refactor(executor): extract provider-neutral tool-use loop (Phase 1)

Splits LocalRunner's OpenAI-specific agentic loop into reusable, provider-
agnostic pieces so later phases can add native Anthropic/OpenAI/Google/Groq/
OpenRouter adapters without duplicating the control flow:

- internal/provider: neutral Provider/ChatRequest/ChatResponse types, plus
  an openaicompat adapter wrapping the existing internal/llm.Client unchanged
- internal/sandbox: Sandbox interface + HostSandbox (git clone/push/cleanup,
  read_file/write_file/run_bash/glob), lifted verbatim from local.go/localtools.go
- internal/agentloop: the extracted tool-use loop (request/response/tool-
  dispatch/loop, ask_user blocking, stream-json envelope, summary fallback)
- internal/agentchannel: AgentChannel/SubtaskSpec/BlockedError/ErrAgentBlocked
  moved out of internal/executor so agentloop can use them without an import
  cycle; internal/executor re-exports via type aliases, so no call site changes
- internal/executor/nativerunner.go: NativeRunner replaces LocalRunner,
  wiring agentloop.Loop + openaicompat + HostSandbox together
- config.Providers map[string]ProviderConfig added (unused until Phase 2+)

Zero intended behavior change: go test -race ./... passes across all
packages, and end-to-end stream-json/summary/changestats output was verified
byte-compatible against a fake OpenAI-compatible server. Adds test coverage
for sandbox tool-dispatch (git clone/push, read/write/bash/glob) that
LocalRunner never had.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs

1 files changed, 265 insertions, 0 deletions

diff --git a/internal/agentloop/agentloop.go b/internal/agentloop/agentloop.go
new file mode 100644
index 0000000..73c4c83
--- /dev/null
+++ b/internal/agentloop/agentloop.go
@@ -0,0 +1,265 @@
+// Package agentloop implements the provider-neutral tool-use control flow
+// extracted from the former executor.LocalRunner.Run: build messages, call a
+// provider.Provider in a bounded loop, dispatch any tool calls the model
+// makes (back-channel tools to an agentchannel.AgentChannel, sandbox tools to
+// a sandbox.Sandbox), and re-feed results until the model stops calling
+// tools or the turn budget is exhausted.
+//
+// Loop deliberately knows nothing about *how* instructions were assembled
+// (planning preamble, tinyllama tool-gating, etc.) or how the sandbox's
+// working directory was established (fresh git clone vs. resumed BLOCKED
+// sandbox) — those decisions stay with the caller (executor.NativeRunner),
+// which lives in internal/executor and can freely reuse executor's existing
+// buildAgentInstructions/withPlanningPreamble helpers without agentloop
+// having to import executor (which would cycle back through NativeRunner).
+package agentloop
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"strings"
+	"time"
+
+	"github.com/thepeterstone/claudomator/internal/agentchannel"
+	"github.com/thepeterstone/claudomator/internal/provider"
+	"github.com/thepeterstone/claudomator/internal/sandbox"
+	"github.com/thepeterstone/claudomator/internal/storage"
+	"github.com/thepeterstone/claudomator/internal/task"
+)
+
+// DefaultMaxTurns bounds the tool-use loop so a misbehaving model cannot spin
+// forever calling tools without finishing. Matches the former
+// executor.maxLocalToolTurns.
+const DefaultMaxTurns = 12
+
+// Loop drives a provider-neutral tool-use conversation for a single task
+// execution.
+type Loop struct {
+	Provider provider.Provider
+	Sandbox  sandbox.Sandbox
+	Channel  agentchannel.AgentChannel
+	MaxTurns int
+
+	// DefaultTemperature is used when the task doesn't specify its own
+	// Agent.Temperature. Matches the former LocalRunner.DefaultTemperature.
+	DefaultTemperature float64
+
+	Logger *slog.Logger
+}
+
+// Run drives the chat completion loop against l.Provider with the agent
+// back-channel + sandbox tools declared (when toolsEnabled), writing
+// assistant text and a final result line to stdout in the same stream-json
+// envelope ClaudeRunner/ContainerRunner emit, so downstream parsers
+// (extractSummary, task.ParseChangestatFromFile) keep working unchanged.
+//
+// instructions is the fully-assembled user-turn text (already including any
+// planning preamble the caller decided to prepend). If the model calls
+// ask_user, Run stops and returns a *agentchannel.BlockedError, leaving the
+// sandbox uncleaned so a resume can reuse it.
+func (l *Loop) Run(ctx context.Context, t *task.Task, e *storage.Execution, stdout io.Writer, instructions string, toolsEnabled bool) error {
+	maxTurns := l.MaxTurns
+	if maxTurns <= 0 {
+		maxTurns = DefaultMaxTurns
+	}
+
+	temperature := t.Agent.Temperature
+	if temperature == nil && l.DefaultTemperature > 0 {
+		v := l.DefaultTemperature
+		temperature = &v
+	}
+
+	var tools []provider.ToolSpec
+	if toolsEnabled {
+		tools = agentToolSpecs()
+	}
+
+	system := strings.TrimSpace(t.Agent.SystemPromptAppend)
+	messages := []provider.Message{{Role: "user", Text: instructions}}
+
+	start := time.Now()
+	var totalIn, totalOut int
+	var lastFinish string
+	blocked := false
+	var fullText string
+
+	for turn := 0; turn < maxTurns; turn++ {
+		req := provider.ChatRequest{
+			Model:       t.Agent.Model,
+			System:      system,
+			Messages:    messages,
+			Temperature: temperature,
+			MaxTokens:   t.Agent.MaxTokens,
+			Tools:       tools,
+		}
+		resp, chatErr := l.Provider.Chat(ctx, req)
+		if chatErr != nil {
+			// If the model doesn't support tool-use, retry once without tools.
+			if tools != nil && strings.Contains(strings.ToLower(chatErr.Error()), "does not support tools") {
+				tools = nil
+				req.Tools = nil
+				resp, chatErr = l.Provider.Chat(ctx, req)
+			}
+			if chatErr != nil {
+				writeResultLine(stdout, "error", chatErr.Error(), totalIn, totalOut)
+				return fmt.Errorf("agentloop: chat: %w", chatErr)
+			}
+		}
+		totalIn += resp.Usage.InputTokens
+		totalOut += resp.Usage.OutputTokens
