Commit Graph

31 Commits

Author SHA1 Message Date
Ramiz Polic 191dcea159 chore: update packages to resolve security issues (#154)
Signed-off-by: Ramiz Polic <rpolic@cisco.com>
2026-02-15 19:56:44 +03:00
Shane McDonald c4aa911e3a feat: add Google Vertex AI support for Claude models (#146)
Add support for using Claude models via Google Cloud Vertex AI through
the `google-vertex-anthropic` provider. This enables users who have
Claude access through their Google Cloud account to use mcphost with
Vertex AI authentication.

Changes:
- Add `google-vertex-anthropic` provider case and createVertexAnthropicProvider()
- Support multiple env var names for project/region to match eino-claude:
  - Project: ANTHROPIC_VERTEX_PROJECT_ID, GOOGLE_CLOUD_PROJECT, GCLOUD_PROJECT
  - Region: CLOUD_ML_REGION (defaults to "global" if not set)
- Upgrade eino from v0.5.11 to v0.7.11 (required by eino-claude v0.1.12)
- Migrate schema API from OpenAPI v3 to JSON Schema (eino v0.7.11 change)

Usage:
  # Authenticate with Google Cloud
  gcloud auth application-default login

  # Set required environment variables
  export ANTHROPIC_VERTEX_PROJECT_ID="your-project-id"
  export CLOUD_ML_REGION="us-east5"  # or use default "global"

  # Run mcphost
  mcphost --model google-vertex-anthropic:claude-sonnet-4@20250514

Reference: https://docs.anthropic.com/en/docs/claude-code/google-vertex-ai

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-10 13:01:18 +03:00
Ed Zynda 7ece291d9a fix anthropic api issue 2026-01-09 17:39:30 +03:00
Ed Zynda f9485cbe59 new models 2026-01-09 17:30:59 +03:00
Ed Zynda 63704f55b5 godoc 2025-11-12 16:48:46 +03:00
Ed Zynda d3281a2f01 format 2025-10-16 16:36:12 +03:00
Ed Zynda 1b7cc2ef6e update models 2025-10-16 16:35:52 +03:00
matscalia d3c04b12bc add ollama api key (#124) 2025-08-11 20:10:32 +03:00
Ed Zynda d3f9759eb4 refactor debug messages 2025-08-08 09:32:04 +03:00
Ed Zynda 5d83df457b update models 2025-08-08 08:02:21 +03:00
Ed Zynda fe4db1998d feat: add --tls-skip-verify flag for self-signed certificates (#115)
* feat: add --tls-skip-verify flag for self-signed certificates

Adds support for skipping TLS certificate verification when connecting to
providers with self-signed certificates. This is particularly useful for
local Ollama instances secured with HTTPS.

- Add --tls-skip-verify command-line flag with security warnings
- Update ProviderConfig to include TLSSkipVerify field
- Modify HTTP client creation for all providers (Ollama, OpenAI, Anthropic, Google, Azure)
- Create helper functions for TLS-aware HTTP client creation
- Add comprehensive unit tests for TLS skip verify functionality
- Update documentation with usage examples and security warnings

Fixes #113

🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>

* feat: add TLS skip verify support to script mode

- Add TLSSkipVerify field to Config struct for script frontmatter
- Update script parsing to handle tls-skip-verify in YAML frontmatter
- Pass TLS configuration to model creation in script mode
- Add example script demonstrating TLS skip verify usage
- Update script examples documentation

This allows scripts to specify tls-skip-verify: true in their frontmatter
to connect to providers with self-signed certificates.

🤖 Generated with [opencode](https://opencode.ai)

Co-Authored-By: opencode <noreply@opencode.ai>

---------

Co-authored-by: opencode <noreply@opencode.ai>
2025-08-05 17:00:58 +03:00
Ed Zynda 32c46e4dc3 Fix for anthropic 2025-06-28 14:17:53 +03:00
Ed Zynda 053e6c32b0 Fix for openai (#95) 2025-06-28 13:38:58 +03:00
Ed Zynda 6a1b2f65d1 fix google/gemini 2025-06-27 11:40:11 +03:00
Ed Zynda a66c55e175 Improve Ollama and GPU handling (#85)
* preload ollama models

* fix num-gpu

* add download progress bar for ollama models

* fmt

* reorg
2025-06-26 13:32:18 +03:00
Ed Zynda 30f720ef7b updates 2025-06-26 10:56:10 +03:00
Ed Zynda 7d6abbf4a0 UI updates (#80)
* ui updates

* catppuccin

* fmt
2025-06-25 17:24:37 +03:00
Ed Zynda a2346721cb Claude max (#78)
* anthropic oauth

* update claude oauth costs
2025-06-25 14:27:19 +03:00
Thomas Conté ff49415679 Add Azure OpenAI provider (#75) 2025-06-24 08:47:46 +03:00
Ed Zynda 1f407bf7fb streamable HTTP 2025-06-19 16:16:19 +03:00
Ed Zynda 33df79adb6 skip model name validation with custom provider URL 2025-06-19 15:14:21 +03:00
Ed Zynda 3faf46ff44 better token tracking and support for more openai models 2025-06-18 15:19:04 +03:00
Ed Zynda aa43421b81 rudimentary token tracking 2025-06-18 14:05:30 +03:00
Ed Zynda 9e87977822 add up to date model data 2025-06-18 13:48:08 +03:00
Ed Zynda 21f60e3560 ollama gpu settings 2025-06-13 11:36:10 +03:00
Ed Zynda 42eb398148 format 2025-06-11 13:09:51 +03:00
Ed Zynda 306fbdb3d0 Standardize (#67)
* Model generation params

* Standardize model URL

* standardize more flags and update max steps check

* fix system prompt handling

* standardize api key handling

* update readme
2025-06-11 11:45:55 +03:00
Ed Zynda cff5c2deda tweak 2025-06-10 14:40:21 +03:00
Ed Zynda 82b50fbf0e fix gemini 2025-06-10 14:20:40 +03:00
Ed Zynda 13ede07ea5 formatting 2025-06-10 01:21:17 +03:00
Ed Zynda 8645a8c36a Huge refactor (#58)
* overhaul

* fix ui glitch

* system messages

* use sonnet 4
2025-06-09 14:38:31 +03:00