Reasoning API¶
The client.reasoning namespace exposes reasoning scaffolding and meta-learning controls that amplify model performance without changing the provider.
SDK proxy¶
crp.sdk.proxies._ReasoningProxy ¶
Reasoning / meta-learning proxy (SPEC-019, §12, §13).
Exposes reasoning scaffolds, source grounding retrieval, CQS detection, and cross-window validation.
scaffold(task, **kwargs) ¶
Build a reasoning scaffold for task.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
task | str | Task description. | required |
**kwargs | Any | Additional options forwarded to the meta-learning engine. | {} |
Returns:
| Type | Description |
|---|---|
str | Scaffold string (empty if scaffolding is disabled). |
sources(fact_id=None, **kwargs) ¶
Retrieve source passages linked to a fact.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
fact_id | str | None | Fact identifier. If | None |
**kwargs | Any | Additional filtering options. | {} |
Returns:
| Type | Description |
|---|---|
list[dict[str, Any]] | List of source passage dicts. |
cqs(signal) ¶
Detect Context Quality Signals (CQS) in signal.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
signal | str | Text to scan for context hunger signals. | required |
Returns:
| Type | Description |
|---|---|
dict[str, Any] | Dict describing detected signals and recommended action. |
cross_window_validate(windows, **kwargs) ¶
Run cross-window consistency validation.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
windows | list[str] | List of window output strings. | required |
**kwargs | Any | Additional options forwarded to the validator. | {} |
Returns:
| Type | Description |
|---|---|
dict[str, Any] | Dict with issues and severity counts. |
Meta-Learning Engine¶
crp.advanced.meta_learning.MetaLearningEngine ¶
ORC + ICML + RTL meta-learning capabilities.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
dispatch_fn | Callable[[str, str], tuple[str, Any]] | None | Callable accepting | None |
model_capability | int | Integer capability level of the active model. | 1 |
config | MetaLearningConfig | None |
| None |
trace_count property ¶
Return the number of traces currently stored in the RTL.
should_use_orc(task_complexity=3, resource_pressure='NONE', probe_quality=0.0) ¶
Gate check for ORC activation.
Gate 1: resource_pressure >= HIGH → False Gate 2: model_capability >= task_complexity → False Gate 3: probe_quality >= 0.7 → False (ORC unnecessary)
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
task_complexity | int | Estimated complexity of the task on a 1–5 scale. | 3 |
resource_pressure | str | Resource pressure label ("NONE", "LOW", "MODERATE", "HIGH", "CRITICAL"). | 'NONE' |
probe_quality | float | Quality score from a zero-shot probe; high values indicate ORC is unnecessary. | 0.0 |
Returns:
| Type | Description |
|---|---|
bool | True when ORC should be used to break the task into steps. |
orchestrated_reasoning(task_intent, task_complexity=3, resource_pressure='NONE') ¶
Decompose and execute an orchestrated reasoning chain.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
task_intent | str | Natural-language description of the task to solve. | required |
task_complexity | int | Estimated complexity of the task. | 3 |
resource_pressure | str | Resource pressure label; reduces the number of allowed steps under higher pressure. | 'NONE' |
Returns:
| Type | Description |
|---|---|
ORCResult | An |
ORCResult | answer. |
build_reasoning_scaffold(task_intent) ¶
Build a reasoning scaffold adapted to model capability.
Capability ≤ 1 (0.5B-1B): Full step-by-step template Capability ≤ 2 (2B-7B): Light approach Capability > 2: No scaffolding
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
task_intent | str | Task description to scaffold. | required |
Returns:
| Type | Description |
|---|---|
str | Scaffold string to prepend to the prompt, or an empty string when |
str | scaffolding is disabled. |
build_metacognitive_envelope(task_intent, base_envelope='', few_shot_traces=None) ¶
Build an envelope with reasoning scaffold + few-shot examples.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
task_intent | str | Task description. | required |
base_envelope | str | Existing envelope text to preserve, if any. | '' |
few_shot_traces | list[ReasoningTrace] | None | Optional explicit traces to include as examples. When omitted, the RTL is queried for matching traces. | None |
Returns:
| Type | Description |
|---|---|
str | Combined envelope string containing the base envelope, scaffold, |
str | and any few-shot examples. |
store_trace(trace) ¶
Store a reasoning trace if quality meets the configured threshold.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
trace | ReasoningTrace |
| required |
Returns:
| Type | Description |
|---|---|
bool | True when the trace was stored, False when RTL is disabled or the |
bool | trace quality is too low. |
to_dict() ¶
Serialize the engine and its trace library.
Returns:
| Type | Description |
|---|---|
dict[str, Any] | Dictionary with the trace library and active configuration. |