# API Reference


## Scanning


Mine feedback events out of transcripts, incrementally.


[scan.scan()](scanning.md#cc_steer.scan.scan)  
Scans transcripts under `roots` for feedback, incrementally.

[scan.ScanReport](scanning.md#cc_steer.scan.ScanReport)  
The outcome of one scan pass.


## Detection


The signal detectors and the candidate shape they emit.


[detectors.detect()](detection.md#cc_steer.detectors.detect)  
Runs every detector over one transcript's events.

[models.FeedbackCandidate](detection.md#cc_steer.models.FeedbackCandidate)  
A single piece of developer pushback extracted from a transcript.

[models.dedup_key()](detection.md#cc_steer.models.dedup_key)  
Returns the stable dedup key for `parts`.


## Storage


The feedback event store.


[store.FeedbackStore](storage.md#cc_steer.store.FeedbackStore)  
Persistent store for collected feedback over the native mining engine.


## Retraining


The weekly retrain lanes -- gate and watcher -- and their promotion machinery.


[retrain.lexical.retrain_gate()](retraining.md#cc_steer.retrain.lexical.retrain_gate)  
One gate retrain pass; returns the journaled one-line verdict.

[retrain.watcher.retrain_watcher()](retraining.md#cc_steer.retrain.watcher.retrain_watcher)  
One watcher retrain pass; returns the journaled one-line verdict.

[retrain.watcher.WatcherRecipe](retraining.md#cc_steer.retrain.watcher.WatcherRecipe)  
Every knob of one watcher LoRA retrain, validated at parse so no degenerate value trains.

[retrain.watcher.register_watcher_adapter()](retraining.md#cc_steer.retrain.watcher.register_watcher_adapter)  
Register (and by default promote) a built mlx-lm adapter as the `watcher` component.

[retrain.watcher.seed_incumbent_probs()](retraining.md#cc_steer.retrain.watcher.seed_incumbent_probs)  
Validate an external incumbent probs cache against the frozen frame, then write it through the store.

[retrain.evalset.freeze_eval()](retraining.md#cc_steer.retrain.evalset.freeze_eval)  
Copy the exported `<view>/test.parquet` into the eval root and merge its sha256 manifest.

[retrain.evalset.freeze_steer_type()](retraining.md#cc_steer.retrain.evalset.freeze_steer_type)  
Build then freeze the steer-type eval; returns the frozen file's sha256.

[retrain.evalset.freeze_pick()](retraining.md#cc_steer.retrain.evalset.freeze_pick)  
Build then freeze the pick-prediction eval; returns the frozen file's sha256.

[retrain.evalset.EvalFrame](retraining.md#cc_steer.retrain.evalset.EvalFrame)  
The frozen watcher eval as the arrays the promotion gate reads.

[retrain.evalset.SteerTypeFrame](retraining.md#cc_steer.retrain.evalset.SteerTypeFrame)  
The frozen steer-type eval as the arrays a category classifier is scored on.

[retrain.evalset.PickFrame](retraining.md#cc_steer.retrain.evalset.PickFrame)  
The frozen pick-prediction eval as the arrays an option classifier is scored on.

[retrain.promotion.corrected_gate()](retraining.md#cc_steer.retrain.promotion.corrected_gate)  
Evaluate the corrected paired gate over common rows at matched budget.

[retrain.promotion.GateResult](retraining.md#cc_steer.retrain.promotion.GateResult)  
The corrected paired gate over a candidate and incumbent at matched budget.

[retrain.promotion.Verdict](retraining.md#cc_steer.retrain.promotion.Verdict)  
One promotion decision: whether to promote and the human-readable reason.


## Many-shot watcher


Score the frozen frame through a byte-constant, cache-amortized many-shot exemplar prefix.


[retrain.manyshot.build_exemplar_system()](many-shot-watcher.md#cc_steer.retrain.manyshot.build_exemplar_system)  
The byte-constant many-shot system prompt: seeded demonstrations under `budget_chars`.

[retrain.manyshot.score_frame()](many-shot-watcher.md#cc_steer.retrain.manyshot.score_frame)  
Score the frozen frame with a cached many-shot prefix and store its `P(NO_STEER)`.


