Markitdown debugging

.claude/settings.local.json

@@ -8,5 +8,9 @@
       "Bash(dotnet build:*)",
       "Bash(dotnet test:*)"
     ]
-  }
+  },
+  "enabledMcpjsonServers": [
+    "aspire"
+  ],
+  "enableAllProjectMcpServers": true
 }

.claude/skills/aspire/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: aspire
+description: "Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps. USE FOR: aspire start, aspire stop, start aspire app, aspire describe, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost. DO NOT USE FOR: non-Aspire .NET apps (use dotnet CLI), container-only deployments (use docker/podman), Azure deployment after local testing (use azure-deploy skill). INVOKES: Aspire CLI commands (aspire start, aspire describe, aspire otel logs, aspire docs search, aspire add), bash. FOR SINGLE OPERATIONS: Use Aspire CLI commands directly for quick resource status or doc lookups."
+---
+
+# Aspire Skill
+
+This repository uses Aspire to orchestrate its distributed application. Resources are defined in the AppHost project (`apphost.cs` or `apphost.ts`).
+
+## CLI command reference
+
+| Task | Command |
+|---|---|
+| Start the app | `aspire start` |
+| Start isolated (worktrees) | `aspire start --isolated` |
+| Restart the app | `aspire start` (stops previous automatically) |
+| Wait for resource healthy | `aspire wait <resource>` |
+| Stop the app | `aspire stop` |
+| List resources | `aspire describe` or `aspire resources` |
+| Run resource command | `aspire resource <resource> <command>` |
+| Start/stop/restart resource | `aspire resource <resource> start|stop|restart` |
+| View console logs | `aspire logs [resource]` |
+| View structured logs | `aspire otel logs [resource]` |
+| View traces | `aspire otel traces [resource]` |
+| Logs for a trace | `aspire otel logs --trace-id <id>` |
+| Add an integration | `aspire add` |
+| List running AppHosts | `aspire ps` |
+| Update AppHost packages | `aspire update` |
+| Search docs | `aspire docs search <query>` |
+| Get doc page | `aspire docs get <slug>` |
+| List doc pages | `aspire docs list` |
+| Environment diagnostics | `aspire doctor` |
+| List resource MCP tools | `aspire mcp tools` |
+| Call resource MCP tool | `aspire mcp call <resource> <tool> --input <json>` |
+
+Most commands support `--format Json` for machine-readable output. Use `--apphost <path>` to target a specific AppHost.
+
+## Key workflows
+
+### Running in agent environments
+
+Use `aspire start` to run the AppHost in the background. When working in a git worktree, use `--isolated` to avoid port conflicts and to prevent sharing user secrets or other local state with other running instances:
+
+```bash
+aspire start --isolated
+```
+
+Use `aspire wait <resource>` to block until a resource is healthy before interacting with it:
+
+```bash
+aspire start --isolated
+aspire wait myapi
+```
+
+Relaunching is safe — `aspire start` automatically stops any previous instance. Re-run `aspire start` whenever changes are made to the AppHost project.
+
+### Debugging issues
+
+Before making code changes, inspect the app state:
+
+1. `aspire describe` — check resource status
+2. `aspire otel logs <resource>` — view structured logs
+3. `aspire logs <resource>` — view console output
+4. `aspire otel traces <resource>` — view distributed traces
+
+### Adding integrations
+
+Use `aspire docs search` to find integration documentation, then `aspire docs get` to read the full guide. Use `aspire add` to add the integration package to the AppHost.
+
+After adding an integration, restart the app with `aspire start` for the new resource to take effect.
+
+### Using resource MCP tools
+
+Some resources expose MCP tools (e.g. `WithPostgresMcp()` adds SQL query tools). Discover and call them via CLI:
+
+```bash
+aspire mcp tools                                              # list available tools
+aspire mcp tools --format Json                                # includes input schemas
+aspire mcp call <resource> <tool> --input '{"key":"value"}'   # invoke a tool
+```
+
+## Important rules
+
+- **Always start the app first** (`aspire start`) before making changes to verify the starting state.
+- **To restart, just run `aspire start` again** — it automatically stops the previous instance. NEVER use `aspire stop` then `aspire run`. NEVER use `aspire run` at all.
+- Use `--isolated` when working in a worktree.
+- **Avoid persistent containers** early in development to prevent state management issues.
+- **Never install the Aspire workload** — it is obsolete.
+- Prefer `aspire.dev` and `learn.microsoft.com/dotnet/aspire` for official documentation.
+
+## Playwright CLI
+
+If configured, use Playwright CLI for functional testing of resources. Get endpoints via `aspire describe`. Run `playwright-cli --help` for available commands.

