chore(release): Update version to v1.4.385

Fix #1931 - Image Generation Feature should warn if the model is not capable of Image Generation

CHANGELOG.md

@@ -1,5 +1,51 @@
 # Changelog
 
+## v1.4.385 (2026-01-20)
+
+### PR [#1947](https://github.com/danielmiessler/Fabric/pull/1947) by [cleong14](https://github.com/cleong14): feat(patterns): add extract_bd_ideas pattern
+
+- Added extract_bd_ideas pattern that extracts actionable ideas from content and transforms them into well-structured bd issue tracker commands
+- Implemented identification system for tasks, problems, ideas, improvements, bugs, and features
+- Added actionability evaluation and appropriate scoping functionality
+- Integrated priority assignment system (P0-P4) with relevant labels
+- Created ready-to-execute bd create commands output format
+
+### PR [#1948](https://github.com/danielmiessler/Fabric/pull/1948) by [cleong14](https://github.com/cleong14): feat(patterns): add create_bd_issue pattern
+
+- Added create_bd_issue pattern that transforms natural language issue descriptions into optimal bd (Beads) issue tracker commands
+- Implemented comprehensive bd create flag reference for better command generation
+- Added intelligent type detection system that automatically categorizes issues as bug, feature, task, epic, or chore
+- Included priority assessment capability that assigns P0-P4 priority levels based on urgency signals in descriptions
+- Integrated smart label selection feature that automatically chooses 1-4 relevant labels for each issue
+
+### PR [#1949](https://github.com/danielmiessler/Fabric/pull/1949) by [ksylvan](https://github.com/ksylvan): Fix #1931 - Image Generation Feature should warn if the model is not capable of Image Generation
+
+- Add image generation compatibility warnings for unsupported models
+- Add warning to stderr when using incompatible models with image generation
+- Add GPT-5, GPT-5-nano, and GPT-5.2 to supported image generation models
+- Create `checkImageGenerationCompatibility` function in OpenAI plugin
+- Add comprehensive tests for image generation compatibility warnings
+
+## v1.4.384 (2026-01-19)
+
+### PR [#1944](https://github.com/danielmiessler/Fabric/pull/1944) by [ksylvan](https://github.com/ksylvan): Add Infermatic AI Provider Support
+
+- Add Infermatic provider to ProviderMap as part of Phase 1 implementation for issue #1033
+- Add test coverage for the Infermatic AI provider in TestCreateClient to verify provider exists and creates valid client
+- Replace go-git status API with native `git status --porcelain` command to fix worktree compatibility issues
+- Simplify `IsWorkingDirectoryClean` and `GetStatusDetails` functions to use CLI output parsing instead of go-git library
+- Use native `git rev-parse HEAD` to get commit hash after commit and remove unused imports from walker.go
+
+## v1.4.383 (2026-01-18)
+
+### PR [#1943](https://github.com/danielmiessler/Fabric/pull/1943) by [ksylvan](https://github.com/ksylvan): fix: Ollama server now respects the default context window
+
+- Fix: Ollama server now respects the default context window instead of using hardcoded 2048 tokens
+- Add parseOllamaNumCtx() function with type-safe extraction supporting 6 numeric types and platform-aware integer overflow protection
+- Extract num_ctx from client request options and add ModelContextLength field to ChatRequest struct
+- Implement DoS protection via 1,000,000 token maximum limit with sanitized error messages
+- Add comprehensive unit tests for parseOllamaNumCtx function covering edge cases including overflow and invalid types
+
 ## v1.4.382 (2026-01-17)
 
 ### PR [#1941](https://github.com/danielmiessler/Fabric/pull/1941) by [ksylvan](https://github.com/ksylvan): Add `greybeard_secure_prompt_engineer` to metadata, also remove duplicate json data file

cmd/fabric/version.go

@@ -1,3 +1,3 @@
 package main
 
-var version = "v1.4.382"
+var version = "v1.4.385"

cmd/generate_changelog/internal/git/walker.go

@@ -2,9 +2,7 @@ package git
 
 import (
 	"fmt"
-	"os"
 	"os/exec"
-	"path/filepath"
 	"regexp"
 	"strconv"
 	"strings"
@@ -425,64 +423,49 @@ func (w *Walker) Repository() *git.Repository {
 }
 
 // IsWorkingDirectoryClean checks if the working directory has any uncommitted changes
+// Uses native git CLI instead of go-git to properly handle worktree scenarios
 func (w *Walker) IsWorkingDirectoryClean() (bool, error) {
 	worktree, err := w.repo.Worktree()
 	if err != nil {
 		return false, fmt.Errorf("failed to get worktree: %w", err)
 	}
 
-	status, err := worktree.Status()
+	worktreePath := worktree.Filesystem.Root()
+
+	// Use native git status --porcelain to avoid go-git worktree issues
+	// go-git's status API has known bugs with linked worktrees
+	cmd := exec.Command("git", "status", "--porcelain")
+	cmd.Dir = worktreePath
+
+	output, err := cmd.Output()
 	if err != nil {
 		return false, fmt.Errorf("failed to get git status: %w", err)
 	}
 
