Struct RunFlags 

pub struct RunFlags {
    pub modified_files: Vec<String>,
    pub modified_file_count: usize,
    pub empty_output: bool,
    pub no_output_tools: bool,
    pub max_iterations_hit: usize,
    pub gates_forced: usize,
    pub workspace_lost: bool,
}

Post-hoc diagnosis of a run’s productivity, persisted in meta.json so a harness (or the dashboard) can tell an empty run from a successful one without inspecting the workspace or parsing logs.

The motivating failure: 13/300 SWE-bench runs completed their whole stage pipeline and produced no file changes at all. Nothing on disk said so, or said why.

Fields

modified_files: Vec<String>

Paths passed to file-modifying tools that succeeded, in first-touch order. Capped at MAX_TRACKED_MODIFIED_FILES; modified_file_count keeps the true total.

modified_file_count: usize

Total successful file-modifying tool calls across the run (uncapped).

empty_output: bool

The run reached a terminal status having modified nothing, and its blueprint gave it a way to modify something. See Self::no_output_tools.

no_output_tools: bool

No stage of the blueprint advertised a file-modifying tool, so this run could never have produced the file changes empty_output looks for.

Recorded because “modified no files” only diagnoses an agent that was supposed to modify files. A router that spawns sub-agents, or an agent whose answer is its text, would otherwise report itself empty on every successful run - which is what happened in issue #192. The framework has no basis to judge such a run, so it says nothing rather than accusing.

This mirrors the escape the runtime’s gate_blocks already applies per stage: a require_modifications gate on a stage that advertises no modifying tool is skipped, because it could never pass.

Phrased negatively so the false that Default and serde(default) produce means “was capable” - the behavior every meta.json written before this field had.

max_iterations_hit: usize

How many stages exhausted their max_iterations.

gates_forced: usize

How many transitions proceeded past an unsatisfied gate because the gate’s re-run budget ran out.

workspace_lost: bool

The working directory disappeared mid-run.

Implementations

impl RunFlags

pub fn record_modification(&mut self, path: &str)

Record a successful modifying tool call on path.

Trait Implementations

impl Clone for RunFlags

fn clone(&self) -> RunFlags

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RunFlags

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

Formats the value using the given formatter.

impl Default for RunFlags

fn default() -> RunFlags

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for RunFlags

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for RunFlags

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for RunFlags

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 RunFlags