.github/skills/aspire/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: aspire
+description: "Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps. USE FOR: aspire start, aspire stop, start aspire app, aspire describe, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost. DO NOT USE FOR: non-Aspire .NET apps (use dotnet CLI), container-only deployments (use docker/podman), Azure deployment after local testing (use azure-deploy skill). INVOKES: Aspire CLI commands (aspire start, aspire describe, aspire otel logs, aspire docs search, aspire add), bash. FOR SINGLE OPERATIONS: Use Aspire CLI commands directly for quick resource status or doc lookups."
+---
+
+# Aspire Skill
+
+This repository uses Aspire to orchestrate its distributed application. Resources are defined in the AppHost project (`apphost.cs` or `apphost.ts`).
+
+## CLI command reference
+
+| Task | Command |
+|---|---|
+| Start the app | `aspire start` |
+| Start isolated (worktrees) | `aspire start --isolated` |
+| Restart the app | `aspire start` (stops previous automatically) |
+| Wait for resource healthy | `aspire wait <resource>` |
+| Stop the app | `aspire stop` |
+| List resources | `aspire describe` or `aspire resources` |
+| Run resource command | `aspire resource <resource> <command>` |
+| Start/stop/restart resource | `aspire resource <resource> start|stop|restart` |
+| View console logs | `aspire logs [resource]` |
+| View structured logs | `aspire otel logs [resource]` |
+| View traces | `aspire otel traces [resource]` |
+| Logs for a trace | `aspire otel logs --trace-id <id>` |
+| Add an integration | `aspire add` |
+| List running AppHosts | `aspire ps` |
+| Update AppHost packages | `aspire update` |
+| Search docs | `aspire docs search <query>` |
+| Get doc page | `aspire docs get <slug>` |
+| List doc pages | `aspire docs list` |
+| Environment diagnostics | `aspire doctor` |
+| List resource MCP tools | `aspire mcp tools` |
+| Call resource MCP tool | `aspire mcp call <resource> <tool> --input <json>` |
+
+Most commands support `--format Json` for machine-readable output. Use `--apphost <path>` to target a specific AppHost.
+
+## Key workflows
+
+### Running in agent environments
+
+Use `aspire start` to run the AppHost in the background. When working in a git worktree, use `--isolated` to avoid port conflicts and to prevent sharing user secrets or other local state with other running instances:
+
+```bash
+aspire start --isolated
+```
+
+Use `aspire wait <resource>` to block until a resource is healthy before interacting with it:
+
+```bash
+aspire start --isolated
+aspire wait myapi
+```
+
+Relaunching is safe — `aspire start` automatically stops any previous instance. Re-run `aspire start` whenever changes are made to the AppHost project.
+
+### Debugging issues
+
+Before making code changes, inspect the app state:
+
+1. `aspire describe` — check resource status
+2. `aspire otel logs <resource>` — view structured logs
+3. `aspire logs <resource>` — view console output
+4. `aspire otel traces <resource>` — view distributed traces
+
+### Adding integrations
+
+Use `aspire docs search` to find integration documentation, then `aspire docs get` to read the full guide. Use `aspire add` to add the integration package to the AppHost.
+
+After adding an integration, restart the app with `aspire start` for the new resource to take effect.
+
+### Using resource MCP tools
+
+Some resources expose MCP tools (e.g. `WithPostgresMcp()` adds SQL query tools). Discover and call them via CLI:
+
+```bash
+aspire mcp tools                                              # list available tools
+aspire mcp tools --format Json                                # includes input schemas
+aspire mcp call <resource> <tool> --input '{"key":"value"}'   # invoke a tool
+```
+
+## Important rules
+
+- **Always start the app first** (`aspire start`) before making changes to verify the starting state.
+- **To restart, just run `aspire start` again** — it automatically stops the previous instance. NEVER use `aspire stop` then `aspire run`. NEVER use `aspire run` at all.
+- Use `--isolated` when working in a worktree.
+- **Avoid persistent containers** early in development to prevent state management issues.
+- **Never install the Aspire workload** — it is obsolete.
+- Prefer `aspire.dev` and `learn.microsoft.com/dotnet/aspire` for official documentation.
+
+## Playwright CLI
+
+If configured, use Playwright CLI for functional testing of resources. Get endpoints via `aspire describe`. Run `playwright-cli --help` for available commands.

