Struct CognitiveState 

pub struct CognitiveState {

    pub input: String,
    pub stream_outputs: HashMap<String, LobeOutput>,
    pub synthesis_result: Option<String>,
    pub budget_tokens: Option<u32>,
    pub loaded_memories: Vec<String>,
    pub working_notes: Vec<WorkingNote>,
    pub current_plan: Option<String>,
    pub confidence: f64,
    pub quality_trend: Vec<f64>,
    pub error_history: Vec<String>,
    pub signals: Vec<CognitiveSignal>,
    pub negative_knowledge: Vec<NegativeKnowledge>,
    pub failure_records: Vec<FailureRecord>,
}

State for the inner cognitive subgraph.

Defines the fields the cognitive architecture operates on. Separate from the outer task state. Implements State so it can be used with CompiledGraph<CognitiveState> directly.

Merge semantics

Last-value-wins (replace): input, synthesis_result, budget_tokens, current_plan, confidence

Merge (HashMap extend): stream_outputs — new keys overwrite, old keys preserved. Key is CognitiveStream::lens or Lobe::name().

Append (Vec extend): loaded_memories, working_notes, quality_trend, error_history, signals, negative_knowledge, failure_records

Fields

input: String

The input prompt/task the agent is processing.

stream_outputs: HashMap<String, LobeOutput>

Full outputs from each cognitive lobe, keyed by lobe name.

Stores the complete LobeOutput (content + confidence + signals + metadata) so the synthesizer receives lossless data. The key is Lobe::name().

synthesis_result: Option<String>

The synthesized result from synthesis node.

budget_tokens: Option<u32>

Token budget for cognitive processing (fraction of agent’s budget).

loaded_memories: Vec<String>

Relevant memories loaded for this cognitive cycle.

working_notes: Vec<WorkingNote>

Agent’s scratchpad — structured notes with categories.

current_plan: Option<String>

What the agent thinks it should do next.

confidence: f64

Confidence level (0.0-1.0), fed from matrix C value when available.

quality_trend: Vec<f64>

Rolling quality scores — is the agent getting better or worse?

error_history: Vec<String>

Record of errors/failures during this session.

signals: Vec<CognitiveSignal>

Signals emitted by lobes for the outer graph to read.

negative_knowledge: Vec<NegativeKnowledge>

Negative knowledge — things the agent learned NOT to do.

failure_records: Vec<FailureRecord>

Structured failure records for pattern recognition.

Trait Implementations

impl Clone for CognitiveState

fn clone(&self) -> CognitiveState

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CognitiveState

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

Formats the value using the given formatter.

impl Default for CognitiveState

fn default() -> CognitiveState

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for CognitiveState

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl NodeFn<CognitiveState> for LobeNode

fn call( &self, state: &CognitiveState, ctx: &NodeContext, ) -> NodeFuture<CognitiveStateUpdate>

Execute the node with a state snapshot and execution context.

fn name(&self) -> &str

Human-readable name for logging and debugging

impl Serialize for CognitiveState

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl State for CognitiveState

type Update = CognitiveStateUpdate

The companion partial-update struct (all fields Optional)

fn apply(&mut self, update: CognitiveStateUpdate)

Apply a partial update — each field uses its channel’s merge strategy