vox-effort-audit API Reference (generated)
Crate: vox-effort-audit · Version: 0.6.0 · Target: Library (lib.rs)
AI-judged audit of git commit history, ranking commits by estimated agent token spend
Crate Overview
Section titled “Crate Overview”AI-judged audit of git commit history.
See docs/superpowers/specs/2026-05-28-effort-audit-core-design.md.
Workspace Dependencies
Section titled “Workspace Dependencies”| Dependency | Kind |
|---|---|
vox-actor-runtime | Normal |
vox-config | Normal |
vox-git | Normal |
vox-telemetry | Normal |
Public API Surface
Section titled “Public API Surface”Modules
Section titled “Modules”| Module | Description |
|---|---|
config | — |
hybrid | — |
judge | — |
output | — |
pipeline | — |
pricing | — |
range | — |
shape | — |
walk | — |
Dependency Topology
Section titled “Dependency Topology”Diagram source
graph { direction: right node vox_effort_audit: "vox-effort-audit" node vox_actor_runtime: "vox-actor-runtime" vox_effort_audit -> vox_actor_runtime node vox_config: "vox-config" vox_effort_audit -> vox_config node vox_git: "vox-git" vox_effort_audit -> vox_git node vox_telemetry: "vox-telemetry" vox_effort_audit -> vox_telemetry node vox_cli: "vox-cli" vox_cli -> vox_effort_audit node vox_cli_research: "vox-cli-research" vox_cli_research -> vox_effort_audit node vox_effort_route: "vox-effort-route" vox_effort_route -> vox_effort_audit}Reverse Dependents (Used By)
Section titled “Reverse Dependents (Used By)”| Consumer Crate | Role |
|---|---|
vox-cli | Direct workspace dependent |
vox-cli-research | Direct workspace dependent |
vox-effort-route | Direct workspace dependent |
Deep Public Symbols (Source-Anchored)
Section titled “Deep Public Symbols (Source-Anchored)”| Kind | Symbol | Signature | Source | Description |
|---|---|---|---|---|
struct | config::EffortAuditConfig | pub struct EffortAuditConfig | crates/vox-effort-audit/src/config.rs#L8-L32 | — |
struct | config::JudgeConfig | pub struct JudgeConfig | crates/vox-effort-audit/src/config.rs#L35-L43 | — |
enum | hybrid::MeasuredCost | pub enum MeasuredCost | crates/vox-effort-audit/src/hybrid/mod.rs#L9-L22 | — |
struct | judge::JudgeOutcome | pub struct JudgeOutcome | crates/vox-effort-audit/src/judge/mod.rs#L17-L24 | — |
enum | judge::JudgeStatus | pub enum JudgeStatus | crates/vox-effort-audit/src/judge/mod.rs#L27-L31 | — |
enum | judge::SkipReason | pub enum SkipReason | crates/vox-effort-audit/src/judge/mod.rs#L34-L37 | — |
trait | judge::Judge | pub trait Judge: Send + Sync | crates/vox-effort-audit/src/judge/mod.rs#L40-L43 | — |
struct | judge::MockJudge | pub struct MockJudge | crates/vox-effort-audit/src/judge/mod.rs#L46-L49 | Deterministic in-memory judge for tests. |
struct | judge::LlmJudge | pub struct LlmJudge | crates/vox-effort-audit/src/judge/mod.rs#L96-L100 | Real judge wired through vox_actor_runtime::llm with the chosen model. All LLM I/O goes through vox_actor_runtime::llm::infer_with_retry. The model id is resolved upstream (orchestrator model registry) and passed in as resolved_model. The judge surface is intentionally vendor-agnostic — no provider hostnames or SDKs leak in here. See AGENTS.md §Model-Agnostic LLM Boundary. |
struct | output::FindingRow | pub struct FindingRow | crates/vox-effort-audit/src/output/mod.rs#L11-L23 | The top-level shape of one line in findings.jsonl. Stable schema_version=“1.0”. |
struct | output::JudgeMeta | pub struct JudgeMeta | crates/vox-effort-audit/src/output/mod.rs#L26-L32 | — |
struct | pipeline::RunSummary | pub struct RunSummary | crates/vox-effort-audit/src/pipeline.rs#L39-L44 | Summary returned to the caller after run finishes. Used by the CLI (F1) to print a one-liner without re-reading manifest.json. |