.mcp.json

@@ -0,0 +1,11 @@
+{
+  "mcpServers": {
+    "aspire": {
+      "command": "aspire",
+      "args": [
+        "agent",
+        "mcp"
+      ]
+    }
+  }
+}

Directory.Packages.props

@@ -3,48 +3,53 @@
     <ManagePackageVersionsCentrally>true</ManagePackageVersionsCentrally>
   </PropertyGroup>
   <ItemGroup>
-    <PackageVersion Include="Aspire.Microsoft.Data.SqlClient" Version="13.1.1" />
-    <PackageVersion Include="Dapper" Version="2.1.66" />
-    <PackageVersion Include="Microsoft.ApplicationInsights.WorkerService" Version="3.0.0" />
-    <PackageVersion Include="Aspire.Hosting.Azure.Functions" Version="13.1.1" />
-    <PackageVersion Include="Aspire.Hosting.DevTunnels" Version="13.1.1" />
-    <PackageVersion Include="Aspire.Hosting.SqlServer" Version="13.1.1" />
+    <PackageVersion Include="Aspire.Microsoft.Data.SqlClient" Version="13.2.4" />
+    <PackageVersion Include="Dapper" Version="2.1.72" />
+    <PackageVersion Include="Markdig.Signed" Version="1.1.3" />
+    <PackageVersion Include="Microsoft.ApplicationInsights.WorkerService" Version="3.1.0" />
+    <PackageVersion Include="Aspire.Hosting.Azure.Functions" Version="13.2.4" />
+    <PackageVersion Include="Aspire.Hosting.DevTunnels" Version="13.2.4" />
+    <PackageVersion Include="Aspire.Hosting.SqlServer" Version="13.2.4" />
     <PackageVersion Include="CommunityToolkit.Aspire.Hosting.Ollama" Version="13.1.1" />
     <PackageVersion Include="DbUp" Version="5.0.41" />
     <PackageVersion Include="DbUp.Extensions.Microsoft.Logging" Version="1.1.0" />
     <PackageVersion Include="Microsoft.AspNetCore.Http.Extensions" Version="2.3.9" />
-    <PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.3" />
-    <PackageVersion Include="Microsoft.AspNetCore.TestHost" Version="10.0.3" />
-    <PackageVersion Include="Microsoft.Azure.Functions.Worker" Version="2.51.0" />
+    <PackageVersion Include="Microsoft.AspNetCore.OpenApi" Version="10.0.7" />
+    <PackageVersion Include="Microsoft.AspNetCore.TestHost" Version="10.0.7" />
+    <PackageVersion Include="Microsoft.Azure.Functions.Worker" Version="2.52.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.ApplicationInsights" Version="2.50.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http" Version="3.3.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Http.AspNetCore" Version="2.1.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.OpenApi" Version="1.6.0" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Extensions.Sql" Version="3.1.527" />
     <PackageVersion Include="Microsoft.Azure.Functions.Worker.Sdk" Version="2.0.7" />
-    <PackageVersion Include="Microsoft.Data.SqlClient" Version="6.1.4" />
-    <PackageVersion Include="Microsoft.Extensions.Configuration" Version="10.0.3" />
+    <PackageVersion Include="Microsoft.Data.SqlClient" Version="7.0.1" />
+    <PackageVersion Include="Microsoft.Extensions.AI.Abstractions" Version="10.5.1" />
+    <PackageVersion Include="Microsoft.Extensions.Configuration" Version="10.0.7" />
     <PackageVersion Include="Microsoft.Extensions.Configuration.Abstractions" Version="10.0.2" />
-    <PackageVersion Include="Microsoft.Extensions.DataIngestion" Version="10.3.0-preview.1.26109.11" />
+    <PackageVersion Include="Microsoft.Extensions.DataIngestion" Version="10.5.0-preview.1.26213.4" />
+    <PackageVersion Include="PdfPig" Version="0.1.14" />
+    <PackageVersion Include="Microsoft.Extensions.DataIngestion.Abstractions" Version="10.5.0-preview.1.26213.4" />
     <PackageVersion Include="Microsoft.Extensions.DataIngestion.Markdig" Version="10.3.0-preview.1.26109.11" />
     <PackageVersion Include="Microsoft.Extensions.DataIngestion.MarkItDown" Version="10.3.0-preview.1.26109.11" />
-    <PackageVersion Include="Microsoft.ML.Tokenizers" Version="2.0.0" />
-    <PackageVersion Include="Microsoft.ML.Tokenizers.Data.Cl100kBase" Version="2.0.0" />
-    <PackageVersion Include="Microsoft.Extensions.Http.Resilience" Version="10.3.0" />
-    <PackageVersion Include="Microsoft.Extensions.Logging" Version="10.0.3" />
-    <PackageVersion Include="Microsoft.Extensions.Resilience" Version="10.3.0" />
-    <PackageVersion Include="Microsoft.Extensions.ServiceDiscovery" Version="10.3.0" />
-    <PackageVersion Include="Microsoft.NET.Test.Sdk" Version="18.0.1" />
-    <PackageVersion Include="ModelContextProtocol.AspNetCore" Version="0.9.0-preview.2" />
+    <PackageVersion Include="Microsoft.ML.Tokenizers" Version="3.0.0-preview.26160.2" />
+    <PackageVersion Include="Microsoft.ML.Tokenizers.Data.Cl100kBase" Version="3.0.0-preview.26160.2" />
+    <PackageVersion Include="Microsoft.Extensions.Http.Resilience" Version="10.5.0" />
+    <PackageVersion Include="Microsoft.Extensions.Logging" Version="10.0.7" />
+    <PackageVersion Include="Microsoft.Extensions.Resilience" Version="10.5.0" />
+    <PackageVersion Include="Microsoft.Extensions.ServiceDiscovery" Version="10.5.0" />
+    <PackageVersion Include="Microsoft.NET.Test.Sdk" Version="18.5.1" />
+    <PackageVersion Include="ModelContextProtocol.AspNetCore" Version="1.2.0" />
+    <PackageVersion Include="ModelContextProtocol.Core" Version="1.2.0" />
     <PackageVersion Include="NSubstitute" Version="5.3.0" />
-    <PackageVersion Include="OpenTelemetry.Exporter.OpenTelemetryProtocol" Version="1.15.0" />
-    <PackageVersion Include="OpenTelemetry.Extensions.Hosting" Version="1.15.0" />
-    <PackageVersion Include="OpenTelemetry.Instrumentation.AspNetCore" Version="1.15.0" />
-    <PackageVersion Include="OpenTelemetry.Instrumentation.Http" Version="1.15.0" />
-    <PackageVersion Include="OpenTelemetry.Instrumentation.Runtime" Version="1.15.0" />
-    <PackageVersion Include="Scalar.Aspire" Version="0.8.55" />
+    <PackageVersion Include="OpenTelemetry.Exporter.OpenTelemetryProtocol" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Extensions.Hosting" Version="1.15.3" />
+    <PackageVersion Include="OpenTelemetry.Instrumentation.AspNetCore" Version="1.15.2" />
+    <PackageVersion Include="OpenTelemetry.Instrumentation.Http" Version="1.15.1" />
+    <PackageVersion Include="OpenTelemetry.Instrumentation.Runtime" Version="1.15.1" />
+    <PackageVersion Include="Scalar.Aspire" Version="0.9.33" />
     <PackageVersion Include="Shouldly" Version="4.3.0" />
-    <PackageVersion Include="SonarAnalyzer.CSharp" Version="10.19.0.132793" />
+    <PackageVersion Include="SonarAnalyzer.CSharp" Version="10.25.0.139117" />
     <PackageVersion Include="xunit.runner.visualstudio" Version="3.1.5" />
     <PackageVersion Include="xunit.v3" Version="3.2.2" />
   </ItemGroup>

