Merge pull request #1572 from ksylvan/0704-OpenAI-Image-Generation-Tool

Add Image Generation Support to Fabric

Author: danielmiessler

README.md

@@ -15,9 +15,7 @@ Fabric is graciously supported by…
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/danielmiessler/fabric)
 
 <div align="center">
-<p class="align center">
 <h4><code>fabric</code> is an open-source framework for augmenting humans using AI.</h4>
-</p>
 </div>
 
 [Updates](#updates) •
@@ -41,9 +39,9 @@ Since the start of modern AI in late 2022 we've seen an **_extraordinary_** numb
 
 It's all really exciting and powerful, but _it's not easy to integrate this functionality into our lives._
 
-<p class="align center">
+<div class="align center">
 <h4>In other words, AI doesn't have a capabilities problem—it has an <em>integration</em> problem.</h4>
-</p>
+</div>
 
 **Fabric was created to address this by creating and organizing the fundamental units of AI—the prompts themselves!**
 
@@ -120,6 +118,8 @@ Keep in mind that many of these were recorded when Fabric was Python-based, so r
 > - Web search is available for both Anthropic and OpenAI providers
 > - Previous plugin-level search configurations have been removed in favor of the new flag-based approach.
 > - If you used the previous approach, consider cleaning up your `~/.config/fabric/.env` file, removing the unused `ANTHROPIC_WEB_SEARCH_TOOL_ENABLED` and `ANTHROPIC_WEB_SEARCH_TOOL_LOCATION` variables.
+> - Fabric now supports image generation using the `--image-file` flag with OpenAI models
+> - Image generation works with both text prompts and input images (via `--attachment`) for image editing tasks
 >
 >
 >June 17, 2025
@@ -292,88 +292,88 @@ yt() {
 
 You can add the below code for the equivalent aliases inside PowerShell by running `notepad $PROFILE` inside a PowerShell window:
 
-```powershell
-# Path to the patterns directory
-$patternsPath = Join-Path $HOME ".config/fabric/patterns"
-foreach ($patternDir in Get-ChildItem -Path $patternsPath -Directory) {
-    $patternName = $patternDir.Name
-
-    # Dynamically define a function for each pattern
-    $functionDefinition = @"
-function $patternName {
-    [CmdletBinding()]
-    param(
-        [Parameter(ValueFromPipeline = `$true)]
-        [string] `$InputObject,
-
-        [Parameter(ValueFromRemainingArguments = `$true)]
-        [String[]] `$patternArgs
-    )
-
-    begin {
-        # Initialize an array to collect pipeline input
-        `$collector = @()
-    }
-
-    process {
-        # Collect pipeline input objects
-        if (`$InputObject) {
-            `$collector += `$InputObject
+    ```powershell
+    # Path to the patterns directory
+    $patternsPath = Join-Path $HOME ".config/fabric/patterns"
+    foreach ($patternDir in Get-ChildItem -Path $patternsPath -Directory) {
+        $patternName = $patternDir.Name
+
+        # Dynamically define a function for each pattern
+        $functionDefinition = @"
+    function $patternName {
+        [CmdletBinding()]
+        param(
+            [Parameter(ValueFromPipeline = `$true)]
+            [string] `$InputObject,
+
+            [Parameter(ValueFromRemainingArguments = `$true)]
+            [String[]] `$patternArgs
+        )
+
+        begin {
+            # Initialize an array to collect pipeline input
+            `$collector = @()
         }
-    }
 
-    end {
-        # Join all pipeline input into a single string, separated by newlines
-        `$pipelineContent = `$collector -join "`n"
+        process {
+            # Collect pipeline input objects
+            if (`$InputObject) {
+                `$collector += `$InputObject
+            }
+        }
 
-        # If there's pipeline input, include it in the call to fabric
-        if (`$pipelineContent) {
-            `$pipelineContent | fabric --pattern $patternName `$patternArgs
-        } else {
-            # No pipeline input; just call fabric with the additional args
-            fabric --pattern $patternName `$patternArgs
+        end {
+            # Join all pipeline input into a single string, separated by newlines
+            `$pipelineContent = `$collector -join "`n"
+
+            # If there's pipeline input, include it in the call to fabric
+            if (`$pipelineContent) {
+                `$pipelineContent | fabric --pattern $patternName `$patternArgs
+            } else {
+                # No pipeline input; just call fabric with the additional args
+                fabric --pattern $patternName `$patternArgs
+            }
         }
     }
-}
-"@
-    # Add the function to the current session
-    Invoke-Expression $functionDefinition
-}
+    "@
+        # Add the function to the current session
+        Invoke-Expression $functionDefinition
+    }
 
-# Define the 'yt' function as well
-function yt {
-    [CmdletBinding()]
-    param(
-        [Parameter()]
-        [Alias("timestamps")]
-        [switch]$t,
-
-        [Parameter(Position = 0, ValueFromPipeline = $true)]
-        [string]$videoLink
-    )
-
-    begin {
-        $transcriptFlag = "--transcript"
-        if ($t) {
-            $transcriptFlag = "--transcript-with-timestamps"
+    # Define the 'yt' function as well
+    function yt {
+        [CmdletBinding()]
+        param(
+            [Parameter()]
+            [Alias("timestamps")]
+            [switch]$t,
+
+            [Parameter(Position = 0, ValueFromPipeline = $true)]
+            [string]$videoLink
+        )
+
+        begin {
+            $transcriptFlag = "--transcript"
+            if ($t) {
+                $transcriptFlag = "--transcript-with-timestamps"
+            }
         }
-    }
 
-    process {
-        if (-not $videoLink) {
-            Write-Error "Usage: yt [-t | --timestamps] youtube-link"
-            return
+        process {
+            if (-not $videoLink) {
+                Write-Error "Usage: yt [-t | --timestamps] youtube-link"
+                return
+            }
         }
-    }
 
-    end {
-        if ($videoLink) {
-            # Execute and allow output to flow through the pipeline
-            fabric -y $videoLink $transcriptFlag
+        end {
+            if ($videoLink) {
+                # Execute and allow output to flow through the pipeline
+                fabric -y $videoLink $transcriptFlag
+            }
         }
     }
-}
-```
+    ```
 
