chore(release): Update version to v1.4.299

chore: upgrade ollama dependency from v0.9.0 to v0.11.7

.vscode/settings.json

@@ -25,6 +25,7 @@
 		"danielmiessler",
 		"davidanson",
 		"Debugf",
+		"debuglog",
 		"dedup",
 		"deepseek",
 		"Despina",
@@ -55,6 +56,7 @@
 		"godotenv",
 		"gofmt",
 		"goimports",
+		"golint",
 		"gomod",
 		"gonic",
 		"goopenai",
@@ -99,6 +101,7 @@
 		"mbed",
 		"metacharacters",
 		"Miessler",
+		"mpga",
 		"nometa",
 		"numpy",
 		"ollama",
@@ -130,7 +133,9 @@
 		"seaborn",
 		"semgrep",
 		"sess",
+		"sgaunet",
 		"shellquote",
+		"SSEHTTP",
 		"storer",
 		"Streamlit",
 		"stretchr",

CHANGELOG.md

@@ -1,5 +1,118 @@
 # Changelog
 
+## v1.4.299 (2025-08-27)
+
+### PR [#1731](https://github.com/danielmiessler/Fabric/pull/1731) by [ksylvan](https://github.com/ksylvan): chore: upgrade ollama dependency from v0.9.0 to v0.11.7
+
+- Updated ollama package from version 0.9.0 to 0.11.7
+- Fixed 8 security vulnerabilities including 5 high-severity CVEs that could cause denial of service attacks
+- Patched Ollama server vulnerabilities related to division by zero errors and memory exhaustion
+- Resolved security flaws that allowed malicious GGUF model file uploads to crash the server
+- Enhanced system stability and security posture through comprehensive dependency upgrade
+
+## v1.4.298 (2025-08-27)
+
+### PR [#1730](https://github.com/danielmiessler/Fabric/pull/1730) by [ksylvan](https://github.com/ksylvan): Modernize Dockerfile with Best Practices Implementation
+
+- Remove docker-test framework and simplify production docker setup by eliminating complex testing infrastructure
+- Delete entire docker-test directory including test runner scripts and environment configuration files
+- Implement multi-stage build optimization in production Dockerfile to improve build efficiency
+- Remove docker-compose.yml and start-docker.sh helper scripts to streamline container workflow
+- Update README documentation with cleaner Docker usage instructions and reduced image size benefits
+
+## v1.4.297 (2025-08-26)
+
+### PR [#1729](https://github.com/danielmiessler/Fabric/pull/1729) by [ksylvan](https://github.com/ksylvan): Add GitHub Community Health Documents
+
+- Add CODE_OF_CONDUCT defining respectful, collaborative community behavior
+- Add CONTRIBUTING with setup, testing, PR, changelog requirements
+- Add SECURITY policy with reporting process and response timelines
+- Add SUPPORT guide for bugs, features, discussions, expectations
+- Add docs README indexing guides, quick starts, contributor essentials
+
+## v1.4.296 (2025-08-26)
+
+### PR [#1728](https://github.com/danielmiessler/Fabric/pull/1728) by [ksylvan](https://github.com/ksylvan): Refactor Logging System to Use Centralized Debug Logger
+
+- Replace fmt.Fprintf/os.Stderr with centralized debuglog.Log across CLI and add unconditional Log function for important messages
+- Improve OAuth flow messaging and token refresh diagnostics with better error handling
+- Update tests to capture debuglog output via SetOutput for better test coverage
+- Convert Perplexity streaming errors to unified debug logging and emit file write notifications through debuglog
+- Standardize extension registry warnings and announce large audio processing steps via centralized logger
+
+## v1.4.295 (2025-08-24)
+
+### PR [#1727](https://github.com/danielmiessler/Fabric/pull/1727) by [ksylvan](https://github.com/ksylvan): Standardize Anthropic Beta Failure Logging
+
+- Refactor: route Anthropic beta failure logs through internal debug logger
+- Replace fmt.Fprintf stderr with debuglog.Debug for beta failures
+- Import internal log package and remove os dependency
+- Standardize logging level to debuglog.Basic for beta errors
+- Preserve fallback stream behavior when beta features fail
+
+## v1.4.294 (2025-08-20)
+
+### PR [#1723](https://github.com/danielmiessler/Fabric/pull/1723) by [ksylvan](https://github.com/ksylvan): docs: update README with Venice AI provider and Windows install script
+
+- Add Venice AI provider configuration with API endpoint
+- Document Venice AI as privacy-first open-source provider
+- Include PowerShell installation script for Windows users
+- Add debug levels section to table of contents
+- Update recent major features with v1.4.294 release notes
+
+## v1.4.293 (2025-08-19)
+
+### PR [#1718](https://github.com/danielmiessler/Fabric/pull/1718) by [ksylvan](https://github.com/ksylvan): Implement Configurable Debug Logging Levels
+
+- Add --debug flag controlling runtime logging verbosity levels
+- Introduce internal/log package with Off, Basic, Detailed, Trace
+- Replace ad-hoc Debugf and globals with centralized debug logger
+- Wire debug level during early CLI argument parsing
+- Add bash, zsh, fish completions for --debug levels
+
+## v1.4.292 (2025-08-18)
+
+### PR [#1717](https://github.com/danielmiessler/Fabric/pull/1717) by [ksylvan](https://github.com/ksylvan): Highlight default vendor/model in model listing
+
+- Update PrintWithVendor signature to accept default vendor and model
+- Mark default vendor/model with asterisk in non-shell output
+- Compare vendor and model case-insensitively when marking
+- Pass registry defaults to PrintWithVendor from CLI
+- Add test ensuring default selection appears with asterisk
+### Direct commits
+
+- Docs: update version number in README updates section from v1.4.290 to v1.4.291
+
+## v1.4.291 (2025-08-18)
+
+### PR [#1715](https://github.com/danielmiessler/Fabric/pull/1715) by [ksylvan](https://github.com/ksylvan): feat: add speech-to-text via OpenAI with transcription flags and comp…
+
+- Add --transcribe-file flag to transcribe audio or video
+- Add --transcribe-model flag with model listing and completion
+- Add --split-media-file flag to chunk files over 25MB
+- Implement OpenAI transcription using Whisper and GPT-4o Transcribe
+- Integrate transcription pipeline into CLI before readability processing
+
+## v1.4.290 (2025-08-17)
+
+### PR [#1714](https://github.com/danielmiessler/Fabric/pull/1714) by [ksylvan](https://github.com/ksylvan): feat: add per-pattern model mapping support via environment variables
+
+- Add per-pattern model mapping support via environment variables
+- Implement environment variable lookup for pattern-specific models
+- Support vendor|model format in environment variable specification
+- Enable shell startup file configuration for patterns
+- Transform pattern names to uppercase environment variable format
+
+## v1.4.289 (2025-08-16)
+
+### PR [#1710](https://github.com/danielmiessler/Fabric/pull/1710) by [ksylvan](https://github.com/ksylvan): feat: add --no-variable-replacement flag to disable pattern variable …
+
+- Add --no-variable-replacement flag to disable pattern variable substitution
+- Introduce CLI flag to skip pattern variable replacement and wire it into domain request and session builder
+- Provide PatternsEntity.GetWithoutVariables for input-only pattern processing support
+- Refactor patterns code into reusable load and apply helpers
+- Update bash, zsh, fish completions with new flag and document in README and CLI help output
+
 ## v1.4.288 (2025-08-16)
 
 ### PR [#1709](https://github.com/danielmiessler/Fabric/pull/1709) by [ksylvan](https://github.com/ksylvan): Enhanced YouTube Subtitle Language Fallback Handling

README.md

@@ -57,6 +57,8 @@ Below are the **new features and capabilities** we've added (newest first):
 
 ### Recent Major Features
 
+- [v1.4.294](https://github.com/danielmiessler/fabric/releases/tag/v1.4.294) (Aug 20, 2025) — **Venice AI Support**: Added the Venice AI provider. Venice is a Privacy-First, Open-Source AI provider. See their ["About Venice"](https://docs.venice.ai/overview/about-venice) page for details.
+- [v1.4.291](https://github.com/danielmiessler/fabric/releases/tag/v1.4.291) (Aug 18, 2025) — **Speech To Text**: Add OpenAI speech-to-text support with `--transcribe-file`, `--transcribe-model`, and `--split-media-file` flags.
 - [v1.4.287](https://github.com/danielmiessler/fabric/releases/tag/v1.4.287) (Aug 16, 2025) — **AI Reasoning**: Add Thinking to Gemini models and introduce `readme_updates` python script
 - [v1.4.286](https://github.com/danielmiessler/fabric/releases/tag/v1.4.286) (Aug 14, 2025) — **AI Reasoning**: Introduce Thinking Config Across Anthropic and OpenAI Providers
 - [v1.4.285](https://github.com/danielmiessler/fabric/releases/tag/v1.4.285) (Aug 13, 2025) — **Extended Context**: Enable One Million Token Context Beta Feature for Sonnet-4
@@ -127,6 +129,7 @@ Keep in mind that many of these were recorded when Fabric was Python-based, so r
     - [From Source](#from-source)
     - [Environment Variables](#environment-variables)
     - [Setup](#setup)
+    - [Per-Pattern Model Mapping](#per-pattern-model-mapping)
     - [Add aliases for all patterns](#add-aliases-for-all-patterns)
       - [Save your files in markdown using aliases](#save-your-files-in-markdown-using-aliases)
     - [Migration](#migration)
@@ -137,6 +140,7 @@ Keep in mind that many of these were recorded when Fabric was Python-based, so r
       - [Bash Completion](#bash-completion)
       - [Fish Completion](#fish-completion)
   - [Usage](#usage)
+    - [Debug Levels](#debug-levels)
   - [Our approach to prompting](#our-approach-to-prompting)
   - [Examples](#examples)
   - [Just use the Patterns](#just-use-the-patterns)
@@ -207,6 +211,17 @@ To install Fabric, you can use the latest release binaries or install it from th
 
 `https://github.com/danielmiessler/fabric/releases/latest/download/fabric-windows-amd64.exe`
 
+Or via PowerShell, just copy and paste and run the following snippet to install the binary into `{HOME}\.local\bin`. Please make sure that directory is included in your `PATH`.
+
+```powershell
+$ErrorActionPreference = "Stop"
+$LATEST="https://github.com/danielmiessler/fabric/releases/latest/download/fabric-windows-amd64.exe"
+$DIR="${HOME}\.local\bin"
+New-Item -Path $DIR -ItemType Directory -Force
+Invoke-WebRequest -URI  "${LATEST}" -outfile "${DIR}\fabric.exe"
+& "${DIR}\fabric.exe" /version
+```
+
 #### macOS (arm64)
 
 `curl -L https://github.com/danielmiessler/fabric/releases/latest/download/fabric-darwin-arm64 > fabric && chmod +x fabric && ./fabric --version`
@@ -284,6 +299,13 @@ fabric --setup
 
 If everything works you are good to go.
 
+### Per-Pattern Model Mapping
+
+ You can configure specific models for individual patterns using environment variables
+ like `FABRIC_MODEL_PATTERN_NAME=vendor|model`
+
+ This makes it easy to maintain these per-pattern model mappings in your shell startup files.
+
 ### Add aliases for all patterns
 
 In order to add aliases for all your patterns and use them directly as commands ie. `summarize` instead of `fabric --pattern summarize`
@@ -591,6 +613,7 @@ Application Options:
       --printsession=               Print session
       --readability                 Convert HTML input into a clean, readable view
       --input-has-vars              Apply variables to user input
+      --no-variable-replacement     Disable pattern variable replacement
       --dry-run                     Show what would be sent to the model without actually sending it
       --serve                       Serve the Fabric Rest API
       --serveOllama                 Serve the Fabric Rest API with ollama endpoints
@@ -626,10 +649,20 @@ Application Options:
       --yt-dlp-args=                Additional arguments to pass to yt-dlp (e.g. '--cookies-from-browser brave')
       --thinking=                   Set reasoning/thinking level (e.g., off, low, medium, high, or
                                     numeric tokens for Anthropic or Google Gemini)
+      --debug=                     Set debug level (0: off, 1: basic, 2: detailed, 3: trace)
 Help Options:
   -h, --help                        Show this help message
 ```
 
+### Debug Levels
+
+Use the `--debug` flag to control runtime logging:
+
+- `0`: off (default)
+- `1`: basic debug info
+- `2`: detailed debugging
+- `3`: trace level
+
 ## Our approach to prompting
 
 Fabric _Patterns_ are different than most prompts you'll see.
@@ -639,7 +672,7 @@ Fabric _Patterns_ are different than most prompts you'll see.
 Here's an example of a Fabric Pattern.
 