-	worktreePath := worktree.Filesystem.Root()
-
-	// In worktrees, files staged in the main repo may appear in status but not exist in the worktree
-	// We need to check both the working directory status AND filesystem existence
-	for file, fileStatus := range status {
-		// Check if there are any changes in the working directory
-		if fileStatus.Worktree != git.Unmodified && fileStatus.Worktree != git.Untracked {
-			return false, nil
-		}
-
-		// For staged files (Added, Modified in index), verify they exist in this worktree's filesystem
-		// This handles the worktree case where the main repo has staged files that don't exist here
-		if fileStatus.Staging != git.Unmodified && fileStatus.Staging != git.Untracked {
-			filePath := filepath.Join(worktreePath, file)
-			if _, err := os.Stat(filePath); os.IsNotExist(err) {
-				// File is staged but doesn't exist in this worktree - ignore it
-				continue
-			}
-			// File is staged AND exists in this worktree - not clean
-			return false, nil
-		}
-	}
-
-	return true, nil
+	// If output is empty, working directory is clean
+	return len(strings.TrimSpace(string(output))) == 0, nil
 }
 
 // GetStatusDetails returns a detailed status of the working directory
+// Uses native git CLI instead of go-git to properly handle worktree scenarios
 func (w *Walker) GetStatusDetails() (string, error) {
 	worktree, err := w.repo.Worktree()
 	if err != nil {
 		return "", fmt.Errorf("failed to get worktree: %w", err)
 	}
 
-	status, err := worktree.Status()
+	worktreePath := worktree.Filesystem.Root()
+
+	// Use native git status --porcelain to avoid go-git worktree issues
+	cmd := exec.Command("git", "status", "--porcelain")
+	cmd.Dir = worktreePath
+
+	output, err := cmd.Output()
 	if err != nil {
 		return "", fmt.Errorf("failed to get git status: %w", err)
 	}
 
-	var details strings.Builder
-	for file, fileStatus := range status {
-		// Only include files with actual working directory changes
-		if fileStatus.Worktree != git.Unmodified && fileStatus.Worktree != git.Untracked {
-			details.WriteString(fmt.Sprintf("  %c%c %s\n", fileStatus.Staging, fileStatus.Worktree, file))
-		}
-	}
-
-	return details.String(), nil
+	return string(output), nil
 }
 
 // AddFile adds a file to the git index
@@ -526,13 +509,17 @@ func (w *Walker) CommitChanges(message string) (plumbing.Hash, error) {
 		return plumbing.ZeroHash, fmt.Errorf("failed to commit: %w (output: %s)", err, string(output))
 	}
 
-	// Get the commit hash from HEAD
-	ref, err := w.repo.Head()
+	// Get the commit hash from HEAD using native git to avoid go-git worktree issues
+	hashCmd := exec.Command("git", "rev-parse", "HEAD")
+	hashCmd.Dir = worktreePath
+
+	hashOutput, err := hashCmd.Output()
 	if err != nil {
 		return plumbing.ZeroHash, fmt.Errorf("failed to get HEAD after commit: %w", err)
 	}
 
-	return ref.Hash(), nil
+	hashStr := strings.TrimSpace(string(hashOutput))
+	return plumbing.NewHash(hashStr), nil
 }
 
 // PushToRemote pushes the current branch to the remote repository

internal/cli/chat_test.go

@@ -1,6 +1,7 @@
 package cli
 
 import (
+	"os"
 	"strings"
 	"testing"
 
