plandex-ai/plandex · error

map input %s is too large: %d

Error message

map input %s is too large: %d

What it means

For map-type contexts, UpdateContexts validates each entry in params.MapBodies against shared.MaxContextMapSingleInputSize (500KB per path). If any single file's map part exceeds this limit, the update is rejected with the offending path and byte size. The CLI normally truncates oversized files upstream (getMapFileDetails), so this fires when raw/untruncated bodies are sent.

Source

Thrown at app/server/db/context_helpers_update.go:266

	errCh = make(chan error, len(*req))

	for id, params := range *req {
		go func(id string, params *shared.UpdateContextParams) {
			defer func() {
				if r := recover(); r != nil {
					log.Printf("panic in UpdateContexts: %v\n%s", r, debug.Stack())
					errCh <- fmt.Errorf("panic in UpdateContexts: %v\n%s", r, debug.Stack())
					runtime.Goexit() // don't allow outer function to continue and double-send to channel
				}
			}()
			context := contextsById[id]

			if context.ContextType == shared.ContextMapType {
				oldNumTokens := context.NumTokens

				for path, part := range params.MapBodies {
					if len(part) > shared.MaxContextMapSingleInputSize {
						errCh <- fmt.Errorf("map input %s is too large: %d", path, len(part))
						return
					}

					if context.MapParts == nil {
						context.MapParts = make(shared.FileMapBodies)
					}
					if context.MapShas == nil {
						context.MapShas = make(map[string]string)
					}
					if context.MapTokens == nil {
						context.MapTokens = make(map[string]int)
					}
					if context.MapSizes == nil {
						context.MapSizes = make(map[string]int64)
					}

					// prevNumTokens := context.MapTokens[path]

View on GitHub (pinned to e2d772072e)

Solutions

1. Exclude the oversized path from the map update (add it to ignore patterns so it isn't mapped)
2. Split the file or map only a summary/truncated portion of it
3. Check the client's truncation logic (shared getMapFileDetails truncates to MaxContextMapSingleInputSize) is actually running
4. If the file is legitimately needed, reduce its size or store the relevant excerpt instead of the whole file

Example fix

// before
mapBodies[path] = fullFileBytes // may exceed 500KB
// after
const maxPart = 500 * 1024
if len(fullFileBytes) > maxPart {
    fullFileBytes = fullFileBytes[:maxPart]
}
mapBodies[path] = fullFileBytes

const maxSingleInput = 500 * 1024
for path, part := range mapBodies {
    if len(part) > maxSingleInput {
        return fmt.Errorf("path %s is %d bytes (max %d)", path, len(part), maxSingleInput)
    }
}

err := updateContexts(req)
if err != nil && strings.Contains(err.Error(), "is too large") {
    // drop or truncate the named path and retry
    var path string; var size int
    fmt.Sscanf(err.Error(), "map input %s is too large: %d", &path, &size)
    delete(req.MapBodies, path)
    return updateContexts(req)
}

When it happens

Trigger: An UpdateContexts call for a map context includes a MapBodies entry whose []byte length > 500*1024 — e.g. a very large generated file, minified bundle, lock file, or dataset committed to the repo and mapped without truncation.

Common situations: Large vendored dependencies, node_modules snapshots, compiled artifacts, video/binary blobs, or generated logs included in the plan's file map.

Related errors

• map has too many paths: %d
• map total size is too large: %d
• invalid context index: %s
• no context found with name: %s
• invalid value: %s

AI-assisted analysis of plandex-ai/plandex@e2d772072e (2026-09-05). Data as JSON: /api/errors/1c582f51af4703d4. Report an issue: GitHub.