Struct RunReport 

pub struct RunReport {

    pub run_id: String,
    pub feature: String,
    pub task: String,
    pub worktree: String,
    pub attempt_status: String,
    pub model_report: Option<Value>,
    pub reason: Option<String>,
    pub pending: Option<Value>,
    pub tool_calls: Vec<Value>,
    pub changes: Vec<(String, String)>,
    pub verification: Option<VerifyReport>,
    pub verdict: Option<Verdict>,
    pub usage: Option<Value>,
    pub integrity: Vec<String>,
    pub ticked: bool,
    pub commit: Option<String>,
    pub acceptance: Option<Value>,
    pub earlier: Vec<EarlierAttempt>,
    pub retry_stop: Option<String>,
    pub saved_attempt: Option<String>,
    pub set_aside: Option<String>,
    pub notices: Vec<String>,
    pub agent: Option<AgentAttempt>,
    pub monitor: Option<Value>,
    pub mutation: Option<Value>,
    pub samples: Vec<Value>,
    pub scope: Option<ScopeFinding>,
    pub attestation: Option<Value>,
    pub instructions: Vec<InstructionFile>,
    pub strength: Option<AcceptanceStrength>,
    pub bug: Option<Box<BugReport>>,
    pub collection: Option<Collection>,
    pub regression: Option<Regression>,
    pub context: Option<ContextManifest>,
}

Result of speccoder run.

Fields

run_id: String

The agentplane run of the attempt.

feature: String

Feature directory name.

task: String

Task ID.

worktree: String

The worktree the attempt worked in.

attempt_status: String

completed, blocked, needs_approval, budget_exhausted or failed.

model_report: Option<Value>

The model’s own closing report — its claim, not the verdict.

reason: Option<String>

Why the attempt stopped, when it did not complete.

pending: Option<Value>

The call awaiting approval, if any.

tool_calls: Vec<Value>

Every tool call with the policy’s decision.

changes: Vec<(String, String)>

Paths changed between the checkpoints: added / modified / deleted.

verification: Option<VerifyReport>

Checks after the attempt, compared with the baseline.

verdict: Option<Verdict>

The verifier’s verdict (only for completed attempts).

usage: Option<Value>

Token usage summed over the attempt’s turns.

integrity: Vec<String>

Integrity findings of the attempt’s diff (each also fails the verdict).

ticked: bool

The engine ticked the task in the worktree’s tasks.md.

commit: Option<String>

The commit on speccoder/<feature> holding the attempt and the tick.

acceptance: Option<Value>

Spec-derived acceptance tests: files, command, red/green, notes.

earlier: Vec<EarlierAttempt>

Earlier attempts at this task in this run, discarded and retried.

retry_stop: Option<String>

Why no further attempt was made after a failed one, if it failed.

saved_attempt: Option<String>

The ref this attempt was saved under when it did not pass; the worktree went back to where it started.

set_aside: Option<String>

The ref uncommitted leftovers were saved under before this run.

notices: Vec<String>

Things a person should know that are not part of the verdict.

agent: Option<AgentAttempt>

The external agent that made the attempt over ACP: its mode, its plan (a claim) and what speccoder decided of what it asked.

monitor: Option<Value>

The gaming monitor’s view of a passing attempt: suspected, findings, usage (or error). Never shown to the implementer.

mutation: Option<Value>

Mutation testing of the attempt’s changes: tool, caught, missed, timeout, unviable, survivors (or error).

samples: Vec<Value>

Best-of-n: every sample’s evidence and which one was kept.

scope: Option<ScopeFinding>

Changes outside the paths the task names: reported, never gated.

attestation: Option<Value>

What the tick’s attestation came to: { state: signed | unsigned | missing, signer, reason }.

instructions: Vec<InstructionFile>

The repository’s instructions the attempt was given (AGENTS.md, CLAUDE.md, …), root first.

strength: Option<AcceptanceStrength>

The acceptance set’s strength: after a verified verdict.

bug: Option<Box<BugReport>>

A bug task: the bug as this run left it (reproduce, confirm, the fix’s discrimination).

collection: Option<Collection>

The test files the attempt added or changed, and whether the run collected a test from each.

regression: Option<Regression>

Why a regression-only verdict is one (set with that verdict only).

context: Option<ContextManifest>

What reached the implementer, by digest (constitution VIII).

Trait Implementations

impl Clone for RunReport

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RunReport

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

Formats the value using the given formatter.

impl JsonSchema for RunReport

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for RunReport

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for RunReport

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for RunReport