@@ -164,3 +165,182 @@ func TestSendNotification_MessageTruncation(t *testing.T) {
 		})
 	}
 }
+
+func TestImageGenerationCompatibilityWarning(t *testing.T) {
+	// Save original stderr to restore later
+	originalStderr := os.Stderr
+	defer func() {
+		os.Stderr = originalStderr
+	}()
+
+	tests := []struct {
+		name          string
+		model         string
+		imageFile     string
+		expectWarning bool
+		warningSubstr string
+		description   string
+	}{
+		{
+			name:          "Compatible model with image",
+			model:         "gpt-4o",
+			imageFile:     "test.png",
+			expectWarning: false,
+			description:   "Should not warn for compatible model",
+		},
+		{
+			name:          "Incompatible model with image",
+			model:         "o1-mini",
+			imageFile:     "test.png",
+			expectWarning: true,
+			warningSubstr: "Warning: Model 'o1-mini' does not support image generation",
+			description:   "Should warn for incompatible model",
+		},
+		{
+			name:          "Incompatible model without image",
+			model:         "o1-mini",
+			imageFile:     "",
+			expectWarning: false,
+			description:   "Should not warn when no image file specified",
+		},
+		{
+			name:          "Compatible model without image",
+			model:         "gpt-4o-mini",
+			imageFile:     "",
+			expectWarning: false,
+			description:   "Should not warn when no image file specified even for compatible model",
+		},
+		{
+			name:          "Another incompatible model with image",
+			model:         "gpt-3.5-turbo",
+			imageFile:     "output.jpg",
+			expectWarning: true,
+			warningSubstr: "Warning: Model 'gpt-3.5-turbo' does not support image generation",
+			description:   "Should warn for different incompatible model",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Note: In a real integration test, we would capture stderr like this:
+			// stderrCapture := &bytes.Buffer{}
+			// os.Stderr = stderrCapture
+			// But since we can't test the actual openai plugin from here due to import cycles,
+			// we'll simulate the integration behavior
+
+			// Create test options (for structure validation)
+			_ = &domain.ChatOptions{
+				Model:     tt.model,
+				ImageFile: tt.imageFile,
+			}
+
+			// We'll test the warning function that was added to openai.go
+			// but we need to simulate the same behavior in our test
+			// Since we can't directly access the openai package here due to import cycles,
+			// we'll create a minimal test that verifies the integration would work
+
+			// For integration testing purposes, we'll verify that the warning conditions
+			// are correctly identified and the process continues as expected
+			hasImage := tt.imageFile != ""
+			shouldWarn := hasImage && tt.expectWarning
+
+			// Check if the expected warning condition matches our test case
+			if shouldWarn && tt.expectWarning {
+				// Verify warning substr is provided for warning cases
+				if tt.warningSubstr == "" {
+					t.Errorf("Expected warning substring for warning case")
+				}
+			}
+
+			// The actual warning would be printed by the openai plugin
+			// Here we verify the integration logic is sound
+			// In a real integration test, we would check stderr output
+
+			if tt.expectWarning {
+				// This is expected since we're not calling the actual openai plugin
+				// In a real integration test, the warning would appear in stderr
+				t.Logf("Note: Warning would be printed by openai plugin for model '%s'", tt.model)
+			}
+
+			// In a real test with stderr capture, we would check for unexpected warnings
+			// Since we're not calling the actual plugin, we just validate the logic structure
+		})
+	}
+}
+
+func TestImageGenerationIntegrationScenarios(t *testing.T) {
+	// Test various real-world scenarios that users might encounter
+	scenarios := []struct {
+		name          string
+		cliArgs       []string
+		expectWarning bool
+		warningModel  string
+		description   string
+	}{
+		{
+			name: "User tries o1-mini with image",
+			cliArgs: []string{
+				"-m", "o1-mini",
+				"--image-file", "output.png",
+				"Describe this image",
+			},
+			expectWarning: true,
+			warningModel:  "o1-mini",
+			description:   "Common user error - using incompatible model",
+		},
+		{
+			name: "User uses compatible model",
+			cliArgs: []string{
+				"-m", "gpt-4o",
+				"--image-file", "output.png",
+				"Describe this image",
+			},
+			expectWarning: false,
+			description:   "Correct usage - should work without warnings",
+		},
+		{
+			name: "User specifies model via pattern env var",
+			cliArgs: []string{
+				"--pattern", "summarize",
+				"--image-file", "output.png",
+				"Summarize this image",
+			},
+			expectWarning: false, // Depends on env var, not tested here
+			description:   "Pattern-based model selection",
+		},
+	}
+
+	for _, scenario := range scenarios {
+		t.Run(scenario.name, func(t *testing.T) {
+			// This test validates the CLI argument parsing would work correctly
+			// The actual warning functionality is tested in the openai package
+
+			// Verify CLI arguments are properly structured
+			hasImage := false
+			model := ""
+
+			for i, arg := range scenario.cliArgs {
+				if arg == "-m" && i+1 < len(scenario.cliArgs) {
+					model = scenario.cliArgs[i+1]
+				}
+				if arg == "--image-file" && i+1 < len(scenario.cliArgs) {
+					hasImage = true
+				}
+			}
+
+			// Validate the scenario setup
+			if scenario.expectWarning && scenario.warningModel == "" {
+				t.Errorf("Expected warning scenario must specify warning model")
+			}
+
+			// Log the scenario for debugging
+			t.Logf("Scenario: %s", scenario.description)
+			t.Logf("Model: %s, Has Image: %v, Expect Warning: %v", model, hasImage, scenario.expectWarning)
+
+			// In actual integration, the warning would appear when:
+			// 1. hasImage is true
+			// 2. model is in the incompatible list
+			// The openai package tests cover the actual warning functionality
+		})
+	}
+}

internal/plugins/ai/openai/openai.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"net/http"
+	"os"
 	"slices"
 	"strings"
 	"time"
@@ -71,6 +72,14 @@ func (o *Client) SetResponsesAPIEnabled(enabled bool) {
 	o.ImplementsResponses = enabled
 }
 
+// checkImageGenerationCompatibility warns if the model doesn't support image generation
+func checkImageGenerationCompatibility(model string) {
+	if !supportsImageGeneration(model) {
+		fmt.Fprintf(os.Stderr, "Warning: Model '%s' does not support image generation. Supported models: %s. Consider using -m gpt-4o for image generation.\n",
+			model, strings.Join(ImageGenerationSupportedModels, ", "))
+	}
+}
+
 func (o *Client) configure() (ret error) {
 	opts := []option.RequestOption{option.WithAPIKey(o.ApiKey.Value)}
 	if o.ApiBaseURL.Value != "" {
@@ -154,6 +163,11 @@ func (o *Client) Send(ctx context.Context, msgs []*chat.ChatCompletionMessage, o
 }
 
 func (o *Client) sendResponses(ctx context.Context, msgs []*chat.ChatCompletionMessage, opts *domain.ChatOptions) (ret string, err error) {
+	// Warn if model doesn't support image generation when image file is specified
+	if opts.ImageFile != "" {
+		checkImageGenerationCompatibility(opts.Model)
+	}
+
 	// Validate model supports image generation if image file is specified
 	if opts.ImageFile != "" && !supportsImageGeneration(opts.Model) {
 		return "", fmt.Errorf("model '%s' does not support image generation. Supported models: %s", opts.Model, strings.Join(ImageGenerationSupportedModels, ", "))

internal/plugins/ai/openai/openai_image.go

@@ -28,6 +28,9 @@ var ImageGenerationSupportedModels = []string{
 	"gpt-4.1-mini",
 	"gpt-4.1-nano",
 	"o3",
+	"gpt-5",
+	"gpt-5-nano",
+	"gpt-5.2",
 }
 
 // supportsImageGeneration checks if the given model supports the image_generation tool

internal/plugins/ai/openai/openai_image_test.go

@@ -1,7 +1,9 @@
 package openai
 
 import (
+	"bytes"
 	"fmt"
+	"os"
 	"strings"
 	"testing"
 