 This also creates a `yt` alias that allows you to use `yt https://www.youtube.com/watch?v=4b0iet22VIk` to get transcripts, comments, and metadata.
 
@@ -493,7 +493,6 @@ fabric -h
 ```
 
 ```plaintext
-
 Usage:
   fabric [OPTIONS]
 
@@ -508,7 +507,9 @@ Application Options:
   -T, --topp=                       Set top P (default: 0.9)
   -s, --stream                      Stream
   -P, --presencepenalty=            Set presence penalty (default: 0.0)
-  -r, --raw                         Use the defaults of the model without sending chat options (like temperature etc.) and use the user role instead of the system role for patterns.
+  -r, --raw                         Use the defaults of the model without sending chat options (like
+                                    temperature etc.) and use the user role instead of the system role for
+                                    patterns.
   -F, --frequencypenalty=           Set frequency penalty (default: 0.0)
   -l, --listpatterns                List all patterns
   -L, --listmodels                  List all available models
@@ -522,9 +523,12 @@ Application Options:
       --output-session              Output the entire session (also a temporary one) to the output file
   -n, --latest=                     Number of latest patterns to list (default: 0)
   -d, --changeDefaultModel          Change default model
-  -y, --youtube=                    YouTube video or play list "URL" to grab transcript, comments from it and send to chat or print it put to the console and store it in the output file
+  -y, --youtube=                    YouTube video or play list "URL" to grab transcript, comments from it
+                                    and send to chat or print it put to the console and store it in the
+                                    output file
       --playlist                    Prefer playlist over video if both ids are present in the URL
-      --transcript                  Grab transcript from YouTube video and send to chat (it is used per default).
+      --transcript                  Grab transcript from YouTube video and send to chat (it is used per
+                                    default).
       --transcript-with-timestamps  Grab transcript from YouTube video with timestamps and send to chat
       --comments                    Grab comments from YouTube video and send to chat
       --metadata                    Output video metadata
@@ -552,6 +556,9 @@ Application Options:
       --liststrategies              List all strategies
       --listvendors                 List all vendors
       --shell-complete-list         Output raw list without headers/formatting (for shell completion)
+      --search                      Enable web search tool for supported models (Anthropic, OpenAI)
+      --search-location=            Set location for web search results (e.g., 'America/Los_Angeles')
+      --image-file=                 Save generated image to specified file path (e.g., 'output.png')
 
