log_pattern_assessment
Record architectural pattern assessments during codebase analysis to compute deterministic maturity scores for multi-agent systems.
Instructions
LOG ASSESSMENT — Record a pattern assessment for a consultation session. Call this during graph traversal (step 3) for each architectural pattern you identify in the user's codebase or confirm is missing. These stored assessments are what score_architecture uses to compute deterministic maturity scores.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| consultation_id | Yes | The consultation session ID from match_concepts | |
| pattern_id | Yes | The concept ID of the pattern being assessed | |
| pattern_name | Yes | Human-readable name of the pattern | |
| status | Yes | Whether the pattern is implemented, partial, missing, or not_applicable (pattern is irrelevant to this architecture, e.g. Agent Calls Human for a batch pipeline) | |
| evidence | No | File path or description of what was found (or not found) | |
| maturity_level | No | Assessed maturity level (1-6, default: 1) | |
| failure_context | No | Optional structured failure context for stress test demos. Fields: code_refs (list of {file, line, snippet}), failure_mode (string describing what breaks), depends_on (list of pattern_ids this depends on) |