@@ -257,6 +259,21 @@ func TestSupportsImageGeneration(t *testing.T) {
 			model:    "o3",
 			expected: true,
 		},
+		{
+			name:     "gpt-5 supports image generation",
+			model:    "gpt-5",
+			expected: true,
+		},
+		{
+			name:     "gpt-5-nano supports image generation",
+			model:    "gpt-5-nano",
+			expected: true,
+		},
+		{
+			name:     "gpt-5.2 supports image generation",
+			model:    "gpt-5.2",
+			expected: true,
+		},
 		{
 			name:     "o1 does not support image generation",
 			model:    "o1",
@@ -442,3 +459,165 @@ func TestAddImageGenerationToolWithUserParameters(t *testing.T) {
 		})
 	}
 }
+
+func TestCheckImageGenerationCompatibility(t *testing.T) {
+	// Capture stderr output
+	oldStderr := os.Stderr
+	r, w, _ := os.Pipe()
+	os.Stderr = w
+
+	tests := []struct {
+		name          string
+		model         string
+		expectWarning bool
+		expectedText  string
+	}{
+		{
+			name:          "Supported model - no warning",
+			model:         "gpt-4o",
+			expectWarning: false,
+		},
+		{
+			name:          "Unsupported model - warning expected",
+			model:         "o1-mini",
+			expectWarning: true,
+			expectedText:  "Warning: Model 'o1-mini' does not support image generation",
+		},
+		{
+			name:          "Another unsupported model - warning expected",
+			model:         "gpt-3.5-turbo",
+			expectWarning: true,
+			expectedText:  "Warning: Model 'gpt-3.5-turbo' does not support image generation",
+		},
+		{
+			name:          "Supported o3 model - no warning",
+			model:         "o3",
+			expectWarning: false,
+		},
+		{
+			name:          "Empty model - warning expected",
+			model:         "",
+			expectWarning: true,
+			expectedText:  "Warning: Model '' does not support image generation",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Reset pipe for each test
+			r, w, _ = os.Pipe()
+			os.Stderr = w
+
+			checkImageGenerationCompatibility(tt.model)
+
+			// Close writer and read output
+			w.Close()
+			var buf bytes.Buffer
+			buf.ReadFrom(r)
+			output := buf.String()
+
+			if tt.expectWarning {
+				assert.NotEmpty(t, output, "Expected warning output for unsupported model")
+				assert.Contains(t, output, tt.expectedText, "Warning message should contain model name")
+				assert.Contains(t, output, "Supported models:", "Warning should mention supported models")
+				assert.Contains(t, output, "gpt-4o", "Warning should suggest gpt-4o")
+			} else {
+				assert.Empty(t, output, "No warning expected for supported model")
+			}
+		})
+	}
+
+	// Restore stderr
+	os.Stderr = oldStderr
+}
+
+func TestSendResponses_WithWarningIntegration(t *testing.T) {
+	client := NewClient()
+	client.ApiKey.Value = "test-api-key"
+	client.ApiBaseURL.Value = "https://api.openai.com/v1"
+	client.ImplementsResponses = true
+	client.Configure() // Initialize client
+
+	tests := []struct {
+		name          string
+		model         string
+		imageFile     string
+		expectWarning bool
+		expectError   bool
+		expectedError string
+	}{
+		{
+			name:          "Unsupported model with image - warning then error",
+			model:         "o1-mini",
+			imageFile:     "test.png",
+			expectWarning: true,
+			expectError:   true,
+			expectedError: "model 'o1-mini' does not support image generation",
+		},
+		{
+			name:          "Supported model with image - no warning, no error",
+			model:         "gpt-4o",
+			imageFile:     "test.png",
+			expectWarning: false,
+			expectError:   false,
+		},
+		{
+			name:          "Unsupported model without image - no warning, no error",
+			model:         "o1-mini",
+			imageFile:     "",
+			expectWarning: false,
+			expectError:   false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// Capture stderr for warning detection
+			oldStderr := os.Stderr
+			r, w, _ := os.Pipe()
+			os.Stderr = w
+
+			opts := &domain.ChatOptions{
+				Model:     tt.model,
+				ImageFile: tt.imageFile,
+			}
+
+			msgs := []*chat.ChatCompletionMessage{
+				{Role: "user", Content: "Generate an image"},
+			}
+
+			// Call sendResponses - this will trigger the warning and potentially error
+			_, err := client.sendResponses(nil, msgs, opts)
+
+			// Close writer and read warning output
+			w.Close()
+			var buf bytes.Buffer
+			buf.ReadFrom(r)
+			warningOutput := buf.String()
+
+			// Restore stderr
+			os.Stderr = oldStderr
+
+			// Check warning expectations
+			if tt.expectWarning {
+				assert.NotEmpty(t, warningOutput, "Expected warning output")
+				assert.Contains(t, warningOutput, "Warning: Model '"+tt.model+"' does not support image generation")
+			} else {
+				assert.Empty(t, warningOutput, "No warning expected")
+			}
+
+			// Check error expectations
+			if tt.expectError {
+				assert.Error(t, err, "Expected error for unsupported model with image")
+				assert.Contains(t, err.Error(), tt.expectedError)
+			} else {
+				// We expect an error here because we don't have a real API key/config
+				// But it shouldn't be the image generation validation error
+				if err != nil {
+					assert.NotContains(t, err.Error(), "does not support image generation",
+						"Should not get image generation error for supported cases")
+				}
+			}
+		})
+	}
+}