 ```bash
-https://github.com/danielmiessler/fabric/blob/main/patterns/extract_wisdom/system.md
+https://github.com/danielmiessler/Fabric/blob/main/data/patterns/extract_wisdom/system.md
 ```
 
 <img width="1461" alt="pattern-example" src="https://github.com/danielmiessler/fabric/assets/50654/b910c551-9263-405f-9735-71ca69bbab6d">

cmd/fabric/version.go

@@ -1,3 +1,3 @@
 package main
 
-var version = "v1.4.288"
+var version = "v1.4.299"

completions/_fabric

@@ -59,6 +59,13 @@ _fabric_gemini_voices() {
   compadd -X "Gemini TTS Voices:" ${voices}
 }
 
+_fabric_transcription_models() {
+  local -a models
+  local cmd=${words[1]}
+  models=(${(f)"$($cmd --list-transcription-models --shell-complete-list 2>/dev/null)"})
+  compadd -X "Transcription Models:" ${models}
+}
+
 _fabric() {
   local curcontext="$curcontext" state line
   typeset -A opt_args
@@ -107,6 +114,7 @@ _fabric() {
     '(--printsession)--printsession[Print session]:session:_fabric_sessions' \
     '(--readability)--readability[Convert HTML input into a clean, readable view]' \
     '(--input-has-vars)--input-has-vars[Apply variables to user input]' \
+    '(--no-variable-replacement)--no-variable-replacement[Disable pattern variable replacement]' \
     '(--dry-run)--dry-run[Show what would be sent to the model without actually sending it]' \
     '(--serve)--serve[Serve the Fabric Rest API]' \
     '(--serveOllama)--serveOllama[Serve the Fabric Rest API with ollama endpoints]' \
@@ -134,6 +142,10 @@ _fabric() {
     '(--think-start-tag)--think-start-tag[Start tag for thinking sections (default: <think>)]:start tag:' \
     '(--think-end-tag)--think-end-tag[End tag for thinking sections (default: </think>)]:end tag:' \
     '(--disable-responses-api)--disable-responses-api[Disable OpenAI Responses API (default: false)]' \
+    '(--transcribe-file)--transcribe-file[Audio or video file to transcribe]:audio file:_files -g "*.mp3 *.mp4 *.mpeg *.mpga *.m4a *.wav *.webm"' \
+    '(--transcribe-model)--transcribe-model[Model to use for transcription (separate from chat model)]:transcribe model:_fabric_transcription_models' \
+    '(--split-media-file)--split-media-file[Split audio/video files larger than 25MB using ffmpeg]' \
+    '(--debug)--debug[Set debug level (0=off, 1=basic, 2=detailed, 3=trace)]:debug level:(0 1 2 3)' \
     '(--notification)--notification[Send desktop notification when command completes]' \
     '(--notification-command)--notification-command[Custom command to run for notifications]:notification command:' \
     '(-h --help)'{-h,--help}'[Show this help message]' \

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 --vendor -V --modelContextLength --output -o --output-session --latest -n --changeDefaultModel -d --youtube -y --playlist --transcript --transcript-with-timestamps --comments --metadata --yt-dlp-args --language -g --scrape_url -u --scrape_question -q --seed -e --thinking --wipecontext -w --wipesession -W --printcontext --printsession --readability --input-has-vars --dry-run --serve --serveOllama --address --api-key --config --search --search-location --image-file --image-size --image-quality --image-compression --image-background --suppress-think --think-start-tag --think-end-tag --disable-responses-api --voice --list-gemini-voices --notification --notification-command --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 --vendor -V --modelContextLength --output -o --output-session --latest -n --changeDefaultModel -d --youtube -y --playlist --transcript --transcript-with-timestamps --comments --metadata --yt-dlp-args --language -g --scrape_url -u --scrape_question -q --seed -e --thinking --wipecontext -w --wipesession -W --printcontext --printsession --readability --input-has-vars --no-variable-replacement --dry-run --serve --serveOllama --address --api-key --config --search --search-location --image-file --image-size --image-quality --image-compression --image-background --suppress-think --think-start-tag --think-end-tag --disable-responses-api --transcribe-file --transcribe-model --split-media-file --voice --list-gemini-voices --notification --notification-command --debug --version --listextensions --addextension --rmextension --strategy --liststrategies --listvendors --shell-complete-list --help -h"
 
   # Helper function for dynamic completions
   _fabric_get_list() {
@@ -74,8 +74,16 @@ _fabric() {
     COMPREPLY=($(compgen -W "$(_fabric_get_list --list-gemini-voices)" -- "${cur}"))
     return 0
     ;;
+  --transcribe-model)
+    COMPREPLY=($(compgen -W "$(_fabric_get_list --list-transcription-models)" -- "${cur}"))
+    return 0
+    ;;
+  --debug)
+    COMPREPLY=($(compgen -W "0 1 2 3" -- "${cur}"))
+    return 0
+    ;;
   # Options requiring file/directory paths
-  -a | --attachment | -o | --output | --config | --addextension | --image-file)
+  -a | --attachment | -o | --output | --config | --addextension | --image-file | --transcribe-file)
     _filedir
     return 0
     ;;

completions/fabric.fish

@@ -47,6 +47,11 @@ function __fabric_get_gemini_voices
         $cmd --list-gemini-voices --shell-complete-list 2>/dev/null
 end
 
+function __fabric_get_transcription_models
+        set cmd (commandline -opc)[1]
+        $cmd --list-transcription-models --shell-complete-list 2>/dev/null
+end
+
 # Main completion function
 function __fabric_register_completions
         set cmd $argv[1]
@@ -92,6 +97,9 @@ function __fabric_register_completions
         complete -c $cmd -l think-start-tag -d "Start tag for thinking sections (default: <think>)"
         complete -c $cmd -l think-end-tag -d "End tag for thinking sections (default: </think>)"
         complete -c $cmd -l voice -d "TTS voice name for supported models (e.g., Kore, Charon, Puck)" -a "(__fabric_get_gemini_voices)"
+        complete -c $cmd -l transcribe-file -d "Audio or video file to transcribe" -r -a "*.mp3 *.mp4 *.mpeg *.mpga *.m4a *.wav *.webm"
+        complete -c $cmd -l transcribe-model -d "Model to use for transcription (separate from chat model)" -a "(__fabric_get_transcription_models)"
+        complete -c $cmd -l debug -d "Set debug level (0=off, 1=basic, 2=detailed, 3=trace)" -a "0 1 2 3"
         complete -c $cmd -l notification-command -d "Custom command to run for notifications (overrides built-in notifications)"
 
         # Boolean flags (no arguments)
@@ -113,8 +121,9 @@ function __fabric_register_completions
         complete -c $cmd -l metadata -d "Output video metadata"
         complete -c $cmd -l yt-dlp-args -d "Additional arguments to pass to yt-dlp (e.g. '--cookies-from-browser brave')"
         complete -c $cmd -l readability -d "Convert HTML input into a clean, readable view"
-        complete -c $cmd -l input-has-vars -d "Apply variables to user input"
-        complete -c $cmd -l dry-run -d "Show what would be sent to the model without actually sending it"
+       complete -c $cmd -l input-has-vars -d "Apply variables to user input"
+       complete -c $cmd -l no-variable-replacement -d "Disable pattern variable replacement"
+       complete -c $cmd -l dry-run -d "Show what would be sent to the model without actually sending it"
         complete -c $cmd -l search -d "Enable web search tool for supported models (Anthropic, OpenAI, Gemini)"
         complete -c $cmd -l serve -d "Serve the Fabric Rest API"
         complete -c $cmd -l serveOllama -d "Serve the Fabric Rest API with ollama endpoints"
@@ -126,6 +135,7 @@ function __fabric_register_completions
         complete -c $cmd -l shell-complete-list -d "Output raw list without headers/formatting (for shell completion)"
         complete -c $cmd -l suppress-think -d "Suppress text enclosed in thinking tags"
         complete -c $cmd -l disable-responses-api -d "Disable OpenAI Responses API (default: false)"
+        complete -c $cmd -l split-media-file -d "Split audio/video files larger than 25MB using ffmpeg"
         complete -c $cmd -l notification -d "Send desktop notification when command completes"
         complete -c $cmd -s h -l help -d "Show this help message"
 end

docs/CODE_OF_CONDUCT.md

@@ -0,0 +1,26 @@
+# Code of Conduct
+
+## Our Expectation
+
+We expect all contributors and community members to act with basic human decency and common sense.
+
+This project exists to help people augment their capabilities with AI, and we welcome contributions from anyone who shares this mission. We assume good faith and trust that everyone involved is here to build something valuable together.
+
+## Guidelines
+
+- **Be respectful**: Treat others as you'd want to be treated in a professional setting
+- **Be constructive**: Focus on the work and help make the project better
+- **Be collaborative**: We're all working toward the same goal - making Fabric more useful
+- **Use good judgment**: If you're not sure whether something is appropriate, it probably isn't
+
+## Reporting Issues
+
+If someone is being genuinely disruptive or harmful, please email the maintainers directly. We'll address legitimate concerns promptly and fairly.
+
+## Enforcement
+
+Maintainers reserve the right to remove content and restrict access for anyone who consistently acts in bad faith or disrupts the community.
+
+---
+
+*This project assumes contributors are adults who can work together professionally. If you can't do that, this isn't the right place for you.*

docs/CONTRIBUTING.md

@@ -0,0 +1,155 @@
+# Contributing to Fabric
+
+Thanks for contributing to Fabric! Here's what you need to know to get started quickly.
+
+## Quick Setup
+
+### Prerequisites
+
+- Go 1.24+ installed
+- Git configured with your details
+
+### Getting Started
+
+```bash
+# Clone and setup
+git clone https://github.com/danielmiessler/fabric.git
+cd fabric
+go build -o fabric ./cmd/fabric
+./fabric --setup
+
+# Run tests
+go test ./...
+```
+
+## Development Guidelines
+
+### Code Style
+
+- Follow standard Go conventions (`gofmt`, `golint`)
+- Use meaningful variable and function names
+- Write tests for new functionality
+- Keep functions focused and small
+
+### Commit Messages
+
+Use descriptive commit messages:
+
+```text
+feat: add new pattern for code analysis
+fix: resolve OAuth token refresh issue
+docs: update installation instructions
+```
+
+### Project Structure
+
+- `cmd/` - Executable commands
+- `internal/` - Private application code
+- `data/patterns/` - AI patterns
+- `docs/` - Documentation
+
+## Pull Request Process
+
+### Changelog Generation (REQUIRED)
+
+Before submitting your PR, generate a changelog entry:
+
+```bash
+cd cmd/generate_changelog
+go build -o generate_changelog .
+./generate_changelog --incoming-pr YOUR_PR_NUMBER
+```
+
+**Requirements:**
+
+- PR must be open and mergeable
+- Working directory must be clean
+- GitHub token available (GITHUB_TOKEN env var)
+
+**Optional flags:**
+
+- `--ai-summarize` - Enhanced AI-generated summaries
+- `--push` - Auto-push the changelog commit
+
+### PR Guidelines
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Write/update tests
+5. Generate changelog entry (see above)
+6. Submit PR with clear description
+
+### Review Process
+
+- PRs require maintainer review
+- Address feedback promptly
+- Keep PRs focused on single features/fixes
+- Update changelog if you make significant changes
+
+## Testing
+
+### Run Tests
+
+```bash
+# All tests
+go test ./...
+
+# Specific package
+go test ./internal/cli
+
+# With coverage
+go test -cover ./...
+```
+
+### Test Requirements
+
+- Unit tests for core functionality
+- Integration tests for external dependencies
+- Examples in documentation
+
+## Patterns
+
+### Creating Patterns
+
+Patterns go in `data/patterns/[pattern-name]/system.md`:
+
+```markdown
+# IDENTITY and PURPOSE
+You are an expert at...
+
+# STEPS
+- Step 1
+- Step 2
+
+# OUTPUT
+- Output format requirements
+
+# EXAMPLE
+Example output here
+```
+
+### Pattern Guidelines
+
+- Use clear, actionable language
+- Provide specific output formats
+- Include examples when helpful
+- Test with multiple AI providers
+
+## Documentation
+
+- Update README.md for new features
+- Add docs to `docs/` for complex features
+- Include usage examples
+- Keep documentation current
+
+## Getting Help
+
+- Check existing issues first
+- Ask questions in discussions
+- Tag maintainers for urgent issues
+- Be patient - maintainers are volunteers
+
+## License
+
+By contributing, you agree your contributions will be licensed under the MIT License.

docs/README.md

@@ -0,0 +1,88 @@
+# Fabric Documentation
+
+Welcome to the Fabric documentation! This directory contains detailed guides and technical documentation for various features and components of Fabric.
+
+## 📚 Available Documentation
+
+### Core Features
+
+**[Automated-Changelog-Usage.md](./Automated-Changelog-Usage.md)**
+Complete guide for developers on using the automated changelog system. Covers the workflow for generating PR changelog entries during development, including setup, validation, and CI/CD integration.
+
+**[YouTube-Processing.md](./YouTube-Processing.md)**
+Comprehensive guide for processing YouTube videos and playlists with Fabric. Covers transcript extraction, comment processing, metadata retrieval, and advanced yt-dlp configurations.
+
+**[Using-Speech-To-Text.md](./Using-Speech-To-Text.md)**
+Documentation for Fabric's speech-to-text capabilities using OpenAI's Whisper models. Learn how to transcribe audio and video files and process them through Fabric patterns.
+
+### User Interface & Experience
+
+**[Desktop-Notifications.md](./Desktop-Notifications.md)**
+Guide to setting up desktop notifications for Fabric commands. Useful for long-running tasks and multitasking scenarios with cross-platform notification support.
+
+**[Shell-Completions.md](./Shell-Completions.md)**
+Instructions for setting up intelligent tab completion for Fabric in Zsh, Bash, and Fish shells. Includes automated installation and manual setup options.
