13 Commits

• fix(ai): support prompt caching for Bedrock application inference profiles (#2346)

  Add AWS_BEDROCK_FORCE_CACHE=1 environment variable support. When the
  model ID doesn't contain a recognizable Claude model name, users can
  set this variable to force cache point injection.

  xu0o0 · 2026-03-18 11:21:10 +01:00
  31d59f8513
• feat(ai,coding-agent): add OpenCode Go provider support closes #1757
  Mario Zechner · 2026-03-03 16:02:29 +01:00
  42579dd923
• docs: add auth.json keys to table and reference to envMap (#1412)

  * docs: add auth.json keys to table and reference to envMap
  
  * docs: adjust envMap reference links

  Emanuel Stadler · 2026-02-08 23:05:27 +01:00
  9d6fcedb91
• fix(ai): move AWS_BEDROCK_SKIP_AUTH inside Node.js environment check

  The process.env access was outside the typeof process check, which
  would throw in browser environments. Moved inside the Node.js/Bun
  block for consistency with other env var access.
  
  Also added changelog entry for #1320 and improved docs clarity.

  Mario Zechner · 2026-02-06 10:45:20 +01:00
  a40bf5fbd5
• fix(ai): provide mechanism to connect to unauthenticated bedrock proxies (#1320)

  fixes #1309

  Dustin Spicuzza · 2026-02-06 10:44:28 +01:00
  df527fb988
• feat(coding-agent): support shell commands and env vars in auth.json API keys

  API keys in auth.json now support the same resolution as models.json:
  - Shell command: "\!command" executes and uses stdout (cached)
  - Environment variable: uses the value of the named variable
  - Literal value: used directly
  
  Extracted shared resolveConfigValue() to new resolve-config-value.ts module.

  Mario Zechner · 2026-02-04 23:02:00 +01:00
  9cf5758b68
• Update providers.md to include opencode provider (#1094)

  add 'opencode' provider configuration to the documentation.

  Emanuel Stadler · 2026-01-30 16:43:32 +01:00
  fd6c6d8772
• feat(ai): add Kimi For Coding provider support

  - Add kimi-coding provider using Anthropic Messages API
  - API endpoint: https://api.kimi.com/coding/v1
  - Environment variable: KIMI_API_KEY
  - Models: kimi-k2-thinking (text), k2p5 (text + image)
  - Add context overflow detection pattern for Kimi errors
  - Add tests for all standard test suites

  Mario Zechner · 2026-01-29 04:12:28 +01:00
  87ab5c5c3b
• feat(ai): add Hugging Face provider support

  - Add huggingface to KnownProvider type
  - Add HF_TOKEN env var mapping
  - Process huggingface models from models.dev (14 models)
  - Use openai-completions API with compat settings
  - Add tests for all provider test suites
  - Update documentation
  
  fixes #994

  Mario Zechner · 2026-01-29 02:40:14 +01:00
  c808de605a
• docs(coding-agent): note that model list is updated with each release
  Mario Zechner · 2026-01-26 00:18:45 +01:00
  6783271d75
• docs(coding-agent): link to custom-provider.md for extension-based providers
  Mario Zechner · 2026-01-26 00:16:20 +01:00
  591525a1ce
• docs(coding-agent): add Custom Providers section to providers.md
  Mario Zechner · 2026-01-26 00:10:07 +01:00
  fd1beb4941
• docs(coding-agent): rename authentication.md to providers.md
  Mario Zechner · 2026-01-26 00:08:29 +01:00
  b08ec08fd4