plandex-ai/plandex · error

context body is too large: %d

Error message

context body is too large: %d

What it means

LoadContexts rejects any single incoming context whose body exceeds shared.MaxContextBodySize bytes. The size is computed as len(context.Body) server-side; the client should have prevented this, so the error indicates an oversized file/blob was submitted directly to the API.

Source

Thrown at app/server/db/context_helpers_load.go:116

	if err != nil {
		return nil, nil, fmt.Errorf("error getting existing contexts: %v", err)
	}

	// check overall context limits - these should be getting enforced by the client, so just error out if exceeded
	numExistingContexts := len(existingContexts)
	if numExistingContexts+len(*req) > shared.MaxContextCount {
		return nil, nil, fmt.Errorf("too many contexts: %d", numExistingContexts+len(*req))
	}

	var totalContextSize int64
	for _, context := range existingContexts {
		totalContextSize += context.BodySize
	}
	for _, context := range *req {
		size := int64(len(context.Body))
		totalContextSize += size
		if size > shared.MaxContextBodySize {
			return nil, nil, fmt.Errorf("context body is too large: %d", size)
		}
	}

	if totalContextSize > shared.MaxTotalContextSize {
		return nil, nil, fmt.Errorf("total context size is too large: %d", totalContextSize)
	}

	existingContextsByName := make(map[string]bool)
	for _, context := range existingContexts {
		composite := strings.Join([]string{context.Name, string(context.ContextType)}, "|")
		existingContextsByName[composite] = true

		if planConfig.AutoLoadContext && context.ContextType == shared.ContextMapType {
			totalMapTokens += context.NumTokens
			totalPlannerTokens -= context.NumTokens
		}

		if !context.AutoLoaded && context.ContextType != shared.ContextMapType {

View on GitHub (pinned to e2d772072e)

Solutions

1. Remove or ignore the oversized file (add it to .plandexignore / don't load it).
2. Load only the relevant portion of the file (split or excerpt it).
3. For generated files, exclude build/dependency directories from context loads.
4. If an API caller, check len(body) <= shared.MaxContextBodySize before submitting.

Example fix

// before: sending the whole file
data, _ := os.ReadFile("dist/bundle.js")
params := shared.LoadContextParams{Body: string(data)}
// after: guard on client side
const MaxContextBodySize = 200 * 1024 // shared.MaxContextBodySize
if len(data) > MaxContextBodySize {
	return fmt.Errorf("file too large for context: %d bytes", len(data))
}

func withinBodyLimit(body string) bool {
	return int64(len(body)) <= shared.MaxContextBodySize
}
for _, p := range reqParams {
	if !withinBodyLimit(p.Body) {
		return fmt.Errorf("skipping %s: body exceeds MaxContextBodySize", p.Name)
	}
}

_, err := client.LoadContexts(req)
if err != nil {
	if strings.Contains(err.Error(), "context body is too large") {
		// extract reported size, split or excerpt the offending file, resubmit
		return splitAndRetry(err)
	}
	return err
}

When it happens

Trigger: A LoadContexts request containing one context with len(Body) > shared.MaxContextBodySize — typically a very large file loaded via direct API call or an automation that skips client checks.

Common situations: Loading generated artifacts (build outputs, lockfiles, datasets, minified bundles) that exceed the per-context size cap; API scripts passing whole large files; binary files base64-bloated past the limit.

Related errors

• too many contexts: %d
• error getting org session: %v
• error committing plan build: %v
• Error storing plan result: planRes is nil
• Error storing plan build result: %v

AI-assisted analysis of plandex-ai/plandex@e2d772072e (2026-09-05). Data as JSON: /api/errors/a0f5b204ce327b00. Report an issue: GitHub.