mastra-ai/mastra · error

Cannot set both `model` and `reflection.model`. Use `model`

Error message

Cannot set both `model` and `reflection.model`. Use `model` to set both agents, or set each individually.

What it means

Same ambiguity rule as for observation.model: the top-level model cannot be combined with reflection.model. The constructor rejects the config so it's clear which model the reflection agent uses.

Source

Thrown at packages/memory/src/processors/observational-memory/observational-memory.ts:475

      }
    }
  }

  constructor(config: ObservationalMemoryConfig) {
    if (!coreFeatures.has('request-response-id-rotation')) {
      throw new Error(
        'Observational memory requires @mastra/core support for request-response-id-rotation. Please bump @mastra/core to a newer version.',
      );
    }

    // Validate that top-level model is not used together with sub-config models
    if (config.model && config.observation?.model) {
      throw new Error(
        'Cannot set both `model` and `observation.model`. Use `model` to set both agents, or set each individually.',
      );
    }
    if (config.model && config.reflection?.model) {
      throw new Error(
        'Cannot set both `model` and `reflection.model`. Use `model` to set both agents, or set each individually.',
      );
    }

    this.shouldObscureThreadIds = config.obscureThreadIds || false;
    this.storage = config.storage;
    this.scope = config.scope ?? 'thread';
    this.retrieval = Boolean(config.retrieval);
    this.retrievalScope = typeof config.retrieval === 'object' ? (config.retrieval.scope ?? 'resource') : 'resource';
    this.retrievalInstructions = typeof config.retrieval === 'object' ? config.retrieval.instructions : undefined;
    this.retrievalSearch = typeof config.retrieval === 'object' && Boolean(config.retrieval.vector);
    this.onIndexObservations = config.onIndexObservations;
    this.hooks = config.hooks;
    this.hookExecution = config.hookExecution ?? 'non-blocking';
    this.mastra = config.mastra;
    this.memory = config.memory;
    this.curationCadence = config.curationCadence;

View on GitHub (pinned to 75dd419e61)

Solutions

1. Remove the top-level model and specify observation.model and reflection.model individually, OR
2. Remove reflection.model so the top-level model applies to both agents
3. When merging configs, delete the top-level model key if a sub-config model exists

Example fix

// before
new ObservationalMemory({ model: gpt4o, reflection: { model: claude } })
// after
new ObservationalMemory({ observation: { model: gpt4o }, reflection: { model: claude } })

if (config.model && config.reflection?.model) {
  throw new Error('Set either top-level model or reflection.model, not both');
}

function hasConsistentModelConfig(c: ObservationalMemoryConfig): boolean {
  return !(c.model && (c.observation?.model || c.reflection?.model));
}

try {
  const mem = new ObservationalMemory(config);
} catch (err) {
  if (err instanceof Error && err.message.includes('Cannot set both `model` and `reflection.model`')) {
    delete config.reflection.model; // let top-level model apply
  } else throw err;
}

When it happens

Trigger: new ObservationalMemory({ model: m1, reflection: { model: m2, ... } }) — top-level model present alongside reflection.model.

Common situations: Setting a default model at top level then customizing only reflection via sub-config; merging base and override config objects where both end up specifying reflection models.

Related errors

• Cannot set both `model` and `observation.model`. Use `model`
• Cookie password must be at least 32 characters. Set WORKOS_C
• Factory rule version is required.
• ${label} must be an object.
• Factory rules must be an object.

AI-assisted analysis of mastra-ai/mastra@75dd419e61 (2026-08-30). Data as JSON: /api/errors/4fe62cfd9aa42db5. Report an issue: GitHub.