 Help Options:
   -h, --help                        Show this help message

cli/flags.go

@@ -76,6 +76,7 @@ type Flags struct {
 	ShellCompleteOutput             bool              `long:"shell-complete-list" description:"Output raw list without headers/formatting (for shell completion)"`
 	Search                          bool              `long:"search" description:"Enable web search tool for supported models (Anthropic, OpenAI)"`
 	SearchLocation                  string            `long:"search-location" description:"Set location for web search results (e.g., 'America/Los_Angeles')"`
+	ImageFile                       string            `long:"image-file" description:"Save generated image to specified file path (e.g., 'output.png')"`
 }
 
 var debug = false
@@ -267,6 +268,7 @@ func (o *Flags) BuildChatOptions() (ret *common.ChatOptions) {
 		ModelContextLength: o.ModelContextLength,
 		Search:             o.Search,
 		SearchLocation:     o.SearchLocation,
+		ImageFile:          o.ImageFile,
 	}
 	return
 }

common/domain.go

@@ -28,6 +28,7 @@ type ChatOptions struct {
 	MaxTokens          int
 	Search             bool
 	SearchLocation     string
+	ImageFile          string
 }
 
 // NormalizeMessages remove empty messages and ensure messages order user-assist-user

completions/_fabric

@@ -96,6 +96,9 @@ _fabric() {
     '(--api-key)--api-key[API key used to secure server routes]:api-key:' \
     '(--config)--config[Path to YAML config file]:config file:_files -g "*.yaml *.yml"' \
     '(--version)--version[Print current version]' \
+    '(--search)--search[Enable web search tool for supported models (Anthropic, OpenAI)]' \
+    '(--search-location)--search-location[Set location for web search results]:location:' \
+    '(--image-file)--image-file[Save generated image to specified file path]:image file:_files -g "*.png *.jpg *.jpeg *.gif *.bmp"' \
     '(--listextensions)--listextensions[List all registered extensions]' \
     '(--addextension)--addextension[Register a new extension from config file path]:config file:_files -g "*.yaml *.yml"' \
     '(--rmextension)--rmextension[Remove a registered extension by name]:extension:_fabric_extensions' \

completions/fabric.bash

@@ -13,7 +13,7 @@ _fabric() {
   _get_comp_words_by_ref -n : cur prev words cword
 
   # Define all possible options/flags
-  local opts="--pattern -p --variable -v --context -C --session --attachment -a --setup -S --temperature -t --topp -T --stream -s --presencepenalty -P --raw -r --frequencypenalty -F --listpatterns -l --listmodels -L --listcontexts -x --listsessions -X --updatepatterns -U --copy -c --model -m --modelContextLength --output -o --output-session --latest -n --changeDefaultModel -d --youtube -y --playlist --transcript --transcript-with-timestamps --comments --metadata --language -g --scrape_url -u --scrape_question -q --seed -e --wipecontext -w --wipesession -W --printcontext --printsession --readability --input-has-vars --dry-run --serve --serveOllama --address --api-key --config --version --listextensions --addextension --rmextension --strategy --liststrategies --listvendors --shell-complete-list --help -h"
+  local opts="--pattern -p --variable -v --context -C --session --attachment -a --setup -S --temperature -t --topp -T --stream -s --presencepenalty -P --raw -r --frequencypenalty -F --listpatterns -l --listmodels -L --listcontexts -x --listsessions -X --updatepatterns -U --copy -c --model -m --modelContextLength --output -o --output-session --latest -n --changeDefaultModel -d --youtube -y --playlist --transcript --transcript-with-timestamps --comments --metadata --language -g --scrape_url -u --scrape_question -q --seed -e --wipecontext -w --wipesession -W --printcontext --printsession --readability --input-has-vars --dry-run --serve --serveOllama --address --api-key --config --search --search-location --image-file --version --listextensions --addextension --rmextension --strategy --liststrategies --listvendors --shell-complete-list --help -h"
 