+
+**[Gemini-TTS.md](./Gemini-TTS.md)**
+Complete guide for using Google Gemini's text-to-speech features with Fabric. Covers voice selection, audio generation, and integration with Fabric patterns.
+
+### Development & Architecture
+
+**[Automated-ChangeLog.md](./Automated-ChangeLog.md)**
+Technical documentation outlining the automated CHANGELOG system architecture for CI/CD integration. Details the infrastructure and workflow for maintainers.
+
+**[Project-Restructured.md](./Project-Restructured.md)**
+Project restructuring plan and architectural decisions. Documents the transition to standard Go conventions and project organization improvements.
+
+**[NOTES.md](./NOTES.md)**
+Development notes on refactoring efforts, model management improvements, and architectural changes. Includes technical details on vendor and model abstraction.
+
+### Audio Resources
+
+**[voices/README.md](./voices/README.md)**
+Index of Gemini TTS voice samples demonstrating different AI voice characteristics available in Fabric.
+
+## 🗂️ Additional Resources
+
+### Configuration Files
+
+- `./notification-config.yaml` - Example notification configuration
+
+### Images
+
+- `images/` - Screenshots and visual documentation assets
+  - `fabric-logo-gif.gif` - Animated Fabric logo
+  - `fabric-summarize.png` - Screenshot of summarization feature
+  - `svelte-preview.png` - Web interface preview
+
+## 🚀 Quick Start
+
+New to Fabric? Start with these essential docs:
+
+1. **[../README.md](../README.md)** - Main project README with installation and basic usage
+2. **[Shell-Completions.md](./Shell-Completions.md)** - Set up tab completion for better CLI experience
+3. **[YouTube-Processing.md](./YouTube-Processing.md)** - Learn one of Fabric's most popular features
+4. **[Desktop-Notifications.md](./Desktop-Notifications.md)** - Get notified when long tasks complete
+
+## 🔧 For Contributors
+
+Contributing to Fabric? These docs are essential:
+
+1. **[./CONTRIBUTING.md](./CONTRIBUTING.md)** - Contribution guidelines and setup
+2. **[Automated-Changelog-Usage.md](./Automated-Changelog-Usage.md)** - Required workflow for PR submissions
+3. **[Project-Restructured.md](./Project-Restructured.md)** - Understanding project architecture
+4. **[NOTES.md](./NOTES.md)** - Current development priorities and patterns
+
+## 📝 Documentation Standards
+
+When adding new documentation:
+
+- Use clear, descriptive filenames
+- Include practical examples and use cases
+- Update this README index with your new docs
+- Follow the established markdown formatting conventions
+- Test all code examples before publication
+
+---
+
+*For general help and support, see [./SUPPORT.md](./SUPPORT.md)*

docs/SECURITY.md

@@ -0,0 +1,158 @@
+# Security Policy
+
+## Supported Versions
+
+We aim to provide security updates for the latest version of Fabric.
+
+We recommend always using the latest version of Fabric for security fixes and improvements.
+
+## Reporting Security Vulnerabilities
+
+**Please DO NOT report security vulnerabilities through public GitHub issues.**
+
+### Preferred Reporting Method
+
+Send security reports directly to: **<kayvan@sylvan.com>** and CC to the project maintainer at **<daniel@danielmiessler.com>**
+
+### What to Include
+
+Please provide the following information:
+
+1. **Vulnerability Type**: What kind of security issue (e.g., injection, authentication bypass, etc.)
+2. **Affected Components**: Which parts of Fabric are affected
+3. **Impact Assessment**: What could an attacker accomplish
+4. **Reproduction Steps**: Clear steps to reproduce the vulnerability
+5. **Proposed Fix**: If you have suggestions for remediation
+6. **Disclosure Timeline**: Your preferred timeline for public disclosure
+
+### Example Report Format
+
+```text
+Subject: [SECURITY] Brief description of vulnerability
+
+Vulnerability Type: SQL Injection
+Affected Component: Pattern database queries
+Impact: Potential data exposure
+Severity: High
+
+Reproduction Steps:
+1. Navigate to...
+2. Submit payload: ...
+3. Observe...
+
+Evidence:
+[Screenshots, logs, or proof of concept]
+
+Suggested Fix:
+Use parameterized queries instead of string concatenation...
+```
+
+## Security Considerations
+
+### API Keys and Secrets
+
+- Never commit API keys to the repository
+- Store secrets in environment variables or secure configuration
+- Use the built-in setup process for key management
+- Regularly rotate API keys
+
+### Input Validation
+
+- All user inputs are validated before processing
+- Special attention to pattern definitions and user content
+- URL validation for web scraping features
+
+### AI Provider Integration
+
+- Secure communication with AI providers (HTTPS/TLS)
+- Token handling follows provider best practices
+- No sensitive data logged or cached unencrypted
+
+### Network Security
+
+- Web server endpoints properly authenticated when required
+- CORS policies appropriately configured
+- Rate limiting implemented where necessary
+
+## Vulnerability Response Process
+
+1. **Report Received**: We'll acknowledge receipt within 24 hours
+2. **Initial Assessment**: We'll evaluate severity and impact within 72 hours
+3. **Investigation**: We'll investigate and develop fixes
+4. **Fix Development**: We'll create and test patches
+5. **Coordinated Disclosure**: We'll work with reporter on disclosure timeline
+6. **Release**: We'll release patched version with security advisory
+
+### Timeline Expectations
+
+- **Critical**: 1-7 days
+- **High**: 7-30 days
+- **Medium**: 30-90 days
+- **Low**: Next scheduled release
+
+## Bug Bounty
+
+We don't currently offer a formal bug bounty program, but we deeply appreciate security research and will:
+
+- Acknowledge contributors in release notes
+- Provide credit in security advisories
+- Consider swag or small rewards for significant findings
+
+## Security Best Practices for Users
+
+### Installation
+
+- Download Fabric only from official sources
+- Verify checksums when available
+- Keep installations up to date
+
+### Configuration
+
+- Use strong, unique API keys
+- Don't share configuration files containing secrets
+- Set appropriate file permissions on config directories
+
+### Usage
+
+- Be cautious with patterns that process sensitive data
+- Review AI provider terms for data handling
+- Consider using local models for sensitive content
+
+## Known Security Limitations
+
+### AI Provider Dependencies
+
+Fabric relies on external AI providers. Security depends partly on:
+
+- Provider security practices
+- Data transmission security
+- Provider data handling policies
+
+### Pattern Execution
+
+Custom patterns could potentially:
+
+- Process sensitive inputs inappropriately
+- Generate outputs containing sensitive information
+- Be used for adversarial prompt injection
+
+**Recommendation**: Review patterns carefully, especially those from untrusted sources.
+
+## Security Updates
+
+Security updates are distributed through:
+
+- GitHub Releases with security tags
+- Security advisories on GitHub
+- Project documentation updates
+
+Subscribe to the repository to receive notifications about security updates.
+
+## Contact
+
+For non-security issues, please use GitHub issues.
+For security concerns, email: **<kayvan@sylvan.com>** and CC to **<daniel@danielmiessler.com>**
+
+---
+
+*We take security seriously and appreciate the security research community's help in keeping Fabric secure.*

docs/SUPPORT.md

@@ -0,0 +1,148 @@
+# Support
+
+## Getting Help with Fabric
+
+Need help with Fabric? Here are the best ways to get assistance:
+
+## 📖 Documentation First
+
+Before reaching out, check these resources:
+
+- **[README.md](../README.md)** - Installation, usage, and examples
+- **[docs/](./README.md)** - Detailed documentation
+- **[Patterns](../data/patterns/)** - Browse available AI patterns
+
+## 🐛 Bug Reports
+
+Found a bug? Please create an issue:
+
+**[Report a Bug](https://github.com/danielmiessler/fabric/issues/new?template=bug.yml)**
+
+Include:
+
+- Fabric version (`fabric --version`)
+- Operating system
+- Steps to reproduce
+- Expected vs actual behavior
+- Error messages/logs
+
+## 💡 Feature Requests
+
+Have an idea for Fabric? We'd love to hear it:
+
+**[Request a Feature](https://github.com/danielmiessler/fabric/issues/new)**
+
+Describe:
+
+- What you want to achieve
+- Why it would be useful
+- How you envision it working
+- Any alternatives you've considered
+
+## 🤔 Questions & Discussions
+
+For general questions, usage help, or community discussion:
+
+**[GitHub Discussions](https://github.com/danielmiessler/fabric/discussions)**
+
+Great for:
+
+- "How do I...?" questions
+- Sharing patterns you've created
+- Getting community advice
+- Feature brainstorming
+
+## 🏷️ Issue Labels
+
+When creating issues, maintainers will add appropriate labels:
+
+- `bug` - Something isn't working
+- `enhancement` - New feature request
+- `documentation` - Documentation improvements
+- `help wanted` - Community contributions welcome
+- `good first issue` - Great for new contributors
+- `question` - General questions
+- `pattern` - Related to AI patterns
+
+## 📋 Issue Templates
+
+We provide templates to help you create detailed reports:
+
+- **Bug Report** - Structured bug reporting
+- **Feature Request** - Detailed feature proposals
+- **Pattern Submission** - New pattern contributions
+
+## 🔒 Security Issues
+
+**DO NOT create public issues for security vulnerabilities.**
+
+See our [Security Policy](./SECURITY.md) for proper reporting procedures.
+
+## ⚡ Response Times
+
+We're a community-driven project with volunteer maintainers:
+
+- **Bugs**: We aim to acknowledge within 48 hours
+- **Features**: Response time varies based on complexity
+- **Questions**: Community often responds quickly
+- **Security**: See security policy for timelines
+
+## 🛠️ Self-Help Tips
+
+Before creating an issue, try:
+
+1. **Update Fabric**: `go install github.com/danielmiessler/fabric/cmd/fabric@latest`
+2. **Check existing issues**: Someone might have the same problem
+3. **Run setup**: `fabric --setup` can fix configuration issues
+4. **Test minimal example**: Isolate the problem
+
+## 🤝 Community Guidelines
+
+When asking for help:
+
+- Be specific and provide context
+- Include relevant details and error messages
+- Be patient - maintainers are volunteers
+- Help others when you can
+- Say thanks when someone helps you
+
+## 📞 Emergency Contact
+
+For urgent security issues only:
+
+- Email: <security@fabric.ai> (if available)
+- Maintainer: <daniel@danielmiessler.com>
+
+## 🎯 What We Can Help With
+
+✅ **We can help with:**
+
+- Installation and setup issues
+- Usage questions and examples
+- Bug reports and fixes
+- Feature discussions
+- Pattern creation guidance
+- Integration questions
+
+❌ **We cannot help with:**
+
+- Custom development for your specific use case
+- Troubleshooting your specific AI provider issues
+- General AI or programming tutorials
+- Commercial support agreements
+
+## 💪 Contributing Back
+
+The best way to get help is to help others:
+
+- Answer questions in discussions
+- Improve documentation
+- Share useful patterns
+- Report bugs clearly
+- Review pull requests
+
+See our [Contributing Guide](./CONTRIBUTING.md) for details.
+
+---
+
+*Remember: We're all here to make Fabric better. Be kind, be helpful, and let's build something amazing together!*

docs/Using-Speech-To-Text.md

@@ -0,0 +1,139 @@
+# Using Speech-To-Text (STT) with Fabric
+
+Fabric supports speech-to-text transcription of audio and video files using OpenAI's transcription models. This feature allows you to convert spoken content into text that can then be processed through Fabric's patterns.
+
+## Overview
+
+The STT feature integrates OpenAI's Whisper and GPT-4o transcription models to convert audio/video files into text. The transcribed text is automatically passed as input to your chosen pattern or chat session.
+
+## Requirements
+
+- OpenAI API key configured in Fabric
+- For files larger than 25MB: `ffmpeg` installed on your system
+- Supported audio/video formats: `.mp3`, `.mp4`, `.mpeg`, `.mpga`, `.m4a`, `.wav`, `.webm`
+
+## Basic Usage
+
+### Simple Transcription
+
+To transcribe an audio file and send the result to a pattern:
+
+```bash
+fabric --transcribe-file /path/to/audio.mp3 --transcribe-model whisper-1 --pattern summarize
+```
+
+### Transcription Only
+
+To just transcribe a file without applying a pattern:
+
+```bash
+fabric --transcribe-file /path/to/audio.mp3 --transcribe-model whisper-1
+```
+
+## Command Line Flags
+
+### Required Flags
+
+- `--transcribe-file`: Path to the audio or video file to transcribe
+- `--transcribe-model`: Model to use for transcription (required when using transcription)
+
+### Optional Flags
+
+- `--split-media-file`: Automatically split files larger than 25MB into chunks using ffmpeg
+
+## Available Models
+
+You can list all available transcription models with:
+
+```bash
+fabric --list-transcription-models
+```
+
+Currently supported models:
+
+- `whisper-1`: OpenAI's Whisper model
+- `gpt-4o-mini-transcribe`: GPT-4o Mini transcription model
+- `gpt-4o-transcribe`: GPT-4o transcription model
+
+## File Size Handling
+
+### Files Under 25MB
+
+Files under the 25MB limit are processed directly without any special handling.
+
+### Files Over 25MB
+
+For files exceeding OpenAI's 25MB limit, you have two options:
+
+1. **Manual handling**: The command will fail with an error message suggesting to use `--split-media-file`
+2. **Automatic splitting**: Use the `--split-media-file` flag to automatically split the file into chunks
+
+```bash
+fabric --transcribe-file large_recording.mp4 --transcribe-model whisper-1 --split-media-file --pattern summarize
+```
+
+When splitting is enabled:
+
+- Fabric uses `ffmpeg` to split the file into 10-minute segments initially
+- If segments are still too large, it reduces the segment time by half repeatedly
