feat: Add benchmarking harness for agent evaluation

Introduces ironclaw-bench, a Rust-native benchmarking crate that drives the
real agent loop headlessly. Supports standard benchmarks (GAIA, Tau-bench,
SWE-bench Pro) and custom JSONL task sets with parallel execution, resume
support, and incremental JSONL output.

Key components:
- BenchChannel: headless Channel impl with auto-approval and response capture
- InstrumentedLlm: LlmProvider wrapper recording per-call token/cost metrics
- BenchRunner: task orchestration with parallel execution and JSONL resume
- Scoring utilities: exact match, contains, regex (all with normalization)
- CLI: run, results, compare, list subcommands via clap
- Four suite adapters: custom, gaia, tau_bench, swe_bench

Also fixes a pre-existing missing SseEvent::ToolResult match arm in the web
gateway and adds FinishReason to the LLM module's public re-exports.

Co-Authored-By: Claude Opus 4.6 <[email protected]>

src/channels/web/types.rs

@@ -314,6 +314,7 @@ impl WsServerMessage {
             SseEvent::Thinking { .. } => "thinking",
             SseEvent::ToolStarted { .. } => "tool_started",
             SseEvent::ToolCompleted { .. } => "tool_completed",
+            SseEvent::ToolResult { .. } => "tool_result",
             SseEvent::StreamChunk { .. } => "stream_chunk",
             SseEvent::Status { .. } => "status",
             SseEvent::ApprovalNeeded { .. } => "approval_needed",

src/llm/mod.rs

@@ -13,7 +13,7 @@ pub mod session;
 pub use nearai::{ModelInfo, NearAiProvider};
 pub use nearai_chat::NearAiChatProvider;
 pub use provider::{
-    ChatMessage, CompletionRequest, CompletionResponse, LlmProvider, Role, ToolCall,
+    ChatMessage, CompletionRequest, CompletionResponse, FinishReason, LlmProvider, Role, ToolCall,
     ToolCompletionRequest, ToolCompletionResponse, ToolDefinition, ToolResult,
 };
 pub use reasoning::{ActionPlan, Reasoning, ReasoningContext, RespondResult, ToolSelection};