anthropic-sdk-csharp — Engineering Performance
2 engineers all time · Nov 2025 – Jan 2026 · built 2026-09-09 · GitHub
Performance snapshot
Today's rolling 90-day reading for anthropic-sdk-csharp, compared with the start of the series. Pick a window to move that comparison point.
Avg. perf / dev / mo
−100.0%
0.55 → 0.00 ETV
Active engineers
−100.0%
3.0 → 0.0
Features
−23.4pp
23.4% → 0.0%
Performance Composition
Each month's output split by type of work: Features (new value), Maintenance (sustaining systems), Tests, Docs, and Fixes (rework). The yellow line is output per engineer, so when it rises each engineer is delivering more, whatever the team size did. Unit: Engineering Throughput Value (ETV).
Engineering capacity
Effective engineers behind anthropic-sdk-csharp, against its pre-AI baseline. Each subject has its own: anthropic-sdk-csharp's is 0.55 ETV / dev / mo, its first reading in Q4 2025. Per-engineer ETV divided by that gives a capacity multiple, and that multiple applied to the engineers active in the trailing 90 days turns it into engineer-equivalents. The line is the real headcount, so the gap between line and area is what the leverage is worth. Because each baseline is its own, every subject opens at 1.0x on its first day: multiples measure improvement and are not comparable between subjects.
Knowledge concentration
How dependent is this repo on a small number of engineers? Higher top-1 share = higher key-person risk.
Stephen Toub owns 90.9 % of commits.
Behind the numbers
Written summary of the work completed each month.
No monthly reports available yet.
Most impactful commits
Top 10 by ETV in the all-time window.
- 2.8ETVAdd Microsoft.Extensions.AI supportStephen Toub · eefa6a05 · 2025-11-04
- 1.3ETVfeat: add Foundry client For more information, see: https://aka.ms/foundry/claude/docs https://docs.claude.com/en/docs/build-with-claude/claude-in-microsoft-foundryRobert Craigie · 5f87e129 · 2025-11-18
- 0.5ETVAdd multi-modal tool result support to IChatClients - Adds support for translating AIContent returned from AIFunctions to map to the corresponding BetaToolResultBlockParamContent - Adds support for passing through the new DeferLoading, Strict, InputExamples, and AllowedCallers settings from AIFunction.AdditionalProperties through to BetaToolStephen Toub · d94eb1d9 · 2025-11-25
- 0.1ETVImprove reporting of token counts in UsageDetails (#70) * Improve reporting of token counts in UsageDetails - InputTokenCount needs to reflect cached tokens. - Only add to AdditionalCounts for positive counts. - Added reporting of WebFetch/SearchRequests. * lint * lint take 2Stephen Toub · 5f7afa45 · 2025-12-11
- 0.1ETVFix incorrect handling of polyfills - The System.Runtime.CompilerServices / System.Diagnostics.CodeAnalysis types should all be internal rather than public; otherwise they will lead to ambiguity warnings with consumers and also won't type unify. - The System.Collection.Immutable / ValueTask types should not be polyfilled; they instead should just use the netstandard2.0 packages. - Anthropic.Foundry needs to include the shims.cs file correctly.Stephen Toub · 5b2afd53 · 2025-11-20
- 0.1ETVdotnet csharpier formatStephen Toub · 737b643a · 2025-11-20
- 0.1ETVUpdate to M.E.AI.Abstractions 10.1.1 (#75)Stephen Toub · d5775c75 · 2026-01-05
- 0.0ETVFix ,IL2026/IL3050 warnings in Anthropic{Beta}ClientExtensions I temporarily unsuppressed them in the csproj and fixed the issues in these two files.Stephen Toub · 42c22fe2 · 2025-11-20
- 0.0ETVDisable CA1510 as the project multitargetsStephen Toub · a8142da8 · 2025-11-19
- 0.0ETVAddress feedbackStephen Toub · 3034edde · 2025-11-19