internal/plugins/ai/openai_compatible/providers_config.go

@@ -145,6 +145,11 @@ var ProviderMap = map[string]ProviderConfig{
 		ModelsURL:           "https://models.github.ai/catalog", // FetchModelsDirectly will append /models
 		ImplementsResponses: false,
 	},
+	"Infermatic": {
+		Name:                "Infermatic",
+		BaseURL:             "https://api.totalgpt.ai/v1",
+		ImplementsResponses: false,
+	},
 	"GrokAI": {
 		Name:                "GrokAI",
 		BaseURL:             "https://api.x.ai/v1",

internal/plugins/ai/openai_compatible/providers_config_test.go

@@ -30,6 +30,11 @@ func TestCreateClient(t *testing.T) {
 			provider: "Abacus",
 			exists:   true,
 		},
+		{
+			name:     "Existing provider - Infermatic",
+			provider: "Infermatic",
+			exists:   true,
+		},
 		{
 			name:     "Existing provider - MiniMax",
 			provider: "MiniMax",

internal/server/chat.go

@@ -35,7 +35,8 @@ type PromptRequest struct {
 
 type ChatRequest struct {
 	Prompts            []PromptRequest `json:"prompts"`
-	Language           string          `json:"language"` // Add Language field to bind from request
+	Language           string          `json:"language"`
+	ModelContextLength int             `json:"modelContextLength,omitempty"` // Context window size
 	domain.ChatOptions                 // Embed the ChatOptions from common package
 }
 
@@ -118,7 +119,7 @@ func (h *ChatHandler) HandleChat(c *gin.Context) {
 					}
 				}
 
-				chatter, err := h.registry.GetChatter(p.Model, 2048, p.Vendor, "", true, false)
+				chatter, err := h.registry.GetChatter(p.Model, request.ModelContextLength, p.Vendor, "", true, false)
 				if err != nil {
 					log.Printf("Error creating chatter: %v", err)
 					streamChan <- domain.StreamUpdate{Type: domain.StreamTypeError, Content: fmt.Sprintf("Error: %v", err)}

internal/server/ollama.go

@@ -7,8 +7,10 @@ import (
 	"fmt"
 	"io"
 	"log"
+	"math"
 	"net/http"
 	"net/url"
+	"strconv"
 	"strings"
 	"time"
 
@@ -79,6 +81,111 @@ type FabricResponseFormat struct {
 	Content string `json:"content"`
 }
 
+// parseOllamaNumCtx extracts and validates the num_ctx parameter from Ollama request options.
+// Returns:
+//   - (0, nil) if num_ctx is not present or is null
+//   - (n, nil) if num_ctx is a valid positive integer
+//   - (0, error) if num_ctx is present but invalid
+func parseOllamaNumCtx(options map[string]any) (int, error) {
+	if options == nil {
+		return 0, nil
+	}
+
+	val, exists := options["num_ctx"]
+	if !exists {
+		return 0, nil // Not provided, caller should use default
+	}
+
+	if val == nil {
+		return 0, nil // Explicit null, treat as not provided
+	}
+
+	var contextLength int
+
+	// Platform-specific max int value for overflow checks
+	const maxInt = int64(^uint(0) >> 1)
+
+	switch v := val.(type) {
+	case float64:
+		if math.IsNaN(v) || math.IsInf(v, 0) {
+			return 0, fmt.Errorf("num_ctx must be a finite number")
+		}
+		if math.Trunc(v) != v {
+			return 0, fmt.Errorf("num_ctx must be an integer, got float with fractional part")
+		}
+		// Check for overflow on 32-bit systems (negative values handled by validation at line 166)
+		if v > float64(maxInt) {
+			return 0, fmt.Errorf("num_ctx value out of range")
+		}
+		contextLength = int(v)
+
+	case float32:
+		f64 := float64(v)
+		if math.IsNaN(f64) || math.IsInf(f64, 0) {
+			return 0, fmt.Errorf("num_ctx must be a finite number")
+		}
+		if math.Trunc(f64) != f64 {
+			return 0, fmt.Errorf("num_ctx must be an integer, got float with fractional part")
+		}
+		// Check for overflow on 32-bit systems (negative values handled by validation at line 177)
+		if f64 > float64(maxInt) {
+			return 0, fmt.Errorf("num_ctx value out of range")
+		}
+		contextLength = int(v)
+
+	case int:
+		contextLength = v
+
+	case int64:
+		if v < 0 {
+			return 0, fmt.Errorf("num_ctx must be positive, got: %d", v)
+		}
+		if v > maxInt {
+			return 0, fmt.Errorf("num_ctx value too large: %d", v)
+		}
+		contextLength = int(v)
+
+	case json.Number:
+		i64, err := v.Int64()
+		if err != nil {
+			return 0, fmt.Errorf("num_ctx must be a valid number")
+		}
+		if i64 < 0 {
+			return 0, fmt.Errorf("num_ctx must be positive, got: %d", i64)
+		}
+		if i64 > maxInt {
+			return 0, fmt.Errorf("num_ctx value too large: %d", i64)
+		}
+		contextLength = int(i64)
+
+	case string:
+		parsed, err := strconv.Atoi(v)
+		if err != nil {
+			// Truncate long strings in error messages to avoid logging excessively large input
+			errVal := v
+			if len(v) > 50 {
+				errVal = v[:50] + "..."
+			}
+			return 0, fmt.Errorf("num_ctx must be a valid number, got: %s", errVal)
+		}
+		contextLength = parsed
+
+	default:
+		return 0, fmt.Errorf("num_ctx must be a number, got invalid type")
+	}
+
+	if contextLength <= 0 {
+		return 0, fmt.Errorf("num_ctx must be positive, got: %d", contextLength)
+	}
+
+	const maxContextLength = 1000000
+	if contextLength > maxContextLength {
+		return 0, fmt.Errorf("num_ctx exceeds maximum allowed value of %d", maxContextLength)
+	}
+
+	return contextLength, nil
+}
+
 func ServeOllama(registry *core.PluginRegistry, address string, version string) (err error) {
 	r := gin.New()
 