+- All segments are transcribed and the results are concatenated
+- Temporary files are automatically cleaned up after processing
+
+## Integration with Patterns
+
+The transcribed text is seamlessly integrated into Fabric's workflow:
+
+1. File is transcribed using the specified model
+2. Transcribed text becomes the input message
+3. Text is sent to the specified pattern or chat session
+
+### Example Workflows
+
+**Meeting transcription and summarization:**
+
+```bash
+fabric --transcribe-file meeting.mp4 --transcribe-model gpt-4o-transcribe --pattern summarize
+```
+
+**Interview analysis:**
+
+```bash
+fabric --transcribe-file interview.mp3 --transcribe-model whisper-1 --pattern extract_insights
+```
+
+**Large video file processing:**
+
+```bash
+fabric --transcribe-file presentation.mp4 --transcribe-model gpt-4o-transcribe --split-media-file --pattern create_summary
+```
+
+## Error Handling
+
+Common error scenarios:
+
+- **Unsupported format**: Only the listed audio/video formats are supported
+- **File too large**: Use `--split-media-file` for files over 25MB
+- **Missing ffmpeg**: Install ffmpeg for automatic file splitting
+- **Invalid model**: Use `--list-transcription-models` to see available models
+- **Missing model**: The `--transcribe-model` flag is required when using `--transcribe-file`
+
+## Technical Details
+
+### Implementation
+
+- Transcription is handled in `internal/cli/transcribe.go:14`
+- OpenAI-specific implementation in `internal/plugins/ai/openai/openai_audio.go:41`
+- File splitting uses ffmpeg with configurable segment duration
+- Supports any vendor that implements the `transcriber` interface
+
+### Processing Pipeline
+
+1. CLI validates file format and size
+2. If file > 25MB and splitting enabled, file is split using ffmpeg
+3. Each file/segment is sent to OpenAI's transcription API
+4. Results are concatenated with spaces between segments
+5. Transcribed text is passed as input to the main Fabric pipeline
+
+### Vendor Support
+
+Currently, only OpenAI is supported for transcription, but the interface allows for future expansion to other vendors that provide transcription capabilities.

go.mod

@@ -21,7 +21,7 @@ require (
 	github.com/joho/godotenv v1.5.1
 	github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51
 	github.com/mattn/go-sqlite3 v1.14.28
-	github.com/ollama/ollama v0.9.0
+	github.com/ollama/ollama v0.11.7
 	github.com/openai/openai-go v1.8.2
 	github.com/otiai10/copy v1.14.1
 	github.com/pkg/errors v0.9.1

go.sum

@@ -180,8 +180,8 @@ github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
-github.com/ollama/ollama v0.9.0 h1:GvdGhi8G/QMnFrY0TMLDy1bXua+Ify8KTkFe4ZY/OZs=
-github.com/ollama/ollama v0.9.0/go.mod h1:aio9yQ7nc4uwIbn6S0LkGEPgn8/9bNQLL1nHuH+OcD0=
+github.com/ollama/ollama v0.11.7 h1:CuYjaJ/YEnvLDpJocJbbVdpdVFyGA/OP6lKFyzZD4dI=
+github.com/ollama/ollama v0.11.7/go.mod h1:9+1//yWPsDE2u+l1a5mpaKrYw4VdnSsRU3ioq5BvMms=
 github.com/onsi/gomega v1.34.1 h1:EUMJIKUjM8sKjYbtxQI9A4z2o+rruxnzNvpknOXie6k=
 github.com/onsi/gomega v1.34.1/go.mod h1:kU1QgUvBDLXBJq618Xvm2LUX6rSAfRaFRTcdOeDLwwY=
 github.com/openai/openai-go v1.8.2 h1:UqSkJ1vCOPUpz9Ka5tS0324EJFEuOvMc+lA/EarJWP8=

internal/cli/chat.go

@@ -9,6 +9,7 @@ import (
 
 	"github.com/danielmiessler/fabric/internal/core"
 	"github.com/danielmiessler/fabric/internal/domain"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins/db/fsdb"
 	"github.com/danielmiessler/fabric/internal/tools/notifications"
 )
@@ -18,6 +19,19 @@ func handleChatProcessing(currentFlags *Flags, registry *core.PluginRegistry, me
 	if messageTools != "" {
 		currentFlags.AppendMessage(messageTools)
 	}
+	// Check for pattern-specific model via environment variable
+	if currentFlags.Pattern != "" && currentFlags.Model == "" {
+		envVar := "FABRIC_MODEL_" + strings.ToUpper(strings.ReplaceAll(currentFlags.Pattern, "-", "_"))
+		if modelSpec := os.Getenv(envVar); modelSpec != "" {
+			parts := strings.SplitN(modelSpec, "|", 2)
+			if len(parts) == 2 {
+				currentFlags.Vendor = parts[0]
+				currentFlags.Model = parts[1]
+			} else {
+				currentFlags.Model = modelSpec
+			}
+		}
+	}
 
 	var chatter *core.Chatter
 	if chatter, err = registry.GetChatter(currentFlags.Model, currentFlags.ModelContextLength,
@@ -122,7 +136,7 @@ func handleChatProcessing(currentFlags *Flags, registry *core.PluginRegistry, me
 	if chatOptions.Notification {
 		if err = sendNotification(chatOptions, chatReq.PatternName, result); err != nil {
 			// Log notification error but don't fail the main command
-			fmt.Fprintf(os.Stderr, "Failed to send notification: %v\n", err)
+			debuglog.Log("Failed to send notification: %v\n", err)
 		}
 	}
 

internal/cli/cli.go

@@ -3,10 +3,10 @@ package cli
 import (
 	"encoding/json"
 	"fmt"
-	"os"
 	"strings"
 
 	"github.com/danielmiessler/fabric/internal/core"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/openai"
 	"github.com/danielmiessler/fabric/internal/tools/converter"
 	"github.com/danielmiessler/fabric/internal/tools/youtube"
@@ -34,7 +34,7 @@ func Cli(version string) (err error) {
 	var registry, err2 = initializeFabric()
 	if err2 != nil {
 		if !currentFlags.Setup {
-			fmt.Fprintln(os.Stderr, err2.Error())
+			debuglog.Log("%s\n", err2.Error())
 			currentFlags.Setup = true
 		}
 		// Return early if registry is nil to prevent panics in subsequent handlers
@@ -74,6 +74,15 @@ func Cli(version string) (err error) {
 		return
 	}
 
+	// Handle transcription if specified
+	if currentFlags.TranscribeFile != "" {
+		var transcriptionMessage string
+		if transcriptionMessage, err = handleTranscription(currentFlags, registry); err != nil {
+			return
+		}
+		currentFlags.Message = AppendMessage(currentFlags.Message, transcriptionMessage)
+	}
+
 	// Process HTML readability if needed
 	if currentFlags.HtmlReadability {
 		if msg, cleanErr := converter.HtmlReadability(currentFlags.Message); cleanErr != nil {

internal/cli/flags.go

@@ -13,6 +13,7 @@ import (
 
 	"github.com/danielmiessler/fabric/internal/chat"
 	"github.com/danielmiessler/fabric/internal/domain"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/util"
 	"github.com/jessevdk/go-flags"
 	"golang.org/x/text/language"
@@ -66,6 +67,7 @@ type Flags struct {
 	PrintSession                    string               `long:"printsession" description:"Print session"`
 	HtmlReadability                 bool                 `long:"readability" description:"Convert HTML input into a clean, readable view"`
 	InputHasVars                    bool                 `long:"input-has-vars" description:"Apply variables to user input"`
+	NoVariableReplacement           bool                 `long:"no-variable-replacement" description:"Disable pattern variable replacement"`
 	DryRun                          bool                 `long:"dry-run" description:"Show what would be sent to the model without actually sending it"`
 	Serve                           bool                 `long:"serve" description:"Serve the Fabric Rest API"`
 	ServeOllama                     bool                 `long:"serveOllama" description:"Serve the Fabric Rest API with ollama endpoints"`
@@ -91,23 +93,21 @@ type Flags struct {
 	ThinkStartTag                   string               `long:"think-start-tag" yaml:"thinkStartTag" description:"Start tag for thinking sections" default:"<think>"`
 	ThinkEndTag                     string               `long:"think-end-tag" yaml:"thinkEndTag" description:"End tag for thinking sections" default:"</think>"`
 	DisableResponsesAPI             bool                 `long:"disable-responses-api" yaml:"disableResponsesAPI" description:"Disable OpenAI Responses API (default: false)"`
+	TranscribeFile                  string               `long:"transcribe-file" yaml:"transcribeFile" description:"Audio or video file to transcribe"`
+	TranscribeModel                 string               `long:"transcribe-model" yaml:"transcribeModel" description:"Model to use for transcription (separate from chat model)"`
+	SplitMediaFile                  bool                 `long:"split-media-file" yaml:"splitMediaFile" description:"Split audio/video files larger than 25MB using ffmpeg"`
 	Voice                           string               `long:"voice" yaml:"voice" description:"TTS voice name for supported models (e.g., Kore, Charon, Puck)" default:"Kore"`
 	ListGeminiVoices                bool                 `long:"list-gemini-voices" description:"List all available Gemini TTS voices"`
+	ListTranscriptionModels         bool                 `long:"list-transcription-models" description:"List all available transcription models"`
 	Notification                    bool                 `long:"notification" yaml:"notification" description:"Send desktop notification when command completes"`
 	NotificationCommand             string               `long:"notification-command" yaml:"notificationCommand" description:"Custom command to run for notifications (overrides built-in notifications)"`
 	Thinking                        domain.ThinkingLevel `long:"thinking" yaml:"thinking" description:"Set reasoning/thinking level (e.g., off, low, medium, high, or numeric tokens for Anthropic or Google Gemini)"`
-}
-
-var debug = false
-
-func Debugf(format string, a ...interface{}) {
-	if debug {
-		fmt.Printf("DEBUG: "+format, a...)
-	}
+	Debug                           int                  `long:"debug" description:"Set debug level (0=off, 1=basic, 2=detailed, 3=trace)" default:"0"`
 }
 
 // Init Initialize flags. returns a Flags struct and an error
 func Init() (ret *Flags, err error) {
+	debuglog.SetLevel(debuglog.LevelFromInt(parseDebugLevel(os.Args[1:])))
 	// Track which yaml-configured flags were set on CLI
 	usedFlags := make(map[string]bool)
 	yamlArgsScan := os.Args[1:]
@@ -123,11 +123,11 @@ func Init() (ret *Flags, err error) {
 			shortTag := field.Tag.Get("short")
 			if longTag != "" {
 				flagToYamlTag[longTag] = yamlTag
-				Debugf("Mapped long flag %s to yaml tag %s\n", longTag, yamlTag)
+				debuglog.Debug(debuglog.Detailed, "Mapped long flag %s to yaml tag %s\n", longTag, yamlTag)
 			}
 			if shortTag != "" {
 				flagToYamlTag[shortTag] = yamlTag
-				Debugf("Mapped short flag %s to yaml tag %s\n", shortTag, yamlTag)
+				debuglog.Debug(debuglog.Detailed, "Mapped short flag %s to yaml tag %s\n", shortTag, yamlTag)
 			}
 		}
 	}
@@ -139,7 +139,7 @@ func Init() (ret *Flags, err error) {
 		if flag != "" {
 			if yamlTag, exists := flagToYamlTag[flag]; exists {
 				usedFlags[yamlTag] = true
-				Debugf("CLI flag used: %s (yaml: %s)\n", flag, yamlTag)
+				debuglog.Debug(debuglog.Detailed, "CLI flag used: %s (yaml: %s)\n", flag, yamlTag)
 			}
 		}
 	}
@@ -151,6 +151,7 @@ func Init() (ret *Flags, err error) {
 	if args, err = parser.Parse(); err != nil {
 		return
 	}
+	debuglog.SetLevel(debuglog.LevelFromInt(ret.Debug))
 
 	// Check to see if a ~/.config/fabric/config.yaml config file exists (only when user didn't specify a config)
 	if ret.Config == "" {
@@ -158,7 +159,7 @@ func Init() (ret *Flags, err error) {
 		if defaultConfigPath, err := util.GetDefaultConfigPath(); err == nil && defaultConfigPath != "" {
 			ret.Config = defaultConfigPath
 		} else if err != nil {
-			Debugf("Could not determine default config path: %v\n", err)
+			debuglog.Debug(debuglog.Detailed, "Could not determine default config path: %v\n", err)
 		}
 	}
 
@@ -183,13 +184,13 @@ func Init() (ret *Flags, err error) {
 					if flagField.CanSet() {
 						if yamlField.Type() != flagField.Type() {
 							if err := assignWithConversion(flagField, yamlField); err != nil {
-								Debugf("Type conversion failed for %s: %v\n", yamlTag, err)
+								debuglog.Debug(debuglog.Detailed, "Type conversion failed for %s: %v\n", yamlTag, err)
 								continue
 							}
 						} else {
 							flagField.Set(yamlField)
 						}
-						Debugf("Applied YAML value for %s: %v\n", yamlTag, yamlField.Interface())
+						debuglog.Debug(debuglog.Detailed, "Applied YAML value for %s: %v\n", yamlTag, yamlField.Interface())
 					}
 				}
 			}
@@ -215,6 +216,22 @@ func Init() (ret *Flags, err error) {
 	return
 }
 
+func parseDebugLevel(args []string) int {
+	for i := 0; i < len(args); i++ {
+		arg := args[i]
+		if arg == "--debug" && i+1 < len(args) {
+			if lvl, err := strconv.Atoi(args[i+1]); err == nil {
+				return lvl
+			}
+		} else if strings.HasPrefix(arg, "--debug=") {
+			if lvl, err := strconv.Atoi(strings.TrimPrefix(arg, "--debug=")); err == nil {
+				return lvl
+			}
+		}
+	}
+	return 0
+}
+
 func extractFlag(arg string) string {
 	var flag string
 	if strings.HasPrefix(arg, "--") {
@@ -284,7 +301,7 @@ func loadYAMLConfig(configPath string) (*Flags, error) {
 		return nil, fmt.Errorf("error parsing config file: %w", err)
 	}
 
-	Debugf("Config: %v\n", config)
+	debuglog.Debug(debuglog.Detailed, "Config: %v\n", config)
 
 	return config, nil
 }
@@ -460,13 +477,14 @@ func (o *Flags) BuildChatOptions() (ret *domain.ChatOptions, err error) {
 
 func (o *Flags) BuildChatRequest(Meta string) (ret *domain.ChatRequest, err error) {
 	ret = &domain.ChatRequest{
-		ContextName:      o.Context,
-		SessionName:      o.Session,
-		PatternName:      o.Pattern,
-		StrategyName:     o.Strategy,
-		PatternVariables: o.PatternVariables,
-		InputHasVars:     o.InputHasVars,
-		Meta:             Meta,
+		ContextName:           o.Context,
+		SessionName:           o.Session,
+		PatternName:           o.Pattern,
+		StrategyName:          o.Strategy,
+		PatternVariables:      o.PatternVariables,
+		InputHasVars:          o.InputHasVars,
+		NoVariableReplacement: o.NoVariableReplacement,
+		Meta:                  Meta,
 	}
 
 	var message *chat.ChatCompletionMessage

internal/cli/listing.go

@@ -5,6 +5,8 @@ import (
 	"os"
 	"strconv"
 
+	openai "github.com/openai/openai-go"
+
 	"github.com/danielmiessler/fabric/internal/core"
