© $([System.DateTime]::Now.Year)</Copyright>
    <PackageLicenseExpression>MIT</PackageLicenseExpression>
    <PackageProjectUrl>https://github.com/petabridge/memorizer-v1</PackageProjectUrl>
    <VersionPrefix>2.3.2</VersionPrefix>
    <TreatWarningsAsErrors>true</TreatWarningsAsErrors>
    <WarningsNotAsErrors>CS1591</WarningsNotAsErrors>
    <Deterministic>true</Deterministic>
    <PackageReleaseNotes>**Bug Fixes**
- [Use Ollama's /api/embed with truncate so long memories can be stored](https://github.com/petabridge/memorizer/pull/253) - Memories longer than the embedding model's context window now store instead of failing
  - Previously any memory whose title plus text exceeded the context window failed with "the input length exceeds the context length" — with the default `all-minilm` model (256 tokens), that is anything over roughly 700 characters
  - The Ollama client now calls `/api/embed` with `truncate: true` in place of the legacy `/api/embeddings` endpoint, so the text is stored in full and its embedding is computed from the part that fits
  - Existing embeddings stay valid: `/api/embed` returns L2-normalised vectors and search ranks by cosine distance
  - Search can still only match the text that fits the context window — widening that needs a larger-context model
- [Return an honest error when a write can't generate its embedding](https://github.com/petabridge/memorizer/pull/233) - A failed write says what went wrong and states that nothing was saved
  - The previous generic "check the arguments against the tool's schema and retry" reply was misleading, since the arguments were not the problem
  - The message now names the model, reports the input length, distinguishes text-too-long from backend-unavailable, and passes the backend's own error through</PackageReleaseNotes>
    <ContinuousIntegrationBuild Condition="'$(GITHUB_ACTIONS)' == 'true'">true</ContinuousIntegrationBuild>
  </PropertyGroup>
</Project>