@@ -161,6 +268,15 @@ func (f APIConvert) ollamaChat(c *gin.Context) {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": "testing endpoint"})
 		return
 	}
+
+	// Extract and validate num_ctx from options
+	numCtx, err := parseOllamaNumCtx(prompt.Options)
+	if err != nil {
+		log.Printf("Invalid num_ctx in request: %v", err)
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+
 	now := time.Now()
 	var chat ChatRequest
 
@@ -210,6 +326,10 @@ func (f APIConvert) ollamaChat(c *gin.Context) {
 			Variables:   variables,
 		}}
 	}
+
+	// Set context length from parsed num_ctx
+	chat.ModelContextLength = numCtx
+
 	fabricChatReq, err := json.Marshal(chat)
 	if err != nil {
 		log.Printf("Error marshalling body: %v", err)

internal/server/ollama_test.go

@@ -1,6 +1,9 @@
 package restapi
 
 import (
+	"encoding/json"
+	"math"
+	"strings"
 	"testing"
 )
 
@@ -98,3 +101,263 @@ func TestBuildFabricChatURL(t *testing.T) {
 		})
 	}
 }
+
+func TestParseOllamaNumCtx(t *testing.T) {
+	tests := []struct {
+		name    string
+		options map[string]any
+		want    int
+		wantErr bool
+		errMsg  string
+	}{
+		// --- Valid inputs ---
+		{
+			name:    "nil options",
+			options: nil,
+			want:    0,
+			wantErr: false,
+		},
+		{
+			name:    "empty options",
+			options: map[string]any{},
+			want:    0,
+			wantErr: false,
+		},
+		{
+			name:    "num_ctx not present",
+			options: map[string]any{"other_key": 123},
+			want:    0,
+			wantErr: false,
+		},
+		{
+			name:    "num_ctx is null",
+			options: map[string]any{"num_ctx": nil},
+			want:    0,
+			wantErr: false,
+		},
+		{
+			name:    "valid int",
+			options: map[string]any{"num_ctx": 4096},
+			want:    4096,
+			wantErr: false,
+		},
+		{
+			name:    "valid float64 (whole number)",
+			options: map[string]any{"num_ctx": float64(8192)},
+			want:    8192,
+			wantErr: false,
+		},
+		{
+			name:    "valid float32 (whole number)",
+			options: map[string]any{"num_ctx": float32(2048)},
+			want:    2048,
+			wantErr: false,
+		},
+		{
+			name:    "valid json.Number",
+			options: map[string]any{"num_ctx": json.Number("16384")},
+			want:    16384,
+			wantErr: false,
+		},
+		{
+			name:    "valid string",
+			options: map[string]any{"num_ctx": "32768"},
+			want:    32768,
+			wantErr: false,
+		},
+		{
+			name:    "valid int64",
+			options: map[string]any{"num_ctx": int64(65536)},
+			want:    65536,
+			wantErr: false,
+		},
+		// --- Invalid inputs ---
+		{
+			name:    "float64 with fractional part",
+			options: map[string]any{"num_ctx": 4096.5},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be an integer, got float with fractional part",
+		},
+		{
+			name:    "float32 with fractional part",
+			options: map[string]any{"num_ctx": float32(2048.75)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be an integer, got float with fractional part",
+		},
+		{
+			name:    "negative int",
+			options: map[string]any{"num_ctx": -100},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be positive",
+		},
+		{
+			name:    "zero int",
+			options: map[string]any{"num_ctx": 0},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be positive",
+		},
+		{
+			name:    "negative float64",
+			options: map[string]any{"num_ctx": float64(-500)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be positive",
+		},
+		{
+			name:    "negative float32",
+			options: map[string]any{"num_ctx": float32(-250)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be positive",
+		},
+		{
+			name:    "non-numeric string",
+			options: map[string]any{"num_ctx": "not-a-number"},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a valid number",
+		},
+		{
+			name:    "invalid json.Number",
+			options: map[string]any{"num_ctx": json.Number("invalid")},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a valid number",
+		},
+		{
+			name:    "exceeds maximum allowed value",
+			options: map[string]any{"num_ctx": 2000000},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx exceeds maximum allowed value",
+		},
+		{
+			name:    "unsupported type (bool)",
+			options: map[string]any{"num_ctx": true},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a number, got invalid type",
+		},
+		{
+			name:    "unsupported type (slice)",
+			options: map[string]any{"num_ctx": []int{1, 2, 3}},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a number, got invalid type",
+		},
+		// --- Edge cases ---
+		{
+			name:    "minimum valid value",
+			options: map[string]any{"num_ctx": 1},
+			want:    1,
+			wantErr: false,
+		},
+		{
+			name:    "maximum allowed value",
+			options: map[string]any{"num_ctx": 1000000},
+			want:    1000000,
+			wantErr: false,
+		},
+		{
+			name:    "very large float64 (overflow)",
+			options: map[string]any{"num_ctx": float64(math.MaxFloat64)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx value out of range",
+		},
+		{
+			name:    "large int64 exceeding maxInt on 32-bit",
+			options: map[string]any{"num_ctx": int64(1 << 40)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx", // either "too large" or "exceeds maximum"
+		},
+		{
+			name:    "long string gets truncated in error",
+			options: map[string]any{"num_ctx": "this-is-a-very-long-string-that-should-be-truncated-in-the-error-message"},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a valid number",
+		},
+		// --- Special float values ---
+		{
+			name:    "float64 NaN",
+			options: map[string]any{"num_ctx": math.NaN()},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a finite number",
+		},
+		{
+			name:    "float64 positive infinity",
+			options: map[string]any{"num_ctx": math.Inf(1)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a finite number",
+		},
+		{
+			name:    "float64 negative infinity",
+			options: map[string]any{"num_ctx": math.Inf(-1)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a finite number",
+		},
+		{
+			name:    "float32 NaN",
+			options: map[string]any{"num_ctx": float32(math.NaN())},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a finite number",
+		},
+		{
+			name:    "float32 positive infinity",
+			options: map[string]any{"num_ctx": float32(math.Inf(1))},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a finite number",
+		},
+		{
+			name:    "float32 negative infinity",
+			options: map[string]any{"num_ctx": float32(math.Inf(-1))},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be a finite number",
+		},
+		// --- Negative int64 (32-bit wraparound prevention) ---
+		{
+			name:    "negative int64",
+			options: map[string]any{"num_ctx": int64(-1000)},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be positive",
+		},
+		{
+			name:    "negative json.Number",
+			options: map[string]any{"num_ctx": json.Number("-500")},
+			want:    0,
+			wantErr: true,
+			errMsg:  "num_ctx must be positive",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := parseOllamaNumCtx(tt.options)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("parseOllamaNumCtx() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if err != nil && tt.errMsg != "" {
+				if !strings.Contains(err.Error(), tt.errMsg) {
+					t.Errorf("parseOllamaNumCtx() error message = %q, want to contain %q", err.Error(), tt.errMsg)
+				}
+			}
+			if got != tt.want {
+				t.Errorf("parseOllamaNumCtx() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