   # Helper function for dynamic completions
   _fabric_get_list() {
@@ -63,12 +63,12 @@ _fabric() {
     return 0
     ;;
   # Options requiring file/directory paths
-  -a | --attachment | -o | --output | --config | --addextension)
+  -a | --attachment | -o | --output | --config | --addextension | --image-file)
     _filedir
     return 0
     ;;
   # Options requiring simple arguments (no specific completion logic here)
-  -v | --variable | -t | --temperature | -T | --topp | -P | --presencepenalty | -F | --frequencypenalty | --modelContextLength | -n | --latest | -y | --youtube | -g | --language | -u | --scrape_url | -q | --scrape_question | -e | --seed | --address | --api-key)
+  -v | --variable | -t | --temperature | -T | --topp | -P | --presencepenalty | -F | --frequencypenalty | --modelContextLength | -n | --latest | -y | --youtube | -g | --language | -u | --scrape_url | -q | --scrape_question | -e | --seed | --address | --api-key | --search-location)
     # No specific completion suggestions, user types the value
     return 0
     ;;

completions/fabric.fish

@@ -60,6 +60,8 @@ complete -c fabric -l printsession -d "Print session" -a "(__fabric_get_sessions
 complete -c fabric -l address -d "The address to bind the REST API (default: :8080)"
 complete -c fabric -l api-key -d "API key used to secure server routes"
 complete -c fabric -l config -d "Path to YAML config file" -r -a "*.yaml *.yml"
+complete -c fabric -l search-location -d "Set location for web search results (e.g., 'America/Los_Angeles')"
+complete -c fabric -l image-file -d "Save generated image to specified file path (e.g., 'output.png')" -r -a "*.png *.jpg *.jpeg *.gif *.bmp"
 complete -c fabric -l addextension -d "Register a new extension from config file path" -r -a "*.yaml *.yml"
 complete -c fabric -l rmextension -d "Remove a registered extension by name" -a "(__fabric_get_extensions)"
 complete -c fabric -l strategy -d "Choose a strategy from the available strategies" -a "(__fabric_get_strategies)"
@@ -84,6 +86,7 @@ complete -c fabric -l metadata -d "Output video metadata"
 complete -c fabric -l readability -d "Convert HTML input into a clean, readable view"
 complete -c fabric -l input-has-vars -d "Apply variables to user input"
 complete -c fabric -l dry-run -d "Show what would be sent to the model without actually sending it"
+complete -c fabric -l search -d "Enable web search tool for supported models (Anthropic, OpenAI)"
 complete -c fabric -l serve -d "Serve the Fabric Rest API"
 complete -c fabric -l serveOllama -d "Serve the Fabric Rest API with ollama endpoints"
 complete -c fabric -l version -d "Print current version"

plugins/ai/dryrun/dryrun.go

@@ -82,6 +82,9 @@ func (c *Client) formatOptions(opts *common.ChatOptions) string {
 			builder.WriteString(fmt.Sprintf("SearchLocation: %s\n", opts.SearchLocation))
 		}
 	}
+	if opts.ImageFile != "" {
+		builder.WriteString(fmt.Sprintf("ImageFile: %s\n", opts.ImageFile))
+	}
 
 	return builder.String()
 }

plugins/ai/openai/openai.go

@@ -134,6 +134,12 @@ func (o *Client) sendResponses(ctx context.Context, msgs []*chat.ChatCompletionM
 	if resp, err = o.ApiClient.Responses.New(ctx, req); err != nil {
 		return
 	}
+
+	// Extract and save images if requested
+	if err = o.extractAndSaveImages(resp, opts); err != nil {
+		return
+	}
+
 	ret = o.extractText(resp)
 	return
 }
@@ -183,6 +189,9 @@ func (o *Client) buildResponseParams(
 		},
 	}
 
+	// Add tools if enabled
+	var tools []responses.ToolUnionParam
+
 	// Add web search tool if enabled
 	if opts.Search {
 		webSearchTool := responses.ToolParamOfWebSearchPreview("web_search_preview")
@@ -195,7 +204,14 @@ func (o *Client) buildResponseParams(
 			}
 		}
 
-		ret.Tools = []responses.ToolUnionParam{webSearchTool}
+		tools = append(tools, webSearchTool)
+	}
+
+	// Add image generation tool if needed
+	tools = o.addImageGenerationTool(opts, tools)
+
+	if len(tools) > 0 {
+		ret.Tools = tools
 	}
 
 	if !opts.Raw {