 	"github.com/danielmiessler/fabric/internal/plugins/ai"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/gemini"
@@ -39,7 +41,7 @@ func handleListingCommands(currentFlags *Flags, fabricDb *fsdb.Db, registry *cor
 		if currentFlags.ShellCompleteOutput {
 			models.Print(true)
 		} else {
-			models.PrintWithVendor(false)
+			models.PrintWithVendor(false, registry.Defaults.Vendor.Value, registry.Defaults.Model.Value)
 		}
 		return true, nil
 	}
@@ -70,5 +72,30 @@ func handleListingCommands(currentFlags *Flags, fabricDb *fsdb.Db, registry *cor
 		return true, nil
 	}
 
+	if currentFlags.ListTranscriptionModels {
+		listTranscriptionModels(currentFlags.ShellCompleteOutput)
+		return true, nil
+	}
+
 	return false, nil
 }
+
+// listTranscriptionModels lists all available transcription models
+func listTranscriptionModels(shellComplete bool) {
+	models := []string{
+		string(openai.AudioModelWhisper1),
+		string(openai.AudioModelGPT4oMiniTranscribe),
+		string(openai.AudioModelGPT4oTranscribe),
+	}
+
+	if shellComplete {
+		for _, model := range models {
+			fmt.Println(model)
+		}
+	} else {
+		fmt.Println("Available transcription models:")
+		for _, model := range models {
+			fmt.Printf("  %s\n", model)
+		}
+	}
+}

internal/cli/output.go

@@ -7,6 +7,7 @@ import (
 	"strings"
 
 	"github.com/atotto/clipboard"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 )
 
 func CopyToClipboard(message string) (err error) {
@@ -30,7 +31,7 @@ func CreateOutputFile(message string, fileName string) (err error) {
 	if _, err = file.WriteString(message); err != nil {
 		err = fmt.Errorf("error writing to file: %v", err)
 	} else {
-		fmt.Fprintf(os.Stderr, "\n\n[Output also written to %s]\n", fileName)
+		debuglog.Log("\n\n[Output also written to %s]\n", fileName)
 	}
 	return
 }

internal/cli/transcribe.go

@@ -0,0 +1,35 @@
+package cli
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/danielmiessler/fabric/internal/core"
+)
+
+type transcriber interface {
+	TranscribeFile(ctx context.Context, filePath, model string, split bool) (string, error)
+}
+
+func handleTranscription(flags *Flags, registry *core.PluginRegistry) (message string, err error) {
+	vendorName := flags.Vendor
+	if vendorName == "" {
+		vendorName = "OpenAI"
+	}
+	vendor, ok := registry.VendorManager.VendorsByName[vendorName]
+	if !ok {
+		return "", fmt.Errorf("vendor %s not configured", vendorName)
+	}
+	tr, ok := vendor.(transcriber)
+	if !ok {
+		return "", fmt.Errorf("vendor %s does not support audio transcription", vendorName)
+	}
+	model := flags.TranscribeModel
+	if model == "" {
+		return "", fmt.Errorf("transcription model is required (use --transcribe-model)")
+	}
+	if message, err = tr.TranscribeFile(context.Background(), flags.TranscribeFile, model, flags.SplitMediaFile); err != nil {
+		return
+	}
+	return
+}

internal/core/chatter.go

@@ -180,7 +180,7 @@ func (o *Chatter) BuildSession(request *domain.ChatRequest, raw bool) (session *
 	}
 
 	// Now we know request.Message is not nil, process template variables
-	if request.InputHasVars {
+	if request.InputHasVars && !request.NoVariableReplacement {
 		request.Message.Content, err = template.ApplyTemplate(request.Message.Content, request.PatternVariables, "")
 		if err != nil {
 			return nil, err
@@ -190,7 +190,12 @@ func (o *Chatter) BuildSession(request *domain.ChatRequest, raw bool) (session *
 	var patternContent string
 	inputUsed := false
 	if request.PatternName != "" {
-		pattern, err := o.db.Patterns.GetApplyVariables(request.PatternName, request.PatternVariables, request.Message.Content)
+		var pattern *fsdb.Pattern
+		if request.NoVariableReplacement {
+			pattern, err = o.db.Patterns.GetWithoutVariables(request.PatternName, request.Message.Content)
+		} else {
+			pattern, err = o.db.Patterns.GetApplyVariables(request.PatternName, request.PatternVariables, request.Message.Content)
+		}
 
 		if err != nil {
 			return nil, fmt.Errorf("could not get pattern %s: %v", request.PatternName, err)

internal/core/plugin_registry.go

@@ -10,6 +10,7 @@ import (
 	"strconv"
 	"strings"
 
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/anthropic"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/azure"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/bedrock"
@@ -20,7 +21,7 @@ import (
 	"github.com/danielmiessler/fabric/internal/plugins/ai/ollama"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/openai"
 	"github.com/danielmiessler/fabric/internal/plugins/ai/openai_compatible"
-	"github.com/danielmiessler/fabric/internal/plugins/ai/perplexity" // Added Perplexity plugin
+	"github.com/danielmiessler/fabric/internal/plugins/ai/perplexity"
 	"github.com/danielmiessler/fabric/internal/plugins/strategy"
 
 	"github.com/samber/lo"
@@ -339,7 +340,7 @@ func (o *PluginRegistry) GetChatter(model string, modelContextLength int, vendor
 		} else {
 			availableVendors := models.FindGroupsByItem(model)
 			if len(availableVendors) > 1 {
-				fmt.Fprintf(os.Stderr, "Warning: multiple vendors provide model %s: %s. Using %s. Specify --vendor to select a vendor.\n", model, strings.Join(availableVendors, ", "), availableVendors[0])
+				debuglog.Log("Warning: multiple vendors provide model %s: %s. Using %s. Specify --vendor to select a vendor.\n", model, strings.Join(availableVendors, ", "), availableVendors[0])
 			}
 			ret.vendor = vendorManager.FindByName(models.FindGroupsByItemFirst(model))
 		}

internal/core/plugin_registry_test.go

@@ -10,6 +10,7 @@ import (
 
 	"github.com/danielmiessler/fabric/internal/chat"
 	"github.com/danielmiessler/fabric/internal/domain"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins"
 	"github.com/danielmiessler/fabric/internal/plugins/ai"
 	"github.com/danielmiessler/fabric/internal/plugins/db/fsdb"
@@ -72,7 +73,12 @@ func TestGetChatter_WarnsOnAmbiguousModel(t *testing.T) {
 	r, w, _ := os.Pipe()
 	oldStderr := os.Stderr
 	os.Stderr = w
-	defer func() { os.Stderr = oldStderr }()
+	// Redirect log output to our pipe to capture unconditional log messages
+	debuglog.SetOutput(w)
+	defer func() {
+		os.Stderr = oldStderr
+		debuglog.SetOutput(oldStderr)
+	}()
 
 	chatter, err := registry.GetChatter("shared-model", 0, "", "", false, false)
 	w.Close()
@@ -81,8 +87,10 @@ func TestGetChatter_WarnsOnAmbiguousModel(t *testing.T) {
 	if err != nil {
 		t.Fatalf("GetChatter() error = %v", err)
 	}
-	if chatter.vendor.GetName() != "VendorA" {
-		t.Fatalf("expected vendor VendorA, got %s", chatter.vendor.GetName())
+	// Verify that one of the valid vendors was selected (don't care which one due to map iteration randomness)
+	vendorName := chatter.vendor.GetName()
+	if vendorName != "VendorA" && vendorName != "VendorB" {
+		t.Fatalf("expected vendor VendorA or VendorB, got %s", vendorName)
 	}
 	if !strings.Contains(string(warning), "multiple vendors provide model shared-model") {
 		t.Fatalf("expected warning about multiple vendors, got %q", string(warning))

internal/domain/domain.go

@@ -13,15 +13,16 @@ const (
 )
 
 type ChatRequest struct {
-	ContextName      string
-	SessionName      string
-	PatternName      string
-	PatternVariables map[string]string
-	Message          *chat.ChatCompletionMessage
-	Language         string
-	Meta             string
-	InputHasVars     bool
-	StrategyName     string
+	ContextName           string
+	SessionName           string
+	PatternName           string
+	PatternVariables      map[string]string
+	Message               *chat.ChatCompletionMessage
+	Language              string
+	Meta                  string
+	InputHasVars          bool
+	NoVariableReplacement bool
+	StrategyName          string
 }
 
 type ChatOptions struct {

internal/log/log.go

@@ -0,0 +1,78 @@
+package log
+
+import (
+	"fmt"
+	"io"
+	"os"
+	"sync"
+)
+
+// Level represents the debug verbosity.
+type Level int
+
+const (
+	// Off disables all debug output.
+	Off Level = iota
+	// Basic provides minimal debugging information.
+	Basic
+	// Detailed provides more verbose debugging.
+	Detailed
+	// Trace is the most verbose level.
+	Trace
+)
+
+var (
+	mu     sync.RWMutex
+	level  Level     = Off
+	output io.Writer = os.Stderr
+)
+
+// SetLevel sets the global debug level.
+func SetLevel(l Level) {
+	mu.Lock()
+	level = l
+	mu.Unlock()
+}
+
+// LevelFromInt converts an int to a Level.
+func LevelFromInt(i int) Level {
+	switch {
+	case i <= 0:
+		return Off
+	case i == 1:
+		return Basic
+	case i == 2:
+		return Detailed
+	case i >= 3:
+		return Trace
+	default:
+		return Off
+	}
+}
+
+// Debug writes a debug message if the global level permits.
+func Debug(l Level, format string, a ...interface{}) {
+	mu.RLock()
+	current := level
+	w := output
+	mu.RUnlock()
+	if current >= l {
+		fmt.Fprintf(w, "DEBUG: "+format, a...)
+	}
+}
+
+// Log writes a message unconditionally to stderr.
+// This is for important messages that should always be shown regardless of debug level.
+func Log(format string, a ...interface{}) {
+	mu.RLock()
+	w := output
+	mu.RUnlock()
+	fmt.Fprintf(w, format, a...)
+}
+
+// SetOutput allows overriding the output destination for debug logs.
+func SetOutput(w io.Writer) {
+	mu.Lock()
+	output = w
+	mu.Unlock()
+}

internal/plugins/ai/anthropic/anthropic.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"fmt"
 	"net/http"
-	"os"
 	"strconv"
 	"strings"
 
@@ -12,6 +11,7 @@ import (
 	"github.com/anthropics/anthropic-sdk-go/option"
 	"github.com/danielmiessler/fabric/internal/chat"
 	"github.com/danielmiessler/fabric/internal/domain"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins"
 	"github.com/danielmiessler/fabric/internal/util"
 )
@@ -195,7 +195,7 @@ func (an *Client) SendStream(
 	}
 	stream := an.client.Messages.NewStreaming(ctx, params, reqOpts...)
 	if stream.Err() != nil && len(betas) > 0 {
-		fmt.Fprintf(os.Stderr, "Anthropic beta feature %s failed: %v\n", strings.Join(betas, ","), stream.Err())
+		debuglog.Debug(debuglog.Basic, "Anthropic beta feature %s failed: %v\n", strings.Join(betas, ","), stream.Err())
 		stream = an.client.Messages.NewStreaming(ctx, params)
 	}
 
@@ -289,7 +289,7 @@ func (an *Client) Send(ctx context.Context, msgs []*chat.ChatCompletionMessage,
 	}
 	if message, err = an.client.Messages.New(ctx, params, reqOpts...); err != nil {
 		if len(betas) > 0 {
-			fmt.Fprintf(os.Stderr, "Anthropic beta feature %s failed: %v\n", strings.Join(betas, ","), err)
+			debuglog.Debug(debuglog.Basic, "Anthropic beta feature %s failed: %v\n", strings.Join(betas, ","), err)
 			if message, err = an.client.Messages.New(ctx, params); err != nil {
 				return
 			}

internal/plugins/ai/anthropic/oauth.go

@@ -9,11 +9,11 @@ import (
 	"fmt"
 	"io"
 	"net/http"
-	"os"
 	"os/exec"
 	"strings"
 	"time"
 
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/util"
 	"golang.org/x/oauth2"
 )
@@ -77,7 +77,7 @@ func (t *OAuthTransport) getValidToken(tokenIdentifier string) (string, error) {
 	}
 	// If no token exists, run OAuth flow
 	if token == nil {
-		fmt.Fprintln(os.Stderr, "No OAuth token found, initiating authentication...")
+		debuglog.Log("No OAuth token found, initiating authentication...\n")
 		newAccessToken, err := RunOAuthFlow(tokenIdentifier)
 		if err != nil {
 			return "", fmt.Errorf("failed to authenticate: %w", err)
@@ -87,11 +87,11 @@ func (t *OAuthTransport) getValidToken(tokenIdentifier string) (string, error) {
 
 	// Check if token needs refresh (5 minute buffer)
 	if token.IsExpired(5) {
-		fmt.Fprintln(os.Stderr, "OAuth token expired, refreshing...")
+		debuglog.Log("OAuth token expired, refreshing...\n")
 		newAccessToken, err := RefreshToken(tokenIdentifier)
 		if err != nil {
 			// If refresh fails, try re-authentication
-			fmt.Fprintln(os.Stderr, "Token refresh failed, re-authenticating...")
+			debuglog.Log("Token refresh failed, re-authenticating...\n")
 			newAccessToken, err = RunOAuthFlow(tokenIdentifier)
 			if err != nil {
 				return "", fmt.Errorf("failed to refresh or re-authenticate: %w", err)
@@ -143,13 +143,13 @@ func RunOAuthFlow(tokenIdentifier string) (token string, err error) {
 		if err == nil && existingToken != nil {
 			// If token exists but is expired, try refreshing first
 			if existingToken.IsExpired(5) {
-				fmt.Fprintln(os.Stderr, "Found expired OAuth token, attempting refresh...")
+				debuglog.Log("Found expired OAuth token, attempting refresh...\n")
 				refreshedToken, refreshErr := RefreshToken(tokenIdentifier)
 				if refreshErr == nil {
-					fmt.Fprintln(os.Stderr, "Token refresh successful")
+					debuglog.Log("Token refresh successful\n")
 					return refreshedToken, nil
 				}
-				fmt.Fprintf(os.Stderr, "Token refresh failed (%v), proceeding with full OAuth flow...\n", refreshErr)
+				debuglog.Log("Token refresh failed (%v), proceeding with full OAuth flow...\n", refreshErr)
 			} else {
 				// Token exists and is still valid
 				return existingToken.AccessToken, nil
@@ -176,10 +176,10 @@ func RunOAuthFlow(tokenIdentifier string) (token string, err error) {
 		oauth2.SetAuthURLParam("state", verifier),
 	)
 
-	fmt.Fprintln(os.Stderr, "Open the following URL in your browser. Fabric would like to authorize:")
-	fmt.Fprintln(os.Stderr, authURL)
+	debuglog.Log("Open the following URL in your browser. Fabric would like to authorize:\n")
+	debuglog.Log("%s\n", authURL)
 	openBrowser(authURL)
-	fmt.Fprint(os.Stderr, "Paste the authorization code here: ")
+	debuglog.Log("Paste the authorization code here: ")
 	var code string
 	fmt.Scanln(&code)
 	parts := strings.SplitN(code, "#", 2)

internal/plugins/ai/models.go

@@ -18,7 +18,8 @@ type VendorsModels struct {
 
 // PrintWithVendor prints models including their vendor on each line.
 // When shellCompleteList is true, output is suitable for shell completion.
-func (o *VendorsModels) PrintWithVendor(shellCompleteList bool) {
+// Default vendor and model are highlighted with an asterisk.
+func (o *VendorsModels) PrintWithVendor(shellCompleteList bool, defaultVendor, defaultModel string) {