+		lastFinish = resp.StopReason
+
+		if resp.Text != "" {
+			writeAssistantTextLine(stdout, resp.Text)
+			fullText += resp.Text
+		}
+
+		if len(resp.ToolCalls) == 0 {
+			break
+		}
+
+		// Re-feed: record the assistant's tool-call turn, then each tool result.
+		messages = append(messages, provider.Message{Role: "assistant", Text: resp.Text, ToolCalls: resp.ToolCalls})
+		for _, tc := range resp.ToolCalls {
+			result, didBlock, toolErr := l.dispatchTool(ctx, tc.Name, tc.ArgsJSON)
+			if toolErr != nil {
+				writeResultLine(stdout, "error", toolErr.Error(), totalIn, totalOut)
+				return fmt.Errorf("agentloop: tool %s: %w", tc.Name, toolErr)
+			}
+			if didBlock {
+				blocked = true
+				break
+			}
+			messages = append(messages, provider.Message{
+				Role: "tool",
+				ToolResults: []provider.ToolResult{{
+					ToolCallID: tc.ID,
+					Name:       tc.Name,
+					Content:    result,
+				}},
+			})
+		}
+		if blocked {
+			break
+		}
+	}
+	elapsed := time.Since(start)
+
+	e.CostUSD = 0
+	e.TokensIn = int64(totalIn)
+	e.TokensOut = int64(totalOut)
+
+	if l.Logger != nil {
+		l.Logger.Info("agentloop run completed",
+			"taskID", t.ID,
+			"tokens_in", totalIn,
+			"tokens_out", totalOut,
+			"finish_reason", lastFinish,
+			"blocked", blocked,
+			"elapsed_ms", elapsed.Milliseconds(),
+		)
+	}
+
+	// If the model asked the user, stop and block. Preserve the sandbox so
+	// resume can reuse it.
+	if q, isBlocked := pendingQuestion(l.Channel); isBlocked {
+		return &agentchannel.BlockedError{QuestionJSON: q}
+	}
+
+	// Push any commits made inside the sandbox back to the origin.
+	if l.Sandbox != nil && l.Sandbox.WorkDir() != "" {
+		if err := l.Sandbox.GitPush(ctx, ""); err != nil {
+			if l.Logger != nil {
+				l.Logger.Warn("agentloop: git push failed", "err", err)
+			}
+		}
+		if err := l.Sandbox.Cleanup(ctx); err != nil {
+			if l.Logger != nil {
+				l.Logger.Warn("agentloop: sandbox cleanup failed", "err", err)
+			}
+		}
+		e.SandboxDir = ""
+	}
+
+	// For tool-less models report_summary is never called, so synthesise a
+	// summary from the raw assistant output so handleRunResult has something
+	// to store.
+	if e.Summary == "" && fullText != "" {
+		s := strings.TrimSpace(fullText)
+		if len(s) > 500 {
+			s = s[:500]
+		}
+		e.Summary = s
+	}
+
+	writeResultLine(stdout, "success", "", totalIn, totalOut)
+	return nil
+}
+
+// pendingAsker is implemented by AgentChannel implementations that buffer an
+// ask_user call so Run can convert it into a BlockedError after the loop
+// exits. Defined structurally here (rather than imported) so agentloop does
+// not need to depend on executor.storeChannel's package to detect it — any
+// AgentChannel with this method shape satisfies it, including
+// executor.storeChannel.
+type pendingAsker interface {
+	PendingQuestion() (questionJSON string, blocked bool)
+}
+
+func pendingQuestion(ch agentchannel.AgentChannel) (string, bool) {
+	if pa, ok := ch.(pendingAsker); ok {
+		return pa.PendingQuestion()
+	}
+	return "", false
+}
+
+// writeAssistantTextLine writes a single stream-json line wrapping `text` as
+// an assistant text block. Format matches what ClaudeRunner/ContainerRunner
+// emit, so extractSummary and ParseChangestatFromFile read it transparently.
+func writeAssistantTextLine(w io.Writer, text string) {
+	line := struct {
+		Type    string `json:"type"`
+		Message struct {
+			Content []struct {
+				Type string `json:"type"`
+				Text string `json:"text"`
+			} `json:"content"`
+		} `json:"message"`
+	}{Type: "assistant"}
+	line.Message.Content = []struct {
+		Type string `json:"type"`
+		Text string `json:"text"`
+	}{{Type: "text", Text: text}}
+	b, err := json.Marshal(line)
+	if err != nil {
+		return
+	}
+	w.Write(b)
+	w.Write([]byte("\n"))
+}
+
+// writeResultLine writes a final stream-json terminator line that downstream
+// parsers can recognise. Mirrors the shape of the result line ClaudeRunner
+// emits.
+func writeResultLine(w io.Writer, subtype, errMsg string, promptTokens, outputTokens int) {
+	line := map[string]any{
+		"type":           "result",
+		"subtype":        subtype,
+		"is_error":       errMsg != "",
+		"prompt_tokens":  promptTokens,
+		"output_tokens":  outputTokens,
+		"total_cost_usd": 0.0,
+	}
+	if errMsg != "" {
+		line["result"] = errMsg
+	}
+	b, err := json.Marshal(line)
+	if err != nil {
+		return
+	}
+	w.Write(b)
+	w.Write([]byte("\n"))
+}