OptimizationCandidate interface
Aggregated evaluation result for a single candidate agent configuration across all tasks.
Properties
| avg_score | Average composite score across all tasks. |
| avg_tokens | Average token usage across all tasks. |
| candidate_id | Server-assigned candidate identifier. Use with GET /candidates/{id} sub-endpoints. |
| eval_id | Foundry evaluation identifier used to score this candidate. |
| eval_run_id | Foundry evaluation run identifier for this candidate's scoring run. |
| mutations | What was mutated from the baseline (e.g., {system_prompt: 'new prompt'}). |
| name | Display name of the candidate (e.g., 'baseline', 'instruction-v2'). |
| promotion | Promotion metadata. Null if the candidate has not been promoted. |
Property Details
avg_score
Average composite score across all tasks.
avg_score: numberProperty Value
number
avg_tokens
Average token usage across all tasks.
avg_tokens: numberProperty Value
number
candidate_id
Server-assigned candidate identifier. Use with GET /candidates/{id} sub-endpoints.
candidate_id?: stringProperty Value
string
eval_id
Foundry evaluation identifier used to score this candidate.
eval_id?: stringProperty Value
string
eval_run_id
Foundry evaluation run identifier for this candidate's scoring run.
eval_run_id?: stringProperty Value
string
mutations
What was mutated from the baseline (e.g., {system_prompt: 'new prompt'}).
mutations?: Record<string, any>Property Value
Record<string, any>
name
Display name of the candidate (e.g., 'baseline', 'instruction-v2').
name: stringProperty Value
string
promotion
Promotion metadata. Null if the candidate has not been promoted.
promotion?: PromotionInfo