Sql.SemanticSearch.slnx

@@ -15,6 +15,7 @@
     <Project Path="tests/Sql.SemanticSearch.Ingestion.Functions.UnitTests/Sql.SemanticSearch.Ingestion.Functions.UnitTests.csproj" />
     <Project Path="tests/Sql.SemanticSearch.Tests.Helpers/Sql.SemanticSearch.Tests.Helpers.csproj" Id="6e28072c-969e-478f-8223-0a74e9f48e31" />
   </Folder>
+  <Project Path="src/Microsoft.Extensions.DataIngestion.MarkItDown/Microsoft.Extensions.DataIngestion.MarkItDown.csproj" />
   <Project Path="src/Sql.SemanticSearch.Api/Sql.SemanticSearch.Api.csproj" />
   <Project Path="src/Sql.SemanticSearch.Core/Sql.SemanticSearch.Core.csproj" />
   <Project Path="src/Sql.SemanticSearch.DatabaseDeployment/Sql.SemanticSearch.DatabaseDeployment.csproj" Id="f474f503-a06d-4dad-a819-955c28875b5f" />

aspire.config.json

@@ -0,0 +1,6 @@
+{
+  "appHost": {
+    "language": "csharp",
+    "path": "src/Sql.SemanticSearch.AppHost/Sql.SemanticSearch.AppHost.csproj"
+  }
+}