Package restructure and API changes, several fixes

- More emphasis on `api` package. It now holds database model structs
  from `lmcli/models` (which is now gone) as well as the tool spec,
  call, and result types. `tools.Tool` is now `api.ToolSpec`.
  `api.ChatCompletionClient` was renamed to
  `api.ChatCompletionProvider`.

- Change ChatCompletion interface and implementations to no longer do
  automatic tool call recursion - they simply return a ToolCall message
  which the caller can decide what to do with (e.g. prompt for user
  confirmation before executing)

- `api.ChatCompletionProvider` functions have had their ReplyCallback
  parameter removed, as now they only return a single reply.

- Added a top-level `agent` package, moved the current built-in tools
  implementations under `agent/toolbox`. `tools.ExecuteToolCalls` is now
  `agent.ExecuteToolCalls`.

- Fixed request context handling in openai, google, ollama (use
  `NewRequestWithContext`), cleaned up request cancellation in TUI

- Fix tool call tui persistence bug (we were skipping message with empty
  content)

- Now handle tool calling from TUI layer

TODO:
- Prompt users before executing tool calls
- Automatically send tool results to the model (or make this toggleable)

pkg/api/api.go

@@ -2,35 +2,41 @@ package api
 
 import (
 	"context"
-
-	"git.mlow.ca/mlow/lmcli/pkg/lmcli/model"
 )
 
-type ReplyCallback func(model.Message)
+type ReplyCallback func(Message)
 
 type Chunk struct {
 	Content    string
 	TokenCount uint
 }
 
-type ChatCompletionClient interface {
+type RequestParameters struct {
+	Model string
+
+	MaxTokens   int
+	Temperature float32
+	TopP        float32
+
+	ToolBag []ToolSpec
+}
+
+type ChatCompletionProvider interface {
 	// CreateChatCompletion requests a response to the provided messages.
 	// Replies are appended to the given replies struct, and the
 	// complete user-facing response is returned as a string.
 	CreateChatCompletion(
 		ctx context.Context,
-		params model.RequestParameters,
-		messages []model.Message,
-		callback ReplyCallback,
-	) (string, error)
+		params RequestParameters,
+		messages []Message,
+	) (*Message, error)
 
 	// Like CreateChageCompletion, except the response is streamed via
 	// the output channel as it's received.
 	CreateChatCompletionStream(
 		ctx context.Context,
-		params model.RequestParameters,
-		messages []model.Message,
-		callback ReplyCallback,
-		output chan<- Chunk,
-	) (string, error)
+		params RequestParameters,
+		messages []Message,
+		chunks chan<- Chunk,
+	) (*Message, error)
 }