feat: document per-request compression override fields

features/agentic-compression.mdx

@@ -91,8 +91,8 @@ Enable compression for specific requests using the SDK or headers:
         "messages": [
           {"role": "user", "content": "Your prompt here"}
         ],
-        "enable_compression": true,
-        "compression_rate": 0.8  // Target ratio: compressed = 80% of original (optional)
+        "compression_model": "agentic",
+        "compression_configuration": { "rate": 0.8 }  // Target ratio: compressed = 80% of original (optional)
       }
     });
     ```
@@ -106,8 +106,8 @@ Enable compression for specific requests using the SDK or headers:
             "messages": [
                 {"role": "user", "content": "Your prompt here"}
             ],
-            "enable_compression": True,
-            "compression_rate": 0.8  # Target ratio: compressed = 80% of original (optional)
+            "compression_model": "agentic",
+            "compression_configuration": {"rate": 0.8}  # Target ratio: compressed = 80% of original (optional)
         }
     )
     ```
@@ -119,17 +119,17 @@ Enable compression for specific requests using the SDK or headers:
         Messages: []edgee.Message{
             {Role: "user", Content: "Your prompt here"},
         },
-        EnableCompression: true,
-        CompressionRate: 0.8, // Target ratio: compressed = 80% of original (optional)
+        CompressionModel: "agentic",
+        CompressionConfiguration: map[string]interface{}{"rate": 0.8}, // optional
     })
     ```
   </Tab>
 
   <Tab title="Rust">
     ```rust
     let input = InputObject::new(vec![Message::user("Your prompt here")])
-        .with_compression(true)
-        .with_compression_rate(0.8); // Target ratio: compressed = 80% of original (optional)
+        .with_compression_model("agentic")
+        .with_compression_configuration(CompressionConfiguration { rate: Some(0.8), semantic_preservation_threshold: None }); // optional
 
     let response = client.send("gpt-5.2", input).await?;
     ```
@@ -140,9 +140,7 @@ Enable compression for specific requests using the SDK or headers:
     curl -X POST "https://api.edgee.ai/v1/chat/completions" \
     -H "Authorization: Bearer $EDGEE_API_KEY" \
     -H "Content-Type: application/json" \
-    -H "x-edgee-enable-compression: true" \
-    -H "x-edgee-compression-rate: 0.8" \
-    -d '{"model": "gpt-5.2", "messages": [{"role": "user", "content": "Your prompt here"}]}'
+    -d '{"model": "gpt-5.2", "messages": [{"role": "user", "content": "Your prompt here"}], "compression_model": "agentic", "compression_configuration": {"rate": 0.8}}'
     ```
   </Tab>
 </Tabs>
@@ -212,8 +210,8 @@ const documents = [
 const response = await edgee.send({
   model: 'gpt-5.2',
   input: `Answer the question based on these documents:\n\n${documents.join('\n\n')}\n\nQuestion: What is the main topic?`,
-  enable_compression: true, // Enable compression for this request
-  compression_rate: 0.8, // Target ratio (0-1): 0.8 = compressed is 80% of original
+  compression_model: "agentic",
+  compression_configuration: { rate: 0.8 }, // Target ratio (0-1): 0.8 = compressed is 80% of original
 });
 
 console.log(response.text);

features/claude-compression.mdx

@@ -45,6 +45,7 @@ In the **Edge Models** section of your console, find the **Claude Token Compress
   There are no compression ratio or BERT threshold settings. Claude Token Compression is fully lossless by design. Just enable it and go.
 </Note>
 
+
 ## Integration with Claude Code
 
 

features/observability.mdx

@@ -213,7 +213,7 @@ See exactly how much token compression is saving you on every request:
 const response = await edgee.send({
   model: 'gpt-5.2',
   input: 'Long prompt with lots of context...',
-  enable_compression: true,
+  compression_model: "agentic",
 });
 
 // Compression details

sdk/go/send.mdx

@@ -43,8 +43,8 @@ When `input` is an `InputObject`, you have full control over the conversation:
 | `Tools` | `[]Tool` | Array of function tools available to the model |
 | `ToolChoice` | `any` | Controls which tool (if any) the model should call. Can be `string` (`"auto"`, `"none"`) or `map[string]interface{}`. See [Tools documentation](/sdk/go/tools) for details |
 | `Tags` | `[]string` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `EnableCompression` | `bool` | Enable token compression for this request. If `true`, the request will be compressed to the compression rate specified in the API key settings. If `false`, the request will not be compressed. |
-| `CompressionRate` | `float64` | The compression rate to use for this request. If `EnableCompression` is `true`, this value will be used to compress the request. The value should be between 0.0 and 1.0. The default value is 0.75. |
+| `CompressionModel` | `*string` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `CompressionConfiguration` | `*CompressionConfiguration` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `Rate` (0.0-1.0, default 0.8) and `SemanticPreservationThreshold` (0-100). |
 
