Struct Evidence 

pub struct Evidence {

    pub runs: usize,
    pub sessions_read: usize,
    pub model: String,
    pub tool_calls: u64,
    pub tool_errors: u64,
    pub tool_error_rate: Option<f64>,
    pub ended_on_failed_call: usize,
    pub ended_on_failed_call_rate: Option<f64>,
    pub compactions: u64,
    pub stop_causes: Vec<(String, usize)>,
    pub mean_peak_context_pressure: Option<f64>,
    pub mean_anticipated_guilt: Option<f64>,
    pub findings: Vec<String>,
    pub history: Vec<String>,
}

Everything the diagnostician is allowed to be handed about a corpus.

Numbers and findings. There is no field for a transcript excerpt, no constructor that takes one, and that absence is the safety property — see the module docs.

Fields

runs: usize

sessions_read: usize

model: String

tool_calls: u64

tool_errors: u64

tool_error_rate: Option<f64>

ended_on_failed_call: usize

ended_on_failed_call_rate: Option<f64>

compactions: u64

stop_causes: Vec<(String, usize)>

mean_peak_context_pressure: Option<f64>

Average Homeostat::peak_context_pressure over the runs that sensed it (docs/GOAL-SYSTEM-DESIGN.md §4 into this brief) — the machine’s own conditions, beside what runs did. A counter like every other field here: the diagnostician judges what a high number means, this module only reports it.

mean_anticipated_guilt: Option<f64>

Average Homeostat::anticipated_guilt over the runs that sensed it (crate::guilt). The sensor has no behavioural consumer yet; this is the corpus existing before anything is built on it.

Not independent of Self::mean_peak_context_pressure above it. crate::guilt::anticipated_guilt’s own formula takes context pressure as one of its three terms, so the two fields will move together by construction whenever pressure is what is driving guilt up — a reader treating a rise in both as two corroborating signals is seeing one cause twice.

findings: Vec<String>

What doctor said, verbatim — machine-authored text, not third-party.

history: Vec<String>

What earlier passes already tried, one line each — machine-authored from the harness candidate store, the way the learner is shown retired rules. Without it a nightly diagnostician re-derives the same rejected change forever, and every night costs a measurement that was already paid for.

Implementations

impl Evidence

pub fn of(model: &str, corpus: &Corpus) -> Evidence

Summarise one model’s slice of the corpus.

pub fn brief(&self) -> String

Render the brief the model is handed.

A rate with no denominator prints as unknown, never as zero: “nothing went wrong” and “nothing happened” are different, and a diagnostician told the second reads it as the first.

Trait Implementations

impl Clone for Evidence

fn clone(&self) -> Evidence

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Evidence

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Evidence

fn default() -> Evidence

Returns the “default value” for a type.