Domain Workflow¶
Domain-Expert Workflow Generation — reusable harness synthesis (spec: custom_agent_harness.md).
Cluster: Uncategorised | Type: component | MCP Tools: None
Overview¶
Public API¶
HarnessArtifacts¶
Which §6.1 harness-package artifacts are actually present (not assumed).
| Field | Type | Default |
|---|---|---|
runs_end_to_end_on_unseen | bool | False |
produces_declared_format | bool | False |
has_workflow_graph | bool | False |
has_rule_ledger | bool | False |
skill_file_count | int | 0 |
skills_have_routing_heuristics | bool | False |
has_rubric | bool | False |
has_eval_suite | bool | False |
has_known_limitations | bool | False |
has_versioned_manifest | bool | False |
has_tool_policy | bool | False |
has_injection_handling | bool | False |
has_escalation_policy | bool | False |
has_failure_mode_docs | bool | False |
has_run_report | bool | False |
has_user_docs | bool | False |
has_maintainer_docs | bool | False |
has_rollback_metadata | bool | False |
composable | bool | False |
EvalSummary¶
Results of running the harness's OWN generated eval suite (§8.2 manifest).
| Field | Type | Default |
|---|---|---|
pass_rate | float \| None | None |
has_golden_tests | bool | False |
has_adversarial_tests | bool | False |
has_regression_tests | bool | False |
has_hard_rule_tests | bool | False |
hard_rule_violation_rate | float | 0.0 |
prompt_injection_success_rate | float | 0.0 |
unsafe_external_action_rate | float | 0.0 |
required_escalation_miss_rate | float | 0.0 |
outperforms_baseline | bool \| None | None |
unresolved_hard_rule_conflicts | int | 0 |
Methods:
blocking_failures(minimum_pass_rate: float = 0.9) -> list[str]¶
The §8.2 blocking requirements that are violated (empty == none).
HarnessCard¶
The §14.1 registry card — honest summary incl. the real eval status.
| Field | Type | Default |
|---|---|---|
harness_id | str | required |
version | str | required |
domain | str | required |
task | str | required |
achieved_tier | str | required |
reliability_label | str | required |
latest_pass_rate | float \| None | required |
blocking_failures | int | required |
when_to_use | list[str] | field(default_factory=list) |
when_not_to_use | list[str] | field(default_factory=list) |
missing_for_next_tier | list[str] | field(default_factory=list) |
Methods:
to_dict() -> dict¶
HarnessAssessment¶
| Field | Type | Default |
|---|---|---|
achieved_tier | str | required |
reliability_label | str | required |
constraint_complete | bool | required |
missing_constraints | list[str] | field(default_factory=list) |
blocking_reasons | list[str] | field(default_factory=list) |
missing_for_next_tier | list[str] | field(default_factory=list) |
prompt_generator_trap | bool | False |
over_claimed | bool | False |
Methods:
to_dict() -> dict¶
Functions¶
check_constraint_completeness(artifacts: HarnessArtifacts) -> tuple[bool, list[str]]¶
Return (complete, missing[]) per §12.2.
completeiff nothing is missing.
is_prompt_generator_trap(artifacts: HarnessArtifacts) -> bool¶
§20 — output that lacks the structural harness core (graph + a skill + an eval suite)
assess_harness(artifacts: HarnessArtifacts, evals: EvalSummary, claimed_tier: str | None = None, minimum_pass_rate: float = 0.9) -> HarnessAssessment¶
Deterministically assess the harness's REAL tier + honest reliability label (§18).
build_harness_card(harness_id: str, version: str, domain: str, task: str, assessment: HarnessAssessment, evals: EvalSummary, when_to_use: list[str] | None = None, when_not_to_use: list[str] | None = None) -> HarnessCard¶
Assemble the §14.1 registry card with the HONEST eval status + achieved tier.