 **Example with InputObject:**
 
@@ -235,8 +235,10 @@ response, err := client.Send("gpt-5.2", edgee.InputObject{
     Messages: []edgee.Message{
         {Role: "user", Content: "Analyze this long document with lots of context..."},
     },
-    EnableCompression: true,
-    CompressionRate: 0.8,
+    CompressionModel: edgee.String("agentic"),
+    CompressionConfiguration: &edgee.CompressionConfiguration{
+        Rate: edgee.Float64(0.8),
+    },
 })
 if err != nil {
     log.Fatal(err)

sdk/go/stream.mdx

@@ -57,8 +57,8 @@ When `input` is an `InputObject` or `map[string]interface{}`, you have full cont
 | `Tools` | `[]Tool` | Array of function tools available to the model |
 | `ToolChoice` | `any` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/go/tools) for details |
 | `Tags` | `[]string` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `EnableCompression` | `bool` | Enable token compression for this request. If `true`, the request will be compressed to the compression rate specified in the API key settings. If `false`, the request will not be compressed. |
-| `CompressionRate` | `float64` | The compression rate to use for this request. If `EnableCompression` is `true`, this value will be used to compress the request. The value should be between 0.0 and 1.0. The default value is 0.75. |
+| `CompressionModel` | `*string` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `CompressionConfiguration` | `*CompressionConfiguration` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `Rate` (0.0-1.0, default 0.8) and `SemanticPreservationThreshold` (0-100). |
 
 For details about `Message` type, see the [Send Method documentation](/sdk/go/send#message-object). 
 For details about `Tool` and `ToolChoice` types, see the [Tools documentation](/sdk/go/tools).

sdk/python/send.mdx

@@ -42,8 +42,8 @@ When `input` is an `InputObject` or dictionary, you have full control over the c
 | `tools` | `list[dict] \| None` | Array of function tools available to the model |
 | `tool_choice` | `str \| dict \| None` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/python/tools) for details |
 | `tags` | `list[str] \| None` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `enable_compression` | `bool` | Enable token compression for this request. If `true`, the request will be compressed to the compression rate specified in the API key settings. If `false`, the request will not be compressed. |
-| `compression_rate` | `float` | The compression rate to use for this request. If `enable_compression` is `true`, this value will be used to compress the request. The value should be between 0.0 and 1.0. The default value is 0.75. |
+| `compression_model` | `str` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `compression_configuration` | `dict` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `rate` (0.0-1.0, default 0.8) and `semantic_preservation_threshold` (0-100). |
 
 **Example with Dictionary Input:**
 
@@ -206,8 +206,8 @@ response = edgee.send(
         "messages": [
             {"role": "user", "content": "Analyze this long document with lots of context..."}
         ],
-        "enable_compression": True,
-        "compression_rate": 0.8
+        "compression_model": "agentic",
+        "compression_configuration": {"rate": 0.8}
     }
 )
 

sdk/python/stream.mdx

@@ -40,8 +40,8 @@ When `input` is an `InputObject` or dictionary, you have full control over the c
 | `tools` | `list[dict] \| None` | Array of function tools available to the model |
 | `tool_choice` | `str \| dict \| None` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/python/tools) for details |
 | `tags` | `list[str] \| None` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `enable_compression` | `bool` | Enable token compression for this request. If `true`, the request will be compressed to the compression rate specified in the API key settings. If `false`, the request will not be compressed. |
-| `compression_rate` | `float` | The compression rate to use for this request. If `enable_compression` is `true`, this value will be used to compress the request. The value should be between 0.0 and 1.0. The default value is 0.75. |
+| `compression_model` | `str` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `compression_configuration` | `dict` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `rate` (0.0-1.0, default 0.8) and `semantic_preservation_threshold` (0-100). |
 
 For details about `Message` type, see the [Send Method documentation](/sdk/python/send#message-object). 
 For details about `Tool` and `ToolChoice` types, see the [Tools documentation](/sdk/python/tools).

sdk/rust/send.mdx

@@ -57,8 +57,8 @@ When `input` is an `InputObject`, you have full control over the conversation:
 | `tools` | `Option<Vec<Tool>>` | Array of function tools available to the model |
 | `tool_choice` | `Option<serde_json::Value>` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/rust/tools) for details |
 | `tags` | `Option<Vec<String>>` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `enable_compression` | `Option<bool>` | Enable token compression for this request (overrides console settings). If not set, uses the configuration from your API key or organization settings |
-| `compression_rate` | `Option<f64>` | Target compression rate (0.0-1.0, default 0.75). Only used if compression is enabled. Higher values attempt more aggressive compression |
+| `compression_model` | `Option<String>` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `compression_configuration` | `Option<CompressionConfiguration>` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `rate` (0.0-1.0, default 0.8) and `semantic_preservation_threshold` (0-100). |
 
