perf(runtime): Hermes Phase 1-3 — prompt caching + parallel tools + smart retry

Phase 1: Anthropic prompt caching
- Add cache_control ephemeral on system prompt blocks
- Track cache_creation/cache_read tokens in CompletionResponse + StreamChunk

Phase 2A: Parallel tool execution
- Add ToolConcurrency enum (ReadOnly/Exclusive/Interactive)
- JoinSet + Semaphore(3) for bounded parallel tool calls
- 7 tools annotated with correct concurrency level
- AtomicU32 for lock-free failure tracking in ToolErrorMiddleware

Phase 2B: Tool output pruning
- prune_tool_outputs() trims old ToolResult > 2000 chars to 500 chars
- Integrated into CompactionMiddleware before token estimation

Phase 3: Error classification + smart retry
- LlmErrorKind + ClassifiedLlmError for structured error mapping
- RetryDriver decorator with jittered exponential backoff
- Kernel wraps all LLM calls with RetryDriver
- CONTEXT_OVERFLOW recovery triggers emergency compaction in loop_runner
This commit is contained in:
iven
2026-04-24 08:39:56 +08:00
parent 6d6673bf5b
commit 9060935401
25 changed files with 672 additions and 129 deletions

View File

@@ -117,7 +117,9 @@ impl Kernel {
}
}
use zclaw_runtime::{AgentLoop, tool::builtin::PathValidator};
use std::sync::Arc;
use zclaw_runtime::{AgentLoop, LlmDriver, tool::builtin::PathValidator};
use zclaw_runtime::driver::{RetryDriver, RetryConfig};
use super::Kernel;
use super::super::MessageResponse;
@@ -161,9 +163,12 @@ impl Kernel {
let subagent_enabled = chat_mode.as_ref().and_then(|m| m.subagent_enabled).unwrap_or(false);
let tools = self.create_tool_registry(subagent_enabled);
self.skill_executor.set_tool_registry(tools.clone());
let driver: Arc<dyn LlmDriver> = Arc::new(
RetryDriver::new(self.driver.clone(), RetryConfig::default())
);
let mut loop_runner = AgentLoop::new(
*agent_id,
self.driver.clone(),
driver,
tools,
self.memory.clone(),
)
@@ -275,9 +280,12 @@ impl Kernel {
let subagent_enabled = chat_mode.as_ref().and_then(|m| m.subagent_enabled).unwrap_or(false);
let tools = self.create_tool_registry(subagent_enabled);
self.skill_executor.set_tool_registry(tools.clone());
let driver: Arc<dyn LlmDriver> = Arc::new(
RetryDriver::new(self.driver.clone(), RetryConfig::default())
);
let mut loop_runner = AgentLoop::new(
*agent_id,
self.driver.clone(),
driver,
tools,
self.memory.clone(),
)