 	if !shellCompleteList {
 		fmt.Printf("\n%v:\n", o.SelectionLabel)
 	}
@@ -42,7 +43,11 @@ func (o *VendorsModels) PrintWithVendor(shellCompleteList bool) {
 			if shellCompleteList {
 				fmt.Printf("%s|%s\n", groupItems.Group, item)
 			} else {
-				fmt.Printf("\t[%d]\t%s|%s\n", currentItemIndex, groupItems.Group, item)
+				mark := "       "
+				if strings.EqualFold(groupItems.Group, defaultVendor) && strings.EqualFold(item, defaultModel) {
+					mark = "      *"
+				}
+				fmt.Printf("%s\t[%d]\t%s|%s\n", mark, currentItemIndex, groupItems.Group, item)
 			}
 		}
 	}

internal/plugins/ai/models_test.go

@@ -1,6 +1,9 @@
 package ai
 
 import (
+	"io"
+	"os"
+	"strings"
 	"testing"
 )
 
@@ -31,3 +34,23 @@ func TestFindVendorsByModel(t *testing.T) {
 		t.Fatalf("FindVendorsByModel() = %v, want %v", foundVendors, []string{"vendor1"})
 	}
 }
+
+func TestPrintWithVendorMarksDefault(t *testing.T) {
+	vendors := NewVendorsModels()
+	vendors.AddGroupItems("vendor1", []string{"model1"}...)
+	vendors.AddGroupItems("vendor2", []string{"model2"}...)
+
+	r, w, _ := os.Pipe()
+	oldStdout := os.Stdout
+	os.Stdout = w
+
+	vendors.PrintWithVendor(false, "vendor2", "model2")
+
+	w.Close()
+	os.Stdout = oldStdout
+	out, _ := io.ReadAll(r)
+
+	if !strings.Contains(string(out), "      *\t[2]\tvendor2|model2") {
+		t.Fatalf("default model not marked: %s", out)
+	}
+}

internal/plugins/ai/openai/openai_audio.go

@@ -0,0 +1,153 @@
+package openai
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"slices"
+	"sort"
+	"strings"
+
+	debuglog "github.com/danielmiessler/fabric/internal/log"
+
+	openai "github.com/openai/openai-go"
+)
+
+// MaxAudioFileSize defines the maximum allowed size for audio uploads (25MB).
+const MaxAudioFileSize int64 = 25 * 1024 * 1024
+
+// AllowedTranscriptionModels lists the models supported for transcription.
+var AllowedTranscriptionModels = []string{
+	string(openai.AudioModelWhisper1),
+	string(openai.AudioModelGPT4oMiniTranscribe),
+	string(openai.AudioModelGPT4oTranscribe),
+}
+
+// allowedAudioExtensions defines the supported input file extensions.
+var allowedAudioExtensions = map[string]struct{}{
+	".mp3":  {},
+	".mp4":  {},
+	".mpeg": {},
+	".mpga": {},
+	".m4a":  {},
+	".wav":  {},
+	".webm": {},
+}
+
+// TranscribeFile transcribes the given audio file using the specified model. If the file
+// exceeds the size limit, it can optionally be split into chunks using ffmpeg.
+func (o *Client) TranscribeFile(ctx context.Context, filePath, model string, split bool) (string, error) {
+	if ctx == nil {
+		ctx = context.Background()
+	}
+
+	if !slices.Contains(AllowedTranscriptionModels, model) {
+		return "", fmt.Errorf("model '%s' is not supported for transcription", model)
+	}
+
+	ext := strings.ToLower(filepath.Ext(filePath))
+	if _, ok := allowedAudioExtensions[ext]; !ok {
+		return "", fmt.Errorf("unsupported audio format '%s'", ext)
+	}
+
+	info, err := os.Stat(filePath)
+	if err != nil {
+		return "", err
+	}
+
+	var files []string
+	var cleanup func()
+	if info.Size() > MaxAudioFileSize {
+		if !split {
+			return "", fmt.Errorf("file %s exceeds 25MB limit; use --split-media-file to enable automatic splitting", filePath)
+		}
+		debuglog.Log("File %s is larger than the size limit... breaking it up into chunks...\n", filePath)
+		if files, cleanup, err = splitAudioFile(filePath, ext, MaxAudioFileSize); err != nil {
+			return "", err
+		}
+		defer cleanup()
+	} else {
+		files = []string{filePath}
+	}
+
+	var builder strings.Builder
+	for i, f := range files {
+		debuglog.Log("Using model %s to transcribe part %d (file name: %s)...\n", model, i+1, f)
+		var chunk *os.File
+		if chunk, err = os.Open(f); err != nil {
+			return "", err
+		}
+		params := openai.AudioTranscriptionNewParams{
+			File:  chunk,
+			Model: openai.AudioModel(model),
+		}
+		var resp *openai.Transcription
+		resp, err = o.ApiClient.Audio.Transcriptions.New(ctx, params)
+		chunk.Close()
+		if err != nil {
+			return "", err
+		}
+		if i > 0 {
+			builder.WriteString(" ")
+		}
+		builder.WriteString(resp.Text)
+	}
+
+	return builder.String(), nil
+}
+
+// splitAudioFile splits the source file into chunks smaller than maxSize using ffmpeg.
+// It returns the list of chunk file paths and a cleanup function.
+func splitAudioFile(src, ext string, maxSize int64) (files []string, cleanup func(), err error) {
+	if _, err = exec.LookPath("ffmpeg"); err != nil {
+		return nil, nil, fmt.Errorf("ffmpeg not found: please install it")
+	}
+
+	var dir string
+	if dir, err = os.MkdirTemp("", "fabric-audio-*"); err != nil {
+		return nil, nil, err
+	}
+	cleanup = func() { os.RemoveAll(dir) }
+
+	segmentTime := 600 // start with 10 minutes
+	for {
+		pattern := filepath.Join(dir, "chunk-%03d"+ext)
+		debuglog.Log("Running ffmpeg to split audio into %d-second chunks...\n", segmentTime)
+		cmd := exec.Command("ffmpeg", "-y", "-i", src, "-f", "segment", "-segment_time", fmt.Sprintf("%d", segmentTime), "-c", "copy", pattern)
+		var stderr bytes.Buffer
+		cmd.Stderr = &stderr
+		if err = cmd.Run(); err != nil {
+			return nil, cleanup, fmt.Errorf("ffmpeg failed: %v: %s", err, stderr.String())
+		}
+
+		if files, err = filepath.Glob(filepath.Join(dir, "chunk-*"+ext)); err != nil {
+			return nil, cleanup, err
+		}
+		sort.Strings(files)
+
+		tooBig := false
+		for _, f := range files {
+			var info os.FileInfo
+			if info, err = os.Stat(f); err != nil {
+				return nil, cleanup, err
+			}
+			if info.Size() > maxSize {
+				tooBig = true
+				break
+			}
+		}
+		if !tooBig {
+			return files, cleanup, nil
+		}
+		for _, f := range files {
+			_ = os.Remove(f)
+		}
+		if segmentTime <= 1 {
+			return nil, cleanup, fmt.Errorf("unable to split file into acceptable size chunks")
+		}
+		segmentTime /= 2
+	}
+}

internal/plugins/ai/openai_compatible/providers_config.go

@@ -102,6 +102,11 @@ var ProviderMap = map[string]ProviderConfig{
 		BaseURL:             "https://api.together.xyz/v1",
 		ImplementsResponses: false,
 	},
+	"Venice AI": {
+		Name:                "Venice AI",
+		BaseURL:             "https://api.venice.ai/api/v1",
+		ImplementsResponses: false,
+	},
 }
 
 // GetProviderByName returns the provider configuration for a given name with O(1) lookup

internal/plugins/ai/perplexity/perplexity.go

@@ -4,9 +4,10 @@ import (
 	"context"
 	"fmt"
 	"os"
-	"sync" // Added sync package
+	"sync"
 
 	"github.com/danielmiessler/fabric/internal/domain"
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins"
 	perplexity "github.com/sgaunet/perplexity-go/v2"
 
@@ -171,7 +172,7 @@ func (c *Client) SendStream(msgs []*chat.ChatCompletionMessage, opts *domain.Cha
 		if err != nil {
 			// Log error, can't send to string channel directly.
 			// Consider a mechanism to propagate this error if needed.
-			fmt.Fprintf(os.Stderr, "perplexity streaming error: %v\\n", err) // Corrected capitalization
+			debuglog.Log("perplexity streaming error: %v\n", err)
 			// If the error occurs during stream setup, the channel might not have been closed by the receiver loop.
 			// However, closing it here might cause a panic if the receiver loop also tries to close it.
 			// close(channel) // Caution: Uncommenting this may cause panic, as channel is closed in the receiver goroutine.

internal/plugins/ai/vendors.go

@@ -148,7 +148,6 @@ func (o *VendorsManager) setupVendorTo(vendor Vendor, configuredVendors map[stri
 		delete(configuredVendors, vendor.GetName())
 		fmt.Printf("[%v] skipped\n", vendor.GetName())
 	}
-	return
 }
 
 type modelResult struct {

internal/plugins/db/fsdb/patterns.go

@@ -31,6 +31,27 @@ type Pattern struct {
 func (o *PatternsEntity) GetApplyVariables(
 	source string, variables map[string]string, input string) (pattern *Pattern, err error) {
 
+	if pattern, err = o.loadPattern(source); err != nil {
+		return
+	}
+
+	err = o.applyVariables(pattern, variables, input)
+	return
+}
+
+// GetWithoutVariables returns a pattern with only the {{input}} placeholder processed
+// and skips template variable replacement
+func (o *PatternsEntity) GetWithoutVariables(source, input string) (pattern *Pattern, err error) {
+
+	if pattern, err = o.loadPattern(source); err != nil {
+		return
+	}
+
+	o.applyInput(pattern, input)
+	return
+}
+
+func (o *PatternsEntity) loadPattern(source string) (pattern *Pattern, err error) {
 	// Determine if this is a file path
 	isFilePath := strings.HasPrefix(source, "\\") ||
 		strings.HasPrefix(source, "/") ||
@@ -39,8 +60,8 @@ func (o *PatternsEntity) GetApplyVariables(
 
 	if isFilePath {
 		// Resolve the file path using GetAbsolutePath
-		absPath, err := util.GetAbsolutePath(source)
-		if err != nil {
+		var absPath string
+		if absPath, err = util.GetAbsolutePath(source); err != nil {
 			return nil, fmt.Errorf("could not resolve file path: %v", err)
 		}
 
@@ -51,26 +72,27 @@ func (o *PatternsEntity) GetApplyVariables(
 		pattern, err = o.getFromDB(source)
 	}
 
-	if err != nil {
-		return
-	}
-
-	// Apply variables to the pattern
-	err = o.applyVariables(pattern, variables, input)
 	return
 }
 
-func (o *PatternsEntity) applyVariables(
-	pattern *Pattern, variables map[string]string, input string) (err error) {
-
-	// Ensure pattern has an {{input}} placeholder
-	// If not present, append it on a new line
+func (o *PatternsEntity) ensureInput(pattern *Pattern) {
 	if !strings.Contains(pattern.Pattern, "{{input}}") {
 		if !strings.HasSuffix(pattern.Pattern, "\n") {
 			pattern.Pattern += "\n"
 		}
 		pattern.Pattern += "{{input}}"
 	}
+}
+
+func (o *PatternsEntity) applyInput(pattern *Pattern, input string) {
+	o.ensureInput(pattern)
+	pattern.Pattern = strings.ReplaceAll(pattern.Pattern, "{{input}}", input)
+}
+
+func (o *PatternsEntity) applyVariables(
+	pattern *Pattern, variables map[string]string, input string) (err error) {
+
+	o.ensureInput(pattern)
 
 	// Temporarily replace {{input}} with a sentinel token to protect it
 	// from recursive variable resolution

internal/plugins/db/fsdb/patterns_test.go

@@ -145,6 +145,22 @@ func TestGetApplyVariables(t *testing.T) {
 	}
 }
 
+func TestGetWithoutVariables(t *testing.T) {
+	entity, cleanup := setupTestPatternsEntity(t)
+	defer cleanup()
+
+	createTestPattern(t, entity, "test-pattern", "Prefix {{input}} {{roam}}")
+
+	result, err := entity.GetWithoutVariables("test-pattern", "hello")
+	require.NoError(t, err)
+	assert.Equal(t, "Prefix hello {{roam}}", result.Pattern)
+
+	createTestPattern(t, entity, "no-input", "Static content")
+	result, err = entity.GetWithoutVariables("no-input", "hi")
+	require.NoError(t, err)
+	assert.Equal(t, "Static content\nhi", result.Pattern)
+}
+
 func TestPatternsEntity_Save(t *testing.T) {
 	entity, cleanup := setupTestPatternsEntity(t)
 	defer cleanup()

internal/plugins/template/extension_registry.go

@@ -10,8 +10,9 @@ import (
 	"strings"
 	"time"
 
+	debuglog "github.com/danielmiessler/fabric/internal/log"
+
 	"gopkg.in/yaml.v3"
-	// Add this import
 )
 
 // ExtensionDefinition represents a single extension configuration
@@ -87,9 +88,7 @@ func NewExtensionRegistry(configDir string) *ExtensionRegistry {
 	r.ensureConfigDir()
 
 	if err := r.loadRegistry(); err != nil {
-		if Debug {
-			fmt.Printf("Warning: could not load extension registry: %v\n", err)
-		}
+		debuglog.Log("Warning: could not load extension registry: %v\n", err)
 	}
 
 	return r

internal/plugins/template/template.go

@@ -6,6 +6,8 @@ import (
 	"path/filepath"
 	"regexp"
 	"strings"
+
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 )
 
 var (
@@ -14,7 +16,6 @@ var (
 	filePlugin     = &FilePlugin{}
 	fetchPlugin    = &FetchPlugin{}
 	sysPlugin      = &SysPlugin{}
-	Debug          = false // Debug flag
 )
 
 var extensionManager *ExtensionManager
@@ -33,9 +34,7 @@ var pluginPattern = regexp.MustCompile(`\{\{plugin:([^:]+):([^:]+)(?::([^}]+))?\
 var extensionPattern = regexp.MustCompile(`\{\{ext:([^:]+):([^:]+)(?::([^}]+))?\}\}`)
 
 func debugf(format string, a ...interface{}) {
-	if Debug {
-		fmt.Printf(format, a...)
-	}
+	debuglog.Debug(debuglog.Trace, format, a...)
 }
 
 func ApplyTemplate(content string, variables map[string]string, input string) (string, error) {

internal/tools/patterns_loader.go

@@ -7,6 +7,7 @@ import (
 	"sort"
 	"strings"
 
+	debuglog "github.com/danielmiessler/fabric/internal/log"
 	"github.com/danielmiessler/fabric/internal/plugins"
 	"github.com/danielmiessler/fabric/internal/plugins/db/fsdb"
 	"github.com/danielmiessler/fabric/internal/tools/githelper"
@@ -335,9 +336,9 @@ func (o *PatternsLoader) createUniquePatternsFile() (err error) {
 					patternNamesMap[entry.Name()] = true
 				}
 			}
-			fmt.Fprintf(os.Stderr, "📂 Also included patterns from custom directory: %s\n", o.Patterns.CustomPatternsDir)
+			debuglog.Log("📂 Also included patterns from custom directory: %s\n", o.Patterns.CustomPatternsDir)
 		} else {
-			fmt.Fprintf(os.Stderr, "Warning: Could not read custom patterns directory %s: %v\n", o.Patterns.CustomPatternsDir, customErr)
+			debuglog.Log("Warning: Could not read custom patterns directory %s: %v\n", o.Patterns.CustomPatternsDir, customErr)
 		}
 	}
 

nix/pkgs/fabric/gomod2nix.toml

@@ -224,8 +224,8 @@ schema = 3
     version = "v1.0.2"
     hash = "sha256-+W9EIW7okXIXjWEgOaMh58eLvBZ7OshW2EhaIpNLSBU="
   [mod."github.com/ollama/ollama"]
-    version = "v0.9.0"
-    hash = "sha256-r2eU+kMG3tuJy2B43RXsfmeltzM9t05NEmNiJAW5qr4="
+    version = "v0.11.7"
+    hash = "sha256-3Wn1JWmil0aQQ2I/r398HbnUsi8ADoroqNyPziuxn/c="
   [mod."github.com/openai/openai-go"]
     version = "v1.8.2"
     hash = "sha256-O8aV3zEj6o8kIlzlkYaTW4RzvwR3qNUBYiN8SuTM1R0="

nix/pkgs/fabric/version.nix

@@ -1 +1 @@
-"1.4.288"
+"1.4.299"

scripts/docker-test/README.md

@@ -1,116 +0,0 @@
-# Docker Test Environment for API Configuration Fix
-
-This directory contains a Docker-based testing setup for fixing the issue where Fabric calls Ollama and Bedrock APIs even when not configured. This addresses the problem where unconfigured services show error messages during model listing.
