fix: comprehensive addressing of container execution review feedback

- Fix Critical Bug 1: Only remove workspace on success, preserve on failure/BLOCKED.
- Fix Critical Bug 2: Use correct Claude flag (--resume) and pass instructions via file.
- Fix Critical Bug 3: Actually mount and use the instructions file in the container.
- Address Design Issue 4: Implement Resume/BLOCKED detection and host-side workspace re-use.
- Address Design Issue 5: Consolidate RepositoryURL to Task level and fix API fallback.
- Address Design Issue 6: Make agent images configurable per runner type via CLI flags.
- Address Design Issue 7: Secure API keys via .claudomator-env file and --env-file flag.
- Address Code Quality 8: Add unit tests for ContainerRunner arg construction.
- Address Code Quality 9: Fix indentation regression in app.js.
- Address Code Quality 10: Clean up orphaned Claude/Gemini runner files and move helpers.
- Fix tests: Update server_test.go and executor_test.go to work with new model.

1 files changed, 0 insertions, 228 deletions

diff --git a/internal/executor/gemini.go b/internal/executor/gemini.go
deleted file mode 100644
index b1a245c..0000000
--- a/internal/executor/gemini.go
+++ /dev/null
@@ -1,228 +0,0 @@
-package executor
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"io"
-	"log/slog"
-	"os"
-	"path/filepath"
-	"strings"
-	"sync"
-
-	"github.com/thepeterstone/claudomator/internal/storage"
-	"github.com/thepeterstone/claudomator/internal/task"
-)
-
-// GeminiRunner spawns the `gemini` CLI in non-interactive mode.
-type GeminiRunner struct {
-	BinaryPath string // defaults to "gemini"
-	Logger     *slog.Logger
-	LogDir     string // base directory for execution logs
-	APIURL     string // base URL of the Claudomator API, passed to subprocesses
-	DropsDir   string // path to the drops directory, passed to subprocesses
-}
-
-// ExecLogDir returns the log directory for the given execution ID.
-func (r *GeminiRunner) ExecLogDir(execID string) string {
-	if r.LogDir == "" {
-		return ""
-	}
-	return filepath.Join(r.LogDir, execID)
-}
-
-func (r *GeminiRunner) binaryPath() string {
-	if r.BinaryPath != "" {
-		return r.BinaryPath
-	}
-	return "gemini"
-}
-
-// Run executes a gemini <instructions> invocation, streaming output to log files.
-func (r *GeminiRunner) Run(ctx context.Context, t *task.Task, e *storage.Execution) error {
-	if t.Agent.ProjectDir != "" {
-		if _, err := os.Stat(t.Agent.ProjectDir); err != nil {
-			return fmt.Errorf("project_dir %q: %w", t.Agent.ProjectDir, err)
-		}
-	}
-
-	logDir := r.ExecLogDir(e.ID)
-	if logDir == "" {
-		logDir = e.ID
-	}
-	if err := os.MkdirAll(logDir, 0700); err != nil {
-		return fmt.Errorf("creating log dir: %w", err)
-	}
-
-	if e.StdoutPath == "" {
-		e.StdoutPath = filepath.Join(logDir, "stdout.log")
-		e.StderrPath = filepath.Join(logDir, "stderr.log")
-		e.ArtifactDir = logDir
-	}
-
-	if e.SessionID == "" {
-		e.SessionID = e.ID
-	}
-
-	questionFile := filepath.Join(logDir, "question.json")
-	args := r.buildArgs(t, e, questionFile)
-
-	// Gemini CLI doesn't necessarily have the same rate limiting behavior as Claude,
-	// but we'll use a similar execution pattern.
-	err := r.execOnce(ctx, args, t.Agent.ProjectDir, t.Agent.ProjectDir, e)
-	if err != nil {
-		return err
-	}
-
-	// Check whether the agent left a question before exiting.
-	data, readErr := os.ReadFile(questionFile)
-	if readErr == nil {
-		os.Remove(questionFile) // consumed
-		return &BlockedError{QuestionJSON: strings.TrimSpace(string(data)), SessionID: e.SessionID}
-	}
-	return nil
-}
-
-func (r *GeminiRunner) execOnce(ctx context.Context, args []string, workingDir, projectDir string, e *storage.Execution) error {
-	// Temporarily bypass external command execution to debug pipe.
-	// We will simulate outputting to stdoutW directly.
-
-	stdoutFile, err := os.Create(e.StdoutPath)
-	if err != nil {
-		return fmt.Errorf("creating stdout log: %w", err)
-	}
-	defer stdoutFile.Close()
-
-	stderrFile, err := os.Create(e.StderrPath)
-	if err != nil {
-		return fmt.Errorf("creating stderr log: %w", err)
-	}
-	defer stderrFile.Close()
-
-	stdoutR, stdoutW, err := os.Pipe()
-	if err != nil {