## Encoder gate


Fine-tune a transformer encoder as the stage-1 gate and score it paired on the frozen gate frame.


[retrain.encoder.EncoderSpec](encoder-gate.md#cc_steer.retrain.encoder.EncoderSpec)  
Recipe for one encoder gate arm: the base model plus its fine-tune and calibration knobs.

[retrain.encoder.EncoderModel](encoder-gate.md#cc_steer.retrain.encoder.EncoderModel)  
A fine-tuned encoder head plus its fitted temperature and held-out calibration error.

[retrain.encoder.train_encoder()](encoder-gate.md#cc_steer.retrain.encoder.train_encoder)  
Fine-tune the encoder head on `train_frame`, temperature-scaled on a held-out val carve.

[retrain.encoder.score_frozen()](encoder-gate.md#cc_steer.retrain.encoder.score_frozen)  
Score the frozen gate eval and persist the calibrated `P(fire)` through `write_probs`.


## Instrument


Paired fast-DeLong AUC comparison and the instrument-card decision rule.


[instrument.delong_se()](instrument.md#cc_steer.instrument.delong_se)  
Return the DeLong standard error of a single AUC.

[instrument.paired_delong()](instrument.md#cc_steer.instrument.paired_delong)  
Compare two score vectors on identical labels with a paired fast-DeLong test.

[instrument.PairedDeLong](instrument.md#cc_steer.instrument.PairedDeLong)  
Result of a paired fast-DeLong comparison of two score vectors on shared labels.

[instrument.bootstrap_ci()](instrument.md#cc_steer.instrument.bootstrap_ci)  
Nonparametric bootstrap 95% CI of the AUC (E27 harness resampling).

[instrument.mde()](instrument.md#cc_steer.instrument.mde)  
Minimum detectable effect for a two-sided z-test at the given standard error.

[instrument.actionable()](instrument.md#cc_steer.instrument.actionable)  
Apply the instrument card's two-part actionability rule to an AUC delta.

[instrument.InstrumentCard](instrument.md#cc_steer.instrument.InstrumentCard)  
The measurement-instrument card: the frame noise floors comparative verdicts consult.

[instrument.Comparison](instrument.md#cc_steer.instrument.Comparison)  
A card-governed comparative verdict between two checkpoints' AUCs on one frame.

[instrument.paired_verdict()](instrument.md#cc_steer.instrument.paired_verdict)  
The card rule over a paired DeLong record -- the production comparative verdict.

[instrument.unpaired_verdict()](instrument.md#cc_steer.instrument.unpaired_verdict)  
The card rule when a counterpart's per-row probs were never persisted.

[retrain.sweep.ArmScore](instrument.md#cc_steer.retrain.sweep.ArmScore)  
One arm's frozen-frame measurement: the scalar metric and the per-row probs behind it.

[retrain.sweep.compare_score_reports()](instrument.md#cc_steer.retrain.sweep.compare_score_reports)  
Card-governed verdict between two arms' score reports -- paired DeLong as the production default.


## Decisions


Mine AskUserQuestion decision rounds from transcript trees into a parquet dataset.


[decisions.mine()](decisions.md#cc_steer.decisions.mine)  
Mine every `AskUserQuestion` decision round under `root`.

[decisions.DecisionRow](decisions.md#cc_steer.decisions.DecisionRow)  
One `AskUserQuestion` round: the question, its options, and the user's pick.

[decisions.MineResult](decisions.md#cc_steer.decisions.MineResult)  
The mined decision rows and the quarantined, un-typed uses.

[decisions.Quarantine](decisions.md#cc_steer.decisions.Quarantine)  
An `AskUserQuestion` use whose result carries no typed rounds.

[decisions.write_decisions()](decisions.md#cc_steer.decisions.write_decisions)  
Write the mined rows to `out` as parquet, stamping the digest and quarantine count.

[decisions.read_decisions()](decisions.md#cc_steer.decisions.read_decisions)  
Read a decisions parquet back into rows, its digest, and its quarantine count.

[decisions.stats_of()](decisions.md#cc_steer.decisions.stats_of)  
Aggregate mined rows into the counts the `decisions stats` command prints.

[decisions.DecisionStats](decisions.md#cc_steer.decisions.DecisionStats)  
Aggregate counts over a decisions dataset.