-
-## Quick Start
-
-```bash
-# Run all tests
-./scripts/docker-test/test-runner.sh
-
-# Interactive mode - pick which test to run
-./scripts/docker-test/test-runner.sh -i
-
-# Run specific test case
-./scripts/docker-test/test-runner.sh gemini-only
-
-# Shell into test environment
-./scripts/docker-test/test-runner.sh -s gemini-only
-
-# Build image only (for development)
-./scripts/docker-test/test-runner.sh -b
-
-# Show help
-./scripts/docker-test/test-runner.sh -h
-```
-
-## Test Cases
-
-1. **no-config**: No APIs configured
-2. **gemini-only**: Only Gemini configured (reproduces original issue #1195)
-3. **openai-only**: Only OpenAI configured
-4. **ollama-only**: Only Ollama configured
-5. **bedrock-only**: Only Bedrock configured
-6. **mixed**: Multiple APIs configured (Gemini + OpenAI + Ollama)
-
-## Environment Files
-
-Each test case has a corresponding environment file in `scripts/docker-test/env/`:
-
-- `env.no-config` - Empty configuration
-- `env.gemini-only` - Only Gemini API key
-- `env.openai-only` - Only OpenAI API key
-- `env.ollama-only` - Only Ollama URL
-- `env.bedrock-only` - Only Bedrock configuration
-- `env.mixed` - Multiple API configurations
-
-These files are volume-mounted into the Docker container and persist changes made with `fabric -S`.
-
-## Interactive Mode & Shell Access
-
-The interactive mode (`-i`) provides several options:
-
-```text
-Available test cases:
-
-1) No APIs configured (no-config)
-2) Only Gemini configured (gemini-only)
-3) Only OpenAI configured (openai-only)
-4) Only Ollama configured (ollama-only)
-5) Only Bedrock configured (bedrock-only)
-6) Mixed configuration (mixed)
-7) Run all tests
-0) Exit
-
-Add '!' after number to shell into test environment (e.g., '1!' to shell into no-config)
-```
-
-### Shell Mode
-
-- Use `1!`, `2!`, etc. to shell into any test environment
-- Run `fabric -S` to configure APIs interactively
-- Run `fabric --listmodels` or `fabric -L` to test model listing
-- Changes persist in the environment files
-- Type `exit` to return to test runner
-
-## Expected Results
-
-**Before Fix:**
-
-- `no-config` and `gemini-only` tests show Ollama connection errors
-- Tests show Bedrock authentication errors when BEDROCK_AWS_REGION not set
-- Error: `Ollama Get "http://localhost:11434/api/tags": dial tcp...`
-- Error: `Bedrock failed to list foundation models...`
-
-**After Fix:**
-
-- Clean output with no error messages for unconfigured services
-- Only configured services appear in model listings
-- Ollama only initialized when `OLLAMA_API_URL` is set
-- Bedrock only initialized when `BEDROCK_AWS_REGION` is set
-
-## Implementation Details
-
-- **Volume-mounted configs**: Environment files are mounted to `/home/testuser/.config/fabric/.env`
-- **Persistent state**: Configuration changes survive between test runs
-- **Single Docker image**: Built once from `scripts/docker-test/base/Dockerfile`, reused for all tests
-- **Isolated environments**: Each test uses its own environment file
-- **Cross-platform**: Works on macOS, Linux, and Windows with Docker
-
-## Development Workflow
-
-1. Make code changes to fix API initialization logic
-2. Run `./scripts/docker-test/test-runner.sh no-config` to test the main issue
-3. Use `./scripts/docker-test/test-runner.sh -i` for interactive testing
-4. Shell into environments (`1!`, `2!`, etc.) to debug specific configurations
-5. Run all tests before submitting PR: `./scripts/docker-test/test-runner.sh`
-
-## Architecture
-
-The fix involves:
-
-1. **Ollama**: Override `IsConfigured()` method to check for `OLLAMA_API_URL` env var
-2. **Bedrock**: Modify `hasAWSCredentials()` to require `BEDROCK_AWS_REGION`
-3. **Plugin Registry**: Only initialize providers when properly configured
-
-This prevents unnecessary API calls and eliminates confusing error messages for users.

scripts/docker-test/base/Dockerfile

@@ -1,30 +0,0 @@
-FROM golang:1.24-alpine AS builder
-
-WORKDIR /app
-COPY go.mod go.sum ./
-RUN go mod download
-
-COPY ./cmd/fabric ./cmd/fabric
-COPY ./internal ./internal
-RUN go build -o fabric ./cmd/fabric
-
-FROM alpine:latest
-RUN apk --no-cache add ca-certificates
-
-# Create a test user
-RUN adduser -D -s /bin/sh testuser
-
-# Switch to test user
-USER testuser
-WORKDIR /home/testuser
-
-# Set environment variables for the test user
-ENV HOME=/home/testuser
-ENV USER=testuser
-
-COPY --from=builder /app/fabric .
-
-# Create fabric config directory and empty .env file
-RUN mkdir -p .config/fabric && touch .config/fabric/.env
-
-ENTRYPOINT ["./fabric"]

scripts/docker-test/test-runner.sh

@@ -1,235 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-# Get the directory where this script is located
-top_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-base_name="$(basename "$top_dir")"
-cd "$top_dir"/../.. || exit 1
-
-# Check if bash version supports associative arrays
-if [[ ${BASH_VERSION%%.*} -lt 4 ]]; then
-    echo "This script requires bash 4.0 or later for associative arrays."
-    echo "Current version: $BASH_VERSION"
-    exit 1
-fi
-
-IMAGE_NAME="fabric-test-setup"
-ENV_DIR="scripts/${base_name}/env"
-
-# Test case descriptions
-declare -A test_descriptions=(
-    ["no-config"]="No APIs configured"
-    ["gemini-only"]="Only Gemini configured (reproduces original issue)"
-    ["openai-only"]="Only OpenAI configured"
-    ["ollama-only"]="Only Ollama configured"
-    ["bedrock-only"]="Only Bedrock configured"
-    ["mixed"]="Mixed configuration (Gemini + OpenAI + Ollama)"
-)
-
-# Test case order for consistent display
-test_order=("no-config" "gemini-only" "openai-only" "ollama-only" "bedrock-only" "mixed")
-
-build_image() {
-    echo "=== Building Docker image ==="
-    docker build -f "${top_dir}/base/Dockerfile" -t "$IMAGE_NAME" .
-    echo
-}
-
-check_env_file() {
-    local test_name="$1"
-    local env_file="$ENV_DIR/env.$test_name"
-
-    if [[ ! -f "$env_file" ]]; then
-        echo "Error: Environment file not found: $env_file"
-        exit 1
-    fi
-}
-
-run_test() {
-    local test_name="$1"
-    local description="${test_descriptions[$test_name]}"
-    local env_file="$ENV_DIR/env.$test_name"
-
-    check_env_file "$test_name"
-
-    echo "===================="
-    echo "Test: $description"
-    echo "Config: $test_name"
-    echo "Env file: $env_file"
-    echo "===================="
-
-    echo "Running test..."
-    if docker run --rm \
-        -e HOME=/home/testuser \
-        -e USER=testuser \
-        -v "$(pwd)/$env_file:/home/testuser/.config/fabric/.env:ro" \
-        "$IMAGE_NAME" --listmodels 2>&1; then
-        echo "✅ Test completed"
-    else
-        echo "❌ Test failed"
-    fi
-    echo
-}
-
-shell_into_env() {
-    local test_name="$1"
-    local description="${test_descriptions[$test_name]}"
-    local env_file="$ENV_DIR/env.$test_name"
-
-    check_env_file "$test_name"
-
-    echo "===================="
-    echo "Shelling into: $description"
-    echo "Config: $test_name"
-    echo "Env file: $env_file"
-    echo "===================="
-    echo "You can now run 'fabric -S' to configure, or 'fabric --listmodels' or 'fabric -L' to test."
-    echo "Changes to .env will persist in $env_file"
-    echo "Type 'exit' to return to the test runner."
-    echo
-
-    docker run -it --rm \
-        -e HOME=/home/testuser \
-        -e USER=testuser \
-        -v "$(pwd)/$env_file:/home/testuser/.config/fabric/.env" \
-        --entrypoint=/bin/sh \
-        "$IMAGE_NAME"
-}
-
-interactive_mode() {
-    echo "=== Interactive Mode ==="
-    echo "Available test cases:"
-    echo
-    local i=1
-    local cases=()
-    for test_name in "${test_order[@]}"; do
-        echo "$i) ${test_descriptions[$test_name]} ($test_name)"
-        cases[i]="$test_name"
-        ((i++))
-    done
-    echo "$i) Run all tests"
-    echo "0) Exit"
-    echo
-    echo "Add '!' after number to shell into test environment (e.g., '1!' to shell into no-config)"
-    echo
-
-    while true; do
-        read -r -p "Select test case (0-$i) [or 1!, etc. to shell into test environment]: " choice
-
-        # Check for shell mode (! suffix)
-        local shell_mode=false
-        if [[ "$choice" == *"!" ]]; then
-            shell_mode=true
-            choice="${choice%!}"  # Remove the ! suffix
-        fi
-
-        if [[ "$choice" == "0" ]]; then
-            if [[ "$shell_mode" == true ]]; then
-                echo "Cannot shell into exit option."
-                continue
-            fi
-            echo "Exiting..."
-            exit 0
-        elif [[ "$choice" == "$i" ]]; then
-            if [[ "$shell_mode" == true ]]; then
-                echo "Cannot shell into 'run all tests' option."
-                continue
-            fi
-            echo "Running all tests..."
-            run_all_tests
-            break
-        elif [[ "$choice" -ge 1 && "$choice" -lt "$i" ]]; then
-            local selected_test="${cases[$choice]}"
-            if [[ "$shell_mode" == true ]]; then
-                echo "Shelling into: ${test_descriptions[$selected_test]}"
-                shell_into_env "$selected_test"
-            else
-                echo "Running: ${test_descriptions[$selected_test]}"
-                run_test "$selected_test"
-            fi
-
-            read -r -p "Continue testing? (y/n): " again
-            if [[ "$again" != "y" && "$again" != "Y" ]]; then
-                break
-            fi
-            echo
-        else
-            echo "Invalid choice. Please select 0-$i (optionally with '!' for shell mode)."
-        fi
-    done
-}
-
-run_all_tests() {
-    echo "=== Testing PR #1645: Conditional API initialization ==="
-    echo
-
-    for test_name in "${test_order[@]}"; do
-        run_test "$test_name"
-    done
-
-    echo "=== Test run complete ==="
-    echo "Review the output above to check:"
-    echo "1. No Ollama connection errors when OLLAMA_URL not set"
-    echo "2. No Bedrock authentication errors when BEDROCK_AWS_REGION not set"
-    echo "3. Only configured services appear in model listings"
-}
-
-show_help() {
-    echo "Usage: $0 [OPTIONS] [TEST_CASE]"
-    echo
-    echo "Test PR #1645 conditional API initialization"
-    echo
-    echo "Options:"
-    echo "  -h, --help       Show this help message"
-    echo "  -i, --interactive Run in interactive mode"
-    echo "  -b, --build-only  Build image only, don't run tests"
-    echo "  -s, --shell TEST  Shell into test environment"
-    echo
-    echo "Test cases:"
-    for test_name in "${test_order[@]}"; do
-        echo "  $test_name: ${test_descriptions[$test_name]}"
-    done
-    echo
-    echo "Examples:"
-    echo "  $0                    # Run all tests"
-    echo "  $0 -i                 # Interactive mode"
-    echo "  $0 gemini-only        # Run specific test"
-    echo "  $0 -s gemini-only     # Shell into gemini-only environment"
-    echo "  $0 -b                 # Build image only"
-    echo
-    echo "Environment files are located in $ENV_DIR/ and can be edited directly."
-}
-
-# Parse command line arguments
-if [[ $# -eq 0 ]]; then
-    build_image
-    run_all_tests
-elif [[ "$1" == "-h" || "$1" == "--help" ]]; then
-    show_help
-elif [[ "$1" == "-i" || "$1" == "--interactive" ]]; then
-    build_image
-    interactive_mode
-elif [[ "$1" == "-b" || "$1" == "--build-only" ]]; then
-    build_image
-elif [[ "$1" == "-s" || "$1" == "--shell" ]]; then
-    if [[ -z "$2" ]]; then
-        echo "Error: -s/--shell requires a test case name"
-        echo "Use -h for help."
-        exit 1
-    fi
-    if [[ -z "${test_descriptions[$2]}" ]]; then
-        echo "Error: Unknown test case: $2"
-        echo "Use -h for help."
-        exit 1
-    fi
-    build_image
-    shell_into_env "$2"
-elif [[ -n "${test_descriptions[$1]}" ]]; then
-    build_image
-    run_test "$1"
-else
-    echo "Unknown test case or option: $1"
-    echo "Use -h for help."
-    exit 1
-fi

scripts/docker/Dockerfile

@@ -1,41 +1,26 @@
-# Use official golang image as builder
-FROM golang:1.24.2-alpine AS builder
+# syntax=docker/dockerfile:1
 
-# Set working directory
-WORKDIR /app
+FROM golang:1.24-alpine AS builder
+
+WORKDIR /src
+
+# Install build dependencies
+RUN apk add --no-cache git
 
-# Copy go mod and sum files
 COPY go.mod go.sum ./
-
-# Download dependencies
 RUN go mod download
 
-# Copy source code
 COPY . .
 
-# Build the application
-RUN CGO_ENABLED=0 GOOS=linux go build -o fabric ./cmd/fabric
+RUN CGO_ENABLED=0 GOOS=linux go build -ldflags="-s -w" -o /fabric ./cmd/fabric
 
-# Use scratch as final base image
 FROM alpine:latest
 
-# Copy the binary from builder
-COPY --from=builder /app/fabric /fabric
+RUN apk add --no-cache ca-certificates \
+    && mkdir -p /root/.config/fabric
 
-# Copy patterns directory
-COPY patterns /patterns
+COPY --from=builder /fabric /usr/local/bin/fabric
 
-# Ensure clean config directory and copy ENV file
-RUN rm -rf /root/.config/fabric && \
-    mkdir -p /root/.config/fabric
-COPY ENV /root/.config/fabric/.env
-
-# Add debug commands
-RUN ls -la /root/.config/fabric/
-
-# Expose port 8080
 EXPOSE 8080
 
-# Run the binary with debug output
-ENTRYPOINT ["/fabric"]
-CMD ["--serve"] 
+ENTRYPOINT ["fabric"]

scripts/docker/README.md

@@ -1,40 +1,48 @@
-# Docker Deployment
+# Fabric Docker Image
 
-This directory contains Docker configuration files for running Fabric in containers.
+This directory provides a simple Docker setup for running the [Fabric](https://github.com/danielmiessler/fabric) CLI.
 
-## Files
+## Build
 
-- `Dockerfile` - Main Docker build configuration
-- `docker-compose.yml` - Docker Compose stack configuration  
-- `start-docker.sh` - Helper script to start the stack
-- `README.md` - This documentation
-
-## Quick Start
+Build the image from the repository root:
 
