feat: OpenAI-compatible model support (GPT, DeepSeek, Ollama, OpenRouter, etc.)

SDK v0.4.1 adds full OpenAI Chat Completions API adapter:
- Auto-detection from BaseURL, API key prefix, model name
- Supports: OpenAI, OpenRouter, DeepSeek, Ollama, Together, Groq, vLLM, LMStudio
- Full tool calling support (function calling format)
- Streaming and non-streaming modes
- Request/response format conversion (Anthropic ↔ OpenAI)

Config:
- "provider" field in settings.json ("anthropic" or "openai", auto if empty)
- Works with existing CODEANY_BASE_URL + CODEANY_API_KEY env vars

Example configs:
  # OpenAI
  {"provider": "openai", "baseURL": "https://api.openai.com/v1", "model": "gpt-4o"}

  # Ollama (local)
  {"baseURL": "http://localhost:11434/v1", "model": "llama3.2"}

  # DeepSeek
  {"baseURL": "https://api.deepseek.com/v1", "model": "deepseek-chat"}

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: idoubi

go.mod

@@ -7,7 +7,7 @@ require (
 	github.com/charmbracelet/bubbletea v1.3.5
 	github.com/charmbracelet/glamour v0.9.1
 	github.com/charmbracelet/lipgloss v1.1.0
-	github.com/codeany-ai/open-agent-sdk-go v0.3.0
+	github.com/codeany-ai/open-agent-sdk-go v0.4.1
 	github.com/muesli/reflow v0.3.0
 	github.com/spf13/cobra v1.9.1
 	gopkg.in/yaml.v3 v3.0.1

go.sum

@@ -32,8 +32,8 @@ github.com/charmbracelet/x/exp/golden v0.0.0-20241011142426-46044092ad91 h1:payR
 github.com/charmbracelet/x/exp/golden v0.0.0-20241011142426-46044092ad91/go.mod h1:wDlXFlCrmJ8J+swcL/MnGUuYnqgQdW9rhSD61oNMb6U=
 github.com/charmbracelet/x/term v0.2.1 h1:AQeHeLZ1OqSXhrAWpYUtZyX1T3zVxfpZuEQMIQaGIAQ=
 github.com/charmbracelet/x/term v0.2.1/go.mod h1:oQ4enTYFV7QN4m0i9mzHrViD7TQKvNEEkHUMCmsxdUg=
-github.com/codeany-ai/open-agent-sdk-go v0.3.0 h1:Levqy7k0fGFSDhNFUjJakWlqM28dfgq5Y/1YVzwodkk=
-github.com/codeany-ai/open-agent-sdk-go v0.3.0/go.mod h1:j9P9/i2oWLD0iMB73vZ6IllaQ9FzgG0LAdPmnqb9VOw=
+github.com/codeany-ai/open-agent-sdk-go v0.4.1 h1:sifjkB79SwgiJDDTaU65whTtKoddisT2i0zkQ68m04Y=
+github.com/codeany-ai/open-agent-sdk-go v0.4.1/go.mod h1:j9P9/i2oWLD0iMB73vZ6IllaQ9FzgG0LAdPmnqb9VOw=
 github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
 github.com/dlclark/regexp2 v1.11.0 h1:G/nrcoOa7ZXlpoa/91N3X7mM3r8eIlMBBJZvsz/mxKI=
 github.com/dlclark/regexp2 v1.11.0/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=

internal/config/config.go

@@ -25,8 +25,9 @@ type Config struct {
 	SmallModel string `json:"smallModel,omitempty"`
 
 	// API settings
-	APIKey  string `json:"apiKey,omitempty"`
-	BaseURL string `json:"baseURL,omitempty"`
+	APIKey   string `json:"apiKey,omitempty"`
+	BaseURL  string `json:"baseURL,omitempty"`
+	Provider string `json:"provider,omitempty"` // "anthropic" or "openai" (auto-detected if empty)
 
 	// Permission settings
 	PermissionMode string `json:"permissionMode,omitempty"`

internal/pipe/pipe.go

@@ -19,6 +19,7 @@ func Run(ctx context.Context, cfg *config.Config, prompt string, outputFmt strin
 		Model:              cfg.Model,
 		APIKey:             cfg.APIKey,
 		BaseURL:            cfg.BaseURL,
+		Provider:           cfg.Provider,
 		CWD:                cwd,
 		MaxTurns:           cfg.MaxTurns,
 		MaxBudgetUSD:       cfg.MaxBudgetUSD,

internal/tui/model.go

@@ -204,6 +204,7 @@ func (m *Model) initAgent() tea.Cmd {
 			Model:              m.cfg.Model,
 			APIKey:             m.cfg.APIKey,
 			BaseURL:            m.cfg.BaseURL,
+			Provider:           m.cfg.Provider,
 			CWD:                cwd,
 			MaxTurns:           m.cfg.MaxTurns,
 			MaxBudgetUSD:       m.cfg.MaxBudgetUSD,