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/cmd/reply.go

@@ -3,9 +3,9 @@ package cmd
 import (
 	"fmt"
 
+	"git.mlow.ca/mlow/lmcli/pkg/api"
 	cmdutil "git.mlow.ca/mlow/lmcli/pkg/cmd/util"
 	"git.mlow.ca/mlow/lmcli/pkg/lmcli"
-	"git.mlow.ca/mlow/lmcli/pkg/lmcli/model"
 	"github.com/spf13/cobra"
 )
 
@@ -30,8 +30,8 @@ func ReplyCmd(ctx *lmcli.Context) *cobra.Command {
 				return fmt.Errorf("No reply was provided.")
 			}
 
-			cmdutil.HandleConversationReply(ctx, conversation, true, model.Message{
-				Role:    model.MessageRoleUser,
+			cmdutil.HandleConversationReply(ctx, conversation, true, api.Message{
+				Role:    api.MessageRoleUser,
 				Content: reply,
 			})
 			return nil