 ```bash
-# Start the Docker stack
-./start-docker.sh
-
-# Or manually with docker-compose
-docker-compose up -d
-
-# View logs
-docker-compose logs -f
-
-# Stop the stack
-docker-compose down
+docker build -t fabric -f scripts/docker/Dockerfile .
 ```
 
-## Building
+## Persisting configuration
+
+Fabric stores its configuration in `~/.config/fabric/.env`. Mount this path to keep your settings on the host.
+
+### Using a host directory
 
 ```bash
-# Build the Docker image
-docker build -t fabric .
-
-# Or use docker-compose
-docker-compose build
+mkdir -p $HOME/.fabric-config
+# Run setup to create the .env and download patterns
+ docker run --rm -it -v $HOME/.fabric-config:/root/.config/fabric fabric --setup
 ```
 
-## Configuration
+Subsequent runs can reuse the same directory:
 
-Make sure to configure your environment variables and API keys before running the Docker stack. See the main README.md for setup instructions.
+```bash
+docker run --rm -it -v $HOME/.fabric-config:/root/.config/fabric fabric -p your-pattern
+```
+
+### Mounting a single .env file
+
+If you only want to persist the `.env` file:
+
+```bash
+# assuming .env exists in the current directory
+docker run --rm -it -v $PWD/.env:/root/.config/fabric/.env fabric -p your-pattern
+```
+
+## Running the server
+
+Expose port 8080 to use Fabric's REST API:
+
+```bash
+docker run --rm -it -p 8080:8080 -v $HOME/.fabric-config:/root/.config/fabric fabric --serve
+```
+
+The API will be available at `http://localhost:8080`.

scripts/docker/docker-compose.yml

@@ -1,11 +0,0 @@
-version: '3.8'
-
-services:
-  fabric-api:
-    build: .
-    ports:
-      - "8080:8080"
-    volumes:
-      - ./ENV:/root/.config/fabric/.env:ro
-    environment:
-      - GIN_MODE=release 

scripts/docker/start-docker.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-
-# Helper script to start the Fabric Docker stack
-
-echo "Starting Fabric Docker stack..."
-cd "$(dirname "$0")"
-docker-compose up -d
-
-echo "Fabric is now running!"
-echo "Check logs with: docker-compose logs -f"
-echo "Stop with: docker-compose down"