observation.bufferActivation as absolute retention (${this.o

Error message

observation.bufferActivation as absolute retention (${this.observationConfig.bufferActivation}) must be less than messageTokens (${observationThreshold})

What it means

When observation.bufferActivation is used in absolute mode (>= 1000), it represents a retention window in tokens and must be smaller than the messageTokens threshold. If the retention window is as large as or larger than the threshold, activation would never fire in a meaningful window relative to message processing, so the constructor rejects the configuration.

Source

Thrown at packages/memory/src/processors/observational-memory/observational-memory.ts:1009

        );
      }
    }

    // Validate observation bufferActivation: (0, 1] for ratio, or >= 1000 for absolute retention tokens
    if (this.observationConfig.bufferActivation !== undefined) {
      if (this.observationConfig.bufferActivation <= 0) {
        throw new Error(`observation.bufferActivation must be > 0, got ${this.observationConfig.bufferActivation}`);
      }
      if (this.observationConfig.bufferActivation > 1 && this.observationConfig.bufferActivation < 1000) {
        throw new Error(
          `observation.bufferActivation must be <= 1 (ratio) or >= 1000 (absolute token retention), got ${this.observationConfig.bufferActivation}`,
        );
      }
      if (
        this.observationConfig.bufferActivation >= 1000 &&
        this.observationConfig.bufferActivation >= observationThreshold
      ) {
        throw new Error(
          `observation.bufferActivation as absolute retention (${this.observationConfig.bufferActivation}) must be less than messageTokens (${observationThreshold})`,
        );
      }
    }

    // Validate observation blockAfter
    if (this.observationConfig.blockAfter !== undefined) {
      if (this.observationConfig.blockAfter < observationThreshold) {
        throw new Error(
          `observation.blockAfter (${this.observationConfig.blockAfter}) must be >= messageTokens (${observationThreshold})`,
        );
      }
      if (!this.observationConfig.bufferTokens) {
        throw new Error(
          `observation.blockAfter requires observation.bufferTokens to be set (blockAfter only applies when async buffering is enabled)`,
        );
      }
    }

View on GitHub (pinned to 75dd419e61)

Solutions

Lower bufferActivation below the messageTokens threshold.
Raise observation.messageTokens above your desired absolute retention value.
Switch to ratio mode (bufferActivation <= 1) so retention scales with messageTokens automatically.

Example fix

// before
new ObservationalMemory({ observation: { messageTokens: 4000, bufferActivation: 6000 } });
// after
new ObservationalMemory({ observation: { messageTokens: 8000, bufferActivation: 6000 } });

Defensive patterns

Strategy: validation

Validate before calling

const observationThreshold = getMaxThreshold(observationConfig.messageTokens);
if (observationConfig.bufferActivation !== undefined && observationConfig.bufferActivation >= 1000 && observationConfig.bufferActivation >= observationThreshold) {
  throw new Error(`bufferActivation (${observationConfig.bufferActivation}) must be < messageTokens (${observationThreshold})`);
}

Prevention

Tune messageTokens and bufferActivation together, not independently.
Prefer ratio mode (<= 1) to avoid threshold coupling.
Re-validate config after any change to messageTokens.

When it happens

Trigger: new ObservationalMemory({ observation: { messageTokens: 4000, bufferActivation: 4000 } }) or bufferActivation: 10000 with default/lower messageTokens.

Common situations: Raising bufferActivation for more context retention without checking messageTokens; combining a large absolute bufferActivation copied from another project with a smaller messageTokens here.

Understand the failure class

Background: "Invalid value" and "allowed values are" config errors: what your library rejected and how to fix it — this error's family across 41 libraries.

Related errors

AI-assisted analysis of mastra-ai/mastra@75dd419e61 (2026-08-30). Data as JSON: /api/errors/e13eec2d0077f821. Report an issue: GitHub.