Merge branch 'main' into chunk-data

Resolved 29 conflicting files. The notable decisions:

Confidence: main's tool-calling gate (RequiredProviderConfidence) and this
branch's local-RAG gate (DataConfidenceLevel) turned out to be the same rule
on the same axis, so they are now one field. Both tool results and data
sources raise it through RequireProviderConfidence(). The gate checks the
level strictly and no longer exempts providers trusted by configuration:
TrustedProviderIds is documented as applying to data-source security checks
only, and organizations set confidence through DataConfidence
.CustomConfidenceScheme instead. The security axis (DataSecurity, ERI,
IsTrustedForDataSourceSecurityChecks) is unchanged.

Provider creation: main's CreateProvider signature won (hfEndpointKind,
capabilityOverrides, no model parameter); tokenizerPath was added to it and
is set for every provider, including the new Hetzner, IONOS and LiteLLM.
Provider and EmbeddingProvider combine the record parameters, Lua parsing and
Lua serialization of both sides.

File types: main's hierarchy (ODT leaf, WORD parent, PowerPoint without the
legacy .ppt, TABULAR instead of DELIMITED_TABLE) plus this branch's
SPREADSHEET parent with ODS and the xlsm/xlsb/xla/xlam extensions, which the
runtime already reads. Both sides had added a conflicting HTML filter; the
reading family keeps the name, and the export path uses a narrow
HTML_DOCUMENT, following the existing LATEX/TEX split.

Runtime: main's file_data.rs is the base, including the prompt-injection
sanitizer and the extraction routes. Token counting and chunk segmentation
moved into take_released, so they act on the text the filter has released
rather than on text it is still holding. A failed count is logged and left
out instead of ending the extraction, because the app counts such a segment
itself.

Data sources: the participating-provider checks of this branch are kept, and
main's GetAllowedDataSources overload now builds on them. DirectChatService
resolves the launched chat's data source options before the check, so filter
and chat see the same options.

.NET and Rust both build clean; I18N regenerated to 4060 keys.

app/MindWork AI Studio/Tools/Validation/ProviderValidation.cs

@@ -27,7 +27,12 @@ public sealed class ProviderValidation
 
     public string? ValidatingHostname(string hostname)
     {
-        if(this.GetProvider() != LLMProviders.SELF_HOSTED)
+        //
+        // Every provider for which IsHostnameNeeded is true must be validated here. Otherwise,
+        // the dialog shows a hostname field which nobody checks, and the provider silently ends
+        // up as a NoProvider later on, because its base URI cannot be built:
+        //
+        if(this.GetProvider() is not (LLMProviders.SELF_HOSTED or LLMProviders.LITE_LLM))
             return null;
         
         if(string.IsNullOrWhiteSpace(hostname))
@@ -122,12 +127,12 @@ public sealed class ProviderValidation
         if(this.GetProvider() is not LLMProviders.HUGGINGFACE)
             return null;
 
-        if (inferenceProvider is HFInferenceProvider.NONE)
+        if (!inferenceProvider.SupportsChat())
             return TB("Please select an Hugging Face inference provider.");
 
         return null;
     }
-    
+
     public string? ValidatingCustomTokenizer(string _)
     {
         var issue = this.GetCustomTokenizerValidationIssue();
@@ -136,4 +141,52 @@ public sealed class ProviderValidation
 
         return issue;
     }
+
+    /// <summary>
+    /// Validates the Hugging Face inference provider chosen for embeddings.
+    /// </summary>
+    /// <remarks>
+    /// Far fewer providers create embeddings for us than serve chat models, so a selection which is
+    /// fine for chatting may not be for embeddings. A provider configured before the choice narrowed
+    /// is no longer among the options, which would leave the user with an empty field and no reason
+    /// given.
+    /// </remarks>
+    /// <param name="inferenceProvider">The inference provider to validate.</param>
+    /// <returns>The message to show, or null when the selection is fine.</returns>
+    public string? ValidatingHFInstanceProviderForEmbeddings(HFInferenceProvider inferenceProvider)
+    {
+        if(this.GetProvider() is not LLMProviders.HUGGINGFACE)
+            return null;
+
+        if (inferenceProvider is HFInferenceProvider.NONE)
+            return TB("Please select an Hugging Face inference provider.");
+
+        if (!inferenceProvider.SupportsEmbeddings())
+            return TB("This Hugging Face inference provider does not create embeddings. Please select another one.");
+
+        return null;
+    }
+
+    /// <summary>
+    /// Validates the Hugging Face inference provider chosen for transcription.
+    /// </summary>
+    /// <remarks>
+    /// As with embeddings, only some of the inference providers transcribe audio for us, so the
+    /// choice is narrower than it is for chatting.
+    /// </remarks>
+    /// <param name="inferenceProvider">The inference provider to validate.</param>
+    /// <returns>The message to show, or null when the selection is fine.</returns>
+    public string? ValidatingHFInstanceProviderForTranscription(HFInferenceProvider inferenceProvider)
+    {
+        if(this.GetProvider() is not LLMProviders.HUGGINGFACE)
+            return null;
+
+        if (inferenceProvider is HFInferenceProvider.NONE)
+            return TB("Please select an Hugging Face inference provider.");
+
+        if (!inferenceProvider.SupportsTranscription())
+            return TB("This Hugging Face inference provider does not transcribe audio. Please select another one.");
+
+        return null;
+    }
 }