apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-17 15:25:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

made fixes based on PR comments

Browse source
This commit is contained in:
Salman Paracha 2026-01-06 14:04:54 -08:00
parent 7d517ace77
commit c1d56684df
3 changed files with 626 additions and 198 deletions
Download patch file Download diff file Expand all files Collapse all files

4
crates/brightstaff/src/handlers/utils.rs
View file

@ -11,7 +11,7 @@ use tokio_stream::StreamExt;
use tracing::warn;
// Import tracing constants and signals
use crate::signals::{InteractionQuality, SignalAnalyzer, FLAG_MARKER};
use crate::signals::{InteractionQuality, SignalAnalyzer, TextBasedSignalAnalyzer, FLAG_MARKER};
use crate::tracing::{error, llm, signals as signal_constants};
use hermesllm::apis::openai::Message;
@ -145,7 +145,7 @@ impl StreamProcessor for ObservableStreamProcessor {
// Analyze signals if messages are available and add to span attributes
if let Some(ref messages) = self.messages {
let analyzer = SignalAnalyzer::new();
let analyzer = TextBasedSignalAnalyzer::new();
let report = analyzer.analyze(messages);
// Add overall quality

818
crates/brightstaff/src/signals/analyzer.rs
View file

File diff suppressed because it is too large Load diff

2
docs/source/concepts/signals.rst
View file

@ -4,7 +4,7 @@
Signals™
========
Agentic Signals are behavioral quality indicators that act as early warning signs of agent performance—highlighting both brilliant successes and **severe failures**. These signals are computed directly from conversation traces without requiring manual labeling or domain expertise, making them practical for production observability at scale.
Agentic Signals are behavioral and executions quality indicators that act as early warning signs of agent performance—highlighting both brilliant successes and **severe failures**. These signals are computed directly from conversation traces without requiring manual labeling or domain expertise, making them practical for production observability at scale.
The Problem: Knowing What's "Good"
==================================