What causes "Context %s exceeds size limit (size %.2f MB, limit %d MB)" in plandex-ai/plandex?

Trim or split the content before adding it as context

Context %s exceeds size limit (size %.2f MB, limit %d MB)

Error message

Context %s exceeds size limit (size %.2f MB, limit %d MB)

What it means

Each context's Body must be no larger than shared.MaxContextBodySize. If a single context body exceeds it, the server rejects the whole load with HTTP 400, reporting the size in MB against the MB limit.

Source

Thrown at app/server/handlers/context_helper.go:78

			for _, body := range context.MapBodies {
				if len(body) > shared.MaxContextMapSingleInputSize {
					log.Printf("Error: Map file %s exceeds size limit (size %d, limit %d)\n", context.FilePath, len(body), shared.MaxContextMapSingleInputSize)
					http.Error(w, fmt.Sprintf("Map file %s exceeds size limit (size %d, limit %d)", context.FilePath, len(body), shared.MaxContextMapSingleInputSize), http.StatusBadRequest)
					return nil, nil
				}
			}
		}

		if totalFiles > shared.MaxContextCount {
			log.Printf("Error: Too many contexts to load (found %d, limit is %d)\n", totalFiles, shared.MaxContextCount)
			http.Error(w, fmt.Sprintf("Too many contexts to load (found %d, limit is %d)", totalFiles, shared.MaxContextCount), http.StatusBadRequest)
			return nil, nil
		}

		fileSize := int64(len(context.Body))
		if fileSize > shared.MaxContextBodySize {
			log.Printf("Error: Context %s exceeds size limit (size %.2f MB, limit %d MB)\n", context.Name, float64(fileSize)/1024/1024, int(shared.MaxContextBodySize)/1024/1024)
			http.Error(w, fmt.Sprintf("Context %s exceeds size limit (size %.2f MB, limit %d MB)", context.Name, float64(fileSize)/1024/1024, int(shared.MaxContextBodySize)/1024/1024), http.StatusBadRequest)
			return nil, nil
		}

	}

	if mapFilesCount > 0 {
		log.Printf("[ContextHelper] Processing %d map files out of %d total contexts", mapFilesCount, totalFiles)
	}

	var err error

	var settings *shared.PlanSettings
	var clients map[string]model.ClientInfo
	var authVars map[string]string
	var orgUserConfig *shared.OrgUserConfig

	for _, context := range *loadReq {
		if context.ContextType == shared.ContextPipedDataType || context.ContextType == shared.ContextNoteType || context.ContextType == shared.ContextImageType {

View on GitHub (pinned to e2d772072e)

Solutions

Trim or split the content before adding it as context
Reference only the relevant portion of the large file
Compress/summarize large data instead of loading it whole

Example fix

// before
body, _ := os.ReadFile("huge.log")
client.LoadContexts(ctx, planId, branch, []shared.LoadContextParams{{Body: string(body)}})
// after
body, _ := os.ReadFile("huge.log")
if int64(len(body)) > shared.MaxContextBodySize {
    body = body[len(body)-int(shared.MaxContextBodySize):] // keep recent tail only
}
client.LoadContexts(ctx, planId, branch, []shared.LoadContextParams{{Body: string(body)}})

Defensive patterns

Strategy: validation

Validate before calling

for i := range loadReq {
    if int64(len(loadReq[i].Body)) > shared.MaxContextBodySize {
        return fmt.Errorf("context %s body %d bytes exceeds limit %d", loadReq[i].Name, len(loadReq[i].Body), shared.MaxContextBodySize)
    }
}

Prevention

Check file/piped size before adding context and truncate or summarize
Never pipe unbounded streams (logs, dumps) directly into context
Validate sizes client-side in scripts and automation

When it happens

Trigger: Loading any context (file, piped data, note, image) whose context.Body length exceeds shared.MaxContextBodySize — e.g. piping a huge log or adding a large generated file.

Common situations: Piping large datasets/logs into a plan (cat big.log | plandex); adding build artifacts or datasets; database dumps added as context files.

Related errors

AI-assisted analysis of plandex-ai/plandex@e2d772072e (2026-09-05). Data as JSON: /api/errors/a9f0f3776a4d70a5. Report an issue: GitHub.