 **Example with InputObject:**
 
@@ -217,8 +217,8 @@ Token compression metrics (when compression is applied):
 let input = InputObject::new(vec![
     Message::user("Analyze this long document with lots of context...")
 ])
-.with_compression(true)
-.with_compression_rate(0.8); // Target 80% compression
+.with_compression_model("agentic")
+.with_compression_configuration(CompressionConfiguration { rate: Some(0.8), semantic_preservation_threshold: None });
 
 let response = client.send("gpt-5.2", input).await?;
 println!("{}", response.text().unwrap_or(""));

sdk/rust/stream.mdx

@@ -55,8 +55,8 @@ When `input` is a `Vec<Message>` or `InputObject`, you have full control over th
 | `tools` | `Option<Vec<Tool>>` | Array of function tools available to the model |
 | `tool_choice` | `Option<serde_json::Value>` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/rust/tools) for details |
 | `tags` | `Option<Vec<String>>` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `enable_compression` | `Option<bool>` | Enable token compression for this request (overrides console settings). If not set, uses the configuration from your API key or organization settings |
-| `compression_rate` | `Option<f64>` | Target compression rate (0.0-1.0, default 0.75). Only used if compression is enabled. Higher values attempt more aggressive compression |
+| `compression_model` | `Option<String>` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `compression_configuration` | `Option<CompressionConfiguration>` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `rate` (0.0-1.0, default 0.8) and `semantic_preservation_threshold` (0-100). |
 
 For details about `Message` type, see the [Send Method documentation](/sdk/rust/send#message-object). 
 For details about `Tool` and `ToolChoice` types, see the [Tools documentation](/sdk/rust/tools).

sdk/typescript/send.mdx

@@ -45,8 +45,8 @@ When `input` is an `InputObject`, you have full control over the conversation:
 | `tools` | `Tool[]` | Array of function tools available to the model |
 | `tool_choice` | `ToolChoice` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/typescript/tools) for details |
 | `tags` | `string[]` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `enable_compression` | `bool` | Enable token compression for this request. If `true`, the request will be compressed to the compression rate specified in the API key settings. If `false`, the request will not be compressed. |
-| `compression_rate` | `number` | The compression rate to use for this request. If `enable_compression` is `true`, this value will be used to compress the request. The value should be between 0.0 and 1.0. The default value is 0.75. |
+| `compression_model` | `string` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `compression_configuration` | `object` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `rate` (0.0-1.0, default 0.8) and `semantic_preservation_threshold` (0-100). |
 
 **Example with InputObject:**
 
@@ -211,8 +211,8 @@ const response = await edgee.send({
     messages: [
       { role: 'user', content: 'Analyze this long document with lots of context...' }
     ],
-    enable_compression: true,
-    compression_rate: 0.8
+    compression_model: "agentic",
+    compression_configuration: { rate: 0.8 }
   }
 });
 

sdk/typescript/stream.mdx

@@ -45,8 +45,8 @@ When `input` is an `InputObject`, you have full control over the conversation:
 | `tools` | `Tool[]` | Array of function tools available to the model |
 | `tool_choice` | `ToolChoice` | Controls which tool (if any) the model should call. See [Tools documentation](/sdk/typescript/tools) for details |
 | `tags` | `string[]` | Optional tags to categorize and label the request for analytics and filtering. Can also be sent via the `x-edgee-tags` header (comma-separated) |
-| `enable_compression` | `bool` | Enable token compression for this request. If `true`, the request will be compressed to the compression rate specified in the API key settings. If `false`, the request will not be compressed. |
-| `compression_rate` | `number` | The compression rate to use for this request. If `enable_compression` is `true`, this value will be used to compress the request. The value should be between 0.0 and 1.0. The default value is 0.75. |
+| `compression_model` | `string` | Compression model for this request: `"agentic"`, `"claude"`, `"opencode"`, `"cursor"`, or `"customer"`. Each model is a bundle of compression strategies. Overrides API key settings when present. |
+| `compression_configuration` | `object` | Configuration for the compression model. Currently only available for `agentic`. Contains optional `rate` (0.0-1.0, default 0.8) and `semantic_preservation_threshold` (0-100). |
 
 For details about `Message` type, see the [Send Method documentation](/sdk/typescript/send#message-object). 
 For details about `Tool` and `ToolChoice` types, see the [Tools documentation](/sdk/typescript/tools).