CHANGES
- Add GitHub Actions workflow to publish Docker images on tags
- Build multi-arch images with Buildx and QEMU across amd64, arm64
- Tag images using semver; push to GHCR and Docker Hub
- Set :latest only for highest semver tag via imagetools
- Gate patterns workflow steps on detected changes instead of failing
- Auto-detect GitHub owner and repo from git remote URL
- Remove hardcoded repository values in changelog release manager
- Normalize image names to lowercase for registry compatibility
- Enable GitHub Actions cache for faster Docker builds
- Add VS Code dictionary entries for Docker-related terms
• Update ollama package to version 0.11.7
• Refresh go.sum with new dependency checksums
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2025-0317](https://nvd.nist.gov/vuln/detail/CVE-2025-0317)
- **CVSS Score**: 7.5 (High)
- **Description**: A vulnerability in ollama/ollama versions <=0.3.14 allows a malicious user to upload and create a customized GGUF model file on the Ollama server. This can lead to a division by zero error in the ggufPadding function, causing the server to crash and resulting in a Denial of Service (DoS) attack.
- **Affected**: Ollama server versions ≤ 0.3.14
- **Impact**: Denial of Service through division by zero error
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2025-0315](https://nvd.nist.gov/vuln/detail/CVE-2025-0315)
- **CVSS Score**: 7.5 (High)
- **Description**: Vulnerability allows Denial of Service via customized GGUF model file upload on Ollama server.
- **Affected**: Ollama/ollama versions ≤ 0.3.14
- **Impact**: Denial of Service through malicious GGUF model file uploads
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2024-12886](https://nvd.nist.gov/vuln/detail/CVE-2024-12886)
- **CVSS Score**: 7.5 (High)
- **Description**: An Out-Of-Memory (OOM) vulnerability exists in the ollama server version 0.3.14. This vulnerability can be triggered when a malicious API server responds with a gzip bomb HTTP response, leading to the ollama server crashing.
- **Affected**: Ollama server version 0.3.14
- **Impact**: Denial of Service through memory exhaustion via gzip bomb attack
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2024-8063](https://nvd.nist.gov/vuln/detail/CVE-2024-8063)
- **CVSS Score**: 7.5 (High)
- **Description**: Security vulnerability with high severity rating
- **Impact**: Requires patching for security compliance
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2024-12055](https://nvd.nist.gov/vuln/detail/CVE-2024-12055)
- **CVSS Score**: 7.5 (High)
- **Description**: High-severity security vulnerability requiring immediate attention
- **Impact**: Critical security flaw needing remediation
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2025-51471](https://nvd.nist.gov/vuln/detail/CVE-2025-51471)
- **CVSS Score**: 6.9 (Medium)
- **Description**: Medium severity security vulnerability
- **Impact**: Security risk requiring patching as part of comprehensive security updates
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2025-46394](https://nvd.nist.gov/vuln/detail/CVE-2025-46394)
- **CVSS Score**: 3.2 (Low)
- **Description**: Low-severity security issue
- **Impact**: Minor security concern addressed as part of comprehensive security maintenance
- **Link**: [https://nvd.nist.gov/vuln/detail/CVE-2024-58251](https://nvd.nist.gov/vuln/detail/CVE-2024-58251)
- **CVSS Score**: 2.5 (Low)
- **Description**: Low-severity security vulnerability
- **Impact**: Minimal security risk addressed for comprehensive security posture
This comprehensive security fix addresses **8 CVEs** total:
- **5 High Severity** vulnerabilities (CVSS 7.5)
- **1 Medium Severity** vulnerability (CVSS 6.9)
- **2 Low Severity** vulnerabilities (CVSS 3.2 and 2.5)
The majority of high-severity issues are related to **Ollama server vulnerabilities** that could lead to Denial of Service attacks through various vectors including division by zero errors, memory exhaustion, and malicious file uploads. These fixes ensure robust protection against these attack vectors and maintain system availability.
**Priority**: The high-severity Ollama vulnerabilities should be considered critical for any systems running Ollama server components, as they can lead to service disruption and potential system crashes.
- Replace fmt.Fprintf/os.Stderr with centralized debuglog.Log across CLI
- Add unconditional Log function to debuglog for important messages
- Improve OAuth flow messaging and token refresh diagnostics
- Update tests to capture debuglog output via SetOutput
- Convert Perplexity streaming errors to unified debug logging
- Emit file write notifications through debuglog instead of stderr
- Warn on ambiguous model selection using centralized logger
- Announce large audio processing steps via debuglog progress messages
- Standardize extension registry and patterns warnings through debuglog
- 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
- Configure Venice AI base URL and response settings
CHANGES
- 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
- Keep shell completion output unchanged without default markers
CHANGES
- 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
- Provide zsh, bash, fish completions for new transcription flags
- Validate media extensions and enforce 25MB upload limits
- Update README with release and corrected pattern link path
• Add per-pattern model mapping documentation section
• Implement environment variable lookup for pattern-specific models
• Support vendor|model format in environment variable specification
• Check pattern-specific model when no model explicitly set
• Transform pattern names to uppercase environment variable format
• Add table of contents entry for new feature
• Enable shell startup file configuration for patterns
- Introduce CLI flag to skip pattern variable replacement.
- Wire flag into domain request and session builder.
- Avoid applying input variables when replacement is disabled.
- 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.
- Document flag in README and CLI help output.
- Add unit tests covering GetWithoutVariables path and behavior.
- Ensure {{input}} placeholder appends when missing in patterns.
- Fix typo "Gemmini" to "Gemini" in README
- Add "kballard" and "shellquote" to VSCode dictionary
- Add "YTDLP" to VSCode spell checker
- Enhance subtitle language options with fallback variants
- Build language options string with comma-separated alternatives
- Add comprehensive "Recent Major Features" section to README
- Introduce new readme_updates Python script for automation
- Enable Gemini thinking configuration with token budgets
- Update CLI help text for Gemini thinking support
- Add comprehensive test coverage for Gemini thinking
- Create documentation for README update automation
- Reorganize README navigation structure with changelog section
## CHANGES
- Upgrade anthropic-sdk-go from v1.7.0 to v1.9.1
- Upgrade golang.org/x/crypto from v0.39.0 to v0.40.0
- Add modelBetas map for beta feature configuration
- Implement context-1m-2025-08-07 beta for Claude Sonnet 4
- Add beta header support in streaming requests
- Add beta header support in standard requests
- Implement fallback mechanism when beta features fail
- Preserve existing beta headers in OAuth transport
- Add test coverage for model beta configuration
CHANGES
- Support 'fabric-ai' alias across Zsh, Bash, and Fish
- Use invoked command for dynamic completion list queries
- Refactor Fish completions into reusable registrar for multiple commands
- Update Bash completion to reference executable via COMP_WORDS[0]
- Extend Zsh compdef to register fabric and fabric-ai
- Add cross-shell installer script with autodetection and dry-run mode
- Document installation, features, troubleshooting in new completions guide