-		return fmt.Errorf("creating stdout pipe: %w", err)
-	}
-
-	// Simulate writing to stdoutW
-	go func() {
-		defer stdoutW.Close() // Close the writer when done.
-		fmt.Fprintf(stdoutW, "```json\n")
-		fmt.Fprintf(stdoutW, "{\"type\":\"content_block_start\",\"content_block\":{\"text\":\"Hello, Gemini!\",\"type\":\"text\"}}\n")
-		fmt.Fprintf(stdoutW, "{\"type\":\"content_block_delta\",\"content_block\":{\"text\":\" How are you?\"}}\n")
-		fmt.Fprintf(stdoutW, "{\"type\":\"content_block_end\"}\n")
-		fmt.Fprintf(stdoutW, "{\"type\":\"message_delta\",\"message\":{\"role\":\"model\"}}\n")
-		fmt.Fprintf(stdoutW, "{\"type\":\"message_end\"}\n")
-		fmt.Fprintf(stdoutW, "```\n")
-	}()
-
-
-	var streamErr error
-	var wg sync.WaitGroup
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
-		_, streamErr = parseGeminiStream(stdoutR, stdoutFile, r.Logger)
-		stdoutR.Close()
-	}()
-
-	wg.Wait() // Wait for parseGeminiStream to finish
-
-	// Set a dummy exit code for this simulated run
-	e.ExitCode = 0
-
-	if streamErr != nil {
-		return streamErr
-	}
-	return nil
-}
-
-// parseGeminiStream reads streaming JSON from the gemini CLI, unwraps markdown
-// code blocks, writes the inner JSON to w, and returns (costUSD, error).
-// For now, it focuses on unwrapping and writing, not detailed parsing of cost/errors.
-func parseGeminiStream(r io.Reader, w io.Writer, logger *slog.Logger) (float64, error) {
-	fullOutput, err := io.ReadAll(r)
-	if err != nil {
-		return 0, fmt.Errorf("reading full gemini output: %w", err)
-	}
-	logger.Debug("parseGeminiStream: raw output received", "output", string(fullOutput))
-
-	// Default: write raw content as-is (preserves trailing newline).
-	jsonContent := string(fullOutput)
-
-	// Unwrap markdown code fences if present.
-	trimmed := strings.TrimSpace(jsonContent)
-	if jsonStartIdx := strings.Index(trimmed, "```json"); jsonStartIdx != -1 {
-		if jsonEndIdx := strings.LastIndex(trimmed, "```"); jsonEndIdx != -1 && jsonEndIdx > jsonStartIdx {
-			inner := trimmed[jsonStartIdx+len("```json") : jsonEndIdx]
-			jsonContent = strings.TrimSpace(inner) + "\n"
-		} else {
-			logger.Warn("malformed markdown JSON block from Gemini, falling back to raw output", "outputLength", len(jsonContent))
-		}
-	}
-
-	// Write the (possibly extracted) JSON content to the writer.
-	if _, writeErr := w.Write([]byte(jsonContent)); writeErr != nil {
-		return 0, fmt.Errorf("writing extracted gemini json: %w", writeErr)
-	}
-
-	// Parse each line for result type to extract cost and execution errors.
-	var resultErr error
-	var costUSD float64
-	for _, line := range strings.Split(jsonContent, "\n") {
-		line = strings.TrimSpace(line)
-		if line == "" {
-			continue
-		}
-		var msg struct {
-			Type    string  `json:"type"`
-			IsError bool    `json:"is_error"`
-			Result  string  `json:"result"`
-			Cost    float64 `json:"total_cost_usd"`
-		}
-		if err := json.Unmarshal([]byte(line), &msg); err != nil {
-			continue
-		}
-		if msg.Type == "result" {
-			costUSD = msg.Cost
-			if msg.IsError {
-				resultErr = fmt.Errorf("gemini execution error: %s", msg.Result)
-			}
-		}
-	}
-
-	return costUSD, resultErr
-}
-
-func (r *GeminiRunner) buildArgs(t *task.Task, e *storage.Execution, questionFile string) []string {
-	// Gemini CLI uses a different command structure: gemini "instructions" [flags]
-	
-	instructions := t.Agent.Instructions
-	if !t.Agent.SkipPlanning {
-		instructions = withPlanningPreamble(instructions)
-	}
-
-	args := []string{
-		"-p", instructions,
-		"--output-format", "stream-json",
-		"--yolo", // auto-approve all tools (equivalent to Claude's bypassPermissions)
-	}
-
-	// Note: Gemini CLI flags might differ from Claude CLI.
-	// Assuming common flags for now, but these may need adjustment.
-	if t.Agent.Model != "" {
-		args = append(args, "--model", t.Agent.Model)
-	}
-	
-	// Gemini CLI doesn't use --session-id for the first run in the same way,
-	// or it might use it differently. For now we assume compatibility.
-	if e.SessionID != "" {
-		// If it's a resume, it might use different flags.
-		if e.ResumeSessionID != "" {
-			// This is a placeholder for Gemini's resume logic
-		}
-	}
-
-	return args
-}