fn | pipeline::run | pub async fn run( | crates/vox-effort-audit/src/pipeline.rs#L68 | Run one vox audit effort pass. Composition: 1. Resolve the commit range (range::resolve). 2. Walk commits, computing diffs + shape features. 3. For each commit: resolve hybrid measured cost, check the per-run token budget, call the judge, emit a FindingRow line to findings.jsonl. 4. Render report.md + manifest.json. transcript_dir_override lets tests point at a fixture transcript tree; None means use cfg.transcript_dir. CLI bookend overrides (F1): - since_override: when Some, overrides cfg.default_since (the --since flag). Accepts the same forms as the TOML key ("30 days ago", "7d", git refs, dates). - until_override: when Some, overrides the default HEAD upper bound (the --until flag). Same form rules as since_override. cfg.limit, when set, caps the number of judged commits — commits past the cap are emitted with JudgeStatus::Skipped(LimitReached) so the manifest.json commits_in_range count still reflects the full walk. |
fn | pipeline::run_with_overrides | pub async fn run_with_overrides( | crates/vox-effort-audit/src/pipeline.rs#L92 | Same as [run] but accepts explicit --since / --until overrides from the CLI. Internal entry-point — keeps the public [run] signature stable for callers that don’t need to wire bookend overrides (tests, library use). |
struct | pricing::ModelRates | pub struct ModelRates | crates/vox-effort-audit/src/pricing.rs#L8-L13 | USD-per-1K-token rates for the resolved judge model. |
fn | pricing::cost_usd | pub fn cost_usd(&self, prompt_tokens: u64, completion_tokens: u64) -> Option<f64> | crates/vox-effort-audit/src/pricing.rs#L17-L25 | Real cost in USD, or None when pricing is unknown (NOT a fake 0.0). |
enum | range::CommitRange | pub enum CommitRange | crates/vox-effort-audit/src/range.rs#L7-L12 | — |
enum | range::RangeError | pub enum RangeError | crates/vox-effort-audit/src/range.rs#L15-L18 | — |
fn | range::parse_duration | pub fn parse_duration(s: &str) -> Result<Duration, RangeError> | crates/vox-effort-audit/src/range.rs#L25-L70 | Parses a duration string of the form NNd, NNh, or NNw (N = ASCII digits), or the long forms "N days ago" / "N hours ago" / "N weeks ago". The compact digits+suffix form requires the prefix to be ALL ASCII digits — refs like feature-2d or abc123d MUST NOT parse as durations. |
fn | range::resolve | pub fn resolve( | crates/vox-effort-audit/src/range.rs#L76 | Resolves CLI args + config default into a CommitRange. since_arg and until_arg are the raw --since/--until strings. If neither parses as a duration, both are treated as git refs. |
fn | range::duration_cutoff | pub fn duration_cutoff(now: DateTime<Utc>, d: Duration) -> DateTime<Utc> | crates/vox-effort-audit/src/range.rs#L94-L96 | For SinceDuration, the wall-clock cutoff at run time. |
struct | shape::ShapeFeatures | pub struct ShapeFeatures | crates/vox-effort-audit/src/shape.rs#L8-L18 | — |
enum | shape::CommitKind | pub enum CommitKind | crates/vox-effort-audit/src/shape.rs#L22-L32 | — |
fn | shape::features | pub fn features(rec: &CommitRecord) -> ShapeFeatures | crates/vox-effort-audit/src/shape.rs#L34-L79 | — |
struct | walk::CommitRecord | pub struct CommitRecord | crates/vox-effort-audit/src/walk.rs#L19-L30 | — |
struct | walk::FileChange | pub struct FileChange | crates/vox-effort-audit/src/walk.rs#L33-L37 | — |
enum | walk::WalkError | pub enum WalkError | crates/vox-effort-audit/src/walk.rs#L40-L45 | — |
fn | walk::iter_commits | pub fn iter_commits( | crates/vox-effort-audit/src/walk.rs#L48 | Iterates commits in the range, newest-first. |