Struct LearningConfig 

pub struct LearningConfig {

    pub enabled: bool,
    pub auto_activate: bool,
    pub min_failures: u32,
    pub improve_threshold: f64,
    pub rollback_threshold: f64,
    pub min_evaluations: u32,
    pub max_versions: u32,
    pub cooldown_minutes: u64,
    pub correction_detection: bool,
    pub correction_confidence_threshold: f32,
    pub detector_mode: DetectorMode,
    pub judge_model: String,
    pub judge_provider: String,
    pub feedback_provider: ProviderName,
    pub judge_adaptive_low: f32,
    pub judge_adaptive_high: f32,
    pub judge_llm_timeout_secs: u64,
    pub correction_recall_limit: u32,
    pub correction_min_similarity: f32,
    pub auto_promote_min_uses: u32,
    pub auto_promote_threshold: f64,
    pub auto_demote_min_uses: u32,
    pub auto_demote_threshold: f64,
    pub cross_session_rollout: bool,
    pub min_sessions_before_promote: u32,
    pub min_sessions_before_demote: u32,
    pub max_auto_sections: u32,
    pub domain_success_gate: bool,
    pub arise_enabled: bool,
    pub arise_min_tool_calls: u32,
    pub arise_trace_provider: ProviderName,
    pub stem_enabled: bool,
    pub stem_min_occurrences: u32,
    pub stem_min_success_rate: f64,
    pub stem_provider: ProviderName,
    pub stem_retention_days: u32,
    pub stem_pattern_window_days: u32,
    pub erl_enabled: bool,
    pub erl_extract_provider: ProviderName,
    pub erl_max_heuristics_per_skill: u32,
    pub erl_dedup_threshold: f32,
    pub erl_min_confidence: f64,
    pub d2skill_enabled: bool,
    pub d2skill_max_corrections: u32,
    pub d2skill_provider: ProviderName,
    pub trace_extraction_enabled: bool,
    pub trace_extraction_provider: ProviderName,
    pub trace_extraction_embedding_provider: ProviderName,
    pub trace_extraction_max_turns: u32,
    pub trace_extraction_max_sessions_queued: usize,
    pub trace_extraction_max_input_bytes: usize,
    pub skill_merge_enabled: bool,
    pub skill_merge_provider: ProviderName,
    pub merge_threshold: f32,
    pub dedup_threshold: f32,
    pub heuristic_promotion_enabled: bool,
    pub heuristic_promotion_provider: ProviderName,
    pub heuristic_promotion_threshold: u32,
    pub heuristic_promotion_interval_hours: u64,
}

Self-learning and skill evolution configuration, nested under [skills.learning] in TOML.

When enabled = true, Zeph tracks skill performance and can automatically improve or roll back skill definitions based on usage outcomes (ARISE, STEM, D2Skill pipelines).

Example (TOML)

[skills.learning]
enabled = true
auto_activate = false
min_failures = 3

Fields

enabled: bool

Enable self-learning pipelines. Default: false.

auto_activate: bool

Automatically activate improved skill versions without user confirmation. Default: false.

min_failures: u32

improve_threshold: f64

rollback_threshold: f64

min_evaluations: u32

max_versions: u32

cooldown_minutes: u64

correction_detection: bool

correction_confidence_threshold: f32

detector_mode: DetectorMode

Detector strategy: “regex” (default) or “judge”.

judge_model: String

Named provider from [[llm.providers]] for the judge detector (legacy field, prefer judge_provider). Empty = use primary provider.

judge_provider: String

Named provider from [[llm.providers]] for the judge detector (detector_mode = "judge").

When set, overrides the model-level fallback: the named provider is resolved and used instead of the primary provider. Empty = use primary provider (same as leaving unset).

feedback_provider: ProviderName

Provider name from [[llm.providers]] for detector_mode = "model" (LlmClassifier).

Empty = use the primary provider. Named but not found in registry = log warning, degrade to regex-only. Never fails startup.

judge_adaptive_low: f32

Regex confidence below this value is treated as “not a correction” — judge not invoked.

judge_adaptive_high: f32

Regex confidence at or above this value is accepted without judge confirmation.

judge_llm_timeout_secs: u64

Maximum seconds to wait for the judge LLM to respond before timing out. Applies to detector_mode = "judge" only.

correction_recall_limit: u32

correction_min_similarity: f32

auto_promote_min_uses: u32

auto_promote_threshold: f64

auto_demote_min_uses: u32

auto_demote_threshold: f64

cross_session_rollout: bool

When true, auto-promote and auto-demote decisions require the skill to have been used across at least min_sessions_before_promote (for promotion) or min_sessions_before_demote (for demotion) distinct conversation sessions. Prevents trust transitions from a single long session.

min_sessions_before_promote: u32

Minimum number of distinct conversation_id values in skill_outcomes before auto-promotion is eligible. Only checked when cross_session_rollout = true.

min_sessions_before_demote: u32

Minimum distinct sessions before auto-demotion when cross_session_rollout = true.

Default 1 (demotion can happen after a single bad session by default). Separate from min_sessions_before_promote because demotion should be fast (low threshold) while promotion benefits from conservative validation (higher threshold).

max_auto_sections: u32

Maximum number of top-level content sections (markdown H2 headers) allowed in auto-generated skill bodies. Bodies exceeding this limit are rejected by validate_body_sections().

domain_success_gate: bool

When true, auto-generated skill versions must pass a domain-conditioned evaluation before promotion. If the improved body drifts from the original skill’s domain, activation is skipped (the version is still saved for manual review).

arise_enabled: bool

Enable ARISE trace-based skill improvement (disabled by default).

arise_min_tool_calls: u32

Minimum tool calls in a turn to trigger ARISE trace improvement.

arise_trace_provider: ProviderName

Provider name from [[llm.providers]] for ARISE trace summarization. Empty = fall back to primary provider.

stem_enabled: bool

Enable STEM automatic tool pattern detection and skill generation (disabled by default).

stem_min_occurrences: u32

Minimum occurrences of a tool sequence before generating a skill candidate.

stem_min_success_rate: f64

Minimum success rate of the pattern before generating a skill candidate.

stem_provider: ProviderName

Provider name from [[llm.providers]] for STEM skill generation. Empty = fall back to primary provider.

stem_retention_days: u32

Days to retain rows in skill_usage_log before pruning.

stem_pattern_window_days: u32

Window in days for pattern detection queries (limits scan cost on large tables).

erl_enabled: bool

Enable ERL post-task heuristic extraction (disabled by default).

erl_extract_provider: ProviderName

Provider name from [[llm.providers]] for ERL heuristic extraction. Empty = fall back to primary provider.

erl_max_heuristics_per_skill: u32

Maximum heuristics prepended per skill at match time.

erl_dedup_threshold: f32

Text similarity threshold (Jaccard) for heuristic deduplication. When exact text match exceeds this, increment use_count instead of inserting.

erl_min_confidence: f64

Minimum confidence to include a heuristic at match time.

d2skill_enabled: bool

Enable D2Skill step-level error correction (disabled by default).

Requires arise_enabled = true to populate corrections from ARISE traces. If d2skill_enabled = true and arise_enabled = false, existing corrections are still applied but no new ones are generated via ARISE.

d2skill_max_corrections: u32

Maximum corrections to inject per failure event.

d2skill_provider: ProviderName

Provider name from [[llm.providers]] for correction extraction from ARISE traces. Empty = fall back to primary provider.

trace_extraction_enabled: bool

Enable background skill extraction from completed conversation traces. Default: false.

trace_extraction_provider: ProviderName

Provider name from [[llm.providers]] for trace extraction LLM calls. Empty = fall back to the primary provider.

trace_extraction_embedding_provider: ProviderName

Provider name from [[llm.providers]] for embedding calls during trace extraction. Must reference a provider that supports embed(). Empty = fall back to the primary provider.

trace_extraction_max_turns: u32

Maximum user messages to include per extraction session. Default: 200.

trace_extraction_max_sessions_queued: usize

Maximum concurrent background extraction tasks before dropping oldest. Default: 10.

trace_extraction_max_input_bytes: usize

Maximum total bytes of user messages to send to the extraction LLM. Default: 131072 (128 KB).

skill_merge_enabled: bool

Enable the Merge branch in the Add/Merge/Discard decision flow. Default: true.

When false, candidates in the merge zone (merge_threshold <= sim < dedup_threshold) are Discarded instead of merged.

skill_merge_provider: ProviderName

Provider name from [[llm.providers]] for LLM merge calls. Empty = fall back to the primary provider.

merge_threshold: f32

Minimum cosine similarity to trigger a merge with the nearest skill. Default: 0.75.

Must be strictly less than dedup_threshold (validated at startup).

dedup_threshold: f32

Minimum cosine similarity to discard a candidate as a near-exact duplicate. Default: 0.90.

Must be strictly greater than merge_threshold (validated at startup).

heuristic_promotion_enabled: bool

Enable periodic heuristic promotion from ERL to full skills. Default: false.

When true, a background task runs every heuristic_promotion_interval_hours hours and evaluates whether accumulated ERL heuristics are substantial enough for promotion.

heuristic_promotion_provider: ProviderName

Provider name from [[llm.providers]] for heuristic promotion LLM calls.

Use a quality provider — promotion is an offline, non-latency-sensitive analysis. Empty = fall back to the primary provider.

heuristic_promotion_threshold: u32

Minimum heuristic count per skill to trigger promotion evaluation. Default: 5.

Skills with fewer heuristics (above erl_min_confidence) are skipped.

heuristic_promotion_interval_hours: u64

Interval in hours between promotion evaluation runs. Default: 24.

Implementations

impl LearningConfig

pub fn validate(&self) -> Result<(), String>

Validate invariants that cannot be expressed through serde defaults alone.

Errors

Returns an error string if merge_threshold >= dedup_threshold.

Trait Implementations

impl Clone for LearningConfig

fn clone(&self) -> LearningConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LearningConfig

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

Formats the value using the given formatter.

impl Default for LearningConfig

fn default() -> LearningConfig

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LearningConfig

fn deserialize<__D>( __deserializer: __D, ) -> Result<LearningConfig, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LearningConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.