Method RunPerFile

internal/llmloop/loop.go:149–268

RunPerFile drives the main LLM conversation loop for a single file. It sends messages with the configured tool definitions, executes any tool calls returned by the model, and collects review comments until task_done is called or limits are reached. Token usage and warnings are aggregated on the Runn

(ctx context.Context, messages []llm.Message, newPath string)

// are aggregated on the Runner across all files. The returned bool is true
// only when the model explicitly calls task_done.
func (r *Runner) RunPerFile(ctx context.Context, messages []llm.Message, newPath string) (bool, error) {
	toolReqCount := r.deps.Template.MaxToolRequestTimes
	const maxConsecutiveEmptyRounds = 3
	consecutiveEmptyRounds := 0
	sessionID := uuid.NewString()

	// Async compression is owned by this conversation alone; the deferred
	// cancel aborts any job still in flight when the conversation ends.
	st := &compressionState{}
	defer r.cancelPendingCompression(st)

	for toolReqCount > 0 {
		select {
		case <-ctx.Done():
			return false, ctx.Err()
		default:
		}

		toolReqCount--

		fs := r.deps.Session.GetOrCreateFileSession(newPath)
		rec := fs.AppendTaskRecord(session.MainTask, append([]llm.Message(nil), messages...))
		startTime := time.Now()

		_, llmSpan := telemetry.StartLLMSpan(ctx, r.deps.Model)
		resp, err := r.deps.LLMClient.CompletionsWithCtx(ctx, llm.ChatRequest{
			Model:     r.deps.Model,
			Messages:  messages,
			Tools:     r.deps.MainToolDefs,
			MaxTokens: r.deps.Template.MaxTokens,
			SessionID: sessionID,
		})
		duration := time.Since(startTime)
		if err != nil {
			rec.SetError(err, duration)
			telemetry.RecordLLMResult(llmSpan, duration, 0, err)
			llmSpan.End()
			telemetry.RecordLLMRequest(ctx, r.deps.Model, duration, 0, "error")
			return false, fmt.Errorf("LLM completion error: %w", err)
		}
		rec.SetResponse(resp, duration)
		totalTokens := int64(0)
		if resp.Usage != nil {
			totalTokens = resp.Usage.TotalTokens
			atomic.AddInt64(&r.totalInputTokens, resp.Usage.PromptTokens)
			atomic.AddInt64(&r.totalOutputTokens, resp.Usage.CompletionTokens)
			atomic.AddInt64(&r.totalCacheReadTokens, resp.Usage.CacheReadTokens)
			atomic.AddInt64(&r.totalCacheWriteTokens, resp.Usage.CacheWriteTokens)
		}
		telemetry.RecordLLMResult(llmSpan, duration, totalTokens, nil)
		llmSpan.End()
		telemetry.RecordLLMRequest(ctx, r.deps.Model, duration, totalTokens, "ok")

		content := resp.Content()
		calls := resp.ToolCalls()

		if len(calls) == 0 {
			fmt.Fprintf(stdout.Writer(), "[ocr] No tool calls parsed for %s, retrying...\n", newPath)