nix/pkgs/fabric/version.nix

@@ -1 +1 @@
-"1.4.382"
+"1.4.385"

patterns/create_bd_issue/system.md

@@ -0,0 +1,104 @@
+# IDENTITY and PURPOSE
+
+You are an expert at transforming natural language issue descriptions into optimal `bd create` commands. You understand the bd (Beads) issue tracker deeply and always select the most appropriate flags based on the user's intent.
+
+Your goal is to produce a single, well-crafted `bd create` command that captures all the relevant details from the input while following bd best practices.
+
+# BD CREATE REFERENCE
+
+Available flags:
+- `--title "string"` or positional first arg: Issue title (imperative mood: "Add...", "Fix...", "Update...")
+- `-d, --description "string"`: Issue description (context, acceptance criteria, notes)
+- `-t, --type TYPE`: bug|feature|task|epic|chore|merge-request|molecule|gate|agent|role|rig|convoy|event (default: task)
+- `-p, --priority P0-P4`: P0=critical, P1=high, P2=normal (default), P3=low, P4=wishlist
+- `-l, --labels strings`: Comma-separated labels (e.g., ux,backend,docs)
+- `-a, --assignee string`: Who should work on this
+- `-e, --estimate int`: Time estimate in minutes
+- `--due string`: Due date (+6h, +1d, +2w, tomorrow, next monday, 2025-01-15)
+- `--defer string`: Hide until date (same formats as --due)
+- `--deps strings`: Dependencies (e.g., 'bd-20' or 'blocks:bd-15')
+- `--parent string`: Parent issue ID for hierarchical child
+- `--acceptance string`: Acceptance criteria
+- `--design string`: Design notes
+- `--notes string`: Additional notes
+- `--external-ref string`: External reference (e.g., 'gh-9', 'jira-ABC')
+- `--ephemeral`: Mark as ephemeral (not exported)
+- `--prefix string` or `--rig string`: Create in specific rig
+- `--repo string`: Target repository for issue
+
+Type-specific flags:
+- Molecules: `--mol-type swarm|patrol|work`
+- Agents: `--agent-rig string`, `--role-type polecat|crew|witness|refinery|mayor|deacon`
+- Events: `--event-actor string`, `--event-category string`, `--event-payload string`, `--event-target string`
+- Gates: `--waits-for string`, `--waits-for-gate all-children|any-children`
+
+# STEPS
+
+1. Parse the input to understand:
+   - What is being requested (the core action/fix/feature)
+   - Any context or background
+   - Urgency or priority signals
+   - Technical domain (for labels)
+   - Time-related constraints
+   - Dependencies or blockers
+   - Acceptance criteria
+
+2. Determine the issue type:
+   - bug: Something is broken
+   - feature: New capability
+   - task: Work that needs doing
+   - epic: Large multi-part effort
+   - chore: Maintenance/cleanup
+
+3. Assess priority:
+   - P0: Production down, security breach, data loss
+   - P1: Major functionality broken, blocking release
+   - P2: Standard work (default)
+   - P3: Nice to have, can wait
+   - P4: Someday/maybe, ideas
+
+4. Select appropriate labels (limit to 1-4):
+   - Domain: frontend, backend, api, db, infra, mobile
+   - Category: ux, perf, security, docs, tech-debt
+   - Size: quick-win, spike, refactor
+
+5. Construct the optimal command:
+   - Title: 3-8 words, imperative mood
+   - Description: 1-3 sentences if complex
+   - Only include flags that add value (skip defaults)
+
+# OUTPUT INSTRUCTIONS
+
+- Output ONLY the bd create command, nothing else
+- No markdown code blocks, no explanations, no warnings
+- Use double quotes for all string values
+- Escape any internal quotes with backslash
+- If description is short, use -d; if long, suggest --body-file
+- Prefer explicit type when not "task"
+- Only include priority when not P2 (default)
+- Only include labels when they add categorization value
+- Order flags: type, priority, labels, then others
+
+# EXAMPLES
+
+Input: "We need to add dark mode to the settings page"
+Output: bd create "Add dark mode toggle to settings page" -t feature -l ux,frontend
+
+Input: "URGENT: login is broken on production"
+Output: bd create "Fix broken login on production" -t bug -p P0 -d "Login functionality is completely broken in production environment"
+
+Input: "maybe someday we could add keyboard shortcuts"
+Output: bd create "Add keyboard shortcuts" -t feature -p P4 -l ux
+
+Input: "need to update the deps before next week"
+Output: bd create "Update dependencies" -t chore --due "next week"
+
+Input: "the api docs are missing the new v2 endpoints, john should handle it"
+Output: bd create "Document v2 API endpoints" -t task -l docs,api -a john
+
+Input: "track time spent on customer dashboard - estimate about 2 hours"
+Output: bd create "Track time spent on customer dashboard" -e 120 -l analytics
+
+# INPUT
+
+INPUT:

patterns/extract_bd_ideas/system.md

@@ -0,0 +1,96 @@
+# IDENTITY and PURPOSE
+
+You are an expert at extracting actionable ideas from content and transforming them into well-structured issue tracker commands. You analyze input text—meeting notes, brainstorms, articles, conversations, or any content—and identify concrete, actionable items that should be tracked as issues.
+
+You understand that good issues are:
+- Specific and actionable (not vague wishes)
+- Appropriately scoped (not too big, not too small)
+- Self-contained (understandable without reading the source)
+- Prioritized by impact and urgency
+
+Take a step back and think step-by-step about how to achieve the best possible results.
+
+# STEPS
+
+1. Read the input content thoroughly, looking for:
+   - Explicit tasks or action items mentioned
+   - Problems that need solving
+   - Ideas that could be implemented
+   - Improvements or enhancements suggested
+   - Bugs or issues reported
+   - Features requested
+
+2. For each potential issue, evaluate:
+   - Is this actionable? (Skip vague wishes or opinions)
+   - Is this appropriately scoped? (Break down large items)
+   - What priority does this deserve? (P0=critical, P1=high, P2=normal, P3=low, P4=wishlist)
+   - What type is it? (feature, bug, task, idea, improvement)
+   - What labels apply? (e.g., ux, backend, docs, perf)
+
+3. Transform each item into a bd create command with:
+   - Clear, concise title (imperative mood: "Add...", "Fix...", "Update...")
+   - Description providing context from the source
+   - Appropriate priority
+   - Relevant labels
+
+4. Order results by priority (highest first)
+
+# OUTPUT SECTIONS
+
+## SUMMARY
+
+A 2-3 sentence summary of what was analyzed and how many actionable items were found.
+
+## ISSUES
+
+Output each issue as a `bd create` command, one per line, formatted for easy copy-paste execution.
+
+## SKIPPED
+
+List any items from the input that were considered but not included, with brief reason (e.g., "too vague", "not actionable", "duplicate of above").
+
+# OUTPUT INSTRUCTIONS
+
+- Output in Markdown format
+- Each bd command should be on its own line in a code block
+- Use this exact format for commands:
+  ```bash
+  bd create "Title in imperative mood" -d "Description with context" -p P2 -l label1,label2
+  ```
+- Priorities: P0 (critical/blocking), P1 (high/important), P2 (normal), P3 (low), P4 (wishlist)
+- Common labels: bug, feature, task, idea, docs, ux, backend, frontend, perf, security, tech-debt
+- Titles should be 3-8 words, imperative mood ("Add X", "Fix Y", "Update Z")
+- Descriptions should be 1-3 sentences providing context
+- Do not include dependencies (--deps) unless explicitly stated in the source
+- Do not include estimates (--estimate) unless explicitly stated
+- Do not give warnings or notes outside the defined sections
+- Extract at least 3 ideas if possible, maximum 20
+- Ensure each issue is distinct—no duplicates
+
+# EXAMPLE OUTPUT
+
+## SUMMARY
+
+Analyzed meeting notes from product planning session. Found 7 actionable items ranging from critical bugs to wishlist features.
+
+## ISSUES
+
+```bash
+bd create "Fix login timeout on mobile Safari" -d "Users report being logged out after 5 minutes on iOS Safari. Affects conversion flow." -p P1 -l bug,mobile,auth
+
+bd create "Add dark mode toggle to settings" -d "Multiple user requests for dark mode. Should respect system preference by default." -p P2 -l feature,ux,settings
+
+bd create "Update API docs for v2 endpoints" -d "New endpoints from last sprint are undocumented. Blocking external integrations." -p P1 -l docs,api,tech-debt
+
+bd create "Explore caching for dashboard queries" -d "Dashboard load times averaging 3s. Consider Redis or query optimization." -p P3 -l perf,backend,idea
+```
+
+## SKIPPED
+
+- "Make everything faster" - too vague, not actionable
+- "The design looks nice" - not an action item
+- "Fix the bug" - insufficient detail to create issue
+
+# INPUT
+
+INPUT: