Skip to main content

Crate ai_agents_recovery

Crate ai_agents_recovery 

Source
Expand description

Error recovery system for AI Agents framework

Structs§

BackoffConfig
Backoff timing configuration used between retry attempts.
ByRoleFilter
ClassifiedError
ErrorRecoveryConfig
Top-level error recovery configuration for an agent. Controls retry, LLM failure handling, tool failure handling, and parse error handling.
KeepRecentFilter
LLMRecoveryConfig
LLM-specific recovery settings: what to do on total failure, rate limits, or context overflow.
ParsingRecoveryConfig
Recovery settings for malformed LLM output (invalid JSON, bad tool call format).
RecoveryManager
RetryConfig
Retry policy: how many times to retry and with what backoff strategy. Applied to both LLM calls and tool calls unless overridden per-tool.
SkipPatternFilter
ToolRecoveryConfig
Tool-level recovery: a default policy plus optional per-tool overrides.
ToolRetryConfig
Retry and failure policy for a single tool (or the default for all tools).

Enums§

BackoffType
Strategy for computing the wait duration between successive retry attempts.
ContextOverflowAction
Action to take when the accumulated message history exceeds max_context_tokens.
ErrorType
Classified error kinds used to decide whether a failure should be retried.
FilterConfig
Selects which messages are passed to the summarizer during context compression.
LLMFailureAction
Action to take when the primary LLM fails after all retries are exhausted.
ParseErrorAction
Action to take when the LLM response cannot be parsed as expected.
RateLimitAction
Action to take when the LLM returns a rate-limit error.
RecoveryError
ToolFailureAction
Action to take when a tool call fails after all retries are exhausted.

Traits§

IntoClassifiedError
MessageFilter